DESC:FIELD OF THE INVENTION
[01] The present invention relates to information technology and more particularly relates to a system and method thereof for assessing individual’s and organizational operational efficiencies and productivity across several parameters within a manufacturing organization and across a consolidated convergent ecosystem of Humans and Machines.
BACKGROUND OF THE INVENTION
[02] The performance measurement system in some manner or the other may be used by and for top management control or continuous shop-floor improvement. It may be compared against internal targets or external benchmarks. No matter what the objective of the system or use of the performance information, a complete performance measurement system especially in the small and medium organization definitely needs to be comprehensive, driven by data and insights generated through that data and cover the most critical performance dimensions of the organisation. It is not obvious how firms should measure their manufacturing performances and some critical business objectives linking the manufacturing value chain. Various approaches, most of them with a large number of measures on different hierarchical levels, exist discretely and mostly are operated in silos.
[03] US 20130073344 discloses a method for optimizing productivity and performance of a workforce acquiring data point set relating to said workforce, measuring and comparing the benchmark data point set against previously compiled data points from within a usefully comparable, like workforces within a like workplaces and timeframes and utilizing differences and similarities between the benchmark data point set and the comparable data point set to produce simulation models which identify and direct specific improvements to be made to increase the productivity and performance of the workforce.
[04] US 20160154402 discloses a production performance management device and a production performance management method thereof are provided. The processor of the device runs the production performance management program. The production performance management program defines a main objective, a plurality of measurement indices, a plurality of factors, a custom mapping function between the main objective and the measurement indices and a plurality of specific mapping functions between the measurement indices and the factors, and uses the custom mapping function and the specific mapping functions to decide a factor value of each of the factors from the production data to make a main objective value of the main objective meet a main constraint.
[05] Many of such the measures used are considered obsolete and inconsistent for various reasons. The manufacturing company regardless of being a discrete manufacturing or continuous process manufacturing industry faces critical challenges that does not only revolve around the acquiring or generating real-time machine or process related data, but also building an intelligence framework while generating the data so that the data and insights makes sense and help the organizational management as the business decision support and hence create overall organizational impact. In order to generate such business insights, the managers, supervisors, operators or even leaders spend hours together in order to manually collate and decipher the information (from multiple sources) which can be represented in management decision support dashboard. The human and the machine exert a close control over each other within the ecosystem and also on the material utilization as well as methods of production therein. The point of control occurs at this very convergence point, which is most often a control and display of the data which more often than not are originated through discrete sources and with a lot of manual interventions which subsequently result in the misrepresentation of the data and is flawed or results in topical decision making which not always rectifies the root cause of the problem area but provides a temporary relief and seldom yield any productivity / efficiency improvements. The second set of challenges comes through the accountability of the data generation and owning up the implications of the generated data, since the assembly line is distributed, hence the accountability of the data across the assembly line gets distributed and as a result management struggles to link the data and make the business decisions based on that. The chief problems with current methodologies in Manufacturing Process Intelligence (MPI) Expert Systems is that data received from Operational Technologies (OT) is not easy to integrate with the data from Information Technology (IT). Moreover, the sources of MPI are too diffused across or within an organization.
[06] With respect to the Four Factors (4M) of Production (namely Man, Machine, Material and Method), getting the relevant data needs collaboration between different teams, which often takes time, or the data is later found to be incomplete inaccurate and insufficient for the purpose. The data on machine efficiency might also be relatively harder to acquire due to multiple issues. But even if the data is acquired by mitigating all the issues through manual or semiautomated manner it may not be totally reliable since its collated manually, unless the people or systems capturing the underlying data are themselves very reliable. Hence there shall always be an element of doubt trust factor of the collated data or, these are presented as dashboards, which may be interpreted differently by the different people viewing them, and there is no single unambiguous course of action that can be taken due to the general lack of consensus between the different teams involved. The data of method (or process) efficiency is largely discovered as a post-mortem activity on rejected units or through audit reports. During a crisis, when a quick decision needs to be made, a lot of time is lost leading to escalation of the failure or downtime. Second, this is a very person-dependent process, and can fail when the necessary experts are not immediately available. Third, these decisions which are taken in a hurry could be faulty at times, which can further compound the issue, and consequently the financial impact of the failure or downtime. Currently, there is no all encompassing technological intervention / methodology / approach through an integrated or expert system that integrates the inefficiencies across the 4M to give a composite 4M Efficiency Index (4MEI), provide the Impact of each inefficiency in each of the 4M’s on the overall manufacturing value chain, prioritize inefficiencies by Impact from the most severe to the least severe, and provide specific prescriptive to-do action lists to manage and optimize each such inefficiencies or anomalies exists therein. The real-time visibility of everyday issues is missing, and by the time such information is collected, enormous harm has been done. All the 4M’s are not covered. Lastly, the lack of predictive tools leads to down-time, inefficient asset and people utilization, deviated cycle times and uncontrolled production deviations hence and end up resulting in cost escalations. Ultimately this leads to user frustration and aggravation, and these systems may fall into disuse. The third set of challenges comes from the absence of a holistic technology system that consolidates the parameters of production and studies them as an interconnected entities and then prescribes the actions for improvement which are derived on the bases real-time as well as historic data sets and predicts the possibility of an anomaly while prescribing the corrective action to avoid or rectify it along with.
[07] To overcome these severe deficiencies, there is a clear need for a Real-time closed loop Artificial Intelligence-based Expert System that self-integrates Operation technologies (OT) and Information technology (IT), as well as data from the 4M(namely Man, Machine, Material and Method) to not just capture the data, run the analytics, detect the inefficiencies, prioritize the inefficiencies based on financial impact, provide actionable insights, but also indicate the actual steps to be taken to rectify the inefficiency.
[08] Accordingly, there exists a need to provide a system and method that can overcome the drawbacks of prior art techniques. Hence, there is a need for a system and method thereof that generates the data that makes sense and help the organizational management as the business decision support and hence create overall organizational impact. Further, the system and method thereof shall be capable of providing enhanced data, critical insights and continuous improvement information for assessing individual’s and organizational operational efficiencies and productivity across several parameters. Further, the system and method thereof shall be useable, scalable and independent of new technology platforms, uses minimum resources that is easy and cost effectively maintained and is portable and can be deployed anywhere in very little time. Proposed invention overcomes these lacunae by proposing a unique system and methodology implemented thereof to assess individual’s and organizational operational efficiencies and productivity to create overall organizational impact through the Artificial & Augmented Intelligence orchestrated through Human Machine Convergence platform ecosystem, as detailed hereinafter.

BRIEF DESCRIPTION OF THE DRAWINGS
[09] The invention is illustrated in the figures of the accompanying drawings, which are meant to be exemplary and not limiting, in which like references are intended to refer to like or corresponding things. The objects and advantages of the present invention will become apparent when the disclosure is read in conjunction with the following figures, wherein
Figure 1 illustrates a complete solution framework of the system in accordance to one of the embodiments of the present invention.
Figure 2 illustrates the assessment/evaluation framework model implemented and executed by the processor of the application module of the cloud communication server according to an embodiment of the present invention.
Figure 3 illustrates the backend logic of the present invention system for the alignment of the performance evaluation parameters and their subsequent assignment to the employees and organizational functions according to one of the embodiments of the present invention.
Figure 4 illustrates an indicative list of a plurality of roles of employees for some critical organization functions according to one of the embodiments of the present invention.
Figure 5 illustrates block diagram of a standard model selection process carried out by the conceptual layer module of the system of the present invention according to one of the embodiments of the present invention.
Figure 6 illustrates a methodical approach for the inference engine embedded at the conceptual layer module according to one of the embodiments of the present invention.
Figure 7 illustrates a table having listing of an indicative possible aggregation of parametric factors of evaluation / assessment or performance outcome indicators in accordance with one of the embodiments of the present invention.
Figure 8 illustrates a typical functional illustration of the computation framework of the system according to one of the embodiments of the present invention.
Figure 9 illustrates the process execution flow of the logical layer module of the system in accordance with one of the embodiments of the present invention.
Figure 10 illustrates classification of performance indicators or the individual or organizational evaluation parameters.
Figure 11 illustrates some illustrative reports and representation.
Figure 12 illustrates categorization of various factors that impacts at the machine as well as on the organizational levels across several organizational impact specifications.
Figure 13 illustrates an exemplary breakdown analysis.
[010] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present invention. Similarly, it will be appreciated that any flowcharts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[011] The present invention relates to information technology and management and more particularly relates to a system and method thereof for assessing individual’s and organizational operational efficiencies and productivity across several parameters for better organizational management.
[012] Throughout this application, with respect to all reasonable derivatives of such terms, and unless otherwise specified (and/or unless the particular context clearly dictates otherwise), each usage of:
“a” or “an” is meant to read as “at least one.” and “the” is meant to be read as “the at least one.”
References in the specification to “one embodiment” or “an embodiment” mean that a particular feature, structure, characteristic, or function described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment.
[013] The systems and methods described herein are explained using examples with specific details for better understanding. However, the disclosed embodiments can be worked on by a person skilled in the art without the use of these specific details. Further, the embodiments may be easily implemented in organizational performance management structures. Embodiments may also be implemented as one or more applications performed by stand alone or embedded systems. Hereinafter, embodiments will be described in detail. For clarity of the description, known constructions and functions will be omitted.
[014] Parts of the description may be presented in terms of operations performed by at least one electrical / electronic circuit, a computer system, using terms such as data, state, link, fault, packet, and the like, consistent with the manner commonly employed by those skilled in the art to convey the substance of their work to others skilled in the art. The term computer system includes general purpose as well as special purpose data processing machines, special purpose electronic circuit boards having computational capabilities such as but not limited to single circuit boards switches, and the like, that are standalone, adjunct or embedded. For instance, some embodiments may be implemented by a processing system that executes program instructions so as to cause the processing system to perform operations involved in one or more of the methods described herein. Moreover, such processing system and/or data storage may be implemented using a single computer system or may be distributed across multiple computer systems (e.g., servers) that are communicatively linked through a network to allow the computer systems to operate in a coordinated manner.
[015] The present invention is related to enhancing the organizational efficiencies, productivity and amplifying the intelligence on the shopfloor by assessing machines, individuals, and organizational efficiency through the data acquired from the respective manufacturing environments and machines/equipment and subsequently evaluating the parametric performance by converging the operational efficiency with workforce efficiency of the human machine ecosystem on the shopfloor to enhance physical as well as cognitive performance. One of the primary object of the invention and envisaged in the solution ecosystem detailed out in this document is also to enable an Augmented Intelligence layer through the data and factor evaluation and obtaining deep insights from them so as to create human-cantered model of both machine intelligence and people intelligence, working in a harmonious environment to heighten physical and cognitive performance like, productivity, efficiency and decision making and prescribe the best possible actions to be taken on the basis of deep learnings derived from these data and business insights.
[016] The system and method thereof of present invention is configured to monitor and study machines/equipment as we all as the workforce / Human Resource / People/ Machine operators/ Man’s performance aligned with such equipment and machines (Permanent as well as contractual workforces) efficiencies, costs, quality in an industry, in accordance with the processes and methodologies and their respective desired outputs and evaluate the workforce performance and productivity in an organization to improvise organizational efficiency. The system and method thereof of present invention is also configured to enhance the workforce efficiency and productivity in an organization and streamline the vendor/ contractual workforce productivities while ensuring performance based and fair practices compliance. The system and method thereof of the present invention is directed to automatically aggregate information and rules, apply this information and rules to input parameters captured to detect areas of greatest inefficiency, and to provide action steps to be taken to resolve the issues across all the 4Ms based on the application of the information and rules to the input parameters (data) that are captured through various sources.
[017] The system and the method of the present invention provides (1) the knowledge as to what operational inefficiencies should be tackled, why, when and in which order, including optimization and further troubleshooting (if required) (2) Action Steps, and (3) Expert System based accurate solutions using combinations of numerous logical flows, optimizing techniques, and proprietary models thus reducing the time as well as costs. The inputted business rules and parametric ranges, as well as the solutions, are added to a repository for later use by the user or other users, thus increasing the knowledge base of the Human Machine convergence system platform and method thereof (Humac) of the present invention. The invention retains the impact for each inefficiency arising out of any of the 4M factors, and allows the user to track impact of delaying corrective action through the Action Steps. The system and method thereof of the present invention pulls in past data, the past data that is previously acquired, captured or entered. Further, it accesses current data that is acquired, captured or entered for each specific machine on a given production line in each of the manufacturing facilities worldwide where the said invention system is installed. Further, it reads information such as the parametric anomaly criteria (previously entered, or computed real-time by machine learning algorithms). The system and method thereof of the present invention applies a combination of meta data, data, meta rules, logical rules, mathematical rules, mathematical equations, models, algorithms, subroutines and a trainable neural network to detect 4M inefficiencies at different locations, and to compute the negative impact. It further prioritizes and decides the sequence in which issues and inefficiencies detected should be handled based on the severity of impact and computes and defines in Real-Time the Actions that should be taken to solve each of the inefficiencies at each manufacturing location.
[018] According to one of the embodiments of the present invention, the user is asked to input information and / or data with regard to the business rules, as well the parametric ranges for determining anomalies and failure points, as well as the data sources to connect to, many of the rules initially can be entered into the repository by experts, creating an initial knowledge base. If this is not possible, the data from different sources on the shop floor can be collected for a few months, based on which the Humac system can learn and formulate some basic business rules. The inputted rules and parameters which are applied to the data, and the resultant solutions can be stored in an electronic repository for later use (either by the same user or now as part of the library of scenarios) thus increasing the knowledge base.
[019] According to one of the embodiments of the present invention the system and method thereof comprises Machine Learning and Deep learning modules within the assessment/evaluation framework model with features allowing the system to learn and incorporate new inputs, parameters, rules, equations, and solutions into the knowledge base. Further, the system and method thereof also configured to make suggestions based on previously inputted and newly learned information to solve each of the inefficiencies at each human – machine convergence ecosystem on manufacturing Shopfloor.
[020] According to one of the embodiments of the present invention the system and method thereof is configured to perform the functions of data capture, data validation, data analysis and generation of insights. The data capture includes receiving data from almost any machine or data point having active data communication ability or can be induced with some enhancement, including analog signals, relays, mimics sensor data, parametric data from PLC or controllers (regardless of their make, communication protocols, or age of controllers), data from Scada systems, data from the Manufacturing Execution system,
[021] According to one of the embodiments of the present invention a system for assessing individuals/ organizational productivity efficiency and outcomes comprises a plurality of sensing devices, a data acquisition module/Universal Data adaption unit, at least one global data repository, at least one local data repository and a cloud communication server. The plurality of sensing devices spread across a factory/organisation environment include but not limited to proximity sensing devices, mechanical sensing devices, and electrical parameters sensing devices, and forms a proximity intelligence framework collecting periodic time stamping data essential for the subsequent productivity / efficiency evaluation and assessment of the man factor. The data acquisition module/Universal Data adaption unit includes at least one user management system module, a universal embedded controller / Edge Device module, at least one memory and at least one data transmission module. The at least one user management system module is configured to identify registered users, facilitate authentication and authorization of a registered user and registration of a new user, and providing access to the user account of the registered user. The universal embedded controller / Edge Device module is configured to collect parametric data from the plurality of sensors, machine and equipment in the factory, transform the data procured from the plurality of sensing devices into standard data structures across all types of equipment to enable consistent reporting and securely transmission to a cloud by means of an automated data transmission engine. The at least one memory is communicatively coupled to the Universal embedded controller module. The at least one data transmission module is comprising of at least one processor configured as single board computer-based EDGE gateway and a memory communicatively coupled to the EDGE gateway. The cloud communication server comprise of at least one application module comprising at least one processor configured to perform the functionality of the application module and at least one database module, at least one organization Structure module, at least one People process & Equipment performance and evaluation framework module, at least one memory communicatively coupled to the processor of the application module. The at least one application module configured for receiving input data from the data transmission module, and process the input data by an assessment / evaluation framework model embedded at the processor of the application module. The assessment/evaluation framework model includes a plurality of layer modules configured for evaluation / assessment of the realtime parameters, the layer modules includes at least one contextual layer module, at least one conceptual layer module, at least one logical layer module and at least one transformational layer module. The at least one contextual layer module is configured to conduct the contextual analysis on the data outlaying organization structure and alignment of the Machines, Equipment, People/ Operators / Humans, people hierarchies, and Material, Methods and processes assigned with the organization structure and production processes that has aggregation and consolidation at the cloud communication server /Edge Server. The at least one conceptual layer module is configured to receive input data from the contextual layer module and perform analytical function particularly, evaluation / assessments of individuals as well as factory/organization from the organizational, departmental, sectional and nodal perspective to detect anomalies in the data then derive Inferences through Inference Engine & Rule based sub module embedded therein. The at least one logical layer module is configured to receive input data from contextual layer module and conceptual layer and perform the performance evaluation of employee as well as organization’s performance and productivity across all the four parametric factors of evaluation (namely Man, Machine, Material and Methods) by analysing the data through a plurality of Machine Learning and Deep Learning models to achieve critical business insights. The at least one transformational layer module is configured to deliver comprehensive analysis across four key area including descriptive analysis, diagnostic analysis, predictive analysis and prescriptive analysis of the parameters from the logical layer module.
[022] The figure 1 illustrates a complete solution framework of the system in accordance to one of the embodiments of the present invention. In an implementation, according to an embodiment of the present invention the factory/organisation environment as depicted in the fig. 1, is consisting of several individual components/elements from where the primary data acquisition can be performed (each individual element can be termed as source data node) such as Machines / equipment’s, Human Resources, PLC’s, SCADA systems, Actuators, RTU’s, Control Panels, Electrical panels as well as individual and isolated sensors installed for the purpose of data acquisition of a particular parametric data, and all the other Information technology applications such as ERP , MES etc. In the context of the present invention this entire ecosystem is considered as Factory Environment.
[023] According to one of the embodiments of the present invention the universal embedded controller module / Edge Device comprises a processing Unit, an opto-Isolated Power Supply, an electrical interface for request-response protocol, a storage medium for operational data and local data storage, and a data communication tracking module. The Universal embedded controller module / Edge Device is designed and configured to collect data including but not limited to digital, analog , coils and holding registers, alarms, messages, warning data and signals from PLC, sensor data, data from Scada systems, data from the Manufacturing Execution system, perform data acquisition from the plurality of sensors, Machine / equipment PLC’s , Controllers and all source data nodes. . The Universal embedded controller module / Edge Device is designed and configured to provide Plug-and-Play universal data collection from programmable logic controllers (PLC) supporting open protocols as well as proprietary connectors, communicate over standard communication protocol as well as embed within itself at least one protocol convertor that can convert the input data received into the standard format, communicate with client controllers/PLCs of different protocols by converting those protocols into its own standard protocol using built-in protocol converters, incorporate an automated data transformational engine configured to transform machine data into standard data structures across all the types of equipment and transmit to the central Gateway that can further push the input data to the cloud server, alternatively push the data to the cloud server from the machine directly. The Universal embedded controller module / Edge Device is designed and configured to connect to the plurality of sensing devices and to the equipment, configure and manage said connectivity remotely through a web interface, perform as an EDGE gateway server capable of functioning as the consolidation and single source data exchange node that synchronizes local data collected from a plurality of machines and all the source data nodes, and with a global database that resides in the cloud infrastructure. Further, the Universal embedded controller module / Edge Device is designed and configured to perform remote management of the distributed network of the Embedded controllers and Proximity intelligence tags and parametric sensors, perform Authentication and Reauthentication functionalities and authorizing the certificate with the help of the Public / Private key logic while transmitting the data, and execute the functionality of running self-registration and authentication service for the Universal embedded controller module during the initial data transmission, thus establishing a trusted device network.
[024] According to one of the embodiments of the present invention the user management system module of the data acquisition module/Universal Data adaption unit configured to perform user registration for a new user, identification of a registered user, user authentication and authorization, and providing access to the user account of the respective user.
[025] The universal embedded controller module/EDGE device comprises a processing Unit, an opto-Isolated Power Supply, an electrical interface for request-response protocol, a storage medium for operational data and local data storage, and a data communication tracking module.
[026] The data validation and pre-processing of the acquired data from the physical ecosystem includes data cleaning, sorting, indexing. The data analysis includes sorting, creating sub-sets, grouping, converting the data into intelligent trends based on parameters, aggregation frequency, running averages and so on. The generation of insights includes formatting the digested data into visual formats for use in reports or dashboards. Machine learning algorithms are then run on the digested data to generate insights and action lists.
[027] According to one of the embodiments of the present invention use of machine learning, deep learning and some of the artificial intelligence algorithms and models empowers a user by selecting the desired inefficiency category (one of the 4M), arranging the inefficiencies in a logical sequence based on severity of the negative impact of the inefficiency, thus using the system and method thereof to guide and influence the path of action of the user.
[028] In one of the implementations, according to an embodiment of the present invention, the plurality of sensors, Machine / equipment PLC’s , Controllers and all source data nodes from where the data acquisition is done through the universal embedded controller module are connected in order to acquire data. This acquired data is collected at a pre-defined time intervals (milliseconds or Seconds) across the machine specific parameters which are pre-configured in the universal embedded controller module. In an embodiment, the data transfer between the plurality of sensing devices and the memory unit is wired or wireless and is monitored by the data communication tracking module.
[029] According to an embodiment some typical example parametric data items includes but not limited to the data collected from various Custom Sensor Values or from PLCs such as parametric data, production data, Set and Actual values of the parameters, Machine Status, Modes, Alarms, Overrides, Load, Speeds, Feeds, PMC parameters, Diagnostics, People Proximity through RF/BLE/UWB Tags and so on. These parameters shall also be dependent and varying on case-to-case basis.
[030] In one of the implementations, according to an embodiment of the present invention the uniqueness / inventions comes from these parameters which have been identified for each type and sub type of the machine and then subsequently pre-configured. There are plurality of parameters for example more than 2000 parameters that the invention system has across the machine types, this approach of pre-configured parameters eliminates the possibility of the insufficient data acquisition and all the possible inaccuracies that can arise out of manual or human dependant data acquisition. The acquired parametric data is then subjected to data segregation mechanism at the cloud server where the data coming from the data sources is updated / store in the telemetry tables which are dedicated tables for all the incoming time series parametric data from the machines. The segregation of the data is done on the basis of Parametric clusters, Parametric clusters can be defined as the aggregation of the parameter which are formulated based on the impact they create on human-machine and subsequently on the end result specifications such as – outcome, Time, losses etc. The parametric clusters includes but not limited to losses specifications including time loss, Production / yield losses, productivity losses, Efficiency Losses, Financial Losses, Resource Losses, Outcome specifications including Capacity Utilization, Defects, Performance, Quality, Production to wage ratio, Through Put, Volume, Operational Specifications including Efficiency - OEE/OOE/ OPMS / Workforce Efficiency, Cost, Productivity, Cycle Time, Plan / Schedule adherence, Utilization - Asset / Resources, Consumption Specifications including Energy Consumption, Fuel consumption - Gasses, Oil etc., Resources Consumption – Consumables, Material Consumptions, Time Specifications including Availability, Idle Time, Breakdown time, Maintenance Time, Set up time, Process / Method Specifications including Adherence to SOP, Adherence to Quality Procedures, Machine / Equipment set up and assembly, Deviation from the Equipment benchmark, Machine / Equipment performance deviations, Functioning Specifications including MTBF / MTTR / MTTF, Defect Density, Asset Life / Turnover, Utilization Rate, and Human / Operators including workforce utilization, Workforce Efficiencies and productivities, Skill to outcome impact, Skill to Yield deviations, Skill to losses, Workforce planning.
[031] In one of the implementation the proximity sensing devices include BLE/RFID/UHF/UWB sensing devices in the wearable form such as but not limited to wearable tags for the Human Resources / employees while the receiving terminals are tagged to the machines, embodied in the Universal embedded controller module. The proximity intelligence framework through the mesh network functions in such a way that the employee’s indoor movement, their proximity with the machines with periodic time stamping data is captured by the receiving terminals embodied in the Universal embedded controller module. Thus, the employee’s proximity around the machines which executing a particular task is obtained, this periodic data input provides inputs to the subsequent productivity / efficiency evaluation and assessment of the Man factor of the invention framework. The peripheral proximity range is configurable to meet the requirement
[032] According to an embodiment some typical example parametric data items include the data collected from various Custom Sensor Values or from PLCs such as but not limited to parametric data, production data, Set and Actual values of the parameters, Machine Status, Modes, Alarms, Overrides, Load, Speeds, Feeds, PMC parameters, Diagnostics, People Proximity through RF / BLE / UWB Tags and so on. These parameters shall also be dependent on case-to-case basis.
[033] In one of the implementations according to an embodiment of present invention the Universal embedded controller module configured as EDGE Gateway server along with functioning as the consolidation & Single source data exchange node to synchronize Local data collected from several machines and all the source data nodes, and with the Global Database that reside in the cloud infrastructure, it also performs several critical functionalities. The Universal embedded controller module configured as EDGE Gateway is configured to perform remote management of the distributed network of the Embedded controllers as well as Proximity intelligence tags and parametric sensors. The Universal embedded controller module configured as EDGE Gateway is configured to extend cloud/ Application intelligence to edge devices (Embedded Controllers & Proximity tags) and enable real-time decisions at the edge. The EDGE Gateway performs real time decisions through the embedded Nodal/EDGE data processing framework that executes the nodal rules logic configured for onsite action to generate action triggers executing the prescribed tasks. The Universal embedded controller module configured as EDGE Gateway also performs certificate and security management, device policies, compliance and rules management and configuration management for the edge devices within the network.
[034] In one of the implementations according to an embodiment of present invention, the processor of the application module of the cloud communication server is configured for data processing. The data fetched by the plurality of sensing devices in then stored in the Telemetry data module of the cloud database server memory and are queued for the further processing through ETL data link from data lake to data warehouse. This step of data processing at the application module of the cloud communication server is preceded with multiple stages, data acquisition, data security, data transfer, data pre-processing and data transmission. While transferring the data to the database sub module, the data becomes structured as well as encrypted. The data structures are encrypted as per machine, section, department, organization, & operator with the unique employee / operator ID etc. and then converted to the cumulative datasets so as to enable the subsequent action that can be taken on the same.
[035] This data is structured in the cloud database in the form of Feature tables, and data marts, and is further used for the measurement of the people performance, machine / equipment performance parameters, productivity parameters, condition-based monitoring parameters as per the assessment and evaluation methodology on a set aggregation frequency (example – each hour, each 4 hours, each 8 hours, end of the day, event triggered, anomaly triggered etc) where these respective algorithms at the backend carry out such automated evaluation and keep storing the outcomes for the visualization and subsequent evaluations.
[036] In one of the implementations according to an embodiment of present invention the processor of the application module of the cloud communication server is configured for the data representation and the subsequent process evaluation to represent the current state as well as deviation in the people, processes, plant/ organizational, productivity and performance data and processes across the entire value chain of the manufacturing process – Man, Machine, Material and Methods.
[037] According to one of the embodiments of the present invention, in the event of any deviation or anomalies in the production processes or any Machine / Equipment functionality from the normal state, action triggers are automatically initiated to the relevant stakeholders for the action to be taken on any abnormalities like machine breakdown, production loss, temperature variations or any other such parameter which may directly or indirectly hazardus and amy cause any safety threat to either machine, human or overall ecosystem and which requires immediate corrective actions or further analysis by the relevant stakeholders.
[038] The application module is configured to perform assessment, execute evaluation methodologies and perform factor-based analysis. The present invention provides a framework for context management with variable types of context parameters / factors and use of advanced techniques like machine learning implemented at the application module of the cloud communication server for an automatic preconfigured parametric factor-based assessment for manufacturing value chain elements – Man, Machine, Material & Methods more specifically human machine convergent ecosystem
[039] In an implementation according to one of the embodiments of the present invention the processor of the application module of the cloud communication server is configured to implement and execute a assessment/evaluation framework model and method thereof.
[040] Figure 2 illustrates the assessment/evaluation framework model embedded /implemented and executed by the processor of the application module of the cloud communication server according to an embodiment of the present invention where the Human – Machine Convergence system of the present invention conducts the integrated value chain assessment on the basis the novel parametric evaluation model. The assessment/evaluation framework model comprises at least one contextual layer module, at least one conceptual layer module, at least one logical (business insights) layer module, and at least one transformational layer module.
[041] In an implementation according to one of the embodiments of the present invention the contextual layer module of the assessment/evaluation framework model embedded at the processor of the application module constituting the assessment / evaluation framework model of the system of the present invention is configured to conduct the contextual analysis on the data, which has undergone through aggregation and consolidation at the cloud communication server /Edge Server and then subsequently has been transmitted to the cloud database. There are a plurality of types of datasets and preferably three types of datasets which typically gets considered for such analytical exercise such as raw data, transactional data and operational data across all the four elements (Man, Machine, Materials & Methods) of the parametric factor evaluation. The input data collected from various data sources which includes Universal embedded controller modules along with sensing devices (if any) collects and transmit the real-time machine related data. Depending on the machines and equipment’s the data acquisition nodes can vary. The data extraction from the machines and equipment ranges from various fixed as well as variable parameters. The invention system has more than 2000 such unique parameters that are already per-configured in the system and at the time of installation depending on the type of machine and industry relevant parameters are automatically assigned and the data acquisition against these pre-configured parameters is initiated. This eliminates the human intervention in deciding the parameters and errors in configuring such input parameters which further eliminates the possibility of wrong data collection.
[042] According to one of the embodiments the input data details for the Human Resources or Man or Machine operators, are collected with the help of the Proximity wearable tags which can have multiple form factors such as – card type, watch type, band type, tags which can be put on the safety helmets (essentially establishing data Transmitters and Receivers network). The plurality of data sets collected from various perspectives of Operator proximity intelligence perspectives includes but not limited to attendance records, proximity intelligence data availability on the machine, indoor proximity and indoor movement (Across multiple machines, sections and departments), work schedule and shift details along with other operator vitals such as heights across XYZ axis, ambient temperatures etc. and all the data sets which can help the system to analyse the data and provide the insights & triggers on the basis of performance and workplace safety aspects of the machine operators.
[043] In an implementation, according to one of the embodiments the details pertaining to the material parameters are collected typically from the integration of the system of the present invention with the MES/ERP or in some cases where the MES/ ERP is absent then in such scenario the material details can be captured as a manual input from the user interface screens of the application by the authorized designated user role.
[044] According to an embodiment of present invention in order to build in the context awareness in the system, and in order to perform the business / operational assessment on the collected data so as to achieve accurate data segmenting, clustering and parameter positioning can be performed on the basis of internal, external and conditional factors of influence which can impact the business outcome, establishing the organizational and people structures and providing the context of organization ecosystem becomes inevitable. To facilitate this context awareness the application module of the system comprises of at least one organization structure module, and at least one people process & equipment performance and evaluation framework module. These modules determine the organizational hierarchies and reporting relationships, people hierarchies and reporting relationships, along with defining the organization level, functional / departmental level and Individual level evaluation parameters and KRA’s and forms the foundation blocks of the evaluation framework.
[045] In an implementation according to one of the embodiments of the present invention an organization structure module configured to provide a digital representation of the organization structure and its subsequent interconnection and reporting relationships. This is very critical since the machines and equipment’s will subsequently be tagged to the relevant department or section and the data gathering from all such machines tagged to section / department is cascaded up to form the evaluation representation for the department.
[046] From the people/human resources perspective, the organizational alignment plays a very critical role, as the position that an employee holds is directly derived from the organization structure, also the evaluation parameters, job descriptions and knowledge and skill parameters are directly assigned to the position that an employee holds, hence all the position evaluation parameters are in direct correlation with the organization evaluation and objective achievements.
[047] In an implementation of the present invention, the organization structure mapping and the human resource mapping once is done then the sensing devices are assigned to the respective machines and the embedded controllers or tags or sensing devices ids are subsequently mapped to the sections / sub-sections in the organization structure so as to establish the relationships of Machine / equipment’s to department / organization node which will be subsequently correlated with the position and the employee occupying that position.
[048] The availability parameters play an important role in the overall operational efficiencies and operational excellence as it defines the amount of time workforce / Machine operators actually spends on the machines and its relationship with the overall production throughput and subsequently machines performance while the operator was operating the machine and this human - machine convergent performance ecosystems can have direct impact on seven major areas of organizational objectives– Losses objectives, production /Outcomes objectives, functional objectives of the machines, time objectives, Process / method objectives, consumption objectives & Operational objectives. The need of the present invention system establishes this essentiality to ensure continuous evaluation around the organization objective through the human -machine convergent ecosystems evaluation.
[049] According to one of the embodiments of the present invention the third critical area of the evaluation framework in the system of the present invention Human Machine Convergence is the People process & Equipment performance and evaluation framework. Typically, the people evaluation and the equipment evaluations would be driving the overall operational effectiveness and the workforce efficiencies. The People process & Equipment performance and evaluation framework module is configured to provide backend logic for the alignment of the performance evaluation parameters and their subsequent assignment to the employees and organizational functions by means of which the productivity and performance matrix
[050] Figure 3 illustrates the backend logic of the present invention system for the alignment of the performance evaluation parameters and their subsequent assignment to the employees and organizational functions by means of which the productivity and performance matrix are defined at People process & Equipment performance and evaluation framework module.
[051] Each employee while being entered in the system is tagged with a job role, which is depending on the respective functions within an organization. As an exemplary illustration some standard role definitions for the manufacturing / process industry are set up by the system of the present invention which can be tagged to the employees. The Figure 4 illustrates an indicative list of a plurality of roles of such employees for some critical organization functions.
[052] While updating the employees in the system each employee gets assigned with the job description for the job role they are going to perform. The Job Description is then automatically assigned to the employee / operator the job role accountabilities and the performance parameters to be evaluated against those accountabilities along with the training and periodicity of the training required for the optimum output delivery as expected by the assigned job role. The invention system has more than 60 such job roles definitions and role descriptions that are per-configured in the system and they are pertaining to specific machines and manufacturing environments and the logic to assign these job role definitions and descriptions depending on the machine type is also pre-defined hence eliminating manual interventions and evaluation error which can arise out of wrong assignment
[053] Along with the job description the performance Parameters (KRA/KPI) and evaluation parameters alignment of the job occupant is done. This evaluation is typically done on the basis of the job role definition and the associated evaluation parameters that are or should be evaluated for the said job role.
[054] To create the impact and scale of the invention, the undermining imperative value where the novelty to the application lies is of the context in which the data is being analysed in the first stage of the evaluation / assessment framework to assess the efficiencies / productivity of individual Operators / Machines Organizations, and consolidated convergent ecosystem encompassing all of these and their individual as well as collective impact on the organizational outcomes and objectives. This context aware first layer of data analysis configured and executed at the contextual layer module helps the invention systems to establish foundations for the subsequent analysis of the data which can create substantial impact on the business out-comes includes but not limited to enabling environment - for the integrated value chain analysis, actors, factors and inputs - for the formation of the contextual rule base, interactions – which relates the parametric factors of assessment together in the given context (how, what, why, when etc.), outputs / outcomes- relates to not only the tangible outputs in terms of numbers but also results in contextual insights and dimensions in which the parametric factors correlate and creates and impact on each other. These outputs / outcomes are subsequently gets analyzed in the conceptual and logical layer of the invention systems to result into transformational actions.
[055] In an implementation according to one of the embodiments of the present invention the conceptual layer module in the assessment / evaluation framework model embedded at the processor of the application module constituting the assessment / evaluation framework model of the system of the present invention is configured to carry out deeper study of the data and the inputs from the contextual layer module analysis (which are outputs of the contextual layer module). The primary responsibility that is carried out by this conceptual layer module is to put the contextual outcomes in the form of the universal concepts which are acceptable to all the workgroups and are valid in the organizational ecosystem and which subsequently works as the foundation or the building block of the parametric evaluation / assessment of the individual / organization.
[056] Figure 5 illustrates block diagram of a Standard model selection process carried out by the conceptual layer module of the system of the present invention according to one of the embodiments of the present invention.
[057] Figure 6 illustrates a methodical approach for the inference engine embedded at the conceptual layer module according to one of the embodiments of the present invention.
[058] The conceptual layer module of the system of the present invention is configured to develop and select a model in the system through structured validation / characterisation steps of the model selection. The structured validation / characterisation steps of the model selection for developing and selecting model embedded at and executed by the conceptual layer module includes but not limited to identification of the parameter characteristics and dimension, determining dimensional consistency, determining and setting of validation and comparison set points with the best case or ideal scenarios, determination of the causality and recurrence frequency and factor based validations.
[059] In an implementation, according to one of the embodiments of the present invention the application module of the cloud communication server includes an assessment / evaluation framework model based on Logic controller, embedded through conceptual layer module.
[060] In an implementation, according to one of the embodiments of the present invention the conceptual layer module of the present invention is configured to detect any anomalies, if present and derive Inferences through Inference Engine & Rule Base established for the logical data analysis embedded at the conceptual layer module. The inference engine configured to perform selection of inference data sets, synthesis, measurement and interpretation.
[061] The inference engine embedded at the conceptual layer module is constituted based on the hierarchical fuzzy logic which is predominantly based on the context as established in the contextual layer module which outlays organization structure and alignment of the Machines, Equipment, People, and Material assigned with the organization structure. The People hierarchies also plays an important role hence the alignment of people with the job tasks, job roles, skills / knowledge and performance attributes also plays a critical role in the designing of the Inference Engine.
[062] The inference engine embedded at the conceptual layer module is configured to perform various analytical function by running a plurality of algorithms and the validation criteria’s that are defined in the Rule base sub module embedded at the conceptual layer module, in order to identify the anomalies & subsequently for establishing inferences which would result in the action. The inference engine is configured to perform evaluation / assessments of individuals as well as organization from the organizational, departmental, sectional and nodal perspective, suggest the set of indexes to subsequently provide the perspective for the value chain impact of these indexes. The inference engine is configured to solve some issues pertaining to the scales and benchmarks / baseline standards that are established prior to the invention system implementation; highlighting the deviation in the assessment framework that existed prior to the invention system implementation
[063] The rule base sub module for the logic controller incorporates Neural Network to evaluate/ assess the dynamic parametric factors of evaluation across Man, Machine, Materials and Methods that keeps a self-regulating characteristic based on the learnings from the data and thus the data tends to keep on continuously creating deeper impact on the business outcomes.
[064] The assessment performed by the system and method thereof of the present invention is deeply depends on a plurality of factors, preferably on two main factors such as but not limited to firstly organization, structural as well as alignment of the people with the organization, jobs, skills and job tasks and secondly on the key performance indicators which are the parametric evaluation factors against which the entire ecosystem is evaluated / assessed. To ensure accuracy of the results and outcome consistency every time for each of the user of the invention system, these critical aspects are preconfigured, and logic have been institutionalized in the invention system to self-regulate these internal alignments.
[065] Figure 7 illustrates a table having listing of but not limited to an indicative possible aggregation of parametric factors of evaluation / assessment or performance outcome indicators in accordance with one of the embodiments of the present invention.
[066] The performance outcome of any factor- based evaluation in the evaluation model has characteristics including but not limited to non-linear nature of the data, evaluation approach and outcomes, time varying nature of the manufacturing process ecosystems, and large number of unpredictable disturbances / factors impacting the definite outcomes.
[067] This makes the assessment and representing the business outcomes and impact in absolute terms, difficult. Thus, such rule-based analytical systems with customised proprietary algorithms of the invention system lead to very useful analysis and evaluation of several problems which does not result in absolute outcomes but are represented as degree of the outcome and its comparison with the baseline / benchmark standards. Many different alternative descriptions can be generated for each degree of deviation / performance anomalies across – Man, Machine, Material and Methods and subsequently in the output logic prescriptive action boards can represent the action that need to be taken, so as to take corrective actions if the degree of deviation is in the negative side of the benchmark standards and thus performance / productivity can be enhanced.
[068] The Logic controller of the system of the present invention is configured to define a function f:X Y with the intention to show that f(x) is the correct answer given the input x. On the base of inputs of performance factors and rule base criteria an approximation of such an ideal function f:X Y is mentioned in fuzzy approaches to control results / outcome indicators. This approximation is achieved by a system of fuzzy IF-THEN rules like: If x is A THEN y is B, where A and B are labels for fuzzy subsets. Human system designer use such a rule as a logical implication A(x) B(y) in our human unformalized logic. This usage leads to good results in a huge number of practical applications where the productivity assessment / evaluation is to be done at the Human-Machine Convergence where the correlation of each performance factors of either one impact not only other’s performance factors but also leads to a large aggregated impact on the overall business outcomes.
[069] In the system of the present invention depending on the nature of the parametric performance factor such rule bases are created dynamically with the help of Self organizing Neural Network which subsequently results in self-regulating assessment / evaluation framework.
[070] The Figure 8 illustrates a typical functional illustration of the computation framework of the system in accordance with one of the embodiments of the present invention. As illustrated in Figure 8 the logic controller used in the combination with the Self organizing Neural Network when used to evaluate/ assess the dynamic parametric factors of evaluation across Man, Machine, Materials & Methods, it presents tremendous opportunities to not only gain the deep hidden business insights but also enables the system of the present invention to keep self-regulating itself based on the learnings from the data and data trends to keep on continuously creating deeper impact on the business outcomes.
[071] The output logic of a logic controller is configured to provide outcomes and action triggers. The output logic of the logic controller serves as the output of the conceptual layer module of the analytics as well where the parametric data evaluation performed by the Logic controller of the system of the present invention represents the outcomes in the form of –
a. Parametric factor evaluation is performed of the input data and its comparison with the benchmarked / baseline standards outcomes as per the organizational as well as manufacturing process requirements
b. Performance evaluation judgement is provided in from the perspective of Degree of deviations from the baseline standard outcomes
c. Aggregated performance factor evaluations and outcome judgements across – Man, Machine, Material and Methods at each Machine, section, department, function, plant and organization level, enabling the decision process through a cross machine (COE)/departmental / functional/ organizational comparatives can be represented and corrective actions based of such findings can be prescribed
d. The Output logic of the logic controller provides normalized data and action triggers resulting into Data & Outcome Measurability, Data & Outcome Accessibility, Data & Outcome Sustainability, Data & Outcome Actionability which subsequently feeds in as an input to the next layer of analysis that take place to generate the business insights in the Logical layer.
[072] In an implementation according to one of the embodiments of the present invention the Logical layer module of the assessment / evaluation framework model of the system of the present invention is configured to perform the performance evaluation of individual’s as well as organization’s performance and productivity across all the four parametric factors of evaluation (namely Man, Machine, Material and Methods)
[073] The Logical layer module of the assessment/evaluation framework model embedded at the processor of the application module constituting the assessment / evaluation framework model of the system of the present invention is configured to perform the performance evaluation of individual’s/employee’s as well as organization’s performance and productivity across all the four parametric factors of evaluation (namely Man, Machine, Material and Methods) concentrates on analysing the data through various Machine Learning and Deep Learning algorithms to achieve critical business insights. These business insights which were hidden earlier, can now be typically derived from understanding & analysing the organizational objectives and performance standards / baselines and the context of the evaluation which gets established in the first two layers of the analysis.
[074] The logical layer module of the present invention is configured to receive the input data from contextual layer module which is typically the real-time input data from the data sources or nodes from Machine as well as man through the hardware elements, as well as from the conceptual layer which are typically analysed data and inferences of the analysis which generally represents the parametric trends and identification of the anomalies derived after passing through the Rule base defined in the logic controller in the conceptual analytics layer.
[075] Figure 9 illustrates the process execution flow of the logical layer module of the system in accordance with one of the embodiments of the present invention. As illustrated in Figure 9 the logical layer module of the system is configured to receive data from various sources through contextual layer module and conceptual layer module. The logical layer module of the system is configured to perform data extraction through scaling and normalization of the data. The logical layer module of the system is configured to perform predictive modelling by formulation of modelling and predictive analysis. The logical layer module of the system is configured to generate business insights by arriving at conclusions and futuristic action. The logical layer module of the system is configured to generate predictive and prescriptive action triggers through predictive and prescriptive modelling leading to improvements.
[076] Data extraction and normalization of the input data is required to extract the required information from all the sources and eliminate loud / noise from the data through the normalization operations. This is done in order to get the accurate data so as to build accurate estimations and business insights on the basis of the input data. During the normalization process the data and values are scaled in provided range (which may differ organization to organization or process to process) and subsequently the extraneous elements are removed by performing correlation analysis, which helps in concluding the final decision.
[077] Predictive modelling is carried out on the normalised data. The predictive model often carries out regression techniques and associated algorithms. In the invention systems the predictive modelling uses pre-set / Pre-configured, self-learning algorithmic modules which forms the core of the analytics and the resultant outcomes in the form of action triggers.
[078] The predictive model in the invention system’s assessment framework for the productivity evaluation of the employees/individuals as well as the organization, is based on building model that is self-reliant, self- regulating, context aware and is capable of making predictions and prescribe / propose actions for elimination of the anomalies across the parameter factors of evaluations namely Man, Machine, Material and Methods. The Model is formulated on basis of the core principals the machine learning algorithms that continuously learn the data properties from the training data sets and the baseline process & equipment standards / benchmarks in order to identify the outliers and anomalies and subsequently make the predictions with the help of regression and pattern classifications.
[079] In the invention system since the nature of the parametric factors is dynamic and time-varying the classical regression models are enhanced by building the analysis of the relationships and interconnectivity as well as interdependence of the variables in order to suit such complex evaluation / assessment resulting into propritery models. For example the prediction of the machine anomalies would not only result in the machine breakdown and loss of the productive hours but it will also have an impact on the employee / Man productivity, and the machine anomaly could have its origins in the wrong methodology followed by the operator (Man) or it can also be due to inappropriate material use. If this example is observed, the prediction of an anomaly in the machine cannot just be seen in isolation but all the factors of productions Man, Machine Material and Methods have to be analysed in integration and the correlation of the data and its impact of all the factors requires a continuously self-regulating regression models.
[080] As against the regression models in the invention system, the pattern classification model continuously perform the task of labelling the observations and outcomes of the data analysis that is continuously carried out against the factors of production – Man, Machine Material and Methods, in such a manner that discrete labels and classes are assigned to the observation and outcomes of such pattern classification outcome based outcomes can be predicted. E.g. in continuation to the above example the pattern classification would result in the prediction such as – a particular machine anomaly would occur under a particular equipment conditions (temperature, humidity, vibrations, & So on) or Machine anomalies occurrence probability is high when the machine in operated by the operator who is in X% deviation from the skills, knowledge and experience level etc. The patter Classification establishes such correlational patterns and subsequently carry out prediction.
[081] In the invention system to limit the exorbitant scale of numerous variables and their cross linkages the predictive models are categorically pre-configured in the manner such that these models examines, visualise and results in the data and action triggers which has direct correlation as well as impact on the above principle and futuristic actions that help the organization to take conclusive and corrective actions in regards to the above three principles, while the rest of the data along with the analysis resides at the backend in the data tables and is utilised for historical trending, parametric cross linkage establishment, training the predictive model and for the self-learning algorithms in order to get the accurate prescriptive and predictive action triggers that leads to the improvements.
[082] The predictive modelling is one of the core modules in the assessment framework’s Logical Layer module in the invention system as showcased in the assessment framework and is based on the basic algorithmic streams of Machine learning such as - Supervised learning, Unsupervised learning , Reinforcement, and deep insights while the context of the way in which all of these algorithmic functionalities execute themselves is explained below.
[083] In an implementation of the present invention according to one of the embodiments, a plurality of supervised learning algorithms are embedded in the logical layer module which are based on the machine learning (ML) and Artificial Intelligence (AI) frameworks, and various preconfigured algorithms are incorporated within the application module, which determine a predictive model using the input dataset with known outcomes, the input- output pair is typically termed as labels from the perspective of the invention system. Some of the standard algorithms and models that are used in the invention system are – Linear regression, Random forests and Neural networks).
[084] In case of executing the Supervised learning model in the invention system to process the input data that is coming from the contextual layer module which is already processed through several robust analytical interventions and has been validated against the rule bases and the baseline standards in the fuzzy inference engine, results mainly in to two possible outcomes as –
a. The assessment outcome / result of a particular parametric assessment impacts the organizational value chain (Four factors of production- Man, Machine, Material & Methods),
b. The assessment outcome / result of a particular parametric assessment contributes to the future trend analysis of the data and does not directly impact the organizational value chain immediately.
[085] In the case where the outcome does not have immediate and direct impact on the organizational value chain (case b) is stored in the backend database and subsequently used for the model learning and regression as well as timeseries analysis.
[086] While in the situation where the assessment outcome / result of a particular parametric assessment has direct impact on the organizational value chain gets classified in the three primary categories, these categorical classification is done on the basis of the nature of impact of such outcomes on the organizational value chain created by the invention system. These primary classification categories are cost, value, & efficiency / productivity.
[087] In the context of the invention system – Human Machine Convergence (Humac) a sample of performance indicators or the individual or organizational evaluation parameters can be classified on the basis of the primary categories & as per business impact of such parameter, is as illustrated in the table of the Figure 10.
[088] The primary classification of the data inputs and their subsequent outcomes in the form of cost, efficiency and value enables the invention system to carry out standard algorithms on the data such as outcome classification model which help to predict the impact of the individual as well as organization performance parameters and subsequently arrive at an appropriate action decision. Another standard data evaluation algorithm that is preconfigured in the invention system is regression, which mainly concentrates on the estimation of the relationships between a dependant outcome indicator and its correlation with one of more variables. The regression algorithms in the invention system, which classifying th e outcome data and establishes the relationship between degree of impact of one outcome indicator on another and model the future relationship between them which subsequently fed as an input to the decision tree for arriving at an appropriate action decision. While in the situation where the assessment outcome / result of a particular parametric assessment has direct impact on the organizational value chain gets classified in the four primary categories such as but not limited to Action triggers, Information, Tasks, and Impact.
[089] The invention system takes these outcomes and through the purpose, built learning models and algorithms and performs classification of such data set so as to establish the relationship between the factors of evaluations collected from the – man, machine method & material (4M), historical trends data which has been continuously been collected and stored in the database, other input information data which is being fed by the machine operators and also collected from other external data sources. The relationship of these datapoints and evaluation factors are orchestrated in such a way that the data set forms Entropy index and information gains for each respective corresponding cross linking and impact validation formulates the decision tree. The Outcome classification decision tree help in not only identifying the anomalies and defective branch node in the entire relationship tree but also helps in identifying its impact on the other factors or other factors impact on the present anomaly. This cross linking mechanism helps the invention system to establish the first proof of anomaly trend and impact classification based on outcomes and investigative clauses which can further be subjected to the next levels of analysis.
[090] In an implementation according to one of the embodiments a plurality of unsupervised learning algorithms and models are embedded in the logical layer module which are based on the machine learning (ML) and Artificial Intelligence (AI) frameworks. The plurality of unsupervised learning algorithms and models as developed in the present invention enables establishing the groupings and interpretation of the model based on not only the input data acquired from 4M’s but also the outcome classification data and all the investigative data interpretations acquired through the previous stages.
[091] According to one of the embodiments of the present invention the nature of the data that is accumulated is not just humongous in volume but also very complex in nature hence in these circumstances unsupervised learning models such as identifying the nearest neighbouring impact parameters, anomaly detection through formulating neural networks of the cross impacting parameters between the Human – Machine ecosystems, or even to perform a singular value decomposition and subsequently performing a principle component analysis helps to carry out these complex and time varying analysis of the data.
[092] In the unsupervised learning model the continuous cross validation of the Human – Machine ecosystems is carried out which enables the invention system to determine what is the impact of any change in the human factor (internal, external or body vital) causing deviations in human performance on that of the performance of the machine or the outcome coming out of the machines and what is the time varying nature of all such correlations along with its impact on the overall organizational performance.
[093] In an implementation according to one of the embodiments a Reinforcement analysis layer module embedded in the logical layer module which are based on the machine learning (ML) and Artificial Intelligence (AI) frameworks establishes its uniqueness by creating a self-aware business insights layer through variety of algorithms and learning models across 4M parametric evaluation framework.
[094] The goal of context management in the invention systems is to design and implement a mechanism by which context information and accumulated data collected from multiple data sources can be updated and distributed for context-aware usage. Context management in the HuMaC (Invention system) is critical, because it indicates the importance and emphasize on the outcomes and findings, the assumptions to draw (or not) about what is being represented, and most importantly, it puts meaning into the data driven analysis that is being carried out on the huge accumulated data.
[095] In this Reinforcement analysis layer module, concept of Parametric Classification in a given / set Context developed and designed in a manner so as to logically group parameters, data and their individual as well as correlated outcomes using raw as well as computed or derived inferences and information.
[096] In the invention system the nature of the machine / Equipment level data that gets accumulated is primarily categorised in two areas – A. Machine specific parametric data & B. Machine Independent parametric data. The machine independent data points typically provide the results around the machine/ equipment functional as well as operational aspects including the losses in terms of the time and resources through breakdowns and other operational defects, while the machine specific parametric data provides the results around the core parameters of machine parameters which are different for different machines related to the core functional as well as operational parameters of the internal working of a machine.
[097] In order to arrive at the real time decision support mechanism and to establish the adaptive decision controls its inevitable for the invention system to constantly map, measure & align the results of the machine specific parameters and its deviations while simultaneously correlating with the machine independent parameters. These continuous parametric correlations observed by the machine learning algorithms recognises the deviations and detects any anomalies in the parametric behaviours of these anomalies and subsequently initiates the triggers to the stakeholders probing for the corrective action to be taken.
[098] All such anomalies and the incidences are observed over the period of time and scale and the factors impacting such anomalies to occur, in the invention system such detection algorithms are built in so as to identify the functional deviations and its impact on the overall organizational outcomes. Through these establishment of the recurrences of the deviations and anomalies in the machine / equipment and its correlation with the outcome or performance, the invention system can provide deep insights towards the impact of such deviations in the form of causes of losses to the organization such as – time loss, efficiency loss, productivity loss, losses caused by human mistakes, material loss etc.
[099] The invention system not only provides the call for corrective actions to the end user so as to fix the abnormalities in the operational deviation, but it also keeps the track of all the corrective actions taken by the user and realigns the backend algorithms to take effect of all such corrective actions, this establishes the human behaviour patterns and registers impact of such behaviours in the management dashboards along with the diverse factors and their correlational impact on the overall manufacturing value chain across 4M’s.
[0100] In an implementation according to one of the embodiments of the present invention the Transformational layer module of the assessment/evaluation framework model embedded at the processor of the application module constituting the assessment / evaluation framework model of the system of the present invention is configured to provide descriptive analysis including but not limited to historical data analysis, recurrence trends, trend based impact assessment, factor correlation impacting productivity/efficiency. The transformational layer module is configured to provide diagnostic analysis including anomaly/deviation reasoning, factors impacting the anomalies, business impact of the anomalies and deviations. The transformational layer module is configured to provide predictive analysis including preventive action against anomalies predictions, prevention of losses and elimination of efficiency leakages and predictive controls and measures. The transformational layer module is configured to provide prescriptive analysis including prescriptive action boards, action recommendations, continuous improvement, and real-time Man, Machine, Method enhancements.
[0101] According to one of the embodiments of the present invention the Transformation layer module converges all the findings from the previous layers and the Machine learning and Artificial Intelligence models produces – Descriptive, Diagnostic , Predictive and Prescriptive analysis dashboards for the users.
[0102] The Descriptive analysis, is more focused on the historical trends and data analysis from the data from the past which results in to indication of the recurring trends, and establishes the assessment of these impact over a period of time.
[0103] While the descriptive analysis does take several parameters in consideration, but it concentrates more on the organizational impact and root causes across organization, units, departments or even specific machines. While showcasing these outcome, the invention systems also constantly compares the outcome with the set standard benchmarks and best practices, hence continuously classifying the performance analysis so that the user instantaneously can get to know which areas are to be concentrated and drilled further down.
[0104] These analysis are also segregated over the time period in the periodic span like – Day, Week, Month and Year. Some of the areas concentrated by the descriptive analysis are – Productivity & Efficiency, Production, Losses & Workforce and some illustrative reports and representation are as showcased in Figure 11.
[0105] The Descriptive analytics also result in to the factor impacting the productivity & efficiency not only at the organization level but also at the machine level. Various factors that impacts at the machine as well as on the organizational levels are categorised across several organizational impact specifications as shown in Figure 12. Each of the parametric data from either the machine or operator (through the proximity tags) contributes in to either of the factors and indicated above and subsequently creates an impact on the organization through the areas as showcased in Figure 12.
[0106] The outcomes from the descriptive analytics layer further feeds into the next level of the deep dive to the diagnostic analysis levels where the Anomalies and deviations are further drilled down, to determine the root cause. An exemplary of breakdown analysis is showcased below where the machine / equipment breakdown is drilled down to the reason causing the breakdown and subsequently to analyse the number of instances for each specific reason for the breakdown and the impact that each such reason for the breakdown create an aggregate impact on the organization as whole as shown in Figure 13.
[0107] The primary focus of the diagnostic analytics layer is to identify the impact of the deviation and the anomalies on the organization, the machine learning models are trained on these factors creating the organization impact as by the time the diagnostic analysis is carried out on the data the garbage or missing pieces of the data is all filtered out and the outcome of the descriptive and diagnostic dataset contains only the information which is critical for the subsequent analysis is to be carried out.
[0108] In the Predictive analysis layer, now the machine learning algorithms models are well trained and are continuously fed with the continuous datasets from the previous analytics layer the models can result in to predictions towards the factors of impact as detailed out above, Predictive models make assumptions based on the current situation and past events to show the desired output, some of the typical exemplary prediction areas could be around
• Predicting the production yield and outcomes based on the equipment conditions and functioning
• Predicting the workforce outcomes based on the operator assignment to a specific machine or equipment or to a particular timeslot (shifts)
• Predicting workforce outcomes based on the skill and efficiency levels
• Predicting preventive actions to reduces the losses, inefficiencies, productivity loopholes
• Predicting the breakdown instances or possible asset utilization deviations
• Predicting the losses
[0109] The predictive analytics model used in the invention system is revised regularly to incorporate the changes in the underlying data. At the same time, most of these prediction models perform faster and complete their calculations in real-time to result in the actions to be taken by the user across the 4M’s to prevent the losses and deviation to minimise the impact.
[0110] Prescriptive analytics in the invention systems is less like a fortune teller but functions more as a doctor. Where it Instead of simply predicting what will happen, prescriptive analysis tweaks certain variables to achieve the best possible outcome, and then prescribes that course of action that should be taken by the users.
[0111] At the core of prescriptive analytics is the idea of optimization, which means every little factor has to be taken into account when building a prescriptive model. Supply chain, workforce costs, scheduling of workers, energy costs, potential machine failure–everything that could possibly be a factor is included in making a prescriptive call for action. While prescribing the call for action the invention system use multiple levels of complex event processing which involves combination of various machine learning algorithms and datasets from the evaluation factors and parameters which are processed together to carry out analysis on complex multidirectional time varying data.
[0112] The invention system also has multiple preconfigured recommendation algorithm engine / models in the prescriptive analytics layer which are designed to predict the positive or negative preference based on what the historic impact has been and what action was taken by the users. The invention system also uses heuristics or alternative methods of problem solving that can approximate the outcomes and the impact of the outcomes in terms of not only the deviation but also in terms of the money value of impact of the prescribed action if not taken by the user. This helps the user to set the respective priorities towards the actions to be taken.
[0113] In an implementation according to one of the embodiments a method for assessing individuals/ organizational productivity efficiency and outcomes, the method comprises configuring the universal embedded controller module as EDGE Gateway server along with functioning as the consolidation & Single source data exchange node to synchronize Local data collected from several machines and all the source data nodes, and with the Global Database that reside in the cloud infrastructure, and perform several critical functionalities. The method includes step of generating initial knowledge base by receiving, information and / or data with regard to the business rules, as well the parametric ranges for determining anomalies and failure points, as well as the data sources to connect to or collecting the data from different sources on the shop floor, learning and formulating some basic business rules by the Humac system based on the collected data from different sources. The method includes step of obtaining continuous human proximity with periodic time stamping data around the machines to capture their proximity within the physical ecosystem. The method includes step of applying the formulated or inputted rules and parameters to the data and performing, data validation and pre-processing of the acquired data from the physical ecosystem by data cleaning, sorting, and indexing. The method includes step of storing and updating at the cloud server the data coming from the data sources in the telemetry tables dedicated for all the incoming time series parametric data from the physical ecosystem and structuring and encrypting the data in the form of Feature tables, and data marts upon transferring the data to the cloud database module. The method includes step of performing data analysis by sorting, creating sub-sets, grouping, converting the data into intelligent trends based on parameters, aggregation frequency, and running averages. The method includes step of segregating by the data segregation mechanism the data on the basis of Parametric clusters formulated by aggregation of the parameters based on the impact they create on human-machine and subsequently on the end result specifications including outcome, Time, losses. The method includes step of conducting, by the contextual layer module a contextual analysis on the data which has undergone through aggregation and consolidation by building context awareness and performing the business / operational assessment on the collected data by performing segmenting, clustering and parameter positioning on the basis of internal, external and conditional factors of influence. The method includes step of putting, the contextual outcomes by the conceptual layer module in the form of the universal concepts which are acceptable to all the workgroups and are valid in the organizational ecosystem for the parametric evaluation / assessment of the individual / organization. The method includes step of performing, by the logical layer module the performance evaluation of individual’s/ employee’s as well as organization’s performance and productivity across all the four parametric factors of evaluation (namely Man, Machine, Material and Methods) to realise critical business insights. Further, the method includes step of converging, by the Transformation layer module all the findings from the previous layers/models and the Machine learning and Artificial Intelligence models to produce Descriptive, Diagnostic, Predictive and Prescriptive analysis dashboards for the users.
[0114] In an implementation according to one of the embodiments of the present invention the method step of conducting by the contextual layer module a contextual analysis includes providing by an organization structure module a digital representation of the organization structure and its subsequent interconnection and reporting relationships, Tagging the machines and equipment’s to the relevant department or section and cascading up the data gathering from all such machines tagged to section / department to form the evaluation representation for the department, Assigning directly the position that an employee holds all the position evaluation parameters such as the evaluation parameters, job descriptions and knowledge and skill parameters, Assigning the sensing devices to the respective machines and subsequently mapping the embedded controllers or tags or sensing devices ids to the sections / sub-sections in the organization structure, defining and establishing availability parameters to determine human - machine convergent performance, Defining the productivity and performance matrix by performing alignment of the performance evaluation parameters and their subsequent assignment to the employees and organizational functions, tagging with a job role to each employee being entered in the system and assigning with the job description for the job role they are going to perform and performing alignment of the performance Parameters (KRA/KPI) and evaluation parameters of the job occupant.
[0115] In an implementation according to one of the embodiments of the present invention the method step of putting, the contextual outcomes by the conceptual layer module in the form of the universal concepts for the parametric evaluation / assessment of the individual / organization includes executing structured validation / characterisation steps of the model selection for developing and selecting model embedded at and executed by the conceptual layer module, detecting anomalies, if present and deriving inferences through Inference Engine & Rule Base, providing, by a output logic of a logic controller outcomes and action triggers.
[0116] In an implementation according to one of the embodiments of the present invention the method step of executing structured validation / characterisation steps of the model selection for developing and selecting model includes identification of the parameter characteristics and dimension, determining dimensional consistency, determining and setting of validation and comparison set points with the best case or ideal scenarios, determining the causality and recurrence frequency, and performing factor based validations.
[0117] In an implementation according to one of the embodiments of the present invention the method step of detecting anomalies, if present and deriving inferences through Inference Engine & Rule Base includes performing, by inference engine various analytical function by running a plurality of algorithms and the validation criteria’s defined in the Rule base, performing, by inference engine from the organizational, departmental, sectional and nodal perspective, evaluation / assessments of individuals as well as organizations, suggesting, by the inference engine set of indexes to subsequently provide the perspective for the value chain impact of these indexes, solving, by the inference engine issues pertaining to the scales and benchmarks / baseline standards highlighting the deviation in the assessment framework that existed, and creating dynamically rule bases using self-organizing neural networks depending on the nature of the parametric performance factor.
[0118] In an implementation according to one of the embodiments of the present invention the method step of providing, by a output logic of a logic controller outcomes and action triggers includes performing parametric factor evaluation of the input data and its comparison with the benchmarked / baseline standards outcomes as per the organizational as well as manufacturing process requirements, providing performance evaluation judgement in from the perspective of Degree of deviations from the baseline standard outcomes, aggregating performance factor evaluations and outcome judgements across – Man, Machine, Material and Methods at each Machine, section, department, function, plant and organization level, prescribing corrective actions based on the findings represented by enabling the decision process through a cross machine (COE)/departmental / functional/ organizational comparatives, and providing, by the output logic of the logic controller normalized data and action triggers resulting into Data & Outcome Measurability, Data & Outcome Accessibility, Data & Outcome Sustainability, Data & Outcome Actionability.
[0119] In an implementation according to one of the embodiments of the present invention the method step of performing, by the logical layer module the performance evaluation includes receiving, by the logical layer module the input data from contextual layer module that includes the real-time input data from the data sources or nodes from Machine as well as man through the hardware elements, and from the conceptual layer the analysed data and inferences of the analysis representing the parametric trends and identification of the anomalies, performing data extraction through scaling and normalization of the data, performing predictive modelling by formulation of modelling and predictive analysis, generating business insights by arriving at conclusions and futuristic actions, generating predictive and prescriptive action triggers through predictive and prescriptive modelling.
[0120] In an implementation according to one of the embodiments of the present invention the method step of performing, by the logical layer module data extraction through scaling and normalization of the data includes extracting the required information from all the sources and eliminating loud / noise from the data through the normalization operations wherein the data and values are scaled in provided range and subsequently the extraneous elements are removed by performing correlation analysis.
[0121] In an implementation according to one of the embodiments of the present invention the method step of performing predictive modelling by formulation of modelling and predictive analysis includes building model that is self-reliant, self- regulating, context aware and capable of making predictions and prescribe / propose actions for elimination of the anomalies across the parameter factors of evaluations namely Man, Machine, Material and Methods, enhancing the classical regression models by building the analysis of the relationships and interconnectivity as well as interdependence of the variables in order to suit complex evaluation / assessment, performing continuously by the pattern classification model the task of labelling the observations and outcomes of the data analysis continuously carried out against the factors of production – Man, Machine Material and Methods, executing, the supervised learning model to process the input data that is coming from the contextual layer module, establishing, by the unsupervised learning models the groupings and interpretation of the model based on the input data acquired from 4M’s, the outcome classification data, and all the investigative data interpretations acquired through the previous stages, developing and designing by the Reinforcement analysis layer module in a given / set Context concept of Parametric Classification and logically grouping parameters, data and their individual as well as correlated outcomes using raw as well as computed or derived inferences and information.
[0122] In an implementation according to one of the embodiments of the present invention the method step of executing, the supervised learning model to process the input data that is coming from the contextual layer module includes the assessment outcome / result of a particular parametric assessment into the assessment outcome / result of a particular parametric assessment impacting the organizational value chain (Four factors of production- Man, Machine, Material & Methods) and the assessment outcome / result of a particular parametric assessment contributing to the future trend analysis of the data and does not directly impact the organizational value chain immediately, classifying, into the categories cost, value, & efficiency / productivity the assessment outcome/result of a particular parametric assessment having direct impact on the organizational value chain, predicting, by the outcome classification model the impact of the individual as well as organization performance parameters and subsequently arriving at an appropriate action decision, classifying by the regression the outcome data and establishing the relationship between degree of impact of one outcome indicator on another and modelling the future relationship between them and subsequently feeding it as an input to the decision tree for arriving at an appropriate action decision categorized into Action triggers, Information, Tasks, and Impact, building learning models and algorithms and performing classification of data set to establish the relationship between the factors of evaluations collected from the – man, machine method & material (4M), historical trends data which has been continuously been collected and stored in the database, other input information data which is being fed by the machine operators and also collected from other external data sources, identifying, by the Outcome classification decision tree the anomalies and defective branch node in the entire relationship tree and its impact on the other factors or other factors impact on the present anomaly, and establishing by the cross linking mechanism the first proof of anomaly trend and impact classification based on outcomes and investigative clauses.
[0123] In an implementation according to one of the embodiments of the present invention the method step of converging, by the Transformation layer module all the findings from the previous layers/models and the Machine learning and Artificial Intelligence models to produce Descriptive, Diagnostic , Predictive and Prescriptive analysis dashboards for the users includes providing descriptive analysis including historical data analysis, recurrence trends, trend based impact assessment, factor correlation impacting productivity/efficiency, providing diagnostic analysis including anomaly/deviation reasoning, factors impacting the anomalies, business impact of the anomalies and deviations, providing predictive analysis including preventive action against anomalies predictions, prevention of losses and elimination of efficiency leakages and predictive controls and measures, and providing prescriptive analysis including prescriptive action boards, action recommendations, continuous improvement, and real-time Man, Machine, Method enhancements.
[0124] The foregoing descriptions of specific embodiments of the present invention have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present invention to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the present invention and its practical application, and to thereby enable others skilled in the art to best utilize the present invention and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but such omissions and substitutions are intended to cover the application or implementation without departing from the scope of the present invention
,CLAIMS:We claim:
1. A method for assessing individuals/ organizational productivity efficiency and outcomes, the method comprising steps of:
configuring the Universal embedded controller module as EDGE Gateway server along with functioning as the consolidation & Single source data exchange node to synchronize Local data collected from several machines and all the source data nodes, and with the Global Database that reside in the cloud infrastructure, and perform several critical functionalities;
generating initial knowledge base by receiving, information and / or data with regard to the business rules, as well the parametric ranges for determining anomalies and failure points, as well as the data sources to connect to or collecting the data from different sources on the shop floor, learning and formulating some basic business rules by the Humac system based on the collected data from different sources;
obtaining continuous human proximity with periodic time stamping data around the machines to capture their proximity within the physical ecosystem;
applying the formulated or inputted rules and parameters to the data and performing, data validation and pre-processing of the acquired data from the physical ecosystem by data cleaning, sorting, and indexing;
storing and updating at the cloud server the data coming from the data sources in the telemetry tables dedicated for all the incoming time series parametric data from the physical ecosystem and structuring and encrypting the data in the form of Feature tables, and data marts upon transferring the data to the cloud database module;
performing data analysis by sorting, creating sub-sets, grouping, converting the data into intelligent trends based on parameters, aggregation frequency, and running averages;
segregating by the data segregation mechanism the data on the basis of Parametric clusters formulated by aggregation of the parameters based on the impact they create on human-machine and subsequently on the end result specifications including outcome, Time, losses;
conducting, by the contextual layer module a contextual analysis on the data which has undergone through aggregation and consolidation by building context awareness and performing the business / operational assessment on the collected data by performing segmenting, clustering and parameter positioning on the basis of internal, external and conditional factors of influence;
putting, the contextual outcomes by the conceptual layer module in the form of the universal concepts which are acceptable to all the workgroups and are valid in the organizational ecosystem for the parametric evaluation / assessment of the individual / organization;
performing, by the logical layer module the performance evaluation of individual’s/ employee’s as well as organization’s performance and productivity across all the four parametric factors of evaluation (namely Man, Machine, Material and Methods) to realise critical business insights; and
converging, by the Transformation layer module all the findings from the previous layers/models and the Machine learning and Artificial Intelligence models to produce Descriptive, Diagnostic , Predictive and Prescriptive analysis dashboards for the users.

2. The method as claimed in claim 1, wherein the step of conducting by the contextual layer module a contextual analysis includes steps of:
providing by an organization structure module a digital representation of the organization structure and its subsequent interconnection and reporting relationships;
Tagging the machines and equipment’s to the relevant department or section and cascading up the data gathering from all such machines tagged to section / department to form the evaluation representation for the department;
Assigning directly the position that an employee holds all the position evaluation parameters such as the evaluation parameters, job descriptions and knowledge and skill parameters;
Assigning the sensing devices to the respective machines and subsequently mapping the embedded controllers or tags or sensing devices ids to the sections / sub-sections in the organization structure;
defining and establishing availability parameters to determine human - machine convergent performance;
Defining the productivity and performance matrix by performing alignment of the performance evaluation parameters and their subsequent assignment to the employees and organizational functions;
tagging with a job role to each employee being entered in the system and assigning with the job description for the job role they are going to perform; and
performing alignment of the performance Parameters (KRA/KPI) and evaluation parameters of the job occupant.

3. The method as claimed in claim 1, wherein the step of putting, the contextual outcomes by the conceptual layer module in the form of the universal concepts for the parametric evaluation / assessment of the individual / organization includes steps of:
executing structured validation / characterisation steps of the model selection for developing and selecting model embedded at and executed by the conceptual layer module;
detecting anomalies, if present and deriving inferences through Inference Engine & Rule Base; and
providing, by a output logic of a logic controller outcomes and action triggers.

4. The method as claimed in claim 1, wherein the step of executing structured validation / characterisation steps of the model selection for developing and selecting model includes step of:
identification of the parameter characteristics and dimension;
determining dimensional consistency;
determining and setting of validation and comparison set points with the best case or ideal scenarios;
determining the causality and recurrence frequency; and
performing factor based validations.

5. The method as claimed in claim 1, wherein the step of detecting anomalies, if present and deriving inferences through Inference Engine & Rule Base includes step of:
performing, by inference engine various analytical function by running a plurality of algorithms and the validation criteria’s defined in the Rule base;
performing, by inference engine from the organizational, departmental, sectional and nodal perspective, evaluation / assessments of individuals as well as organizations;
suggesting, by the inference engine set of indexes to subsequently provide the perspective for the value chain impact of these indexes;
solving, by the inference engine issues pertaining to the scales and benchmarks / baseline standards highlighting the deviation in the assessment framework that existed; and
creating dynamically rule bases using self-organizing neural networks depending on the nature of the parametric performance factor.
6. The method as claimed in claim 1, wherein the step of providing, by a output logic of a logic controller outcomes and action triggers includes steps of:
performing parametric factor evaluation of the input data and its comparison with the benchmarked / baseline standards outcomes as per the organizational as well as manufacturing process requirements;
providing performance evaluation judgement in from the perspective of Degree of deviations from the baseline standard outcomes;
aggregating performance factor evaluations and outcome judgements across – Man, Machine, Material and Methods at each Machine, section, department, function, plant and organization level;
prescribing corrective actions based on the findings represented by enabling the decision process through a cross machine (COE)/departmental / functional/ organizational comparatives; and
providing, by the output logic of the logic controller normalized data and action triggers resulting into Data & Outcome Measurability, Data & Outcome Accessibility, Data & Outcome Sustainability, Data & Outcome Actionability.

7. The method as claimed in claim 1, wherein the step of performing, by the logical layer module the performance evaluation includes steps of:
Receiving, by the logical layer module the input data from contextual layer module that includes the real-time input data from the data sources or nodes from Machine as well as man through the hardware elements, and from the conceptual layer the analysed data and inferences of the analysis representing the parametric trends and identification of the anomalies;
performing data extraction through scaling and normalization of the data;
performing predictive modelling by formulation of modelling and predictive analysis;
generating business insights by arriving at conclusions and futuristic actions; and
generating predictive and prescriptive action triggers through predictive and prescriptive modelling.

8. The method as claimed in claim 1, wherein the step of performing, by the logical layer module data extraction through scaling and normalization of the data includes extracting the required information from all the sources and eliminating loud / noise from the data through the normalization operations wherein the data and values are scaled in provided range and subsequently the extraneous elements are removed by performing correlation analysis.

9. The method as claimed in claim 1, wherein the step of performing predictive modelling by formulation of modelling and predictive analysis includes steps of:
building model that is self-reliant, self- regulating, context aware and capable of making predictions and prescribe / propose actions for elimination of the anomalies across the parameter factors of evaluations namely Man, Machine, Material and Methods;
enhancing the classical regression models by building the analysis of the relationships and interconnectivity as well as interdependence of the variables in order to suit complex evaluation / assessment;
performing continuously by the pattern classification model the task of labelling the observations and outcomes of the data analysis continuously carried out against the factors of production – Man, Machine Material and Methods;
executing, the supervised learning model to process the input data that is coming from the contextual layer module;
establishing, by the unsupervised learning models the groupings and interpretation of the model based on the input data acquired from 4M’s, the outcome classification data, and all the investigative data interpretations acquired through the previous stages; and
developing and designing by the Reinforcement analysis layer module in a given / set Context concept of Parametric Classification and logically grouping parameters, data and their individual as well as correlated outcomes using raw as well as computed or derived inferences and information.

10. The method as claimed in claim 1, wherein the step of executing, the supervised learning model to process the input data that is coming from the contextual layer module includes:
the assessment outcome / result of a particular parametric assessment into the assessment outcome / result of a particular parametric assessment impacting the organizational value chain (Four factors of production- Man, Machine, Material & Methods) and the assessment outcome / result of a particular parametric assessment contributing to the future trend analysis of the data and does not directly impact the organizational value chain immediately;
classifying, into the categories cost, value, & efficiency / productivity the assessment outcome/result of a particular parametric assessment having direct impact on the organizational value chain;
predicting, by the outcome classification model the impact of the individual as well as organization performance parameters and subsequently arriving at an appropriate action decision;
classifying by the regression the outcome data and establishing the relationship between degree of impact of one outcome indicator on another and modelling the future relationship between them and subsequently feeding it as an input to the decision tree for arriving at an appropriate action decision categorized into Action triggers, Information, Tasks, and Impact;
building learning models and algorithms and performing classification of data set to establish the relationship between the factors of evaluations collected from the – man, machine method & material (4M), historical trends data which has been continuously been collected and stored in the database, other input information data which is being fed by the machine operators and also collected from other external data sources;
identifying, by the Outcome classification decision tree the anomalies and defective branch node in the entire relationship tree and its impact on the other factors or other factors impact on the present anomaly; and
establishing by the cross linking mechanism the first proof of anomaly trend and impact classification based on outcomes and investigative clauses.

11. The method as claimed in claim 1, wherein the step of converging, by the Transformation layer module all the findings from the previous layers/models and the Machine learning and Artificial Intelligence models to produce Descriptive, Diagnostic , Predictive and Prescriptive analysis dashboards for the users includes step of:
providing descriptive analysis including historical data analysis, recurrence trends, trend based impact assessment, factor correlation impacting productivity/efficiency;
providing diagnostic analysis including anomaly/deviation reasoning, factors impacting the anomalies, business impact of the anomalies and deviations;
providing predictive analysis including preventive action against anomalies predictions, prevention of losses and elimination of efficiency leakages and predictive controls and measures; and
providing prescriptive analysis including prescriptive action boards, action recommendations, continuous improvement, and real-time Man, Machine, Method enhancements.

12. A system for assessing individuals/ organizational productivity efficiency and outcomes, the system comprises:
a plurality of sensing devices, the plurality of sensing devices spread across a factory/organisation environment and forms a proximity intelligence framework collecting periodic time stamping data essential for the subsequent productivity / efficiency evaluation and assessment of the man factor;
a data acquisition module/Universal Data adaption unit includes:
at least one user management system module configured to identify registered users, facilitate authentication and authorization of a registered user and registration of a new user, and providing access to the user account of the registered user,
a universal embedded controller / Edge Device module configured to collect parametric data from the plurality of sensors, machine and equipment in the factory, transform the data procured from the plurality of sensing devices into standard data structures across all types of equipment to enable consistent reporting and securely transmission to a cloud by means of an automated data transmission engine, and
at least one memory communicatively coupled to the Universal embedded controller module;
at least one data transmission module, the data transmission module comprises at least one processor configured as single board computer-based EDGE gateway and a memory communicatively coupled to the EDGE gateway; and
a cloud communication server, the cloud communication server includes at least one application module configured for receiving input data from the data transmission module, process the input data by an assessment / evaluation framework model embedded at the processor of the application module, the assessment/evaluation framework model includes a plurality of layers configured for evaluation / assessment of the realtime parameters, the layers include:
at least one contextual layer module configured to conduct the contextual analysis on the data outlaying organization structure and alignment of the Machines, Equipment, People/ Operators / Humans, people hierarchies, and Material, Methods and processes assigned with the organization structure and production processes that has aggregation and consolidation at the cloud communication server /Edge Server,
at least one conceptual layer module configured to receive input data from the contextual layer module and perform analytical function particularly, evaluation / assessments of individuals as well as factory/organization from the organizational, departmental, sectional and nodal perspective to detect anomalies in the data then derive Inferences through Inference Engine & Rule based sub module embedded therein,
at least one logical layer module configured to receive input data from contextual layer module and conceptual layer and perform the performance evaluation of employee as well as organization’s performance and productivity across all the four parametric factors of evaluation (namely Man, Machine, Material and Methods) by analysing the data through a plurality of Machine Learning and Deep Learning models to achieve critical business insights,
at least one transformational layer module configured to deliver comprehensive analysis across four key area including descriptive analysis, diagnostic analysis, predictive analysis and prescriptive analysis of the parameters from the logical layer module.
13. The system as claimed in claim 12, wherein the universal embedded controller module comprises a processing Unit, an opto-Isolated Power Supply, an electrical interface for request-response protocol, a storage medium for operational data and local data storage, and a data communication tracking module, said Universal embedded controller module / Edge Device is designed and configured to:
collect data including but not limited to digital, analog , coils and holding registers, alarms, messages, warning data and signals from PLC, sensor data, data from Scada systems, data from the Manufacturing Execution system;
perform data acquisition from the plurality of sensors, Machine / equipment PLC’s, Controllers and all source data nodes;
provide Plug-and-Play universal data collection from programmable logic controllers (PLC) supporting open protocols as well as proprietary connectors;
communicate over standard communication protocol as well as embed within itself at least one protocol convertor that can convert the input data received into the standard format;
communicate with client controllers/PLCs of different protocols by converting those protocols into its own standard protocol using built-in protocol converters;
incorporate an automated data transformational engine configured to transform machine data into standard data structures across all the types of equipment and transmit to the central Gateway that can further push the input data to the cloud server, alternatively push the data to the cloud server from the machine directly;
connect to the plurality of sensing devices and to the equipment, configure and manage said connectivity remotely through a web interface;
perform as an EDGE gateway server capable of functioning as the consolidation and single source data exchange node that synchronizes local data collected from a plurality of machines and all the source data nodes, and with a global database that resides in the cloud infrastructure;
perform remote management of the distributed network of the Embedded controllers and Proximity intelligence tags and parametric sensors;
perform Authentication and Reauthentication functionalities and authorizing the certificate with the help of the Public / Private key logic while transmitting the data, and
execute the functionality of running self-registration and authentication service for the Universal embedded controller module during the initial data transmission, thus establishing a trusted device network.
14. The system as claimed in claim 12, wherein the user management system module of the data acquisition module/Universal Data adaption unit configured to perform user registration for a new user, identification of a registered user, user authentication and authorization, and providing access to the user account of the respective user.

15. The system as claimed in claim 12, wherein the memory unit of the data acquisition module/Universal Data adaption unit is configured to receive data from the plurality of sensing devices and the data transfer happens via a wireless medium within the surveillance of the data communication tracking module.

16. The system as claimed in claim 12, wherein the plurality of sensing devices are deigned in the form of wearable transmission tags for the Human Resources / employees while the receiving terminals are tagged to the machines, embodied in the Universal embedded controller module to form a proximity intelligence framework such that the employee’s / operator’s parametric data including indoor movement, their proximity with the machines with periodic time stamping data are captured for subsequent productivity / efficiency evaluation and assessment of the Man factor of the invention framework.

17. The system as claimed in claim 12, wherein the application module of the cloud communication server includes an assessment / evaluation framework model based on Logic controller, embedded through conceptual layer module.,

18. The system as claimed in claim 12, wherein the rule base sub module for the logic controller incorporates Neural Network to evaluate/ assess the dynamic parametric factors of evaluation across Man, Machine, Materials and Methods that keeps a self-regulating characteristic based on the learnings from the data and thus the data tends to keep on continuously creating deeper impact on the business outcomes.

19. The system as claimed in claim 12 includes Machine Learning & Deep Learning module within the assessment/evaluation framework model that continuously learns and incorporate new inputs, parameters, rules, equations, and solutions into the knowledge base that eventually make suggestions based on previously inputted and newly learned information to solve each of the inefficiencies at each human – machine convergence ecosystem on manufacturing Shopfloor.
Dated this on 27th September, 2024

Prafulla Wange
(Agent for the applicant)
(IN/PA-2058)