Claims:We Claim:
1. A processor implemented method, comprising:
obtaining, via one or more hardware processors, an input text description (202);
pre-processing the input text description document to obtain a pre-processed input text description (204);
identifying, via the one or more hardware processors, (i) one or more processes from pre-processed input text description, (ii) one or more inputs for the one or more processes, and (iii) one or more outputs for the one or more processes (206);
splitting, via the one or more hardware processors, each of the one or more processes to one or more nth level sub-processes (208);
identifying, via the one or more hardware processors, (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof, wherein the set of relevant processes serve as a set of tasks and the set of relevant nth level sub-processes serve as one or more corresponding nth level sub-tasks of the set of tasks, based on an associated output of the relevant process and the relevant nth level sub-process (210);
processing, via a rule nexus model executed by the one or more hardware processors, (i) the set of tasks and (ii) the set of relevant nth level sub-tasks based on (i) one or more associated properties thereof, and (ii) the one or more inputs to obtain one or more parameters and one or more nth level sub-parameters, wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters correspond to (i) a specific task from the set of tasks and (ii) a specific nth level sub-task from the set of nth level sub-tasks, and wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters are indicative of a weightage being assigned to each corresponding task and a nth level sub-task (212);
automatically generating, via the one or more hardware processors, a multidimensional correlation feature matrix using the one or more parameters and the one or more nth level sub-parameters (214); and
performing, via the one or more hardware processors, one or more logical operations on the multidimensional correlation feature matrix and a decision matrix associated with the input text description to obtain one or more desired outputs, wherein the one or more desired outputs correspond to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks (216).

2. The processor implemented method of claim 1, wherein the one or more nth level sub-processes are identified based on one or more reference text segments comprised in the pre-processed input text description.

3. The processor implemented method of claim 1, further comprising recommending, via the rule nexus model, the one or more desired outputs corresponding to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks.

4. The processor implemented method of claim 1, wherein the weightage of the one or more parameters and the one or more nth level sub-parameters comprises at least one of a numerical value and a categorical value.

5. The processor implemented method of claim 1, wherein the one or more logical operations are performed based on an evaluation of the one or more parameters and the one or more nth level sub-parameters using the weightage being assigned.

6. A system (100), comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
obtain an input text description;
pre-processing the input text description document to obtain a pre-processed input text description;
identify (i) one or more processes from pre-processed input text description, (ii) one or more inputs for the one or more processes, and (iii) one or more outputs for the one or more processes;
split each of the one or more processes to one or more nth level sub-processes;
identify (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof, wherein the set of relevant processes serve as a set of tasks and the set of relevant nth level sub-processes serve as one or more corresponding nth level sub-tasks of the set of tasks, based on an associated output of the relevant process and the relevant nth level sub-process;
process, via a rule nexus model executed by the one or more hardware processors, (i) the set of tasks and (ii) the set of relevant nth level sub-tasks based on (i) one or more associated properties thereof, and (ii) the one or more inputs to obtain one or more parameters and one or more nth level sub-parameters, wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters correspond to (i) a specific task from the set of tasks and (ii) a specific nth level sub-task from the set of nth level sub-tasks, and wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters are indicative of a weightage being assigned to each corresponding task and a nth level sub-task;
automatically generate, via the one or more hardware processors, a multidimensional correlation feature matrix using the one or more parameters and the one or more nth level sub-parameters; and
perform, via the one or more hardware processors, one or more logical operations on the multidimensional correlation feature matrix and a decision matrix associated with the input text description to obtain one or more desired outputs, wherein the one or more desired outputs correspond to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks.

7. The system of claim 6, wherein the one or more nth level sub-processes are identified based on one or more reference text segments comprised in the pre-processed input text description.

8. The system of claim 6, wherein the one or more hardware processors are further configured by the instructions to recommend, via the rule nexus model, the one or more desired outputs corresponding to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks.

9. The system of claim 6, wherein the weightage of the one or more parameters and the one or more nth level sub-parameters comprises at least one of a numerical value and a categorical value.

10. The system of claim 6, wherein the one or more logical operations are performed based on an evaluation of the one or more parameters and the one or more nth level sub-parameters using the weightage being assigned.

Dated this 30th day of December 2021

Tata Consultancy Services Limited
By their Agent & Attorney

(Adheesh Nargolkar)
of Khaitan & Co
Reg No IN-PA-1086 , Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
MULTIDIMENSIONAL CORRELATION FEATURE MATRIX BASED GENERATION OF DESIRED OUTPUTS FOR TASKS AND NTH LEVEL SUB-TASKS

Applicant
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India

Preamble to the description:
The following specification particularly describes the invention and the manner in which it is to be performed.
TECHNICAL FIELD
[001] The disclosure herein generally relates to data analytics for decision making in an entity, and, more particularly, to multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks.

BACKGROUND
[002] Many business processes use a logical appraisal of data based upon certain criteria, with a primary intention of making an informed, unprejudiced business decision for carrying our various business process. Whereas a small proportion of the data is analyzed on basis of metrics, most other decisions are based upon few kinds of semantic protocols, which are query and criteria based. In such protocols, application of metrics is extremely difficult or often impossible. Hence, despite large data volume, its processing requires human intervention. Eventually, the process is delayed, often completed with a bias or inadequate analysis, or partially completed, despite being critical. Some common examples of this includes a) analysis of service or complaint tickets in incident / complaint management system, where the ticket quality analysis is based upon the content of the response or closure comments examined against the original query and also the customer feedback b) analysis of social media posts (for vigilance processes), pharmacovigilance, materio vigilance, National security vigilance etc.) where the analysis is based upon the content text with respect to words or subject, sentiment, intensity, availability of requisite information, etc. c) analysis of literature (for scientific and vigilance purposes) where the analysis is based upon the content text with respect to query terms, scientific relevance, evidence level and reference to context, etc., d) analysis of the data of associates in an office location for selection of various human resource process (of organization or delivery accounts), based upon the credentials, contextual information about the associate, 5) recruitment and prioritization of a locality and identification of critical individuals there in for maximum efficiency output of community based drives such as evacuation in the catastrophe warnings, Mass immunization /medication drives, decentralized community based clinical trials, etc.
[003] In all above examples, for correct use of any data for its subsequent procedures, its effective unbiased appraisal is critical. Large amount of data and individual’s perception may influence the primary and thereby the subsequent process. While most of such data is systematically appraised with various criteria, the amount of data and complexity of the appraisal criteria usually makes the process cumbersome. One example from the above list is explained in further details below: Post lockdown, almost all the projects/accounts of an organization would be required to operate on limited office resources. Hence, a strategic planning would be required to select associates in a pattern that would maintain all critical business aspects including productivity, associate safety, maximum utility of the office space abiding with the norms etc. Hence, data of all the associates must be systematically basis Government regulations prevailing at that time, Business Criticality, Support coverage, infra (Device/internet availability), Government regulations of Marking of Red/ Orange/ Green zones basis which movement of associates are governed, etc. to identify who should be called to office. While the manual process is possible with small accounts/projects using simple tools such as word-processing techniques (e.g., Microsoft® Excel) most of the accounts, which are large face challenges to appraise and keep error-free record of repetitive changes for audits etc. Producing list on periodic basis is usually cumbersome if done manually.
[004] Most of these are programs are based upon the logical case-based reasoning for appraisal, classification, prioritization, etc. Hence, using automated / statistically trained data models are not sufficient for the justifiable, explainable case-based reasoning of the data processed. This requires a combination of the human’s ability of contextual association of the data with logical reasoning for the action, which a human achieves through a stated or unstated protocol with defined criteria for a judgment or decision.

SUMMARY
[005] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one aspect, there is provided a processor implemented method for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks. The method comprises obtaining, via one or more hardware processors, an input text description; pre-processing, via the one or more hardware processors, the input text description document to obtain a pre-processed input text description; identifying, via the one or more hardware processors, (i) one or more processes from pre-processed input text description, (ii) one or more inputs for the one or more processes, and (iii) one or more outputs for the one or more processes; splitting, via the one or more hardware processors, each of the one or more processes to one or more nth level sub-processes; identifying, via the one or more hardware processors, (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof, wherein the set of relevant processes serve as a set of tasks and the set of relevant nth level sub-processes serve as one or more corresponding nth level sub-tasks of the set of tasks, based on an associated output of the relevant process and the relevant nth level sub-process; processing, via a rule nexus model executed by the one or more hardware processors, (i) the set of tasks and (ii) the set of relevant nth level sub-tasks based on (i) one or more associated properties thereof, and (ii) the one or more inputs to obtain one or more parameters and one or more nth level sub-parameters, wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters correspond to (i) a specific task from the set of tasks and (ii) a specific nth level sub-task from the set of nth level sub-tasks, and wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters are indicative of a weightage being assigned to each corresponding task and a nth level sub-task; automatically generating, via the one or more hardware processors, a multidimensional correlation feature matrix using the one or more parameters and the one or more nth level sub-parameters; and performing, via the one or more hardware processors, one or more logical operations on the multidimensional correlation feature matrix and a decision matrix associated with the input text description to obtain one or more desired outputs for each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks based on the comparison.
[006] In an embodiment, the one or more nth level sub-processes are identified based on one or more reference text segments comprised in the pre-processed input text description.
[007] In an embodiment, the method further comprises recommending, via the rule nexus model, the one or more desired outputs corresponding to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks.
[008] In an embodiment, the weightage of the one or more parameters and the one or more nth level sub-parameters comprises at least one of a numerical value and a categorical value.
[009] In an embodiment, the one or more logical operations are performed based on an evaluation of the one or more parameters and the one or more nth level sub-parameters using the weightage being assigned.
[010] In another aspect, there is provided a processor implemented system for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks. The system comprises: a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: obtain an input text description; pre-process the input text description document to obtain a pre-processed input text description; identify (i) one or more processes from pre-processed input text description, (ii) one or more inputs for the one or more processes, and (iii) one or more outputs for the one or more processes; split each of the one or more processes to one or more nth level sub-processes; identify (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof, wherein the set of relevant processes serve as a set of tasks and the set of relevant nth level sub-processes serve as one or more corresponding nth level sub-tasks of the set of tasks, based on an associated output of the relevant process and the relevant nth level sub-process; process, via a rule nexus model, (i) the set of tasks and (ii) the set of relevant nth level sub-tasks based on (i) one or more associated properties thereof, and (ii) the one or more inputs to obtain one or more parameters and one or more nth level sub-parameters, wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters correspond to (i) a specific task from the set of tasks and (ii) a specific nth level sub-task from the set of nth level sub-tasks, and wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters are indicative of a weightage being assigned to each corresponding task and a nth level sub-task; automatically generating a multidimensional correlation feature matrix using the one or more parameters and the one or more nth level sub-parameters; and performing one or more logical operations on the multidimensional correlation feature matrix and a decision matrix associated with the input text description to obtain one or more desired outputs for each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks based on the comparison.
[011] In an embodiment, the one or more nth level sub-processes are identified based on one or more reference text segments comprised in the pre-processed input text description.
[012] In an embodiment, the one or more hardware processors are further configured by the instructions to recommend, via the rule nexus model, the one or more desired outputs corresponding to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks.
[013] In an embodiment, the weightage of the one or more parameters and the one or more nth level sub-parameters comprises at least one of a numerical value and a categorical value.
[014] In an embodiment, the one or more logical operations are performed based on an evaluation of the one or more parameters and the one or more nth level sub-parameters using the weightage being assigned.
[015] In yet another aspect, there are provided one or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause a method for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks. The method comprises obtaining, via the one or more hardware processors, an input text description; pre-processing, via the one or more hardware processors, the input text description document to obtain a pre-processed input text description; identifying, via the one or more hardware processors, (i) one or more processes from pre-processed input text description, (ii) one or more inputs for the one or more processes, and (iii) one or more outputs for the one or more processes; splitting, via the one or more hardware processors, each of the one or more processes to one or more nth level sub-processes; identifying, via the one or more hardware processors, (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof, wherein the set of relevant processes serve as a set of tasks and the set of relevant nth level sub-processes serve as one or more corresponding nth level sub-tasks of the set of tasks, based on an associated output of the relevant process and the relevant nth level sub-process; processing, via a rule nexus model executed by the one or more hardware processors, (i) the set of tasks and (ii) the set of relevant nth level sub-tasks based on (i) one or more associated properties thereof, and (ii) the one or more inputs to obtain one or more parameters and one or more nth level sub-parameters, wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters correspond to (i) a specific task from the set of tasks and (ii) a specific nth level sub-task from the set of nth level sub-tasks, and wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters are indicative of a weightage being assigned to each corresponding task and a nth level sub-task; automatically generating, via the one or more hardware processors, a multidimensional correlation feature matrix using the one or more parameters and the one or more nth level sub-parameters; and performing, via the one or more hardware processors, one or more logical operations on the multidimensional correlation feature matrix and a decision matrix associated with the input text description to obtain one or more desired outputs for each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks based on the comparison.
[016] In an embodiment, the one or more nth level sub-processes are identified based on one or more reference text segments comprised in the pre-processed input text description.
[017] In an embodiment, the method further comprises recommending, via the rule nexus model, the one or more desired outputs corresponding to each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks.
[018] In an embodiment, the weightage of the one or more parameters and the one or more nth level sub-parameters comprises at least one of a numerical value and a categorical value.
[019] In an embodiment, the one or more logical operations are performed based on an evaluation of the one or more parameters and the one or more nth level sub-parameters using the weightage being assigned.
[020] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
[021] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
[022] FIG. 1 depicts an exemplary system for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks, in accordance with an embodiment of the present disclosure.
[023] FIG. 2 depicts an exemplary flow chart illustrating a method for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks, using the system of FIG. 1, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[024] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
[025] As mentioned above, most of these are programs/models are based upon the logical case-based reasoning for appraisal, classification, prioritization, etc. Despite the analytics programs/models are advanced on presentation and addressing complex solution, these models have limitations in semantic contextual data appraisal because of various reasons. These challenges are based upon the model used.
1. Metrics / Statistics Driven Models - The metrics or statistics-based models and highly syntax driven require data to be available in a specific tabular (whether in Structured Query Language (SQL) or no SQL) format, which can be statistically observed and analyzed for deriving requisite outcomes.
2. Models based upon Natural Language Processing (NLP) with other concurrent Artificial Intelligence (AI) technology - Highly dependent upon the principles of relative data processing which include statistical relevance parameters like probability-based Models such as assignment-classifiers, goodness of fit. These technologies may give near-desired outcomes as can be simulated with human beings multiple-classifier approach to process the data systematically. However, this method cannot produce reliable justifications for the decision taken. Hence, the challenges in generating the appraisal information in a justifiable, explainable report format is not possible and continues to pose other constraints/limitations. Despite generation of an explainable AI kind of report, the model is based upon its own logic hence is often biased with the data relativity. Hence, data analysis performed on basis of probabilistic machine learning AI approach tends to carry forward the errors committed in the data classification and does not allow the humans to justify / correct it logically. These limit use of technology currently available for automation for business process to help in appraisal, ranking and prioritization of data such as identifying which associates should operate from the office basis varied predefined factors/ parameters.
[026] The business process automation, therefore, requires a hybrid approach, where some manual processes are automated with rules and data processes are mapped to these rule-based process through the AI models. This approach can be executed by ingestion of a protocol which is written as a business process or remains an unwritten through process. Such protocol includes multiple levels and multiple criteria. The AI system converts the protocol into a series of complex rules and generates the template in which the reports need to be created, based upon sematic ingestion with NLP. This entire rule nexus converts it into the syntax of information and forms a level 1 model. Since factors and parameters are dynamic and the interim changes in the rules-nexus is automated. This model for creation of a protocol and report template resolves the challenge of business which requires justified processing along with reporting.
[027] The second set of challenges includes handling of the data of different types presented in different format. While human beings have various capabilities to ingest and comprehend the data of different types directly with imbibed intelligence, the machine segregates this data into the data types. Hence, the strategy of machine to deal with each data type differs. For example, the data processing requires a specified strategy for categorical data, numeric data in statistics. In case of the textual data, the problem is even more complex, as the strategy needs to be defined basis available information. Any AI system and analytics models are currently not trained to create and train a model based upon the information types, dynamically on a rules-nexus.
[028] To overcome the above technical problems, embodiments of the present disclosure provide system and method for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks. More specifically, the present disclosure provides a system that implements an AI-ML model to (a) ingest a protocol which is uploaded or created by a human-being and generate the rules-nexus (creation of rules-nexus from AI-ML model), (b) create the report template and strategy for creation model to handle the data type as per the rules-nexus, (c) process the data with the strategy-driven model with other AI/statistical process and provide statistical throughput for generation of the final outcome with a staged, detailed, justified case based reasoning for each processed data point and its outcome (through put generation with selection of statistical model, compound case based reasoning). By performing above steps/methods, the present disclosure enables the system and method to handle data and appraisal approach significantly similar to the human process. This is an interactive solution, which provides humans an optional control on some critical processes, especially to define the appraisal protocols where extraction of data is performed rather than metrics based, conversion of semantic data into syntax, automated systematic appraisal of the information, and use of semantic data processing techniques.
[029] More specifically, system and method of the present disclosure enables generation of master record of all data with its component based systematic appraisal. This data is presented for every individual record and a collective analysis of all sematic responses to make a proposed decision for every individual record. This helps the business users to save bias, time, effort, etc. and identify appraised data in general. For example, in a scenario as implemented by the system, the method the logical protocol/operation(s) to classify the associates in various zones (e.g., Green/ Orange zones) as per government norms, and may also use other factors/ parameters as well such as Business Criticality, Support coverage, Devices used by associates, internet availability in remote regions, etc. in a specific precedence and each associate in the order of priority. The final ranks in aggregate forms a report of patterned prioritization, which can be adjusted with some additional parameters at a batch level, if required.
[030] Referring now to the drawings, and more particularly to FIGS. 1 through 2, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[031] FIG. 1 depicts an exemplary system for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks, in accordance with an embodiment of the present disclosure. In an embodiment, the system 100 includes one or more hardware processors 104, communication interface device(s) or input/output (I/O) interface(s) 106 (also referred as interface(s)), and one or more data storage devices or memory 102 operatively coupled to the one or more hardware processors 104. The one or more processors 104 may be one or more software processing components and/or hardware processors. In an embodiment, the hardware processors can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor(s) is/are configured to fetch and execute computer-readable instructions stored in the memory. In an embodiment, the system 100 can be implemented in a variety of computing systems, such as laptop computers, notebooks, hand-held devices (e.g., smartphones, tablet phones, mobile communication devices, and the like), workstations, mainframe computers, servers, a network cloud, and the like.
[032] The I/O interface device(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface device(s) can include one or more ports for connecting a number of devices to one another or to another server.
[033] The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic-random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, a database 108 is comprised in the memory 102, wherein the database 108 comprises input text description for which desired outputs are to be generated and recommended. The database 108 further comprises pre-processed input text description, (i) one or more identified processes from pre-processed input text description, (ii) one or more inputs identified for the one or more processes, and (iii) one or more outputs identified for the one or more processes, one or more nth level sub-processes being obtained from the processes after splitting, (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof which serves as tasks and nth level sub-tasks, respectively, one or more parameters and one or more nth level sub-parameters of each task and sub-task, multidimensional correlation feature matrix, rule nexus model, logical operations, and the like. The memory 102 further comprises (or may further comprise) information pertaining to input(s)/output(s) of each step performed by the systems and methods of the present disclosure. In other words, input(s) fed at each step and output(s) generated at each step are comprised in the memory 102 and can be utilized in further processing and analysis.
[034] FIG. 2, with reference to FIG. 1, depicts an exemplary flow chart illustrating a method for multidimensional correlation feature matrix based generation of desired outputs for tasks and nth level sub-tasks, using the system 100 of FIG. 1, in accordance with an embodiment of the present disclosure. In an embodiment, the system(s) 100 comprises one or more data storage devices or the memory 102 operatively coupled to the one or more hardware processors 104 and is configured to store instructions for execution of steps of the method by the one or more processors 104. The steps of the method of the present disclosure will now be explained with reference to components of the system 100 of FIG. 1, and the flow diagram as depicted in FIG. 2. In an embodiment, at step 202 of the present disclosure, the one or more hardware processors 104 obtain an input text description. In an embodiment, at step 204 of the present disclosure, the one or more hardware processors 104 pre-process the input text description document to obtain a pre-processed input text description. The system 100 and method of the present disclosure may employ known in the art pre-processing techniques to pre-process the input text description wherein stop words, unnecessary words, spelling errors, grammatical errors are identified, corrected and/filtered to obtain pre-processed input text description.
[035] In an embodiment, at step 206 of the present disclosure, the one or more hardware processors 104 identify (i) one or more processes from pre-processed input text description, (ii) one or more inputs for the one or more processes, and (iii) one or more outputs for the one or more processes. For instance, post pre-processing of the input text description, the pre-processed input text description is obtained as below:
“Selection of sample from population for prioritization in critical procedures such as resuming office after catastrophic shut down (e.g., say pandemic) or participation in a community based decentralized clinical trial.”
[036] Basis the above pre-processed input text description, the one or more hardware processors 104 identify (i) technical flow as at least one process, (ii) text document contains selection criteria and information about population as an input, and (iii) filtered sample from population meets selection criteria as a desired output.
[037] Upon identifying the above process, input and output, in an embodiment, at step 206 of the present disclosure, the one or more hardware processors 104 split each of the one or more processes to one or more nth level sub-processes and identify (i) a set of relevant processes from the one or more processes and (i) a set of relevant nth level sub-processes based on an associated correlation thereof at step 208, wherein the set of relevant processes serve as a set of tasks and the set of relevant nth level sub-processes serve as one or more corresponding nth level sub-tasks of the set of tasks, based on an associated output of the relevant process and the relevant nth level sub-process. In an embodiment, the one or more nth level sub-processes are identified based on one or more reference text segments (uniform resource locators - URLs) comprised in the pre-processed input text description. For instance, selection of relevant sub task includes a scenario wherein for structured data sub tasks are basically the feature of the database which shows correlation with process. Employee data for instance may be extracted from one or more URLs (e.g., personal employee data may be extracted from https://xyz.com/user-data and employee project data may be extracted from say https://abc.com/project-data. Further, company/office/entity requirement data may be extracted accordingly. For instance, project requirement data may be extracted from say, https://xyz.com/project-requirement and resources restriction data may be extracted from say, https://abc.com/resources-requirement.
[038] The above steps of 206 and 208 are better understood by way of following description:
Say, process identified is ‘Opening ABC office in India’. ABC office refers to an entity in which a decision is to be made. A first task identified may be ‘what is the positive rate overall’ (e.g., say 30%), and an associated sub-task identified may be ‘Areas which are green’ (e.g., say 20%). A second task identified may be ‘National government regulations’ (e.g., say supports: compliant). A sub-process of the process may be identified as ‘Opening of the ABC office in Maharashtra’. Likewise, task and sub-tasks may be identified accordingly. The desired output may include can open in Maharashtra and/or other states in India.
[039] Another example may include process being identified as ‘Organization XYZ calls employees after pandemic using provided guidelines, out of total criteria’.
Sub Process 1: Selection criteria based on location such as project location, and employee location less than x kms from the project location
Associated Task of the sub process l1: Location
Sub Task: identify project location
Sub Task: identify employee Location
Sub Process 2: Selection criteria based on productivity and experience such as employee has minimum A band, 4 out of 5 rating, with relevant 4 years of experience,
Sub Process 2a: Selection criteria based on Productivity such as employee has minimum A band, 4 out of 5 rating.
Task: Productivity
Sub Task: Rating
Sub Task: Performance
Sub Process 2b: Selection criteria based on Experience, with relevant 4 years of experience,
Task: Experience
Sub Task 1: Total years of experience
Sub Task la: Inside XYZ experience
Sub Task 1b: Outside XYZ experience
Sub Task 1c: Current Project experience
[040] Referring to steps of FIG. 2, in an embodiment, at step 210 of the present disclosure, the one or more hardware processors 104 process, via the rule nexus model, (i) the set of tasks and (ii) the set of relevant nth level sub-tasks based on (i) one or more associated properties thereof, and (ii) the one or more inputs to obtain one or more parameters and one or more nth level sub-parameters, wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters correspond to (i) a specific task from the set of tasks and (ii) a specific nth level sub-task from the set of nth level sub-tasks, and wherein each parameter from the one or more parameters and each nth level sub-parameter from the one or more nth level sub-parameters are indicative of a weightage being assigned to each corresponding task and a nth level sub-task. The output of the rule nexus model is one or more parameters and/or sub-parameters. In an embodiment, the parameters are referred as tasks and serve as output of the rule nexus model. In another embodiment, the sub-parameters are referred as sub-tasks and serve as output of the rule nexus model. In an embodiment, the rule nexus model comprises the following which when executed parameters and nth level sub-parameters are obtained.
Input: Task or Sub-task with data (data frame)
Weightage is numerical, in one embodiment of the present disclosure.
Process: Fuzzy logic, Machine learning Prediction, Deep learning
Output: Parameter or sub parameter with score/Task or sub task with score

1. Fuzzy logic: Different set logical operations /if-else. For instance, for Location Task, check condition for employee location and project location less than 50 km.
2. Machine Learning Prediction: Supervised or Unsupervised prediction. For instance, for Productivity task, to predict/classify performance text/review (like spam prediction, etc.)
3. Deep Learning Prediction: Special Supervised/Unsupervised prediction with very large data. Vision or Text or timeseries prediction gives better result with DL models. For instance, time series future prediction of the performance, leaves, etc.
The above may be either obtained or identified based on the input text description of the URLs or specifically given/provided by one or more users. Further, in the requirement section of the input text description, if there is presence of high priority/mandatory sub-process. particular task is mapped with weightage score by the system 100. For example, better the band provided in a performance review, better is the prioritization. For instance, for categorical variables (Bands A(2)>B(1)>C(0)), weightage is in hierarchical order. For numerical variables (Location <50 km, score 1 or 0), equal weightages may be given to all features.
[041] In an embodiment, the weightage of the one or more parameters and the one or more nth level sub-parameters comprises at least one of a numerical value and/or a categorical value.
[042] In an embodiment, at step 212 of the present disclosure, the one or more hardware processors 104 automatically generate a multidimensional correlation feature matrix using the one or more parameters and the one or more nth level sub-parameters. Below Table 1 depicts an example of the multidimensional correlation feature matrix generated for the above exemplary text description serving as input to the system 100:
Table 1
Task Score Selection Criteria at level 1 Selection Criteria at level 2
Location 100 < 50 km NA
Productivity and Experience 3 out of 4 1 out of 2 sub-task for productivity
2 out of 2 sub-task for experience
Rating > =4
performance NA
Organization Experience >= 4 years
Current Project Experience > 1 year

Score column of above Table 1 is output of the rule nexus model for an employee selection criteria at level ‘n’ and represent condition (obtained from doc) of sub-process at level n. For an employee there are 4 sub-tasks (rating, performance, current project experience, inside organization experience, and the like) of task productivity and experience. Only 3 sub-tasks are fulfilled therefore 3 out of 4 at sub-process level 1 and so on. The output of the rule nexus model depends upon the number of important sub-tasks at particular level which feed into the rule nexus model (for categorical and numerical). For instance, productivity and experience has total 4 sub-tasks in which only 3 are mandatory and performance is optional. If a mandatory feature fulfills then output is 1 else 0. 100 kms (or kilometers) is the distance of an employee’s location to office location.
[043] In an embodiment, at step 212 of the present disclosure, the one or more hardware processors 104 perform one or more logical operations on the multidimensional correlation feature matrix and a decision matrix associated with the input text description to obtain one or more desired outputs for each task from the set of tasks and each nth level sub-task from the set of nth level sub-tasks based on the comparison. In other words, the one or more desired outputs correspond to each task from the set of tasks and/or each nth level sub-task from the set of nth level sub-tasks. Below Table 2 depicts decision matrix on which logical operations being identified are performed. The logical operations are also performed on the multidimensional correlation feature matrix associated with the input text description. In an embodiment of the present disclosure the decision matrix is decision matrix comprises information extracted from the input text description.
Table 2: Decision matrix
Output Final Eligibility
Calling Employee or Not All tasks must be fulfilled
Task eligible
Location Yes
Productivity and Experience Yes

In the present disclosure, a comparison is a logical operation that is performed between the multidimensional correlation feature matrix and the decision matrix. For instance, based on the Table 1 and Table 2 comparison, it is observed that for an employee, Location -> distance > 50 km therefore location -> 1 and Productivity and Experience > 4 therefore, Productivity and Experience -> 1
[044] The desired output generated by the system 100 is depicted in below Table 3:
Table 3
Employee ID Eligible
123456 Yes
654321 No
348732 Yes

[045] As mentioned above, current AI-based methods are highly dependent upon principles of relative data processing such as classifiers, goodness of fit, or any statistical method, etc. However, these methods have no or insufficient justification for decision making. Human beings indirectly take multiple-classifier approach to rank the data systematically. This approach includes forming a written or unwritten protocol of multiple criteria, based upon semantic understanding, and converting it into the syntax of information. While most of such data is systematically appraised with various criteria, the amount of data and complexity of the appraisal criteria usually makes the process cumbersome. Embodiment of the present disclosure provide system and method that implement artificial intelligence (AI)-based models using various protocols (e.g., human defined protocol(s)) for generating a master record of all data with its component based systematic appraisal. This data is presented for every individual record and a collective analysis of all semantic responses to make a proposed decision for every individual record. Moreover, the method described herein by the system 100 of the present disclosure is an interactive solution that provides users an optional control on some critical processes, especially to take decision of calling employee back to office and similar use cases. It is to be understood by a person having ordinary skill in the art or person skilled in the art that the example(s) described by the system 100 (e.g., decision to call employees to office post pandemic) shall not be construed as limiting the scope of the present disclosure.
[046] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[047] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g., hardware means like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g., using a plurality of CPUs.
[048] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[049] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[050] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[051] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.