Claims:1. A system comprising:
at least one memory storing a plurality of instructions;

one or more hardware processors communicatively coupled with the at least one memory, wherein the one or more hardware processors are configured to execute one or more modules;

a data collection module configured to collect business data, wherein the business data includes transaction data from one or more predefined data sources and feedback from one or more customers;

a data processing module configured to process the collected business data to remove noises using a predefined data processing parameters;

a knowledge graph generation module configured to generate a knowledge graph using the processed data, wherein each of the one or more data points of the knowledge graph is represented by a node and the relation among the nodes is expressed by an edge that represents kinds of the relationship;

a data extraction module configured to extract unstructured data and structured data from the knowledge graph using a natural language processing, wherein the extracted unstructured data is converted into a structured data;

a model development module configured to develop a cognitive model using the structured and unstructured data along with a transfer learning, a machine learning, and a deep learning;

a determination module configured to determine an assortment of the plurality of consumer packaged goods using the generated cognitive model and considering one or more factors, wherein the one or more factors includes a product affinity, a product substitution, a product discontinuity, a product localization, and one more customers’ feedback; and

a recommendation module configured to recommend an assortment of one or more consumer packaged goods (CPG) to one or more retailers for Stock Keeping Units (SKUs), wherein the recommendation is done at an individual store level.

2. The system claimed in claim 1, wherein one or more customers’ feedback from the business are fed back to the cognitive model to tune the cognitive model to improve performance of the cognitive model.

3. The system claimed in claim 1, wherein the cognitive model is generated to perform one or more tasks independently.

4. The system claimed in claim 1, wherein the Natural Language Processing (NLP) analyzes the extracted unstructured data that comes from one or more data sources.

5. The system claimed in claim 1, wherein a big data architecture is used to handle huge amount of unstructured online data, wherein the unstructured online data is analyzed and retrieved in real time from an unstructured database.

6. A processor-implemented method comprising one or more steps of:
collecting one or more business data, wherein the business data includes transaction data from one or more predefined sources and feedback from one or more customers;

processing the collected one or more business data to remove noises using a predefined data processing parameters;

generating a knowledge graph using the processed data, wherein each of the one or more data points of the knowledge graph is represented by a node and the relation among the nodes is expressed by an edge that represents kinds of the relationship;

extracting unstructured data and structured data from the generated knowledge graph using a natural language processing, wherein the extracted unstructured data is converted into a structured data;

generating a cognitive model using the extracted structured and unstructured data along with a transfer learning, a machine learning, and a deep learning;

determining an assortment of the plurality of consumer packaged goods using the generated cognitive model and considering one or more factors, wherein the one or more factors includes a product affinity, a product substitution, a product discontinuity, a product localization, and one more customers’ feedback; and

recommending the assortment of the one or more consumer packaged goods (CPG) to one or more retailers for Stock Keeping Units (SKUs), wherein the recommendation is done at an individual store level.

7. The method claimed in claim 6, wherein one or more customers’ feedback from the business are fed back to the cognitive model to tune the cognitive model to improve performance of the cognitive model.

8. The method claimed in claim 6, wherein the cognitive model is generated to perform one or more tasks independently.

9. The method claimed in claim 6, wherein the Natural Language Processing (NLP) analyzes the extracted unstructured data that comes from one or more data sources.

10. The method claimed in claim 6, wherein a big data architecture is used to handle huge amount of unstructured online data, wherein the unstructured online data is analyzed and retrieved in real time from an unstructured database.
, 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:

SYSTEM AND METHOD TO RECOMMEND OPTIMIZED ASSORTMENT FOR CONSUMER PACKAGED GOODS TO RETAILERS

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

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 a field of assortment of consumer packaged goods and, more particularly, a system and method to recommend optimized assortment for consumer packaged goods to retailers.

BACKGROUND
[002] One of the decision problems that marketing and sales planner from a consumer packaged goods (CPG) company face today is to determine the best assortment that suits the retailers. In the manual assortment creation process, the planner may miss some of the important goods that should be part of the assortment or in few cases assortment may contain unwanted goods to the retailers. Also, there is no automatic replacement recommendation in case the goods dropped or discontinued by the CPG companies. Due to this, the quality of the assortment is compromised, resulting in order amendments, returns handling, broken customer experience and loss of revenue.

[003] Most of the existing solutions use sales forecast, profit margin, etc. as an input. There are other important factors that needs to be considered while arriving at the recommendation of assortment for retailer. Some of the important factors like product affinity, product substitution, product discontinuity, localization, etc. need to be taken into account while arriving at the recommendation of consumer packaged goods for retailers. Most of the existing system use one method (or approach) to select the product assortment.

[004] Thus, solutions or platforms that uses product affinity, product substitution, product discontinuity, localization, and customer feedback etc. to arrive at the recommendation of product assortment would be appreciated.

SUMMARY
[005] Embodiments of the present disclosure provides 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 embodiment, a method and system to recommend an assortment of a plurality of consumer packaged goods to one or more retailers while considering one or more factors as product affinity, product substitution, product discontinuity, and localization. It would be appreciated that the consumer packaged goods are one of the fast moving items in the market.

[006] A processor-implemented method to recommend an assortment of a plurality of consumer packaged goods (CPG) to one or more retailers while considering one or more factors as product affinity, product substitution, product discontinuity, and localization. It would be appreciated that this is an ensemble cognitive approach to arrive at the recommendation for both structured and unstructured data sources.

[007] The method comprises one or more steps as collecting one or more business data, wherein the business data includes transaction data from one or more predefined sources and customer feedback. Further, the collected data is processed to remove one or more noises from the processed one or more business data using a predefined data correction parameters. Furthermore, generating a knowledge graph using the processed data, wherein one or more data points of the knowledge graph is represented by one or more nodes and the relation among the one or more nodes is expressed by a relation. Further, extracting one or more structured and unstructured texts from the generated knowledge graph using a natural language processing. It is to be noted that the extracted unstructured text data is also converted into a structured text data. A cognitive model is developed using the extracted structured and converted unstructured data along with a transfer learning, a machine learning, and a deep learning. Further, determining the assortment of the plurality of consumer packaged goods using the generated cognitive model and considering product affinity, product substitution, product discontinuity, localization, and customer feedback. Finally, recommending assortment of the plurality of the consumer packaged goods wherein the recommendation is done at an individual store level.

[008] A system is configured to recommend an assortment of a plurality of consumer packaged goods to one or more retailers while considering one or more factors as product affinity, product substitution, product discontinuity, and localization. The system comprising at least one memory storing a plurality of instructions and one or more hardware processors communicatively coupled with the at least one memory. The one or more hardware processors are configured to execute one or more modules comprises of a data collection module, a data processing module, a knowledge graph generation module, a data extraction module, a model development module, a determination module, and a recommendation module.

[009] The data collection module is configured to collect one or more business data, wherein the business data includes transaction data from one or more predefined sources and customer feedback. The data processing module is configured to process the collected data to remove noises from the collected one or more business data using a predefined data correction parameters. The knowledge graph generation module is configured to generate a knowledge graph using the processed data, wherein one or more data points of the knowledge graph is represented by one or more nodes and the relation among the one or more nodes is expressed by a relation. The data extraction module is configured to extract one or more structured and unstructured texts from the generated knowledge graph using a Natural Language Processing (NLP). The model development module is configured to develop a cognitive model using the extracted structured and unstructured data along with a transfer learning, a machine learning, and a deep learning technologies. The determination module is configured to determine the assortment of the plurality of consumer packaged goods using the generated cognitive model and considering product affinity, product substitution, product discontinuity, localization, and customer feedback. Finally, the recommendation module is configured to recommend assortment of the plurality of consumer packaged goods wherein the recommendation is done at an individual store level.

[010] 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
[011] 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:

[012] FIG. 1 illustrates a system to recommend an assortment of a plurality of consumer packaged goods while considering one or more factors as product affinity, product substitution, product discontinuity, and localization, in accordance with some embodiments of the present disclosure;

[013] FIG. 2 is a schematic for B2B product assortment in CPG retail industry based on ensemble approach of knowledge graph and convolution deep learning algorithms using the business data and secondary data sources, in accordance with some embodiments of the present disclosure; and

[014] FIG. 3 is a flow diagram to illustrate a method to recommend an assortment of a plurality of consumer packaged goods while considering one or more factors as product affinity, product substitution, product discontinuity, and localization, in accordance with some embodiments of the present disclosure.

[015] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems and devices embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, 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 EMBODIMENTS
[016] 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 spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.

[017] The embodiments herein provide a method and a system to recommend an assortment of a plurality of consumer packaged goods to one or more retailers while considering one or more predefined factors. Wherein the one or more predefined factors include product affinity, product substitution, product discontinuity, and localization. It would be appreciated that this is an ensemble cognitive approach to arrive at the recommendation for both structured and unstructured data sources. In addition to this, the feedback from the business is fed back to the machine learning model for further tuning of the machine learning model and that helps in performance improvement. It uses product affinity, product substitution, product discontinuity, localization, customer feedback etc. to arrive at the recommendation of product assortment for retailers. The disclosure uses cognitive approach along with transfer learning, machine learning, deep learning, and optimization methodologies to arrive at the final product recommendation. The ensemble methods to arrive at the solution recommended by a suite of algorithm at different stages of the solution approach for both structured and unstructured data sources. The ensemble approach consists of several algorithms that consumes all these data points to create recommendations for the retailers.

[018] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3, 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.

[019] FIG. 1 illustrates a system (100) to recommend an assortment of a plurality of consumer packaged goods to one or more retailers while considering one or more factors as product affinity, product substitution, product discontinuity, and localization. In the preferred embodiment, the system (100) comprises at least one memory (102) with a plurality of instructions and one or more hardware processors (104) which are communicatively coupled with the at least one memory (102) to execute modules therein.

[020] The hardware processor (104) may 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 hardware processor (104) is configured to fetch and execute computer-readable instructions stored in the memory (102). Further, the system comprises a data collection module (106), a data processing module (108), a knowledge graph generation module (110), a data extraction module (112), a model development module (114), a determination module (116), and a recommendation module (118).

[021] In the preferred embodiment of the disclosure, the data collection module (106) of the system (100) is configured to collect one or more business data. The business data includes transaction data from one or more predefined data sources and customer feedback. Some of the predefined data sources are a Point-of-sale (POS) data as the transaction data, and an aggregated data from the retailer as the customer feedback. Further, a syndicate data like Nielsen, IRI and SPINS, historical assortments recommended to the retailer, a promotion calendar, holidays events etc. (both past and future), and demographic spread from one or more data sources. Furthermore, the one or more business data includes sales data that are given as input to the system (100).

[022] In the preferred embodiment, the data collection module (106) of the system (100) also collects a set of drivers of sales together at different format and levels. It would be appreciated that the one or more predefined data sources includes an inventory management, performance processing, competition information, and store demographics. It is to be noted that the one or more predefined data sources are not limited to above list. It may also comprise market share, customer lifestyle, customer behavior, and weather and seasonality. Some of the sources such as inventory are from the retailer and some of them are from third party vendors. All the sources will have different format and different level of information.

[023] In the preferred embodiment of the disclosure, the data processing module (108) of the system (100) is configured to process the collected data to remove noises from the collected business data using predefined data correction parameters. It should be note that the collected business data may have noises as it is coming from different data sources. Therefore correction algorithms need to be used to process the collected data. The selection of the correction algorithm depends on the collected data considered for the processing.

[024] It would be appreciated that generally there are fixed kind of data available like unstructured text data, tables and charts in these areas. The fixed kind of data is parsed by a python packages and stored in a database of the system. This is happened via API and does not need any extra documents or data, so this automation reduces pain to user by not asking any extra information. This improves the user experience and brings in more business growth. Further, the collected data is processed in a level such that the sales is better explained by the causative factors. In one instance, the inventory information is aggregated at day level or week level depending on the sales explain ability by inventory. Similar approach is followed for other sales drivers. Customer lifestyle data need to be processed from the customers who visited on a particular time period and the customer behavior data need to be processed to explain the sales variation in better way.

[025] In another embodiment, wherein if the transaction data is not available then decompose the historical sales into seasons, trend and random component. Group the one or more products with same seasonal pattern and trend as items that are having great affinity. The affinity for new items that are getting introduced in the proposed assortment might not be available, to overcome this limitation, consider the affinity of new item if it is sold in another similar store and use the same in an optimization model. Generating a set of items that can be part of possible assortment and considering the sales forecast of the existing items and new items to be included. The final recommendation output from the algorithms is considered from the ensemble of several algorithms’ output.

[026] In the preferred embodiment, the knowledge graph generation module (110) of the system (100) is configured to generate a knowledge graph using the processed data. The one or more data points of the knowledge graph is represented by one or more nodes and the relation among the one or more nodes is expressed by a relation. It would be appreciated that the knowledge graph is a brain of the system (100) where an unstructured form of the collected data is processed. Further, the knowledge graph is highly efficient in terms of the search engine optimization and handling various kinds of data.

[027] In the preferred embodiment, for handling the huge amount of unstructured online data, a layer of Natural Language Processing (NLP) is needed to convert the unstructured data to structured data. Further, in order to manage the volume of the unstructured data, a big data architecture, to be implemented. For example, a Kafka is implemented to manage the volume of the unstructured data. Further herein, the unstructured data shall be analyzed and retrieved in real time from the unstructured database. The unstructured data have been converted the available data into structured form. The consolidated data is stored in a business database. The application of the knowledge graph and deep learning algorithms is implemented on the business database. The knowledge graph is used for storage and retrieval of the data in the form of nodes and edges. The machine leaning model is built on top of the knowledge graph database.

[028] In the preferred embodiment, the data extraction module (112) of the system (100) is configured to extract one or more structured and unstructured texts from the generated knowledge graph using a Natural Language Processing (NLP). The NLP algorithm extracts the unstructured data that comes from one or more data sources. Using a Structured Query Language (SQL) query, the required data that constitute the business data can be mined and several critical information including business insights can be mined as well. For every automated recommendation, the required data is retrieved from the database for generating real-time recommendations. In addition to this, a big data architecture is used to handle huge amount of unstructured online data. The unstructured online data shall be analyzed and retrieved in real time from the unstructured database.

[029] In the preferred embodiment, the model development module (114) of the system (100) is configured to develop a cognitive model using the extracted structured and unstructured data along with a transfer learning, a machine learning, and a deep learning technologies. By the transfer learning technologies, the cognitive model is trained using the data of the business of the same domain from other vendors and the data from secondary sources like business sales data in a given region. The machine learning technologies are used for developing the predictive algorithms which learn from the past business data. The deep learning technologies are a special kind of machine learning algorithms that handles the relationship of non-linear data more efficiently, which works on the principle of simulating human intelligence in computer programs. These deep learning technologies enable the capture of the knowledge of the diverse business data.

[030] In other words simultaneous consideration of all causative factors are mapped with simultaneous consideration of the product performance through machine learning technologies. This set up tries to learn the business behavior that exist in the passing information. Also the secondary sources of data is considered for the improvement of the generalization of the machine algorithm learning process.

[031] In the preferred embodiment of the disclosure, the determination module (116) of the system (100) is configured to determine the assortment of the plurality of the consumer packaged goods to one or more retailers using the generated cognitive model and considering product affinity, product substitution, product discontinuity, localization, and customer feedback. The product affinity deals with the information of the product frequency being sold versus the profit margin in each goods in the retail outlet. The product substitution means that if any kind of product is being stopped at manufacture level, then what are the other goods that can be substituted at the SKUs (Stock Keeping Units). The product discontinuity is the information of the product that are needed to be stopped in the supply, which is required for the recommendation in the real time. These information are related to the regions and customer specific and the weather data is considered as well. All these above product information is fed at the cognitive model for generating the accurate recommendation to the retail store.

[032] In the preferred embodiment, the recommendation module (118) of the system (100) is configured to recommend the assortment of the plurality of the consumer packaged goods to one or more retailers wherein the recommendation is done at an individual store level. It is to be noted that the targeted recommendation is shared with each retailer based on the machine learning algorithms. It would be appreciated that the system (100) is a dynamic and has a real time response that constitute the key feature.

[033] Referring FIG. 2, a schematic shows B2B product assortment in CPG retail industry based on an ensemble approach of the knowledge graph and machine learning algorithms using the transaction data and one or more secondary data sources. Herein, to forecast the sales by the stock-keeping-unit (SKUs) apply a rule of mining on the transaction data to capture the affinity of a set of items. The set of items are generated that can be part of possible assortment considering the sales forecast and the existing item and new items to be included. The final recommendation output from the algorithms is considered from the ensemble of several algorithms’ output. A cognitive recommendation engine of the cognitive model uses the transaction data that can track the task and behavioral patterns of the users in a given region so that it can judge the customer needs and behavior. The cognitive model is based on the creation of knowledge graph and the machine learning algorithms that uses data of the transactions and from various sources. Several machine learning algorithms are employed for the recommendation and the final recommendation is based on the ensemble output of the algorithms.

[034] Some business data are explicit and rest may be implicit data points that also includes the data from the users on daily basis. Therefore, there is a need for automated tool that can do task of data extraction very accurately and reliably. Further, an optimization is run to get the optimized assortment that maximizes revenue, margin, minimizes missing items considering constraints like localization, affinity, vendor order contracts, upcoming promotion calendar, events, product substitution, cannibalization, impact of promotion on sales etc. A dashboard reports the high margin items that are not part of present assortment recommended and their margin contribution. The dashboard presents a group of items (high, medium, and low) based on margin that are part of recommended assortment. The dashboard helps the planner to do what-if analysis to understand the impact of removing or adding an item to the proposed assortment will have on the revenue, margin, etc. Report of the historical performance of the assortment recommended in the past and identifying anomalies, outliers and issue alerts to the planner.

[035] In addition to this, the system (100) also learns how sales happens at individual product level when all the consumer packaged goods are available and when some of the consumer packaged goods are missing how the sales happens across goods while considering all other causative factors. However, this example will vary depending on how the past historical information is happened. The success of learning depends on the period of data used for learning and ideally it needs to be as long as possible and it should capture all possible scenarios that exist in real retail scenarios. There are other sources of factors like weather data and related sales data is considered. The model with learnt behavior is ready to be used to estimate sales pattern across goods for different scenarios.

[036] Referring FIG. 3, a processor-implemented method (200) to recommend an assortment of a plurality of consumer packaged goods to one or more retailers while considering one or more factors as product affinity, product substitution, product discontinuity, and localization. The method comprises one or more steps as follows.

[037] Initially, at the step (202), one or more business data are collected at a data collection module (106) of the system (100). The business data includes transaction data from one or more predefined sources and customer feedback. Some of the predefined data sources are a Point-of-sale (POS) data as the transaction data, and an aggregated data from the retailer as the customer feedback.

[038] In the preferred embodiment of the disclosure, at the next step (204), processing at a data processing module (108) of the system (100) the collected information to remove noises from the processed one or more business data using a predefined data correction parameters.

[039] In the preferred embodiment of the disclosure, at the next step (206), generating a knowledge graph using the processed data at a knowledge graph generation module (110) of the system (100). The one or more data points of the knowledge graph is represented by one or more nodes and the relation among the one or more nodes is expressed by a relation. It would be appreciated that the knowledge graph is a brain of the system (100) where an unstructured form of the collected data is processed. Further, the knowledge graph is highly efficient in terms of the search engine optimization and handling various kinds of data.

[040] In the preferred embodiment of the disclosure, at the next step (208), extracting one or more structured and unstructured texts from the generated knowledge graph using a natural language processing at an extraction module (112) of the system (100). It is to be noted that the extracted unstructured text data is also converted into a structured text data. It would be appreciated that in order to manage the volume of the unstructured data, a big data architecture, to be implemented. For example, a Kafka is implemented to manage the volume of the unstructured data.

[041] In the preferred embodiment of the disclosure, at the next step (210), develop a cognitive model using the extracted structured and converted unstructured data along with a transfer learning, a machine learning, and a convolutional deep learning technologies at a model development module (114) of the system (100).

[042] In the preferred embodiment of the disclosure, at the step (212), determining the assortment of the plurality of consumer packaged goods using the generated cognitive model and considering product affinity, product substitution, product discontinuity, localization, and customer feedback at a determination module (116) of the system (100).

[043] In the preferred embodiment of the disclosure, at the last step (214), recommending assortment of the plurality of consumer packaged goods at a recommendation module (118) of the system (100). It would be appreciated that the recommendation is done at an individual store level. It is to be noted that the targeted recommendation is shared with each retailer based on the machine learning algorithms.

[044] 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.

[045] The embodiments of present disclosure herein addresses unresolved problem of assortment of a plurality of consumer packaged goods. The reason is that in the manual assortment creation process, the planner may miss some of the important consumer packaged goods that should be part of the assortment or in few cases assortment may contain unwanted consumer packaged goods to the retailers. Also, there is no automatic replacement recommendation in case the goods dropped or discontinued by the consumer packaged goods companies. Due to this, the quality of the assortment is compromised, resulting in order amendments, returns handling, broken customer experience and loss of revenue.

[046] 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 modules 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.

[047] 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 modules described herein may be implemented in other modules or combinations of other modules. 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.

[048] 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 and spirit 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.

[049] 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.

[050] It is intended that the disclosure and examples be considered as exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims.