System and method for classification, cleansing and enrichment of a product and material master data

Abstract

A system (100) for classification, cleansing and enrichment of a product and material master data is disclosed The input module (120) receives one or more files from a user via an user interface for creation of a master data. The processing module (130) processes the one or more files by utilizing a large language model. The classification module (140) categorizes the one or more files based on a taxonomy file or a default taxonomy uploaded by the user. The cleansing module (150) assigns a plurality of characteristics corresponding to the plurality of products based on the class, subclass and the one or more files. The enrichment module (160) extracts an additional information about the plurality of products from an external source. The output module (170) provides the data of the one or more files in a plurality of formats.

Description

[0001] SYSTEM AND METHOD FOR CLASSIFICATION, CLEANSING AND ENRICHMENT OF A PRODUCT AND MATERIAL MASTER DATA

[0002] EARLIEST PRIORITY DATE:

[0003] This Application claims priority from a complete patent application filed in India having Patent Application No. 202441073890, filed on 30th day of September 2024, and titled “SYSTEM AND METHOD FOR CLASSIFICATION, CLEANSING AND ENRICHMENT OF A PRODUCT AND MATERIAL MASTER DATA”.

[0004] FIELD OF INVENTION

[0005] Embodiments of the present disclosure relate to the field of master data management, and more particularly, system and method for classification, cleansing and enrichment of a product and material master data.

[0006] BACKGROUND

[0007] Traditionally, material master data in an organization includes a vast array of items such as bearings, motors, gearboxes, valves, and other components. When creating entries of the items in an Enterprise Resource Planning (ERP) system, these entries often lack standardization, leading to inconsistencies in descriptions or information of the items, missing manufacturer details, and poor data organization as an inventory grows. Over time, this results in difficulties tracking existing materials, causing inefficiencies such as duplicate entries, missing out on vendor discounts, and compliance challenges. When an organization attempts to order the items, inability to accurately search for the correct items due to vague or inconsistent descriptions can lead to unnecessary procurement of the items that are already in stock. To address above mentioned issues, a user manually classifies and cleans the descriptions of the items and assign them to predefined categories based on gathered manufacturer details. This classification is often supported by data dictionaries, from which the user selects appropriate class and characteristics for the items. However, this manual process is time-consuming and resource-intensive, often resulting in delays and inaccuracies in the material management. The inefficiencies caused by poor material data quality significantly impact inventory management, procurement processes, and overall operational effectiveness.

[0008] Hence, there is a need for an improved system for management of master data which addresses the aforementioned issue(s).

[0009] OBJECTIVE OF THE INVENTION

[0010] An objective of the invention is to automate classification, cleansing and enrichment of an unstructured data to achieve accurate and efficient management of material or product master data.

[0011] Another objective of the invention is to utilize a large language model to achieve efficiency and adaptability in the process.

[0012] Yet, another objective of the invention is to facilitate sourcing of additional information from an external source on an internet, thereby enhancing data richness and completeness of the master data.

[0013] Yet, another objective of the invention is to allow the user to process either one material record at a time (real-time mode), or a large volume of multiple material records (batch mode) thereby enabling creation of the product or master data during initial creation process and the latter enabling cleansing and enriching historical data.

[0014] Yet, an objective of the invention is to provide the user interface that facilitates the output of data in a plurality of formats (hypertext markup language (HTML page), or excel file download, or application programming interface (API)), thereby enhancing flexibility and accessibility of the processed data for various user needs and system integrations. Another objective of the invention is to provide flexibility to the user to either use the user own taxonomy file (data dictionary / data model) or use the default taxonomy file for processing.

[0015] BRIEF DESCRIPTION

[0016] In accordance with an embodiment of the present disclosure, a system for classification, cleansing and enrichment of a product and material master data is provided. The system includes a processing subsystem hosted on a server. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes an input module configured to receive one or more files from a user via an user interface for creation of a material master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files includes information of a plurality of products in an unstructured format. The processing subsystem includes a processing module operatively coupled to the input module wherein the processing module is configured to process the one or more files by utilizing a large language model wherein the large language model is enabled with subject matter expert prompts and sequence and trained on a plurality of datasets. The processing module includes a classification module configured to categorize the one or more files based on a taxonomy file uploaded by the user or a default taxonomy. Further, the classification module is configured to assign a class and a subclass corresponding to the plurality of products. The processing module includes a cleansing module operatively coupled to the classification module wherein the cleansing module is configured to assign a plurality of attribute names corresponding to the class and the subclass of the plurality of products. Further, the cleansing module is configured to generate an plurality of attribute values for corresponding the plurality of attribute names, from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or default taxonomy. Furthermore, the processing module includes an enrichment module operatively coupled to the cleansing module wherein the enrichment module is configured to search and extract additional information about the plurality of products from an plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors. Further, the enrichment module is configured to integrate the additional information into the corresponding the plurality of products’ attribute values, for enhancing data richness and completeness. The processing subsystem includes an output module operatively coupled to the processing module wherein the output module is configured to provide the data of the one or more files in a plurality of formats. Further, the output module is configured to facilitate seamless integration of the data with an enterprise system via an application programming interface.

[0017] In accordance with another embodiment of the present disclosure, a method for classification, cleansing and enrichment of a product and material master data is provided. The method includes receiving, by an input module, one or more files from a user via an user interface for creation of a master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files includes information of a plurality of products in an unstructured format. The method also includes processing, by a processing module, the one or more files by utilizing a large language model wherein the large language model is enabled with a subject matter expert prompts and sequence and trained on a plurality of datasets. Further, the method includes categorizing, by a classification module, the one or more files based on a taxonomy file uploaded by the user or a default taxonomy. Furthermore, the method includes assigning, by the classification module, a class and a subclass to corresponding to the plurality of products. Moreover, the method includes assigning, by a cleansing module, a plurality of attribute names corresponding to the class, subclass of the plurality of products. Additionally, the method includes generating, by the cleansing module, the plurality of attribute values to the corresponding plurality of attribute names from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or a default taxonomy. Further, the method includes searching and extracting, by an enrichment module, an additional information about the plurality of products from a plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors. Furthermore, the method includes integrating, by the enrichment module, the additional information into the corresponding plurality of products attribute names for enhancing data richness and completeness. The method includes providing, by an output module, the data of the one or more files in a plurality of formats. The method also includes facilitating, by the output module, seamless integration of the data with an enterprise system via an application programming interface.

[0018] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.

[0019] BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:

[0021] FIG. 1 is a block diagram representation of a system for classification, cleansing and enrichment of a product and material master data with an embodiment of the present disclosure;

[0022] FIG. 2 is a block diagram of an exemplary embodiment of system for classification, cleansing and enrichment of a product and material master data in accordance with an embodiment of the present disclosure; FIG. 3 is a block diagram of a computer or a server in accordance with an embodiment of the present disclosure; and

[0023] FIG. 4 illustrates a flow chart representing the steps involved in a method for classification, cleansing and enrichment of a product and material master data in accordance with an embodiment of the present disclosure.

[0024] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.

[0025] DETAILED DESCRIPTION

[0026] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.

[0027] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or subsystems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

[0029] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.

[0030] Embodiments of the present disclosure relates to classification, cleansing and enrichment of a product and material master data. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes an input module configured to receive one or more files from a user via an user interface for creation of a material master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files includes information of a plurality of products in an unstructured format. The processing subsystem includes a processing module operatively coupled to the input module wherein the processing module is configured to process the one or more files by utilizing a large language model wherein the large language model is enabled with subject matter expert prompts and sequence and trained on a plurality of datasets. The processing module includes a classification module configured to categorize the one or more files based on a taxonomy file uploaded by the user or a default taxonomy. Further, the classification module is configured to assign a class and a subclass corresponding to the plurality of products. The processing module includes a cleansing module operatively coupled to the classification module wherein the cleansing module is configured to assign a plurality of attribute names corresponding to the class and the subclass of the plurality of products. Further, the cleansing module is configured to generate an plurality of attribute values for corresponding the plurality of attribute names, from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or default taxonomy. Furthermore, the processing module includes an enrichment module operatively coupled to the cleansing module wherein the enrichment module is configured to search and extract additional information about the plurality of products from a plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors. Further, the enrichment module is configured to integrate the additional information into the corresponding the plurality of products’ attribute values, for enhancing data richness and completeness. The processing subsystem includes an output module operatively coupled to the processing module wherein the output module is configured to provide the data of the one or more files in a plurality of formats. Further, the output module is configured to facilitate seamless integration of the data with an enterprise system via an application programming interface.

[0031] FIG. 1 is a block diagram for classification, cleansing and enrichment of a product and material master data is provided in accordance with an embodiment of the present disclosure. The system (100) includes a processing subsystem (105) hosted on a server (108). In one embodiment, the server (108) may include a cloud-based server. In another embodiment, parts of the server (108) may be a local server coupled to a user device (not shown in FIG.l). The processing subsystem (105) is configured to execute on a network (112) to control bidirectional communications among a plurality of modules. In one example, the network (112) may be a private or public local area network (LAN) or Wide Area Network (WAN), such as the Internet. In another embodiment, the network (112) may include both wired and wireless communications according to one or more standards and / or via one or more transport mediums. In one example, the network (112) may include wireless communications according to one of the 802.11 or Bluetooth specification sets, or another standard or proprietary wireless communication protocol. In yet another embodiment, the network (112) may also include communications over a terrestrial cellular network, including, a global system for mobile communications (GSM), code division multiple access (CDMA), and / or enhanced data for global evolution (EDGE) network.

[0032] The processing subsystem (105) includes an input module (120), a processing module (130), a classification module (140), a cleansing module (150), an enrichment module (160), and an output module (170).

[0033] The input module (120) is configured to receive one or more files from a user via an user interface for creation of master data. Examples of the master data includes, but is not limited to the following:

[0034] • Materials purchased from various manufacturers: The Master data includes contain details about raw materials, sourced from specific suppliers. This would include data like material grade, and supplier name.

[0035] • Parts and components: Products like bearings, motors, gearboxes, and valves are examples of physical components for which the master data records part numbers, dimensions, material composition, manufacturer details, warranty information, and maintenance schedules.

[0036] • Supplier information: The master data captures details about suppliers, including supplier name, catalogue or part number.

[0037] The one or more files are uploaded in a real-time or a batch mode. The one or more files includes information of a plurality of products in an unstructured format. Typically, the unstructured format refers to a data format that includes information about the plurality of products in a non-standardized, non-tabular manner, potentially combining various aspects of details of the plurality of products an inconsistent or intermingled fashion. The unstructured format of the plurality of products includes, but is not limited to, product descriptions containing manufacturer details interspersed within general descriptions, technical specifications embedded within vendor information, or any combination of product attributes presented without a consistent, predefined structure. The unstructured format poses challenges for traditional data processing methods, necessitating advanced techniques for accurate information extraction and categorization.

[0038] The processing module (130) is operatively coupled to the input module (120). The processing module (130) is configured to process the one or more files by utilizing a large language model that is enabled with subject matter expert prompts and sequence. Typically, the subject matter expert prompts refer to a set of specialized instructions and guidelines used when invoking the large language model. The subject matter expert prompts encapsulate domain-specific knowledge and best practices for processing the plurality of products and the material master data. Examples of the subject matter expert prompts includes, but is not limited to, instructions for parsing product descriptions according to predefined attribute structures, methods for standardizing attribute values across various product categories, techniques for merging data extracted from external internet sources with input data, and protocols for resolving conflicts or inconsistencies in product information. Further, the subject matter expert prompts enables the system to process and interpret complex, domain-specific information with a level of nuance and accuracy that mimics the expertise of a human subject matter expert in a field of the product and material data management.

[0039] Typically, the large language model is an artificial intelligence system trained on billions of data points to understand human language. Further, the large language model processes the unstructured data by recognizing patterns, extracting meaningful information, and transforming the data into useful formats. The large language model is trained on a plurality of datasets from an internet. Examples of the plurality of datasets trained by the large language model includes, but is not limited to articles, technical documentation, product catalogs, and manuals. The plurality of datasets enables the large language model to develop a deep understanding of language, allowing to interpret complex product descriptions, specifications, and even free-form text in the one or more files uploaded by the user.

[0040] The processing module (130) includes a classification module (140), a cleansing module (150), and an enrichment module (160).

[0041] The classification module (140) is configured to categorize the one or more files based on a taxonomy file uploaded by the use or a default taxonomy. The taxonomy file includes a class and a subclass of the plurality of products. The classification module (140) is also configured to assign a class and a subclass to corresponding to the plurality of products. For example, the class is a motor, and the subclass is a alternating current (AC) motor.

[0042] The cleansing module (150) is operatively coupled to the classification module (140). The cleansing module (150) is configured to assign a plurality of attribute names to the class and the subclass of the plurality of files. The cleansing module (150) is also configured to generate a plurality of attribute values form the plurality of products from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or the default taxonomy. Examples of the plurality of attribute names of the motor includes, but is not limited to, power output (130 kW), voltage rating (24V), efficiency (70% efficiency), and manufacturer details. For example, the plurality of attribute names and the plurality of attribute values for the DC motor is as follows:

[0043]

[0044] The enrichment module (160) is operatively coupled to the cleansing module (150). The enrichment module (160) is configured to search and extract an additional information about the plurality of products from a plurality of external sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors. Typically, from the manufacturer website. Further, the enrichment module (160) is also configured to integrate the additional information into the corresponding plurality of products attribute names for enhancing data richness and completeness. For example, consider the DC motor that is already in the one or more files with basic details like: power output: 140 kW and voltage: 24V. The enrichment module (160) retrieves additional information from the manufacturer’s website, such as weight: 12 kg, IP Rating: IP65 and Operating Temperature Range: - 20°C to 70°C.

[0045] The output module (170) is operatively coupled to the processing module (130). The output module (170) is configured to provide the data of the one or more files in a plurality of formats. The output module (170) is also configured to facilitate seamless integration of the data with an enterprise system via an application programming interface, thereby allowing the enterprise system to easily access and utilize the data without manual intervention, ensuring that the data is readily available for various business operations, such as inventory management, procurement, or reporting, by directly communicating with other software systems in a smooth and automated manner.

[0046] FIG. 2 is a block diagram of an exemplary embodiment of system for classification, cleansing and enrichment of a product and material master data in accordance with an embodiment of the present disclosure Further, the processing subsystem (105) includes a cloud module (180) operatively coupled to the processing module (130). The cloud module (180) is configured to enable handling of the processed data through a cloudbased deployment.

[0047] In an example, consider a scenario, user X creates a comprehensive material master data for a wide range of products, such as motors, bearings, and valves, to improve an industry inventory management system. The user X uploads the one or more files containing details of the plurality of products in an unstructured format (like text documents and spreadsheets) via the system’s input module (120), either in real-time mode or batch mode. The one or more files include information on thousands of the plurality of products from various suppliers. The processing module (130) leverages the large language model to interpret the data and classify the plurality of products based on the taxonomy file or the default taxonomy files uploaded by the user X. The classification module (140) assigns appropriate class (e.g., Motors) and the subclass (e.g., DC Motors) to each of the plurality of product. The cleansing module (150) then assigns specific characteristics, such as voltage, power output, and dimensions, generating the attribute name and the attribute value for each product category. The enrichment module (160) pulls additional information, such as operating temperature ranges and IP ratings, from the manufacturer website and integrates this into the product records to enhance the data richness and completeness. Finally, the output module (170) formats the data into various formats like hypertext markup language, excel file download, application programming interface, CSV and JSON and integrates it seamlessly with the User X’s enterprise resource planning (ERP) system via an API, enabling real-time updates to the company’s inventory system.

[0048] FIG. 3 is a block diagram of a computer or a server in accordance with an embodiment of the present disclosure. The server (108) includes processor(s) (230), and memory (210) operatively coupled to the bus (220). The processor(s) (230), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.

[0049] The memory (210) includes several subsystems stored in the form of executable program which instructs the processor (230) to perform the method steps illustrated in FIG. 1. The memory (210) includes a processing subsystem (105) of FIG.l. The processing subsystem (105) further has following modules: the input module (120), the processing module (130), the classification module (140), the cleansing module (150), the enrichment module (160), and the output module (170).

[0050] The input module (120) configured to receive one or more files from a user via an user interface for creation of a material master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files includes information of a plurality of products in an unstructured format. The processing subsystem (105) includes a processing module (130) operatively coupled to the input module (120) wherein the processing module (130) is configured to process the one or more files by utilizing a large language model wherein the large language model is enabled with subject matter expert prompts and sequence and trained on a plurality of datasets. The processing module (130) includes a classification module (140) configured to categorize the one or more files based on a taxonomy file uploaded by the user or a default taxonomy. Further, the classification module (! 40) is configured to assign a class and a subclass corresponding to the plurality of products. The processing module (140) includes a cleansing module (150) operatively coupled to the classification module (140) wherein the cleansing module (150) is configured to assign a plurality of attribute names corresponding to the class and the subclass of the plurality of products. Further, the cleansing module (150) is configured to generate an plurality of attribute values for corresponding the plurality of attribute names, from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or default taxonomy. Furthermore, the processing module (130) includes an enrichment module (160) operatively coupled to the cleansing module (150) wherein the enrichment module (160) is configured to search and extract additional information about the plurality of products from a plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors. Further, the enrichment module (!60) is configured to integrate the additional information into the corresponding the plurality of products’ attribute values, for enhancing data richness and completeness. The processing subsystem (105) includes an output module (170) operatively coupled to the processing module (130) wherein the output module (170) is configured to provide the data of the one or more files in a plurality of formats. Further, the output module (170) is configured to facilitate seamless integration of the data with an enterprise system via an application programming interface.

[0051] The bus (220) as used herein refers to internal memory channels or computer network that is used to connect computer components and transfer data between them. The bus (220) includes a serial bus or a parallel bus, wherein the serial bus transmits data in bitserial format and the parallel bus transmits data across multiple wires. The bus (220) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus, and the like.

[0052] FIG. 4 illustrates a flow chart representing the steps involved in a method for classification, cleansing and enrichment of a product and material master data in accordance with an embodiment of the present disclosure. The method (300) includes receiving, by an input module, one or more files from a user via a user interface for creation of a master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files includes information of a plurality of products in an unstructured format in step 310. In one embodiment, the user is allowed to select a combination of the classification module (140), cleansing module (150) and the enrichment module (160) in the processing module (130) based on requirement.

[0053] The method (300) also includes processing, by a processing module, the one or more files by utilizing a large language model wherein the large language model is enabled with a subject matter expert prompts and sequence and trained on a plurality of datasets in step 320.

[0054] In one embodiment, the large language model is trained on the plurality of datasets ensuring contextual understanding and adaptability of the information stored in the one or more files.

[0055] In one embodiment, the processing module (130) is configured to optimize management of the plurality of products for asset-heavy industries and enterprises.

[0056] Further, the method (300) includes categorizing, by a classification module, the one or more files based on a taxonomy file uploaded by the user or a default taxonomy in step 330.

[0057] The method (300) includes assigning, by the classification module a class and a subclass to corresponding to the plurality of products in step 340.

[0058] The method (300) also includes assigning, by a cleansing module, a plurality of attribute names corresponding to the class, subclass of the plurality of products in step 350.

[0059] In one embodiment, the cleansing module (150) is configured to identify and rectify inaccuracies while standardizing the one or more files.

[0060] Further, the method (300) includes generating, by the cleansing module, a plurality of attribute values to the corresponding plurality of attribute names from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or a default taxonomy in step 360.

[0061] Furthermore, the method (300) includes searching and extracting, by an enrichment module, an additional information about the plurality of products from a plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors in step 370.

[0062] Additionally, the method (300) includes integrating, by the enrichment module, the additional information into the corresponding plurality of products attribute names for enhancing data richness and completeness in step 380.

[0063] Further, the method (300) includes providing, by an output module, the data of the one or more files in a plurality of formats in step 390.

[0064] In one embodiment, the plurality of formats includes at least one of the real-time display, batch download, application programming interface response of the processed data.

[0065] Furthermore, the method (300) includes facilitating, by the output module, seamless integration of the data with an enterprise system via an application programming interface in step 400.

[0066] Various embodiments of the system for classification, cleansing and enrichment of a product and material master data and a method thereof as described above automates the classification, enrichment, and cleansing of the master data, significantly reduces manual effort and minimizes errors. By organizing the data through automatic categorization into detailed classes and subclasses, it ensures the user can easily locate and utilize information. Further, the cleansing module (150) enhances quality of the data by identifying and correcting errors, while the enrichment module (160) adds valuable details from external sources (manufacturer website), making the data more comprehensive. The output module (170) provides flexible output options, including real-time displays and downloadable files, facilitating easy integration into various systems. With cloud-based deployment, it offers scalable and accessible data management, and the large language model ensures accurate, contextually relevant processing of unstructured data.

[0067] The techniques described in this disclosure may be implemented, at least in part, in hardware, software, firmware, or any combination thereof. For example, various aspects of the described techniques may be implemented within one or more processors, including one or more microprocessors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or any other equivalent integrated or discrete logic circuitry, as well as any combinations of such components. The term “processor” or “processing subsystem” may generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry, or any other equivalent circuitry. A control unit including hardware may also perform one or more of the techniques of this disclosure.

[0068] Such hardware, software, and firmware may be implemented within the same device or within separate devices to support the various techniques described in this disclosure. In addition, any of the described units, modules, or components may be implemented together or separately as discrete but interoperable logic devices. Depiction of different features as modules or units is intended to highlight different functional aspects and does not necessarily imply that such modules or units must be realized by separate hardware, firmware, or software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware, firmware, or software components, or integrated within common or separate hardware, firmware, or software components. It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.

[0069] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0070] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, the order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

Claims

WE CLAIM:

1. A system (100) for classification, cleansing and enrichment of a product and material master data comprising: a processing subsystem (105) hosted on a server (108) wherein the processing subsystem (105) is configured to execute on a network (115) to control bidirectional communications among a plurality of modules comprising: characterized in that, an input module (120) configured to receive one or more files from a user via an user interface for creation of a material master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files includes information of a plurality of products in an unstructured format; a processing module (130) operatively coupled to the input module (120) wherein the processing module (130) is configured to process the one or more files by utilizing a large language model wherein the large language model is enabled with a subject matter expert prompts and sequence and trained on a plurality of datasets wherein the processing module (130) comprises: a classification module (140) configured to: categorize the one or more files based on a taxonomy file uploaded by the user or a default taxonomy; and assign a class and a subclass to corresponding to the plurality of products; a cleansing module (150) operatively coupled to the classification module (140) wherein the cleansing module (150) is configured to:assign a plurality of attribute names corresponding to the class, subclass of the plurality of products; and generate a plurality of attribute values to the corresponding plurality of attribute names from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or a default taxonomy; an enrichment module (160) operatively coupled to the cleansing module (150) wherein the enrichment module (160) is configured to: search and extract an additional information about the plurality of products from an plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors; and integrate the additional information into the corresponding plurality of products attribute names for enhancing data richness and completeness; and an output module (170) operatively coupled to the processing module (130) wherein the output module (170) is configured to: provide the data of the one or more files in a plurality of formats; and facilitate seamless integration of the data with an enterprise system via an application programming interface.

2. The system (100) as claimed in claim 1, wherein the processing module (130) is configured to optimize management of the plurality of products for asset-heavy industries and enterprises.

3. The system (100) as claimed in claim 1, wherein the cleansing module (150) is configured to identify and rectify inaccuracies while standardizing the one or more files.

4. The system (100) as claimed in claim 1, wherein the plurality of formats comprises at least one of the real-time display, batch download, application programming interface response of the processed data.

5. The system (100) as claimed in claim 1, comprises a cloud module (180) operatively coupled to the processing module (130) wherein the cloud module (180) is configured to enable handling of the processes data through a cloud-based deployment.

6. The system (100) as claimed in claim 1, wherein the large language model is trained on the plurality of datasets ensuring contextual understanding and adaptability of the information stored in the one or more files.

7. The system (100) as claimed in claim 1, wherein the user is allowed to select a combination of the classification module (140), cleansing module (150) and the enrichment module (160) in the processing module (130) based on requirement.

8. A method (300) for classification, cleansing and enrichment of a product and material master data comprising: characterized in that, receiving, by an input module, one or more files from a user via an user interface for creation of a master data, wherein the one or more files are uploaded in a real-time or a batch mode, wherein the one or more files comprises information of a plurality of products in an unstructured format; (310)processing, by a processing module, the one or more files by utilizing a large language model wherein the large language model is enabled with a subject matter expert prompts and sequence and trained on a plurality of datasets; (320) categorizing, by a classification module, the one or more files based on a taxonomy file uploaded by the user or a default taxonomy; (330) assigning, by the classification module a class and a subclass to corresponding to the plurality of products; (340) assigning, by a cleansing module, a plurality of attribute names corresponding to the class, subclass of the plurality of products; (350) generating, by the cleansing module, a plurality of attribute values to the corresponding plurality of attribute names from the plurality of products followed by standardizing the plurality of attribute values in a format based on the taxonomy file or a default taxonomy; (360) searching and extracting, by an enrichment module, an additional information about the plurality of products from a plurality of sources on an internet, prioritizing a catalog of respective manufacturer of the plurality of products or leading reputed industrial distributors; (370) integrating, by the enrichment module, the additional information into the corresponding plurality of products attribute names for enhancing data richness and completeness; (380) providing, by an output module, the data of the one or more files in a plurality of formats; (390) andfacilitating, by the output module, seamless integration of the data with an enterprise system via an application programming interface. (400)

Images