Description:FIELD OF INVENTION
The present invention relates to identifying dependencies and relationships between disparate business applications. More particularly, it relates to a system and method of identifying dependencies and relationships between disparate systems, enabling the systems using advanced techniques such as machine learning, large language models (LLMs), and historical data.

BACKGROUND
Modern organizations rely on numerous business systems and applications, such as Customer Relationship Management (CRM) tools, code repositories, and task management platforms. These systems, though designed for specialized purposes, are often interconnected, with workflows and decisions depending on their seamless interaction. However, understanding the dependencies and relationships between these disparate systems remains a significant challenge. The inability to visualize and analyze these interdependencies affects decision-making and hampers the ability to optimize workflows.
Traditionally, identifying these relationships relied on manual processes and human expertise, which were time-consuming, inconsistent, and prone to errors. These methods lacked a standardized approach and the ability to handle large volumes of data generated by modern systems. The growing complexity of enterprise environments further highlighted the limitations of such methods.
PRIOR ART
US11816636B2 discloses techniques for mining training data to train dependency models, primarily focusing on co-occurrence patterns and skills in datasets. Although this approach is effective for training models, it lacks integration with context graphs or probabilistic ranking to validate dependencies comprehensively, which the present invention achieves.
EP3944127A1 discusses creating dependency graphs for natural language processing, emphasizing semantic tagging and pipeline optimization. However, its scope is limited to NLP tasks and does not extend to broader enterprise system dependencies, as addressed by the present system.
US11681914B2 describes multivariate time-series analysis using attention mechanisms. This approach uncovers data dependencies with uncertainty measures but does not incorporate contextual graphs or machine learning models fine-tuned for entity-level relationship determination.
The present invention addresses these challenges by leveraging advanced techniques such as machine learning, large language models (LLMs), and historical data analysis to automate the identification of relationships and dependencies; thereby providing a robust and efficient solution for optimizing workflows and enabling seamless integration across diverse systems.

DEFINITIONS:
The expression “system” used hereinafter in this specification refers to an ecosystem comprising, but is not limited to an scoring system with a user, input and output devices, processing unit, plurality of mobile devices, a mobile device-based application to identify dependencies and relationships between diverse businesses, a visualization platform, and output; and is extended to computing systems like mobile, laptops, computers, PCs, etc.
The expression “input unit” used hereinafter in this specification refers to, but is not limited to, mobile, laptops, computers, PCs, keyboards, mouse, pen drives or drives.
The expression “output unit” used hereinafter in this specification refers to, but is not limited to, an onboard output device, a user interface (UI), a display kit, a local display, a screen, a dashboard, or a visualization platform enabling the user to visualize, observe or analyse any data or scores provided by the system.
The expression “processing unit” refers to, but is not limited to, a processor of at least one computing device that optimizes the scoring system.

OBJECTS OF THE INVENTION:
The primary object of the present invention is to provide a system and method of identifying dependencies and relationships between disparate systems.
Yet another object of the present invention is to enable the identification of intrinsic attributes to facilitate their effective utilization.
Yet another object of the present invention is to implement an innovative mechanism for constructing graphical representations to illustrate interconnections, dependencies, and hierarchical arrangements among diverse entities.
Yet another object of the present invention is to incorporate probabilistic and analytical techniques to validate and rank the interrelationships between entities based on contextual and sequential data.
Further, the object of the present invention is to provide an advanced framework for identifying latent interdependencies within entities to enhance operational efficiency and decision-making processes.

SUMMARY
Before the present invention is described, it is to be understood that the present invention is not limited to specific methodologies and materials described, as these may vary as per the person skilled in the art. It is also to be understood that the terminology used in the description is for the purpose of describing the particular embodiments only and is not intended to limit the scope of the present invention.
The invention relates to a system and method for identifying dependencies and relationships between disparate business applications and systems. By leveraging advanced techniques such as machine learning, large language models (LLMs), and historical data analysis, the system automates the identification and visualization of dependencies, providing a more efficient solution than traditional manual methods. It includes components like a data ingestion module, an attribute extraction module, a reverse engineering module, and a context-graph construction module, all working together to process data from various business tools like CRM platforms, task management systems, and code repositories. The system analyzes incoming data, extracts key attributes, and constructs a graphical representation to visualize interdependencies and hierarchies.
Thus, the present invention addresses the challenges faced by modern organizations in understanding the complex relationships between their interconnected systems. Traditional dependency identification methods often relied on inconsistent manual processes, which were prone to errors and inefficiencies. By applying probabilistic and analytical techniques, the present invention enables the automated identification of dependencies, improving decision-making and optimizing workflows. The system's output includes detailed reports with dependency maps and actionable insights, helping organizations streamline their operations and improve overall efficiency by enhancing system integration.

BRIEF DESCRIPTION OF DRAWINGS
FIG. 1 illustrates an overview of the system of the present invention.
FIG. 2 illustrates the components of the system
FIG. 3 illustrates the method encompassing Data Packet Ingestion, Attribute Extraction Using LLMs, Reverse Engineering, Context-Graph Construction, Correlation Analysis, and Output Generation.

DETAILED DESCRIPTION OF INVENTION:
Before the present invention is described, it is to be understood that this invention is not limited to methodologies described, as these may vary as per the person skilled in the art. It is also to be understood that the terminology used in the description is for the purpose of describing the particular embodiments only and is not intended to limit the scope of the present invention. Throughout this specification, the word “comprise”, or variations such as “comprises” or “comprising”, will be understood to imply the inclusion of a stated element, integer or step, or group of elements, integers or steps, but not the exclusion of any other element, integer or step, or group of elements, integers or steps. The use of the expression “at least” or “at least one” suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the invention to achieve one or more of the desired objects or results. Various embodiments of the present invention are described below. It is, however, noted that the present invention is not limited to these embodiments, but rather the intention is that modifications that are apparent are also included.
To understand the invention clearly, the various components of the system are referred as below:

No. Component
10 System
100 Input unit
200 Processing unit
300 Output unit
210 Data Packet Ingestion Module
220 Attribute Extraction Module
230 Reverse Engineering Module
240 Context-Graph Construction Module
250 Correlation Analysis Module
260 Dependency Analysis Module
270 Output Generation Module
400 Method

The present invention is directed to a system and method for identifying dependencies and relationships between disparate business systems and applications, wherein the system (10) comprises an input unit (100), a processing unit (200) further comprising a data packet ingestion module (210), an attribute extraction module (220) utilizing large language models (LLMs), a reverse engineering module (230), a context-graph construction module (240), a correlation analysis module (250), a dependency analysis module (260), and an output generation module (270) and an output unit (300). The system operates to analyze incoming data packets from various business systems, extract attributes such as source, type, and intent using fine-tuned LLMs, and construct a context-graph to visualize relationships and dependencies. By employing probabilistic ranking and sequential analysis, the system (10) identifies matches and establishes dependency hierarchies, enabling organizations to optimize workflows and decision-making processes.
According to a preferred embodiment, the data packet ingestion module (210) acts as the primary interface for collecting data packets from disparate systems, such as customer relationship management (CRM) tools, code repositories, and task management platforms. The module captures and organizes incoming data, ensuring that all relevant information is prepared for subsequent processing.
According to another embodiment, the attribute extraction module (220) employs fine-tuned LLMs to derive key attributes from data packets, including the source of the packet, its type (e.g., ticket, pull request), and intent (e.g., feature request, bug fix). This module ensures a structured representation of each data packet, facilitating accurate analysis and mapping of relationships.
According to yet another embodiment, the reverse engineering module (230) identifies underlying entities and links them to their corresponding attributes. This process establishes the intent and context of each data packet, forming the foundation for constructing the context-graph.
According to a further embodiment, the context-graph construction module (240) visualizes the extracted relationships, showing dependencies, hierarchies, and interactions among entities. This representation enables administrators and decision-makers to understand complex interdependencies and prioritize actions accordingly.
In yet another embodiment, the correlation analysis module (250) applies probabilistic ranking and sequential analysis to determine the best matches among data packets; and identifies precise relationships, ensuring robust and accurate results by integrating probabilities with timelines.
According to another embodiment, the dependency analysis module (260) employs advanced algorithms to uncover and quantify dependencies between packets. This module uses techniques such as the shortest path analysis to identify sequences and hierarchies within the data, providing a clear view of the system's operational flow.
In a further embodiment, the output generation module (270) delivers detailed reports containing relationship maps, dependency hierarchies, and actionable recommendations. These outputs help organizations prioritize system (10) updates and enhance their overall efficiency.
In another preferred embodiment of the invention, a method (400) for identifying dependencies and relationships between disparate business systems and applications, enabling the system to evaluate, analyze, and derive insights into interdependencies and relationships, is disclosed. The method (400) comprises the following steps:
1. Data Packet Ingestion Module (210):
The present module initiates the process by systematically collecting data packets from disparate business systems, such as CRM platforms, code repositories, and task management tools. The module is configured to parse and extract key attributes such as origin, type, and context from the ingested data. These attributes are then organized into a structured format, such as a table or dataset, facilitating downstream modules' processing. The output of this module serves as an input for subsequent stages of analysis.
2. Attribute Extraction Module (220):
This module employs fine-tuned large language models (LLMs) to derive detailed attributes from each data packet. The process involves: (a) identifying the source of the packet (e.g., CRM, code repository); (b) classifying the type of packet (e.g., pull request, ticket); and (c) determining the intent of the packet (e.g., feature request, bug fix). Extracted attributes are represented in a structured format, ensuring efficient downstream analysis. The extracted attributes feed into downstream modules, enabling processes such as Candidate Validation and Probable List Generation to optimize and refine dependency mapping.
3. Reverse Engineering Module (230):
The reverse engineering module (230) identifies and links underlying entities within the data packets, such as user IDs or system components, to their associated attributes. This module establishes the context and intent of each data packet, forming the foundation for constructing the relationship map in subsequent modules.
4. Context-Graph Construction Module (240):
The context-graph construction module (240) visualizes the relationships and dependencies extracted from the data packets. Using the entities and attributes identified earlier, the module generates a graph that represents dependencies, hierarchies, and interactions among the components. This graph provides a clear and actionable view of interdependencies for system administrators.
5. Correlation Analysis Module (250):
The process involves calculating probabilities for potential matches and confirming relationships based on timelines and contextual attributes. A Probable List Generation step is incorporated, generating ranked lists of potential dependencies based on confidence scores and historical patterns. This step ensures that the most relevant matches are prioritized for subsequent analysis. Furthermore, the module employs Sequential Analysis techniques to analyze temporal relationships and validate the order of interdependent activities, enhancing the depth of the analysis.
6. Dependency Analysis Module (260):
The dependency analysis module (260) applies advanced algorithms to evaluate dependencies and sequences within the data. It includes a Candidate Validation process, which confirms the relevance and accuracy of identified dependencies. This validation leverages probabilistic models and contextual analysis to ensure that each relationship is precise and actionable. By incorporating sequential analysis, the module traces and validates the chronological and operational sequences within workflows. This structured approach enhances the clarity and reliability of the identified dependencies, providing actionable insights.
7. Output Generation Module (270):
This module generates a comprehensive evaluation report detailing the identified dependencies, relationships, and hierarchies. The report includes actionable insights and recommendations for optimizing workflows and resolving bottlenecks. It serves as a critical tool for decision-makers to enhance system integration and efficiency.
The present invention provides several advantages, as it revolutionizes the identification of dependencies and relationships between disparate business systems and applications by introducing a structured, data-driven analytical approach instead of relying on manual or fragmented assessments. Through its components, such as the data packet ingestion module (210), attribute extraction module (220) utilizing large language models (LLMs), reverse engineering module (230), context-graph construction module (240), correlation analysis module, dependency analysis module (260), and the output generation module (270), the invention ensures precise identification, actionable insights, and consistent evaluation across diverse systems. This approach addresses the limitations of traditional methods, offering a robust solution for modern enterprises to analyze, integrate, and optimize their system (10) interdependencies effectively.

While considerable emphasis has been placed herein on the specific elements of the preferred embodiment, it will be appreciated that many alterations can be made and that many modifications can be made in preferred embodiment without departing from the principles of the invention. These and other changes in the preferred embodiments of the invention will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the invention and not as a limitation.
, Claims:CLAIMS:
We claim,
1. A system and method (400) for identifying dependencies and relationships between disparate business systems and applications;
wherein the system (10) comprises an input unit (100), a processing unit (200) further comprising a data packet ingestion module (210), an attribute extraction module (220) utilizing large language models (LLMs), a reverse engineering module (230), a context-graph construction module (240), a correlation analysis module (250), a dependency analysis module (260), an output generation module (270), and an output unit (300);
characterized in that:
the data packet ingestion module (210) systematically collects and organizes data packets from disparate systems, including CRM platforms, code repositories, and task management tools, to ensure compatibility with subsequent analysis processes;
the attribute extraction module (220) employs fine-tuned LLMs to identify and extract attributes such as source, type, and intent from the data packets, providing a structured representation for further analysis;
the reverse engineering module (230) identifies underlying entities and links them to extracted attributes, establishing context and intent for each data packet;
the context-graph construction module (240) creates a graph-based visualization of the relationships and dependencies among identified entities, highlighting hierarchies and interactions;
the correlation analysis module (250) utilizes probabilistic ranking and sequential analysis to identify and confirm relationships between data packets, ensuring precision and accuracy;
the dependency analysis module (260) applies advanced algorithms, such as shortest path analysis, to uncover dependencies and establish sequences within the data;
the output generation module (270) generates detailed reports, including dependency hierarchies, visualizations, and actionable recommendations for optimizing system (10) integrations.

2. The system as claimed in claim 1, wherein the data packet ingestion module (210) ensures accurate data collection through the integration of APIs and data pipelines across diverse systems.

3. The system as claimed in claim 1, wherein the attribute extraction module (220) fine-tunes large language models with domain-specific datasets to enhance the precision and relevance of extracted attributes.

4. The system as claimed in claim 1, wherein the reverse engineering module (230) links related data packets by matching extracted attributes and historical data patterns, enabling a comprehensive understanding of system relationships.

5. The system as claimed in claim 1, wherein the context-graph construction module (240) employs graph algorithms to dynamically update relationship hierarchies based on real-time data analysis.

6. The system as claimed in claim 1, wherein the correlation analysis module (250) incorporates machine learning models to rank relationship probabilities, improving the accuracy of dependency mapping.

7. The system as claimed in claim 1, wherein the output generation module (270) provides detailed visualizations of dependency hierarchies, including timelines and projected impacts of recommended optimizations on workflows.

8. The method as claimed in claim 1, wherein the various components of the processing unit (200) employs a method (400) comprising the steps of:
a. Data Packet Ingestion Module (210)
- collecting and organizing data packets from disparate business systems such as CRM platforms, code repositories, and task management tools,
- preprocessing data packets to ensure compatibility with further modules,
- outputting structured data packets for subsequent analysis;
b. Attribute Extraction Module (220)
- employing fine-tuned LLMs to extract key attributes, including source, type, and intent, from data packets,
- structuring extracted attributes into a standardized format,
- outputting attribute data for downstream analysis;
c. Reverse Engineering Module
- identifying underlying entities linked to data packets, such as user IDs and system components,
- establishing context and intent for each packet based on extracted attributes,
- outputting linked data packets for relationship mapping;
d. Context-Graph Construction Module (240)
- visualizing relationships and dependencies using graph-based techniques,
- highlighting hierarchies and interactions among entities,
- outputting the context-graph for correlation analysis;
e. Correlation Analysis Module
- ranking potential matches and confirming relationships between data packets using probabilistic methods,
- incorporating timelines and contextual attributes for precise mapping,
- outputting confirmed relationships and dependencies for further analysis;
f. Dependency Analysis Module (260)
- applying advanced algorithms to evaluate dependencies and sequences within the data,
- establishing dependency hierarchies and operational flows,
- outputting comprehensive dependency maps for reporting;
g. Output Generation Module (270)
- compiling evaluation results into detailed reports,
- including visualizations of dependencies and actionable recommendations for optimization,
- outputting reports for stakeholder decision-making;
- sending the reports finally to the output unit (300)

Dated this 31st day of December, 2024.