Description:FIELD OF INVENTION
The present invention relates to the field of computer-based technological systems. Specifically, the invention provides a system and method for correlating code commits and pull requests with project management issues and tasks, enhancing traceability, alignment, and efficiency in development workflows.

BACKGROUND
In contemporary project computer based technological ecosystems, the development of complex solutions often requires collaborative efforts across diverse teams and tools. To manage this complexity, organizations rely on platforms like Jira and Trello for project planning, task tracking, and resource allocation. Simultaneously, version control systems such as GitHub and GitLab are used to manage and document changes, facilitating collaborative workflows for teams working on the same project.
Despite the widespread use of these tools, they function as isolated systems, with limited mechanisms to share or interpret data across platforms. This siloed approach creates significant challenges in aligning task management with changes made during implementation. For instance, there is often no direct way to trace a specific commit or pull request to the project management task it addresses, making it difficult to evaluate progress or assess how individual contributions align with overarching goals.
This disconnect not only leads to inefficiencies but also introduces risks, such as overlooked dependencies, miscommunication between teams, and delays in delivering the final product. To overcome these challenges, there is a pressing need for a unified system that bridges the gap between task management and version control, enabling seamless traceability, enhanced collaboration, and improved alignment of activities with organizational objectives.
In the prior art WO2008130759A1 - Using Code Analysis for Requirements Management, various computer based technologies and techniques are disclosed that allow project requirements to be associated with underlying code elements. A particular project is analyzed to generate a list of code elements contained within it. A user of a requirements management application provides input to associate one or more project requirements with specific code elements. The project requirements and their association with the corresponding code elements are then stored in a data store for later retrieval. These associations are used to track when changes are made to the underlying code elements that may potentially affect the project requirements.
In another prior art, US8312415B2 - Using Code Analysis for Requirements Management various technologies and techniques are disclosed that allow project requirements to be associated with underlying code elements. A particular project is analyzed to generate a list of code elements contained within it. A user of a requirements management application provides input to associate one or more project requirements with specific code elements. The project requirements and their association with the corresponding code elements are stored in a data store for later retrieval. These associations are used to track when changes are made to the underlying code elements that may potentially affect the project requirements.
OBJECTS OF THE INVENTION:
The primary object of the present invention is to provide a system and method for correlating source control data and project management data to establish traceability between code changes and project objectives.
Yet another object of the present invention is to utilize Large Language Models (LLMs) to infer and validate the intent of code changes and associate them with corresponding project management items, such as tasks, stories, and epics.
Yet another object of the present invention is to ensure seamless synchronization between source control systems and project management platforms by providing real-time monitoring and on-demand synchronization capabilities.
Further, the object of the present invention is to resolve conflicts between multiple project tasks and overlapping code changes using customized LLMs to rank and prioritize matches based on relevance metrics.
Yet another object of the present invention is to create a searchable database using a knowledge graph to store and retrieve bidirectional links between project management data and source control information, enabling efficient traceability and analytics.
Yet another object of the present invention is to generate chronological timelines and visualizations for stakeholders to understand project progress, release milestones, and feature evolution comprehensively.

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 present invention relates to a system and method for transforming disparate input data sources into a validated, refined, and searchable dataset, ensuring data consistency and reliability through a multi-stage processing workflow. The system comprises input sources , a processing module utilizing a large language model (LLM) to convert raw data into intent-driven packets and organize them into a timeline, a validation module with a Reviewer Agent to ensure data accuracy, and a conflict resolution module with a Ranking Agent to resolve inconsistencies and prioritize data. The final processed data is presented in a searchable output format for user interaction. The system may also include additional modules for dynamic feedback to continuously improve the data processing and validation mechanisms.

BRIEF DESCRIPTION OF DRAWINGS
The present invention, together with further objects and advantages thereof, is more particularly described in conjunction with the accompanying drawings in which:
FIG. 1 illustrates a system and method for correlating code commits and pull requests with project management issues, tasks, stories, and epics. The diagram provides a high-level overview of the components involved, including project management platforms, source control systems, data processing modules, and the generation of visual timelines and knowledge graphs to establish traceability between project and code-level activities.

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.
The present invention describes system and method for correlating code commits and pull requests with project management issues, epics and tasks, enhancing traceability, alignment, and efficiency in development workflows. The system also utilizing Large Language Models (LLMs) to infer and validate the intent of changes and create accurate project timelines. It also helps in maintaining a searchable database of correlated data for future analysis.
According to the embodiment of the present invention, the system comprises of operational modes module, input sources, data processing module, timeline generation module, intent validation module, conflict resolution module and knowledge linking module.
According to an embodiment of the present invention, FIG. 1 illustrates a system and method for correlating code commits and pull requests with project management issues, tasks, stories, and epics. The diagram provides a high-level overview of the components involved, including project management platforms, source control systems, data processing modules, and the generation of visual timelines and knowledge graphs to establish traceability between project and code-level activities. The components work in synergy to process inputs, analyse intents, generate timelines, and store linked data for actionable insights and retrieval. The flow emphasizes real-time monitoring, on-demand synchronization, conflict resolution, and intent validation, ensuring efficient project alignment and traceability.
According to the embodiment of the present invention, the system operates in two primary operational modes:
• On-Demand Sync: This mode allows users to trigger synchronization manually. It is ideal for scenarios where users need to ensure immediate consistency between project management and source control systems. For example, a project manager can request an on-demand sync to validate that recent commits align with active tasks.
• Monitoring Mode: This mode leverages webhooks to automatically track changes in real-time. Whenever updates occur in project management tools or source control systems, they are processed and synchronized. This ensures continuous alignment without manual intervention and is especially useful for agile development environments.
In the input sources module, the system ingests data packets from:
1. Project Management Tools: Extracts detailed information, including issue identifiers, descriptions, task assignments, priorities, and change histories. This data provides a comprehensive view of project objectives and ongoing work.
2. Source Control Systems: Processes commit messages, pull request descriptions, code diffs, and metadata such as author details and timestamps. This data represents the technical implementation of project objectives.
In the data processing module, the system processes data packets as follows:
a. Project Management Data:
- Extracts issue, task, story, and epic information.
- Uses LLMs to analyse descriptions, comments, and metadata to infer the intent behind each item. For instance, a task labelled 'Improve login security' may be converted into an intent packet labelled 'Enhance authentication mechanisms.'
b. Source Control Data:
- Analyses commit messages and code changes.
- Uses LLMs to infer the purpose of the changes, such as 'Bug fix,' 'Performance optimization,' or 'Feature addition.'
- Correlates technical changes with project objectives by identifying overlapping intents.
In the timeline generation module, the system integrates project management and source control data into a unified timeline. Key steps include
- Feature Identification: Analysing project history to group related tasks, stories, and epics into features.
- Release Annotation: Mapping features and intents to specific releases, creating a chronological view of the product’s evolution.
- Visualization: Generating visual timelines to aid stakeholders in understanding project progress and milestones.
In the next step, the intent validation module ensures accuracy in inferred intents and summaries. The steps include:
- Reviewer Agent: An LLM-powered agent reviews intents and summaries for consistency and correctness. For example, it checks whether a commit labelled as a 'Bug fix' genuinely addresses the reported issue.
- Feedback Mechanism: Provides actionable feedback to improve incorrect or ambiguous mappings, ensuring high-quality results.
According to the embodiment of the present invention, ambiguities arise when multiple project tasks match the same code change. The system resolves such conflicts through:
- Candidate Ranking: A customized LLM evaluates potential matches based on relevance metrics, such as keyword similarity and task priority.
- Selection Criteria: The highest-ranked match is selected based on predefined thresholds.
- Iterative Refinement: Continuously improves ranking models using feedback and examples from public datasets.
In the final step, the knowledge linking module establishes bidirectional links between project management and source control data:
-Knowledge Graph: Constructs a graph database where nodes represent tasks, stories, commits, and pull requests, and edges represent relationships like 'implements' or 'relates to.'
-Searchable Database: Stores all linked data in Elasticsearch, enabling quick retrieval and analysis.
The invention hereafter will be cited by way of examples only for a better and detailed understanding.
Example:
Scenario:
A developer commits code to a repository with a message: 'Refactored login authentication for better security.'
The system: Extracts the commit message and code diff. Identifies the intent ('Enhance security') using an LLM. Cross-references project management tasks to find a matching story, such as 'Implement 2FA for login.'
The reviewer agent validates the inferred intent and the match. The system creates a timeline entry: 'Release 1.2.0: Enhanced security with refactored login authentication.' Stores the result in Elasticsearch for future traceability.
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.
, C , Claims:We claim:
1. A system and method for correlating code commits and pull requests with project management issues, tasks, stories, and epics to establish traceability between source control data and project objectives
characterized in that
the system comprises of operational modes module, input sources, data processing module, timeline generation module, intent validation module, conflict resolution module and knowledge linking module;
the method involves the steps of:
using the LLMs to identify intents from project management and source control packets;
integrating reviewer agents for validating inferred intents and summaries;
using conflict resolution mechanism utilizing customized LLMs for ranking ambiguous matches;
maintaining a searchable database to store and retrieve correlated data for traceability and analytics.
2. The system and method as claimed in claim 1, wherein the system operates in two primary operational modes including on-demand sync mode that allows users to trigger synchronization manually and monitoring mode that leverages webhooks to automatically track changes in real-time.
3. The system and method as claimed in claim 1, wherein in the input sources module, the system ingests data packets from project management tools and source control systems.

4. The system and method as claimed in claim 1, wherein in the data processing module, the system processes data packets such as Project Management Data by extracting issue, task, story, and epic information and uses LLMs to analyse descriptions, comments, and metadata to infer the intent behind each item and Source Control Data analyses commit messages and code changes, uses LLMs to infer the purpose of the changes, and correlates technical changes with project objectives by identifying overlapping intents.
5. The system and method as claimed in claim 1, wherein in the timeline generation module, the system integrates project management and source control data into a unified timeline by the following steps:
• feature identification by analyzing project history to group related tasks, stories, and epics into features.
• release annotation by mapping features and intents to specific releases, creating a chronological view of the product’s evolution.
• visualization by generating visual timelines to aid stakeholders in understanding project progress and milestones.
6. The system and method as claimed in claim 1, wherein the intent validation module ensures accuracy in inferred intents and summaries by the following steps:
• An LLM-powered reviewer agent reviews intents and summaries for consistency and correctness;
• Feedback Mechanism provides actionable feedback to improve incorrect or ambiguous mappings, ensuring high-quality results.
7. The system and method as claimed in claim 1, wherein the system resolves ambiguity conflict by candidate ranking that includes a customized LLM evaluates potential matches based on relevance metrics, such as keyword similarity and task priority; selection criteria that includes the highest-ranked match is selected based on predefined thresholds and iterative refinement that includes continuously improves ranking models using feedback and examples from public datasets.
8. The system and method as claimed in claim 1, wherein the knowledge linking module establishes bidirectional links between project management and source control data by constructing a graph database where nodes represent tasks, stories, commits, and pull requests, and edges represent relationships like 'implements' or 'relates to’ and stores all linked data in database, enabling quick retrieval and analysis.