Description:FIELD OF INVENTION
The present invention relates to the transformation of the organizational data into event-timelines. More particularly, the invention relates to a system and method to integrate siloed enterprise data from multiple organizational tools into a unified event-timeline, enabling it as a tool for large language models.

BACKGROUND
Organizational data refers to the information about organization structures, roles, and relationships, including data like employee IDs, titles, departments, and reporting structures. This data is used to route tasks to the appropriate employees or teams based on their roles and responsibilities. It is also used to create reports and perform analytics on employee performance, departmental productivity, and other organizational metrics. It facilitates communication and collaboration by providing a clear understanding of who reports to whom and who is responsible for what. Further, it provides critical input for business intelligence systems, enabling organizations to make data-driven decisions. This data, thus, forms the foundation for various software applications, ensuring that the right information is accessible to the right people and that workflows are executed correctly.
In the modern enterprise landscape, organizational data is distributed across diverse tools which are designed for specific functions such as project management, source code control, service desk performance, maintaining repositories for documentation, and communication. However, these tools operate in silos and store their data in unstructured and semi-structured formats, thereby making cross-platform events understanding difficult. While, large language models have the capacity to extract insights and perform reasoning, they require structured and contextual input and thereby making the evaluation of the employee performance, departmental productivity, and other organizational metrics a complicated, time consuming and investment heavy task.
To overcome these drawbacks, it is essential to introduce a system which integrates siloed enterprise data from multiple organizational tools into structured timelines, which is also compatible with large language models.
Prior Arts:
US11132541B2 discloses a system and method for generating event timelines by analysing natural language texts from a textual dataset. The invention extracts event-trigger words and time mentions from textual datasets and anchors them to a timeline.
US20050091241A1 introduces a method for dynamically organizing and managing metadata, data, and structures using self-referencing hypergraphs, allowing distributed analysis and automatic database updates
US6078916A introduces a method of organizing information in which the search activity of a user is monitored and such activity is used to organize articles in a subsequent search. The invention adjusts the ranking and categorizations of articles, using scores and user interactions to refine search results over time.
Prior arts hereinabove deal with timeline generation, data organization, and metadata management. However, these prior arts lack a system which focuses on unification of the unstructured or semi-structured enterprise data from multiple organizational tools into event timelines. Further, they lack a system which enables large language models to access and utilize this data.
Thus, there is a need to introduce a system that integrates all unstructured or semi-structured enterprise data from multiple organizational tools, and transforms it into event timelines compatible with large language models such that the evaluation of the employee performance, departmental productivity, and other organizational metrics becomes simple, cost effective and easily manageable task.

DEFINITIONS:
The expression “system” used hereinafter in this specification refers to an ecosystem comprising, but is not limited to a 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 system.
The expression “large language model (LLM)” used hereinafter in this specification refers to a type of machine learning model designed for natural language processing tasks such as language generation. LLMs are language models with many parameters, and are trained with self-supervised learning on a vast amount of text.
The expression “API” used hereinafter in this specification stands for Application Programming Interface. It is a set of protocols, routines, and tools for building software and applications. An API specifies how software components should interact and allows different software systems to communicate with each other.
The expression “data silos” used hereinafter in this specification refer to isolated collections of data that prevent data sharing between different departments, systems and business units. When data becomes siloed, organizations can struggle to maintain data quality and make data-driven decisions.
The expression “Named Entity Recognition (NER)” used hereinafter in this specification refer to a technique in Natural Language Processing (NLP) that focuses on identifying and classifying entities within unstructured text. These entities can include names of people, organizations, locations, dates, quantities, and more. The primary goal of NER is to extract structured information from text, enabling machines to understand and categorize entities for various applications such as text summarization, building knowledge graphs, and question answering.
The expression “cosine similarity” used hereinafter in this specification represents the semantic meaning or content of text documents. Because it focuses on the direction rather than the magnitude of the vectors, cosine similarity is particularly useful for comparing the similarity of text documents without being affected by their length or scale.

OBJECTS OF THE INVENTION:
The primary object of the present invention is to provide a system and method to transform organizational data into event-timelines.

Another object of the invention is to correlate cross-platform events using semantic embeddings, time-based heuristics, and knowledge graph construction.

Yet another object of the invention is to make the event-timelines compatible with large language models through APIs.

Yet another object of the invention is to support event lookup and reason backtracking, to enable the identification of underlying issues.

Yet another object of the invention is to provide for plug-in connectors which are modular and scalable.

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 describes a method for ingesting enterprise data and converting into hourly summarized event packets. The system assists in correlating cross-platform events using semantic embeddings, time-based heuristics, and knowledge graph construction. The system ingests data and converts them into hourly summarized event packets. The system comprises of an input unit, a processing unit and output unit, wherein the processing unit comprises of connector module, preprocessing engine module, summarization engine module, event packet generator module, timeline sorter module and bucketization module.

According to an aspect of the present invention, the method comprises the steps of connectors ingest data, normalize and preprocess the data, LLM summarization pipeline summarizes the data, event packet generator divides the data into packets, cross system correlation, sort and sequence events, generate timeline buckets and make the timeline accessible via LLM compatible APIs.

BRIEF DESCRIPTION OF DRAWINGS
A complete understanding of the present invention may be made by reference to the following detailed description which is to be taken in conjugation with the accompanying drawing. The accompanying drawing, which is incorporated into and constitutes a part of the specification, illustrates one or more embodiments of the present invention and, together with the detailed description, it serves to explain the principles and implementations of the invention.

FIG. 1 illustrates a system architecture of the present invention.
FIG.2 illustrates a flowchart that depicts the method of the present invention.

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.

Reference Numbers Component
10 System
100 Connector module
101 Project Management Tool
102 Source Code Control Tool
103 Service Desk
104 Documentation Repository
105 Communication Platform
200 Preprocessing Engine module
300 Summarization Engine module
400 Event Packet Generator module
500 Timeline Sorter module
600 Bucketization module
700 API

The present invention describes a system and method to transform organizational data into event-timelines. The system enables transforming siloed enterprise data or isolated data from multiple organizational tools into a unified, temporally-sequenced, semantically-linked event timeline. Using connectors, pre-processing engines, summarization models (LLMs), and advanced correlation and sequencing logic, the system enables AI models to interact meaningfully with enterprise operations. The system utilises this intelligence through API endpoints compatible with Large Language Model (LLM) tools.
The system comprises of an input unit, a processing unit and output unit, wherein the processing unit further comprises of connector module, preprocessing engine module, summarization engine module, event packet generator module, timeline sorter module and bucketization module. In the present invention, FIG. 1 illustrates a system architecture diagram that depicts how the system connects various input sources, processes them through modules, and outputs the event timeline. The modules function in detail as follows:
1. Connector Module (100): This is the System Integration Layer. The Connector module pulls data periodically using APIs or webhooks. Each data source has a dedicated adapter for formatting and scheduling. The data sources include but are not limited to the Project Management Tools (101) (e.g. Jira, Aha), Source Code Control Tools (102) (e.g. Git, Bitbucket), Service Desk (103) (e.g. ServiceNow, Zendesk), Documentation Repository (104) (e.g. Confluence, SharePoint), and Communication Platform (105) (e.g. Slack, MS teams). All timestamps are normalized to UTC (Coordinated Universal time- It is the primary time standard globally used to regulate clocks and time.
2. Preprocessing Engine module (200): This module is responsible for data ingestion and preprocessing. It carries out de- duplication of data based on hash of content and timestamp proximity. The data deduplication technique identifies and eliminates duplicated data blocks with a cryptographic hash function. Hash-based data deduplication methods use a hashing algorithm to distinguish “chunks” of data individually. Further, Named Entity Recognition (NER) tags the data with key actors such as users, modules, issues. It also tags Metadata for example- project name, service ID, author, file path, tag.
3. Summarization Engine module (300): This module assists in chunking of large documents into context windows (for example around 2000 tokens) by LLM. Chunking refers to the process of breaking down large pieces of data into smaller, more manageable units called chunks. These chunks can be of fixed size or created based on logical divisions (like paragraphs, sentences, or tokens in a document). The module uses multi-pass LLM prompts: such as extract, then normalize and then summarize. Example: a 30-line commit log is summarized into 2 sentences with relevant metadata.
4. Event Packet Generator module (400): Each hourly interval of the summarised data results in multiple event packets with titles as System ID, Summary, Related entities, and Timestamp and Tags.
5. Timeline Sorter module (500): This module first assists in correlation and Event Linking. Cosine similarity between embeddings identifies related data summaries. The rules can be Time Proximity: ±1 hour, Entity Match: same user/story/module, Sequence Cues: causal keywords like “fixed after”, “as a result”. The Graph is constructed using NetworkX or Neo4j.
For the timeline formation, the Event DAG (Directed Acyclic Graph) is topologically sorted. Sorting Algorithm ensures stability where no causal links exist. Merge sort is an efficient, general-purpose, and comparison-based sorting algorithm. Each sorted timeline formed, represents a thread of activity.
6. Bucketization module (600) : This module helps to bucket the Final timelines by hour/day/week. This helps to make the timelines accessible to developers via HTTP REST APIs and Lang Chain Tool APIs (700). They can support timeline view, event lookup by tag/entity/time and backtrace reasoning.
According to an embodiment of the present invention, the method to transform organizational data into event-timelines ,as illustrated in FIG. 2, comprises the steps of:
• Connectors ingest data
• Normalise and preprocess the data
• LLM Summarisation pipeline summarised the data
• Event packet generator divides the data into packets
• Cross system corelation
• Sort and sequence events
• Generate timeline buckets
• Make the timeline accessible via LLM compatible APIs
This invention is a fundamental enabler for enterprise-level reasoning with LLMs. It represents the bridge between fragmented organizational knowledge and intelligent systems capable of understanding the sequence, cause, and context of enterprise events. This enhances decision-making, automation, and productivity at scale.
Advantages of the present system and method to transform organizational data into event-timelines include:
- overcoming the silo walls between different tools.
- Gives LLMs temporal and semantic awareness.
- Empowers agents for reasoning, alerts, reporting, and remediation.
- Generic and pluggable for different enterprise setups.
Examples and Use Cases:
*Example 1:*
- 10:03 AM - Jira ticket ABC-123 created.
- 10:15 AM - Slack message about blocker in ABC-123.
- 10:22 AM - Git commit referencing ABC-123.
- 10:45 AM - Confluence page updated with resolution.
*System Output:*
- A timeline showing ABC-123's life cycle.
- Highlighted causality: Message -> Commit -> Doc Update.

*Example 2:*
- Policy change uploaded on SharePoint.
- Multiple Slack discussions.
- Series of incident reports in Zendesk.
*System correlates these into a Policy Impact Timeline.*
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:We claim,

1. A system and method to a system and method to transform organizational data into event-timelines
characterized in that
the system ingests data and converts them into hourly summarized event packets;
the system comprises of an input unit, a processing unit and output unit, wherein the processing unit comprises of connector module (100), preprocessing engine module (200), summarization engine module (300), event packet generator module (400), timeline sorter module (500) and bucketization module (600);
and the method comprises the steps of connectors ingest data, normalize and preprocess the data, LLM summarization pipeline summarizes the data, event packet generator divides the data into packets, cross system correlation, sort and sequence events, generate timeline buckets and make the timeline accessible via LLM compatible APIs (700).
2. The system and method as claimed in claim 1, wherein the connector module (100) pulls data from data sources comprising of the project management tools (101), source code control tools (102), service desk (103), documentation repository (104) , and communication platform (105).

3. The system and method as claimed in claim 1, wherein preprocessing engine module (200) carries out de- duplication of data based on hash of content and timestamp proximity, Named Entity Recognition tags the data with key actors such as users, modules, issues and also tags metadata.

4. The system and method as claimed in claim 1, wherein summarization engine module (300) assists in chunking of large documents into context windows by using multi-pass LLM prompts.

5. The system and method as claimed in claim 1, wherein event packet generator module (400) generates event packets at each hourly interval of the summarized data with titles as system id, summary, related entities, and timestamp and tags.

6. The system and method as claimed in claim 1, wherein timeline sorter module (500) assists in correlation and event linking by using cosine similarity between embeddings to identify related data summaries and for the timeline formation, the sorting algorithm ensures stability where no causal links exist.

7. The system and method as claimed in claim 1, wherein bucketization module (600) helps to bucket the final timelines by hour, day or week and makes the timelines accessible to developers via APIs (700) which support timeline view, event lookup by tag, entity or time and backtrace reasoning.

8. The system and method as claimed in claim 1, wherein the system supports plug-in connectors and scalable and modular deployment.