LLM-Powered Knowledge Graphs for Enterprise Intelligence and Analytics
Rajeev Kumar, Kumar Ishan, Harishankar Kumar, Abhinandan Singla
TL;DR
Fragmented enterprise data impede actionable insights. The paper proposes an LLM-powered, user-centered activity knowledge graph that unifies emails, calendars, chats, documents, and logs through automatic entity and relationship extraction plus contextual enrichment. It introduces a real-time graph-construction pipeline and an analytics layer for expertise discovery, task prioritization, and data-driven decision support, validated via a six-month pilot with strong extraction accuracy and adoption. This approach bridges data silos and enables scalable, intelligent analytics that can adapt across domains and organizational contexts.
Abstract
Disconnected data silos within enterprises obstruct the extraction of actionable insights, diminishing efficiency in areas such as product development, client engagement, meeting preparation, and analytics-driven decision-making. This paper introduces a framework that uses large language models (LLMs) to unify various data sources into a comprehensive, activity-centric knowledge graph. The framework automates tasks such as entity extraction, relationship inference, and semantic enrichment, enabling advanced querying, reasoning, and analytics across data types like emails, calendars, chats, documents, and logs. Designed for enterprise flexibility, it supports applications such as contextual search, task prioritization, expertise discovery, personalized recommendations, and advanced analytics to identify trends and actionable insights. Experimental results demonstrate its success in the discovery of expertise, task management, and data-driven decision making. By integrating LLMs with knowledge graphs, this solution bridges disconnected systems and delivers intelligent analytics-powered enterprise tools.