An Explainable Natural Language Framework for Identifying and Notifying Target Audiences In Enterprise Communication

2025-08-07

AI Summary

Large-scale maintenance organizations face challenges in expert identification, inefficient cross-departmental communication, information overload, and delayed incident response. Method: This paper proposes an interpretable query framework integrating RDF graph databases with large language models (LLMs). It constructs a semantic-aware, multi-source entity–relationship knowledge graph (encompassing devices, vendors, engineers, etc.) and adopts a two-stage “planning–orchestration” architecture: first, an LLM parses natural-language queries to infer intent and generate logical reasoning paths; second, the graph database executes semantic matching and multi-hop path reasoning for precise stakeholder identification. Contribution/Results: The framework synergistically combines LLMs’ semantic understanding with graph databases’ structured reasoning, ensuring result interpretability and system trustworthiness. Experiments demonstrate significant improvements in message delivery accuracy and response timeliness, validating its effectiveness and practicality in real-world enterprise settings.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Planning, Routing, and Scheduling: Planning with Language Models
• Knowledge Representation and Reasoning: Description Logics

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

In large-scale maintenance organizations, identifying subject matter experts and managing communications across complex entities relationships poses significant challenges -- including information overload and longer response times -- that traditional communication approaches fail to address effectively. We propose a novel framework that combines RDF graph databases with LLMs to process natural language queries for precise audience targeting, while providing transparent reasoning through a planning-orchestration architecture. Our solution enables communication owners to formulate intuitive queries combining concepts such as equipment, manufacturers, maintenance engineers, and facilities, delivering explainable results that maintain trust in the system while improving communication efficiency across the organization.

Problem

• Identifying subject matter experts in large organizations
• Managing complex enterprise communication relationships
• Reducing information overload in maintenance workflows

Innovation

• Combines RDF graph databases with LLMs
• Processes natural language queries precisely
• Provides transparent reasoning via planning-orchestration