Ontology-Based Knowledge Graph Framework for Industrial Standard Documents via Hierarchical and Propositional Structuring

TL;DR

This paper presents a novel ontology-based framework for constructing knowledge graphs from complex industrial standard documents, enabling better reasoning and question answering over technical content.

Contribution

It introduces a hierarchical and propositional structuring method combined with LLM-based triple extraction to effectively represent domain-specific semantics in industrial standards.

Findings

Significant performance improvements in QA tasks over existing methods

Effective representation of complex rules and structures in industrial documents

Demonstrated scalability and reliability for industrial knowledge management

Abstract

Ontology-based knowledge graph (KG) construction is a core technology that enables multidimensional understanding and advanced reasoning over domain knowledge. Industrial standards, in particular, contain extensive technical information and complex rules presented in highly structured formats that combine tables, scopes of application, constraints, exceptions, and numerical calculations, making KG construction especially challenging. In this study, we propose a method that organizes such documents into a hierarchical semantic structure, decomposes sentences and tables into atomic propositions derived from conditional and numerical rules, and integrates them into an ontology-knowledge graph through LLM-based triple extraction. Our approach captures both the hierarchical and logical structures of documents, effectively representing domain-specific semantics that conventional methods fail to reflect. To verify its effectiveness, we constructed rule, table, and multi-hop QA datasets, as well as a toxic clause detection dataset, from industrial standards, and implemented an ontology-aware KG-RAG framework for comparative evaluation. Experimental results show that our method achieves significant performance improvements across all QA types compared to existing KG-RAG approaches. This study demonstrates that reliable and scalable knowledge representation is feasible even for industrial documents with intertwined conditions, constraints, and scopes, contributing to future domain-specific RAG development and intelligent document management.