Research on the Construction and Application of a Water Conservancy Facility Safety Knowledge Graph Based on Large Language Models

To address the challenges of integrating multi-source heterogeneous data and low knowledge utilization rates in water conservancy facility safety management, this study proposes a knowledge graph construction method that integrates ontology modeling with large language model enhancement. First, an ontology framework for water conservancy facility safety is constructed, encompassing four core elements: agencies and personnel, engineering equipment, risks and hidden dangers, and systems and processes. Subsequently, a KG-LLM-GraphRAG architecture is designed, which optimizes the knowledge extraction effectiveness of large language models through ontology-constrained prompt templates and utilizes the Neo4j graph database for knowledge storage and multi-hop reasoning. Experimental results demonstrate that the proposed method significantly outperforms traditional approaches in entity-relationship extraction tasks. The constructed knowledge graph not only effectively supports application scenarios such as safety hazard identification, emergency decision-making, and knowledge reuse but also provides an efficient knowledge organization and reasoning tool for water conservancy facility safety management, strongly propelling the digital transformation of the water conservancy industry.