大语言模型赋能的领域知识图谱构建与应用研究

打开文本图片集

中图分类号：TP18；TP391.1 文献标识码：A DOI：10.11968/tsyqb.1003-6938.2025076

Research on Construction and Application of Domain Knowledge Graph Empowered by Large Language Models

Xu Hao Kang Zhenyuan Zhang Yan Deng Sanhong Zou Chen

Abstract This paper integrates Large Language Models （LLMs） with deep learning to propose an LLMDL framework for the entire Domain Knowledge Graph （DKG） construction process.The framework includes： data preprocessing drawingon text clasification principles;semi-automated domain ontology construction via LLMs;domain-adaptive optimizationof the W2NER named entity recognition （NER）model with LLM-baseddata annotation andresult verification; relation extraction considering inter-relation correlations;entityalignment through the integrationof SBERTand LLMs; and construction of high-quality DKG with scenario-specific applications.Experimental results show that the proposed methodefctivelybalances textvalue whilecontroling textlength;improvestheFlscoreof named entityrecognition by 2.24% compared with the original model;achieves a 22.07% Fl score improvement in relation extraction compared with traditional BERT models; and 84.85% of entities achieve standardized expressions in knowledge fusion.

Key words Large Language Models; Domain Knowledge Graph; deep learning

信息技术的快速发展正在推动各行业向智能化、数字化方向转型升级。（剩余21353字）