计算机科学与探索2024，Vol.18Issue(10)：2656-2667,12.DOI:10.3778/j.issn.1673-9418.2406013
基于大语言模型的知识图谱构建及应用研究
Research on Construction and Application of Knowledge Graph Based on Large Language Model
摘要
Abstract
Massive amounts of operational and maintenance(O&M)data from nuclear power distributed control sys-tem(DCS)contain rich operational experience and expert knowledge.Effectively extracting DCS alarm response information and forming knowledge service is a current hotspot and frontier research area in rapid DCS response.Due to the lack of clear structure and standards in multi-source heterogeneous data of nuclear power DCS,previous knowledge extraction primarily relied on manual annotation and deep learning methods,which require extensive domain knowledge and information processing capabilities and are constrained by the heavy workload of data annota-tion.Therefore,this study proposes a knowledge extraction method using large language model(LLM)with a step-by-step prompting strategy,constructing a DCS O&M knowledge graph(KG).Based on large language model tech-nology and secondary intent recognition methods,intelligent question and answer(Q&A)and other knowledge ser-vices are developed utilizing the knowledge graph.Using O&M data from a nuclear power plant's DCS as a case study,the research focuses on knowledge extraction,knowledge graph construction,and intelligent Q&A.The re-sults show that the model achieves an overall precision(P)of 91.24%,recall(R)of 85.85%,and F1-score of 88.43%.The proposed method can comprehensively capture key entities and attribute information from multi-source heterogeneous DCS O&M data,guiding domain knowledge Q&A,assisting O&M personnel in timely re-sponding to DCS alarm anomalies,analyzing fault causes and response strategies,and providing guidance for DCS O&M training and maintenance in power plants.关键词
核电分布式控制系统/知识图谱/大语言模型/知识抽取/智能问答Key words
nuclear power distributed control system/knowledge graph/large language model/knowledge extrac-tion/intelligent question and answer(Q&A)分类
信息技术与安全科学引用本文复制引用
张才科,李小龙,郑胜,蔡家骏,叶小舟,罗静..基于大语言模型的知识图谱构建及应用研究[J].计算机科学与探索,2024,18(10):2656-2667,12.基金项目
中国核电集中研发项目(K220604).This work was supported by the Concentrated Research and Development Project of China Nuclear Power(K220604). （K220604）
