世界科学技术-中医药现代化2026，Vol.28Issue(6)：2030-2042,13.DOI:10.11842/wst.20250706001
基于赵炳南流派知识图谱的可解释多跳检索增强问答方法研究
Research on Interpretable Multi-hop Retrieval Enhanced Question Answering Method Based on the Zhao Bingnan School Knowledge Graph
摘要
Abstract
Objective This paper takes the knowledge graph of Zhao Bingnan's school of traditional Chinese dermatology as a starting point and proposes a knowledge graph-based interpretable multi-hop retrieval enhancement method(KG-IMHRE)to solve complex question-answering challenges in the field of traditional Chinese medicine.Methods By combining subgraph mining with dynamic retrieval query generation strategies,the method guides large language models to perform multi-hop relational reasoning,enhancing the handling of complex question-answering tasks in traditional Chinese medicine while ensuring the interpretability of the reasoning results.Results Based on the Zhao Bingnan school test benchmark,KG-IMHRE achieved objective evaluation scores of 85.2 for multiple-choice questions,45.78 for question-answering tasks,and an overall score of 73.38;the expert score for question-answering tasks was 4.2.Conclusion Experimental results show significant advantages over various mainstream models and retrieval schemes,significantly improving the accuracy and reasoning ability of the question-answering process.关键词
中医药知识图谱/可解释多跳检索增强/大语言模型/赵炳南流派/中医问答Key words
Traditional Chinese medicine knowledge graph/Interpretable multi-hop retrieval enhancement/Large language model/Zhao Bingnan School/Traditional Chinese medicine question answering分类
信息技术与安全科学引用本文复制引用
陈靖耀,夏舒淇,李敬华,于彤..基于赵炳南流派知识图谱的可解释多跳检索增强问答方法研究[J].世界科学技术-中医药现代化,2026,28(6):2030-2042,13.基金项目
国家自然科学基金委员会面上项目(82274683):基于深度学习的赵炳南流派知识图谱与群体性认知模型研究,负责人:于彤 （82274683）
中国中医科学院科技创新工程(CI2021A05308):基于海量文献的中医脾胃病知识图谱自动构建与知识服务研究,负责人:于彤 （CI2021A05308）
中国中医科学院科技创新工程(CI2021B002):中医药信息学创新团队大规模中医药知识图谱的构建、融合与有效方药发现研究,负责人:李敬华. （CI2021B002）
