融合思维链与知识图谱的中医问答模型  

Traditional Chinese Medicine Question Answering Model Based on Chain-of-Thought and Knowledge Graph

作　　者：苑中旭 李理[1,2] 何凡 杨秀 韩东轩 YUAN Zhongxu;LI Li;HE Fan;YANG Xiu;HAN Dongxuan(School of Computer Science and Technology,Southwest University of Science and Technology,Mianyang,Sichuan 621010,China;Sichuan Engineering Technology Research Center of Industrial Self-Supporting and Artificial Intelligence,Mianyang,Sichuan 621010,China;School of Computer Science and Technology,University of Science and Technology of China,Hefei 230027,China)

机构地区：[1]西南科技大学计算机科学与技术学院,四川绵阳621010 [2]四川省工业自主可控人工智能工程技术研究中心,四川绵阳621010 [3]中国科学技术大学计算机科学与技术学院,合肥230027

出　　处：《计算机工程与应用》2025年第4期158-166,共9页Computer Engineering and Applications

基　　金：国家自然科学基金重点项目(U21A20157);国家重点研发计划(2019YFB1310501);四川省自然科学基金青年科学基金(2023NSFSC1402)。

摘　　要：针对中医问诊领域数据规模大,以及医生在问诊中主观性强、数据对齐难的问题,提出了一种中医问答领域的大语言模型ChatTCM。利用大语言模型(large language model,LLM)在处理自然语言理解与文本生成方面的强大能力,通过对大语言模型进行微调,使LLM具有在中医问答领域的专业知识和能力,避免模型在生成时出现幻觉的现象。提取中医书籍中的三元组信息,构建中医知识图谱数据库,实现中医知识的数据对齐与系统化整合,并为大语言模型生成答案提供背景知识;结合思维链(chain-of-thought,COT)与知识图谱数据库的动态交互,生成客观的推理过程,确保诊疗建议具有科学依据;把思维链与知识图谱的推理结果作为新知识进行存储,从而不断扩展本地知识库。与中医领域的HuaTuoGPT模型对比实验表明,ChatTCM模型在MedChatZH数据集上BLEU-4和ROUGE-L的评测指标分别提高了10.6和10.5个百分点,并且在已开源的数据集上准确度达到了70%,比同类型的MedChatZH模型提升了10个百分点。In response to the large scale of data in the field of Chinese medicine diagnosis,as well as the high subjectivity of doctors in diagnosis and the difficulty of data alignment,ChatTCM,a large language model for the Q&A domain of traditional Chinese medicine(TCM),is proposed.Taking advantage of the power of large language model(LLM)in dealing with natural language understanding and text generation,and fine-tuning the large language model,the LLM has expertise and competence in the field of TCM Q&A,thus preventing the model from generating hallucinations.Firstly,extract triplet information from TCM books to construct a TCM knowledge graph database,achieving data alignment and systematic integration of TCM knowledge,while providing background knowledge for large language models to generate answers.Secondly,integrate chain-of-thought(COT)reasoning with dynamic interactions from the knowledge graph database to generate an objective reasoning process,ensuring that the diagnostic recommendations are based on scientific evidence.Additionally,store the reasoning results from the chain-of-thought and knowledge graph as new knowledge,continuously expanding the local knowledge base.The ChatTCM model improves the BLEU-4 and ROUGE-L metrics on the MedChatZH dataset by 10.6 and 10.5 percentage points,respectively,and achieves 70%accuracy on the open-source dataset,which is a 10 percentage points improvement over the same type of MedChatZH model.

关 键 词：大语言模型 微调 知识图谱 思维链 中医知识 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]