| 1,867 | 2 | 127 |
| 下载次数 | 被引频次 | 阅读次数 |
构建基于大语言模型的中医妇科知识图谱，旨在系统化整理并展现中医妇科领域复杂知识体系，揭示病症间的内在联系与演变规律，以提升临床决策的精准度。选取中国知网349篇中医妇科文献，采用ChatGLM通过多轮提示词模板实现零样本实体关系抽取，设计评价指标评估抽取效果，借助API接口与模型交互，使用Neo4j图数据库构建并可视化知识图谱。研究表明，ChatGLM在知识抽取方面优于传统Bi-LSTM-CRF模型，显著提升了精确率、召回率和F1值。所构建的知识图谱有效支持了中医妇科领域的临床决策，提高了诊疗效率与准确性，体现了其实用价值。
Abstract：The study aims to construct a knowledge graph for traditional Chinese medicine(TCM) gynecology based on large language models. The goal is to systematically organize and present the complex knowledge system of this field, revealing the intrinsic connections and evolution patterns among diseases, thereby enhancing the precision of clinical decision-making. The study selected 349 TCM gynecology papers from China National Knowledge Infrastructure(CNKI). ChatGLM was used with multi-round prompt templates to achieve zero-shot entity relationship extraction. Evaluation metrics were designed to objectively assess the extraction results. Efficient processing was achieved through API interfaces interacting with the model. The Neo4j graph database was used to construct and visualize the knowledge graph. The study shows that ChatGLM performs better in knowledge extraction compared to traditional Bi-LSTM-CRF models, significantly improving precision, recall and F1 scores. The constructed knowledge graph effectively supports the clinical decision-making in TCM gynecology, enhancing the diagnostic efficiency and accuracy and demonstrating the practical value.
[1] 韩延华，刘淑君，宋秀珍，等.当代中医妇科名家学术思想源流探究[J].中华中医药杂志，2008,23(3):189-191.
[2] 刘峤，李杨，段宏，等.知识图谱构建技术综述 [J].计算机研究与发展，2016,53(3):582-600.
[3] 翟东升，娄莹，阚慧敏，等.基于多源异构数据的中医药知识图谱构建与应用研究 [J].数据分析与知识发现，2023,7(9):146-158.
[4] GLM T,ZENG A,XU B,et al.ChatGLM:A family of large language models from GLM-130b to glm-4 all tools [J].arXiv Preprint arXiv,2024,2406:12793.
[5] 王松，李正钧，杨涛，等.中医药知识图谱研究现状及发展趋势[J].南京中医药大学学报，2022,38(3):272-278.
[6] 周涛，常凯.基于Neo4j的中医妇科知识图谱构建研究 [J].信息技术与信息化，2024(6):209-212.
[7] 王琨翎子.基于知识元理论的中医妇科古籍带下病文献标引与规则库构建研究[D].北京：中国中医科学院，2023.
[8] 刘艺.痛经中医临床证据图谱研究 [D].保定：河北大学，2023.
[9] 田赛男.《傅青主女科》证治规律及知识图谱构建研究 [D].长沙：湖南中医药大学，2022.
[10] ZHAO W X,ZHOU K,LI J,et al.A survey of large language models [J].arXiv Preprint arXiv,2303,2023:18223.
[11] HAN K,XIAO A,WU E,et al.Transformer in transformer [J].Advances in Neural Information Processing Systems,2021,34:15908-15919.
[12] CHANG Y P,WANG X,WANG J D,et al.A survey on evaluation of large language models[J].ACM Trans Intell Syst Technol,2024,15(3):1-45.
[13] MAO R,LIU Q,HE K,et al.The biases of pre-trained language models:an empirical study on prompt-based sentiment analysis and emotion detection[J].IEEE Trans Affect Comput,2023,14(3):1743-1753.
[14] ZHANG B,HADDOW B,BIRCH A.Prompting large language model for machine translation:A case study [C]// International Conference on Machine Learning.PMLR,2023:41092-41110.
[15] SHAO Z W,YU Z,WANG M,et al.Prompting large language models with answer heuristics for knowledge-based visual question answering[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Vancouver,BC:IEEE,2023:14974-14983.
[16] GAO Y,XIONG Y,GAO X,et al.Retrieval-augmented generation for large language models:A survey [J].arXiv preprint arXiv,2023,2312:10997.
[17] SUN J,XU C,TANG L,et al.Think-on-graph:Deep and responsible reasoning of large language model with knowledge graph [J].arXiv Preprint arXiv,2023,2307:7697.
[18] LUO L,LI Y F,HAFFARI G,et al.Reasoning on graphs:Faithful and interpretable large language model reasoning [J].arXiv Preprint arXiv,2023,2310:1061.
[19] 张洪程，李林育，杨莉，等.基于对比学习与语言模型增强嵌入的知识图谱补全[J].计算机工程，2024,50(4):168-176.
[20] 李源，马新宇，杨国利，等.面向知识图谱和大语言模型的因果关系推断综述[J].计算机科学与探索，2023,17(10):2358-2376.
[21] TRAJANOSKA M,STOJANOV R,TRAJANOV D.Enhancing knowledge graph construction using large language models [J].arXiv Preprint arXiv,2023,2305:4676.
[22] 陈明，刘蓉，熊回香.基于医疗知识图谱的智能问答系统研究 [J].情报科学，2023,41(12):118-126.
[23] 朱金阳.基于知识图谱的肝病智能问答的研究 [D].南京：南京中医药大学，2024.
[24] GAO Y,LI R,CASKEY J,et al.Leveraging a medical knowledge graph into large language models for diagnosis prediction [J].arXiv Preprint arXiv,2023,2308:14321.
[25] 杨波，孙晓虎，党佳怡，等.面向医疗问答系统的大语言模型命名实体识别方法[J].计算机科学与探索，2023,17(10):2389-2402.
[26] 徐增林，盛泳潘，贺丽荣，等.知识图谱技术综述[J].电子科技大学学报，2016,45(4):589-606.
[27] 鲍彤，章成志.ChatGPT中文信息抽取能力测评——以三种典型的抽取任务为例 [J].数据分析与知识发现，2023,7(9):1-11.
[28] MESKó B.Prompt engineering as an important emerging skill for medical professionals:tutorial[J].J Med Internet Res,2023,25:50638.
[29] WHITE J,FU Q,HAYS S,et al.A prompt pattern catalog to enhance prompt engineering with chatgpt [J].arXiv Preprint arXiv,2023,2302:11382.
[30] WEI J,WANG X,SCHUURMANS D,et al.Chain-of-thought prompting elicits reasoning in large language models [J].Advances in Neural Information Processing Systems,2022,35:24824-24837.
[31] FENG G,ZHANG B,GU Y,et al.Towards revealing the mystery behind chain of thought:a theoretical perspective [J].Advances in Neural Information Processing Systems,2024,36:15408.
[32] 肖瑞，胡冯菊，裴卫.基于BiLSTM-CRF的中医文本命名实体识别[J].世界科学技术-中医药现代化，2020,22(7):2504-2510.
[33] 徐安迎，胡孔法，杨涛.基于Neo4j的肺癌中医诊疗知识图谱构建研究[J].世界科学技术-中医药现代化，2023,25(4):1456-1461.
[34] 郑泳霞，余璟玮，刘晓琳，等.基于方证分析下中医妇科常见证候的Ⅲ级分类与规律研究 [J].世界中医药，2024,19(9):1312-1315,1323.
[35] 李翠萍，卢金镶.古今妇科医案经方集萃[M].上海：第二军医大学出版社，2008.
[36] 王雪苔，刘冠军.中国当代针灸名家医案[M].长春：吉林科学技术出版社，1991:26.
基本信息:
DOI：10.13193/j.issn.1673-7717.2026.01.001
中图分类号:TP391.1;R271
引用信息:
[1]汤少梁,龙秋予,李君妍,等.基于ChatGLM的中医妇科知识图谱自动化构建与临床决策支持研究[J].中华中医药学刊,2026,44(01):1-6+259-263.DOI:10.13193/j.issn.1673-7717.2026.01.001.
基金信息:
国家社会科学基金重点项目(19AZD018); 江苏智慧中医药健康服务工程研究中心开放课题项目(ZHZYY202402)
2025-03-12
2025-03-12
2025-03-12