Construction of a knowledge graph for the textbook History of Chinese Medicine based on large language models and Neo4j

doi:10.3760/cma.j.cn115259-20251102-01390

Chinese Journal of Medical Education ›› 2026, Vol. 46 ›› Issue (7): 515-520.DOI: 10.3760/cma.j.cn115259-20251102-01390

• Educational Technologies • Previous Articles Next Articles

Construction of a knowledge graph for the textbook History of Chinese Medicine based on large language models and Neo4j

Liu Siyan¹, Zhou Yaqian², Chu Jiaqi¹, Jiang Yutong³, Sun Lingzhi⁴

¹Public Administration Major, Enrolled in 2023, School of Management, Beijing University of Chinese Medicine, Beijing 102488, China;
²Business Administration Major, Enrolled in 2023, School of Management, Beijing University of Chinese Medicine, Beijing 102488, China;
³Chinese Medicine Major (Excellence 5+3 Integrated Program), Enrolled in 2023, School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 102488, China;
⁴Department of Medical History and Classical Literature, School of Traditional Chinese Medicine & Philosophy and Social Sciences Laboratory of the Ministry of Education: Laboratory of Digitalization and Humanistic Innovation of Traditional Chinese Medicine Classics & National Research Center for the Translation and Communication of Traditional Chinese Medicine Classics, Beijing University of Chinese Medicine, Beijing 102488, China

Received:2025-11-02 Online:2026-07-01 Published:2026-07-01
Contact: Sun Lingzhi, Email: sunlingzhi@bucm.edu.cn
Supported by:
Qihuang Elite Research Talent Cultivation Program, Beijing University of Chinese Medicine (K2023D02); Educational Science Research Project, Beijing University of Chinese Medicine (XJY24011); Fundamental Research Funds for the Central Universities, Research Platform Construction Project of Beijing University of Chinese Medicine (2026-JYB-KYPT-12)

Abstract

Abstract: History of Chinese medicine is a compulsory course in traditional Chinese medicine (TCM) universities and colleges. Its complex knowledge system poses certain challenges to teaching. Existing research on TCM knowledge graphs has not covered the systematic knowledge involved in this course. This study aims to leverage modern information technology to achieve knowledge structuring and visualization of the History of Chinese Medicine textbook, thereby supporting TCM education. By employing a large language model combined with manual verification, a bottom-up approach was adopted to construct the knowledge graph, which was then stored in the Neo4j graph database. A knowledge graph containing 2 879 entities and 2 487 semantic relationships was successfully built. The model achieved a triplet extraction precision of 65.42%, recall of 77.82%, and an F1 score of 71.09%, demonstrating high consistency between manual verification and model extraction results. This knowledge graph provides teaching visualization and associative retrieval support, possesses diverse educational potential, and offers a reference example and framework for intelligent innovation in medical humanistic education.

Key words: Educational technology, History of Chinese medicine, Knowledge graph, Large language model, Neo4j, Digital education in traditional Chinese medicine

CLC Number:

R-05
R2-09

Liu Siyan, Zhou Yaqian, Chu Jiaqi, Jiang Yutong, Sun Lingzhi. Construction of a knowledge graph for the textbook History of Chinese Medicine based on large language models and Neo4j[J]. Chinese Journal of Medical Education, 2026, 46(7): 515-520, DOI: 10.3760/cma.j.cn115259-20251102-01390.

References

[1] 陈邦贤. 医学史的意义与价值[J]. 中华医学杂志, 1945, 31(5-6): 259-261.
[2]郭利强, 李佳宁. 知识图谱赋能数字教材:动因、障碍及实施路向[J].课程.教材.教法,2024,44(11):37-43.
[3]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. DOI: 10.11842/wst.20220311005.
[4]俞凡, 张薇, 许涛, 等. 基于Neo4j技术探寻中医治疗功能性便秘的经验与规律:"脾统四脏"理论之思[J].右江民族医学院学报,2025,47(3):498-503. DOI: 10.3969/j.issn.1001-5817.2025.03.020.
[5]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.
[6]王菁薇, 肖莉, 晏峻峰. 基于Neo4j的《伤寒论》知识图谱构建研究[J].计算机与数字工程,2021,49(2):264-267,396. DOI: 10.3969/j.issn.1672-9722.2021.02.007.
[7]卢彦杰,盛威,刘伟,等.《五十二病方》知识图谱的构建与应用研究[J].中国数字医学,2023,18(10):105-110.
[8]高诗岳.基于Neo4j《脾胃论》知识图谱的构建及其甘温除热治法的临床应用[D].沈阳: 辽宁中医药大学, 2024.
[9]李儒婷, 吴翔宇, 张翼飞, 等. 基于Neo4j构建《海药本草》知识图谱的研究[J].广州中医药大学学报,2024,41(11):3063-3069. DOI: 10.13359/j.cnki.gzxbtcm.2024.11.036.
[10]张德政, 谢永红, 李曼, 等. 基于本体的中医知识图谱构建[J].情报工程,2017,3(1):35-42.
[11]国务院办公厅. 国务院办公厅关于加快医学教育创新发展的指导意见[EB/OL]. (2020-09-23)[2025-10-27].https://www.gov.cn/zhengce/content/2020-09/23/content_5546373.htm.
[12]Smith BR. Atlas of knowledge: anyone can map by Katy Börner (review)[J]. Leonardo, 2016, 49(3): 278-279. DOI: 10.1162/LEON_r_01243.
[13]于骊, 邓为民, 张士杰, 等. 知识图谱赋能基础医学教育的实践[J].中华医学教育杂志,2024,44(7):513-516. DOI: 10.3760/cma.j.cn115259-20230729-00055.
[14]郭宏伟. 基于智能教育的高校在线课程知识图谱构建研究——以中国医学史为例[J].中国电化教育,2021(2):123-130. DOI: 10.3969/j.issn.1006-9860.2021.02.017.
[15]陈瑞安, 王琳琳, 朱朝阳, 等. 医学教育中跨学科教学方法的探索[J].中华医学教育杂志,2022,42(1):38-41. DOI: 10.3760/cma.j.cn115259-20210531-00700.
[16]Hu BH, Zheng LW, Zhu JY, et al. Teaching plan generation and evaluation with GPT-4: unleashing the potential of LLM in instructional design[J]. IEEE Transactions on Learning Technologies, 2024, 17: 1445-1459. DOI: 10.1109/TLT.2024.3384765.
[17]Cope B , Kalantzis M , Zhai CX ,et al.Maps of medical reason: applying knowledge graphs and artificial intelligence in medical education and practice[EB/OL].(2022-04-22)[2025-10-27]. https://link.springer.com/chapter/10.1007/978-3-030-95006-4_8.

Construction of a knowledge graph for the textbook History of Chinese Medicine based on large language models and Neo4j

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Wei Xiaotong, Wen Deliang. Application of dynamic cases based on large language models in pediatric medical education [J]. Chinese Journal of Medical Education, 2026, 46(4): 269-274.
[2]	Luo Yingyi, Li Jia, Sun Wenwen, Sheng Yueying, Weng Huachun, Chen Yanfeng. Application and evaluation of teaching effects of knowledge graph in promoting deep learning in epidemiology [J]. Chinese Journal of Medical Education, 2026, 46(4): 275-279.
[3]	Ma Xiaowen, Zuo Xu, Gong Jing, Gu Yajia. Evaluating the capability of large language models in answering questions on radiologic contrast agents [J]. Chinese Journal of Medical Education, 2026, 46(4): 315-320.
[4]	Sang Jianfeng, Dai Linghui, Shi Xianbiao, Zhang Guang, Sang yiran, Li Xiu. Design and application of small private online courses (SPOC) combined with knowledge graph in surgical operative medicine teaching [J]. Chinese Journal of Medical Education, 2026, 46(1): 42-46.
[5]	Zhu Jing, Wang Xiaofei, Zhou Weibing, Liu Hengyu. Visual analysis of research on generative artificial intelligence in medical education based on scientific citation databases [J]. Chinese Journal of Medical Education, 2025, 45(9): 661-665.
[6]	Fang Yaqing, Zhu Lina, Hu Huimei, Wu Haihua. Research on teaching reform of medical information literacy course based on digital knowledge graph [J]. Chinese Journal of Medical Education, 2025, 45(4): 288-292.
[7]	Chen Jiancong, Zhang Kunsong, Huang Xitai, Zhang Yunjian, Feng Shaoting, Kuang Ming. Applications and challenges of generative artificial intelligence in surgical teaching [J]. Chinese Journal of Medical Education, 2025, 45(3): 167-173.
[8]	Yan Jingrui, Deng Weimin, Zhang Shijie, Mo Jing, Wen Ke, Yu Li. Study on knowledge graph empowering the training of clinical thinking [J]. Chinese Journal of Medical Education, 2025, 45(12): 900-905.
[9]	Wei Xiaotong, Wen Deliang. Bibliometric analysis of research hotspots and trends in medical education from the perspective of ″new medicine″ [J]. Chinese Journal of Medical Education, 2024, 44(8): 570-575.
[10]	Jiang Zhehan, Feng Shicong, Wang Weimin. Exploratory practice of generative large language models in the construction of medical item banks [J]. Chinese Journal of Medical Education, 2024, 44(8): 561-569.
[11]	Yu Li, Deng Weimin, Zhang Shijie, Mo Jing, Wen Ke, Yan Jingrui. A practical study on knowledge graph empowering medical basic education [J]. Chinese Journal of Medical Education, 2024, 44(7): 513-516.
[12]	Yan Jingrui, Deng Weimin, Zhang Shijie, Mo Jing, Wen Ke, Yu Li. Construction and application of knowledge graph of core courses in basic medical education stage [J]. Chinese Journal of Medical Education, 2024, 44(3): 176-179.
[13]	Wang Min, Jin Hongbo, Zhang Shue, Li Qinglin, Wang Yanping, Zhou Shengyan, Yuan Jia, Wang Zijiao, Liu Xiaoning, He Jiajun, Cao Depin. Visual analysis of development context and research direction of functional experiment teaching research in China since the 21st century [J]. Chinese Journal of Medical Education, 2023, 43(11): 842-846.
[14]	Cao Zhenyu, Wang Lei, Tu Yue, Lin Feng. Exploring the key points and difficulties of therapeutic exercise course based on knowledge graph and item response theory [J]. Chinese Journal of Medical Education, 2022, 42(12): 1083-1088.
[15]	Yang Ning, Jin Siyan, Qin Hecong, Shi Lijun, Li Yutong, Zhao Jinsong. Innovation of teaching method and technology for undergraduate course of ophthalmology [J]. Chinese Journal of Medical Education, 2021, 41(9): 818-821.