大语言模型驱动的中医智能诊疗研究思路与方法

杨涛; 王欣宇; 朱垚; 胡孔法; 朱学芳

doi:10.14148/j.issn.1672-0482.2023.0967

大语言模型驱动的中医智能诊疗研究思路与方法

doi: 10.14148/j.issn.1672-0482.2023.0967

杨涛^{1, 2,},
王欣宇²,
朱垚³,
胡孔法^{2, 4, 5, 6},
朱学芳^1, ,

1.
南京大学信息管理学院, 江苏南京 210023
2.
南京中医药大学人工智能与信息技术学院, 江苏南京 210023
3.
南京中医药大学第一临床医学院, 江苏南京 210023
4.
江苏省中医药防治肿瘤协同创新中心, 江苏南京 210023
5.
江苏省中医外用药开发与应用工程研究中心, 江苏南京 210023
6.
江苏重大健康风险管理与中医药防控政策研究中心, 江苏南京 210023

基金项目:

江苏省高校哲学社会科学研究项目 2021SJA0333

国家自然科学基金面上项目 82174276

国家自然科学基金面上项目 82074580

国家重点研发计划 2022YFC3500201

江苏省重点研发计划 BE2022712

中国博士后科学基金面上项目 2021M701674

江苏省博士后科研资助计划项目 2021K457C

江苏高校“青蓝工程”资助项目 2021

详细信息

作者简介:
杨涛，男，副教授，E-mail：380786@njucm.edu.cn

通讯作者:
朱学芳，男，教授，博士生导师，主要从事人工智能、模式识别的研究, E-mail：xfzhu@nju.edu.cn

中图分类号: R2-03
计量
- 文章访问数: 462
- HTML全文浏览量: 62
- PDF下载量: 68
- 被引次数: 0
出版历程
- 收稿日期: 2023-08-02
- 网络出版日期: 2023-11-10
- 发布日期: 2023-10-10

Research Ideas and Methods of Intelligent Diagnosis and Treatment of Traditional Chinese Medicine Driven by Large Language Model

YANG Tao^{1, 2
,},
WANG Xin-yu²,
ZHU Yao³,
HU Kong-fa^{2, 4, 5, 6},
ZHU Xue-fang^{1
, ,}

1.
School of Information Management, Nanjing University, Nanjing 210023, China
2.
School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China
3.
The First School of Clinical Medicine, Nanjing University of Chinese Medicine, Nanjing 210023, China
4.
Jiangsu Collaborative Innovation Center of Traditional Chinese Medicine in Prevention and Treatment of Tumor, Nanjing 210023, China
5.
Jiangsu Provincial Research Center for the Development and Application of Traditional Chinese Medicine External Medicines, Nanjing 210023, China
6.
Jiangsu Research Center for Major Health Risk Management and TCM Control Policy, Nanjing 210023, China

摘要

摘要: 中医诊疗智能化是中医现代化发展的重要方向。大语言模型技术推动了人工智能发展，将其与中医药结合，构建大语言模型驱动的中医智能诊疗方法和应用，对中医创新发展具有重要意义。在分析和总结中医智能诊疗面临的挑战基础上，提出构建涵盖语料准备、知识表征、指令微调和强化学习于一体，大语言模型驱动的中医智能诊疗研究思路与方法，以期为中医诊疗的智能化研究提供参考。
- 中医诊疗 /
- 智能诊疗 /
- 大语言模型 /
- 思路与方法
Abstract: Intelligent diagnosis and treatment of traditional Chinese medicine is an important direction for the modern development of traditional Chinese medicine. Large language model technology has promoted the development of artificial intelligence. Combining it with traditional Chinese medicine to build intelligent diagnosis and treatment methods and applications of traditional Chinese medicine driven by large language models is of great significance to the innovative development of traditional Chinese medicine. On the basis of analyzing and summarizing the challenges faced by intelligent diagnosis and treatment of traditional Chinese medicine, it is proposed to build research ideas and methods for intelligent diagnosis and treatment of traditional Chinese medicine driven by large language models based on large language models, covering corpus preparation, knowledge representation, instruction fine-tuning and reinforcement learning, in order to provide reference for intelligent research on traditional Chinese medicine diagnosis and treatment.
- traditional Chinese medicine diagnosis and treatment /
- intelligent diagnosis and treatment /
- large language model /
- ideas and methods

HTML全文

图 1 中医智能诊疗大语言模型构建思路

Figure 1. Ideas for constructing a large language model for intelligent diagnosis and treatment of traditional Chinese medicine

下载: 全尺寸图片幻灯片

参考文献(19)

[1]	朱文锋. 证素辨证学[M]. 北京: 人民卫生出版社, 2008: 1-2. ZHU WF. Syndrome Differentiation[M]. Beijing: People's medical publishing house, 2008: 1-2.
[2]	杨涛, 朱学芳. 中医辨证智能化研究现状及发展趋势[J]. 南京中医药大学学报, 2021, 37(4): 597-601. doi: 10.14148/j.issn.1672-0482.2021.0597 YANG T, ZHU XF. Discussion on the status and development trend of research on intellectualization of Chinese medicine syndrome differentiation[J]. J Nanjing Univ Tradit Chin Med, 2021, 37(4): 597-601. doi: 10.14148/j.issn.1672-0482.2021.0597
[3]	文志华, 夏帅帅, 刘东波, 等. 中医智能辨证诊断技术的演进与问题探讨[J]. 世界科学技术-中医药现代化, 2021, 23(11): 4298-4304. https://www.cnki.com.cn/Article/CJFDTOTAL-SJKX202111050.htm WEN ZH, XIA SS, LIU DB, et al. Discussion on the evolution and problems of intelligent syndrome differentiation diagnosis technology in traditional Chinese medicine[J]. Mod Tradit Chin Med Mater Med World Sci Technol, 2021, 23(11): 4298-4304. https://www.cnki.com.cn/Article/CJFDTOTAL-SJKX202111050.htm
[4]	韦昌法, 晏峻峰. 从知识表示与推理方法探讨中医数字辨证发展[J]. 中华中医药杂志, 2019, 34(10): 4471-4473. https://www.cnki.com.cn/Article/CJFDTOTAL-BXYY201910004.htm WEI CF, YAN JF. Study on Chinese medicine digital syndrome differentiation with its knowledge representation and reasoning methods[J]. China J Tradit Chin Med Pharm, 2019, 34(10): 4471-4473. https://www.cnki.com.cn/Article/CJFDTOTAL-BXYY201910004.htm
[5]	刘广, 孙艳秋, 裴媛. 基于C4.5决策树算法的中医胃炎实验数据分类挖掘研究[J]. 中华中医药学刊, 2016, 34(12): 2958-2961. https://www.cnki.com.cn/Article/CJFDTOTAL-ZYHS201612041.htm LIU G, SUN YQ, PEI Y. Classified mining of TCM gastritis based on C4.5 decision tree algorithm[J]. Chin Arch Tradit Chin Med, 2016, 34(12): 2958-2961. https://www.cnki.com.cn/Article/CJFDTOTAL-ZYHS201612041.htm
[6]	徐璡, 许朝霞, 许文杰, 等. 基于贝叶斯网络原理的835例冠心病病例中医证候分类研究[J]. 上海中医药杂志, 2014, 48(1): 10-13. https://www.cnki.com.cn/Article/CJFDTOTAL-SHZZ201401005.htm XU J, XU ZX, XU WJ, et al. Classification of TCM syndromes in 835 cases of coronary heart disease: On the basis of Bayesian networks principle[J]. Shanghai J Tradit Chin Med, 2014, 48(1): 10-13. https://www.cnki.com.cn/Article/CJFDTOTAL-SHZZ201401005.htm
[7]	陆萍, 林坤辉, 周昌乐. 基于神经网络的中医面诊证素辨证的研究[J]. 计算机应用研究, 2008, 25(9): 2655-2657. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ200809023.htm LU P, LIN KH, ZHOU CL. Research of TCM face diagnosis and symptom factor based on NN[J]. Appl Res Comput, 2008, 25(9): 2655-2657. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ200809023.htm
[8]	DEVLIN J, CHANG MW, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[EB/OL]. [2023-08-01]. https://arxiv.org/abs/1810.04805.
[9]	ZHANG ZY, HAN X, LIU ZY, et al. ERNIE: Enhanced language representation with informative entities[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy. Stroudsburg, PA, USA: Association for Computational Linguistics, 2019: 1441-1451.
[10]	TOM BB, BENJAMIN M, NICK R, et al. Language models are few-shot learners[C]. NIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, B.C., Canada, 2020: 1877-1901.
[11]	ZHOU C, LI Q, LI C, et al. A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT[EB/OL]. [2023-08-01]. https://arxiv.org/abs/2302.09419.
[12]	LIU YH, HAN TL, MA SY, et al. Summary of ChatGPT-related research and perspective towards the future of large language models[EB/OL]. [2023-08-01]. https://arxiv.org/abs/2304.01852.
[13]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all You need[EB/OL]. [2023-08-01]. https://arxiv.org/abs/1706.03762.
[14]	韩家炜, MICHELINE K, 裴健, 等. 数据挖掘: 概念与技术[M]. 北京: 机械工业出版社, 2012. FAN JW, MICHELINE K, PEI J, et al. Data mining: Concepts and techniques[M]. Beijing: China machine press, 2012.
[15]	BALESTRIERO R, IBRAHIM M, SOBAL V, et al. A cookbook of self-supervised learning[EB/OL]. [2023-08-01]. https://arxiv.org/abs/2304.12210.
[16]	DU ZX, QIAN YJ, LIU XA, et al. GLM: General language model pretraining with autoregressive blank infilling[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin, Ireland. Stroudsburg, PA, USA: Association for Computational Linguistics, 2022: 320-335.
[17]	ZHAO WX, ZHOU K, LI JY, et al. A survey of large language models[EB/OL]. [2023-08-01]. https://arxiv.org/abs/2303.18223.
[18]	赵朝阳, 朱贵波, 王金桥. ChatGPT给语言大模型带来的启示和多模态大模型新的发展思路[J]. 数据分析与知识发现, 2023, 7(3): 26-35. https://www.cnki.com.cn/Article/CJFDTOTAL-XDTQ202303005.htm ZHAO CY, ZHU GB, WANG JQ. The inspiration brought by ChatGPT to LLM and the new development ideas of multi-modal large model[J]. Data Anal Knowl Discov, 2023, 7(3): 26-35. https://www.cnki.com.cn/Article/CJFDTOTAL-XDTQ202303005.htm
[19]	陈永伟. 超越ChatGPT: 生成式AI的机遇、风险与挑战[J]. 山东大学学报(哲学社会科学版), 2023(3): 127-143. https://www.cnki.com.cn/Article/CJFDTOTAL-SDZS202303012.htm CHEN YW. Beyond ChatGPT: Opportunities, risks, and challenges from generative AI[J]. J Shandong Univ Philos: Soc Sci, 2023(3): 127-143. https://www.cnki.com.cn/Article/CJFDTOTAL-SDZS202303012.htm