Research on the Construction of TCM Diagnosis Model based on Large Language Model
DOI:
https://doi.org/10.54097/fpbnvg67Keywords:
TCM Syndrome Differentiation, Large Language Model, ChatGLM3, LoRA Fine Tuning, Data AnnotationAbstract
To solve many problems in TCM syndrome differentiation, including the lack of public data and quality differences, the problem of singleness and universality of models, and the lack of interpretability of models, a solution based on large language model ChatGLM3 combined with LoRA fine-tuning technology was proposed. The open source TCM-SD TCM syndrome differentiation data set was adopted, and after data filtering and integration optimization, 1027 TCM syndrome differentiation definition data sets, 41180 consultation training data and 5485 testing and verification data were obtained, so that the model could deeply learn the specialized knowledge of TCM syndromes and the actual consultation records of TCM syndrome differentiation. The experimental results show that the evaluation indexes of two different trainings using LoRA fine-tuning technology are significantly improved by about 20%.
Downloads
References
[1] General Office of the State Council of the People’s Republic of China. The 14th Five Year Plan for the development of traditional Chinese medicine [EB/OL]. (2022-03-03)[2024-02-03]. https://www.gov. cn/gongbao/ content/ 2022/ content_ 568 6029.htm.
[2] Wang Ye. Research on Intelligent Chinese Medicine Discriminatory Method Based on Deep Learning [D]. Henan University of Science and Technology,2022.000120.
[3] SONG Yijie, MA Suya, DAI Yasheng, et al. Key issues and technical challenges of artificial intelligence-assisted Chinese medicine discernment[J]. China Engineering Science,2024,26 (02): 234-244.
[4] YANG Lele, WANG Zhe, YAO Keyu, LIU Lihong, ZHU Yan. Prospective thoughts on the application of big language modelling in the field of traditional Chinese medicine[J/OL]. Chinese Journal of Traditional Chinese Medicine, 1-20.
[5] Wang R, Pan C, Chen J, et al. Construction of a knowledge framework system for intelligent diagnosis in Chinese medicine [J]. Journal of Traditional Chinese Medicine, 2024, 65(4): 341-346.
[6] LIU Yuehan, HUO Haobin, JIN Changuo. Practice and exploration of building enterprise-level private big language model assistant based on ChatGLM3 and RPA technology[J]. Architectural Design Management,2023,40(12):33-40.
[7] Hu E J , Shen Y , Wallis P ,et al. LoRA: Low-Rank Adaptation of Large Language Models[J]. 2021.DOI: 10. 48550/ arXiv. 2106.09685.pdf.
[8] PAPINENI K, ROUKOS S, WARD T, et al. Bleu: a method for automatic evaluation of machine translation [C]// Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 2002:311-318.
[9] LIN C Y. Rouge: A package for automatic evaluation of summaries[C]//Text summarisation branches out. 2004:74-81.
[10] Zhang Jundong, Yang Songhuah,Liu Jiangfeng,et al.AIGC empowers the revitalisation of ancient Chinese medicine:the construction of the Huang-Di grand model[J].Library Forum, 2024, 44(10):103-112.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
