计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6A): 250300167-7.doi: 10.11896/jsjkx.250300167

• 人工智能 • 上一篇    下一篇

基于云服务与RAG技术的中成药智能推荐系统

唐翎双1, 李威1, 黄萍萍1, 黄玺行1, 王庆香1,刘继洪2   

  1. 1 广州中医药大学医学信息工程学院 广州 510000
    2 佛山市中医院治未病中心 广东 佛山 528000
  • 出版日期:2026-06-16 发布日期:2026-06-12
  • 通讯作者: 王庆香(wang_q_x@qq.com)
  • 作者简介:(lingshuangtang@outlook.com)

Intelligent Recommendation System of Chinese Patent Medicine Based on Cloud Service and RAG Technology

TANG Lingshuang1, LI Wei1, HUANG Pingping1, HUANG Xihang1, WANG Qingxiang1, LIU Jihong2   

  1. 1 Guangzhou University of Chinese Medicine,School of Medical Information Engineering,Guangzhou 510000,China
    2 Foshan Hospital of Traditional Chinese Medicine,Preventive Treatment Center,Foshan,Guangdong 528000,China
  • Published:2026-06-16 Online:2026-06-12
  • About author:TANG Lingshuang,born in 2005,undergraduate.Her main research interests include artificial intelligence and natural language processing.
    WANG Qingxiang,born in 1975,Ph.D,associate professor.His main research interests include medical image processing and artificial intelligence.

PDF (PC)

41

摘要： 近年来,大型语言模型(LLM)在医疗领域的应用虽取得显著进展,但其在中医药场景中仍面临两大核心挑战:1)算力资源的动态需求与成本控制之间的矛盾;2)传统本地化部署架构难以支撑中医药知识库的实时更新与复杂推理需求。为此,文中提出一种基于云原生架构与检索增强生成(RAG)技术的中成药智能推荐系统,通过阿里云百炼平台的弹性算力资源与通义千问-Max-Latest大模型,结合DashScope API接口与低代码开发平台AppBuilder,构建了动态更新的在线中成药知识库。以感冒病症为验证场景,系统整合了《中国药典》、中医临床诊疗术语体系及佛山市中医院2022年1月1日至2024年12月31日关于感冒病的患者个性化问诊数据,深度融合了RAG技术驱动的知识检索与生成式推理能力。通过多轮交互式问诊与动态推荐策略,系统能够基于患者症状特征、体质辨识及实时反馈,生成符合中医辨证论治原则的个性化用药方案。本系统通过云服务的弹性扩展机制与RAG技术的高效知识整合,有效解决了传统中成药推荐系统在知识库静态化与算力资源动态调度受限方面的双重挑战,为中医药智能化发展提供了可落地的技术方案,同时显著提升了治疗方案的精准度与患者满意度。

关键词: 中成药推荐, RAG技术, 云服务, 中医辨证论治, 个性化医疗

Abstract: In recent years,although significant progress has been made in the application of large-scale language models(LLMs) in the medical field,they still face two core challenges in TCM scenarios:firstly,the contradiction between the dynamic demand of arithmetic resources and the cost control,and secondly,the difficulty of the traditional localised deployment architecture to support real-time updating of the knowledge base of TCM and the demand for complex reasoning.This paper proposes an intelligent recommendation system for pCms based on cloud-native architecture and retrieval-enhanced generation(RAG) technology,which constructs a dynamically updated online pCm knowledge base through the elastic arithmetic resources of AliCloud's Hundred Refinement Platform and Tongyi Thousands of Questions-Max-Latest Big Model,combined with the DashScope API interface and the low-code development platform,AppBuilder.Taking cold and flu as a validation scenario,the system integrates the Chinese Pharmacopoeia,the Chinese medicine clinical diagnosis and treatment terminology system,and the personalised consultation data on cold and flu from Foshan Hospital of Traditional Chinese Medicine from 1 January 2022 to 31 December 2024,and integrates in-depth knowledge retrieval and generative reasoning capability driven by RAG technology.Through multiple rounds of interactive consultation and dynamic recommendation strategies,the system is able to generate a personalised medication plan based on patients' symptom characteristics,constitution identification and real-time feedback,which is in line with the principles of Chinese medicine diagnosis and treatment.This system effectively addresses the dual challenges of static knowledge bases and constrained dynamic allocation of computing resources in traditional pCm recommendation systems through the elastic scaling mechanism of cloud services and the efficient knowledge integration of RAG technology.It provides a feasible technical solution for the intelligent development of traditional Chinese medicine,while significantly improving the precision of treatment plans and patient satisfaction.

Key words: Proprietary Chinese medicine recommendation, Retrieval augmented generation technology, Cloud services, TCM syndrome differentiation and treatment, Personalized medicine

中图分类号: 

  • TP391
[1] DONG G T,GAO L.On the Inheritance and Development of Famous Traditional Chinese Medicine Practitioners' Diagnostic and Treatment Experience under Artificial Intelligence Technology[J].China Journal of Traditional Chinese Medicine and Pharmacy,2023,38(9):4026-4029.
[2] SONG Y J,MA S Y,DAI Y S,et al.Key Issues and Technical Challenges of Artificial Intelligence-assisted Syndrome Differentiation in Traditional Chinese Medicine[J].Chinese Engineering Science,2024,26(2):234-244.
[3] YIN Y D,ZHANG H L,GAO R.Discussion on the Problems and Current Status of Rational Use of Chinese Patent Medicine Based on Prescription Review and Prescription Analysis[J].China New Drugs Journal,2023,32(4):364-371.
[4] LEWIS P,PEREZ E,PIKTUS A,et al.Retrieval-augmented generation for knowledge-intensive NLP tasks[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems.New York:ACM,2020:9459-9474.
[5] CHEN J M,ZHANG W D,TAN R P.Drug Recommendation Algorithm Based on Dialogue Structure and Graph Attention Network[J].Journal of Computer Science and Exploration,2024,18(8):2130-2139.
[6] CHENG Y,LÜ S,CHEN G X.Research on Intelligent Q&A Technology of Standard Literature Based on Large Models[J].Information Technology and Standardization,2024(8):38-43.
[7] DU Y,ZHAO G Z,YE H R,et al.Visual Analysis of Artificial Intelligence Application Research Literature in the Field of Traditional Chinese Medicine[J].China Journal of Traditional Chinese Medicine Information,2023,30(5):44-49.
[8] LIAO Y,JIANG S,WANG Y,et al.MING-MOE:Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts[J].arXiv:2404.09027,2024.
[9] ZHAO R C,CHEN H L,WANG W S,et al.Retrieving Multimodal Information for Augmented Generation:A Survey[J].arXiv:2303.10868,2023.
[10] SONG Y J,MA S Y,DAI Y S,et al.Key Issues and Technical Challenges of Artificial Intelligence-assisted Syndrome Differentiation in Traditional Chinese Medicine[J].Chinese Engineering Science,2024,26(2):234-244.
[11] YANG R,LIU H,MARRESE-TAYLOR E,et al.KG-Rank:Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques[C]//Proceedings of the 23rd Workshop on Biomedical Natural Language Processing.2024.
[12] LU Y,WEI Z H,ZOU W S,et al.Artificial Intelligence Biology:An Important Strategic Resource and Competitive Hotspot for Future Modernization Research of Traditional Chinese Medicine[J].Journal of Nanjing University of Chinese Medicine,2021,37(3):331-336.
[13] SHENG X Y,SHAO Q.ABS-HDL:A Chinese Medical Named Entity Recognition Model Based on BIASRU[J].Modeling and Simulation,2024,13(4):4075-4089.
[14] LIN J Y,LI S P,GUO Y,et al.The Current Status,Problems and Suggestions of Artificial Intelligence in Promoting the Development of Traditional Chinese Medicine[J].World Traditional Chinese Medicine,2022,17(6):864-867.
[15] SINGHAL K,AZIZI S,TU T,et al.Large language models encode clinical knowledge[J].Nature,2023,620:172-180.
[16] CHEN Q T,NI J W,XU J,et al.Research on Traditional Chinese Medicine Prescription Generation Driven by Generative Artificial Intelligence GPT-4[J].China Pharmacy,2023,34(23):2825-2828.
[17] YIN Z C.Research on the Generation of Traditional ChineseMedicine Prescriptions Based on Contrastive Learning and Graph Networks[D].Guangzhou:Guangzhou University,2023.
[18] SUN Z R,YOU X Q,HAN Q C,et al.Progress and Current Status of Artificial Intelligence in the Field of Traditional Chinese Medicine[J].World Science and Technology-Modernization of Traditional Chinese Medicine,2021,23(6):1803-1811.
[19] SHAZEER N,STERN M.The computational costs of large language models[J].arXiv:2205.05198,2022.
[20] HUANG J,ZHAO Y,LI H,et al.Cloud-based AI platforms for large language models[J].IEEE Transactions on Cloud Computing,2023,11(3):899-908.
[21] LI J,LI D,SAVARESE S,et al.BLIP-2:Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models[J].arXiv:2301.12597.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发