面向高层语义抽象的中医案例分析系统：基于提示与RAG的优化
Traditional Chinese Medicine Case Analysis System for High-Level Semantic Abstraction: Optimized with Prompt and RAG
- Chongqing Jiudun Technology Co., Ltd.（重庆九盾科技有限公司）
- School of Mechanical Science & Engineering, Huazhong University of Science and Technology（华中科技大学机械科学与工程学院）
- Xinjiang Medical University（新疆医科大学）
- School of Nursing, Shanghai Jiao Tong University（上海交通大学护理学院）
- School of Mathematical Sciences, Shanghai Jiao Tong University（上海交通大学数学科学学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一个中医案例分析系统，通过爬取5000余例临床案例构建结构化数据库，结合RAG、重排序与Jieba关键词匹配的两阶段检索优化，并利用ERNIE与DeepSeekv2模型生成高质量JSON输出。
AI中文摘要：
本文详细阐述了一项利用网络爬虫构建中医临床案例数据库的技术方案。借助包括360doc在内的多个平台，我们收集了超过5,000个中医临床案例，进行了数据清洗，并以患者详情、病机、证候和注释等关键字段对数据集进行了结构化处理。使用百度ERNIE Speed 128K API去除冗余信息，并通过DeepSeekv2 API生成最终答案，以标准JSON格式输出结果。我们在检索过程中利用RAG和重排序技术优化数据召回，并开发了一种混合匹配方案。通过将两阶段检索方法与基于Jieba的关键词匹配相结合，我们显著提升了模型输出的准确性。
英文摘要：
This paper details a technical plan for building a clinical case database for Traditional Chinese Medicine (TCM) using web scraping. Leveraging multiple platforms, including 360doc, we gathered over 5,000 TCM clinical cases, performed data cleaning, and structured the dataset with crucial fields such as patient details, pathogenesis, syndromes, and annotations. Using the $Baidu\_ERNIE\_Speed\_128K$ API, we removed redundant information and generated the final answers through the $DeepSeekv2$ API, outputting results in standard JSON format. We optimized data recall with RAG and rerank techniques during retrieval and developed a hybrid matching scheme. By combining two-stage retrieval method with keyword matching via Jieba, we significantly enhanced the accuracy of model outputs.
