基于ChatGLM的中医妇科知识图谱自动化构建与临床决策支持研究OA

The study aims to construct a knowledge graph for traditional Chinese medicine(TCM)gynecology based on large language models.The goal is to systematically organize and present the complex knowledge system of this field,revealing the in-trinsic connections and evolution patterns among diseases,thereby enhancing the precision of clinical decision-making.The study selected 349 TCM gynecology papers from China National Knowledge Infrastructure(CNKI).ChatGLM was used with multi-round prompt templates to achieve zero-shot entity relationship extraction.Evaluation metrics were designed to objective-ly assess the extraction results.Efficient processing was achieved through API interfaces interacting with the model.The Neo4j graph database was used to construct and visualize the knowledge graph.The study shows that ChatGLM performs better in knowledge extraction compared to traditional Bi-LSTM-CRF models,significantly improving precision,recall and F1 scores.The constructed knowledge graph effectively supports the clinical decision-making in TCM gynecology,enhancing the diagnostic efficiency and accuracy and demonstrating the practical value.