名老中医临床经验知识图谱构建方法探索  

Exploration on construction method of Knowledge Graph of veteran TCM physicians’ clinical experiences

作　　者：刘凡 王明强 李凌香 何丽云[1] LIU Fan;WANG Ming-qiang;LI Ling-xiang;HE Li-yun(Institute of Basic Research in Clinical Medicine,China Academy of Chinese Medical Sciences.Beijing 100700,China;TCM Data Centre,China Academy of Chinese Medical Sciences,Beijing 100700,China)

机构地区：[1]中国中医科学院中医临床基础医学研究所,北京100700 [2]中国中医科学院中医药数据中心,北京100700

出　　处：《中华中医药杂志》2021年第4期2281-2285,共5页China Journal of Traditional Chinese Medicine and Pharmacy

基　　金：国家自然科学基金面上项目(No.81673964)。

摘　　要：知识图谱作为一种结构化的语义知识库,在互联网大数据时代已成为知识表达、组织、管理的有效工具,在智能信息服务领域具有重要的应用价值。本研究以姚乃礼医师临床经验为研究对象,利用非结构化文本数据,基于Neo4j图数据库构建知识图谱,模式层图谱包含19个节点、18个标签、27条关系和17种关系类型;数据层图谱包含18个标签和524个节点,17种关系类型和1 097条关系,10种属性和622个属性值。构建完成的知识图谱实现了可视化展示和语义化搜索的功能,为分析和展示医师临证思维及其诊疗特点提供新的工具和系统流程,也为人工智能时代知识问答、辅助诊疗奠定方法学基础。As a structured semantic knowledge base,Knowledge Graph has become an effective tool for knowledge expression,organization and management in the era of big data on the Internet,and has important application value in the field of intelligent information services.In this study,YAO Nai-li’s clinical experience was taken as the research object.Using unstructured text data,the Knowledge Graph was constructed based on Neo4 j graph database.The mode layer includes 19 nodes,18 labels,27 relations and 17 types of relations,and the data layer contains 524 nodes under 18 lables,1097 relationships under 17 relationship types,and 622 property keys under 10 properties.The constructed Knowledge Graph realizes the functions of visual display and semantic search.It provides a new tool and system flow for analyzing and displaying doctors’clinical thinking and diagnosis and treatment characteristics,and also lays a methodological foundation for knowledge question and answer and assistant diagnosis and treatment in the era of artificial intelligence.

关 键 词：名老中医 知识图谱 方法学 临证经验 姚乃礼 

分 类 号：R249[医药卫生—中医临床基础]