基于知识元标引与知识图谱的中医古籍知识表示、获取与发现研究

Research on Knowledge Representation,Acquisition and Discovery of Ancient Chinese Medicine Books Based on Knowledge Element Indexing and Knowledge Graph

中医古籍是记录和传承中医药的重要载体,蕴含着海量的医学知识,但现有的古籍知识表示与获取方法未能充分挖掘其中的动态知识与诊疗思维。本研究利用知识元标引与知识图谱技术深入解析不同类型的中医古籍体例、内容以及知识内核,提出了“病脉证并治”知识元语义网络表示模型,优化了现有的知识元标引方法,进而构建蕴含中医诊疗思维的中医古籍知识图谱。并利用Neo4j数据库的Cypher查询语句在知识图谱中对消渴病进行了临床特征、“三消”分治、与胰相关等知识发现,为中医理论与临床创新提供了新思路。

Ancient traditional Chinese medicine(TCM)books,which contains a large amount of medical knowledge,are important carriers for recording and inheriting TCM.But the existing methods of knowledge representation and acquisition of ancient TCM books can't fully explore the dynamic knowledge and thinking of diagnosis and treatment.This study used knowledge element indexing and knowledge graph technology to deeply analyze the style,content,and knowledge core of different types of ancient TCM books.This article puts forward the knowledge element-semantic network representation model of"disease-pulse-syndrome combined treatment",which optimizing the existing indexing methods of knowledge element.The knowledge graph of ancient TCM books was constructed,which containing diagnosis and treatment thinking.And the Cypher query sentence of Neo4j database was used to discover the clinical characteristics of Xiaoke,the separation and treatment of"Sanxiao"and the related knowledge between Xiaoke and pancreas in the knowledge graph.This study provides a new idea for theoretical and clinical innovation of TCM with the knowledge of ancient TCM books.