基于命名实体识别的《神农本草经》知识图谱构建及可视化分析OACSTPCD

Objective To construct the knowledge map of Shen Nong Ben Cao Jing;To analyze basic knowledge of materia medica,explore implicit knowledge,and conduct visualization display;To provide methodological references for the study of ancient books.Methods The types of knowledge entities and relationships between entities involved in the Shen Nong Ben Cao Jing were organized and expressed.A training corpus dataset was produced using the BIO sequence labeling method;a self-developed CNLP text labeling system was used for text labeling;the BERT model was used to recognize named entities;the relationships between entities were set based on rules and semantic associations;the data were imported into the Neo4j-community 4.4.9 graph database using Cypher language for storage and visualization display after knowledge fusion;finally a knowledge graph was constructed.Results The knowledge map of Shen Nong Ben Cao Jing included 5 273 nodes and 11 064 relationships.The pattern layer contained 14 entity classes and 16 relationship types.Through Cypher language query,knowledge was visualized from the aspects of TCM classification,medicinal property theory,compatibility of seven emotions and application of TCM.Conclusion The knowledge graph constructed in this study intuitively reflects the knowledge recorded in Shen Nong Ben Cao Jing and the recessive relationship,which is suitable for knowledge mining and intuitive multi-dimensional display of ancient TCM books.