Chinese text recognition and knowledge graph of Shen Nong Ben Cao Jing based on BERT pretrained language models

Lin Tong; Xu Tong; Lei Lei; Ziling Zeng; Sihong Liu; Lei Zhang; Cheng Wang; Sharmila Upadhyaya; Hongjun Yang; Huamin Zhang

doi:10.1097/gscm.0000000000000017

摘要：Objective:To construct the knowledge graph of Shen Nong Ben Cao Jing,analyze basic knowledge of materia medica,explore implicit knowledge,and conduct visualization display,as well as provide methodological references for the study of ancient traditional Chinese medicine(TCM)books. Background:The research and utilization of ancient TCM books are relatively limited at present.With the rapid development of artificial intelligence,knowledge graph-related technology has brought light to this field. Methods:The types of knowledge entities and relationships between entities in Shen Nong Ben Cao Jing were analyzed.A training corpus data set was produced by using the begin-inside-outside sequence labeling method,a self-developed Chinese natural language processing text labeling system was used for text labeling,the bidirectional encoder representations from transformers model was used to recognize named entities,the relationships between entities were set based on rules and semantic associations,the data into the Neo4j-community 4.4.9 graph database was imported by using Cypher language for storage and visualization display after knowledge fusion,and finally,a knowledge graph was constructed. Results:The knowledge graph of Shen Nong Ben Cao Jing included 5273 nodes and 11,064 relationships.The schema layer contained 14 entity types and 15 relationship types.Through the query,knowledge can be visualized from the aspects of classification,property,and 7 mutual relationships of herbal combinations. Conclusion:The knowledge graph constructed in this study directly refiects the knowledge recorded in Shen Nong Ben Cao Jing and the relationship between them,which is suitable for knowledge mining and intuitive multidimensional display of ancient TCM books.