Construction And Research Of Knowledge Graph Based On "Chinese Pharmacopoeia"

With the rapid development of Internet technology in China,a large amount of data and information have been generated,and how to realize the semantic analysis of big data by machine has become particularly important.Among them,retrieval and application in massive data is a key problem,and the concept of knowledge graph can solve this problem well.The health security field represented by the medical and pharmaceutical industry is one of the fields where knowledge graphs are widely used.How to extract useful medical information from a large amount of data is a key issue in current medical big data analysis."The Pharmacopoeia of the People’s Republic of China",as China’s code to ensure the quality of medicines,is scientific,advanced,normative and authoritative.However,most of the current research on the pharmacopoeia is that medicine and medical experts discuss the book from the perspective of medical content.There are few scholars and experts based on the knowledge map technology to play the maximum role of the pharmacopoeia,and there are also certain gaps in the research on the pharmacopoeia and DRG payment methods.The main work of this paper is as follows:(1)Using the mainstream named entity recognition technology BiLSTM-CRF to perform named entity recognition on the "Pharmacopoeia of the People’s Republic of China"(2020)(hereinafter referred to as "Chinese Pharmacopoeia"),realizing the named entity recognition of the drug data in the second part of the Pharmacopoeia.(2)Associate the Chinese Pharmacopoeia with relevant databases such as the medical insurance catalogue,production enterprise database,and operating enterprise database,and build a knowledge map for each drug in the Chinese Pharmacopoeia,so as to realize the approval number,specification,Correlation of data related to dosage forms,ingredients,ATC classifications,etc.It fills the gap in the research field of Chinese Pharmacopoeia map construction,and has a high reference value for the visual display of the Pharmacopoeia of the People’s Republic of China and the supervision of drug manufacturers.(3)Sankey diagrams of DRG-DRUG-ATC and ATC-DRUG-DRG models were constructed.The two DRG models provide certain data support for effectively adjusting the hospital charging structure,researching and discussing how to find DRG patient group related data and DRG cost data through drugs,and for the national medical insurance DRG payment reform.(4)The drug map,enterprise map,enterprise heat map,drug heat map,and enterprise overview map were constructed,which provided data support for the route planning of the newly added production and operation enterprise management or offline supervision by the regional drug administrations.