Method and device for constructing medical knowledge graph

Abstract

The invention relates to a method and device for constructing a medical knowledge graph. In the method, first, extraction and entity recognition are performed on words of a medical knowledge data source, bodies which entities belong to are determined, a feature vector of an entity pair composed of any two entities in one sentence is constructed, and includes entity information and information of the bodies which the entities belong to, then all the entities are sieved, classification is performed based on a preset relation between the entities, first triplet data of two entities and the entityrelation is obtained and finally introduced into a database for visualization, and then the medical knowledge graph is obtained. In the embodiment of the method, medical knowledge can be effectivelysorted from case history or medical treatment knowledge documents and other data, the medical knowledge graph is automatically generated, and then a detailed and effective reference scheme can be provided when a doctor makes a diagnosis.

Description

technical field [0001] The present invention relates to the field of software technology, in particular to a method and device for constructing a medical knowledge map. Background technique [0002] Medical records are written records made by medical personnel on the occurrence, development, outcome, examination, diagnosis, treatment and other medical activities of patients. Medical records are not only a summary of clinical practice, but also a legal basis for exploring the law of diseases and handling medical disputes. They are the precious wealth of the country. In clinical medicine, effectively sorting out medical records and digging out doctors' clinical experience is of great significance to medical progress. [0003] However, in the process of implementing the embodiments of the present invention, the inventors found that in actual diagnosis and treatment, due to the differences in knowledge reserve and clinical experience of medical personnel, different medical pers...

AI Technical Summary

Problems solved by technology

[0003] However, in the process of implementing the embodiments of the present invention, the inventors found that in actual diagnosis and treatment, due to the differences in knowledge reserve and clinical experience of medical personnel, different medical personnel often use different diagnostic methods for the same disease or symptom. And medication habits are not the same, but some results are significant while others have little effect

However, through the organization of medical personnel in the industry to exchange treatment experience, it not only requires a lot of manpower and material resources, but also does not have real-time live and universal sharing

Images