A method and device for constructing a medical knowledge graph

Abstract

An embodiment of the present invention provides a method and device for constructing a medical knowledge map. The method includes: obtaining diagnostic evidence information, clinical manifestation information, and disease information; according to the diagnostic evidence information, clinical manifestation information, and disease information, using preset diagnostic criteria, Clinical criteria and diagnostic methods of diseases, establish the relationship between diseases and multi-level clinical manifestations, and the relationship between clinical manifestations and diagnostic evidence at each level; The association relationship of diagnostic evidence, constructing a medical knowledge map that includes the association relationship between diagnostic evidence entities, clinical manifestation entities and disease entities. The present invention adds clinical manifestation information to the medical knowledge map, and establishes the relationship between diagnostic evidence and disease through multi-layered clinical manifestations, so that the medical knowledge map can fully reflect the doctor's differential diagnosis ideas.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a method and device for constructing a medical knowledge graph. Background technique [0002] Compared with the traditional knowledge representation, the knowledge graph has the characteristics of rich semantics, friendly structure, massive scale, and excellent quality. When medical knowledge is represented in the knowledge graph, the advantages of the knowledge graph and related technologies can be used for reasoning and application. At present, the knowledge map representing medical knowledge, its data model is mostly the direct relationship between symptoms and other evidence and disease. Using the current knowledge map, the direct relationship between symptoms and other evidence can not be considered for the direction of the disease, and the accuracy of the disease inference results is also low. not tall. Contents of the invention [0003] I...

AI Technical Summary

Problems solved by technology

At present, the knowledge map representing medical knowledge, its data model is mostly the direct relationship between symptoms and other evidence and disease. Using the current knowledge map, the direct relationship between symptoms and other evidence can not be considered for the direction of the disease, and the accuracy of the disease inference results is also low. not tall

Images