Medical attribute knowledge graph construction method and device, equipment and medium

Abstract

The invention relates to the technical field of knowledge maps of big data, and discloses a medical attribute knowledge map construction method and device, equipment and a medium. The method includesidentifying medical attributes in the to-be-identified text through a regularization expression technology and a preset medical dictionary; performing entity classification on all the identified medical attributes through an attribute classification identification model, and identifying attribute categories; constructing a medical attribute combination unit according to the attribute category; performing relationship extraction and identification on the medical attribute combination unit through a medical attribute relationship identification model to obtain an identification result; and constructing a medical attribute knowledge graph corresponding to the to-be-recognized text according to all recognition results. According to the invention, the medical attribute knowledge graph can be quickly and accurately constructed, the omission condition of manual construction is avoided, and the construction accuracy and efficiency are improved. The invention is suitable for the field of smartmedical treatment, and can further promote the construction of smart cities.

Description

technical field [0001] The present invention relates to the technical field of knowledge graph of big data, in particular to a method, device, equipment and medium for constructing a medical attribute knowledge graph. Background technique [0002] In the prior art, the structured data of the drug is mined by manually reading the drug instructions to construct the knowledge map of the drug. The attributes of the structured data include the object, usage, and dosage of the drug. These attributes are unavailable in the drug instructions. The sequence is distributed in various locations. When reading manually, it is necessary to find out the location of these attributes and then combine the contents of these attributes to determine the relationship between attributes, and then output structured data according to the relationship between these attributes to build the system. The knowledge map of medicines, due to the different granularity of manual reading and the different medic...

AI Technical Summary

Problems solved by technology

[0002] In the prior art, the structured data of the drug is mined by manually reading the drug instructions to construct the knowledge map of the drug. The attributes of the structured data include the object, usage, and dosage of the drug. These attributes are unavailable in the drug instructions. The sequence is distributed in various locations. When reading manually, it is necessary to find out the location of these attributes and then combine the contents of these attributes to determine the relationship between attributes, and then output structured data according to the relationship between these attributes to build the system. The knowledge map of medicines, due to the different granularity of manual reading and the different medical knowledge, errors or omissions will occur in the content of the attributes found, and the relationship between the attributes will be incomplete when finally determined, resulting in the construction of a structured The data is incomplete, so in the existing technical scheme, the threshold of constructing a drug knowledge map is high, the time is long and the efficiency is low, and the accuracy and completeness are not high

Images