Chinese medical knowledge mining and analysis based on syntactic dependency and named entity recognition

In the hospital, when doctors get the patient's case analysis, they often need to spend a lot of time reading the text of the current case and then analyze it, in order to get the cause that affects the patient's disease, most of which are limited to the cause of the disease. In order to allow doctors to see the cause of the patient's condition more intuitively and clearly, combined with Python's powerful data processing, text training, data mining and other functions, firstly carry out text training on the hospital's case details in previous years, and perform named entity recognition on medical entities to achieve entity classification. Then, based on the Chinese text structure, through dependency syntax analysis, a keyword for a disease analysis is extracted, and finally a triple is formed. The ontology project is constructed through protege, and a knowledge map is formed, which not only serves as an intuitive analysis and display of this disease.