Drug recommendation model training method and device, drug recommendation method and device, equipment and medium

Abstract

The invention discloses a drug recommendation model training method and device, a recommendation method and device, equipment and a medium. The method comprises the steps of obtaining model training data including training drugs, training disease data and training comment data; performing sentiment analysis on the training comment data to obtain a labeling sentiment label; performing feature extraction on the training disease data and the training comment data to obtain training text features; obtaining a model training sample based on each training text feature and the labeled emotion label; inputting the model training sample into a feature classifier corresponding to the training text feature for model training, and obtaining an original feature drug recommendation model corresponding to the training text feature; and testing the original feature drug recommendation model by adopting the model training sample to obtain a target feature drug recommendation model corresponding to the training text features. According to the method, the accuracy and effectiveness of the target recommended medicine recommended by the target characteristic medicine recommendation model can be guaranteed.

Description

technical field [0001] The present invention relates to the field of smart medical technology, in particular to a drug recommendation model training method, recommendation method, device, equipment and medium. Background technique [0002] At present, when doctors prescribe medicines to patients, they mainly formulate prescriptions based on the doctor's knowledge and experience, that is, to use the doctor's knowledge and experience to analyze the symptoms of the disease, previous clinical history and related drug performance, etc., to determine the final treatment. Prescribing regimen. In this way, whether the medicine prescribed by the doctor is effective for the patient's disease symptoms mainly depends on the doctor's knowledge and experience, and it is impossible to verify whether the doctor's medicine is effective against the patient's disease symptoms, which is not conducive to protecting the life and health of the patient. The existing drug recommendation system main...

AI Technical Summary

Problems solved by technology

[0003] Embodiments of the present invention provide a drug recommendation model training method, device, computer equipment, and storage medium to solve the problem of low recommendation accuracy and effectiveness in existing drug recommendation systems

Images