Drug recommendation method, device, computer equipment and storage medium

Abstract

The present application discloses a drug recommendation method, device, computer equipment, and storage medium. The method includes: acquiring at least two target user attribute information of the target user, and inputting at least two target user attribute information into a drug index prediction model; Each medication index prediction network in the index prediction model determines the medication index of each target user attribute information of the target user under the action of each drug; based on the medication index prediction model, determine the target medication corresponding to at least two target user attribute information under the action of any drug indicators to obtain multiple target drug indicators corresponding to multiple drugs; determine the maximum target drug indicator from the multiple target drug indicators, and push the target drug with the largest target drug indicator to the target user. By adopting the present application, medicines can be accurately recommended to users, which improves the accuracy of model medicine recommendation and improves the user stickiness of medicine recommendation.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a drug recommendation method, device, computer equipment and storage medium. Background technique [0002] At present, drugs can be recommended to patients through neural network models or statistical models. When recommending drugs to patients through the neural network model, the neural network model can predict the drugs that need to be recommended to the patient based on all the characteristics of the patient, but due to the characteristics of the neural network sharing neurons, it can only explain all the characteristics of the patient, while Failure to explain a certain feature of the patient may result in the patient not accepting the drug recommended by the above model. It can be seen that the above neural network model lacks sufficient interpretability and poor applicability. In addition, when recommending drugs to patients through statistical models, althou...

AI Technical Summary

Problems solved by technology

When recommending drugs to patients through the neural network model, the neural network model can predict the drugs that need to be recommended to the patient based on all the characteristics of the patient, but due to the characteristics of the neural network sharing neurons, it can only explain all the characteristics of the patient, while Unable to explain a certain characteristic of the patient, the patient may not accept the drug recommended by the above model. It can be seen that the above neural network model lacks sufficient interpretability and poor applicability

In addition, when recommending drugs to patients through statistical models, although the statistical models have sufficient interpretability, the accuracy of the models is low

Images