Drug recommendation method based on artificial intelligence and related equipment

Abstract

The invention discloses a drug recommendation method and system based on artificial intelligence, computer equipment and a computer readable storage medium. The method comprises the following steps: collecting historical medical data to construct an original portrait; preprocessing the original portrait and outputting a feature data set; taking the preprocessed feature data set as training data, and respectively training in advance to obtain an XGBOOST recommendation model and a deep neural network recommendation model; obtaining a first recommendation intensity probability value and a secondrecommendation intensity probability value through an XGBOOST recommendation model and a deep neural network recommendation model; carrying out linear addition to obtain a target recommendation intensity probability value; and according to the target recommendation intensity probability value, screening out a preset number of target drug information ranked at the top, and pushing the target drug information to the user. According to the method, the model results of the two are linearly added, so that the drug recommendation accuracy can be effectively improved.

Description

technical field [0001] The invention relates to the field of medicine, in particular to an artificial intelligence-based drug recommendation method, system, computer equipment and computer-readable storage medium. Background technique [0002] When existing patients purchase medicines, they usually choose to go to physical pharmaceutical retail stores such as chain pharmacies. Specifically, patients describe their symptoms to pharmacists, and pharmacists choose corresponding medicines for patients. However, this method has the following defects. The level of licensed pharmacists in pharmacies may vary, resulting in recommended drugs that may not be suitable for patients. In addition, each physical store needs to be equipped with multiple pharmacists, resulting in a rapid increase in labor costs. Therefore, there are now many companies that can recommend drugs to users. Most of the existing drug recommendation systems are basically based on the indications of the drug itself ...

AI Technical Summary

Problems solved by technology

[0002] When existing patients purchase medicines, they usually choose to go to physical pharmaceutical retail stores such as chain pharmacies. Specifically, patients describe their symptoms to pharmacists, and pharmacists choose corresponding medicines for patients. However, this method has the following defects. The level of licensed pharmacists in pharmacies may vary, resulting in recommended drugs that may not be suitable for patients. In addition, each physical store needs to be equipped with multiple pharmacists, resulting in a rapid increase in labor costs. Therefore, there are now many companies that can recommend drugs to users. Most of the existing drug recommendation systems are basically based on the indications of the drug itself to match the indications of the drug. It is theoretically feasible, but it ignores a large number of specialized drug history data

Images