Comparison of Multiple Models of Recommendation Systems

In patients' medical service consumption behavior, patients' choice of medical institution is an important link, which determines patients' medical quality and medical cost, and even further affects the distribution of medical resources in the whole health service market. Patients may have problems such as high knowledge barrier and information redundancy in the process of choosing hospitals. Nowadays, with the continuous development of machine learning, the recommendation system using graph neural network has achieved good results in solving this kind of information overload problem. Therefore, we mainly focus on the application of the recommendation system in the process of patients choosing hospitals. Here we complete the construction of the initial data set through data simulation, and then we train and debug the six graph neural network recommendation system models. In addition, we propose a new comprehensive index to improve the traditional index, which is difficult to better represent the model performance. In the future, we plan to apply this research to our smart medical big data cloud platform. On the one hand, the cloud platform will provide a more solid data basis for our model; on the other hand, we can provide personalized medical recommendation services for platform users by using the recommendation system.