Personalized health service recommendation method based on hierarchical model

Abstract

The invention discloses a personalized health service recommendation method based on a hierarchy model, and mainly solves the problems that in the present personalized health service recommendations the selection of the characteristic data is single-handed, the recommendation results are unreliable and the recommendation results are low in coverage. The implementation scheme comprises the steps that 1, the geographical location information of a user is utilized, and a model of the geographical location information of the user is constructed; 2, the user chooses the labels which suit himself, and a user label model is constructed; 3, personal basic information, physical indicators and the patient case information of the user is considered comprehensively, a collaborative filtering method is utilized to construct a user similarity model; 4, a recommendation list based on the steps 1-3 is formed; and 5, the recommendation list is updated in time based on the feedbacks of the user. According to the personalized health service recommendation method, various information of the user is comprehensively considered, the personalization degree and the recommendation coverage are high, more reliable personalized health service recommendations can be provided for the user, and the personalized health service recommendation method can be used for providing medical information references for the user.

Description

technical field [0001] The invention belongs to the technical field of data mining, and further relates to a method for recommending personalized health services. Can be used to provide medical information reference for users. Background technique [0002] At present, with the rapid development of information technology and the advent of the era of big data, more and more medical resources are characterized by informatization, complexity and diversification. When people face a large number of medical resources, they cannot quickly choose the medical resources that meet their needs. [0003] The Chinese patent "A Smart Medical Personalized Recommendation System and Its Implementation Method" (patent application number: 201410271293.7, publication number CN104036445A) discloses a smart medical personalized recommendation system and its implementation method. The method involves a wireless sensor network and a personalized recommendation platform. The wireless sensor network ...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that only the physiological indicators of the patient are considered, and the data dimension considered is too single to form effective and reliable recommendation results in complex and diverse medical resources.

The disadvantage of this method is that it is only for the recommendation of doctors, without the recommendation of other medical resources, and the comprehensive effect of the recommendation results is not good.

Images