Medical science popularization article recommendation method and system based on portraits

Abstract

The invention discloses a medical science popularization article recommendation method and system based on portraits, and the method comprises the following steps: recording a behavior log of a clientor a server through log dotting, wherein record content of the behavior log comprises a medical science popularization article related log, a user search log, a user questioning log and a login log;a log queue performing data statistics on the behavior log, extracting feature data, and processing the feature data to generate user portraits and article portraits; and receiving a request for a medical science popularization article, and generating a corresponding recommendation file list through a machine learning algorithm according to the user portraits and the article portraits. The embodiment of the invention at least has the following beneficial effects that the subsequent article pushing content is continuously optimized by analyzing user operation behaviors, so that the pushing speed and quality are improved, the click rate of the article is improved, and the requirement of the user on information is met.

Description

technical field [0001] The invention relates to the technical field of Internet article recommendation, in particular to a method and system for recommending medical popular science articles based on portraits. Background technique [0002] The emergence and popularization of the Internet has brought a lot of information to users, which meets the needs of users for information in the information age. However, with the rapid development of the network, the amount of information has also increased significantly, making it difficult for users to learn from the massive amount of information. Get information that is really useful to you. [0003] In the field of medical popular science articles, there are a huge number of users and great differences in preferences. Existing recommendation systems mostly use collaborative filtering algorithms, making it difficult to find users with similar preferences, and it is also difficult to obtain a recommendation list of relevant medical sc...

AI Technical Summary

Problems solved by technology

[0002] The emergence and popularization of the Internet has brought a lot of information to users, which meets the needs of users for information in the information age. However, with the rapid development of the network, the amount of information has also increased significantly, making it difficult for users to learn from the massive amount of information. Get information that is really useful to you

[0003] In the field of medical popular science articles, there are a huge number of users and great differences in preferences. Existing recommendation systems mostly use collaborative filtering algorithms, and it is difficult to find users with similar preferences, and it is also difficult to obtain a recommendation list of relevant medical science popular documents.

Images