Information recommendation method and system

Abstract

The invention provides an information recommendation method and system. According to the information recommendation method and system, the operation of a user in a current recommendation page can be monitored to obtain each piece of recommended information clicked and viewed by the user and user behavior information of each piece of recommended information, and based on the user behavior information of each piece of recommended information, the preference degree of each piece of recommended information is obtained; furthermore, based on the preference degree of each piece of recommended information and position information of each piece of recommended information, a weight reduction coefficient of recommended information which is not clicked and viewed by the user is obtained; and by the preference degree of each piece of recommended information and the weight reduction coefficient of the recommended information which is not clicked and viewed by the user, the position information of each piece of recommended information in a next recommendation page is adjusted, so that each piece of recommended information clicked and viewed by the user can be adjusted to be displayed before each piece of recommended information which is not clicked and viewed by the user, the user can search favorite recommended information more visually in time, and the recommendation accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of personalized information recommendation, and more specifically, to an information recommendation method and system. Background technique [0002] In today's information overload and the rapid increase in the number of Internet users, the recommendation system, as a bridge connecting users and content, plays a very important role in news, shopping, video and other content websites. Among them, the personalized recommendation system is particularly important. The personalized recommendation system can treat each user as an independent individual, recommend items of interest to each user, and truly achieve "thousands of people and thousands of faces". Recommended effect. [0003] At present, the existing personalized recommendation systems can better respond to the user's active behavior. For example, when the user clicks on a video or evaluates a news, the personalized recommendation system can obt...

AI Technical Summary

Problems solved by technology

[0004] However, the personalized recommendation system often recommends dozens or even hundreds of recommended information on the recommendation interface. Users usually only click or like one or more of the recommended information, and the recommended information that has not been clicked by the user accounts for a large number. The vast majority of recommended information, however, the current personalized recommendation system cannot process the recommended information that has not been clicked by the user, so that in future recommendations, the recommended information that has not been clicked by the user will affect the entire recommended information display of

Images