Content recommendation method and system based on community user behaviors

Abstract

The invention provides a content recommendation method based on community user behaviors. The method includes the steps that a client receives requests input by community users and sends behavior information to a server; the community user behavior information in the server is collected and analyzed; the collected behavior information is preprocessed, and the normalized behavior information in the server is uploaded and stored through hadoop; the normalized behavior information is classified; different community user models are established, and the community users are classified; a community user portrait is generated through the community user models; recommended content for the community users is obtained. According to the method, personalized recommendation can be achieved on the home page of a mobile client or a computer, personalized recommendation is uniformly carried out according to the hobbies and interests of community users, and precise services for different people are provided; through precise recommendation, the click rate of recommended content is increased by 2-8 times compared with that of recommended content based on fixed positions in a traditional method.

Description

technical field [0001] The invention relates to the field of network technology, in particular to a processing and storage method for dynamically outputting pictures of arbitrary specifications in real time. Background technique [0002] The mobile Internet era is changing the lives of each of us. Under the characteristics of rapid changes, all data on the mobile Internet is changing at any time. Especially in the era of personalization, individualized differentiation and positioning are carried out according to the needs of each user, so that everyone can see different information when they turn on their computers or mobile phones, which is more conducive to content providers to distribute their own content Accurate distribution is more conducive to effectively helping business owners achieve brand content fermentation and accurate content dissemination. [0003] In particular, with the development of online advertising today, higher requirements have been put forward for ...

AI Technical Summary

Problems solved by technology

However, the precision advertising delivery systems developed by most companies either focus on a certain link of advertising delivery (such as advertising effect monitoring), or focus on precise advertising delivery in a certain field (such as search engine advertising), and have not formed a A common platform for the system

Images