Personalized recommended content access duplicate removal management method

Abstract

The personalized recommended content access duplicate removal management method comprises the following steps: constructing a total pool, and adding new content to a specified position of the total pool in real time; when a user starts an application each time, a user pool is constructed in redis, and one page of list data is obtained; recording browsing behaviors of the user on the system by starting the application, and if the personalized recommendation cache pool of the user is expired, repeating the step 1, the step 2, the step 3 and the step 4. According to the method, the new content can be added to the interior of the total pool in real time when the new content exists; there are a plurality of user pools established in redis when the user starts the application, because the acquired list data is taken from the redis and the redis is a server which is high in performance and supports high concurrency, the data can be efficiently acquired, different contents which are not browsed can be efficiently recommended to the user according to different recommendation algorithms due to personalized recommendation, so that the efficiency and the practical effect of recommending the contents are improved.

Description

technical field [0001] The present invention relates to the technical field of management methods for deduplication of content access, in particular to a management method for deduplication of personalized recommended content access. Background technique [0002] In today's information society, personalized recommendation systems have become inseparable from our lives. When we read news, shop online, listen to music, and watch videos, we will see various "recommendation" lists in the form of "guess you like", "products you may be interested in", "with you Users with similar interests are still watching" and so on. Personalized recommendation uses in-depth analysis and mining of user behavior data to recommend information or products of real interest to users. For individuals, personalized recommendations can help users solve the problem of being at a loss when faced with a wide variety of products, movies, songs, videos and other services. For enterprises, personalized re...

AI Technical Summary

Problems solved by technology

[0003] However, in the existing methods for accessing personalized recommended content, the storage capacity of redis is too large-each user has its own cache, and when the number of users is large, the amount of data stored in redis is too large. When the storage capacity is large, a redis server It is not enough, use the cluster method to solve it. At this time, the redis server has data consistency problems. It will take a lot of time to build the device cache every time, and the practical rate is not high.

Images