Recommended content deduplication method, electronic equipment and storage medium

Abstract

The invention provides a recommended content deduplication method, electronic equipment and a storage medium, wherein the method comprises the steps of obtaining a content candidate set which comprises at least one piece of candidate content; searching an identifier of the candidate content in an ith layer of bitmap in a Bloom filter BF, wherein the ith layer of bitmap has a jth probability, i and j are both larger than or equal to 1 and smaller than or equal to N, and N is a positive integer larger than 1; if the identifier of the candidate content is found in the ith-layer bitmap, generating a random probability, and if the random probability is smaller than the jth probability, deleting the candidate content from the content candidate set; if the random probability is greater than or equal to the j-th probability, retaining the candidate content in the content candidate set. Therefore, on the basis of the random probability and the jth probability, the candidate content with the identifier is deleted or reserved, so that the memory space is reasonably utilized, and duplicate removal and recommendation of the candidate content are realized.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for deduplication of recommended content, an electronic device and a computer-readable storage medium. Background technique [0002] At present, in some application scenarios, it may be necessary to recommend content to users. For example, in a bookstore, recommend books and their contents to users, or, in restaurants, recommend dishes and the number of people suitable for dining. [0003] When recommending content to users, the recommended (or read) content is usually no longer put into the recommendation candidate set, that is, no repeated recommendations are made to avoid repeatedly recommending the same content to users and affecting the user experience . [0004] However, if no repeated recommendations are made, some high-quality recommendations or user-favorite recommendations may not be recommended to the user again, causing the user to miss high-quality ...

AI Technical Summary

Problems solved by technology

[0004] However, if no repeated recommendations are made, some high-quality recommendations or user-favorite recommendations may not be recommended to users again, causing users to miss high-quality recommended content or user-favorite recommended content

Images