Video recommendation filtering method and device, server and storage medium

Abstract

The embodiment of the invention relates to a video recommendation filtering method and device, a server and a storage medium. The method comprises the steps of obtaining a video recommendation request; according to the video recommendation request, obtaining at least one piece of to-be-recommended video information; filtering the video information recorded by a first Bloom file and / or a second Bloom file from the at least one piece of video information, wherein the first Bloom file comprises a file generated according to a film watching log uploaded by the user terminal equipment, and the filmwatching log is a film watching log which takes the previous unit time corresponding to the current moment as a benchmark and traces forwards for a first fixed time period, and the second Bloom filecomprises a file which is recommended to the user terminal equipment according to the server and is generated by backtracking video information in a second fixed time period forwards by taking the current moment as a reference; and recommending the residual video information after filtering to the user terminal equipment. By means of the mode, the watched videos are efficiently and accurately filtered for the user, and the videos which are not watched are recommended.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a video recommendation filtering method, device, server and storage medium. Background technique [0002] When the recommendation engine recommends videos, it needs to filter the videos that the user has watched recently, that is, the videos that the user has watched recently will no longer be displayed to the user. This process requires fast processing (millisecond level) and supports massive browsing data. filter. [0003] If you want to judge whether an element is in a set, the general idea is to save all the elements in the set, and then determine it by comparison. In a similar way, when a recommendation engine recommends videos, it also needs to compare a certain video with videos that the user has already watched, and then filter and process it. However, as the number of video elements in the video collection watched by the user increases, ...

AI Technical Summary

Problems solved by technology

However, as the number of video elements in the video collection that users have watched increases, the storage space required becomes larger and the retrieval speed becomes slower and slower.

Using this technology to achieve viewing exposure filtering requires a large amount of cache space, and when the recommendation engine needs to perform high-concurrency queries in the face of more viewing requests sent by users, there is a bottleneck in query efficiency. As the amount of data increases, the accuracy of the query will also decrease.

Images