Video recommendation method, device, device and storage medium

Abstract

The present application discloses a video recommendation method, apparatus, device and storage medium, which relate to the field of data processing, and in particular, to the field of big data technology. The specific implementation scheme is: according to the video recommendation request of the target user, obtain the target video partition set matching the target user, and the videos in each video partition are determined by the video operation behavior of the target user; from each video partition in the target video partition set, Obtain a set number of candidate recommended videos respectively to form a candidate recommended video set; de-duplicate the candidate recommended video set according to presentation and / or time factors to obtain a target recommended video set, and according to the target recommended video set, correct the recommended video set. Target users make video recommendations. By maintaining different video partition sets for different users according to the user's video operation behavior, and determining the way of recommending videos from each user's video partition set, it is possible to simply and conveniently recommend personalized video content to users.

Description

technical field [0001] The embodiments of the present application relate to the field of data processing, in particular to the field of big data technologies, and in particular to a video recommendation method, apparatus, device, and storage medium. Background technique [0002] With the continuous development of Internet short video technology, more and more users are watching short videos. [0003] At present, the recommendation technology of short video needs to establish a recommendation model in advance, and the recommendation model needs to collect data and train before going online, so it requires a long development cycle. At the same time, the recommendation technology based on the recommendation model is mainly suitable for scenarios with sufficient users and resources. When the number of resources and users included in the video platform is small, it is difficult to establish a complete recommendation model, and the above video recommendation technology cannot be u...

AI Technical Summary

Problems solved by technology

[0003] The current short video recommendation technology needs to build a recommendation model in advance, and the recommendation model needs to collect data and train before going online, so it requires a long development cycle

At the same time, the recommendation technology based on the recommendation model is mainly suitable for scenarios where the number of users and resources are relatively sufficient. However, when the number of resources and users included in the video platform are small, it is difficult to establish a complete recommendation model, and the above-mentioned video recommendation technology cannot be used.

Images