Digital content distribution method and device and storage medium

Abstract

The invention discloses a digital content distribution method and device and a storage medium. The method comprises the following steps: generating a training content sequence according to a historical behavior of triggering digital content by a user group; inputting the generated training content sequence into a preset model to carry out training so as to obtain a feature vector associated with the digital content; calculating an estimated interest score of the current target user for each digital content in the candidate content set according to a historical behavior of triggering the digital content by the current target user needing to distribute the digital content and the feature vector; and sorting each digital content in the candidate content set according to the pre-estimated interest score and distributing the digital content in the candidate content set. According to the invention, the static attribute information of the digital content is introduced into the original user behavior sequence, and the updated sequence is modeled, so that the similarity information of the digital content is obtained, and the digital content which the user is most interested in is obtained.

Description

technical field [0001] The present invention relates to the technical field of content distribution, in particular to a digital content distribution method, device and storage medium. Background technique [0002] At present, smart terminals (such as smart TVs), as content bearing platforms, often undertake multiple digital content providers. At the same time, users have various interests. For example, some users are accustomed to using a certain application on smart terminals to watch animation content, while some users are accustomed to using another app to watch variety show content. The richness of content also brings great challenges to the content distribution system, mainly including sparsity and application cold start problems. The problem of sparsity is mainly reflected in: when smart terminal users tend to only interact with a small number of content providers, it is very difficult to train an accurate content distribution model to predict user preferences; the pr...

AI Technical Summary

Problems solved by technology

The problem of sparsity is mainly reflected in: when smart terminal users tend to only interact with a small number of content providers, it is very difficult to train an accurate content distribution model to predict user preferences; the problem of application cold start is mainly reflected in : For a newly connected content provider, due to the lack of user behavior data, it is difficult to accurately predict the user's preference for the content provided by the content provider

Images