Multimedia resource recommendation method and device, electronic equipment and storage medium

Abstract

The invention relates to a multimedia resource recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of computers. According to the embodiment of the invention, the interests of the user account are integrated and analyzed through the multimedia resources interacted by the user account, which multimedia resources are the core interests of the user account are analyzed according to the aggregation condition determined by the multimedia resources according to the similarity, and the candidate interests of the user account are analyzed according to the similarity between the multimedia resources and the candidate multimedia resources. According to the method, the multimedia resources which are similar to the candidate multimedia resources can be analyzed, and the multimedia resources which are similar to the candidate multimedia resources and can represent the core interest of the user account can be naturally analyzed from the multimedia resources interacted with the user account by combining the two factors. Therefore, multimedia resource recommendation is performed for the user account, the recommended target multimedia resource can conform to the core interest of the user account and the preference of the user, and the accuracy of a recommendation result is improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a multimedia resource recommendation method, device, electronic equipment and storage medium. Background technique [0002] With the rapid development of computer technology, intelligent recommendation plays an increasingly important role. The main task of intelligent recommendation is to obtain the user's preference or interest in multimedia resources by analyzing the relevant information of the user account, and recommend multimedia resources for the user account accordingly. [0003] In related technologies, the multimedia resource recommendation method usually obtains the multimedia resources that the user account has interacted with, and uses a convolutional neural network (Convolutional Neural Networks, CNN) or a recurrent neural network (Recurrent Neural Network, RNN) to select multiple candidate multimedia resources. The multimedia resource that is most li...

AI Technical Summary

Problems solved by technology

[0004] If the user account has interacted with many multimedia resources, the maximum pooling step in CNN will ignore the more important parts and loop signals in these multimedia resources, and cannot accurately capture the core interests of the user account.

However, RNN has the characteristic of forgetting long-term characteristics. When extracting the interest of the user account from the multimedia resources that the user account has interacted with, there is a short-term bottleneck, and the long-term interest of the user account cannot be captured, and the captured interest is not accurate enough.

Therefore, the user features extracted in the above method are inaccurate, resulting in poor accuracy of recommendation results.

Images