Content recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a content recommendation method and device, electronic equipment, a storage medium and a computer program product containing an instruction in the technical field of computers. The method comprises the following steps of displaying label user accounts corresponding to all field classifications to a current user account; obtaining a following instruction ofa current user account for a specified label user account, responding to the following instruction; and pushing the consumption content of the specified label user account to the current user account.Therefore, the content stream meeting the account demand of a new user can be quickly taught. The cold start process of the new user account is accelerated, the retention of the new user account andthe overall activity of the platform are further improved, meanwhile, the specified label user account followed by the old user account is obtained, the method can be used for optimizing the information flow of the old user account and avoiding the cocoon house effect of the information of the old user account, and therefore the old user account finds more wonderful content.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to a content recommendation method, device, electronic equipment, and storage medium. Background technique [0002] With the development of Internet technology and the acceleration of people's life rhythm, users often hope to see the media content such as articles and videos that they are interested in in the shortest time. In addition to portraits, there is generally a lack of personalized data for new users. It is difficult for content platforms to recommend content that meets the needs of new users. Judging the user's preference, gradually adjusting to meet the content flow of the user's needs, but there is a problem of cold start in this recommendation method. For new users or new fields that the user cares about, because there is no user's historical viewing behavior, it cannot be quickly and efficiently. Targetedly recommend content that users are interested i...

AI Technical Summary

Problems solved by technology

[0002] With the development of Internet technology and the acceleration of people's life rhythm, users often hope to see the media content such as articles and videos that they are interested in in the shortest time. In addition to portraits, there is generally a lack of personalized data for new users. It is difficult for content platforms to recommend content that meets the needs of new users. Judging the user's preference, gradually adjusting to meet the content flow of the user's needs, but there is a problem of cold start in this recommendation method. For new users or new fields that the user cares about, because there is no user's historical viewing behavior, it cannot be quickly and efficiently. Targetedly recommend the content that users are interested in, and if the user does not find the content they are interested in after long-term debugging of the information flow, they may leave the platform, which will not improve the retention of new users and the overall activity of the platform

Images