Device, method and computer-readable storage medium for information recommendation

Abstract

An information recommendation method, device and system and a computer-readable storage medium. The information recommendation device comprises a memory and a processor. The memory is stored with an information recommendation system therein. When being executed by the processor, the information recommendation system is configured to: determine, before recommending a target object to a user, an approximate object corresponding to the target object according to a mapping relationship between a preset target object and the approximate object, and use both the target object and the determined approximate object to be objects for analysis (S1); acquire, from a preset data source, evaluation data performed by each user on the objects for analysis in a predetermined time, and perform analysis on the evaluation data of each object for analysis according to a preset analysis rule to obtain a positive tag value corresponding to each object for analysis (S2); if the positive tag value is greater than or equal to a preset threshold, determine whether to recommend the target object to the user according to a preset recommendation algorithm (S3); and if so, determine that the user is a related user to the target object, and recommend the target object to the user (S4). The above information recommendation system can recommend customized information to a user accurately.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to an information recommendation device, method and computer-readable storage medium. Background technique [0002] In the current personalized information recommendation scheme, the user's point of interest is mainly obtained by analyzing the user's historical behavior, and then various information is pushed according to the user's point of interest. The user's historical behavior can be obtained through the social media used by the user (such as Weibo, blog, forum, podcast, etc.). In the prior art, the user's positive preference is obtained by analyzing the user's historical behavior. If there are more texts and photos about travel and food published on the website, it can be analyzed that the positive preference of user A is that he likes travel and food. However, on the one hand, the user’s historical behavior is limited, and it is not accurate to recommend perso...

AI Technical Summary

Problems solved by technology

However, on the one hand, the user’s historical behavior is limited, and it is not accurate to recommend personalized information to the user based on the user’s online historical behavior; on the other hand, the user’s interest is relatively stable, while the social background is changing dynamically (such as current hot news or time, etc.), it is also impossible to accurately recommend personalized information to users only by analyzing the user's historical behavior

Images