New media content recommendation method and system

Abstract

The invention provides a new media content recommendation method and system, and relates to the field of data processing. According to the method, the text in the new media text database is represented by a semantic neural network; the method not only reflects the real text, but also reflects the knowledge most likely to be associated when people see the text, on one hand, the method is beneficialto introducing the prior knowledge, the information lacking in the text content is complemented by introducing the prior knowledge, on the other hand, the problem of natural language fuzziness can bealleviated, and the learning and reasoning capabilities of the algorithm are enhanced. The method is based on a semantic neural network. Construction of three-layer attention model, according to themethod, a three-layer attention model is improved by introducing external knowledge and a feedback mechanism to obtain a recommendation model, a deep learning algorithm is improved based on the recommendation model, intelligent recommendation of new media content is realized by applying the improved deep learning algorithm, the matching degree between users of the new media content interested by the users is improved, and accurate pushing is realized.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for recommending new media content. Background technique [0002] In the era of information overload, the task of the recommendation system is to connect users and information, help users find valuable information for themselves, and at the same time let the information be displayed in front of users who are interested in it, so as to realize the relationship between information consumers and information producers. Win-win. [0003] Existing recommendation systems generally adopt two methods: content-based recommendation method and collaborative filtering method. The basic idea of ​​content-based recommendation is to recommend similar content to users based on the content they browse or bookmark, as well as user preferences. Collaborative filtering methods are further divided into user-based collaborative filtering and model-based collaborative filtering. The ...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a new media content recommendation method, which solves the technical problem of inaccurate recommendation when the existing recommendation system is applied to new media content

Images