Content recommendation method and device based on user behaviors

Abstract

The invention discloses a content recommendation method and device based on user behaviors. The method comprises the steps of collecting behavior data of a target user when the target user watches multimedia content, according to the behavior data, predicting and evaluating a plot line of the multimedia content to obtain plot evaluation values of plot segments contained in the plot line, according to the plot evaluation values, screening plot segments of which the plot evaluation values meet a preset high-energy segment screening condition from the plot line as high-energy plot segments, determining the preset high-energy fragment screening condition based on historical behavior data when the user watches the multimedia content, and performing recommendation according to the high-energy plot segments. The plot evaluation values of the plot segments contained in the plot line can be evaluated and determined based on the behavior data of the user, so that the high-energy plot segments concerned by the user are determined, and multimedia content recommendation conforms to habits of the user. Furthermore, recommendation is performed based on the merged high-energy plot segments during recommendation, so that the highlights of the contents are highlighted, and the popularization of the contents is more convenient.

Description

Technical field [0001] The present invention relates to the field of computer technology, and more particularly to a content recommendation method and apparatus based on user behavior. Background technique [0002] When the user shares the multimedia content, the existing technology generally shares the elements in multimedia content such as text, pictures or links to other users, and the content of sharing is difficult to reflect the sharing. And sharing the content style is unique to attract attention to other users. Therefore, there is a need for a method of identifying user behavior, a method recommended by user behavior to solve the above problems. Inventive content [0003] In view of the above problems, the present invention is proposed to provide a content recommendation method and apparatus that overcomes the above problems or at least partially solves the above problems. [0004] According to one aspect of the invention, a content recommendation method based on user be...

AI Technical Summary

Problems solved by technology

[0002] When users share multimedia content, the existing technology generally directly shares the elements in the multimedia content, such as text, pictures, or links to the entire content, to other users in a single form, and the shared content is difficult to reflect the viewing preferences of the sharer himself. , and the single style of shared content is difficult to attract the attention of other users

Images