A program recommendation method based on matrix online completion and program features
A program recommendation and program feature technology, applied in image communication, selective content distribution, electrical components, etc., can solve the problems of low evaluation requirements and insufficient push accuracy, and achieve the effect of strong pertinence and high accuracy of push
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0024] Embodiment: There are a large number of broadcast programs on the system platform, so recommending broadcast programs of interest to audiences is an important function of the system platform. Since the interests of the audience are changing every day, the data in our system platform is also constantly updated, for example, some new programs have been added, and the audience has rated some programs and so on. Therefore, the real-time performance of recommendation has a very important impact on the accuracy of broadcast program recommendation. Traditional recommendation algorithms perform poorly in real-time performance.
[0025] If the audience and the broadcast program are regarded as two dimensions, then the rating of the program by the audience can be regarded as a matrix, which is called the rating matrix. Because only a fraction of the audience rated certain programs, elements at some positions in the rating matrix are unknown. Recommending broadcast programs for ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


