Unlock instant, AI-driven research and patent intelligence for your innovation.

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

Active Publication Date: 2021-04-27
杭州联汇科技股份有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention mainly solves the technical problem of insufficient push accuracy existing in the prior art, and provides a program recommendation method based on matrix online completion and program features with high accuracy and low evaluation requirements

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A program recommendation method based on matrix online completion and program features
  • A program recommendation method based on matrix online completion and program features
  • A program recommendation method based on matrix online completion and program features

Examples

Experimental program
Comparison scheme
Effect test

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 ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a program recommendation method based on matrix online completion and program features, which includes the following steps: S01, reading the features of each program; S02, calculating the correlation between each program; S03 . Solving the objective function by an iterative method to obtain a completion matrix X; S04. Selecting programs for target audiences according to the completion matrix X and recommending them. The scoring matrix can be adjusted in real time after new programs are put into storage or viewers score, and the push is highly targeted and accurate. This solution is applicable to the screening and recommendation of multimedia program platforms.

Description

technical field [0001] The invention relates to the field of media program evaluation and push, in particular to a program recommendation method based on matrix online completion and program features. Background technique [0002] Watching / listening to media programs such as audio and video is one of the common entertainment methods for people. With the development of science and technology and the improvement of living standards, people listen to and watch programs more on Internet-based devices such as computers, mobile phones, and PADs. In order to attract users to watch many different programs and increase ratings, the media provider will actively push them to users. How to accurately push programs of interest to users is one of the important topics in the era of big data. Existing recommendation algorithms are often inefficient and cannot meet the real-time requirements. Moreover, the characteristic information of the program itself is not applied to the recommendatio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/466H04N21/25H04N21/475
Inventor 单雪松吴洁顾江标盛国林赵凡
Owner 杭州联汇科技股份有限公司