Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

TV program feature recommendation method and system based on non-negative matrix factorization

A non-negative matrix decomposition, TV program technology, applied in the field of TV program thematic recommendation methods and systems, can solve the problem of not being able to reasonably cover user portraits, and achieve the effect of reasonable distribution

Active Publication Date: 2021-07-13
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem that existing TV program recommendations cannot reasonably cover user portraits, and proposes a TV program feature recommendation method and system based on non-negative matrix decomposition

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
  • TV program feature recommendation method and system based on non-negative matrix factorization
  • TV program feature recommendation method and system based on non-negative matrix factorization
  • TV program feature recommendation method and system based on non-negative matrix factorization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0032] Comparative analysis of various dimensionality reduction methods, in the dimensionality reduction of high-dimensional data, because the distance-based dimensionality reduction method in high-dimensional data will show that the nearest neighbor and the farthest neighbor are almost equidistant in most cases, the dimensionality reduction effect is poor, So distance-based dimensionality reduction methods are no longer applicable. NMF non-negative matrix decomposition is based on the degree of correlation between features for dimensionality reduction. The tag data of TV programs is high-dimensional data, and by analyzing the correlation between tags to analyze the intersection of tags in the field of interest, and then determine Whether to integrate dimensionality reduction, so the present invention uses NMF non-negative matrix factorization for label ...

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 relates to the technical field of big data, and aims to solve the problem that the existing TV program recommendation cannot reasonably cover user portraits, and proposes a TV program topic recommendation method based on non-negative matrix decomposition, including: real-time acquisition of TV programs to be recommended to users The label information of the program, the label information includes: user portrait data, program label data and thematic label data, the user portrait data is used to represent the user's score for each label; construct a non-negative matrix decomposition model to convert label information into full labels matrix, decompose the full label matrix according to the non-negative matrix factorization model to obtain a probability matrix; reconstruct the user portrait data and thematic label data according to the label information in the probability matrix, and reconstruct the user portrait data and thematic label data according to the reconstructed user portrait data and thematic label data. Make recommendations on TV program topics. The present invention realizes the reasonable distribution of the user recommendation list in the interest field by merging the interest fields.

Description

technical field [0001] The present invention relates to the field of big data technology, in particular to a TV program feature recommendation method and system. Background technique [0002] In the personalized recommendation of smart TVs, the issue of the intersection of tags in the field of interest has not been paid attention to. That is, certain tags are preferred by users with the same interest psychology, such as action and martial arts. Movies with high ratings also score high on martial arts. However, in the algorithm for generating the recommendation list, the ranking is mainly based on the ratings of the tags by the user. If the user has high ratings on martial arts, action, costumes, etc., most of the tags covered by the recommended list programs are these. But there are also tags with user ratings that are centered on the top, for example, inspirational, adventure, comedy, etc. However, due to the large proportion of programs with themes such as martial arts a...

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): H04N21/235H04N21/25H04N21/258H04N21/435H04N21/45H04N21/466G06F16/9535
CPCG06F16/9535H04N21/2355H04N21/251H04N21/25891H04N21/4355H04N21/4532H04N21/4668
Inventor 何林凯于跃
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com