Machine learning TV program recommendation method based on domain decomposition machine

A machine learning and TV program technology, applied in the field of big data, can solve the problems of excessive human intervention and poor recommendation effect, and achieve the effect of reducing manual intervention, improving program effect, and improving recommendation effect.

Inactive Publication Date: 2018-01-26
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: to propose a machine learning TV program recommendation method based on a domain decomposition machine, to solve the problem of human intervention in the program recommendation scheme in the traditional technology and not only based on the use of user historical behavior data, there is a recommendation effect bad question

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
  • Machine learning TV program recommendation method based on domain decomposition machine
  • Machine learning TV program recommendation method based on domain decomposition machine
  • Machine learning TV program recommendation method based on domain decomposition machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention aims to propose a machine learning TV program recommendation method based on a domain decomposition machine to solve the problem of poor recommendation effect due to human intervention in the program recommendation scheme in the traditional technology and not only based on the use of user historical behavior data.

[0025] For ease of understanding, we first introduce the recommendation process of TV programs. The TV program recommendation system mainly includes the processing of user historical behavior data, the online recommendation algorithm, the output of the recommendation results of the offline recommendation algorithm, and the recommendation results are sorted and recommended to users based on user portraits and program characteristics. The key processes are extracted as follows:

[0026] 1. Collection and arrangement of user historical behavior data and program feature data.

[0027] 2. Establishment of recommendation algorithm model and ...

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 field of big data technology, and discloses a machine learning TV program recommendation method based on a domain decomposition machine, aiming at solving the problems that a program recommendation scheme in a traditional technology has more human interventions, is not applied by only taking the historical behavior data of users as the basis, and is poor in recommendation effect. The method comprises the following steps: a, arranging the historical behavior data of the users and feature information of programs; b, constructing an FFM algorithm recommendation modelby taking the arranged data as basic data of the model; c, calculating recommendation results by adopting a logistic regression algorithm based on the constructed FFM algorithm recommendation model; and d, sorting the recommendation results, and pushing the sorted recommendation results to the users.

Description

technical field [0001] The invention relates to the field of big data technology, in particular to a machine learning TV program recommendation method based on a domain decomposition machine. Background technique [0002] At present, the TV program recommendation system has been an important part of the smart TV platform, and the analysis of the traditional TV program recommendation system will find that there are obvious traces of manual intervention in the selection of recommended program features, including program names, categories, years, etc. selection of various features. The so-called recommended program features include that during the recommendation process, the main recommendation weights are based on the type of TV programs, such as martial arts and military, or based on age and actors. The selection of these weight ratios is often subjective. to decide. Therefore, the recommendation process is not conducive to personalized recommendations and the improvement o...

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 Applications(China)
IPC IPC(8): H04N21/466H04N21/25G06F17/30
Inventor 于跃刘鑫牛文臣
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap