A method for recommending iptv programs based on multi-user context recognition

A program recommendation and context technology, applied in image communication, selective content distribution, electrical components, etc., can solve the problem of reducing the quality of recommendation, and achieve the effect of improving quality

Inactive Publication Date: 2016-04-06
EAST CHINA NORMAL UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the IPTV portal service, there is a multi-user problem, and the commonly used recommendation technology is often subject to this problem, which greatly reduces the quality of the recommendation

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 method for recommending iptv programs based on multi-user context recognition
  • A method for recommending iptv programs based on multi-user context recognition
  • A method for recommending iptv programs based on multi-user context recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] refer to figure 2 , In a family, multiple family members share the IPTV portal service, and the service is generally provided by a "set-top box". Through steps 1 to 4 of the present invention, the playing history records of the "set-top box" are analyzed to identify various context users, and steps 5 to 8 use the identified context information to generate a program recommendation list to the context users.

[0069] For example, in a family there are: old people, children and middle-aged people, they share IPTV portal services and accumulate certain historical records; through steps 1 to 4, three contexts are identified: the old people are used to watching historical dramas in the morning, record c1; Children like to watch cartoons at noon, record c2; middle-aged people are used to watching gunfight movies at night, record c3. Steps 5 to 8 use the information of c1, c2 and c3 to recommend historical dramas for the elderly in the morning, cartoons for children at noon, ...

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 an IPTV program recommendation method based on multi-user context recognition. Through cluster analysis of program viewing time, the time period in which the user's viewing time is relatively concentrated is obtained, and the user's program preference in different time periods is calculated, and different time periods are analyzed. The similarity of program preferences between time periods, combining time periods with similar viewing programs into a new type of context, using context information to make recommendations, to a certain extent, overcomes the multi-user problem in IPTV portal services and improves the quality of recommendations.

Description

technical field [0001] The invention relates to the technical field of IPTV (Interactive Personality TV) recommendation, in particular to an IPTV program recommendation method based on multi-user context recognition. Background technique [0002] In IPTV services, with the continuous explosive growth of IPTV programs, TV will once again become the center of home entertainment. However, because the input function of the remote control terminal is relatively weak, and sometimes users do not know what they want to watch, It is difficult for users to find the content they need and like. Therefore, recommendation is becoming more and more important in IPTV services. [0003] Collaborative filtering is often used in the recommendation of IPTV programs. Commonly used collaborative filtering techniques are: collaborative filtering based on browsing history and collaborative filtering based on content. At present, the main recommendation technology is based on the use, improvement ...

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): H04N21/466
Inventor 杨燕王智谨郝娟黄保荃陈昊裴逸钧
Owner EAST CHINA NORMAL UNIV
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