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

Television member user recommendation method and system based on user feedback

A recommendation method and user technology, applied in the field of signal processing, can solve the problems of reducing the accuracy of TV member users and not considering the behavior feedback information of TV member users, so as to achieve the effect of improving performance

Active Publication Date: 2021-07-09
SHANDONG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The current methods to solve this problem are mostly based on user portraits or the user's playback history for a period of time to predict. The inventor found that in the TV member user extension / recommendation scenario, after the user purchases the package, the subsequent playback history, etc. Behavior feedback is still related to the member recommendation task. However, the existing potential prediction or recommendation of TV member users does not consider the behavior feedback information of TV member users, which reduces the accuracy of potential prediction results of TV member users and the probability of recommending users to become TV members. accuracy

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
  • Television member user recommendation method and system based on user feedback
  • Television member user recommendation method and system based on user feedback
  • Television member user recommendation method and system based on user feedback

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] combine figure 1 and figure 2 As shown, a method for recommending TV member users based on user feedback in this embodiment specifically includes the following steps:

[0045] Step 1: Obtain the payment behavior information within the historical set time period, mark the users who have paid the behavior within the historical set time period as seed users, and mark the users who have not paid the behavior as candidate users.

[0046] For ease of description, a week is used for measurement. Get the membership package purchase data information in the past week, and get the list of user IDs who successfully purchased the package and the corresponding order time.

[0047] Mark users who have purchased membership packages as seed users, and users who have not purchased membership packages as candidate users.

[0048] Users who have successfully purchased the package are used as seed users, and those current non-member users are candidate users. Our subsequent extended use...

Embodiment 2

[0097] The present embodiment provides a TV membership user recommendation system based on user feedback, which specifically includes the following modules:

[0098] A user division module, which is used to obtain payment behavior information within a historically set time period, marking users who have paid for within a historically set time period as seed users, and users who have not paid for as candidate users;

[0099] The user vector representation module is used to extract and describe user interest according to the user's video playback behavior, obtain the user interest representation vector, and then splice with the user portrait, and obtain the user embedding representation vector through the fully connected layer;

[0100] The user expansion recommendation module is used to cluster the seed users to obtain a plurality of seed user groups, and the average vector of each seed user group is represented as a corresponding user group vector to calculate the similarity be...

Embodiment 3

[0103] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for recommending TV member users based on user feedback as described above are implemented.

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 belongs to the field of signal processing, and provides a television member user recommendation method and system based on user feedback. The method comprises the following steps: acquiring payment behavior information in a historical set time period, marking a user who has a payment behavior in the historical set time period as a seed user, and marking a user who does not have the payment behavior as a candidate user; extracting and depicting user interests according to video playing behaviors of users to obtain user interest representation vectors, splicing the user interest representation vectors with user portraits, and obtaining user embedded representation vectors through a full connection layer; and clustering the seed users to obtain a plurality of seed user groups, taking an average vector of each seed user group as a corresponding user group vector representation, calculating the similarity between the candidate users and the seed user groups, selecting the users with the similarity exceeding a set threshold value from the candidate users as extended users, and performing member recommendation.

Description

technical field [0001] The invention belongs to the field of signal processing, in particular to a method and system for recommending TV member users based on user feedback. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] In the current major video networks and platforms, such as Youku, iQiyi and other online platforms, there are massive and rich video resources, including TV series, movies, variety shows, etc. These videos are provided for platform users to watch. The website platform launches a membership package service for these videos. The package contains many videos, and these videos can only be watched after users pay for the package. Moreover, the income from membership packages accounts for a large proportion of the revenue of current video websites. Therefore, finding those users who are likely to purchase membership packages f...

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): G06Q30/02G06Q30/06G06K9/62G06N3/04G06N3/08
CPCG06Q30/0202G06Q30/0631G06N3/08G06N3/044G06F18/23
Inventor 彭朝晖郝振云王雪王健许晓康
Owner SHANDONG UNIV
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