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

A video clustering recommendation method and device

A recommendation method and video technology, applied in the field of video clustering, can solve problems such as low quality of clustering results, easy to be affected by outliers, and low computational efficiency

Active Publication Date: 2020-01-14
TCL CORPORATION
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a video clustering recommendation method to solve the existing segmentation clustering algorithm, which requires multiple iterative operations, low calculation efficiency, and is easily affected by outliers, resulting in low quality clustering results The problem

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 video clustering recommendation method and device
  • A video clustering recommendation method and device
  • A video clustering recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] figure 1 The implementation flow of the video clustering recommendation method provided by the first embodiment of the present invention is shown, and the details are as follows:

[0052] In step S101, according to the number of ratings of all users on the video, the videos are sorted to obtain the video set n is the number of videos.

[0053] Specifically, all the users mentioned in the embodiments of the present invention may be the video ratings of all users of the platform obtained through a data collection platform such as Internet TV, or may be comprehensive data obtained by multiple data collection platforms.

[0054] The number of ratings of the video refers to the number of ratings for a certain video, and the more the number of ratings, the higher the popularity of the video. As an optional implementation, the number of ratings may be the number of users who have rated the video, that is, for the same user, when the same video has been rated multiple times,...

Embodiment 2

[0080] figure 2 The implementation flow of the video clustering recommendation method provided by the second embodiment of the present invention is shown, and the details are as follows:

[0081] In step S201, according to the method described in the first embodiment, the videos are clustered to generate video collection classes.

[0082] In step S202, the target video input by the user is received, and the video collection class to which the target video belongs is searched.

[0083] Specifically, the target video input by the user in the embodiment of the present invention may be the video that the user is searching for, or the video that the user is currently watching. In addition, in order to improve the accuracy of video recommendation, it is also possible to set the The duration exceeds a certain length of time, such as watching a video for more than five minutes.

[0084] The video collection class to which the target video belongs can be calculated by calculating th...

Embodiment 3

[0098] image 3 A schematic structural diagram of a video clustering recommendation device provided by the third embodiment of the present invention is shown, and the details are as follows:

[0099] The video clustering and recommending device described in the embodiment of the present invention includes:

[0100] The sorting unit 301 is used to sort the videos according to the number of ratings of the videos by all users to obtain the video set n is the number of videos;

[0101] The degree of difference calculation unit 302 is used to calculate the scores of each video in turn from high to low according to the number of ratings of the videos Compared with the number of ratings High video, or by the ratio of the number of ratings High video constitutes a video collection class, and the collection difference is calculated;

[0102] The video set class generation unit 303 is configured to obtain the calculated minimum set difference degree, and if the set set differen...

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 present invention provides a method for video clustering and recommendation, which includes: sorting the videos according to the number of ratings of all users on the videos to obtain the video set n as the number of videos; according to the number of ratings of the videos, calculating each video For videos with a higher ratio to the number of ratings, perform set difference calculation; obtain the calculated set difference minimum value, if the set set difference minimum value is less than the preset threshold, then set the score corresponding to the set set difference minimum value Videos with a high number ratio are combined with videos into a video collection class. The present invention can effectively avoid multiple iterative operations during clustering, is not easily affected by abnormal values, and greatly improves classification efficiency and clustering quality.

Description

technical field [0001] The invention belongs to the field of video clustering, and in particular relates to a video clustering recommendation method and device. Background technique [0002] With the continuous enrichment of Internet resources, when people view multimedia resources, such as watching videos or playing music files, they need to search for files in a large number of multimedia resources, and it takes a lot of time to obtain the multimedia data that users like. [0003] In order to improve users’ access to favorite multimedia files, such as video data, the existing video recommendation methods are generally based on clustering technology and collaborative filtering recommendation algorithm. Through clustering technology, the scope of searching the nearest neighbors of the target object is narrowed to the target object. Several clusters with the highest degree of similarity can effectively reduce the amount of calculation and improve real-time response capability...

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): G06K9/62G06F16/783
CPCG06F16/783G06F18/23213
Inventor 冯研
Owner TCL CORPORATION
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