Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Video label sorting method based on random walk

A video tag, random walk technology, applied in video data retrieval, metadata video data retrieval, special data processing applications, etc., to achieve the appropriate effect of video tag selection

Pending Publication Date: 2020-07-24
HANGZHOU QUWEI SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is to overcome the above-mentioned deficiencies in the prior art, and provides a video tag sorting method based on random walk to solve the problem of video tag selection in non-personalized 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
  • Video label sorting method based on random walk
  • Video label sorting method based on random walk
  • Video label sorting method based on random walk

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0035] A method for sorting video tags based on random walks, specifically comprising the steps of:

[0036] (1) Video tag graph: Define the similarity between video tag i and tag j, calculate the similarity between each tag, and construct a tag graph, and finally get a complete graph; define video tag i, video tag j The similarity calculation formula is as follows:

[0037]

[0038] Among them: N(i) represents the number of videos under label i, and N(j) represents the number of videos under label j. Such as figure 1 As shown, the steps to construct a video tag map are as follows:

[0039] (11) Define graph G=(V,E,p), where V={v 1 ,v 2 ,...,v m} is the set of vertices in the graph, and each vertex represents a video label; E={e 1 ,e 2 ,...,e n} is the set of edges in the graph, and each edge represents the relationship between vide...

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 a video label sorting method based on random walk. The method specifically comprises the following steps: (1) a video label graph: defining the similarity between a video labeli and a label j, calculating the similarity between the labels, constructing the label graph, and finally obtaining a complete graph; (2) vertex density: defining the vertex density according to a random walk algorithm to measure the representativeness of a certain label; (3) vertex density correction: correcting the vertex density through an IDF value, and defining the corrected vertex density;and (4) outputting a sorted video tag sequence by adopting a self-adaptive step length tag sorting algorithm. The method has the beneficial effects that the problem of video label selection in non-personalized recommendation can be solved, so that the video label selection in the non-personalized recommendation is more suitable.

Description

technical field [0001] The present invention relates to the related technical field of video tags, in particular to a video tag sorting method based on random walk. Background technique [0002] The current recommendation methods can be divided into personalized recommendation and non-personalized recommendation. Personalized recommendation generally recommends videos suitable for users based on information such as the user's historical behavior, user basic portrait, and video attributes. When faced with some users with sparse historical behavior or newly registered users, the non-personalized recommendation method of directly recommending popular videos is usually adopted. Popular videos are usually obtained through simple rankings such as time, click-through rate, and total video playback. [0003] In popular video sorting, if click-through rate and playback volume are used as the sorting basis, the sorting results will be biased towards videos under certain tags, and the ...

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
IPC IPC(8): G06F16/78G06F16/735
CPCG06F16/7867G06F16/735Y02D10/00
Inventor 黄睿智范俊顾湘余李文杰姜文蓄
Owner HANGZHOU QUWEI SCI & TECH
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
Eureka Blog
Learn More
PatSnap group products