Video label generation method

A video and label technology, applied in the field of video label generation, can solve problems such as low accuracy, labor and time consumption, and achieve the effect of solving low accuracy

Pending Publication Date: 2022-02-18
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem solved by the present invention is to provide a method for generating video tags, which solves the problems of low accuracy and consuming a lot of manpower and time in the existing manually edited video tags

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 generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The tag generation method of the video of the present invention, as attached figure 1 shown, including the following steps:

[0017] S01. Obtain a similar video set of the video and the similarity between the video and each similar video in the similar video set;

[0018] Specifically, the similar video set of the video and the similarity between the video and each similar video in the similar video set are obtained through a collaborative filtering algorithm or a swing algorithm. For example: given a certain video V, find similar videos and similarities with the video V in the video library through collaborative filtering algorithm or swing algorithm, arrange the obtained similar videos in order of similarity from large to small, select The top 20 similar videos are used as elements in the similar video set, that is, similar videos V1, V2, V3...V20 are obtained.

[0019] S02. Perform normalization processing on the similarity to obtain a second similarity of each sim...

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 a video label generation method, and relates to the technical field of video labels. The method comprises the following steps: based on user behavior data, obtaining a similar video set of videos and the similarity between the videos and each similar video in the similar video set through a collaborative filtering algorithm or a swing algorithm, and then carrying out normalization processing on the similarity, obtaining a second similarity of the similar videos, taking the information elements of the similar videos as initial tags of the videos, obtaining the weight of each initial tag by using the second similarity, and taking the initial tags of which the weights are greater than a preset value as the tags of the videos, thereby solving the problems that the existing manual editing of the video tags is low in accuracy and high in efficiency, and a lot of manpower and time are consumed. The method is suitable for video tag generation.

Description

technical field [0001] The invention relates to the technical field of video tags, in particular to a method for generating video tags. Background technique [0002] With the rapid development of the film and television industry, there are all kinds of videos on the Internet for people to choose to watch. People can choose the content they like to watch according to the tags of the videos, or according to the tags of the videos, the recommendation system is based on the tags of the videos. Recommend videos of interest to users. However, most of the tags of these videos rely on manual editing. Because people have different understandings of things, the tags for the same video are also different, and manual editing of tags consumes a lot of manpower and time. . Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a method for generating video tags, which solves the problems of low accuracy and consuming a lot of manpo...

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): G06F16/78G06F16/9536G06K9/62
CPCG06F16/7867G06F16/9536G06F18/22
Inventor 马荣深吴上波
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