A video tag determination method based on video comment text

A video labeling and video commenting technology, applied in the field of data processing, can solve the problems of unsupervised, slow convergence, poor classification effect, etc., and achieve the effect of improving utilization rate, reducing risk, and reducing labor cost

Active Publication Date: 2022-05-13
ZHEJIANG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the user's expression is relatively ambiguous and does not directly use tag words, it is easy to fail to extract accurate keywords; or when multiple synonyms express the same keyword, the correlation between different keywords cannot be connected
[0007] Supervised methods such as SVM, TextCNN, RNN, etc. use machine learning models to solve some problems in unsupervised methods, but because they do not take into account the contribution of different comments and different words to label determination, such methods have slow convergence. The problem of poor classification

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 tag determination method based on video comment text
  • A video tag determination method based on video comment text
  • A video tag determination method based on video comment text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments, and the purpose and effects of the present invention will become more apparent.

[0035] figure 1 The flow chart of the method of the present invention is given. The present invention divides the determination of the label for the video based on the video comment text into three steps, that is, preprocessing the video comment text, training the multi-layer attention network model, and based on the target video comment document. Determine the label of the target video.

[0036] Such as figure 1 As shown, in step 101, the specific steps of comment text preprocessing are as follows: based on the original comment data, the non-text information such as special symbols and punctuation marks in each original comment data is deleted, and some emoji may be included in the original comment data Meaningless symbols such as emoticons, punctuation...

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 tag determination method based on video comment text. The method includes: (1) performing data cleaning and preprocessing on video comments; (2) using the preprocessed comment documents D and corresponding video labels to train a multi-layer attention network model; (3) using the comment documents of the target video Input to the trained multi-layer attention network model to determine the label of the target video. The video label determination method provided by the present invention can effectively determine the corresponding label required by the video.

Description

technical field [0001] The invention belongs to the technical field of data processing, and relates to a video label determination method based on video comment text. Specifically, it involves a method for obtaining key information from comments and determining the label of the target video when the user comments of the target video are given. Background technique [0002] In order to better help users retrieve videos, video portals usually put multiple tags on videos, so that users can quickly understand the theme and style of videos, and help users quickly retrieve the videos they want to watch, thereby improving user experience and video clicks Rate. [0003] In the prior art, video tags are usually manually tagged, that is, the uploader manually selects the corresponding tag when the video is uploaded. Since it mainly relies on the subjective judgment of the video uploader and lacks effective feedback from users, manually uploaded tags There is a certain degree of rand...

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): G06F16/78G06F16/75G06N3/04G06N3/08
CPCG06F16/7867G06F16/75G06N3/084G06N3/045
Inventor 王瑞琛杜歆
Owner ZHEJIANG 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