Check patentability & draft patents in minutes with Patsnap Eureka AI!

Video hotspot fragment detection method and device based on bullet screen emotion, and storage medium

A technology of video clips and detection methods, which is applied in the fields of instruments, electronic digital data processing, character and pattern recognition, etc., can solve the problems of many new words on the Internet, inaccurate calculation of emotional intensity, and obvious colloquialism of barrage texts, etc., and achieve high The effect of detecting accuracy and improving calculation accuracy

Active Publication Date: 2021-04-23
CHONGQING UNIV OF POSTS & TELECOMM
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method based on the emotional dictionary mainly uses the emotional dictionary to calculate the emotional strength, but the bullet-screen text is obviously colloquial, and there are many new words on the Internet, so the calculation of the emotional strength is inaccurate
Supervised machine learning methods require a large amount of labeled corpus and cannot quantify emotional strength

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 hotspot fragment detection method and device based on bullet screen emotion, and storage medium
  • Video hotspot fragment detection method and device based on bullet screen emotion, and storage medium
  • Video hotspot fragment detection method and device based on bullet screen emotion, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Such as figure 1 As shown, the present invention is based on the barrage emotion video hotspot segment detection method, and the overall overall flow chart is as follows figure 1 As shown, specifically steps S1-S7 are included:

[0075] Step S1, cleaning the acquired bullet chat video, and segmenting the cleaned bullet chat video to obtain video clips;

[0076] Step S2, constructing a bullet chatting sentiment dictionary, using the constructed bullet chatting sentiment dictionary to calculate the emotional intensity of the bullet chatting in the video clip in step S2, obtain the overall emotional intensity of the video clip, and calculate the overall emotional intensity of the video clip according to the overall emotional intensity tendency to judge

[0077] Step S3, according to the overall emotional intensity of each video segment obtained in step S2, calculate the rate of change of the emotional intensity of each video segment;

[0078] Step S4, according to the t...

Embodiment 2

[0129] The present invention provides a video hotspot segment detection device based on barrage emotion, including a preprocessing module, an emotion calculation module, a topic similarity calculation module, a boundary judgment module, and a detection module, wherein,

[0130] The preprocessing module is used to segment and clean the acquired bullet chat video data to obtain video fragments and construct a bullet chat sentiment dictionary;

[0131] The emotional calculation module is used to calculate the overall emotional intensity of the video clips and determine the overall emotional tendency using the barrage emotional dictionary built by the preprocessing module, and calculate the emotional intensity change rate of adjacent video clips for the video clips that have completed the overall emotional intensity calculation. calculation;

[0132] The topic similarity calculation module is used to calculate the topic similarity of the video clips, use the LDA topic model to ext...

Embodiment 3

[0137] A computer-readable storage medium, on which a computer program is stored, and the computer program implements the bullet chat emotion-based video hotspot segment detection method described in Embodiment 1 when running.

[0138] It can be understood that the present invention comprehensively considers facial expressions, modal particles, and network terms, constructs a new bullet-screen emotion dictionary, and improves the calculation accuracy of bullet-screen emotion intensity; at the same time, combined with the timing characteristics of bullet-screen, a new bullet-screen emotion is proposed. The intensity calculation method can obtain more accurate emotional intensity calculation results; the problem of hot video segment detection is transformed from the analysis of video frames to the analysis of the bullet chat text corresponding to the video segment, which meets the needs of users to retrieve hot segments by using emotional tendencies and keywords demand, with high...

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 bullet screen emotion-based video hotspot fragment detection method and device and a storage medium, and the method comprises the steps: cleaning an obtained bullet screen video, carrying out the segmentation of the cleaned bullet screen video, constructing a bullet screen emotion dictionary, and carrying out the emotion intensity calculation and overall emotion tendency judgment of a bullet screen in a video fragment; calculating the emotion intensity change rate of the adjacent video clips; performing topic extraction by using an LDA topic model, and calculating topic similarity of adjacent video clips; constructing a hotspot video clip detection model; and inputting a barrage video to be detected into the model to obtain a hotspot video clip. According to the constructed barrage emotion dictionary, the barrage emotion intensity calculation accuracy is improved, a more accurate emotion intensity calculation result can be obtained through the barrage emotion intensity calculation method, analysis directly corresponding to the barrage text meets the requirement of a user for retrieving hot spot fragments through emotion tendency and keywords, and high detection accuracy is achieved.

Description

technical field [0001] The invention relates to the field of network public opinion, in particular to a method, device and storage medium for detecting video hotspot segments based on barrage emotion. Background technique [0002] In recent years, with the popularity of online videos, the number of videos has exploded. It is of great practical significance to efficiently push high-quality hot video clips that meet content needs and emotional tendencies for user groups. However, the existing methods for detecting video hotspot segments on video websites mainly include manual screening and clipping and automatic machine recognition. For the increasingly generated video data, the manual editing method is ineffective, time-consuming, and costly, and the accuracy of automatic machine recognition and detection is low. [0003] There are two main methods for machine automatic identification of hotspot video clip detection, one is based on the number of barrage in the video 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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06F40/242G06F40/253G06F40/284G06K9/62
CPCG06F40/242G06F40/253G06F40/284G06V20/41G06V20/49G06F18/22
Inventor 吴渝张运凯杨杰李芊
Owner CHONGQING UNIV OF POSTS & TELECOMM
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com