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

Video identifying method, device and system

A technology of video and video content, applied in the field of communication, can solve problems such as poor effect, low recognition accuracy, and single recognition dimension, and achieve the effect of improving recognition effect and accuracy

Active Publication Date: 2016-12-21
TENCENT TECH (SHENZHEN) CO LTD +1
View PDF6 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the prior art, the inventors of the present invention found that, because the recognition dimension of the existing recognition scheme is relatively single, the recognition accuracy is low and the effect is not good

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 identifying method, device and system
  • Video identifying method, device and system
  • Video identifying method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] This embodiment will be described from the perspective of a video recognition device. Specifically, the video recognition device may be integrated in a server or the like. The server may be a single server or a service cluster.

[0036] A method for identifying a video, comprising: acquiring video information that needs to be identified, the video information including video content and video-related information, etc.; identifying pictures in the video content to obtain a picture identification result; Recognize the voice to obtain the speech recognition result; recognize the subtitles in the video content and the text of the video-related information to obtain the text recognition result; perform fusion calculation on the picture recognition result, speech recognition result and text recognition result to obtain the video recognition result.

[0037] Such as Figure 1b As shown, the specific flow of the video recognition method can be as follows:

[0038] 101. Acquir...

Embodiment 2

[0095]According to the method described in Embodiment 1, an example will be given below for further detailed description.

[0096] In this embodiment, it will be described by taking the video recognition device integrated in a service cluster as an example.

[0097] Such as Figure 2a As shown, the service cluster may include an access layer module ( Figure 2a referred to as access layer), image recognition module, speech recognition module, text recognition module, user trend analysis module, and policy layer module ( Figure 2a (referred to as strategy layer in the middle), etc., the details can be as follows:

[0098] (1) access layer module;

[0099] The access layer module is used to receive the video information that needs to be identified sent by the service server, such as the video information of the live video, etc., and then transmit the video information that needs to be identified to the picture recognition module and the voice recognition module respectively ...

Embodiment 3

[0156] In order to better realize the above method, the embodiment of the present invention can also provide a video recognition device, such as Figure 3a As shown, the video recognition device may include an acquisition unit 301, a picture recognition unit 302, a speech recognition unit 303, a text recognition unit 304 and a fusion unit 305, as follows:

[0157] (1) acquisition unit 301;

[0158] The acquiring unit 301 is configured to acquire video information that needs to be identified.

[0159] Wherein, the video information may include video content and video-related information, the video content may include information such as video pictures, voice and subtitles, and the video-related information may include information such as video-related introductions, comments, and / or barrage.

[0160] In addition, the video information may also include other information such as viewing user information. Wherein, the viewing user information may include information such as the ...

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 embodiment of the invention discloses a video identifying method, device and system. After video information needing identification is obtained, correlated information of a picture, a voice, a subtitle, and a video in the video content is identified respectively to obtain multi-dimensional identification results including a picture identification result, a voice identification result, and a text identification result and the like; and fusion calculation is carried out on the identification results to obtain a video identification result. According to the scheme, the identification accuracy is enhanced and the identification result is improved.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a video recognition method, device and system. Background technique [0002] At present, watching clear and smooth videos in real time on terminals has become the first choice for many users for leisure and entertainment. For this reason, a large number of video resources have emerged on the market. How to identify these mixed video resources to avoid The dissemination of videos with inappropriate content has also become a concern of the industry. [0003] The so-called videos with objectionable content refer to videos that are prohibited from being collected or disseminated by laws and regulations such as pornography, prostitution, violence, and political sensitivity. In the existing technology, for video identification, it mainly relies on manual review one by one. However, in the Internet era of live broadcast by the whole people, the number of live videos is i...

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): G06K9/00G06F17/27G06K9/62G06T7/40G10L15/26H04N21/233H04N21/234H04N21/235
CPCH04N21/233H04N21/23418H04N21/235G10L15/26G06T2207/10016G06T2207/30196G06F40/284G06V40/16G06V20/47G06V20/40G06F18/256
Inventor 余宗桥
Owner TENCENT TECH (SHENZHEN) CO LTD
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