Training and auditing method and device of content auditing model, equipment and storage medium

A content and model technology, applied in the field of video review, can solve the problems of high cost of model training and low efficiency of video review

Active Publication Date: 2020-02-14
GUANGZHOU NETSTAR INFORMATION TECH CO LTD
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Embodiments of the present invention provide a content review model training and review method, device, device, and storage medium to solve the problem of manual

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
  • Training and auditing method and device of content auditing model, equipment and storage medium
  • Training and auditing method and device of content auditing model, equipment and storage medium
  • Training and auditing method and device of content auditing model, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0044] Example one

[0045] figure 1 This is a flowchart of a method for training a content audit model provided in the first embodiment of the present invention. This embodiment is applicable to the situation where video data is automatically annotated by time and space. The method can be performed by a training device of the content audit model. Execution, the training device of the content audit model can be implemented by software and / or hardware, and can be configured in computer equipment, such as a server, a workstation, a personal computer, etc., the method specifically includes the following steps:

[0046] S101. Receive a sample video file.

[0047] A sample video file belongs to a video (vedio), which has multiple frames of continuous image data. When the continuous image data changes more than 24 frames per second, according to the principle of persistence of vision, the human eye cannot distinguish a single static picture. It looks like a smooth and continuous visual ef...

Example Embodiment

[0077] Example two

[0078] image 3 This is a flowchart of a method for training a content audit model provided in the second embodiment of the present invention. Based on the foregoing embodiment, this embodiment further refines the processing operations of extracting sample image data, locating time points, and extracting image region data. The method specifically includes the following steps:

[0079] S301. Receive a sample video file.

[0080] Among them, the sample video file has multiple frames of image data.

[0081] S302: Divide the sample video file into at least two sample video segments.

[0082] S303. Extract part of the image data from each of the sample video clips as sample image data.

[0083] In a specific implementation, the sample video file can be segmented according to a certain time interval t, that is, the sample video file is divided into at least two sample video segments.

[0084] Randomly extract n frames of image data for each sample video segment as sample i...

Example Embodiment

[0119] Example three

[0120] Figure 4 This is a flowchart of a method for reviewing video content provided in the third embodiment of the present invention. This embodiment is applicable to the situation where video data is reviewed through time and space. The method can be executed by a video content review device. The video content review device can be implemented by software and / or hardware, and can be configured in computer equipment such as servers, workstations, personal computers, etc. The method specifically includes the following steps:

[0121] S401: Receive a target video file.

[0122] The target video file belongs to the video (vedio), which has multiple frames of continuous image data. When the continuous image data changes more than 24 frames per second, according to the principle of persistence of vision, the human eye cannot distinguish a single static picture. It looks like a smooth and continuous visual effect.

[0123] For different business scenarios, the forma...

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 training and auditing method and device of a content auditing model, equipment and a storage medium. The training method of the content auditing model comprises the following steps: receiving a sample video file; extracting partial image data in the sample video file as sample image data; if the content of the sample image data is illegal, positioning the time point of the sample image data in the sample video file; extracting image region data with significance from the image data surrounding the time point; and training a content auditing model according to the image region data and the sample image data. Sample image data of content violation is positioned in time, image area data with significance is positioned in space, features representingcontent violation can be rapidly sampled from a sample video file, and the quality of the features is improved in time and space dimensions, so that a content auditing model is trained, and the performance of the content auditing model can be ensured.

Description

technical field [0001] The embodiment of the present invention relates to the technology of video auditing, and in particular to the training and auditing method, device, equipment and storage medium of the content auditing model. Background technique [0002] With the development of Internet technology, Internet video traffic has increased significantly in recent years, and various new types of UGC (User Generated Content) such as short videos and live broadcasts have made Internet videos more and more abundant. [0003] At the same time, a large number of videos with illegal content, such as videos involving terror, violence, pornography, gambling, etc., are also produced and intended to be spread on the Internet. [0004] Therefore, before or after the video is released, it is generally necessary to review the content of the video to filter out videos with illegal content. [0005] In the early days, it was generally relied on to manually check whether the video resource...

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): G06K9/00G06K9/62G06F16/783G06N3/04
CPCG06F16/783G06V20/41G06N3/045G06F18/214G06V20/46G06N3/084G06V20/49G06V10/82G06V10/22G06V10/774G06T3/40H04N21/4542H04N21/466
Inventor 石峰刘振强
Owner GUANGZHOU NETSTAR INFORMATION TECH 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