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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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