Image sequence auditing method and system, electronic equipment and storage medium

An image sequence and sequence technology, which is applied in the computer field, can solve problems such as the inability to realize image sequence review, and achieve the effects of automatic review, improvement of correct rate, and reduction of labor costs

Pending Publication Date: 2019-12-10
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide an image sequence review method and system, electronic equipment and storage media in order to overcome the defect that image sequence review cannot be realized in the prior art

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
  • Image sequence auditing method and system, electronic equipment and storage medium
  • Image sequence auditing method and system, electronic equipment and storage medium
  • Image sequence auditing method and system, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides an image sequence review method based on deep learning, which can automatically and accurately identify whether the image sequence meets the release requirements of Internet sites. An image sequence is also a set of images with sorting rules. Such as figure 1 As shown, the audit methodology includes the following steps:

[0056] Step 101, establishing an image sequence model based on a neural network.

[0057] Such as figure 2 As shown, step 101 specifically includes:

[0058] Step 101-1. Obtain a marked image sequence as a first training sample.

[0059] Step 101-1 is to construct an initial sample set for training a neural network. Get labeled image sequences from Internet sites as initial samples. For new businesses that do not have historical data, some image sequences can be manually labeled as training samples, that is, some image sequences are collected and marked using the review standards formulated by the business.

[0060] Mar...

Embodiment 2

[0088] Embodiment 2 is basically the same as Embodiment 1, except that the review method of this embodiment also performs tuning training on the image sequence model. Such as image 3 As shown, the review method of this embodiment, after step 108, also includes:

[0089] Step 110, mark the target image sequence as a second training sample.

[0090] The target image sequence is the image sequence that the user lodges a complaint after the image sequence model judges, and the business personnel will mark it after review, and add the marked target image sequence to the difficult sample database as the second training sample for model tuning train. The second training sample will be integrated into the initial sample set and downloaded automatically. In the process of model training, you can set the number of samples for each training, for example, 5000. When the number of samples exceeds 5000, the training process will be triggered; otherwise, the number of samples will be con...

Embodiment 3

[0094] Figure 4 A schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention shows a block diagram of an exemplary electronic device 30 suitable for implementing the embodiment of the present invention. Figure 4 The electronic device 30 shown is only an example, and should not limit the functions and scope of use of the embodiments of the present invention.

[0095] Such as Figure 4 As shown, electronic device 30 may take the form of a general-purpose computing device, which may be a server device, for example. Components of the electronic device 30 may include, but are not limited to: at least one processor 31 , at least one memory 32 , and a bus 33 connecting different system components (including the memory 32 and the processor 31 ).

[0096] The bus 33 includes a data bus, an address bus, and a control bus.

[0097] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 3...

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 an image sequence auditing method and system, electronic equipment and a storage medium. The auditing method comprises the following steps: establishing an image sequence modelbased on a neural network; obtaining a to-be-audited image sequence; and extracting image features of each image in the image sequence and inputting the image features into the image sequence model,and calculating the confidence coefficient that the image sequence meets the publishing requirement. According to the invention, manual auditing is replaced by the image sequence model based on deep learning, so that automatic auditing of the image sequence is realized, the accuracy is greatly improved, and the labor cost is reduced.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an image sequence review method and system, electronic equipment and a storage medium. Background technique [0002] In order to comply with the relevant regulations, the image needs to be reviewed before it can be published on the Internet site. For example, on e-commerce or third-party evaluation websites, it is necessary to review the correlation between pictures and text, the quality of pictures, whether there are illegal elements, and the associated sequence of multiple related pictures. Different websites have different requirements. [0003] Currently, there are two main methods of image review: [0004] (1) Purely manual review, that is, a single picture and a sequence of pictures are checked one by one by specialized business personnel according to the review rules. This method has high labor cost, low efficiency, and high error rate; [0005] (2) Semi-manual revie...

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): G06K9/66G06N3/04
CPCG06V30/194G06N3/045
Inventor 朱俊伟张震涛佘志东王曦晨王刚张亮饶正锋
Owner BEIJING JINGDONG SHANGKE 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