Unlock instant, AI-driven research and patent intelligence for your innovation.

A method, device, and electronic device for automatic retrieval of image-type infringing entities

An image and entity technology, applied in neural learning methods, digital data information retrieval, electronic digital data processing, etc., can solve problems such as the inability to protect the interests of enterprises, the inability to quickly discover and confirm risks, and the long time spent. , to achieve the effect of suppressing the influence of anti-disturbance, good adaptability, and reducing time consumption

Active Publication Date: 2021-08-31
天际友盟(珠海)科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, in the process of preventing and controlling digital risks, the discovery and confirmation process generally adopts the method of manual retrieval and monitoring, which takes a long time, especially when the business scale is large, it takes longer and cannot be quickly discovered. And confirm the risk, so as to quickly enter the disposal stage, take corresponding measures to control the risk, and then fail to protect the interests of the enterprise well

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
  • A method, device, and electronic device for automatic retrieval of image-type infringing entities
  • A method, device, and electronic device for automatic retrieval of image-type infringing entities
  • A method, device, and electronic device for automatic retrieval of image-type infringing entities

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as figure 1 As shown, the embodiment of the present invention provides an automatic retrieval method for image-type infringing entities, including:

[0050] S101. Receive a risk image and determine its corresponding category, where the category of the risk image includes enterprise LOGO, user avatar, visible page, text thumbnail and / or key frame of video;

[0051] S102. Perform pre-computation processing on the risk image according to the category of the risk image to obtain a feature vector of the risk image; the pre-calculation processing includes: performing an infringement instance on the map for the risk image of the enterprise LOGO class Candidate area identification to obtain a candidate image; performing image vectorization against image compression on the candidate image or the risk image of the user avatar, visible page, text thumbnail and / or key frame class of the video to obtain the image vectorization of the risk image Feature vector;

[0052] S103. ...

Embodiment 2

[0101] Such as figure 2 As shown, another aspect of the present invention also includes a functional module architecture that is completely consistent with the aforementioned method flow, that is, the embodiment of the present invention also provides an automatic retrieval device for image-type infringing entities, including:

[0102] The image receiving module 201 is used to receive the risk image and determine its corresponding category, the category of the risk image includes enterprise LOGO, user avatar, visible page, text thumbnail and / or key frame of video;

[0103] The pre-calculation module 202 is used to perform pre-calculation processing on the risk image according to the category of the risk image to obtain the feature vector of the risk image; the pre-calculation processing includes: performing a Identify the candidate region of the infringement instance on the graph to obtain the candidate image; carry out image vectorization against image compression for the can...

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 automatic retrieval method, device and electronic equipment for image-type infringing entities. The method includes: receiving different types of risk images, including enterprise LOGOs, user avatars, visible pages, text thumbnails and / or key frames of videos, etc.; performing pre-calculation processing on different types of risk images to obtain the obtained The feature vector of the risk image; searching based on the feature vector of the risk image, searching for images similar to the risk image, and obtaining the entity information to which the image belongs. The solution has good adaptability; by identifying the candidate area of ​​the infringement instance for the risk image of the enterprise LOGO, it effectively solves the problem that the classification accuracy drops sharply with the increase of LOGO, and can adapt to the massive LOGO infringing entity retrieval scene; in addition , through the anti-image compression image vectorization method, the calculation time is reduced and the calculation accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of enterprise digital security, in particular to an automatic retrieval method, device and electronic equipment for image-type infringing entities. Background technique [0002] With the continuous development of digital technology, online and digital capabilities are becoming the basic survival skills for enterprises facing new scenarios. In the process of digital transformation, enterprises will have more digital platforms, provide customers with more independent services and new media services; enterprises will quickly release more systems and functions to maintain competitiveness; enterprises will deploy more IT Cloudification of infrastructure, and even direct use of public cloud services. However, every time an enterprise introduces a new technology in the process of digitalization, it will inevitably increase the complexity of networks, applications, and data storage, and the digital risks faced by e...

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 Patents(China)
IPC IPC(8): G06F16/583G06F16/783G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06F16/583G06F16/783G06N3/08G06V10/44G06N3/047G06N3/045G06F18/241G06F18/2415
Inventor 董龙飞
Owner 天际友盟(珠海)科技有限公司
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