Multi-modal fusion sensitive information classification detection method

A sensitive information, classification detection technology, applied in the Internet field, can solve the problems of inaccuracy and insufficient detection of sensitive information, and achieve the effect of high detection accuracy

Active Publication Date: 2021-06-25
HENAN UNIV OF SCI & TECH
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned technical problems, the present invention aims at the insufficient and inaccurate detection of sensitive information in social networks, and proposes a multi-modal fusion sensitive information classification and detection method based on deep learning in combination with two modalities of text and pictures

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
  • Multi-modal fusion sensitive information classification detection method
  • Multi-modal fusion sensitive information classification detection method
  • Multi-modal fusion sensitive information classification detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] In order to verify the effectiveness of the present invention, different types of pictures crawled from the Internet by crawler programs are used to divide sensitive categories into four categories, including sensitive category A, sensitive category B, sensitive category C and other categories. Sensitive text datasets are obtained by splicing and reorganizing related sensitive words, including sensitive category A, sensitive category B, sensitive category C and other categories. The normal text data set comes from the normal comment set of Weibo. Technical scheme of the present invention can be specifically implemented as follows:

[0049] (1) In the sensitive model training stage. Use the sensitive word library of jieba word segmentation to train the text model; in the process of image model training, firstly, the input image is randomly flipped, sheared, enlarged, cropped, etc. to expand the data set to increase the diversity of the image, and finally the The images...

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

A multi-modal fusion sensitive information classification detection method comprises the steps of 1, carrying out sensitivity primary detection on a text and a picture, 2, judging the sensitivity of the text based on emotion, and 3, carrying out multi-modal sensitivity detection of image-text fusion, and the sensitive information is detected and classified by combining two modes of the text and the picture. Sensitivity detection needs to be carried out on the text and the picture respectively, and the sensitivity of the content can be accurately judged in combination with the influence of emotion polarity and intensity on sensitive information. The image-text sensitivity problem is solved according to a proper fusion method, and high detection precision is achieved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a multi-modal fusion sensitive information classification and detection method. Background technique [0002] With a large number of Internet users around the world, online social networks have become the preferred platform for information exchange. With the popularization and application of social networks more and more widely, the information of social networks takes pictures, texts, audio and video as the carrier, showing a trend of diversification, complexity, and massification. A large amount of sensitive information is flooded in social networks, seriously affecting Cybersecurity and people's physical and mental health. How to use artificial intelligence technology to efficiently and accurately detect sensitive information has become an urgent problem to be solved in academia and industry. [0003] Most of the existing research on sensitive information detection uses...

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): G06K9/62G06F16/35G06F16/55G06F40/216G06N20/00
CPCG06F16/355G06F16/55G06F40/216G06N20/00G06F18/2415G06F18/25
Inventor 张志勇宋斌张蓝方梁腾翔徐艳艳苗坤霖赵长伟黄帅娜李静张孝国
Owner HENAN UNIV OF SCI & TECH
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