Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Advertisement intercepting system and method based on graphs and machine learning

An ad blocking and machine learning technology, applied in the field of ad blocking systems based on graph and machine learning, can solve problems such as blacklist blocking error page loading time, affecting user online experience, and inability to display page content, reducing labor costs, Improve the interception ability and the effect of high interception accuracy

Pending Publication Date: 2021-01-15
山西三友和智慧信息技术股份有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] For the advertisements appearing on the webpage, the currently known effective interception method is to use the blacklist and browser extensions to intercept. This method has been proved to be effective, but because the advertisements on the page will be updated continuously, and the update of the blacklist requires Manual completion greatly increases labor costs. At the same time, the blacklist also has interception errors and slows down the page loading time, making normal page content impossible to display, thereby affecting the user's online experience

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
  • Advertisement intercepting system and method based on graphs and machine learning
  • Advertisement intercepting system and method based on graphs and machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Such as Figure 1 to Figure 2 As shown, an advertisement blocking system and method based on graph and machine learning, the system includes a sequentially connected traceability graph building module, feature extraction module, and classifier module;

[0034] The traceability map construction module is used to collect page resource loading information in the browser rendering page pipeline, construct a traceability map, and map the resources in the page to their unique source;

[0035] The feature extraction module is used to receive the traceability graph generated by the traceability graph construction module, extract content features and structural features for each node in the graph, that is, page resources, and generate a multidimensional feature vector for each node;

[0036] The classifier module is used to classify and identify the multi-dimensional feature vectors of multiple nodes extracted in the feature extraction module, find out the advertising resources ...

Embodiment 2

[0044] On the basis of embodiment 1, it also includes a blacklist module, a marking module, a learning module and a feedback module, the marking module is connected with the feature extraction module and the blacklist module respectively, and the marking module is extracted according to the existing data marking feature in the blacklist module The multidimensional feature vector generated by the module is stored; the learning module is connected with the labeling module and the classifier module respectively,

[0045] The feedback module is respectively connected with the classifier module and the blacklist module, and the feedback module is used to further process the url of the advertisement resources obtained in the classifier module, generate filtering rules not in the blacklist module, and expand the blacklist module.

[0046] According to the set time interval, the learning module trains the classifier model according to the newly added data in the marking module, and is ...

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 relates to an advertisement interception system and method based on graphs and machine learning. The system comprises a traceability graph construction module, a feature extraction module and a classifier module. The traceability graph construction module collects page resource loading information in a pipeline of a browser rendering page, constructs a traceability graph, and enablesresources in the page to correspond to a unique source of the resources; A learning module performs learning training through the training data obtained by the marking module to obtain a classifier for identifying advertisement resources; and the classifier module classifies and identifies the network resource nodes in the traceability graph obtained in the feature extraction module, finds out advertisement resources in the network resource nodes, and extracts urls corresponding to the advertisement resources. The advertisement resources in pages are recognized and intercepted by constructingthe traceability graph and adopting the machine learning method, the functions of increasing the page loading speed and being high in interception accuracy rate are achieved, and meanwhile the function of automatically expanding the blacklist can be achieved according to the advertisement resources found out from the traceability graph; the invention relates to the technical field of network security.

Description

technical field [0001] The present invention relates to the technical field of network security, and more specifically, to an advertisement blocking system and method based on graph and machine learning. Background technique [0002] For the advertisements appearing on the webpage, the currently known effective interception method is to use the blacklist and browser extensions to intercept. This method has been proved to be effective, but because the advertisements on the page will be updated continuously, and the update of the blacklist requires Manual completion greatly increases the labor cost. At the same time, the blacklist also has blocking errors and slows down the loading time of the page, so that the normal page content cannot be displayed, which in turn affects the user's online experience. [0003] Therefore, it is necessary to improve the prior art. Contents of the invention [0004] In order to overcome the deficiencies in the prior art, an advertisement bloc...

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): G06F16/9535G06F16/951G06F16/955G06K9/62G06N20/00
CPCG06F16/9535G06F16/951G06F16/9566G06N20/00G06F18/24
Inventor 潘晓光王小华王宇琦潘晓辉董虎弟
Owner 山西三友和智慧信息技术股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com