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

Abnormal advertisement flow detection method based on user portrait

A traffic detection and user technology, applied in the computer field, can solve the problems of advertiser loss in the online advertising industry, malicious cheating in the online advertising business, etc., and achieve the effects of increasing timeliness and speeding up monitoring

Pending Publication Date: 2020-04-10
杭州古点网络科技有限公司
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development of Internet technology, people's way of life has also changed, and the demand for online advertising business is constantly increasing. More and more advertisers choose to place advertisements online. Faced with huge market profits, malicious cheating in online advertising business is becoming more and more serious. Huge losses to the online advertising industry and advertisers

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
  • Abnormal advertisement flow detection method based on user portrait

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Specifically, as shown in the figure, a method for detecting abnormal advertising traffic based on user portraits includes the following steps:

[0026] Step 1. Track user behavior on the advertisements viewed by users: collect user attribute information and user behavior information, locate users through cookie information in the browser, and secondly locate users through IP information;

[0027] Step 2. Characteristic analysis of user attributes: For the user attributes, behavior information and overall traffic conditions within a time period collected by a single user analysis, each attribute and behavior will generate a user label;

[0028] Step 3: Analyze the profile of a single user on the basis of Step 2: through aggregation and analysis of the historical data of multiple user tags, further adjust the user characteristic information; this step analyzes the historical context data of the user, that is, a single user behavior cannot Accurately outline user portrait...

Embodiment 2

[0032] In order to predict abnormal traffic more accurately, on the basis of Embodiment 1, in Step 4, user traffic can be further analyzed in terms of time and region. The specific steps are as follows:

[0033] (1) Statistical data according to time, region, and advertisement type dimensions. The time dimension is divided into hours, days, and months. The geographical dimension is divided according to the actual geographic location, and the advertisement type is divided according to the advertisement type data browsed by the user;

[0034] (2) Analyze user historical data on the basis of step (1), calculate traffic trends, and predict the abnormal situation of time advertisements according to the trend data.

[0035] In the second step of the present invention, the user label includes the following information:

[0036] The user identifier is the unique identification information of the user, which is used to connect the text and attributes of the user; the IP address, which ...

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 abnormal advertisement flow detection method based on a user portrait. User attributes are collected through webpage operation data, user behavior information is tracked, feature recognition is conducted on the attributes and behavior analysis of a user through a feature model, the user portrait is drawn according to features, user labeling can be achieved through the features, and finally whether the user is an effective user or not is recognized through clustering analysis. According to the method, the abnormal flow can be accurately identified by combining the historical data of the user, and meanwhile, the abnormal flow monitoring speed can be increased by combining the scheme with a real-time analysis technology, so that the timeliness is improved.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for detecting abnormal advertisement traffic based on user portraits. Background technique [0002] With the development of Internet technology, people's lifestyles have also changed, and the demand for online advertising business is constantly increasing. More and more advertisers choose to place advertisements online. Faced with huge market profits, malicious cheating in online advertising business is becoming more and more serious. It has brought huge losses to the online advertising industry and advertisers. Contents of the invention [0003] The purpose of the present invention is to provide a method for effectively identifying abnormal advertising traffic against the defects of the prior art, which is mainly used to solve how to effectively identify abnormal traffic in a web environment with limited information and ensure the interests of advertisers. [0004] In order ...

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): G06Q30/02G06K9/62
CPCG06Q30/0242G06Q30/0201G06F18/23213
Inventor 陈逗
Owner 杭州古点网络科技有限公司
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