Method and device for predicting advertisement click rate based on user behaviors

A technology of advertising click and prediction method, which is applied in the fields of regression model, user behavior analysis, and advertising click-through rate prediction. Advertisements that are of interest to users, etc.

Inactive Publication Date: 2012-02-08
亿赞普(北京)科技有限公司
View PDF2 Cites 150 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the advertising placement strategy in the prior art does not take into account the user's individual interests, and cannot accurately

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
  • Method and device for predicting advertisement click rate based on user behaviors
  • Method and device for predicting advertisement click rate based on user behaviors
  • Method and device for predicting advertisement click rate based on user behaviors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] figure 1 A flow chart showing a method for predicting the click-through rate of an advertisement based on user network access behavior (referred to herein as user behavior) according to Embodiment 1 of the present invention, the following refers to figure 1 Detailed steps of the method in this embodiment will be described in detail.

[0032] The method of the present embodiment generally includes two stages, as figure 1 As shown in , the first stage of the part shown by the thin solid line is the behavior orientation stage, and the second stage shown by the thick solid line is the intra-category ranking stage using the content matching / search trigger method.

[0033] The first stage specifically includes the following steps:

[0034] Step S110, acquiring user feature information related to the behavior of the user clicking on the advertisement.

[0035] Specifically, according to the user's historical search messages, the user's web browsing messages, and the user's ...

Embodiment 2

[0094] Figure 4 It is a structural block diagram of an advertising click-through rate prediction device based on user behavior according to Embodiment 2 of the present invention, according to the following Figure 4 Describe the composition of the device.

[0095] The device includes a behavior orientation prediction unit, an intra-category sorting unit, and a comprehensive sorting unit.

[0096] The behavior-oriented prediction unit is used to train a behavior-oriented model by analyzing user behavior, predict the user's click-through rate for different types of advertisements according to the behavior-oriented model, and obtain a click-through rate prediction value.

[0097] The intra-category sorting unit is configured to sort the advertisements in each category according to the user's current behavior type to obtain a sorted list of advertisements in the category.

[0098] A comprehensive sorting unit, configured to sort the click-through rates of all advertisements bas...

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 a method and device for predicting advertisement click rate based on user behaviors. The method comprises the following steps of: behavior directional prediction: training a behavior directional model by analyzing the user behaviors, and predicting the click rates of the user on different types of advertisements to obtain a predicted value of the click rate; in-type sorting: sorting the advertisements of each type according to the current behavior type of the user to obtain an in-type advertisement sorting list; and comprehensive sorting: sorting the click rates of all advertisements according to the predicted value of click rate and the in-type advertisement sorting list to obtain a comprehensive sorting list. Through the method disclosed by the invention, a prediction model can be established for each type of advertisements so as to sort the advertisements more accurately according to the type characteristics of the advertisements.

Description

technical field [0001] The invention relates to advertisement click-through rate prediction, user behavior analysis, and regression model, in particular to attempting to model and analyze users' web browsing or search behaviors so as to predict their click-through rates for advertisements. Background technique [0002] The rise of the Internet enables people to see different advertisements when browsing the same page, realizing the personalized display of advertisements. In this way, it is possible to more accurately display advertisements that may be of interest to each user, thereby increasing the click-through rate of advertisements and improving the effect of advertisement delivery. [0003] Existing advertising precision placement strategies mainly include the following three categories: sponsored search, content match, and behavioral targeting. [0004] Among them, the search trigger strategy includes searching advertisements according to the keywords submitted by the...

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): G06Q30/00G06F17/30
Inventor 罗峰黄苏支李娜
Owner 亿赞普(北京)科技有限公司
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