Method for generating click rate prediction model and method for predicting click probability
A technology for estimating models and click-through rates, applied in the field of information processing, can solve problems such as differences in sample data distribution and small sample training deviations, and achieve the effects of reducing operation and maintenance costs and solving data sparseness
Active Publication Date: 2022-04-15
ALIBABA GRP HLDG LTD
View PDF16 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
On the other hand, from the perspective of machine learning, this processing scheme is more inclined to learn samples with a large amount of data (or data quality), and there is a bias in the training of small samples
[0004] Therefore, there is a need for a click-through rate estimation scheme that can well solve the problem of sample data distribution differences
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] An exemplary embodiment of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown, it is understood that the disclosure can be implemented in various forms without limitation. Instead, these embodiments are provided to be more thoroughly understood to disclose the present disclosure, and can communicate the scope of the scope of the present disclosure to those skilled in the art.
[0033] figure 1 A schematic diagram of an application scenario 100 in accordance with one embodiment of an embodiment of the present invention is shown. Such as figure 1As shown, the scene 100 includes a client 110, a platform 120, and a server 130. The platform 120 provides a variety of services that are presented to the user through the client 110. At the same time, the traffic line of the platform 120 involves multiple traffic sources. According to an embodiment of the pr...
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
Login to View More Abstract
The invention discloses a method for generating a click rate prediction model and a method for predicting the click probability. Wherein, the method for generating the click-through rate estimation model includes the steps of: acquiring feature data related to the target element clicked by the user and a traffic identifier corresponding to the feature data; inputting the feature data into the first click-through rate estimation model for training, and obtaining the trained The basic network component, wherein the first click-through rate estimation model includes a basic network component and a score calculation component coupled to each other; Two click-through rate prediction models are trained to obtain the trained second click-through rate prediction model as the generated click-through rate prediction model, wherein the second click-through rate prediction model includes trained basic network components coupled to each other and multi-source migration components. The invention also discloses corresponding computing equipment.
Description
Technical field [0001] The present invention relates to the field of information processing, and more particularly to methods of generating a hit rate predictive model and a prediction clicking probability. Background technique [0002] With the rapid development of Internet technology, the click rate (CTR) has become one of the core basis for traffic allocation of Internet platforms. Taking the advertisement on the Internet platform as an example, according to the user's history and behavior of the user, analyze the user's interest and behavior, and thus predict the user's future click behavior to promote accurate delivery of advertisements. This is indispensable for ensuring users, advertisels, and platform triparties. [0003] Simply, the click rate is the ratio of a number of contents on the website page and the number of times the display. At present, common click rate estimates are collectively collecting various sample data, and a unified hit rate estimate model is trained...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L67/1396H04L41/14
CPCH04L41/145H04L67/535
Inventor 陈冠豪王路路孟晓楠
Owner ALIBABA GRP HLDG LTD