Prediction model training method and device and information recommendation method and device

A prediction model and training method technology, applied in the computer field, can solve problems such as low accuracy of prediction results

Pending Publication Date: 2022-03-01
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, the content of the recommended information may not match the user's preference in the training samples of the CTR prediction model, but because the recommended information is displayed to the user in the front position, the user repeatedly clicks on the recommended information, which strengthens the CTR. The prediction model learns the recommendation information, and the accuracy of the prediction results of the obtained CTR prediction model is relatively low.

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
  • Prediction model training method and device and information recommendation method and device
  • Prediction model training method and device and information recommendation method and device
  • Prediction model training method and device and information recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to make the purpose, technical solution and advantages of this specification clearer, the technical solution of this specification will be clearly and completely described below in conjunction with specific embodiments of this specification and corresponding drawings. Apparently, the described embodiments are only some of the embodiments in this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this specification.

[0056] In order to eliminate the impact of the display position on the prediction accuracy of the click-through rate prediction model, this specification provides a method for training the prediction model and a method for information recommendation. In this method, see figure 1 , the prediction model includes a prediction network and a position compensation network, and the position compen...

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 prediction model training method and an information recommendation method and device, and particularly discloses a method for obtaining a training sample, inputting the training sample into a prediction model so as to enable the prediction model to determine a prediction click rate for historical recommendation information according to the historical recommendation information and feature information of a user, and according to the display environment information, determining a click rate compensation value corresponding to the display position of the historical recommendation information, finally, according to the click rate compensation value, compensating the predicted click rate of the historical recommendation information to obtain a compensated click rate, and according to the compensated click rate and the actual browsing condition corresponding to the historical recommendation information, determining the actual browsing condition of the historical recommendation information. And training the prediction model. Therefore, a corresponding click rate compensation value can be trained for each display position, and the influence of the display position on the prediction precision of the prediction model is eliminated through the click rate compensation value, so that the prediction precision of the prediction model is improved.

Description

technical field [0001] This specification relates to the field of computer technology, in particular to a method for training a predictive model, and a method and device for information recommendation. Background technique [0002] With the development of network technology, the data volume of network information has shown the characteristics of explosive growth. In this way, in order to enable users to obtain the information they are interested in more quickly and easily. When recommending information to users, the service platform usually predicts the predicted click-through rate of users clicking on the information to be recommended through the click-through rate (CTR) prediction model for each user, according to user preferences and information to be recommended, And push information to the user according to the predicted click-through rate. [0003] When training the CTR prediction model, the information recommended to the user in history (that is, the information tha...

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): G06F16/9535G06K9/62
CPCG06F16/9535G06F18/214
Inventor 贺明慧李爽王永康王兴星
Owner BEIJING SANKUAI ONLINE TECH CO LTD
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