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

Method for training recommendation probability prediction model, recommendation probability prediction method and device

A probabilistic prediction and model technology, applied in the field of artificial intelligence, can solve the problems of differences in the output results of multiple neural networks, the influence of the prediction accuracy of the information to be predicted, and the convergence of the output results of multiple neural networks, so as to improve the prediction accuracy and improve the The effect of predicting performance

Active Publication Date: 2021-11-02
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current multi-task learning model usually has the problem of the convergence of the output results of multiple neural networks, that is, the output results of multiple neural networks are very small, so that the prediction performance of the multi-task learning model after training is not high, which will treat The forecast accuracy of the forecast information is affected

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 for training recommendation probability prediction model, recommendation probability prediction method and device
  • Method for training recommendation probability prediction model, recommendation probability prediction method and device
  • Method for training recommendation probability prediction model, recommendation probability prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] In order to make the purpose, technical solution and advantages of the application clearer, the application will be further described in detail below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0081] In order to facilitate those skilled in the art to better understand the technical solutions of the present application, terms involved in the present application are introduced below.

[0082] Multi-task learning model: A model learns multiple tasks at the same time. For example, in the video recommendation scenario: a recommendation model not only learns the click probability prediction task, but also learns the playback duration prediction task, and learns the...

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

This application provides a method for training a recommendation probability prediction model, a recommendation probability prediction method and a device, which relate to the field of artificial intelligence technology. The sample data is input into the recommendation probability prediction model to obtain the predicted recommendation results corresponding to the sample data; the corresponding basic loss value is obtained according to the predicted recommendation results corresponding to the sample data and the actual recommendation results; based on the basic loss value and the first adjustment value, the corresponding The target loss value of ; wherein, the first adjustment value is used to represent the total difference degree of the output results of each two task networks obtained based on the corresponding sample data, and the first adjustment value is negatively correlated with the target loss value; according to the target The loss value is to adjust the parameters of the recommendation probability prediction model to improve the prediction performance of the trained recommendation probability prediction model, thereby improving the prediction accuracy of the prediction information to be predicted.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a method for training a recommendation probability prediction model, a recommendation probability prediction method and a device. Background technique [0002] With the continuous development of Internet technology, various network information emerges in an endless stream, such as articles, videos, pictures, products, advertisements, etc., making information recommendation systems widely used. In practical applications, when recommending articles, videos, pictures and other information to the target object through the information recommendation system, the purpose is to achieve the following recommendation effect: the target object clicks on the recommended information, then reads the entire content of the recommended information, and likes it , forwarding, commenting and other interactions. [0003] In related technologies, in order to achieve 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9535G06F16/735G06N3/08G06N3/04
CPCG06F16/9535G06F16/735G06N3/08G06N3/045
Inventor 伍海洋
Owner TENCENT TECH (SHENZHEN) CO LTD
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