Recommendation model training method and device, medium and computing equipment

A model training and model technology, applied in the computer field, can solve the problems of insufficient satisfaction of users with pushed content, achieve the effects of reducing the Matthew effect, improving coverage, and reducing the leading role

Pending Publication Date: 2022-05-13
NETEASE MEDIA TECH BEIJING
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The disclosure provides a recommendation model training method, medium, device and computing equipment to solve the problem that the content recommended by the content recommendation system in the prior art is too biased towards popular content, resulting in insufficient user satisfaction with the pushed content

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
  • Recommendation model training method and device, medium and computing equipment
  • Recommendation model training method and device, medium and computing equipment
  • Recommendation model training method and device, medium and computing equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only for those skilled in the art to better understand and implement the present disclosure, but not to limit the scope of the present disclosure in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0047] As will be appreciated by those skilled in the art, embodiments of the present disclosure may be implemented as a system, apparatus, device, method or computer program product. Accordingly, the present disclosure may be embodied in entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0048] According to the embodiments of the present disclosure, a recommendation model tra...

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 embodiment of the invention provides a recommendation model training method and device, a medium and computing equipment. The method comprises the steps of generating a training sample based on a push record of push content and an interactive operation record of a user on the push content, the training sample comprising popularity corresponding to the push content and a label value indicating whether the user has an interactive operation on each push content; the training samples are input into a recommendation model for training, the user feature parameters and the content feature parameters are output, and the recommendation model is a matrix decomposition model. The popularity is brought into a training target, so that popular and non-popular factors in the obtained user feature parameters and content feature parameters are decoupled, the leading effect of popular contents on a recommendation model when determining to-be-pushed contents is reduced, the Mortai effect that the pushed contents are biased to popular is reduced, and the pushing quality of the to-be-pushed contents is improved. The coverage degree of interest preference fields except user popularity is improved, and better experience is brought to the user.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and more particularly, the embodiments of the present disclosure relate to a recommendation model training method, medium, apparatus, and computing device. Background technique [0002] This section is intended to provide a background or context for the embodiments of the present disclosure that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] With the development of Internet technology, the content recommendation function is used in more and more applications. By pushing corresponding content according to the characteristics of user traffic, the user experience can be improved. [0004] Current recommender systems prefer to recommend popular content to users. And for these popular content, because it has more exposure opportunities, it will be more popular. For content that has not been push...

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): G06F16/9535G06F16/955G06K9/62G06Q30/06
CPCG06F16/9535G06F16/955G06Q30/0631G06F18/214
Inventor 张华沈童
Owner NETEASE MEDIA TECH BEIJING
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