Unlock instant, AI-driven research and patent intelligence for your innovation.

User preference recommendation method and device based on neural network set operation

A set operation and neural network technology, applied in the field of user preference recommendation based on neural network set operation, can solve problems such as model performance impact, and achieve the effect of improving accuracy and ensuring accuracy

Active Publication Date: 2022-06-17
ZHEJIANG UNIV BINJIANG RES INST
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This practice will limit the amount of information represented by user preferences, causing the performance of such models to suffer

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
  • User preference recommendation method and device based on neural network set operation
  • User preference recommendation method and device based on neural network set operation
  • User preference recommendation method and device based on neural network set operation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and do not limit the protection scope of the present invention.

[0023] Based on the problems existing in the background technology, the embodiments provide a method and device for recommending user preference based on collective operation of neural networks. The method and device make full use of negative feedback interaction item information corresponding to negative preferences. The corresponding vectors of the positive feedback interaction items and the negative feedback interaction items of the The concatenation of the representation, the negative feedback preference representation and the user's global preference representa...

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 user preference recommendation method and device based on neural network set operation, and the method comprises the steps: obtaining a positive feedback interaction sequence, a negative feedback interaction sequence and user global preference information; meanwhile, a positive feedback interaction vector sequence and a negative feedback interaction vector sequence corresponding to the positive feedback interaction sequence and the negative feedback interaction sequence are combined, and positive feedback preference representation and negative feedback preference representation are obtained by adopting set operation; performing mapping calculation on the positive feedback preference representation, the negative feedback preference representation and a user global preference vector corresponding to the user global preference information by using a multilayer perceptron to obtain a user comprehensive preference representation, and finally evaluating a recommendation score by calculating the similarity between the user comprehensive preference representation and a vector corresponding to a candidate interaction item. And user preference recommendation is realized according to the recommendation score, so that the accuracy of user preference recommendation can be improved.

Description

technical field [0001] The present invention relates to the technical field of cross-combination of neural network and recommendation, in particular to a method and device for recommending user preference based on the collective operation of neural network. Background technique [0002] Recommender systems (RSs) are widely used in online services and shopping platforms and have contributed significantly to the success of businesses today. RSs can learn the user's preference representation through the user's historical feedback information, and recommend personalized items to the user. In real-world RSs, since items are mostly not clicked, the amount of implicit feedback is far greater than explicit feedback, so it is crucial for recommender systems to learn user preference representations from implicit feedback. In implicit feedback, some user-observed items are considered positive feedback because they indicate the user's preference for those items, while unobserved items ...

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): G06F16/9535G06F16/958G06K9/62G06N3/04G06N3/08G06Q30/06
CPCG06F16/9535G06F16/958G06Q30/0631G06N3/04G06N3/084G06F18/22G06N3/0499G06N7/01G06N3/08
Inventor 韩蒙李明杜文涛林昶廷俞伟平
Owner ZHEJIANG UNIV BINJIANG RES INST