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

Recommendation method based on improved matrix factorization and a cross-channel convolutional neural network

A technology of convolutional neural network and matrix decomposition, which is applied in the field of recommendation based on improved matrix decomposition and cross-channel convolutional neural network, can solve the problems of insufficient model generalization ability and low recognition rate, so as to improve the overall recommendation performance and improve The effect of generalization ability

Active Publication Date: 2019-05-24
GUANGDONG UNIV OF TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) The generalization ability of the model is not enough
[0005] (2) Under the same training conditions, the convolutional neural network has a low recognition rate for text

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 method based on improved matrix factorization and a cross-channel convolutional neural network
  • Recommendation method based on improved matrix factorization and a cross-channel convolutional neural network
  • Recommendation method based on improved matrix factorization and a cross-channel convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with specific embodiment:

[0043] A recommendation method based on improved matrix decomposition and cross-channel convolutional neural network described in this embodiment, the specific steps are as follows:

[0044] Step 1: Add the impact factors of users and items on the basis of the matrix factorization recommendation model to obtain an improved matrix factorization recommendation model; the specific analysis is as follows:

[0045] The matrix decomposition recommendation model refers to decomposing the user-item rating matrix R into the product of two low-dimensional matrices P and Q:

[0046] R=P T Q (1)

[0047] Suppose there are U users, D items, and R is the scoring matrix;

[0048] Assuming there are K hidden variables, find the matrix P K×U and Q K×D ; p and q represent the row vector and column vector of matrix P and matrix Q respectively, and decompose the user's rating matrix R into m...

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 recommendation method based on improved matrix decomposition and a cross-channel convolutional neural network, and the method comprises the steps: adding influence factors ofa user and a project on the basis of a matrix decomposition recommendation model, and obtaining an improved matrix decomposition recommendation model; adding a cross-channel convolutional layer behind the convolutional layer of the convolutional neural network to obtain an improved cross-channel convolutional neural network; and finally, fusing the improved matrix decomposition model and the cross-channel convolutional neural network and recommending. The method has the advantages of being high in generalization ability, high in text recognition rate under the same training condition and thelike.

Description

technical field [0001] The invention relates to the technical field of e-commerce website and video website recommendation, in particular to a recommendation method based on improved matrix decomposition and cross-channel convolutional neural network. Background technique [0002] In e-commerce, the recommendation system is more and more widely used, and the accuracy of the recommendation model prediction results is self-evident. With the explosive growth of the number of users and items, the recommendation system faces two challenges. On the one hand, the explosive growth of the number of users and items exacerbates the sparsity of user-item rating data, which will reduce the prediction accuracy of traditional recommendation models. On the other hand, now whether it is an e-commerce website or a mainstream social software, users have more and more text evaluation data on items, and a recommendation model that can not only use user rating data for items but also identify use...

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): G06F17/27G06Q30/02G06Q10/04G06N3/04
Inventor 翁海瑞林穗
Owner GUANGDONG UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com