Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Convolution neural network collaborative filtering recommendation method and system based on attention model

A convolutional neural network and collaborative filtering recommendation technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as sparse input data, unfavorable training model prediction scores, and less information, to improve accuracy performance, improving prediction accuracy, and speeding up training

Active Publication Date: 2019-02-01
NORTHEAST NORMAL UNIVERSITY
View PDF6 Cites 65 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, if only one-hot vectors representing users and items are used for training, the input data will become sparse and contain too little information, which is not conducive to the training model to predict ratings more accurately

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
  • Convolution neural network collaborative filtering recommendation method and system based on attention model
  • Convolution neural network collaborative filtering recommendation method and system based on attention model
  • Convolution neural network collaborative filtering recommendation method and system based on attention model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, this application provides a convolutional neural network collaborative filtering recommendation method that integrates the attention model, including:

[0058] Step S1: splicing and merging the user feature vector and the item feature vector into a new vector;

[0059] Step S2: Send the new vector as the input vector into the multi-layer perceptron for learning, and predict the score;

[0060] Among them, the attention model is fused into the latent vector of the item, the convolutional neural network to obtain the feature vector of the item, or the hidden layer of the multi-layer perceptron.

[0061] Such as figure 2 As shown, the methods for obtaining feature vectors of items include:

[0062] Step a1: Select the Glove method to pre-train the original data of the item, which can express the words in the text in the form of vectors with a fixed size, forming a word vector matrix D∈R a*I , the Glove method is a known algorithm in the prio...

Embodiment 2

[0109] Such as image 3 As shown, the application also provides a convolutional neural network collaborative filtering recommendation system that integrates attention models, including: user feature vector 1, item feature vector 2 and attention convolution collaborative filtering model, attention convolution collaborative filtering model Includes: Attention Models3, Convolutional Neural Networks, and Multilayer Perceptrons4. The multi-layer perceptron 4 is used to calculate the new vector after splicing and fusion of the user feature vector and the item feature vector, and predict the score.

[0110] As described in Embodiment 1, the attention model 3 can be respectively fused with the latent vector of the item, the convolutional neural network 5 for obtaining the feature vector 2 of the item, and the hidden layer of the multilayer perceptron 4 , which will not be repeated here.

[0111] For a rating matrix, collaborative filtering uses the data of connections between users o...

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 collaborative filtering recommendation method and a collaborative filtering recommendation system of a convolution neural network integrating an attention model, which relates to the technical field of data mining recommendation, improves feature extraction efficiency and scoring prediction accuracy, reduces operation and maintenance cost, simplifies cost management mode,and is convenient for joint operation and large-scale promotion and application. The invention relates to a collaborative filtering recommendation method of a convolution neural network integrating an attention model, comprising the following steps: step S1, splicing a user feature vector and an item feature vector into a new vector; S2, sending the new vector as an input vector into the multi-layer perceptron to learn and predict the score; The attention model is fused into the object potential vector to obtain the convolution neural network of the object feature vector or the hidden layer of the multi-layer perceptron.

Description

technical field [0001] The present application relates to the technical field of data mining recommendation, in particular to a convolutional neural network collaborative filtering recommendation method and system fused with an attention model. Background technique [0002] Existing deep learning is an important means of dealing with the field of big data. It mimics human brain neurons for abstract modeling. In the recommendation system, the user and item information in the data are used as the input vector of the neural network to do the prediction task. To improve prediction accuracy, the model needs to perform feature extraction efficiently. High-dimensional feature vectors are obtained from sparse input data for training. However, it is not advisable to improve the efficiency of feature extraction and improve the prediction accuracy of the model by increasing the number of layers of the neural network alone. Doing so will increase the complexity of the model, and it ...

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): G06F16/9535G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 张邦佐张昊博孙小新冯国忠
Owner NORTHEAST NORMAL UNIVERSITY
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com