Convolutional Neural Network Collaborative Filtering Recommendation Method and System Fusion Attention Model
A convolutional neural network, collaborative filtering recommendation technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problems of low amount of information, sparse input data, unfavorable training model prediction scores, etc., to improve accuracy performance, speed up training, and improve prediction accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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 feature vector of the item, the convolutional neural network to obtain the feature vector of the item, and 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 pr...
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More