Recommendation system recall method based on attention mechanism

A recommender system and attention-based technology, which can be applied to instruments, sales/lease transactions, electronic digital data processing, etc., and can solve the problem of few recommended system models

Active Publication Date: 2020-04-24
SUN YAT SEN UNIV
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are few studies on applying the attention mechanism to the recommendation system model.

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 system recall method based on attention mechanism
  • Recommendation system recall method based on attention mechanism
  • Recommendation system recall method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

example

[0102] Our data is collected from data similar to the click-through rate estimation CTR model. The characteristics of each sample can be divided into two parts, one part is user characteristics, such as gender, age, etc., and the other part is product characteristics, such as type, price, etc. Each sample corresponds to a label, and the value of the label is 1 or 0, which represents whether the user has purchased (in actual situations, whether it has been clicked or whether it has been favorited can also be used as a label). That is, each sample represents a user's purchase behavior for a product. Then the problem we need to solve is the binary classification problem. We need to train a binary classification model through these samples. The output of the model is to judge whether the user has purchased the product. The model will output a probability value from 0 to 1. The probability The value represents the possibility of the user's purchase of the product, and the larger th...

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 system recall method based on an attention mechanism, and the method comprises the following steps: extracting user features and commodity features in a training sample, converting the user features into a user embedding vector, and converting the commodity features into a commodity embedding vector; inputting the user embedding vector and the commodity embedding vector into an attention mechanism model for training, learning the weight of each feature through an attention network in the model, and performing weighted summation on the embedding vectorsof all the features according to the weights to obtain a user representation vector and a commodity representation vector; calculating an inner product of the user representation vector and the commodity representation vector to obtain a user commodity purchase intention matching degree of the training sample, establishing a cross entropy loss function of the user commodity purchase intention matching degree, calculating a minimized cross entropy loss function, and converging an attention mechanism model; and inputting the to-be-tested sample into the converged attention mechanism model, obtaining a user commodity purchase intention matching degree of the to-be-tested sample, and selecting a commodity of which the user commodity purchase intention matching degree is in a preset interval asa recall result for recommendation. According to the invention, the generalization is enhanced, and the calculation amount of recall recommendation is greatly simplified.

Description

technical field [0001] The invention relates to the field of computer recommendation systems, in particular to a method for recalling a recommendation system based on an attention mechanism. Background technique [0002] With the improvement of living standards, we have more and more choices for consumption. From shopping around to now, it takes a lot of time to find the goods we need, and even if we find what we want , may not be the most suitable for us. The recommendation system can help us find the relevant products we search for from the product pile, and recommend the products that are most suitable for us to us. Recommender systems are widely used today and are ubiquitous in life. When shopping online, we hope that the platform will recommend the products we just want to buy. When listening to music, we hope to hear songs that suit our taste. When searching for things, we hope that the search results will be what we are looking for. Therefore, fast and accurate pre...

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): G06Q30/06G06F16/9535
CPCG06Q30/0631G06F16/9535
Inventor 郑子彬李威琪周晓聪
Owner SUN YAT SEN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap