Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sequence recommendation method based on self-attention auto-encoder

A technology of autoencoder and recommendation method, applied in the direction of neural learning methods, instruments, complex mathematical operations, etc., can solve the problems of low accuracy and inability to consider users' long-term and short-term preferences at the same time

Pending Publication Date: 2020-05-08
纪信智达(广州)信息技术有限公司
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a sequence recommendation method based on a self-attention autoencoder in order to overcome the technical defects that the existing sequence recommendation algorithm cannot simultaneously consider the user's long-term and short-term preferences, and the accuracy of the recommendation is low.

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
  • Sequence recommendation method based on self-attention auto-encoder
  • Sequence recommendation method based on self-attention auto-encoder
  • Sequence recommendation method based on self-attention auto-encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] Such as figure 1 As shown, the sequence recommendation method based on self-attention autoencoder includes the following steps:

[0090] S1: Obtain the user product sequence and scoring matrix, and preprocess the product sequence;

[0091] S2: Use the self-attention model to train the product sequence and predict the correlation score between the user and the product;

[0092] S3: Use the autoencoder to reconstruct the scoring matrix and calculate the user preference index;

[0093] S4: Combining the correlation score between the user and the product and the user preference index, the product with a high score is recommended for the user first.

[0094] More specifically, in the step S1, the process of preprocessing the commodity sequence is as follows:

[0095] The product sequence S browsed by user u u split into input sequences (S 1 ,S 2 ,...,S |su-1| ) and the output sequence (S 2 ,S 3 ,...,S |su| ), where the input sequence is used a...

Embodiment 2

[0161] More specifically, the present invention proposes a sequence recommendation method based on a self-attention autoencoder, which uses a self-attention mechanism to model the interaction between the user's long and short preferences, and adds an autoencoder to The user's rating matrix is ​​reconstructed, and then the information of these two modules is fused, so as to realize the personalized intelligent recommendation for the user. Such as figure 2 As shown, the overall frame diagram of the algorithm of the present invention mainly includes two parts: the self-attention model and the autoencoder model.

[0162] In the specific implementation process, such as image 3 The word vector learning neural network structure of the embedding layer of the self-attention model shown above, the idea of ​​the neural network work is based on the distributed assumption, that is, two identical commodities, if their contexts are similar, then the two commodity It may also be a h...

Embodiment 3

[0211] More specifically, the three data sets of the beauty makeup (Beauty) data set and the video game (Videogame) data set in the Amazon data source, and the MovieLens1M data set in the MovieLens data source are selected to evaluate the method of the present invention. The specific information of the set is shown in Table 1:

[0212] Table 1

[0213]

[0214] Two sets of evaluation metrics were used in this experiment. For the self-encoder, the mean square error is used as the evaluation index; for the self-attention model and the entire model of the present invention, the two most common Top k evaluation indexes are selected, which are respectively hit rate (Hitrate@k) and normalized discounted cumulative gain (NDCG@k).

[0215] The parameter settings of this experiment are slightly different on the three datasets. In the selection of several important parameters, the final model parameter values ​​are selected by comparing the performance of the model on d...

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 provides a sequence recommendation method based on a self-attention auto-encoder, and the method comprises the steps: obtaining a user commodity sequence and a scoring matrix, and carrying out the preprocessing of the commodity sequence; training the commodity sequence by using a self-attention model, and predicting a relevance score of the user and the commodity; reconstructing thescoring matrix by using an auto-encoder, and calculating a user preference index; and in combination with the relevance score of the user and the commodity and the user preference index, obtaining a high-score commodity to preferentially recommend to the user. According to the sequence recommendation method based on the self-attention auto-encoder, the article browsing sequence of the user is converted into a low-dimensional dense vector by using a word embedding method; the position codes are combined and input into the self-attention model, then the self-encoder is used for fitting and reconstructing the scoring matrix, the user preference index is calculated, finally, the final prediction score is obtained, recommendation is made for the user, factors such as long-term and short-term preferences of the user are considered at the same time, and the recommendation precision is effectively improved.

Description

technical field [0001] The present invention relates to the technical field of sequence recommendation, and more specifically, to a sequence recommendation method based on a self-attention autoencoder. Background technique [0002] A recommendation system is a typical solution that actively helps users find the information they need. The general recommendation system is mainly based on the user's personal basic information, historical interaction data, and even use this part of the data of all users to combine them to model the user's interests and help users find what they may be interested in in the massive data. Information or products of interest. But in the actual user scenario, all the information of all users is a difficult data to obtain. In addition, the needs of users change dynamically, and the historical data information reflects the long-term preferences of users, while the short-term preferences of users are passed through Historical data is difficult to feed...

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
IPC IPC(8): G06Q30/06G06Q10/06G06N3/04G06N3/08G06F17/16
CPCG06Q30/0631G06Q10/06393G06N3/08G06F17/16G06N3/045
Inventor 谭军杜建伟钟鸣林鑫凌洁静
Owner 纪信智达(广州)信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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