Recommendation method and device based on context and user long and short term preference adaptive learning

An adaptive learning and recommendation method technology, applied in data processing applications, special data processing applications, instruments, etc., can solve problems such as low accuracy of prediction results and loss of accuracy, and achieve improved user satisfaction, accuracy, The effect of improving the accuracy of feature extraction

Active Publication Date: 2021-05-28
HENAN UNIVERSITY OF TECHNOLOGY
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present application is to propose a recommendation method and device based on context and user long-term and short-term preference adaptive learning, so as to solve the problem of low accuracy of prediction results caused by loss of precision when recommending items for users in the prior art

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 and device based on context and user long and short term preference adaptive learning
  • Recommendation method and device based on context and user long and short term preference adaptive learning
  • Recommendation method and device based on context and user long and short term preference adaptive learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Embodiment 1, specific reference figure 1 , figure 1 A schematic diagram of an embodiment of a recommendation method based on context and user long-term and short-term preference adaptive learning is shown in the present application, and the recommendation method based on context and user long-term and short-term preference adaptive learning includes: candidates for adaptive learning Item Feature Extraction, Target User Preference Feature Extraction and Rating Prediction for Adaptive Learning.

[0063] (1) Feature extraction of candidate items for adaptive learning

[0064] For the candidate item p, its features are obtained through the adaptive learning of the CNN network to the candidate item description of the weighted multi-type context fusion. The main process is as follows:

[0065] First, the multi-type context embedding during recommendation is used to generate weight context embedding according to the attention mechanism, and then the weight context embeddin...

Embodiment 2

[0102] Embodiment 2, specific reference Figure 4 , Figure 4 It shows a flow chart of an embodiment of adaptively extracting the features of the candidate items in the embodiment of the present application, which specifically includes the following steps:

[0103] 4-1, Obtain multi-type context embedding generation The context embedding matrix C of dimension u,p , embedding the context matrix C u,p Converts to a d-dimensional weighted context embedding c with context weights u,p ;

[0104] 4-2, the method of integrating the weight context embedding into the item description embedding matrix, so that each word embedding in the matrix implies context information, specifically embedding the weight context c u,p into the dimension of The item description embedding matrix D p In , the generated dimension is The item description embedding matrix with weighted context information of

[0105] 4-3, Embedding the item description with weight context information into the m...

Embodiment 3

[0106] Embodiment three, specific reference Figure 5 , Figure 5 It shows a flow chart of an embodiment of adaptively extracting long-term and short-term preference features of the target user in the embodiment of the present application, which specifically includes the following steps:

[0107] 5-1. Obtain the historical interactive item sequence IS of the target user u u ;

[0108] 5-2. According to the historical interaction item sequence IS of the target user u u Get the corresponding historical interaction context sequence CS u ;

[0109] 5-3, using the attention mechanism, each C u,k Converted to contextual embedding c with weight information u,k , so as to get N u A sequence of weighted context embeddings corresponding to the sequence of historical items;

[0110] 5-4, will each c u,k with the corresponding x k Perform fusion to obtain N u x k,c ;

[0111] 5-5, will N u x k,c Input into the GRU network in turn to obtain the hidden state of each step of t...

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 embodiment of the invention discloses a recommendation method and device based on context and user long and short term preference adaptive learning, and belongs to the technical field of data analysis mining, and the method comprises the steps: carrying out the adaptive learning of a weight multi-type context fusion candidate article description matrix through a CNN network, and obtaining the features of candidate articles; according to the historical interaction article sequence of the target user, combining two factors of weight multi-type context and user long-term and short-term preferences, performing adaptive learning based on a GRU network, and obtaining preference features of the target user; and performing score prediction based on the user long-term and short-term preference weights of adaptive learning, determining a score prediction result, and performing article recommendation based on the score prediction result. According to the method and device, a more excellent recommendation effect can be obtained, and the predicted user score is more accurate, so that the recommendation accuracy is improved, and the user satisfaction is improved.

Description

technical field [0001] The present application relates to the technical field of data analysis and mining, and in particular to a recommendation method and device for adaptive learning based on context and long-term and short-term preferences of users. Background technique [0002] At present, information resources are growing explosively, and there is a serious "information overload" problem, that is, it is difficult for people to obtain the required information from the massive amount of information. The recommendation technology relies on the mining and analysis of user and item-related information. The means of information needed, and become the development "engine" of e-commerce companies. [0003] At present, recommendation methods are divided into traditional recommendation methods and deep learning-based recommendation methods. Traditional recommendation methods mainly include content-based recommendation methods and collaborative filtering-based recommendation metho...

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): G06F16/9535G06F16/9536G06Q30/06
CPCG06F16/9535G06F16/9536G06Q30/0631
Inventor 赵晨阳于俊伟王俊岭李磊曹鹤玲廖天力王峰
Owner HENAN UNIVERSITY OF TECHNOLOGY
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