Item recommendation method for protecting user privacy, device and learning system

A user privacy and learning system technology, applied in the field of equipment and learning systems, project recommendation methods to protect user privacy, and can solve problems such as data islands and data security

Active Publication Date: 2021-12-21
ALIBABA DAMO (HANGZHOU) TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current recommendation model will face the problems of data islands and data security during the training process

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
  • Item recommendation method for protecting user privacy, device and learning system
  • Item recommendation method for protecting user privacy, device and learning system
  • Item recommendation method for protecting user privacy, device and learning system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0037] In addition, the sequence of steps in the following method embodiments is only an example, rather than a strict limitation.

[0038] The Matrix Factorization (MF) problem is a basic problem in the recommendation system. As the name implies, matrix factorization is to decompose a matrix into two or more matrices, so that the decomposed matri...

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 provides an item recommendation method for protecting user privacy, a device and a learning system, and the method comprises the steps: any data device obtains a score matrix collected locally, wherein the score matrix is used for describing the scoring conditions by a plurality of users for a plurality of projects, and the score matrices collected by respective data devices have the same user set and have different item sets; locally training item expression matrices and a user expression matrices corresponding to the scoring matrices, and sending a locally trained first user expression matrix to a server, so that the server aggregates the user expression matrices uploaded by the plurality of data devices and sends a second user expression matrix obtained by aggregation to the plurality of data devices; and if the training stop condition is met, predicting the preference degrees of a plurality of users to the plurality of items according to the locally trained item expression matrices and the second user expression matrix, so as to perform item recommendation for the plurality of users according to the preference degrees.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an item recommendation method, device and learning system for protecting user privacy. Background technique [0002] With the continuous development of technologies such as the Internet of Things and mobile Internet, the Internet is full of various information, which poses challenges for users to search for effective information. For example, taking the e-commerce scenario as an example, it takes a lot of time for users to search for products that meet their expectations among a large number of products. Based on this, various recommendation models are designed to implement targeted recommendations for users. [0003] The current recommendation model will face the problems of data islands and data security during the training process. The industry continues to face important technical issues, that is, it must first protect users' private data from being misused ...

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): G06F16/9535G06K9/62G06Q30/06
CPCG06F16/9535G06Q30/0631G06F18/214G06N20/00
Inventor 周靖人丁博麟李子韬
Owner ALIBABA DAMO (HANGZHOU) TECH CO LTD
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