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

Recommendation method based on privacy protection

A recommendation method and privacy protection technology, applied in the direction of digital data protection, data processing applications, sales/lease transactions, etc., can solve problems such as no solution, and achieve the effect of reducing computing costs and protecting privacy

Active Publication Date: 2022-03-25
EAST CHINA NORMAL UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The privacy-protected product recommendation method needs to balance the personalized service requirements and privacy guarantees, which is a challenging problem, and there is currently no effective solution in the industry

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 based on privacy protection
  • Recommendation method based on privacy protection
  • Recommendation method based on privacy protection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] figure 1 This is a flow chart of the specific implementation of the privacy protection-based recommendation method of the present invention. like figure 1 As shown, the specific steps of the privacy protection-based recommendation method of the present invention include:

[0041] S101: Set up a semi-trusted third-party organization:

[0042] A semi-trusted third party is set up between the user and the e-commerce platform server. Semi-trusted third-party organizations have the following two characteristics:

[0043] 1) Honest: The institution will complete its own tasks in accordance with the agreed agreement, and will not tamper with the information sent by users;

[0044] 2) Curious: The agency will use the received information to find ways to make profits for itself; for example: use the intermediate calculation results sent by users to find ways to mine users' preferences and resell to other platforms.

[0045] In the field of e-commerce, semi-trusted third-par...

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 method based on privacy protection. A semi-trusted third-party organization is set in the user and the e-commerce platform server. The e-commerce platform server discloses the feature vectors of all commodities, and the user obtains the commodity feature vectors from the server. Its own purchase data learns its user feature vector locally, and calculates the update gradient of the product feature vector based on it, and uses the global noise vector and temporary noise for disturbance and sends it to a semi-trusted third-party organization, and a semi-trusted third-party organization Aggregate the disturbed update gradients and send them to the server. The server removes the disturbance from the received update gradients, and then updates the product feature vector. The user then calculates the predicted interaction vector based on the updated product feature vector, and thus obtains product recommendations. result. Adoption of the present invention can effectively realize the protection of user privacy in the commodity recommendation process.

Description

technical field [0001] The invention belongs to the technical field of commodity recommendation, and more particularly, relates to a recommendation method based on privacy protection. Background technique [0002] With the popularization of computing devices, applications closely related to daily life have been implemented, and many organizations and institutions have collected and stored a large number of users' digital information. For example, navigation systems collect information on the geographic location of vehicles, and e-commerce sites collect customers' shopping habits. With the help of recommendation algorithms such as matrix factorization, this data can provide opportunities for data collectors to improve the quality of service and bring social and economic benefits. For example, by analyzing real-time road conditions, the navigation system can help drivers avoid congestion; by analyzing customers' historical orders, it can help merchants place advertisements ac...

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 Patents(China)
IPC IPC(8): G06Q30/06G06F21/64G06F21/62
CPCG06Q30/0631G06Q30/0601G06F21/64G06F21/6245
Inventor 刘文炎王晓玲
Owner EAST CHINA NORMAL UNIV
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