Data processing method and device for realizing privacy protection

A privacy protection and data processing technology, applied in the field of data security, can solve problems such as leaking user identities, and achieve the effects of preventing leaks, high availability, and ensuring user privacy and security

Active Publication Date: 2020-08-11
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the abundance of raw sensor data

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
  • Data processing method and device for realizing privacy protection
  • Data processing method and device for realizing privacy protection
  • Data processing method and device for realizing privacy protection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The following describes the solutions provided in this specification with reference to the drawings.

[0021] The embodiment of this specification discloses a data processing method for realizing privacy protection, which can realize the protection of user identity privacy by performing anonymization processing on the original sensor data. Specifically, with the rise of machine learning, the inventor thought that machine learning technology can be applied to the technical field of data privacy and security, by training a machine learning model for anonymizing raw sensor data (hereinafter referred to as data anonymity model). ) To protect user privacy.

[0022] figure 1 Shows an implementation architecture diagram of a data processing method according to an embodiment, such as figure 1 As shown, first input the acquired sensor data to be processed into the data anonymity model to obtain anonymous data; then, on the one hand, input the anonymous data into the pre-trained user ...

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 a data processing method for realizing privacy protection, and the method comprises the steps: obtaining to-be-processed sensor data, a corresponding identitytype label and a service label, wherein the service label corresponds to a service prediction task for a user; then, inputting the sensor data into a data anonymity model to obtain anonymity data; furthermore, on one hand, inputting the anonymous data into a pre-trained user identity recognition model to obtain an identity prediction result, wherein the identity prediction result is used for determining identity prediction loss in combination with an identity category label; on the other hand, inputting the anonymous data into a pre-trained service prediction model to obtain a service prediction result, wherein the service prediction result is used for determining service prediction loss in combination with the service label; then, training the data anonymity model by utilizing the comprehensive loss; wherein the comprehensive loss is negatively correlated with the identity prediction loss and positively correlated with the service prediction loss; wherein the trained data anonymity model is used for carrying out anonymity processing on the target sensor data.

Description

Technical field [0001] One or more embodiments of this specification relate to the field of data security technology, and in particular to a data processing method and device for realizing privacy protection. Background technique [0002] At present, there are many sensors embedded in personal smart devices, including accelerometers, gyroscopes, and magnetometers. The application APP installed on smart devices can access the raw data collected by these sensors and process the raw sensor data. Realize the interaction with the user, or calculate the indicator data displayed to the user to help the user understand their own activity or physical state. [0003] However, the rich raw sensor data also brings the risk of leaking user identities. Therefore, there is a need for a solution that can prevent the leakage of user identity information while the number of sensors can be normally used for subsequent business processing, thereby effectively protecting user privacy. Summary of the ...

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): G06F21/62G06N3/04G06N3/08G06N20/00
CPCG06F21/6245G06N3/084G06N20/00G06N3/045
Inventor 李龙飞周俊
Owner ALIPAY (HANGZHOU) INFORMATION 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