Privacy protection link prediction method and system based on mail data

A technology of privacy protection and prediction method, which is applied in the field of privacy protection link prediction method and system based on email data, which can solve the problems of small amount of calculation and unprotected social relations of personnel, and achieve the effect of protecting sensitive relations

Active Publication Date: 2022-05-17
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF14 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and provide a privacy protection link prediction method and system based on email data, aiming to solve the problem that the social relationship of personnel under the email system cannot be protected in the existing link prediction technology problem, the diversity of generated samples is guaranteed, and in the prediction of non-sensitive relations, privacy protection is better and the calculation amount is smaller than encryption technology

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
  • Privacy protection link prediction method and system based on mail data
  • Privacy protection link prediction method and system based on mail data
  • Privacy protection link prediction method and system based on mail data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] In this example, if figure 1 As shown, a privacy-preserving link prediction method based on email data includes: preprocessing the email data, mining the implicit relationship in the email, and constructing a character relationship knowledge graph based on the email data; using energy-based learning entity low-dimensional The embedding model encodes the entities and implicit relationships in the character relationship knowledge map, and obtains the embedding space and embedding data that have a one-to-one relationship between different entities; using the generative confrontation network, the encoded embedding data is used to train the generative model, And use the model to simulate the embedding space; use the reconstruction method of gradient descent to confuse the implicit sensitive relationship and non-sensitive relationship in the original data, and fine-tune the distribution structure of the embedding space; reasoning predictions.

[0065] In this example, if f...

Embodiment 2

[0117] In this embodiment, a privacy-preserving link prediction system based on email data is constructed using the method provided in Embodiment 1, such as Figure 4 As shown, the system includes the following modules:

[0118] Data preprocessing module: build a knowledge map based on the original mail data, and form strict mathematical definitions and goals;

[0119] Entity-relationship low-dimensional embedding module: Given a set of (h, l, t) triple training set S, including two entities h, t∈E (entity set), a relationship l∈L (relationship set) . The entity-relationship low-dimensional embedding module mainly learns the low-dimensional embedding of entities and relationships, which has a relatively good effect on downstream link prediction tasks. This patent selects the TransE model with excellent performance for the entity-relationship embedding module.

[0120] Generator training module: This module is as figure 2 .As shown in part ①, this module includes a generat...

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 privacy protection link prediction method and system based on mail data. The method comprises the following steps: constructing a character relationship knowledge graph by using the mail data; using the generative adversarial network to train a generative model for distribution of training data for learning; reconstructing the multivariate relation data so as to obfuscate sensitive and non-sensitive relation information implied in the data; the reconstructed multivariate relation data is used for complementing the relation between the entities, and the sensitive relation between the entities is protected while the non-sensitive relation between the entities is complemented. The invention further provides a privacy protection link prediction system based on the mail data, and the privacy protection link prediction method is implemented by the privacy protection link prediction system. According to the method, the relationship between the entities is complemented by using the reconstructed multivariate relationship data, so that the purpose of protecting the sensitive relationship between the entities while the non-sensitive relationship between the entities is complemented is achieved, and the technical problem that the social relationship of personnel in a mail system cannot be protected in the existing link prediction technology is solved.

Description

technical field [0001] The present invention relates to the technical fields of adversarial learning, graph network representation learning, knowledge graph and link prediction, and in particular to a method and system for privacy-protected link prediction based on email data. Background technique [0002] As one of the applications of the Internet, email is one of the important ways of information exchange in modern society. Email data records the content of people's communication, including important information such as communication relationship, communication time, and communication frequency. Through simple entity relationship extraction and data mining, multiple knowledge graphs can be established for one email data. For example, take the campus student mail system as an example: from the perspective of communication relationship, a communication relationship graph can be established for it, and from the perspective of online device login, an online login behavior gra...

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): H04L9/40H04L51/42G06N3/08
CPCH04L63/0407G06N3/08
Inventor 王勇王范川王晓虎秦瑞张应福石锟
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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