Individuation difference privacy recommendation method based on local clustering

A differential privacy and recommendation method technology, applied in computer components, instruments, calculations, etc., can solve the problems of not considering the localization characteristics of the CF algorithm and not being able to cope with data updates, and achieve strong privacy protection, leakage protection, and computational efficiency high effect

Active Publication Date: 2018-07-06
WUHAN UNIV
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is worth mentioning that these methods are either too simple to deal with data updates; or simply consider that the privacy preferences of all users are consistent; or do not consider the localization characteristics of the CF algorithm

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
  • Individuation difference privacy recommendation method based on local clustering
  • Individuation difference privacy recommendation method based on local clustering
  • Individuation difference privacy recommendation method based on local clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The prior art related to the present invention and the technical solution of the present invention will be further described in detail below.

[0027] 1. System model and privacy protection goals

[0028] 1. System model

[0029] Note that the recommendation system in the present invention is here For the set of all users, A collection of all items. make and represent the number of users and items, respectively. In addition, the recommendation system G also saves user rating data and item attribute data. The information of user u is denoted as S u, represents user u’s ratings for all items, and we denote S u (i)=r(u,i), where r(u,i) represents user u's rating on item i. The attribute data of the item is recorded as v i , which contains relevant characteristics of the item, for example, whether a sport is a ball game or not.

[0030] Given a target user u', our goal is to recommend k items that u' may like based on similar users of user u'. To character...

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 relates to an individuation difference privacy recommendation method based on local clustering. The method comprises the steps that for the situation that the privacy requirements of different users for different goods are different, firstly, a user file data set is sampled, then a noise-containing KNN of a target user is selected by using the sampled data set, goods are clustered based on the local similarity, user data is modified by using a clustered result, and finally a recommendation result is calculated by using the modified user data. The individuation difference privacyrecommendation method has high availability, and the privacy requirement of any user can be precisely met.

Description

technical field [0001] The invention belongs to the technical field of recommendation with a privacy protection function, and in particular relates to a personalized differential privacy collaborative filtering recommendation method. Background technique [0002] Benefiting from the development of electronic equipment manufacturing technology, human society generates a large amount of data every day. According to a survey report by IBM, in 2002, the total amount of online data was about 5 EB (exabyte). In 2009, the total amount of data increased to 281EB, a 56-fold increase in 7 years. In addition, according to Forrester Research Inc.'s research, the total amount of data stored by enterprises doubles every three years. Obviously, it is impossible to browse all these data by manpower alone and obtain effective information. The recommendation algorithm is proposed under such circumstances, which allows people to quickly find the information they need from massive amounts of...

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): G06F17/30G06K9/62
CPCG06F16/9535G06F18/23G06F18/24147
Inventor 刘树波李永凯蔡朝晖王俊
Owner WUHAN UNIV
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