TopN collaborative filtering recommendation method based on differential privacy

A collaborative filtering recommendation and differential privacy technology, applied in special data processing applications, instruments, electrical digital data processing, etc., to achieve the effect of protecting the original scoring data

Inactive Publication Date: 2017-12-19
XUZHOU MEDICAL UNIV
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing literature on differential privacy protection has not addressed the privacy protection of TopN recommender systems

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
  • TopN collaborative filtering recommendation method based on differential privacy
  • TopN collaborative filtering recommendation method based on differential privacy
  • TopN collaborative filtering recommendation method based on differential privacy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Such as figure 1 As shown, a TopN collaborative filtering recommendation method based on differential privacy, the following is the concept of ε-differential privacy and the related concepts of noise addition mechanism used in this method.

[0029] Definition 1ε-differential privacy definition: Given two data sets D and D' differ by at most one record, Range(A) is the value range of any random data mining algorithm A, Pr[E s ] for event E s The risk of privacy being disclosed, if any output result O(O∈Range(A)) of algorithm A on data sets D and D' satisfies the following inequality, then A satisfies ε-differential privacy:

[0030] Pr[A(D)∈O]≤e ε ×Pr[A(D')∈O]

[0031] Among them, ε represents the privacy cost parameter, and the smaller ε is, the higher the degree of privacy protection is. It can be seen from Definition 1 that if a data processing algorithm satisfies the definition of ε-differential privacy, the algorithm can effectively protect user privacy.

[003...

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 TopN collaborative filtering recommendation method based on differential privacy and relates to the technical fields of differential privacy technologies and collaborative recommendation. According to the method, Laplace noise is reasonably added to original input data Rm*n firstly to obtain user grading records (shown in the description) after disturbance, and then cosine similarity is utilized to calculate the similarity between a target user and other users. On one hand, the records meet an epsilon-differential privacy protection model by adding the Laplace noise to original user grading records, it is ensured that the records have higher availability while the privacy security of issued data sets is guaranteed, and original grading data of users is effectively protected; on the other hand, improvement starts from a recommendation algorithm itself, the problem that an existing TopN recommendation model leaks the privacy of the users is solved, attackers are prevented from speculating their browsing histories according to a recommendation list of the target user so as to obtain personal preferences of the users, and accurate recommendation can be provided for the users while the privacy of the users is protected.

Description

technical field [0001] The invention relates to the field of differential privacy protection technology and collaborative recommendation technology, in particular to a TopN collaborative filtering recommendation method based on differential privacy. Background technique [0002] The recommendation algorithm is a method of discovering knowledge from the user's historical data and using this knowledge to predict the user's preference for related objects. The application direction of the recommendation algorithm mainly includes: predicting the rating of the user on the item and using TopN to recommend a personalized recommendation list to the user. Among them, TopN recommendation is a practical recommendation model generally recognized by scholars at home and abroad. Among many recommendation algorithms, collaborative filtering algorithm is the most commonly used recommendation algorithm, and the TopN recommendation system based on collaborative filtering algorithm is often us...

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): G06F17/30G06Q50/00
CPCG06F16/9535G06Q50/01
Inventor 胡俊峰吴响毛亚青王换换
Owner XUZHOU MEDICAL 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