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

Recommendation system based on mobile cloud location privacy protection

A recommendation system and privacy protection technology, applied in the field of social networks, can solve problems such as user interest recommendation deviation, user trouble, privacy leakage, etc., and achieve good recommendation results

Inactive Publication Date: 2016-06-01
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current research techniques meet some needs of users to a certain extent, but there are two problems in these research techniques: 1) The current geographical location and time of the user are rarely considered, which leads to the lack of interest in the user. There is a large deviation in the recommendation; 2) Even though individual studies may take into account the user's current geographic location, they do not take into account the privacy issues involved in the user's current geographic location
In the process of uploading the user's current geographic location information, it is likely to cause privacy leakage and cause unnecessary trouble to the user.

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 system based on mobile cloud location privacy protection
  • Recommendation system based on mobile cloud location privacy protection
  • Recommendation system based on mobile cloud location privacy protection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The flow of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0016] Accompanying drawing is the flowchart of this scheme. The specific implementation process is as follows:

[0017] 1. Cloud server module. This module is mainly divided into three stages: 1) According to the user's check-in historical data, the user's behavior pattern is analyzed, and the user's behavior-time probability is obtained: S G (u, l, c, t); 2) According to the user's social relationship data, analyze the user's social relationship, and get the probability of the friend's K-top interest point: S F (u, l, c, t); 3) to integrate:

[0018] S(u,l,c,t)=μ.S G (u,l,c,t)+λ.S F (u, l, c, t)

[0019] μ+λ=1

[0020] 1) User behavior pattern analysis method: According to the user's check-in data, analyze geographic correlation and geographic item correlation, the steps are as follows:

[0021] Step 1: Interest pilot estimation, using t...

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 new scheme of a recommendation system based on geographical privacy protection of a mobile cloud. The scheme is designed not to leak current geographical location information of a user, and can well combine the current geographic information and time of the user and historical sign-in data of the user, so as to perform effective interest point recommendation on the user. The scheme mainly comprises the following two parts: (1), performing preliminary interest point range recommendation by a cloud: the cloud analyzes a social pattern, a time pattern, a spatial pattern and a distribution probability of interest points of the user according to the sign-in historical data and a social relation of the user on a social tool, so as to give a preliminary recommendation list of user interest points; and (2), acquiring current geographic information and time of the user by a mobile phone, filtering and adjusting a preliminary recommendation result of the cloud, and making a more accurate recommendation.

Description

technical field [0001] The invention discloses a new scheme of a mobile cloud-based geographical privacy protection recommendation system. The technical field belongs to the field of social network. Background technique [0002] At present, the recommendation system based on geographic location is relatively mature, and most studies have made full use of the user's check-in data to obtain the user's interest, including temporal interest and spatial interest. Temporal interest representation: According to the user's check-in history data, determine what time the user likes to do. Spatial interest representation: Determine where the user prefers to stay based on the spatial location of the user. At the same time, these studies also consider the influence between social users, such as two users who are similar or close, the interest recommendation between them will be easier for the other party to accept. Some studies also take into account the influence of geographic locatio...

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): H04L29/08G06Q50/00G06F17/30
CPCG06F16/9535G06Q50/01H04L67/52
Inventor 钱红燕关海燕
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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