Geo-locating Individuals via Derived Social Network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location tracking systems face challenges in accurately determining an individual's dwelling venue due to sparse and uncertain location data from mobile phones, especially in densely populated areas, where multiple venues fall within the uncertainty radius.
Innovation Solution
The system leverages a user's derived social network to infer their location by correlating GPS information with social connection data, including temporal and geographic proximity, preferences, and habits, allowing for reliable venue assignment even when exact location data is not disclosed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If mobile phones record location frequently to improve location density, then location data coverage is improved, but battery consumption increases
Solution Approach 1:
The system performs preliminary actions by collecting location data only when users check-in at venues or when location events occur, rather than continuously tracking. This preliminary data collection approach builds a sufficient location database without requiring frequent ongoing measurements, thus saving battery power while maintaining adequate location density for analysis.
2Measurement precision
If location uncertainty radius is reduced to improve accuracy, then location precision is improved, but the number of venues within the radius decreases, reducing data availability
Solution Approach 1:
The system introduces social connection data as an intermediary element to bridge the gap between location uncertainty and venue identification. By incorporating check-in data, social network relationships, and contextual information about user behaviors and preferences, the system can accurately infer venue identity even when multiple venues fall within the GPS uncertainty radius, thus maintaining data availability without requiring reduced uncertainty.
3Measurement precision
If exact location data is collected to improve location precision, then venue identification accuracy is improved, but user privacy requirements increase
Solution Approach 1:
The system extracts and utilizes only the necessary location information for venue identification purposes, rather than collecting and storing complete exact location data. By processing location events and check-in data to infer venue identity without retaining precise coordinates, the system achieves accurate venue identification while minimizing privacy loss and reducing the amount of sensitive user information that must be protected.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Techniques for determining a location of a user based on locations of other users. First user location information and second user location information is received. The first user location information includes a first centroid and first radius associated with a first user position and the second user location information includes a second centroid and second radius associated with a second user position. The second user is further associated with second user venue information. A venue correlation score between the first user and the second user is determined based on an amount of overlap between the first user radius and the second user radius and a social metric indicating a strength of a social relationship between the first user and second user. Venue information for the first user is created based on the second user venue information when the relationship score exceeds a threshold value.