Mobile Location Anomaly Detection via Non-Location Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location-based services for mobile devices have limitations, including privacy concerns, power consumption issues, and GPS signal unavailability, which hinder effective tracking of a mobile device's location.
Innovation Solution
A system and method that utilize non-location information, such as serving cell identifiers, signal strengths, and sensor data, to create probabilistic models, allowing for the detection of location anomalies by comparing current device data with historical patterns, without relying on GPS data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If location-based services (GPS) are used to track mobile device location, then location accuracy is improved, but power consumption increases and privacy concerns arise
Solution Approach 1:
The patent replaces GPS satellite-based positioning (mechanical/electromagnetic system) with a cellular network-based location inference system. Instead of using GPS hardware and satellite signals, the system uses cellular tower triangulation and non-location data (app usage, sensor data) to probabilistically determine device location, thereby reducing power consumption while maintaining location tracking capability
Solution Approach 2:
The patent introduces an intermediary probabilistic model that indirectly infers location from non-location data. Rather than directly measuring GPS coordinates, the system uses intermediate indicators (cell tower signals, app context, sensor readings) to probabilistically deduce location, reducing the need for continuous GPS activation and lowering power consumption
2Reliability
If GPS location services are continuously activated for tracking, then location monitoring reliability is improved, but device battery life deteriorates
Solution Approach 1:
The patent implements periodic location updates through cellular network data collection rather than continuous GPS activation. The system periodically gathers non-location data (cell tower information, app usage patterns, sensor data) and updates location estimates at intervals, maintaining monitoring reliability while significantly extending battery life compared to continuous GPS tracking
Solution Approach 2:
The patent makes the cellular network infrastructure serve multiple functions: it provides both communication services and location tracking capabilities. By utilizing existing cellular data connections for dual purposes, the system eliminates the need for dedicated GPS hardware operation, thereby extending battery life while maintaining location monitoring reliability through the same network infrastructure
3Loss of information
If GPS location tracking is implemented, then location awareness is improved, but user privacy is compromised
Solution Approach 1:
The patent extracts location tracking functionality from direct GPS coordinate collection and relocates it to an indirect inference system. By separating location awareness from direct GPS data collection and using non-location data (app usage, sensor information, cell tower data) as proxies, the system maintains location awareness while reducing privacy intrusion by not directly exposing precise GPS coordinates
Solution Approach 2:
The patent inverts the traditional location tracking approach: instead of directly obtaining location data and inferring user context, the system starts with non-location data (app usage patterns, sensor readings, cellular information) and inverts the inference process to probabilistically determine location. This reversal reduces privacy concerns by making location a derived rather than primary data point
Data Source
AI summary
A location anomaly for a mobile device can be detected using non-location information from the mobile device. The non-location information does not include data from a location based device, such as a GPS. A probabilistic model is created using historical non-location information accumulated from the mobile device. Current non-location data is compared with the probabilistic model to determine a probability associated with the current non-location information. If the probability is less than a predetermined or configurable threshold, a location anomaly is detected. A notification of the location anomaly may be displayed and/or transmitted in response to detecting the location anomaly.


