Continuous Location Tracking via Periodic Sensor Sampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack effective methods for continuously tracking and analyzing the location and behavioral patterns of mobile device users, particularly in inferring user activities from device sensor data while ensuring privacy and managing large data volumes.
Innovation Solution
Equipping mobile devices with location and acceleration sensors to continuously collect and upload data, which is then processed by a server to extract statistical information on user behaviors, including location tracking, speed inference, and aggregation for individual and group patterns, with options for user control and data management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If location and acceleration sensors continuously track user movements, then behavioral pattern analysis accuracy is improved, but energy consumption increases
Solution Approach 1:
The system implements periodic sampling of location and acceleration data at configurable intervals (e.g., every 5 seconds or 100 meters), rather than continuous monitoring. This periodic action maintains sufficient behavioral pattern analysis accuracy while significantly reducing energy consumption and processing requirements.
Solution Approach 2:
The system selectively processes only the most relevant sensor data points needed for behavioral pattern recognition, rather than analyzing all collected data. This partial action approach maintains analysis accuracy for key behaviors while reducing overall computational energy consumption.
2Loss of information
If detailed location data is continuously collected, then user behavior analysis is improved, but privacy concerns increase
Solution Approach 1:
The system extracts and retains only the essential behavioral patterns and statistical summaries from detailed location data, removing personally identifiable information and specific location details. This extraction process preserves useful behavioral analysis while eliminating privacy-sensitive information.
Solution Approach 2:
The system transforms precise location coordinates into generalized behavioral parameters such as movement patterns, activity types, and temporal statistics. This parameter transformation maintains analytical value while reducing the granularity of personal information to acceptable privacy levels.
3Measurement precision
If large volumes of location data are stored and processed, then statistical accuracy is improved, but data management complexity increases
Solution Approach 1:
The system performs preliminary processing and aggregation of location data into statistical summaries and behavioral patterns during data collection, rather than processing all raw data later. This preliminary action reduces the volume of data requiring complex management while maintaining statistical accuracy.
Solution Approach 2:
The system segments data management into distinct modules: data collection, filtering, aggregation, statistical analysis, and storage. This segmentation reduces overall complexity by allowing each module to handle specific tasks independently with optimized data structures and processing methods.
Data Source
AI summary
In one embodiment, one or more computing devices receive, from one or more mobile devices respectively associated with one or more users, one or more sets of data, wherein each set of data comprises: a user identifier indicating to which user the set of data corresponds; a location where the corresponding user was at; and a time when the corresponding user was at the location. The computing devices store the one or more sets of data; and extract one or more statistics from the one or more sets of data that represent behavioral pattern of at least one of the one or more users.