User Motion Profiling via Cell Handover and GPS Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current positioning systems for mobile users face challenges in actively monitoring locations without invading user privacy, as GPS data is typically only available on the device and constant active positioning drains battery life, making it costly and detrimental to user experience.
Innovation Solution
An apparatus and method that utilizes cell handover data to profile user motion by distributing location data into buckets, calculating sub-distances between users, aggregating these distances, and employing agglomerative hierarchical clustering to identify clusters of users with similar commuting patterns and stationary areas, without requiring client-side applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS is used to actively monitor user location, then positioning accuracy is improved, but battery consumption increases and user privacy is compromised
Solution Approach 1:
The patent extracts positioning information from GPS data that is already being collected by the mobile device for other purposes. Instead of requiring continuous active GPS monitoring for positioning purposes, the system utilizes existing GPS traces that are captured incidentally during normal device operation, thereby achieving accurate positioning without additional battery consumption.
Solution Approach 2:
The system creates a copy of the user's movement trajectory from stored GPS data points. By processing these copied position records to generate simplified movement patterns and profiles, the system achieves continuous positioning capability without requiring the device to actively maintain GPS reception, thus conserving battery power while preserving positioning accuracy.
2Measurement precision
If GPS is used to actively monitor user location, then positioning accuracy is improved, but user privacy is compromised
Solution Approach 1:
The system extracts only the essential movement pattern information from complete GPS data sets. By identifying and retaining only the critical trajectory points that define user movement patterns while discarding redundant detailed location information, the system maintains positioning accuracy for movement analysis while minimizing privacy intrusion.
Solution Approach 2:
The patent applies different levels of data retention to different aspects of location information. Detailed GPS coordinates are retained only where necessary to define movement patterns, while other location details are aggregated or generalized. This selective preservation of information quality ensures positioning accuracy where needed while protecting privacy in other contexts.
3Object-affected harmful factors
If cell handover data is used for user profiling, then user privacy is protected, but positioning accuracy deteriorates
Solution Approach 1:
The system merges cell handover data with available GPS data points to create a hybrid positioning approach. By combining the privacy-protecting characteristics of cell-based positioning with the accuracy of GPS where available, the system achieves both privacy protection and sufficient positioning accuracy for movement pattern recognition.
Solution Approach 2:
The patent dynamically adjusts the precision parameters of positioning based on data availability and context. When GPS data is available, higher precision is used; when only cell handover data is available, the system adapts to lower precision thresholds that are still sufficient for identifying movement patterns. This parameter adaptation maintains privacy while achieving adequate positioning accuracy.
4Measurement precision
If detailed GPS data is collected continuously, then movement pattern accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent segments continuous GPS data into discrete movement episodes or trajectories. By dividing the data stream into meaningful segments that represent complete movement patterns between stationary points, the system reduces processing complexity while maintaining accuracy. Each segment can be independently analyzed and stored, making the overall data management more efficient.
Solution Approach 2:
The system performs preliminary processing of GPS data to identify and extract movement patterns before detailed analysis is required. By pre-processing the data to recognize trajectories, stationary points, and movement episodes in advance, the system reduces the complexity of subsequent analysis while preserving the accuracy needed for user profiling.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
It is provided a method, comprising distributing respective location data of a plurality of users into respective buckets for each of the users, wherein each of the location data indicates a location of the respective user, each of the buckets includes a respective time interval, the time intervals cover the time period, and there is a bucket for each of the users for each of the time intervals; calculating, for each pair of the users and for each of the time intervals, a respective sub-distance between the users of the respective pair based on the location data; aggregating, for each of the pairs of the users, the sub-distances over the time period to obtain a distance between the users of the respective pair; clustering the users having a closest distance from each other.