Venue Zone Event Tracking for Group Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location-based technologies, such as GPS, struggle to detect and infer interpersonal groups within venues due to their reliance on absolute location and inability to define zones within venues, limiting their ability to discern relationships between mobile device users based on movement patterns.
Innovation Solution
A computer-implemented method that tracks zone events representing relative movements and dwelling times of mobile devices within configured venue zones, inferring relationships between users by setting and satisfying specific threshold criteria such as entry, exit, distance, and dwell times, allowing for automated group inference and personalized promotions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS and traditional location-based technologies are used, then absolute location can be determined, but the ability to detect and infer interpersonal groups within venues is limited
Solution Approach 1:
The venue is segmented into multiple configurable zones with different characteristics (high-traffic, low-traffic, promotion zones, etc.). This segmentation allows the system to track device movements within specific zones and infer interpersonal relationships based on co-location patterns in different venue areas, resolving the limitation of treating the entire venue as a single location.
Solution Approach 2:
The system transitions from two-dimensional GPS coordinates to a multi-dimensional venue zone model that includes zone identifiers, dwell times, entry/exit events, and zone characteristics. This dimensional transformation enables sophisticated analysis of movement patterns and interpersonal group inference that cannot be achieved with traditional absolute location data alone.
2Productivity
If traditional location-based technologies are used, then basic location tracking is achieved, but automated group inference based on movement patterns is not possible
Solution Approach 1:
The system pre-configures venue zones, thresholds for group inference, and analysis parameters before deployment. This preliminary configuration enables automated real-time group inference without requiring complex real-time decision-making logic, reducing computational complexity while maintaining high productivity in identifying interpersonal groups.
Solution Approach 2:
The system automatically infers interpersonal groups by analyzing device co-location patterns against pre-configured thresholds, without requiring manual intervention or complex external processing. The automated threshold-based inference engine processes zone events and self-determines group relationships, achieving high automation with manageable system complexity.
3Measurement precision
If zone event tracking is implemented, then interpersonal group inference accuracy is improved, but data processing requirements increase
Solution Approach 1:
The system extracts only the essential zone events (entries, exits, dwell times) relevant to group inference from the continuous stream of location data. By filtering and extracting only these critical events rather than processing all location points, the system maintains high inference accuracy while significantly reducing the volume of data that requires processing.
Solution Approach 2:
The system monitors all zone events for all devices but applies inference logic only to specific partial sets of events that meet predefined thresholds and patterns. This selective application of analysis to relevant subsets of data maintains high group inference accuracy while avoiding the computational burden of processing every single zone event for every device.
Data Source
AI summary
Zone events are tracked within a venue. The zone events represent relative movements and dwelling times of multiple mobile devices within the venue as users of the respective mobile devices move and dwell among and within multiple configured zones of the venue. A relationship is inferred between at least two of the users responsive to a configured zone event threshold being satisfied by the tracked zone events that represent the relative movements and dwelling times of the mobile devices of the at least two users.