Context-Aware Geofence Generation and Resizing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geofence solutions are entity-oblivious and one-size-fits-all, leading to high rates of false-negative and false-positive triggers, as they fail to accurately size and shape geofences based on user context and ambient conditions, making them ineffective for delivering location-based notifications.
Innovation Solution
The proposed architecture uses rich user context and crowd-sourced data to automatically generate and resize geofences that are intelligently sized, shaped, and placed, incorporating user travel paths, ambient conditions, and crowd-sourced entity-identifiable data to create spatiotemporally accurate geofences that adapt to user intent and mobility, allowing for gradient-based triggering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If context-oblivious geofences are used, then the system is simple to implement, but the geofences become noisy with many false negatives and false positives
Solution Approach 1:
The patent changes the parameters of geofence construction by incorporating multiple context factors (user travel path, mode of transport, entity type, user incentive, probability of entry, time-criticality) and ambient conditions (traffic, weather, spatial uniqueness) to dynamically adjust geofence characteristics. This resolves the contradiction by making the system more reliable through contextual parameters while managing complexity through automated processing of these parameters.
Solution Approach 2:
The system performs automatic geofence generation and adjustment without requiring manual user intervention. The automated analysis of context and crowd-sourced data, along with gradient-based triggering mechanisms, enables the system to self-optimize geofence parameters, reducing the need for complex manual configuration while improving trigger accuracy.
2Measurement precision
If manual editing of geofences is enabled, then geofence accuracy can be improved, but the process becomes tedious and impractical for speech-based scenarios
Solution Approach 1:
The system automatically generates and adjusts geofences based on contextual analysis and crowd-sourced data without requiring manual user editing. The automated gradient-based triggering and dynamic resizing eliminate the need for tedious manual adjustments, especially in speech-based scenarios where users cannot visually verify geofence placement.
Solution Approach 2:
The patent replaces manual visual inspection and editing mechanisms with automated computational analysis of context data, crowd-sourced information, and gradient-based triggering algorithms. This substitution enables accurate geofence placement without requiring user visualization or manual adjustment, particularly beneficial in hands-free speech-based interactions.
3Device complexity
If one-size-fits-all geofences are used, then the system is easy to implement, but the geofences fail to adapt to different user contexts and conditions
Solution Approach 1:
The patent applies local quality by creating customized geofences tailored to specific user contexts, entity types, and ambient conditions rather than using uniform geofences. Each geofence is dynamically adjusted based on local factors such as user travel path, mode of transport, and time-criticality, enabling the system to adapt to diverse scenarios while managing complexity through automated contextual analysis.
Solution Approach 2:
The system implements dynamic geofences that automatically adjust their characteristics based on changing user context and ambient conditions. The geofences are not static but adapt in real-time to factors such as traffic conditions, weather, and user behavior patterns, providing versatility while maintaining manageable system complexity through automated dynamic adjustment mechanisms.
Data Source
AI summary
Architecture that enables the capability to more effectively define and resize geofences to provide improved geofence utility based on rich context and crowd-sourced data. The architecture enables the intelligent placement of geofences based on rich context that includes both user context and ambient context such as the (predicted or implicitly/explicitly defined) user's travel path, mode of transport, the type of the entity to be visited by the user and geofenced, and the user incentive for visiting the entity to be geofenced. The ambient context includes non-user specific information such as external conditions that may limit or thwart user mobility such as traffic and weather conditions. The rich context and crowd-sourced data assist in improving the spatiotemporal accuracy of suggested/constructed geofences thereby creating a “shaped” geofence that is sufficiently defined to approximate the shape of the entity being geofenced with some degree of accuracy.