Dynamic Virtual Perimeter Adjustment for Location-Based Notifications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional geo-fence technologies use static perimeter sizes, which limit the relevance and effectiveness of notifications to users, as they do not adapt to changes in user preferences or environmental conditions.
Innovation Solution
A location-based notification service that dynamically adjusts the size of virtual perimeters based on user preferences, behavior, and environmental factors, such as gas prices, popularity, and user interaction history, to improve notification relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed size perimeter is used for geo-fence notifications, then the system is simple to implement, but the notification relevance to users decreases
Solution Approach 1:
The patent implements dynamic perimeter sizes that automatically adjust based on user behavior patterns and preferences. The system transitions from static, manually-configured perimeters to dynamic perimeters that are continuously optimized through machine learning algorithms analyzing user interaction data, thereby improving notification relevance without requiring manual intervention.
Solution Approach 2:
The system enables self-service by automatically learning and adapting perimeter configurations based on user behavior. The machine learning model continuously processes user interaction data and autonomously adjusts perimeter parameters, eliminating the need for users to manually configure or adjust notification zones while maintaining high personalization levels.
2Reliability
If a larger perimeter size is used to ensure users receive notifications, then notification coverage is improved, but users receive more irrelevant notifications
Solution Approach 1:
The patent applies local quality by creating personalized perimeter zones for different users based on their individual behavior patterns and preferences. Instead of using a uniform large perimeter for all users, the system generates customized notification zones that are optimally sized and positioned for each user, ensuring high relevance while maintaining reliable notification delivery.
Solution Approach 2:
The system dynamically changes perimeter parameters (size, position, shape) based on user behavior data and contextual factors. The machine learning model continuously optimizes these parameters to balance coverage and relevance, adjusting the perimeter configuration in response to changing user patterns and environmental conditions.
3Adaptability or versatility
If manual configuration of perimeter sizes is used, then the system is easy to understand, but it cannot adapt to changing user preferences
Solution Approach 1:
The patent implements feedback loops where user interactions with notifications are continuously monitored and fed back to the machine learning model. This feedback mechanism enables the system to learn from user behavior patterns and automatically adjust perimeter configurations, creating a closed-loop system that continuously improves personalization while managing complexity through automated processing.
Solution Approach 2:
The system replaces manual mechanical configuration with automated computational processes. Instead of users manually adjusting perimeter parameters, the patent employs machine learning algorithms that automatically process user behavior data and compute optimal perimeter configurations, substituting complex manual operations with intelligent automated systems.
Data Source
AI summary
Location-based notification architecture that provides notification relevance to a user and/or a user goal. The size of the virtual perimeter or boundary is changed dynamically based on changes in relevance to a user and/or user goal, and thus, can be made dependent on various factors. The size of the perimeter can increase or decrease according to user preferences that are learned over time (e.g., preference for a gas station of a specific company). These capabilities improve the relevance of the notification the user receives. The relevance of a notification to the user can be improved by tuning the perimeter size according to known parameters that depend on the point of interest (e.g., business) itself and/or by tuning of the size of virtual perimeter according to parameters associated with user behavior. Other parameters can be considered as well, such as environmental conditions, and traffic conditions, for example.