Event Detection System Using Mobile Device Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current location-based services struggle to accurately and efficiently detect events by congregating mobile devices, as they rely on manual entry of event types and locations, and are unable to differentiate between temporary or ad-hoc events, such as parades or concerts, and fail to scale with increasing numbers of mobile devices providing location data.
Innovation Solution
The system employs algorithms and processing techniques, including a queue structure, to efficiently compare location data from multiple mobile devices, detect congregations, and establish virtual perimeters around events, leveraging access to wireless carrier systems to reduce battery consumption and improve data gathering, while predicting future events based on historical data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If manual entry of event types and locations is used, then system complexity is reduced, but event detection accuracy and automation are worsened
Solution Approach 1:
The system automatically detects events by analyzing location data from mobile devices without requiring manual entry of event information. The event detection module autonomously identifies congregations of devices, determines event types based on location patterns, and generates event data structures, enabling the system to serve itself rather than relying on human operators.
Solution Approach 2:
The system transforms raw location data parameters into meaningful event parameters by analyzing spatial and temporal patterns. It converts coordinates and timestamps from multiple devices into event type classifications and location identifiers, changing the parameter representation from individual device positions to aggregated event characteristics.
2Measurement precision
If location data from multiple mobile devices is processed to detect congregations, then event detection accuracy is improved, but data processing time and computational resources are worsened
Solution Approach 1:
The system segments the large dataset of location information into manageable groups by spatial location and time window. It divides the processing task into identifying individual device positions, grouping devices by proximity, and then analyzing each group for congregation patterns, thereby reducing the computational complexity of processing all devices simultaneously.
Solution Approach 2:
The system processes location data partially by focusing only on relevant time windows and spatial regions where congregations are likely to occur. It applies filtering criteria to process only the necessary portion of location data rather than analyzing every data point in detail, reducing processing time while maintaining detection accuracy.
3Quantity of substance
If the system scales to handle increasing numbers of mobile devices, then coverage and data availability are improved, but processing efficiency and battery consumption are worsened
Solution Approach 1:
The system uses periodic time windows to collect and process location data from mobile devices rather than continuous processing. It aggregates location information at regular intervals, allowing devices to enter low-power states between measurement cycles, thereby reducing battery consumption while maintaining the ability to detect events across large numbers of devices.
Solution Approach 2:
The system creates a universal event detection framework that handles varying numbers of devices through the same location-based congregation analysis. The event detection module serves multiple functions by identifying different event types (concerts, sports events, gatherings) using the same core algorithm, making the system scalable without proportionally increasing processing requirements.
Data Source
AI summary
In general, embodiments of the present invention provide systems, methods and computer readable media for detecting aggregation events.