Incident Prediction Using Mobile Device Weight Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current incident prediction systems are insufficient in predicting incidents over a meaningful time span, relying primarily on historical crime data and lacking the ability to effectively utilize real-time data from mobile devices to anticipate potential incidents.
Innovation Solution
An incident prediction system that combines historical data with real-time data from mobile devices, using weight factors based on proximity to past incidents and situational factors to generate prediction data, enabling proactive measures by law enforcement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If historical crime data is used for incident prediction, then the system can provide a baseline prediction capability, but the prediction accuracy over meaningful time spans remains insufficient
Solution Approach 1:
The patent combines historical crime data with real-time mobile device data to create a hybrid prediction system. The crowd detection unit continuously monitors mobile device identifiers in the vicinity, which are then merged with historical incident data from the database. This combination allows the system to maintain accurate predictions over extended time spans by detecting changes in crowd composition and density that historical data alone cannot capture.
Solution Approach 2:
The system performs preliminary detection of crowd characteristics by monitoring mobile device identifiers before incidents occur. By establishing a baseline of normal crowd composition and detecting deviations from this baseline, the system can predict incidents over meaningful time spans while maintaining accuracy. The weight factors associated with mobile device identifiers enable the system to identify problematic individuals or groups in advance.
2Reliability
If real-time mobile device data is collected and analyzed, then incident prediction accuracy improves, but the system complexity increases
Solution Approach 1:
The prediction subsystem serves multiple functions: it detects crowd density, identifies problematic mobile device identifiers, calculates risk scores using weight factors, and generates predictions. By consolidating these functions into a single modular subsystem that interfaces with existing crowd detection units and databases, the system achieves high prediction accuracy without proportionally increasing overall system complexity.
Solution Approach 2:
The incident database automatically associates weight factors with mobile device identifiers based on their proximity to historical incidents. This self-service mechanism eliminates the need for manual configuration of risk parameters, reducing system complexity while maintaining high prediction accuracy. The system automatically updates and refines weight factors as new historical data becomes available.
3Loss of information
If mobile device identifiers are monitored to detect crowd composition, then situational awareness improves, but the amount of data to be processed increases
Solution Approach 1:
The prediction subsystem extracts only the critical information from mobile device data - specifically the device identifiers and their association with historical incidents. Rather than processing all raw sensor data, the system focuses on identifying and monitoring specific mobile device identifiers that have been associated with past incidents through weight factors. This extraction approach maintains high situational awareness while significantly reducing the data processing burden.
Solution Approach 2:
The system applies different levels of monitoring intensity to different mobile device identifiers based on their associated weight factors. Devices with higher weight factors (those previously associated with incidents) receive more intensive monitoring and analysis, while devices with lower weight factors receive minimal processing. This localized quality approach ensures that critical information is captured without processing unnecessary data volume.
Data Source
AI summary
An incident prediction system and an incident prediction method are provided for predicting an incident. The system comprises a crowd detection interface for receiving a plurality of mobile device identifiers and an incident database wherein a plurality of weight factors is associated with a plurality of stored mobile device identifiers. The weights associated to mobile devices which were present at a site during a previous, historical incident are higher. The system further comprises a prediction subsystem configured for determining a total weight factor at a site to predict an occurrence of an incident. The system and the method may provide information on a composition of a crowd which may help to better prevent incidents from happening. As such, the provided system and method may enable a more effective prediction of incidents compare to currently available systems and methods.