Correlation Engine Weighting for False Alarm Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing surveillance systems lack the intelligence to correlate sensory data effectively, leading to high false alarm rates and an inability to filter out irrelevant information, which is crucial for enhancing security, safety, and business productivity.
Innovation Solution
A system that processes sensory data from various sources, applies weight vectors based on attribute data to prioritize alerts, and correlates events across time and space to identify critical events, using a correlation engine and hierarchical storage management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensory data from multiple sources is collected and correlated, then the ability to identify critical events improves, but the complexity of the system increases
Solution Approach 1:
The patent introduces a correlation engine as an intermediary component that receives sensory data from multiple sources, applies weight vectors based on attribute data, and produces correlated event outputs. This mediator handles the complexity of multi-source data integration internally, presenting a simplified interface to external systems while improving critical event identification through weighted correlation analysis.
Solution Approach 2:
The system changes parameters by introducing weight vectors that assign different importance levels to various sensory data sources and attributes. By dynamically adjusting these weight parameters based on attribute data (such as sensor reliability, environmental conditions, or event criticality), the system optimizes event correlation without requiring structural complexity increases.
2Loss of information
If all sensory events are processed and stored, then complete information is available for analysis, but false alarm rates increase
Solution Approach 1:
The patent applies local quality by assigning different weight values to different sensory data sources and attributes based on their reliability and relevance. Instead of treating all sensory events uniformly, the system applies localized quality assessment through weight vectors that emphasize credible sources and de-emphasize unreliable ones, thereby maintaining information completeness while reducing false alarms through differential weighting.
Solution Approach 2:
The system performs partial action by selectively processing and correlating only those sensory events that meet certain weight threshold criteria. Rather than exhaustively analyzing every sensory input, the correlation engine applies partial processing focused on high-weight events, maintaining adequate information analysis while filtering out low-value data that contributes to false alarms.
3Reliability
If weight vectors are applied to prioritize alerts, then false alarm reduction improves, but the computational processing requirements increase
Solution Approach 1:
The system performs preliminary action by pre-calculating and storing weight vectors based on attribute data before actual event correlation occurs. By preparing these weighting parameters in advance (during system initialization or through learned models), the runtime processing requires only simple weighted summation operations rather than complex real-time analysis, reducing computational energy consumption while maintaining false alarm reduction effectiveness.
Data Source
AI summary
One embodiment comprises a non-transitory storage medium storing program code to receive one or more sensory events from a sensory event analytics module that receives sensory data about a physical environment from one or more sensors and processes the sensory data from the one or more sensors to detect the one or more sensory events. The one or more sensors include at least an Internet Protocol (IP) video camera. The one or more sensory events include one of a face detected, a vehicle detected, and a license plate detected. The program code includes code to store the sensory events for later retrieval as stored sensory events; and evaluate one or more historical correlations among the stored sensory events by evaluating the stored sensory events for the one or more historical correlations across at least one of time and space based on at least one weight vector.