Correlation Engine for Multisensor Events and False-Alarm Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing surveillance systems lack the intelligence to correlate information about vehicles and do not have connectivity to law enforcement databases, leading to high false alarm rates and inefficiencies in security and surveillance, particularly in preventing crimes and ensuring safety in environments like schools and businesses.
Innovation Solution
A system that collects and correlates sensory data from various devices, including video cameras, to detect events, manage storage hierarchically, and generate intelligent alerts based on meta-data and attribute data, using a correlation engine to identify critical events and trigger alerts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing surveillance systems collect and process sensory data from multiple sensors, then the system can detect various events and provide comprehensive monitoring coverage, but the system generates high false alarm rates and produces large amounts of spurious information that reduce operational efficiency
Solution Approach 1:
The patent introduces a correlation engine as an intermediary component between sensory event detection and alert generation. This correlation engine receives sensory events from multiple sensors, correlates them based on predefined rules and historical data, and only generates alerts when correlation thresholds are met. This intermediary layer filters out spurious information and reduces false alarms while maintaining system complexity at an acceptable level through modular architecture.
Solution Approach 2:
The system implements feedback mechanisms where alert history and correlation data are fed back into the correlation engine to continuously refine alert generation. The correlation engine learns from historical false alarms and adjusts correlation thresholds and rules dynamically, improving reliability over time while maintaining manageable system complexity through automated adaptation rather than manual configuration.
2Measurement precision
If the system correlates information from multiple sensors and databases, then it can identify critical events more accurately, but the processing time and computational resources increase significantly
Solution Approach 1:
The system performs preliminary actions by pre-processing sensory events and pre-establishing correlation rules before critical events occur. The correlation engine pre-categorizes events, pre-loads historical data, and pre-configures correlation thresholds based on historical analysis. This preliminary preparation enables rapid real-time correlation processing without significant delays when actual events need to be detected and responded to.
Solution Approach 2:
The correlation engine segments the correlation process into distinct modular stages: event normalization, historical data retrieval, correlation rule application, and alert generation. Each segment can be independently optimized and processed in parallel, reducing overall processing time while maintaining comprehensive correlation analysis across multiple sensors and databases.
3Loss of information
If the system stores and processes large volumes of sensory data from multiple sources, then it can perform comprehensive analysis, but the storage requirements and data management complexity increase
Solution Approach 1:
The system extracts only the essential and relevant information from large volumes of sensory data for storage and processing. The correlation engine identifies and extracts key event attributes, temporal patterns, and spatial relationships while discarding redundant and spurious information. This extraction approach maintains information completeness for critical analysis while significantly reducing storage requirements and data management complexity.
Solution Approach 2:
The system applies local quality by storing and processing data with different levels of detail based on their importance and usage patterns. Frequently accessed and critical event data are stored with high detail and retained longer, while less important data are stored with reduced detail or shorter retention periods. This differentiated data management maintains information completeness where needed while reducing overall storage burden and management complexity.
Data Source
AI summary
Monitoring systems and methods for use in security, safety, and business process applications utilizing a correlation engine are disclosed. Sensory data from one or more sensors are captured and analyzed to detect one or more events in the sensory data. The events are correlated by a correlation engine, optionally by weighing the events based on attributes of the sensors that were used to detect the primitive events. The events are then monitored for an occurrence of one or more correlations of interest, or one or more critical events of interest. Finally, one or more actions are triggered based on a detection of one or more correlations of interest, one or more anomalous events, or one or more critical events of interest. A hierarchical storage manager, having access to a hierarchy of two or more data storage devices, is provided to store data from the one or more sensors.