Collocation Detection Using Grid-Based Mapping and Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analyzing electronic activity data for suspicious activities, such as meetings between suspect individuals, is a time and resource-consuming task for intelligence and law enforcement agencies due to the vast amounts of collected data.
Innovation Solution
A system and method for collocation detection that uses a data fusion system to process observation data from mobile devices and other sources, identifying potential meetings by determining if two or more devices were present at the same location for a predefined period, utilizing a grid-based mapping approach to analyze geographical locations and time stamps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of electronic activity data is performed, then detection accuracy can be maintained, but time consumption and resource requirements increase significantly
Solution Approach 1:
The patent segments the vast electronic activity data into discrete observation records with specific attributes (location, time, device ID). By dividing the continuous data stream into structured, comparable units, the system enables automated processing while maintaining detection accuracy through systematic analysis of segmented data points.
Solution Approach 2:
The patent replaces manual mechanical analysis with an automated computer-based system that processes observation data through algorithmic comparison. The system automatically detects collocations by comparing device positions and timestamps, substituting human analysts with computational processes that achieve comparable accuracy without time constraints.
2Productivity
If automated processing is implemented, then time and resource efficiency improve, but system complexity increases
Solution Approach 1:
The patent creates a multi-functional system that performs multiple tasks: receiving observation data from various sources, storing it in a database, comparing device collocations, and generating reports. This universal system handles diverse data types and operations through a unified architecture, improving productivity while managing complexity through functional integration.
Solution Approach 2:
The patent introduces a database as an intermediary layer between data collection and analysis processes. The database stores observation data in a standardized format, serving as a buffer that decouples data ingestion from processing, thereby simplifying the overall system architecture while enabling efficient automated processing.
3Reliability
If comprehensive data collection is performed, then detection completeness improves, but data volume and processing burden increase
Solution Approach 1:
The patent extracts only the essential attributes needed for collocation detection from the comprehensive electronic activity data: device identification, location coordinates, and timestamps. By taking out only these critical elements and discarding redundant information, the system maintains detection completeness while significantly reducing data volume and processing burden.
Solution Approach 2:
The patent performs preliminary processing of observation data by filtering and structuring it before analysis. The system pre-processes incoming data to extract relevant features and organize them into a standardized format, preparing the data in advance for efficient collocation detection without needing to process the entire raw data set.
Data Source
AI summary
Systems and methods are disclosed for collocation detection. In accordance with one implementation, a method is provided for collocation detection. The method includes obtaining a first object observation that includes a first object identifier, a first observation time, and a first observation location. The method also includes obtaining a second object observation that includes a second object identifier, a second observation time, and a second observation location. In addition, the method includes associating the first observation with a first area on a map, associating the second observation with a second area on the map, and determining whether a potential meeting occurred between objects associated with the first object identifier and the second object identifier based on the first and second observation times, and the first and second areas.