Location History Vector Analysis for Subject Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Law-enforcement and security agencies face challenges in identifying associated subjects, such as family members or coworkers, based on location tracking data, as existing methods lack efficiency in quantifying co-location and normalizing weights to reduce spurious associations.
Innovation Solution
A system and method that calculates weights for each subject based on their location history within geographic areas and time intervals, normalizes these weights to account for co-location frequency, and constructs vectors to measure similarity between subjects, thereby identifying potential associations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If location tracking data is collected for multiple subjects to identify associations, then the ability to detect related subjects improves, but the complexity of processing and analyzing the data increases
Solution Approach 1:
The patent transforms location tracking data into weighted vectors by changing the parameter representation from raw coordinate data to normalized weight values. Each weight reflects the degree of co-location between subjects, transforming the data into a comparable format that simplifies association analysis while maintaining accuracy.
Solution Approach 2:
The patent replaces complex manual or rule-based analysis of location data with an automated computational system that calculates weights and computes vector similarities. This substitution of mechanical/manual processes with algorithmic processing reduces complexity while improving reliability of association identification.
2Measurement precision
If weights are calculated for each subject-geographic area-time interval combination to quantify co-location, then the precision of association measurement improves, but the quantity of calculations and data processing increases
Solution Approach 1:
The patent segments the overall analysis into distinct components: first calculating individual weights for each subject-geographic area-time interval combination, then organizing these weights into vectors, and finally computing similarities between vectors. This segmentation allows precise measurement while managing the quantity of calculations through systematic organization.
Solution Approach 2:
The patent calculates weights for all possible subject-geographic area-time interval combinations (excessive action) to ensure complete coverage and precision, then uses normalization and vector comparison to efficiently process this comprehensive data set, accepting the full calculation burden in exchange for measurement precision.
3Reliability
If normalization is applied to weights to account for co-location frequency, then the reduction of false positives improves, but the processing time and computational effort increase
Solution Approach 1:
The patent performs normalization of weights as a preliminary step before computing vector similarities. By pre-processing the weight data to account for co-location frequency and normalize the vectors, the system reduces false positives in the subsequent similarity comparison, accepting the upfront processing time investment to improve overall reliability.
4Measurement precision
If vectors are constructed from normalized weights to measure similarity between subjects, then the accuracy of association identification improves, but the computational complexity of vector operations increases
Solution Approach 1:
The patent changes the parameter representation from raw weight values to normalized vectors, enabling the use of efficient vector similarity operations. This parameter transformation maintains measurement precision while allowing the application of standardized vector mathematics to compute associations between subjects.
Data Source
AI summary
Systems and methods to track the respective locations of subjects over time. The system identifies subjects who, overtime, were co-located with one another suggesting they are associated with one another, and the pairs are analyzed. For each of the subjects, the system produces a vector that quantifies the subject's location history by including a respective weight for each combination of a time interval with a geographical area. The vectors are compared using a distance metric, and any pair of subjects whose vectors are sufficiently close are flagged as being an associated pair. The respective vector belonging to each subject is normalized to account for the total number of other subjects who were co-located with the subject. For each interval-area pair, the system may compute the frequency of the interval-area pair, and then divide each weight that corresponds to the interval-area pair by the frequency of the interval-area pair.