Identity De-duplication via Network Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current law enforcement systems face challenges in eliminating data duplication, particularly due to misspelling of names and inadequate preventative measures, leading to inaccurate identification of duplicate identities, as existing methods are static and do not account for variability or human error.

Innovation Solution

The implementation of network analysis and behavioral comparisons, which examine extended networks and centrality measures to verify duplicate identities, increasing accuracy by considering multiple degrees of separation and social network importance, rather than relying solely on facial image or string comparisons.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If static comparison methods (facial image or string comparison) are used to identify duplicate identities, then the system is simple to operate, but the accuracy of duplicate detection is low and cannot account for variability or human error

Engineering Contradiction:
Improveaccuracy of duplicate detectionVSAvoidcomplexity of identification system
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transitions from static two-dimensional comparison (facial images or name strings) to multi-dimensional network analysis that examines relationships across multiple degrees of separation. By adding the dimension of social network connections and behavioral patterns, the system achieves higher detection accuracy while managing complexity through structured network modeling

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The identification system is segmented into multiple independent analysis components: network structure analysis, behavioral pattern comparison, centrality measure calculation, and similarity scoring. Each component handles a specific aspect of duplicate detection, allowing the system to achieve high accuracy through coordinated analysis while maintaining operational manageability through modular design

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If network analysis examining extended networks and multiple degrees of separation is used, then the accuracy of identifying duplicate identities is significantly enhanced, but the computational complexity and data processing requirements increase

Engineering Contradiction:
Improveaccuracy of duplicate detectionVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-calculating and storing network centrality measures, connection counts, and behavioral baselines for each individual in the database. This preprocessing allows the duplicate detection algorithm to compare pre-computed metrics rather than analyzing entire network structures in real-time, significantly reducing computational complexity while maintaining high detection accuracy

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent changes the parameters being analyzed from raw network data to derived metrics such as centrality scores, connection density, and behavioral deviation thresholds. By transforming complex network structures into standardized parameters with defined ranges and significance thresholds, the system achieves high measurement precision while simplifying the computational comparison process

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS10009457B2De-duping identities using network analysis and behavioral comparisons
Publication Date: 2018.06.26 MARK43 INC

AI summary

A processing device identifies comparison subjects comprising a first subject and a second subject. The processing device builds a first network of a first profile of the first subject and a second network of a second profile of the second subject, wherein the first network and the second network are multi-degree connections networks. The processing device the first network and second network to produce a similarity score. The processing device examining first-degree connections between the first network and the second network and accounting for centralities that rely on information about the first network and the second network. Responsive to the similarity score exceeding a similarity threshold, indicating the first profile and the second profile correspond to a common profile for the first subject and the second subject.