Identity Resolution System with Typed Relevance Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current identity resolution systems face challenges in efficiently processing and resolving identity records with different relevance scores and types, leading to difficulties in identifying relevant entities and generating accurate alerts or reports without manual intervention.
Innovation Solution
A computer-implemented method and system that accesses and resolves identity records with multiple relevance scores of different types, determining a common individual and generating relevance scores for entities, while allowing for configurable rules and alerts based on predefined criteria, enabling flexible querying and reporting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If identity resolution systems process multiple relevance scores of different types, then the ability to identify relevant entities is improved, but the system complexity increases
Solution Approach 1:
The patent segments the relevance scoring system into multiple independent relevance types (e.g., fraud risk, credit risk, marketing relevance). Each identity record can have multiple relevance scores of different types, allowing the system to evaluate entities from multiple dimensions without creating a monolithic complex scoring system. This segmentation enables precise entity identification while maintaining manageable system architecture through modular, type-specific scoring rules.
2Productivity
If the system automatically generates alerts and reports based on multiple relevance types, then manual effort is reduced, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-configuring relevance types, scoring rules, and alert thresholds before actual identity resolution processing. The framework establishes the multi-type relevance scoring structure in advance, so that during runtime, the system can efficiently process identity records by applying pre-defined rules rather than creating complex logic dynamically. This preliminary setup reduces processing time during operational phases.
Solution Approach 2:
The identity resolution system automatically generates alerts and reports by self-evaluating identity records against multiple relevance types without requiring manual intervention. The system autonomously computes relevance scores, compares them against thresholds, and triggers appropriate alerts or reports based on the scoring results. This self-service capability reduces manual effort while the system manages computational resources efficiently through automated processing pipelines.
3Loss of information
If the system resolves identity records into entities with multiple relevance scores, then the completeness of entity information is improved, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent applies local quality by assigning different relevance scores to different aspects (local qualities) of the same entity. Instead of using a single overall relevance score, the system evaluates and stores multiple relevance scores of different types (e.g., fraud risk score, credit risk score, marketing relevance score) for each entity. This allows comprehensive entity information storage while simplifying measurement and detection by treating each relevance type as an independent, manageable metric with its own evaluation criteria.
Data Source
AI summary
Techniques are disclosed for configuring an identity resolution system to support distinct relevance types. Identity records are accessed that are assigned relevance scores of distinct relevance types. Upon determining that the identity records refer to a common individual, the identity records are resolved into an entity representing the common individual. Relevance scores of the distinct relevance types are then determined for the entity, based on the identity records.