Entity Relevance Scoring Without Alert Infrastructure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Entity resolution systems cannot determine an entity's relevance score when they do not generate or track alerts, limiting their ability to identify potential threats and fraud, or to prioritize entities based on importance without manual alert management.
Innovation Solution
The system processes identity records to assign a base relevance score to entities based on associated identity records and calculates an association relevance score from related entities and relationship strengths, allowing for the computation of a derived relevance score without relying on alerts or alert lifecycles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the entity resolution system does not generate or track alerts, then the system complexity is reduced and ease of operation is improved, but the ability to determine entity relevance scores is lost
Solution Approach 1:
The patent introduces an intermediary mechanism that computes entity relevance scores by leveraging relationship information and identity record associations without requiring the full alert generation infrastructure. This intermediary approach allows relevance determination to function independently of the alert system, resolving the contradiction between operational simplicity and measurement capability.
2Reliability
If the system computes relevance scores based on relationships to other entities, then the identification of potential threats and fraud is improved, but the device complexity increases
Solution Approach 1:
The patent segments the relevance scoring process into distinct components: identity record association, relationship strength calculation, and aggregate relevance determination. This segmentation allows each component to be implemented independently with appropriate complexity, enabling reliable threat detection without requiring the entire system to be overly complex.
Solution Approach 2:
The system implements partial action by computing relevance scores only for entities that have associated identity records and relationships, rather than computing scores for all entities in the system. This selective approach improves threat detection capability while avoiding the complexity of a universal scoring mechanism.
3Productivity
If the system assigns relevance scores based on identity records and relationships, then the productivity of threat identification is improved, but the difficulty of detecting and measuring increases
Solution Approach 1:
The system implements self-service by automatically computing entity relevance scores using readily available identity records and relationship data without requiring manual intervention or complex external measurement tools. This automation improves threat identification productivity while managing measurement complexity through algorithmic processing of existing data.
Data Source
AI summary
An entity resolution system configured to process an inbound identity record and to generate a relevance score for the inbound identity record is disclosed. One process of resolving identity records and detecting relationships between entities may be performed using a pre-determined or configurable entity resolution rules. Further, the entity resolution system may assign base relevance scores, association relevance scores, and derived relevance scores to each resolved entity. The relevance score for the inbound identity record may be computed based on base relevance scores, association relevance scores, derived relevance scores, and/or relationship strengths of entities related to the inbound identity record.