Entity Matching via Demographic Data Sanitization and Probabilistic Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing entity matching systems face challenges in reliably linking entities that have undergone name changes, due to unreliable governmental identification numbers and data entry errors, leading to inconsistencies and increased memory storage and processing resources.
Innovation Solution
A system that sanitizes and standardizes demographic data, performs probabilistic searches in internal and external resources, adjusts search criteria based on result quality, and creates new identifiers when necessary, to ensure accurate and secure entity matching with reduced resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If governmental identification numbers are used for entity matching, then entity identification reliability is improved, but data security and privacy risks increase
Solution Approach 1:
The patent extracts and removes sensitive governmental identification numbers from the entity matching process. Instead of using SSNs or other government IDs, the system relies on demographic data fields such as name, date of birth, and address. This extraction eliminates the security and privacy risks associated with storing and processing sensitive identification numbers while maintaining entity matching capability through alternative demographic attributes.
2Productivity
If traditional entity matching methods are used, then processing speed is maintained, but matching accuracy decreases due to name changes and data errors
Solution Approach 1:
The patent applies preliminary action by pre-processing demographic data through sanitization and standardization before the actual entity matching process. The system standardizes name formats, normalizes date formats, and cleans address data in advance. This preliminary preparation ensures that subsequent matching operations work with consistent, high-quality data, improving accuracy without adding computational overhead during the critical matching phase.
Solution Approach 2:
The system dynamically adjusts matching strategies based on the quality and completeness of available demographic data. When certain fields are missing or unreliable, the system adapts by weighing available fields differently or switching to alternative matching approaches. This dynamic adaptation allows the system to maintain both speed and accuracy across diverse data quality scenarios.
3Stability of the object's composition
If demographic data is sanitized and standardized, then data consistency is improved, but processing time increases
Solution Approach 1:
The patent performs sanitization and standardization as preliminary actions during data ingestion and storage phases, rather than during query processing. Demographic data is cleaned, normalized, and standardized when first entered into the system, and this pre-processed data is then reused for subsequent matching operations. This approach establishes data consistency upfront while avoiding repeated processing overhead during entity matching queries.
Data Source
AI summary
Improvements in data processing to match entities allow for more accurate records to be kept, with less memory storage used and fewer processing resources to be expended when accessing records. When receiving a request for an identifier for an entity, the request is parsed to identify various demographic fields within the request. A probabilistic search is performed to compare the entity to the candidate records that are augmented with expanded demographic data, which improve the reliability in matching the requested entity to its records. As updates are made to the external resources, the requests are rerun to update the internal resource and to eliminate any new identifiers created due to non-updated data, thus reducing data storage overhead.