Genealogical Entity Resolution via Multi-Feature Similarity Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Genealogical databases face challenges in entity resolution, specifically identifying and linking different manifestations of the same real-world object due to discrepancies in historical records and human accounts, leading to duplicate entities across user trees, which complicates ancestor data management and user relationships.
Innovation Solution
A method is developed to determine if two tree persons in a genealogical database correspond to the same individual by extracting features, generating similarity scores, and modifying the cluster database to reflect node connections, using machine learning techniques to improve accuracy and efficiency in entity resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional entity resolution methods are used to identify duplicate persons across genealogical trees, then data aggregation and user relationship management become simpler, but accuracy deteriorates due to discrepancies in historical records and human accounts
Solution Approach 1:
The system transforms the entity resolution problem from exact matching to similarity scoring by changing the comparison parameters. Instead of requiring exact matches on name, birth date, and location, the system extracts multiple features (name components, date elements, location hierarchy) and computes similarity scores that accommodate variations in historical records and user input
Solution Approach 2:
The system combines multiple independent features (first name, last name, birth month, birth day, birth year, location components) into a composite similarity score. This composite approach allows the system to tolerate discrepancies in individual features while maintaining overall resolution accuracy through the aggregation of multiple evidence points
2Measurement precision
If multiple features are extracted and compared for each tree person pairing, then entity resolution accuracy improves, but computational complexity increases
Solution Approach 1:
The system segments the entity resolution process into distinct phases: feature extraction, similarity scoring, and threshold-based decision making. Each phase handles specific tasks independently, making the overall complex system manageable and maintainable while preserving accuracy through systematic processing
Solution Approach 2:
The system manages complexity by transforming the comparison task from examining entire person records to evaluating discrete feature pairs. By changing parameters from holistic comparison to feature-level comparison, the system reduces computational burden while maintaining resolution accuracy through aggregated feature evidence
3Measurement precision
If comprehensive feature extraction is performed for all tree person pairings, then duplicate identification accuracy improves, but processing time increases
Solution Approach 1:
The system implements self-service through automated feature extraction and similarity computation that operates without manual intervention. The automated process efficiently handles large numbers of tree person pairings by systematically extracting features and computing scores, reducing the time investment required compared to manual entity resolution while maintaining high accuracy
Data Source
AI summary
Systems and methods for determining whether two tree persons in a genealogical database correspond to the same real-life individual. Embodiments include obtaining, from a tree database, a first tree person from a first genealogical tree and a second tree person from a second genealogical tree. Embodiments also include identifying a plurality of familial categories. Embodiments further include, for each familial category of the plurality of familial categories, extracting a first quantity of features for each of the tree persons in the familial category, generating a first similarity score for each possible pairing of tree persons, identifying a representative pairing based on a maximum first similarity score, and extracting a second quantity of features for each of the tree persons in the representative pairing. Embodiments may also include generating a second similarity score based on the second quantity of features.