Name Matching System Using Segmented Detection Stages
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing person name matching technologies face low matching accuracy and high false alarm rates due to the difficulty in controlling the fuzzy degree in person name fuzzy matching, primarily relying on string matching algorithms with thresholds set by experience.
Innovation Solution
A method and apparatus for matching names that involve obtaining a name to be matched, determining a standard name set, detecting if the name is synonymous with names in the set but with different characters, and determining the matching result based on this detection, incorporating techniques like abbreviation detection, address term detection, and multi-language detection to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a string matching algorithm with a low threshold is used to perform person name fuzzy matching, then the omission rate is reduced, but the matching accuracy decreases and the false alarm rate increases
Solution Approach 1:
The patent segments the name matching process into multiple independent detection stages: exact match detection, abbreviation detection, synonym detection, and fuzzy match detection. Each stage handles specific types of name variations, allowing the system to maintain high accuracy while comprehensively covering different matching scenarios without relying on a single low threshold
Solution Approach 2:
The patent changes the matching parameters dynamically based on the detection stage. Instead of using a fixed low threshold throughout, it applies different matching criteria: exact string comparison for exact matches, abbreviation expansion rules for abbreviated names, synonym relationships for synonymous names, and threshold-based fuzzy matching only when necessary. This parameter adaptation resolves the contradiction between reducing omission and maintaining accuracy
2Reliability
If a string matching algorithm with a low threshold is used to perform person name fuzzy matching, then the omission rate is reduced, but the system false alarm rate increases
Solution Approach 1:
The patent segments the matching process to handle different name relationship types separately. By detecting exact matches, abbreviations, and synonyms through dedicated modules before resorting to fuzzy matching, it reduces false alarms caused by inappropriate fuzzy matching while ensuring genuine matches are not missed
Solution Approach 2:
The patent performs preliminary detection of exact matches, abbreviations, and synonyms before executing fuzzy matching. This preliminary action filters out cases that can be confidently resolved without fuzzy matching, preventing false alarms from low-threshold fuzzy matching while maintaining comprehensive coverage through subsequent fuzzy matching only for ambiguous cases
Data Source
AI summary
An input comprising a name to be matched is received, where the name includes a plurality of words. A first name set corresponding to the name is determined, where the first name set includes a plurality of elements. Each of the plurality of words is matched with each of the plurality of elements based on a similarity degree to generate a standard name set. Whether the name is synonymous with at least one standard name in the standard name set is determined, where one or more characters of the name is not identical with one or more characters of the standard name. In response to determining that the name is synonymous with the at least one standard name, a matching result of the name is generated.