Multi-entity Ontology Weighting for Entity Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional data matching techniques, such as record linkage and frequency-based matching, are insufficient for accurately identifying specific entities in large-scale data searches due to their limited accuracy and inefficiency, particularly when dealing with common names or terms.
Innovation Solution
A computer-implemented method and system that uses multi-entity ontology weighting to identify target entities by determining labels, identifying candidate entities, assigning weights based on frequency, and ranking them to output the highest weighted candidate for each label, leveraging a knowledge base with context information to enhance precision and recall.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If simple record linkage technique is used to match data records with same alphanumeric characters, then the searching process is simple and fast, but the accuracy is low because many people share the same name
Solution Approach 1:
The patent segments the entity identification process into multiple independent components: name matching, context analysis, frequency-based scoring, and relationship verification. Each component processes specific features separately and contributes to the overall matching score, allowing the system to maintain speed while improving accuracy through multi-factor evaluation rather than relying on name alone
Solution Approach 2:
The patent transforms the matching criterion from a single parameter (name equality) to multiple parameters including name frequency, contextual relevance, entity relationships, and attribute matching. By changing the evaluation parameters and assigning different weights to each, the system achieves both efficiency through automated scoring and accuracy through comprehensive parameter consideration
2Measurement precision
If frequency-based matching is used to increase accuracy by considering context, then the matching accuracy improves, but the processing time increases significantly when searching large volumes of data
Solution Approach 1:
The patent performs preliminary actions by pre-computing and storing entity frequencies, contextual relationships, and attribute profiles in the knowledge base before the actual matching process. During search operations, the system retrieves these pre-computed values rather than calculating them in real-time, significantly reducing processing time while maintaining high accuracy through comprehensive frequency-based and context-aware matching
Solution Approach 2:
The system uses the knowledge base to provide self-service functionality where entity frequencies, contextual information, and relationship data are automatically maintained and updated. The matching algorithm automatically retrieves and applies relevant frequency statistics and contextual relationships without requiring manual intervention, enabling efficient large-scale processing while maintaining accuracy through automated context-aware scoring
Data Source
AI summary
Systems and methods are provided for multi-entity ontology weighting. In one implementation, a computer-implemented method is provided for identifying one or more target entities. The method receives an input data set. The input data set includes a plurality of tokens that reflect the one or more target entities. The method determines which of the plurality of tokens are labels, identifies a plurality of candidate entities that are related to each of the labels, assigns a weight to each of the plurality of candidate entities based on a frequency of each of the plurality of candidate entities, and ranks, for each of the labels, the plurality of candidate entities according to the assigned weights. The method then outputs, for each of the labels, the one of the plurality of candidate entities for that label that has been assigned a highest weight value.