Entity Relationship Quantification via Ontological Co-occurrence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data analysis techniques face challenges in discovering and quantifying non-obvious relationships between entities within unstructured data, which is crucial for applications like natural language processing, health insights, and fraud detection, as they often rely on limited factors and lack comprehensive methods to calculate relationship scores accurately.
Innovation Solution
A method and system that query data sources to extract entities, build an ontological structure, determine initial relationship strength based on co-occurrence, and calculate a relationship score using additional factors such as co-occurrence timeline and reasons for co-occurrence, to provide a more comprehensive understanding of entity relationships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data analysis techniques rely on limited factors for relationship detection, then the process is simpler and faster, but the accuracy and comprehensiveness of relationship quantification deteriorates
Solution Approach 1:
The relationship quantification process is segmented into multiple independent factors (co-occurrence frequency, temporal proximity, contextual relevance, etc.), each analyzed separately before being integrated into the final relationship score. This allows comprehensive evaluation while maintaining manageable complexity through modular analysis.
Solution Approach 2:
The patent transitions from single-factor relationship detection to multi-dimensional relationship quantification by incorporating temporal, contextual, and frequency dimensions alongside basic co-occurrence analysis. This dimensional expansion enables more accurate relationship scoring without overwhelming complexity.
2Measurement precision
If comprehensive factors are considered for relationship score calculation, then relationship identification accuracy improves, but processing time and computational complexity increase
Solution Approach 1:
The system performs preliminary entity extraction and ontological structure building before relationship analysis. By pre-processing and organizing entity data in advance, the actual relationship scoring process can focus only on calculating relationships between extracted entities, significantly reducing processing time while maintaining comprehensive factor consideration.
Solution Approach 2:
Different weights and thresholds are applied to different factors based on their specific characteristics and importance. Not all factors are treated equally; instead, local optimization is applied to each factor's contribution, allowing efficient processing by focusing computational resources on the most impactful factors for each specific relationship evaluation.
Data Source
AI summary
Aspects of the present disclosure relate to identifying and quantifying relationships between entities. Data sources can be queried to receive data regarding a party. Entities can be extracted from the data to receive a set of entities, wherein the party is a first entity of the set of entities. An ontological structure can be built that interrelates entities within the set of entities. An initial relationship strength can be determined between the first entity and a second entity based on co-occurrence between the first and second entities, wherein the second entity is a second party. A relationship score can be calculated between the first and second entities based on the initial relationship strength and at least one additional factor.