Ontology Property Extraction Using Instance Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual ontology creation is time-consuming, prone to errors, and subject to terminology variation, leading to inconsistent and difficult-to-compare ontologies.
Innovation Solution
Automated processes using instance graphs to determine properties and generate class definitions for ontologies, including label alignment and graph decomposition, enabling rapid and accurate ontology development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual ontology creation is used, then ontology can be customized according to user needs, but the process is extraordinarily time consuming and prone to errors
Solution Approach 1:
The system automatically extracts ontological concepts, properties, and relationships from domain documents without requiring manual curation. The automated ontology creation system processes documents, identifies concepts, and generates ontologies independently, eliminating the time-consuming manual creation process while maintaining accuracy through systematic analysis
Solution Approach 2:
The patent replaces manual mechanical ontology creation with automated computational processes. The system uses algorithms to extract information from documents, identify semantic concepts, and construct ontologies automatically, substituting human manual work with automated mechanical-like processing that is both faster and more consistent
2Reliability
If manual ontology creation is used, then users can identify relevant semantic concepts, but different users may use different labels for common semantic concepts leading to terminology variation
Solution Approach 1:
The system automatically standardizes terminology by mapping different labels to standardized concept identifiers. The automated process detects various terminology variations in documents and reconciles them to a consistent ontology vocabulary, ensuring that different users' terminology is normalized to a stable, consistent representation
Solution Approach 2:
The automated system serves multiple functions simultaneously: it extracts concepts, standardizes terminology, identifies relationships, and generates ontologies all through a single unified process. This multi-functional approach ensures both complete concept identification and terminology consistency that manual single-function approaches cannot achieve
3Productivity
If automated ontology creation is used, then ontology creation speed increases, but the system must process large corpora of documents requiring computational resources
Solution Approach 1:
The system extracts only the relevant ontological information from large document corpora, filtering out unnecessary data. By selectively extracting concepts, properties, and relationships rather than processing every detail of all documents, the system achieves high productivity while reducing computational resource consumption
Solution Approach 2:
The automated ontology creation process is divided into discrete computational stages: document processing, concept extraction, relationship identification, and ontology generation. This segmentation allows the system to handle large corpora efficiently by processing data in manageable chunks through specialized algorithms for each stage, reducing overall computational burden
Data Source
AI summary
Properties for an ontology, such as used for semantic query execution, automated analytical reasoning, or for machine learning, are determined using instance graphs. A corpus of documents is received, representing a plurality of domain instances of a domain. Instance graphs are generated for instances of the plurality of instance graphs to provide a plurality of instance graphs. Properties represented in the plurality of instance graphs are determined. At least a portion of the properties are assigned to an ontology for the domain.