Self-Updating Ontologies for Evolving Document Knowledge Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manually created ontologies are time-consuming, prone to errors, and may miss relevant or outdated concepts, particularly for new or evolving domains, leading to inefficiencies in data integration and artificial intelligence systems.
Innovation Solution
A method for tracking property usage over time, changing property status based on thresholds, and updating ontologies automatically to include or remove properties, ensuring relevance and completeness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If ontologies are manually created and updated, then ontologies can be customized and adapted to specific needs, but the process is extraordinarily time consuming and prone to errors
Solution Approach 1:
The system automatically monitors property usage in electronic documents and self-updates the ontology by adding or removing properties based on observed usage patterns, eliminating the need for manual ontology maintenance while preserving adaptability to domain-specific needs
Solution Approach 2:
The system implements a feedback loop where property usage is tracked over time, usage statistics are analyzed against thresholds, and ontology updates are automatically triggered based on this feedback, enabling continuous adaptation without manual intervention
2Measurement precision
If ontologies are manually created, then specific concepts can be identified, but relevant new concepts may be overlooked or outdated concepts may not be identified
Solution Approach 1:
The system continuously monitors property usage in electronic documents over time, ensuring that new relevant concepts are automatically detected as they emerge and that outdated concepts are identified for removal, maintaining complete concept coverage without manual review
Solution Approach 2:
The manual mechanical process of concept identification is replaced with an automated computational system that uses threshold-based analysis of property usage statistics to objectively determine which concepts should be added or removed from the ontology
3Reliability
If property status changes are made frequently to maintain relevance, then ontology accuracy improves, but system complexity and processing overhead increase
Solution Approach 1:
The system uses threshold-based triggering where property status changes are made only when usage statistics exceed or fall below predetermined thresholds, avoiding unnecessary frequent updates while maintaining ontology relevance through targeted partial updates rather than comprehensive re-evaluation
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Techniques and solutions are provided for improved use of knowledge graphs in document processing. The relevance of properties to a knowledge graph may change over time. While a property may appear, it may take some time before it is apparent that the property should be used in a knowledge graph. Similarly, while a property may be relevant for a period of time, it can lose its relevance. The present disclosure provides techniques for tracking the use of properties over time, and making or proposing property status changes. These changes can result in making the properties visible or non-visible in a knowledge graph, which in turn can affect how future documents are processed. Further, in some cases a property can be made active, and documents processed when the property was not present or not active can be reprocessed to obtain information for the property.