Machine-Learned Knowledge Graph Rules for Accurate Data Completion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently generating and refining rules for completing knowledge graphs, particularly in integrating diverse and evolving data sources, which limits their effectiveness in semantic reasoning and data integration across applications.
Innovation Solution
A computer-implemented technology that generates rules for completing knowledge graphs using a generic machine learning model, refines and filters these rules based on predefined user settings, and provides inferred facts for knowledge graph completion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual rule definition based on expert knowledge is used, then rule accuracy is improved, but time consumption and cost increase
Solution Approach 1:
The system enables automatic generation of completion rules through machine learning models that self-learn from existing knowledge graph data, eliminating the need for manual expert definition while maintaining rule accuracy through iterative optimization and validation mechanisms
Solution Approach 2:
The patent replaces the mechanical process of manual expert rule definition with an automated machine learning system that uses algorithms to discover and generate completion rules, significantly reducing time consumption while maintaining or improving rule quality through data-driven insights
2Quantity of substance
If diverse data sources are integrated, then knowledge graph completeness is improved, but data quality and consistency deteriorate
Solution Approach 1:
The system implements feedback mechanisms where generated rules are validated against existing knowledge graph data and user feedback is incorporated to continuously refine and improve rule quality, ensuring that integrating diverse data sources maintains data consistency and reliability through iterative optimization
Solution Approach 2:
The patent introduces completion rules as intermediary elements that mediate between diverse data sources and the knowledge graph, providing a standardized framework that harmonizes different data formats and quality levels while maintaining overall data consistency
3Measurement precision
If complex rule sets are used, then completion accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments complex completion tasks into manageable rule components that can be independently generated, validated, and applied, reducing overall system complexity while maintaining high completion accuracy through modular rule structures that can be composed to handle complex scenarios
Data Source
AI summary
Provided is a computer-implemented technology which generates rules for completion of a knowledge graph by producing, with a generic machine learning model or one that is trained on the knowledge graph, inferred triples, optionally refines and filters the produced rules along predefined user settings and provides the resulting rules, along with the inferred facts covered by the rules, as candidates for completion of the knowledge graph.