🤖 AI Summary
This study addresses the challenges of internal consistency and external interoperability in the automatic alignment and integration of heterogeneous knowledge graphs by proposing an ontology-compatible knowledge graph construction approach. The method integrates a novel ontology-driven term-matching algorithm, a schema-based compliance modeling mechanism, and a quantitative metric for assessing conformance, ensuring that the resulting knowledge graphs strictly adhere to prescribed ontological specifications at both structural and semantic levels. Experimental validation in the architectural domain demonstrates the effectiveness of the approach, significantly enhancing the interpretability of the knowledge graphs and their interoperability across systems. This work thus offers a viable pathway toward the automated fusion of heterogeneous knowledge graphs while preserving ontological fidelity.
📝 Abstract
Ontologies can act as a schema for constructing knowledge graphs (KGs), offering explainability, interoperability, and reusability. We explore \emph{ontology-compliant} KGs, aiming to build both internal and external ontology compliance. We discuss key tasks in ontology compliance and introduce our novel term-matching algorithms. We also propose a \emph{pattern-based compliance} approach and novel compliance metrics. The building sector is a case study to test the validity of ontology-compliant KGs. We recommend using ontology-compliant KGs to pursue automatic matching, alignment, and harmonisation of heterogeneous KGs.