Incremental Reasoning over Multiple Ontologies

Abstract

Semantic web data management on top of relational database has been regarded as a promising solution for scalable ontology storing, querying and reasoning. In order to reduce query response time, inferred results often need to be pre-computed and materialized. However, this approach faces the great challenge when data is updated, since the repositories need to perform reasoning from scratch to guarantee the consistency of the inferred results. This paper proposes a novel solution to enable the incremental data update on the context that ontology reasoning and user-defined rule reasoning are performed over multiple ontologies. We propose an effective data organization method that uniformly organizes both original ontologies and inferred results for ontology and user-defined rule reasoning, with the support of named graph. Inspired by the Rete algorithm, we design an inference network to link the ontology data, inferred results, and intermediate inferred results. As a consequence, when the ontology data update, changes can be effectively propagated in the network based on their named graphs. We implement the proposed approach on our previous ontology store and the experimental results show that our solution can significantly improve the reasoning performance when ontology data update happens.