In the book Prolog Programming for Artificial Intelligence, a large and intricate chapter (chapter 14) is dedicated to Expert Systems. In these systems, a knowledge-database is represented through facts and rules in a declarative manner, and then we use the PROLOG inference engine to derive statements and decisions.

I was wondering: are there any examples of expert systems that represent knowledge through a standard Relational Database approach and then extract facts through SQL queries? Is there any research in this area? If not, why is a rule-based approach preferred?


A recent research example is the "Grind" system. Take a look at the paper Computing FO-Rewritings in $\mathcal{E} \mathcal{L}$ in Practice: from Atomic to Conjunctive Queries (2018) by Peter Hansen and Carsten Lutz. Here's the abstract.

A prominent approach to implementing ontology-mediated queries (OMQs) is to rewrite into a first-order query, which is then executed using a conventional SQL database system. We consider the case where the ontology is formulated in the description logic $\mathcal{E} \mathcal{L}$ and the actual query is a conjunctive query and show that rewritings of such OMQs can be efficiently computed in practice, in a sound and complete way. Our approach combines a reduction with a decomposed backwards chaining algorithm for OMQs that are based on the simpler atomic queries, also illuminating the relationship between first-order rewritings of OMQs based on conjunctive and on atomic queries. Experiments with real-world ontologies show promising results.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.