The Enterprise Ontologist reverse engineers data models to accelerate design the Enterprise Ontology and Data Scientists use the ontology to data model mapping building the knowledge graph. The left-hand side shows institution-level applications of the use case. The ontologist can focus on the value-added work of revising the design, adding Defined Classes, complex class restrictions, beyond the Entity/Relationship model, and hence beyond CODT reverse-engineering.
Just like FIB-DM saves manual work of entering ontology-derived data model objects into the modeling tool, the reverse-engineered ontology provides a starting point of data model-derived classes and properties. The UML diagram depicts the CODT system with the primary use case to reverse-engineer a data model into an ontology. We load in triples into the ontology platform, using SPARQL CONSTRUCT or bulk insert. Power Queries and formulas break the data set down into triples.
This final installment examines the reverse transformation. The second article showed that the " Ontology Class- and Data Model Entity-hierarchy" are the same, and the third states that " Object Properties are Associative Entities."
The first FIB-DM article, " Finance Ontology transformed into an Enterprise Data Model," and the CODT utility patent application state that the transformation technology is bi-directional, but they don't provide the rationale and detail. Published reverse transformation research and tooling address databases - there is no tool or research to reverse-engineer an ontology from PowerDesigner, ERWin, or other data modeling tools. Hence, 900 users downloaded the Open Source version of the Financial Industry Business Data Model (FIB-DM), derived with CODT from the industry-standard domain ontology. While simplified ontology-to-data model mappings have been widely published, there was no tool to transform an ontology into a useful data model. We reverse-engineer databases for which we have no physical model, and we can reverse-engineer data models without having a reference ontology. Note that "reverse" doesn't mean that a higher-level must be pre-existing. Hence, I use the term reverse-engineered for data models transformed into ontologies. Semantic Enterprise Information Architecture (SEIA) places the ontology at the apex with derived, forward-engineered models for data and object. The term reverse-engineering refers to the automated conversion of a database schema into a physical model. Data Architects use the term forward-engineering for transformations of a higher-level logical model into a physical model and subsequently into a database schema. Model transformations migrate a model into another type of model. Finally, for an optimal ontology, we must reverse engineer associative entities into object properties - not classes. I revisit the isomorphism and bi-directional Metadata Sets, central to the Configurable Ontology to Data Model Transformation (CODT). The uses cases are for Knowledge Graphs, Operational and Enterprise Ontologies, benefit from using LDM logical names and subtypes rather than abbreviated database names and foreign keys. This article describes a novel approach transforming Logical Data Models (LDM), rather than database schemas into ontologies.