Authors - NamUook, Kim, Gihwan Bong, Yoon Seok, Chang Abstract - The heterogeneity of data sources makes the design of traditional da ta ware-houses complex and time-consuming. Indeed, the data warehouse system must process structured, semi-structured, and unstructured sources. To over-come this challenge, we propose an interactive approach to data ware house design based on a federated ontology. The ontology serves as a unified conceptual layer that integrates heterogeneous data sources and facilitates the building of the data warehouse. Our approach allows decision-makers to in teractively select the subdomain of the federated ontology according to their needs and generate their data warehouse. The generation of the data ware-house in the constellation schema is automated using algorithms. It also ensures the maintenance of the data warehouse to take into account various changes in data and decision-makers' needs. The proposed methodology is summarized through architectures defined at each stage, each addressing a specific challenge. At the ontology construction level, it resolves issues related to data heterogeneity while enabling interoperability among multiple do-main ontologies. It also provides a complete scenario for the decision-maker to assist in the full construction of a data warehouse from an ontology. Finally, it facilitates querying the constructed data warehouse using requests ex-pressed by the decision-maker in natural language.
Open Zoom