Automated Query Formulation Using an Entity–Relationship Conceptual Schema

Abstract

Significant effort is expended in developing a high–level conceptual schema for a relational database. However, critical knowledge is often discarded when the conceptual schema is mapped to a set of relation schemas. As a result, designers and users must employ sparser logical–level knowledge to access data. Unfortunately, naive users do not possess the detailed logical–level knowledge required to formulate queries corresponding to ad hoc requests. A universal relation interface can shield users from underlying design details. However, most universal relation systems have been based on abstractions not typically used by database designers. Consequently, the usefulness of these interfaces has been limited. This article demonstrates how an Entity–Relationship (ER) conceptual schema can be used by a high–level interface to formulate queries automatically. The notion of contexts is introduced to describe the segmentation of an ER conceptual schema into overlapping subgraphs that correspond to sets of relations that can be joined in a lossless manner. Given a set of contexts, natural join query formulation is straightforward. As demonstrated with a case study using the prototype QUICK system, the techniques presented facilitate the construction of high–level, intelligent interfaces.