Semantic data models for database systems provide powerful tools to assist database administrators in designing and maintaining schemas, but provide little or no direct support for users of the database. Some research has been done on mapping user models of a domain to the underlying database using semantic schemas. Little has been done, however, on mapping conceptually meaningful data structures to a database lacking a semantic schema, or to a multi-database system that lacks a consistent semantic schema. We argue for the appropriateness of a knowledge representation language as a language for describing the database schema, user data structures, and the mapping between them; present a problem domain in which an existing relational database without a semantic schema must be accessed by a knowledge-based application; and describe our implementation of a system that provides access to a relational database from a KL-ONEstyle knowledge representation language. 1 Introduction The integra...

The evolution of database systems tends to the development of higher degree of user-friendliness such that the system can be directly handled by nonprofessionals. In order to reach this goal, the database system needs to provide a query language by which queries can be speci ed conceptually. Also, the query condition may be relaxed such that information within a certain semantic distance to the exact answer can be obtained. Moreover, the real-world information is usually imprecise and incomplete. It is therefore important to store imprecise and incomplete information in a database, and to manipulate this information accordingly. In this paper, we provide a conceptual query language by which fuzzy query conditions and neighborhood query conditions can be speci ed. Query processing strategies for these two query conditions are proposed considering imprecise and incomplete information. A domain concept hierarchy is constructed ontopofanumerical domain to handle imprecise data, while dependencies between database attributes are derived for incomplete information. An application of the techniques for processing queries under network partitioning is also discussed. 1