Object-Oriented Knowledge Representation and Data Storage Using Inhomogeneous Classes
This work addresses data storage and code efficiency issues for developers using object-oriented models, but it appears incremental as it builds on existing class concepts.
The paper tackles the problem of inefficient data storage and code duplication in object-oriented knowledge representation by extending homogeneous classes to single-core and multi-core inhomogeneous classes, which allow multiple types within one class, reducing program code sizes and improving database storage efficiency, with experimental results showing increased efficiency in some cases.
This paper contains analysis of concept of a class within different object-oriented knowledge representation models. The main attention is paid to structure of the class and its efficiency in the context of data storage, using object-relational mapping. The main achievement of the paper is extension of concept of homogeneous class of objects by introducing concepts of single-core and multi-core inhomogeneous classes of objects, which allow simultaneous defining of a few different types within one class of objects, avoiding duplication of properties and methods in representation of types, decreasing sizes of program codes and providing more efficient information storage in the databases. In addition, the paper contains results of experiment, which show that data storage in relational database, using proposed extensions of the class, in some cases is more efficient in contrast to usage of homogeneous classes of objects.