There are several purposes for modeling and analyzing the problem domain before starting the software requirements analysis. First, it focuses on the problem domain, so that the domain users could be involved easily. Secondly, a comprehensive description on the problem domain will advantage getting a comprehensive software requirements model. This paper proposes an ontology-based approach for mod- eling the problem domain. It interacts with the domain users by using terminology that they can under- stand and guides them to provide the relevant information. A multiple paradigm analysis approach, with the basis of the description on the problem domain, has also been presented. Three criteria, i.e. the ra- tionality of organization structure, the achievability of organization goals, and the feasibility of organiza- tion process, have been proposed. The results of the analysis could be used as feedbacks for guiding the domain users to provide further information on the problem domain. And those models on the problem domain could be a kind of document for the pre-requirements analysis phase. They also will be the basis for further software requirements modeling.
Knowledge engineering stems from E. A. Figenbaum＇s proposal in 1977, but it will enter a new decade with the new challenges. This paper first summarizes three knowledge engineering experiments we have undertaken to show possibility of separating knowledge development from intelligent software development. We call it the ICAX mode of intelligent application software generation. The key of this mode is to generate knowledge base, which is the source of intelligence of ICAX software, independently and parallel to intelligent software development. That gives birth to a new and more general concept ＂knowware＂. Knowware is a commercialized knowledge module with documentation and intellectual property, which is computer operable, but free of any built-in control mechanism, meeting some industrial standards and embeddable in software/hardware. The process of development, application and management of knowware is called knowware engineering. Two different knowware life cycle models are discussed： the furnace model and the crystallization model. Knowledge middleware is a class of software functioning in all aspects of knowware life cycle models. Finally, this paper also presents some examples of building knowware in the domain of information system engineering.
