This page would look a lot spiffier if you downloaded a standards compliant web browser.
Precedents are commonly used as a means of investigation and inspiration in architectural design. Designers often refer to past solutions when they are confronted with a similar problem context. This offers a promising application domain for recent research in AI that introduces the technique of case-base reasoning (CBR) to the design domain. The computational support in a case based design (CBD) system involves the recall and re-use of past solutions in new problem situations.
An efficient indexing of past solutions is crucial to computational design
systems performing complex retrieval on large case-bases. This research suggests an hybrid approach to the indexing and retrieval of design precedents. The suggested approach accounts for the issues of classification manifested in architectural discussions on type and CBD literature. The indexing scheme integrates description-logic based representation for classification and an object-based representation for precedents. The hybrid scheme constitutes a basis for the implementation of a generic case indexing and retrieval mechanism for SEED: a Software Environment to support the Early phases of building Design. The suggested classification and case-base functionalities are supported by two distinct engines: SEED-KBC (SEED - Classification Knowledge-Base) and SEED-CBD (SEED - Design Case-Base), and accessed through engine specific APIs.