Structural Similarity and Adaptation

Most commonly, case-based reasoning is applied in domains where attribute value representations of cases are su cient to represent the features relevant to support classi cation, diagnosis or design tasks. Distance functions like the Hamming-distance or their transformation into similarity functions are applied to retrieve past cases to be used to generate the solution of an actual problem. Often, domain knowledge is available to adapt past solutions to new problems or to evaluate solutions. However, there are domains like architectural design or law in which structural case representations and corresponding structural similarity functions are needed. Often, the acquisition of adaptation knowledge seems to be impossible or rather requires an e ort that is not manageable for elded applications. Despite of this, humans use cases as the main source to generate adapted solutions. How to achieve this computationally? This paper presents a general approach to structural similarity assessment and adaptation. The approach allows to explore structural case representations and limited domain knowledge to support design tasks. It is exemplarily instantiated in three modules of the design assistant FABEL-Idea that generates adapted design solutions on the basis of prior CAD layouts.