Second Guessing: Designer Classification of Problem Definition Fragments

Abstract

Engineering designers progressively develop their own understanding of ill-defined problems through a process of abstraction, decomposition, completion, enhancement, classification and conflict resolution. We have developed a computational aid to support problem formulation in which designers input problem definition fragments into different categories as free form text. We used natural language processing to determine if designers had misplaced problem fragments in inappropriate categories. In this paper, we present our work on how this problem can be addressed by looking for keywords in design descriptions and extracting knowledge from text ontologies using these keywords. We collected data from a group of students who used the Problem Formulator testbed to express their understanding of the given design problem. For each of the six categories in the Problem Formulator ontology, we identified classes using existing ontologies and tools that closely define them. In our method, we first parsed the user inputs to extract the keywords depending on the category in which they were entered. We then associated these keywords to the previously identified classes and categorized them into the correct category.