Extraction method of design rationale from speech in design processes

Abstract

As products become large-scale and complex, manufacturing industry faces problems in communication between workers. Among the information to be communicated, design rationale, such as reasons for decided design and the process of consideration leading to the decisions, is rarely expressed in shared design data. This paper proposes a information extraction method of design rationale. While design are conducted, conversations are recorded. Recorded sounds are transcribed using the voice input functions in Google Docs. The transcribed data is analyzed by TF/IDF, which evaluates importance of each word in the script by its frequency and rarity. By extracting sentences that contains important words, it is assumed that most design rationales can be depicted. The proposed method was applied to the design of scissors. The case shows that the proposed method has potential for extracting design rationale.

Keywords

• design rationale
• information sharing
• information extraction
• tf/idf
• design experiment
• natural language processing