Published in

Proceeding of the 2nd international workshop on Patent information retrieval - PaIR '09

DOI: 10.1145/1651343.1651358

Links

Tools

Export citation

Search in Google Scholar

A design rationale representation model using patent documents

Proceedings article published in 2009 by Yan Liang, Ying Liu ORCID, Chun Kit Kwong, Wing Bun Lee
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Green circle
Preprint: archiving allowed
Green circle
Postprint: archiving allowed
Red circle
Published version: archiving forbidden
Data provided by SHERPA/RoMEO

Abstract

PaIR 09 - 2nd Workshop on Patent Information Retrieval, Co-located with the 18th ACM International Conference on Information and Knowledge Management, CIKM 2009, Hong Kong, 2-6 November 2009 ; Design rationale (DR) refers to the explanation of why an artifact is designed the way it is. The management of DR in engineering design is an important task since DR is often regarded as crucial information in design decision support, design analysis and design knowledge management. The existing DR systems largely target at manually capturing DRs along design activities. These systems are not only weak in revealing the internal relationships of design components, but also time consuming and they can not extract DR from archival design documents which are usually unstructured or semi-structured texts, such as design changes and test reports. Furthermore, the lack of open accessible DR data has limited the research and spreading of DR systems. In view of such challenges, it has motivated us to propose a new DR model to intelligently discover DR from patent documents since patents are deemed as quality data sources open for public access and they contain rich information about DR, invention details, technology development and so on. Our approach of DR discovery from patents consists of two stages. In the first stage, we propose a novel triple layer DR representation model, i.e. issue layer, design solution layer and artifact layer, to mine DR in a single patent document. The second stage aims to form a DR network based on the salient patent information that is discovered and explicitly represented in the first stage. We then exemplify our representation model using a case study of patents of inkjet printer. Lastly, we briefly discuss some potential applications by taking advantage of our representation model, such as DR reasoning and technology development trend mining. ; Department of Industrial and Systems Engineering