A semantic-based visualised wiki system (SVWkS) for lesson-learned knowledge reuse situated in product design

Abstract

In the process of product design, engineers usually find it is difficult to precisely find and reuse others’ empirical knowledge resources, especially the lesson-learned knowledge, which is usually not well collected by the organisation. This study proposes a novel approach, which uses a semantic-based visualised wiki system (SVWkS) to support lesson-learned knowledge reuse. The core of visualised knowledge search framework is a semantic-based topic knowledge map. The architecture of this knowledge map creation method is designed, which has five major modules: lesson-learned items pre-processing, topic extraction, topic relation computation, topic weight computation and topic knowledge map generation modules. Then a working scenario of SVWkS is briefly introduced. We have conducted three sets of experiments to evaluate quality of visualised results-knowledge map, the effectiveness of semantic-based visualised searching mechanisms and the performance of utilising SVWkS for knowledge reuse in outfitting design of a ship-building company. The first experiment shows that knowledge maps generated by SVWkS are accepted by domain experts from the evaluation since precision and recall are high. The second experiment shows a semantic-based visualised searching mechanism supported by semantic relations is more useful than a traditional keyword search in terms of precision and recall. The third experiment shows that SVWkS-based group outperforms keyword search-based group in both learning score and satisfaction level, which are two measurements of performance of utilising SVWkS. The promising results confirm the feasibility of SVWkS in helping engineers to find needed lesson-learned knowledge and reuse-related knowledge.

Keywords:

• knowledge management
• knowledge reuse
• knowledge map
• wiki
• semantic
• lesson-learned
• product design

Acknowledgements

The authors would like to thank all the participants for their efforts in our experiments, and also thank professor A. Dolgui and the reviewers for their useful comments.

Additional information

Funding

Funding. The research is supported by National Nature Science Foundation of China [grant number 70971085], [grant number 71271133]; the Research Fund for the Doctoral Programme of Higher Education of China [grant number 20100073110035] and Innovation Programme of Shanghai Municipal Education Commission [grant number 13ZZ012].