Knowledge recommendation for product development using integrated rough set-information entropy correction

New product development is knowledge intensive as it needs the work teams and design engineers located at various locations to constantly share, update, and re-use knowledge. As such, improving the efficiency of acquiring knowledge and coping with the challenge of frequently retrieving related knowledge have become a key factor to managing knowledge in new product development. This paper combines rough set theory and information entropy to establish a new knowledge recommender technique to address the issue of knowledge reuse for new product development. Our method enhances knowledge acquisition and reuse, as it provides a realistic framework for knowledge acquisition and reuse, encompassing the entire process from what the design and work teams need, to recommending what they should have. To validate the proposed approach, we perform experiments on a case study to demonstrate the benefit and performance.