Context-aware cognitive design assistant: Implementation and study of design rules recommendations

Design rules are an essential interface to facilitate the information exchange between designers and experts. Despite many innovations in Knowledge-Based Engineering Knowledge Management, unstructured design documents still widely used manufacturing industry. Due complexity of process, these often contain hundreds rules, applicable varying contexts. Searching for right according a context is demanding time cognitive resources. In this paper, we propose Context-Aware Cognitive Assistant (CACDA) capture perform tasks such as recommendation verification solutions, or automation routines. Contrary existing works model quality testing, CACDA uses proactive approach application helps provide error-free designs on first attempt. present system CACDA, its capabilities implementation. Then, measure impact recommendations compare our with use traditional documents. Results show that CACDA’s lower perceived difficulty retrieval from 75 43.5 scale 100. On average, participants demonstrator successfully applied 8.6 25 set. Participants documentation correctly 4.3 rules. The global weight activity well performances appear be unchanged. These results demonstrate usability positive process CAD models. Future will focus overcome main limitations current experiments, panel professional designers, lager set implementation several lacking features into demonstrator.