A computational tool for creative idea generation based on analogical reasoning and ontology. Issue 4 (5th October 2018)

• Record Type: Journal Article
• Authors: Han, Ji; Shi, Feng; Chen, Liuqing; Childs, Peter R.N.
• Editors: Fu, Katherine; Fuge, Mark; Brown, David
• Is Part Of: AI EDAM. Volume 32:Issue 4(2018)
• Page Start: 462
• Page End: 477
• Publication Date: 2018-10-05
• Subjects: Analogy, -- creativity, -- design creativity, -- ideation, -- ontology; Engineering design -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; 620.00420285
• DOI: 10.1017/S0890060418000082
• Languages: English
• ISSNs: 0890-0604

Abstract

Abstract: Analogy is a core cognition process used to produce inferences as well as new ideas using previous knowledge and experience. Ontology is a formal representation of a set of domain concepts and their relationships. The use of analogy and ontology in design activities to support design creativity have previously been explored. This paper explores an approach to construct ontologies with sufficient richness and coverage to support reasoning over real-world datasets for prompting creative idea generation. This approach has been implemented into a computational tool for assisting designers in generating creative ideas during the early stages of design. The tool, called "the Retriever", has been developed based on ontology by embracing the aspects of analogical reasoning. A case study has indicated that the tool can be effective and useful for idea generation. The results have indicated that the tool, in its current formulation, can significantly improve the fluency and flexibility of idea generation and the usefulness of ideas, as well as slightly increase the originality of ideas, for the case study concerned.