Reproduce “Supporting Assessment of Novelty of Design Problems Using Concept of Problem SAPPhIRE” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sanjay Singh, Amaresh Chakrabarti
Researchers from IISc Bangalore developed an automated framework to assess the novelty of design problems by representing them as "Problem SAPPhIREs" and comparing them against historical records using BERT semantic similarity and word-vector cosine distance. A case study on electric kettles demonstrated the framework's ability to classify current problems into varying degrees of novelty, with one problem consistently scoring 0.7 for high novelty.
Key insights
- The SAPPhIRE model of causality, traditionally used for products, can be effectively adapted to represent and compare design problems ("Problem SAPPhIREs").
- Assessing problem novelty at the early "task clarification stage" is crucial for strategic resource allocation and fostering greater design creativity.
- Automated textual similarity methods, like BERT and word-vectors, enable objective and scalable novelty assessment, overcoming limitations of manual evaluations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.