Expert representation of design repository space: A comparison to and validation of algorithmic output

• We test an algorithmic method of structuring patent databases for design-by-analogy.
• The method's output is similar to structures generated by design experts.
• Similarity to experts' structures is highest in regions of high expert consensus.
• The experts judge the method's output to be sensible and usable.
• Arranging patents to reflect their interrelatedness is laborious for humans but automatic for the algorithm.

Development of design-by-analogy tools is a promising design innovation research avenue. Previously, a method for computationally structuring patent databases as a basis for an automated design-by-analogy tool was introduced. To demonstrate its strengths and weaknesses, a computationally-generated structure is compared to four expert designers' mental models of the domain. Results indicate that, compared to experts, the computationally-generated structure is sensible in clustering of patents and organization of clusters. The computationally-generated structure represents a space in which experts can find common ground/consensus – making it promising to be intuitive/accessible to broad cohorts of designers. The computational method offers a resource-efficient way of usefully conceptualizing the space that is sensible to expert designers, while maintaining an element of unexpected representation of the space.