Patent-based analogy search tool for innovative concept generation
MetadataShow full item record
Design-by-Analogy is a powerful tool to augment the traditional methods of concept generation and offers avenues to develop innovative and novel design solutions. Few tools exist to assist designers in systematically seeking and identifying analogies from within design repositories such as the United States Patent and Trademark Office patent database. A new tool for extracting functional analogies from patents has been developed to perform this task utilizing a Vector Space Model algorithm to quantitatively evaluate the functional similarity between design problems and patent descriptions of products. Initially, a Boolean Search approach was evaluated and several limitations were identified such as a lack of quantitative metrics for determining search result relevancy ranking as well as inadequate query mapping methods. Next, a Vector Space Model search tool was developed which includes extensive expansion of the Functional Basis using human-based term classification and automated document indexing techniques. The resulting functional patent controlled vocabulary consists of approximately 2,100 unique functions extracted from 65,000 randomly selected patents. The patent search database was generated by indexing 275,000 patents selected from the over 4 million patents available in digital form. A graphical user interface was developed to facilitate query vector generation, and the accompanying search result viewing interface provides data clustering and relevancy ranking. Two case studies are conducted to evaluate the efficacy of the search engine. The first case study successfully replicated the functional similarity results of a classic Design-by-Analogy problem of the guitar pickup winder. The second case study is an original design problem consisting of an automated window washer, and the results illustrate the range of analogically distant solutions that can be extracted ranging from very near-field, literal solutions to the far-field cross domain solutions. Finally, the search tool’s efficacy with regard to increasing quantity and novelty of ideas produced during Concept Generation is experimentally evaluated. The two factors evaluated are first whether analogies improved performance and second how the functionality level of the analogy impacted performance. The experimental results showed an increase in novelty for high functionality analogies compared with the control and other experimental groups. No statistically significant difference was found with regard to quantity of ideas generated.