An official website of the United States government
Design-by-analogy (DbA) is an important method for innovation that has gained much attention due to its history of leading to successful and novel design solutions. The method uses a repository of existing design solutions where designers can recognize and retrieve analogical inspirations. Yet, exploring for analogical inspiration has been a laborious task for designers. This work presents a computational methodology that is driven by a topic modeling technique called non-negative matrix factorization (NMF). NMF is widely used in the text mining field for its ability to discover topics within documents based on their semantic content. In the proposed methodology, NMF is performed iteratively to build hierarchical repositories of design solutions, with which designers can explore clusters of analogical stimuli. This methodology has been applied to a repository of mechanical design-related patents, processed to contain only component-, behavior-, or material-based content to test if unique and valuable attribute-based analogical inspiration can be discovered from the different representations of patent data. The hierarchical repositories have been visualized, and a case study has been conducted to test the effectiveness of the analogical retrieval process of the proposed methodology. Overall, this paper demonstrates that the exploration-based computational methodology may provide designers an enhanced control over design repositories to retrieve analogical inspiration for DbA practice.
more »
« less
Approaches for Supporting Exploration for Analogical Inspiration With Behavior, Material and Component Based Structural Representations of Patent Databases
This paper presents an explorative-based computational methodology to aid the analogical retrieval process in design-by-analogy practice. The computational methodology, driven by Nonnegative Matrix Factorization (NMF), iteratively builds a hierarchical repositories of design solutions within which clusters of design analogies can be explored by designers. In the work, the methodology has been applied on a large repository of mechanical design related patents, processed to contain only component-, behavior-, or material-based content, to demonstrate that unique and valuable attribute-based analogical inspiration can be discovered from different representations of patent data. For explorative purposes, the hierarchical repositories have been visualized with a three-dimensional hierarchical structure and two-dimensional bar graph structure, which can be used interchangeably for retrieving analogies. This paper demonstrates that the explorative-based computational methodology provides designers an enhanced control over design repositories, empowering them to retrieve analogical inspiration for design-by-analogy practice.
more »
« less
- Award ID(s):
- 1663204
- PAR ID:
- 10088046
- Date Published:
- Journal Name:
- ASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference Volume 2A: 44th Design Automation Conference
- Volume:
- 2A
- Page Range / eLocation ID:
- V02AT03A017
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
One means to support for design-by-analogy (DbA) in practice involves giving designers efficient access to source analogies as inspiration to solve problems. The patent database has been used for many DbA support efforts, as it is a preexisting repository of catalogued technology. Latent Semantic Analysis (LSA) has been shown to be an effective computational text processing method for extracting meaningful similarities between patents for useful functional exploration during DbA. However, this has only been shown to be useful at a small-scale (100 patents). Considering the vastness of the patent database and realistic exploration at a large scale, it is important to consider how these computational analyses change with orders of magnitude more data. We present analysis of 1,000 random mechanical patents, comparing the ability of LSA to Latent Dirichlet Allocation (LDA) to categorize patents into meaningful groups. Resulting implications for large(r) scale data mining of patents for DbA support are detailed.more » « less
-
ABSTRACT Analogy is a powerful tool for fostering conceptual understanding and transfer in STEM and other fields. Well‐constructed analogical comparisons focus attention on the causal‐relational structure of STEM concepts, and provide a powerful capability to draw inferences based on a well‐understood source domain that can be applied to a novel target domain. However, analogy must be applied with consideration to students' prior knowledge and cognitive resources. We briefly review theoretical and empirical support for incorporating analogy into education, and recommend five general principles to guide its application so as to maximize the potential benefits. For analogies to be effective, instructors should use well‐understood source analogs and explain correspondences fully; use visuospatial and verbal supports to emphasize shared structure among analogs; discuss the alignment between semantic and formal representations; reduce extraneous cognitive load imposed by analogical comparison; and encourage generation of inferences when students have some proficiency with the material. These principles can be applied flexibly to topics in a wide variety of domains.more » « less
-
Fitch, T.; Lamm, C.; Leder, H.; Teßmar-Raible, K. (Ed.)Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of analogs? We address this question by comparing human performance on visual analogies created using images of familiar three-dimensional objects (cars and their subregions) with the performance of alternative computational models. Human reasoners achieved above-chance accuracy for all problem types, but made more errors in several conditions (e.g., when relevant subregions were occluded). We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations. The compositional model based on part representations, but not the deep learning models, generated qualitative performance similar to that of human reasoners.more » « less
-
Using analogies is a standard practice for both teaching and communicating ideas in science. Here we upend the traditional lesson, where the instructor provides a fully constructed analogy and explains it, by having the students develop a complex analogy themselves. This high engagement, peer learning activity engages students in critical thinking and analogical reasoning to foster deeper understanding of molecular processes and their interconnection. In this lesson, groups of students are asked to relate given items to DNA and to decide which level it best represents (nucleotide, gene, chromosome, or genome). Next they are tasked with extending the analogy to include other actors in the central dogma of molecular biology (RNA, protein, polymerases, ribosomes, etc.), and then to extend it even further (introns/exons, mutations, evolution, etc.). Finally, each group presents their analogy to the class, and they evaluate each other. We provide multiple examples of items that can be used in the activity, but others can be identified with some creativity. This exercise is also an excellent tool for instructors to discover where their students have gaps and need help making connections to bridge their understanding of processes in molecular biology.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1115/DETC2018-85591
