Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Overload to Insight: Scaffolding Creative Ideation through Structuring Inspiration

Yaqing Yang, Vikram Mohanty, Nikolas Martelaro, Aniket Kittur, Yan-Ying Chen, Matthew K. Hong

TL;DR

Problem: designers face overload of inspiration spaces, hindering insight. Approach: an AI-assisted prototype constructs a mechanism-tree hierarchy from unstructured stimuli and generates analogical cues for cross-domain adaptation using a GPT-based pipeline. Contributions: a hierarchical organization of design stimuli by functional mechanisms, a triplet of analogical cues (diverse cross-domain applications, active ingredients, transfer strategies), and preliminary pilot findings showing improved discovery and adaptation. Findings: hierarchical view improved scanning and novelty discovery; analogical cues supported adaptation, though static transfers limited guidance; suggests interactive LLM refinement as future. Impact: enables scalable ideation tools for design and research.

Abstract

Creative ideation relies on exploring diverse stimuli, but the overwhelming abundance of information often makes it difficult to identify valuable insights or reach the `aha' moment. Traditional methods for accessing design stimuli lack organization and fail to support users in discovering promising opportunities within large idea spaces. In this position paper, we explore how AI can be leveraged to structure, organize, and surface relevant stimuli, guiding users in both exploring idea spaces and mapping insights back to their design challenges.

From Overload to Insight: Scaffolding Creative Ideation through Structuring Inspiration

TL;DR

Problem: designers face overload of inspiration spaces, hindering insight. Approach: an AI-assisted prototype constructs a mechanism-tree hierarchy from unstructured stimuli and generates analogical cues for cross-domain adaptation using a GPT-based pipeline. Contributions: a hierarchical organization of design stimuli by functional mechanisms, a triplet of analogical cues (diverse cross-domain applications, active ingredients, transfer strategies), and preliminary pilot findings showing improved discovery and adaptation. Findings: hierarchical view improved scanning and novelty discovery; analogical cues supported adaptation, though static transfers limited guidance; suggests interactive LLM refinement as future. Impact: enables scalable ideation tools for design and research.

Abstract

Creative ideation relies on exploring diverse stimuli, but the overwhelming abundance of information often makes it difficult to identify valuable insights or reach the `aha' moment. Traditional methods for accessing design stimuli lack organization and fail to support users in discovering promising opportunities within large idea spaces. In this position paper, we explore how AI can be leveraged to structure, organize, and surface relevant stimuli, guiding users in both exploring idea spaces and mapping insights back to their design challenges.

Paper Structure

This paper contains 13 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Prototype Design
  3. Structuring Design Stimuli through Functional Hierarchies
  4. Providing Analogical Cues for Cross-Domain Adaptation
  5. Preliminary Findings
  6. Stimuli of Interest
  7. Familiar yet Feasible Ideas
  8. Previously Overlooked but Relevant Concepts
  9. Novel or Unexpected Ideas
  10. Hierarchical Structure and Analogical Cues
  11. Hierarchical Structure for Efficient Exploration
  12. Analogical Cues for Creative Adaptation
  13. Conclusion

Figures (2)

  • Figure 1: Mechanism Tree for a design task: laundry with less water
  • Figure 2: Examples for the mechanism 'ultrasonic cleaning' for solving the problem: laundry with less water