生成设计
生成语法
计算机科学
创造力
代表(政治)
形成性评价
过程(计算)
产品(数学)
外化
工程设计过程
介绍(产科)
设计过程
人机交互
人工智能
在制品
工程类
数学教育
程序设计语言
数学
心理学
运营管理
公制(单位)
精神分析
法学
社会心理学
几何学
政治学
放射科
机械工程
医学
政治
作者
Jiayi Yao,Pei Chen,Zhuoshu Li,Yu‐Dong Cai,Yexinrui Wu,Weitao You,Lingyun Sun
摘要
Abstract In product conceptual design, designers utilize multiple design representations to iteratively ideate, externalize, and refine concepts. Mixed representations, defined as the simultaneous presentation of multiple representations, foster deeper insights and facilitate broader exploration compared to focusing on a single representation. However, designers often struggle with the cumbersome process of creating, transforming, and refining these representations. Advanced AI capabilities now significantly lower the barriers to creating text, images, and 3D models, presenting substantial potential for application in design practice. However, current design tools based on generative AI tend to produce polished product images directly, hindering designers from continuously deliberating on mixed representations, and thus limiting their creative potential. Therefore, based on a formative study, we propose StepIdeator, a step-by-step design tool driven by generative AI. This tool facilitates seamless transition and refinement of mixed design representations. Through a comparative study (N=16), we validated StepIdeator's effectiveness in improving idea externalization and enhancing creativity. Furthermore, the results revealed that designers perceived greater confidence, ownership, and sense of contribution when collaborating with StepIdeator.
科研通智能强力驱动
Strongly Powered by AbleSci AI