目的 针对AIGC技术在产品设计中存在的需求形式化困难、方案质量不稳定及评估标准不完善等问题,探索构建面向产品的生成式人工智能（AIGC）辅助设计方法论。方法 构建一种基于提示词优化的AIGC辅助产品设计（POA）框架,通过需求分析、概念生成和方案评价的协同迭代提升AIGC辅助设计的质量。首先,基于主成分分析（PCA）的多源数据分析实现设计需求形式化表达,提取外观特征、动力性能等关键主成分;其次,基于对比语言-图像预训练（CLIP）模型构建“基础描述+功能约束+风格定义”的分层提示词架构,通过定向优化与结构化重构提升生成质量;最后,运用改进的属性层次模型-逼近理想解排序法（AHM-TOPSIS）多准则决策方法,建立包含人机工程学、材料选用等多维度量化评估体系。结果 以手持式旋耕机设计为例进行验证,结果表明相较于单纯AIGC方法,本文提出的POA方法在需求分析、概念方案生成和迭代优化等方面表现出显著改进且整体设计周期显著缩短,方案创新性和用户满意度均有所提升。结论 所提出的基于提示词优化的AIGC辅助产品设计方法,通过需求结构化表达、方案优化及多准则决策,实现了AIGC技术在产品设计领域的标准化应用,为人工智能辅助设计提供新的理论框架与技术路径。
Abstract
In response to the challenges of formalizing requirements, unstable solution quality, and incomplete evaluation standards in product design with AIGC technology, the work aims to explore the development of an Artificial Intelligence Generated Content (AIGC)-assisted design method for products. A Prompt-Optimized AIGC Design (POA) framework was constructed, which enhanced the quality of AIGC-assisted design through collaborative iteration across requirement analysis, concept generation, and solution evaluation. Firstly, the multi-source data analysis based on Principal Component Analysis (PCA) was used to formalize design requirements and extract key principal components such as appearance features and dynamic performance. Secondly, a hierarchical prompt word structure ("basic description + functional constraints + style definition") was constructed based on the Contrastive Language-Image Pretraining (CLIP) model, which optimized the generated quality through directional optimization and structural reconstruction. Finally, an improved AHM-TOPSIS multi-criteria decision-making method was applied to establish a multi-dimensional quantitative evaluation system that included ergonomics, material selection, and other factors. With the handheld rotary tiller design as a case study, the results showed that compared to the pure AIGC method, the proposed POA method significantly improved requirement analysis, concept generation, and iterative optimization, while also reducing the overall design cycle. Furthermore, the innovation of solutions and user satisfaction were enhanced. The proposed Prompt-Optimized AIGC Design method standardizes the application of AIGC technology in product design through structured requirement expression, solution optimization, and multi-criteria decision-making evaluation, providing a new theoretical framework and technical pathway for the AI-assisted design.
关键词
生成式人工智能（AIGC） /
提示词优化 /
CLIP对比语言-图像预训练模型 /
手持式旋耕机
Key words
Artificial Intelligence Generated Content (AIGC) /
Prompt Word Optimization (PWO) /
Contrastive Language-Image Pretraining (CLIP) /
handheld rotary tiller (HRT)
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HO J, CHAN W, SAHARIA C, et al.Imagen Video: High Definition Video Generation with Diffusion Models[J]. Arxiv Preprint Arxiv, 2022: 2303.
[2] CHAMBON P, BLUETHGEN C, LANGLOTZ C P, et al.Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains[J]. Arxiv Preprint Arxiv, 2022, 2022: 2210.
[3] RAMESH A, DHARIWAL P, NICHOL A, et al.Hierarchical Text-Conditional Image Generation with Clip Latents[J]. Arxiv Preprint Arxiv, 2022, 1(2): 3.
[4] 卢裕弘, 封颖超杰, 朱琳, 等. PromptVis: 面向文本生成图片的提示词的交互式可视分析方法[J]. 计算机辅助设计与图形学学报, 2025, 37(4): 687-696.
LU Y H, FENG Y C J, ZHU L, et al. PromptVis: An interactive visual analysis method for prompt words for text-generated images[J]. Journal of Computer-Aided Design and Graphics, , 2025, 37(4): 687-696.
[5] 路鹏, 吴凡, 唐建. 基于人工智能生成内容的产品造型设计与评价方法[J]. 图学学报, 2024, 45(6): 1277-1288.
LU P, WU F, TANG J.Product Design and Evaluation Methods Based on AI-Generated Content[J]. Journal of Graphics, 2024, 45(6): 1277-1288.
[6] JIANG Z B, XU F F, ARAKI J, et al.How Can we Know What Language Models Know?[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 423-438.
[7] LIU V, CHILTON L B.Design Guidelines for Prompt Engineering Text-to-Image Generative Models[C]//CHI Conference on Human Factors in Computing Systems. New Orleans: ACM, 2022: 1-23.
[8] WU T S, JIANG E, DONSBACH A, et al.PromptChainer: Chaining Large Language Model Prompts through Visual Programming[C]//CHI Conference on Human Factors in Computing Systems Extended Abstracts. New Orleans: ACM, 2022: 1-10.
[9] ROMBACH R, BLATTMANN A, LORENZ D, et al.High-Resolution Image Synthesis with Latent Diffusion Models[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022: 10674-10685.
[10] BERTUCCI D, HAMID M M, ANAND Y, et al.DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps[J]. IEEE Trans Vis Comput Graph, 2023, 29(1): 320-330.
[11] SHIN T, RAZEGHI Y, LOGAN R L, et al.AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online. Stroudsburg: USAACL, 2020: 4222-4235.
[12] Gao T, Fisch A, Chen D, et al.Making Pre-Trained Language Models Better Few-Shot Learners[C]//Proceedings of ACL/IJCNLP, Stroudsburg: ACL, 2021: 3816-3830.
[13] STROBELT H, WEBSON A, SANH V, et al.Interactive and Visual Prompt Engineering for Ad-Hoc Task Adaptation with Large Language Models[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(1): 1146-1156.
[14] WANG Y L, SHEN S Y, LIM B Y.RePrompt: Automatic Prompt Editing to Refine AI-Generative Art towards Precise Expressions[C]//Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. Hamburg: ACM, 2023.
[15] LIU V, QIAO H, CHILTON L.Opal: Multimodal Image Generation for News Illustration[C]//Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology. Bend: ACM, 2022: 23.
[16] WONG K K, WANG X B, WANG Y, et al.Anchorage: Visual Analysis of Satisfaction in Customer Service Videos via Anchor Events[J]. IEEE Transactions on Visualization and Computer Graphics, 2024, 30(7): 4008-4022.
[17] ZENG H P, WANG X B, WANG Y, et al.GestureLens: Visual Analysis of Gestures in Presentation Videos[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(8): 3685-3697.
[18] YANG J, FAN J P, HUBBALL D, et al.Semantic Image Browser: Bridging Information Visualization with Automated Intelligent Image Analysis[C] //2006 IEEE Symposium on Visual Analytics Science and Technology. Baltimore: IEEE, 2006: 191-198.
[19] XIE X, CAI X W, ZHOU J P, et al.A Semantic-Based Method for Visualizing Large Image Collections[J]. IEEE Transactions on Visualization and Computer Graphics, 2019, 25(7): 2362-2377.
[20] CHEN C J, WU J, WANG X H, et al.Towards Better Caption Supervision for Object Detection[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 28(4): 1941-1954.
[21] 尹虎, 殷莹熙彤, 陈殿生, 等. 基于AIGC协同工业设计流程的气道廓清辅具设计研究与实践[J]. 包装工程, 2024, 45(16): 51-65.
YIN H, YIN Y, CHEN D S, et al.Research and Practice of Airway Clearance Assistive Device Design Based on AIGC Collaborative Industrial Design Process[J]. Packaging Engineering, 2024, 45(16): 51-65.
[22] 吕金阳, 黄剑波, 罗帆. 程式化下的创新: AIGC人机合作式环境空间创意设计表达[J]. 家具与室内装饰, 2024, 31(4): 126-131.
LYU J Y, HUANG J B, LUO F.Innovation under Programmatization: AIGC Human Machine Collaborative Environmental Space Creative Design Expression[J]. Furniture & Interior Design, 2024, 31(4): 126-131.
[23] 罗婷, 郑冬琴. 基于人工智能的传统手工艺彝族刺绣艺术设计融合创新研究[J]. 家具与室内装饰, 2024, 31(8): 17-23.
LUO T, ZHENG D Q.Research on the Integration and Innovation of Traditional HaLnudo iTcirnagf & t Zheng DongqinYi Embroidery Art Design Based on Artificial Intelligence[J]. Furniture & Interior Design, 2024, 31(8): 17-23.
[24] 汪皓, 李雪莲. 针对软体家具领域的AIGC辅助设计路径优化研究[J]. 家具与室内装饰, 2024, 31(6): 56-61.
WANG H, LI X L.Optimization of AI-Assisted Design Process in the Field of Soft Furniture Design[J]. Furniture & Interior Design, 2024, 31(6): 56-61.
[25] 牛晓霆, 刘祥源. 基于AIGC技术下圈椅数字化修复应用研究[J]. 家具与室内装饰, 2025, 32(3): 9-15.
NIU X T, LIU X Y.Research on the Digital Restoration and Application of Circle Chairs Based on AIGC Technology[J]. Furniture & Interior Design, 2025, 32(3): 9-15.
[26] 缪翌, 张卫锋, 徐领. 基于CLIP的视频时刻检索预训练模型[J]. 计算机应用研究, 2024, 41(12): 3866-3872.
MIAO Y, ZHANG W F, XU L.Pre-Training Model for Video Moment Retrieval Based on CLIP[J]. Application Research of Computers, 2024, 41(12): 3866-3872.
[27] WANG J, CHAN K C K, LOY C C. Exploring CLIP for Assessing the Look and Feel of Images[C]//Proceedings of the Thirty Seventh AAAI Conference on Artificial Intelligence and Thirty Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence, Palo Alto: AAAI Press, 2023: 2555-2563
[28] 李玲燕, 顾昊. 基于AHM-可拓评价模型的老旧小区绿色改造综合效益评价研究[J]. 生态经济, 2021, 37(3): 95-100.
LI L Y, GU H.Study on Comprehensive Benefit Evaluation of Green Transformation in Old Residential Areas Based on AHM-Extension Evaluation Model[J]. Ecological Economy, 2021, 37(3): 95-100.
[29] 李海君, 徐廷学, 应新永. 基于测试数据与扩展TOPSIS-灰色关联的导弹状态评估决策[J]. 航空兵器, 2021, 28(6): 88-94.
LI H J, XU T X, YING X Y.Missile Condition Assessment Decision Based on Test Data and Extended TOPSIS-Grey Correlation[J]. Aero Weaponry, 2021, 28(6): 88-94.
[30] 杨展华, 许成, 胡继鹏, 等. 基于熵值-TOPSIS法的国有企业内部经济责任审计评价体系研究[J]. 中国内部审计, 2021(2): 18-26.
YANG Z H, XU C, HU J P, et al.Research on Audit Evaluation System of Internal Economic Responsibility of State-Owned Enterprises Based on Entropy -TOPSIS Method[J]. Internal Auditing in China, 2021(2): 18-26.
基金
湖南省社会科学成果评审委员会重点课题（XSP22ZDI001）
PDF(5865 KB)
渝公网安备 50010702501717号