创造力
建筑
过程(计算)
计算机科学
人工智能
领域(数学)
工程设计过程
概念设计
航程(航空)
人机交互
软件工程
数据科学
工程类
视觉艺术
艺术
操作系统
法学
政治学
纯数学
航空航天工程
数学
机械工程
标识
DOI:10.1016/j.jobe.2023.107999
摘要
The field of artificial intelligence has introduced a groundbreaking process called text-to-image generation, which allows humans to visualize ideas in new ways. This study suggests that architects and designers can utilize these tools in conceptual design to enhance their creativity. AI provides designers with fresh perspectives and opens up new possibilities for design concepts. These tools also allow for easier manipulation of data and the development of innovative solutions to complex problems, expanding the designer's range of creative abilities beyond traditional methods. We are examining the application of usage-based models to different activities, exploring the suitability of DALL-E 2, Midjourney, and StableDi platforms for typical examples in architectural design. By using NLP techniques to extract typical usage patterns from a data collection of 40 million Midjourney inquiries, we can analyze these patterns and how they are currently being used. We examined architectural glossaries to identify keywords related to architecture. We only included keywords that appeared at least 10 % of the time, and the names of 941 famous architects from Wikipedia were added to the keyword list. This allowed us to identify 2.6 million searches (6.8 %) that potentially had an architectural intention, including 1 million (2.6 %) that specifically mentioned "architect", "interior", or "exterior" design. Our filters ensured the accuracy of our findings. Conclusions, the use of technology can greatly enhance the engineering design process. Architects and other creatives find it particularly exciting and useful due to its user-friendly interface and ability to generate a wide range of images.
科研通智能强力驱动
Strongly Powered by AbleSci AI