城市规划学刊Issue(1)：55-63,9.DOI:10.16361/j.upf.202501008
大模型的专业学习:构建融入城市空间形态设计知识的图像生成模型
Domain-specific Learning for Large Models:Integrating Urban Spatial Form Design Knowledge into Image Generation Model
摘要
Abstract
The primary challenge in developing a domain-specific large model based on a general large model lies in effectively integrating domain-specific knowledge into the general large model.There is a significant amount of tacit knowledge in ur-ban spatial form design,and the public policy nature of urban planning necessitates the efficient communication of tacit knowledge to the public.Leveraging the unique ability of large model to learn and transfer tacit knowledge,this paper proposes a technical framework for integrating urban spatial form design knowledge into general image generation models through domain-specific learning.Tacit and explicit knowl-edge in spatial form design with design orientation constitutes the core components to guide the domain-specific learning of large models.The integration of urban spa-tial form design knowledge into a general image generation model is accomplished through the application of large model fine-tuning techniques.Using community pub-lic space renewal as a case study,a domain-specific large model incorporating the knowledge of urban spatial form design is constructed.The case shows that the domain-specific large model plays a crucial role in effectively transferring tacit knowledge,enhancing communication efficiency in community renewal,and support-ing participatory design processes.关键词
规划专业大模型/空间形态设计知识/隐性知识/图像生成模型/大模型微调/社区公共空间更新Key words
domain-specific large model for urban planning/spatial form design knowledge/tacit knowledge/im-age generation model/large model fine-tuning/community public space renewal分类
土木建筑引用本文复制引用
钮心毅,刘思涵,桑田,顾睿星,吴雪菲,王桨..大模型的专业学习:构建融入城市空间形态设计知识的图像生成模型[J].城市规划学刊,2025,(1):55-63,9.基金项目
国家重点研发计划课题"国土空间多场景综合效能评价与调控关键技术"(项目编号2022YFC3800804) （项目编号2022YFC3800804）
