PurposeAncient Chinese architecture is famous for its wooden frame structure and unique position in world architecture history. As numerous types of components and complex combinations exist, the overall structural system and how they are interlocked have always been crucial but challenging parts of the study. Students find it hard to understand and remember the concepts using traditional 2D paper media, making such knowledge unattractive to pass on to the new generation. To overcome the challenges, this research aims to examine the effect of combining Virtual Reality (VR) with digital interaction games in learning structural characteristics (dougong) of ancient Chinese architecture.Design/methodology/approachThis research develops an interactive cognitive system in the VR environment based on constructivist theory to improve the learning approach of ancient Chinese architecture. Applying an experimental procedure, the feedback of an experimental group using the VR cognition system and a control group using traditional learning 2D media are collected to examine the differences in learning effectiveness and user experience.FindingsThis study develops an interactive cognitive system to aid in learning the structural system of ancient Chinese architecture. The results indicate that integrating VR and interactive learning games can increase students' positive attitudes and learning effectiveness towards ancient Chinese architecture.Originality/valueThis study integrates VR technology and interactive games to improve the learning approach. It examines the effect of applying the concept of human–computer interaction in learning ancient Chinese buildings. The concept of designing the interactive cognitive system is expected to guide students gradually to be the main body of learning and stimulate their learning enthusiasm and motivation.

Existing methods for generating 2D plans based on intelligent systems usually require human-defined rules, and their operations are complex. GANs can solve these problems through independent research and learning. However, they only have generative design research based on a single constraint condition, and whether they can generate a qualified design scheme under many constraints is still unclear. Therefore, this paper develops the M-StruGAN generative model based on the structural design framework of a GAN. Its application research is extended to the 2D-plan layout generation of homestay based on the constraints of hybrid structures, and the feasibility of the method is comprehensively verified through three aspects: image synthesis quality assessment, scheme rationality assessment, and scheme design quality assessment. Experimental results show that the quality of the drawings generated by M-StruGAN is qualified, designers have a high degree of acceptance of the design results of M-StruGAN, and M-StruGAN completed the learning of the critical points of the 2D layout. Finally, through the human–computer interaction application of M-StruGAN, it can be found that compared with traditional design methods, M-StruGAN based on pix2pixHD has high-definition image quality, higher design efficiency, lower design cost, and more stable design quality.

No abstract

No abstract

No abstract