In the early stages of product design, generating creative ideas is crucial for designers as it lays the groundwork for innovative products. This study explores how different idea generation methods, including modern artificial intelligence-generated content (AIGC) and traditional approaches, affect designers' creativity. Using a mixed-methods approach, we conducted a detailed experiment with 38 s-year university students majoring in product design, comparing four methods: traditional brainstorming (with and without images) and AIGC (using DCGANs and PGGANs). Our findings indicate that while AIGC offers benefits, it does not consistently surpass traditional techniques in fostering creativity. The quality of AIGC-generated images significantly impacts creativity, with higher-quality images proving more inspirational. Additionally, gender differences were observed: male designers preferred traditional methods, while female designers favored AIGC for creative enhancement. Male designers generated more creative ideas when working with low-quality images, whereas female designers were more productive with high-quality stimuli. This study suggests that to optimize creativity in product design, it is essential to balance the benefits of both AIGC and traditional methods, choosing the approach that best fits the project's unique needs rather than focusing solely on the latest or most advanced methods. Moreover, maintaining a good balance between AIGC and traditional idea generation methods throughout the process should be considered.
Collaborative problem-solving (CPS) has become essential in today's society because it provides opportunities for deep learning and critical thinking. During CPS, students tend to spontaneously adopt different roles that facilitate the interactive process. Previous studies have focused on the influence of emergent roles on learning outcomes and CPS skills, but have rarely used procedural approaches to analyze the diversity of and changes in emergent roles during CPS. The availability of naturally occurring educational discourse data provides the opportunity to identify emergent roles at a fine-grained level. Therefore, this study identified emergent roles based on fine-grained coding and used hierarchical regression and epistemic network analysis to explore the influence of emergent roles on learning outcomes through CPS activities and their co-occurrence with CPS skills. The identification of emergent roles was based on observations of 54 undergraduates and postgraduates. The results showed that the participants played different, flexible roles during the CPS process. Roles focused on content and performance appeared more frequently, while those related to social emotion and evaluation were relatively less frequent. Furthermore, knowledge seeker and distractor significantly impeded the success of CPS activities, and harmonizer was conducive to high-quality learning outcomes. In addition, information giver always co-occurred with the skills of maintaining team function. Content- and performance-focused roles usually appeared together with negotiation and coordination. These findings highlight the importance of emergent roles during the CPS process, and provide some practical suggestions for improving learning outcomes and CPS skills.