Development of an AI Userbot for Engineering Design Education Using an Intent and Flow Combined Framework

Abstract

As the inclusion of users in the design process receives greater attention, designers need to not only understand users, but also further cooperate with them. Therefore, engineering design education should also follow this trend, in order to enhance students’ ability to communicate and cooperate with users in the design practice. However, it is difficult to find users on teaching sites to cooperate with students because of time and budgetary constraints. With the development of artificial intelligence (AI) technology in recent years, chatbots may be the solution to finding specific users to participate in teaching. This study used Dialogflow and Google Assistant to build a system architecture, and applied methods of persona and semi-structured interviews to develop AI virtual product users. The system has a compound dialog mode (combining intent- and flow-based dialog modes), with which multiple chatbots can cooperate with students in the form of oral dialog. After four college students interacted with AI userbots, it was proven that this system can effectively participate in student design activities in the early stage of design. In the future, more AI userbots could be developed based on this system, according to different engineering design projects for engineering design teaching.

Participatory design curriculum promotes engineering design, critical thinking, and creativity for students from kindergarten to 12th grade.

“…Some student behaviors, such as communication and decision making, were less frequent in this study. Other design-teaching studies encountered similar issues (Atman & Bursic, 1998; Atman et al, 2007; Chien & Yao, 2020; Chien et al, 2020). Therefore, a longitudinal study of the same design may be needed to remedy the insufficient number of behaviors, and this would strengthen the students’ familiarity with design activities through repeated teaching.…”

“…Previous related studies argued that students frequently disregard the significance of self-iterations and transitions and skip some of the design processes (Atman et al, 2007; Chien & Yao, 2020; Chien et al, 2020). However, students can complete the design process only if they realize what the issues are and what users require from all perspectives, repeatedly identify problems with the users, and continuously revise the products (McIntosh & Marques, 2017).…”

“…Design is an interdisciplinary problem-solving process (Chien & Yao, 2020; Chien et al, 2020), which should be used as a powerful vehicle for STEM/STEAM learning. This study integrated the important features of participatory design into the design process as an innovative teaching strategy.…”

Does the Improvement in AI Tools Necessitate a Different Approach to Engineering Education?

“…However, the insights offered are directly applicable to the course examined in our case study section. Chien and Yao's research, while not directly centered on AI pedagogy, highlights the potential of AI bots in participatory design [26]. This indirectly underscores the essential AI components that should be integral to engineering curricula.…”

Mining the Chatbot Brain to Improve COVID-19 Bot Response Accuracy

“…Labeeb [16] introduced an intelligent conversational agent to enhance course teaching and allied learning outcomes. Chien et al [17] proved that students could collaborate with chatbots for better design solutions. Fryer et al [18] investigated why chatbots are not yet a powerful tool for language learning.…”