The Design Model for Robotic Waitress
journal contributionposted on 14.02.2022, 16:54 by Jiaji Yang, Esyin Chew
With the rapid development of traditional industries, intelligent robots have been widely used in the hospitality industry. Although the development of intelligent robots faces a positive trend and a good market in the hospitality industry, it also faces the problem that robots cannot effectively collect and use user data in the field of human–computer interaction. It not only affects the interaction experience between users and robots, but also prevents companies from getting valuable feedback in a timely manner. In order for intelligent robots to effectively utilize interactive information, the user experience of robot entertainment is improved. This paper proposes and establishes a basic technical model called iRCXM. Combining the iRCXM model with a decision tree classification algorithm is excepted effectively improve the interaction experience between humans and robots in hospitality. This paper designs a model of intelligent robot based on decision tree algorithm. The model divides the user into three sections, each corresponding to a different standard function. Using a decision tree classification algorithm model is excepted effectively judge users’ current stage and whether they can move to the next stage. When the user reaches the final stage, it proves that the user has obtained a good interactive experience. At the same time, for users at different stages, the model will provide strategies for downward transformation so that companies can adjust and improve existing problems in a timely manner. In addition, the research developed a robot user interaction system based on the existing technology. The system is based on Android. Using HTTP protocol and Baidu Cloud AI API to realize simple face recognition and Sanbot-OpenSDK to implement simple robot control, the development of this system is to verify the feasibility of the model. The developed samples were tested in a real environment and feedback from customer experience was collected through semi-structured interviews. Finally, the feasibility of the model is verified.