Faculty of Electrical Engineering, Automatic Control and Informatics, Opole University of Technology, 45-758 Opole, Poland.
Weegree Sp. z o.o. S.K., 45-018 Opole, Poland.
Sensors (Basel). 2020 Jul 22;20(15):4074. doi: 10.3390/s20154074.
This paper presents a novel user experience optimization concept and method, named User Experience Sensor, applied within the Hybrid Intelligence System (HINT). The HINT system, defined as a combination of an extensive AI system and the possibility of attaching a human expert, is designed to be used by relational agents, which may have a physical form, such as a robot, a kiosk, be embodied in an avatar, or may also exist as only software. The proposed method focuses on automatic process evaluation as a common sensor for optimization of the user experience for every process stage and the indicator for human-expert automatic session activation. This functionality is realized by the User Experience Sensor, which constitutes one of main elements of the self-optimizing interaction system. The authors present the optimization mechanism of the HINT system as an analogy to the process of building a Tower of Hanoi. The proposed sensor evaluates the user experience and measures the user/employee efficiency at every stage of a given process, offering the user to choose other forms of information, interaction, or expert support. The designed HINT system is able to learn and self-optimize, making the entire process more intuitive and easy for each and every user individually. The HINT system with the proposed sensor, implemented in a window assembly facility, successfully reduced assembly time, increased employees' satisfaction, and assembly quality. The proposed approach can be implemented in numerous man-machine interaction applications.
本文提出了一种新颖的用户体验优化概念和方法，称为用户体验传感器，应用于混合智能系统（HINT）中。HINT 系统被定义为一个广泛的人工智能系统和附加人类专家的可能性的结合体，旨在被关系代理使用，这些代理可以具有物理形式，例如机器人、信息亭、化身体现，或者也可以仅作为软件存在。所提出的方法侧重于自动过程评估，作为每个过程阶段用户体验优化的通用传感器，以及人类专家自动会话激活的指标。这种功能是通过用户体验传感器实现的，它构成了自优化交互系统的主要元素之一。作者将 HINT 系统的优化机制比作建造汉诺塔的过程。所提出的传感器评估用户体验，并在给定过程的每个阶段测量用户/员工的效率，为用户提供选择其他形式的信息、交互或专家支持的机会。设计的 HINT 系统能够学习和自我优化，使整个过程对每个用户来说更加直观和容易。在窗户装配设施中实现的带有传感器的 HINT 系统成功地减少了装配时间，提高了员工的满意度和装配质量。所提出的方法可以应用于众多人机交互应用中。
