發展面試互動情緒感知與評量機器人之設計思考   免費試閱

Design Thinking for Developing Emotional Sensing and Evaluation Robot of Interactive Interview

本研究探討如何應用設計思考方法，提供不同背景的使用者，於面試互動中情緒感知及評量的方法與系統。若能透過系統化及跨領域設計，發展能模擬面試，並偵測面試者之情緒，以及整合語意偵測及專業關鍵字評量的對話機器人，將有助於面試者透過自我練習與評量的回饋，增進面試時的專業表現。研究顯示，若導入情感運算技術及機器學習機制，深化互動服務機器人與使用者之間的互動與回饋，則更能符合服務情境與未來創新服務發展的需求。本研究架構於跨領域整合設計思考、情緒偵測技術及案例式推理分析的方法，以模擬面試的服務情境為實證研究案例，建置情緒感知機器人的原型系統，針對情緒感知的方法進行規劃與測試，並提出三個情緒偵測分析指標：臉部表情快樂指數、眼睛眨眼頻率、個人履歷文本語意情緒；作為本研究情緒感知的分析依據，以實驗結果分析相關技術整合的成效，以及系統發展之價值、效用與示能性。本研究以應用案例式推理分析的方法，建立互動服務情境及使用者專業背景與情緒感知評價系統的連結，除能符合人本設計以使用者為導向的需求及系統應用之示能性外，後續可透過案例庫累積，逐步調整各情緒偵測指標之權重，建立情緒感知機器人在未來學習機制的基礎。

As the application of design and technology has become more interdisciplinary and integrated, the development of interactive service robots (ISRs), which are designed according to unique situational requirements, has emerged as a popular trend. Research has shown that if affective computing technology and machine learning mechanisms can be introduced to enhance interaction and feedback between ISRs and users, ISRs can better satisfy the needs of a greater number of people. In addition, they may be better aligned with both the service context and the future development of innovative services. Based on an interdisciplinary integration framework, this study combines the concept and method of design thinking, emotion-detection technology, and case-based reasoning (CBR) to simulate the service situation of an interview, and thus to develop a prototype emotion-sensing robot (ESR) system. The results of the experiment were then used to analyze the effectiveness of integrating corresponding technologies as well as the value, utility, and affordance of the developed system. This study constructed an ESR prototype and validated its worth as an application by integrating and testing core emotion-detection technologies. The ESR developed based using an interdisciplinary approach is able to connect user needs and the application of technology to the development of corresponding functions. Furthermore, this study introduced CBR analysis to establish a link between an interactive service context, the professional backgrounds of users, and an emotion-sensing evaluation system. Despite meeting both user requirements and user-centered design requirements, as well as demonstrating the feasibility of the system, future studies are necessary to enrich the cases in the database of CBR system and establish a foundation of machine learning principles for ESRs.