Yi-Hui Liu

Language barriers remain a critical challenge in health care delivery, particularly for migrant and multicultural populations. This study presents the design, implementation, and evaluation of an artificial intelligence (AI)–driven multilingual medical health education chatbot to enhance health care communication and accessibility. The proposed system introduces a user-state–driven multi-layer logical architecture, which enables efficient multilingual interaction by dynamically routing user queries to language-specific processing modules. In addition, a hybrid retrieval–generative framework is developed to combine expert-curated health education content with conversational AI (ChatGPT), ensuring both information reliability and interaction flexibility. The system is deployed on the LINE platform and evaluated using the System Usability Scale, Net Promoter Score, and Customer Satisfaction Score with 85 participants from diverse linguistic and cultural backgrounds. The results demonstrate satisfactory usability and user acceptance, with consistent performance observed across nationality groups, supporting the system’s cross-cultural applicability. Overall, the findings indicate that the proposed architecture provides a scalable, efficient, and practical solution for multilingual health care communication, reducing language barriers and improving patient understanding in real-world clinical environments.

The recent COVID-19 epidemic has affected the global sports industry to a certain extent, and health clubs are no exception. To avoid unsustainable operations, health clubs need to restructure their programs to suit members’ needs. Therefore, this study constructs a two-stage framework model to evaluate health club members’ purchase of coaching programs. The first stage is to construct a hierarchy of evaluation, using the modified Delphi method, to select suitable criteria and extended sub-criteria, and add and delete them through expert discussion. In the second stage, we use the pairwise comparison matrix to calculate the weight of each criterion and sub-criterion to influence each other. Next, we evaluate and compare physical, online and offline, and live-stream coaching programs, by using network hierarchy analysis to identify the best class purchase plan during the epidemic and provide relevant suggestions. The results of the study found that during the epidemic, the primary sales were for weight training among physical programs (0.314), and activity classes among online and offline programs (0.633) as well as live-stream coaching programs (0.280). These findings have implications for health clubs in deciding which mode they need to adopt for sustainable operations.

Purpose: This paper aims to present an augmented reality (AR) application to aid the elderly in library reference search. The application supports the elderly in searching books and videos in a large library when librarians have insufficient time to meet their needs. The elderly searching in a large library could be difficult for them due to the vast area, complicated online library catalogs and their physical deterioration, such as failing eyesight, tendinitis and memory problems. Our system, SearchAR, fully supports the 3D images of object content based on books and videos in Ling Tung University (LTU) library catalogs. Using the latest AR technology, users can use mobile phone to scan the quick response (QR) code in front of the LTU library, and then the elderly can experience LTU library map labeled by different colors in real-time and understand the locations of the video areas and book shelves areas. Later, they can use SearchAR to scan the QR codes on bookshelves, books or videos to view the 3D graphics without reading complicated catalogs and content. The results show that among the images, the elderly recognition of the “3 D images” was the highest, and the experimental group using AR technology as a searching aid shows a higher searching effectiveness than the control group; 60 per cent of the elderly felt they saved more time for searching books and videos with the help of SearchAR, and it was easy to arouse their association; the elderly indicated that combined image of the library map and the labels with different colors are clear and simple; the content of books and videos are easy associated with the 3D images; the elderly mentioned that using SearchAR is a great experience without any reading complicated online catalogs. Finally, this study concludes that AR technology does enhance the elderly searching ability in LTU large library. Design/methodology/approach: The SearchAR application was an integrating library catalog, which provides AR and 3D graphics. The elderly can also use SearchAR to see a library map and every library element via 3D graphics before they start searching in a wide area. Findings: This makes it easier for elderly to navigate a library without using complicated online catalogs, and it reduces time spent on reading and searching. Originality/value: AR has been used for a variety of guiding and educational purposes. However, AR has been rarely applied to supplement traditional library services for elderly.