- Reset all ×
- Poster Presentation ×
- College of Professional and Continuing Education, The Hong Kong Polytechnic University ×
- The Education University of Hong Kong ×
- Lingnan University ×
- Tung Wah College ×
- Yew Chung College of Early Childhood Education ×
- 1.2 Fund for Innovative Technology-in-Education (FITE) ×
Filter Presentations
2 posts found
Poster Presentation Time: 1225-1400; 1500-1600
Venue: I4, Tai Po-Shek-O Room, Lower Level I
Presenter(s)
– Dr Yanjie SONG, Associate Professor, Department of Mathematics and Information Technology, The Education University of Hong Kong
– Mr Kaiyi WU, Department of Mathematics and Information Technology, The Education University of Hong Kong
Abstract
Integrating artificial intelligence (AI) into educational settings is crucial for developing innovative teaching methods that enhance student learning. This study investigates the development and application of Learningverse, a 2D/3D metaverse platform that integrates digital humans with advanced Large Language Model Operations (LLMOps) to create AI teaching agents. Leveraging the capabilities of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), we designed intelligent digital human teachers. These LLMOps system-constructed multi-agents, including Communication Encoder, Body Movement Coding Encoder, Eye Gaze Coding Encoder, and Expression Coding Encoder, provide personalized and strategic scaffolding to students, offering real-time feedback and support to improve their learning outcomes. Additionally, the platform utilizes GPT-SoVITS trained TTS to clone real teachers’ voices, enhancing the realism of digital human teachers. The platform can customize digital teachers and build scenarios based on different subject courses, adapting them to various thematic curricula. A pilot study evaluated the effectiveness of these digital teachers in enhancing student engagement and performance in Learningverse. Preliminary findings reveal a significant improvement in students’ interactions, motivation, and overall learning achievements. This research highlights the potential of LLMOps-integrated digital human teachers in transforming teaching practices and enriching educational experiences in the metaverse.
Theme: 1. Showcase Project Achievements
Sub-theme: 1.2Â Fund for Innovative Technology-in-Education (FITE)
Poster Presentation Time: 1225-1400; 1500-1600
Venue: I3, Tai Po-Shek-O Room, Lower Level I
Presenter(s)
– Ms Winnie WONG, Educational Development Manager, Centre for Learning, Teaching and Technology, The Education University of Hong Kong
– Mr Vincent CHAN, Educational Development Assistant, Centre for Learning, Teaching and Technology, The Education University of Hong Kong
Abstract
Background and Objectives: This project aims to leverage the immersive capabilities of the metaverse to enhance data security and privacy awareness among students and staff at the Education University of Hong Kong. Develop a series of interactive and engaging educational materials to enhance the understanding of data security principles and data privacy policies. Design and implement a dynamic and user-friendly online platform (Metaverse Space) to host the educational materials, facilitating easy access and learning for target audiences. Methods and Findings: Within this metaverse-based platform, users are presented with practical scenarios that simulate real-world situations involving security-critical concepts. The educational virtual environment is strategically gamified to motivate users through rewarding challenges and progressive levels, bridging the gap between theory and practice. The dynamic simulation exercises allow participants to directly experience the impact of security failures and rehearse protective actions in a risk-free, controlled setting, nurturing applied skills alongside conceptual understanding. The survey results, based on responses from (n=20), indicate that the gamified metaverse prototype is both engaging and effective in teaching data security and privacy concepts. The interactive scenarios and simulations were particularly praised for their usefulness in understanding real-world data security issues. The navigation of the metaverse environment was generally considered easy. Overall, the positive responses suggest that the gamified metaverse is a valuable tool for learning data security, demonstrating its effectiveness in an educational context. Discussion and Perspectives: Leveraging Metaverses data security learning platform offers an innovative and immersive approach to addressing the limitations of traditional training methods, empowering users with comprehensive knowledge and applied skills to mitigate evolving cyber threats.