The restaurant industry struggles with managing high volumes of phone-based customer interactions, particularly during peak hours, leading to operational inefficiencies, increased labor costs, and diminished customer satisfaction. Inspired by the rise of large language models (LLMs) in recent years, in this paper, we introduce an AI-driven customer service application leveraging fine-tuned LLMs to address these challenges by integrating speech recognition, text generation, and text-to-speech technologies for seamless real-time interactions. Using domain-specific conversational data from a local restaurant, the system fine-tunes state-of-the-art LLMs, including Llama-3.2-1B and Llama-2-7B, to generate human-like responses tailored to the restaurant industry. The architecture consists of client-side voice-to-text and text-to-voice components alongside a server-side AI backend, ensuring efficient processing and a smooth user experience. Experimental results show that the fine-tuned Llama-2-7B model delivers superior accuracy and robustness, while GPU utilization significantly enhances response latency and overall performance. Through our designed platform, we demonstrate the potential of domain-specific LLM fine-tuning in transforming customer service applications by automating phone-based interactions, reducing operational costs, and improving customer satisfaction. Our demo video can be reached with the link: https://www.youtube.com/watch?v=K_qQaueAmtA.

In this paper, we explore the potential of utilizing Digital Twin (DT) technology for real-time data storage and processing in emergency healthcare. Focusing on Internet of Things (IoT) and cloud computing technologies, we investigate various enabling technologies, including cloud platforms, data transmission formats, and storage file formats, to develop a feasible DT storage solution for emergency healthcare. Through our analysis, we find Amazon AWS to be the most suitable cloud platform due to its sophisticated real-time data processing and analytical tools. Additionally, we determine that the MQTT protocol is suitable for real-time medical data transmission, and FHIR is the most appropriate medical file storage format for emergency healthcare situations.We propose a cloud-based DT storage solution, in which real-time medical data is transmitted to AWS IoT Core, processed by Kinesis Data Analytics, and stored securely in AWS HealthLake. Despite the feasibility of the proposed solution, challenges such as insufficient access control, lack of encryption, and vendor conformity must be addressed for successful practical implementation. Future work may involve incorporating Hyperledger Fabric technology and HTTPS protocol to enhance security, while the maturation of DT technology is expected to resolve vendor conformity issues. By addressing these challenges, our proposed DT storage solution has the potential to improve data accessibility and decision-making in emergency healthcare settings.