<p>Over the past decade, although the global demand for cruise tourism has steadily increased, a decline in customer satisfaction has also emerged as a significant challenge. Quality function deployment (QFD) is an effective approach for transforming customer requirements into product or service quality characteristics, which helps to identify key customer needs and optimize service quality. Therefore, this study aims to apply the QFD model to provide practical recommendations for improving cruise service quality. To achieve this, the large language models (LLMs) combined with prompt engineering is first utilized to extract from online cruise reviews and conduct sentiment analysis. Then, the Kano model is applied to classify customer requirements and the weight balance coefficient is introduced to ensure a rational allocation of weights. Hence, a social network-based bilateral interaction consensus mechanism is developed to resolve opinion conflicts within the QFD decision making team, enabling consensus-driven decisions and deriving the final prioritization of quality characteristics. Finally, a real-world cruise case study is conducted to validate the proposed approach, supported by systematic analysis and discussion to highlight its advantages. Overall, this study establishes a QFD framework that integrates LLMs, Kano model and group consensus methods based on online cruise reviews, which provides a data-driven and adaptive solution for improving cruise service quality.</p>