Optimization and System Construction of Smart Airport Passenger Services Driven by Generative AI and Big Data Analytics

As the construction of smart civil aviation continues to advance globally, the level of personalization, efficiency, and precision in passenger services has a direct and profound impact on the enhancement of an airport's core competitiveness. However, current smart airport passenger services still face significant practical challenges. Issues such as severe data fragmentation across different operational departments, delayed responses to dynamic passenger needs, and insufficient scenario adaptation make it increasingly difficult to keep pace with the rapidly diversifying demands of modern air travel. To address these critical bottlenecks, this paper leverages Generative Artificial Intelligence (GenAI) as the core technological pillar, deeply integrating advanced big data analysis methods to systematically break through the inherent limitations of traditional service models. It comprehensively explores optimization paths for passenger services that strictly align with current industry realities and establishes a highly integrated, intelligent service system architecture. Furthermore, the research details the specific mechanisms through which generative models can synthesize predictive insights from vast datasets, thereby enabling proactive service delivery and seamless operational coordination. By rigorously validating the feasibility and effectiveness of the proposed technological solutions through empirical practical cases from major aviation hubs, such as Shenzhen Bao'an International Airport and Guangzhou Baiyun International Airport, this study provides both robust theoretical references and actionable practical insights. Ultimately, the findings contribute significantly to the high-quality, sustainable development of smart airport passenger services in the digital era.