基于大模型与多源数据融合的景区导览优化策略研究——以蜀南竹海为例

Research on Optimization Strategy of Scenic Area Guidance Based on Large Model and Multi-Source Data Fusion—A Case Study of Shunan Bamboo Sea

摘要: 本文以生态旅游典范蜀南竹海为研究对象，探索大语言模型(LLM)与多源数据融合背景下的智能导览优化策略。通过对景区门票与客流、交通路径、游客行为等多维数据的分析，结合大模型在语义理解与交互方面的优势，构建一套集游客画像建模、路径偏好推荐、拥堵预测引导与语音交互讲解于一体的导览策略体系。论文提出了面向个性化游览需求与实时感知的智能决策机制，对比其在游客满意度、游览效率、拥堵缓解等方面的改进效果。研究结果表明，大模型驱动的导览优化策略具备较高的智能化与适应性，可为智慧景区建设提供理论支持与决策参考。

Abstract: This paper takes Shunan Bamboo Sea, a model of eco-tourism, as the research object to explore intelligent tour guidance optimization strategies under the background of large language model (LLM) and multi-source data fusion. Through the analysis of multi-dimensional data such as scenic spot tickets and passenger flows, traffic routes, and tourist behaviors, and combining the advantages of large models in semantic understanding and interaction, a set of tour guidance strategy system integrating tourist portrait modeling, path preference recommendation, congestion prediction guidance, and voice interaction explanation is constructed. The paper proposes an intelligent decision-making mechanism oriented towards personalized sightseeing demands and real-time perception, and compares its improvement effects in terms of tourist satisfaction, sightseeing efficiency, and congestion relief. The research results show that the large model-driven tour guidance optimization strategy has high intelligence and adaptability, which can provide theoretical support and decision-making reference for the construction of smart scenic spots.