风景区旅游客流量短期预测方法研究

发布时间：2018-01-06 18:53

本文关键词：风景区旅游客流量短期预测方法研究　出处：《合肥工业大学》2013年硕士论文　论文类型：学位论文

【摘要】：随着世界经济的发展和人民生活水平的提高，旅游业由此得到了极大的发展。旅游项目的产品定位和整体规划对行业的发展有着深远的影响，科学制定旅游业的持续发展战略规划就显得尤为重要。而旅游客流量短期预测工作是其中一个非常重要的环节。每日客流量的预测值一直是景区管理者在制定政策和日常管理工作中希望了解到的数据。在旅游旺季，准确的短期客流量预测可以让旅游管理部门和管理者在物质、交通、服务配备等方面更好的进行合理、科学的调度和规划。旅游客流量的预测，尤其是短期客流量的预测工作是比较繁杂而不确定的。预测理论和预测模型的选择对预测结果的准确性将产生很大的影响,因此本文在预测理论、预测的影响因素方面和预测模型进行了相关的研究。文中对黄山风景区信息化建设的重点项目——“智慧黄山风景区客流量预测系统”进行了详细分析。这为旅游景区短期客流量预测工作提供了相关的方法，各旅游景区的政策制定和日常管理工作也可对文中一些建议进行参考。本文主要的研究内容如下：（1）阐述了旅游需求影响因素的国内外研究现状，灰色关联分析理论在旅游行业中的应用现状，以及旅游需求预测模型的国内外研究现状，针对短期微观旅游需求预测建立了相关的研究路线。（2）对旅游需求预测的影响因素进行分析研究，，阐述了旅游需求预测的相关概念，分析了长期客流量影响因素和日客流量影响因素两个方面，提出筛选影响因素的相关原则，并在此基础上给出基于灰色关联分析的影响因素的筛选方法。（3）对旅游需求的预测模型进行了分析研究，介绍了支持向量回归（SVR）和BP神经网络这两种预测模型的基本原理，并建立相关的预测模型。（4）以黄山风景区为例进行具体的预测工作，针对风景区获得的数据进行收集、整理和分析，从中选取一些对客流量有影响的关键因素，然后采用灰色关联度对结果排序和进行影响因素的筛选，最终选取SVR和BP神经网络对短期客流量进行预测，进而分析了预测结果。本文研究了前人在风景区客流量预测方面的成果，采用相关的预测理论和模型对黄山景区预测系统进行分析和验证，希望能为今后各大景区在客流量预测方面提供借鉴和指导。
[Abstract]:With the development of world economy and the improvement of people's living standard, the tourism industry has got great development. There is a great influence on the development of tourism project product positioning and overall planning of the industry, the scientific development of the tourism industry sustainable development strategic planning is particularly important. While tourism flow forecasting is one very important. To predict the daily traffic is always the value of tourist scenic spot management in the formulation of policies and the daily management work to understand the data. In the tourist season, accurate short-term traffic prediction can make tourism management departments and managers in the material, transportation, services are equipped with better scientific and reasonable the scheduling and planning.
Forecast of tourist flow, especially the prediction of short-term passenger flow is more complicated and uncertain. The prediction theory and model selection on the accuracy of the predicted results will have a huge impact, based on the forecasting theory, model and forecast the influence factors of the related research. The informatization construction in Mount Huangshan scenic areas of key projects -- "the wisdom of Mount Huangshan scenic area traffic prediction system" are analyzed in detail. This work provides a relevant method for prediction of short-term passenger flow of tourist attractions, the tourism policy formulation and daily management work can also be a reference for some suggestions in this paper. The main research contents of this article the following:
(1) elaborated the domestic and foreign research status of tourism demand influencing factors, the application status of grey relational analysis theory in tourism industry, and the domestic and foreign research situation of tourism demand prediction model, and established related research routes for short-term micro tourism demand prediction.
(2) to study the influencing factors on tourism demand forecasting, expounds the related concepts of tourism demand forecasting, analyzes two factors influence factors of long-term traffic and traffic influence, put forward related factors influence selection principle, and on the basis of this screening method is given based on the grey relational analysis influence factors.
(3) the prediction model of tourism demand is analyzed and studied. The basic principles of two prediction models of support vector regression (SVR) and BP neural network are introduced, and relevant prediction models are established.
(4) in the Mount Huangshan scenic area as an example to predict the concrete work, in the scenic area obtained data collection, collation and analysis, select the key factors of passenger flow from it, then using the grey correlation of results ranking and the factors influencing the selection, final selection of SVR and BP neural network prediction for short-term traffic, and then analyzes the prediction results.
This paper studies the predecessors' achievements in the prediction of tourist volume in scenic area, analyzes and verifies the prediction system of Mount Huangshan scenic area by using relevant prediction theories and models, hoping to provide reference and guidance for future scenic spots in the prediction of passenger volume.

【学位授予单位】：合肥工业大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：F592.7;F224

【参考文献】