山岳型旅游風景區(qū)日客流量預測模型研究
發(fā)布時間：2018-08-24 08:59
【摘要】：隨著中國社會環(huán)境的和諧發(fā)展和人民生活水平的大幅度提高,我國的旅游業(yè)也展現(xiàn)出了它蓬勃的生命力。然而,旅游業(yè)的快速發(fā)展卻提高了旅游景區(qū)管理者科學決策的難度,尤其是山岳型風景區(qū),因其獨特的地貌特征,在資源調(diào)度和資源保護方面的問題更加突出、更加難以解決。為了從根源降低山岳型景區(qū)協(xié)調(diào)管理的難度,建立山岳型日客流量預測模型,從而為景區(qū)管理者提供科學的決策依據(jù),讓山岳型景區(qū)的旅游環(huán)境能夠在科學布局和區(qū)別決策中保持健康蓬勃的生命力。論文的主要研究如下:(1)對國內(nèi)外學者的文獻研究進行梳理,以黃山景區(qū)六年的日客流量數(shù)據(jù)特點為研究對象,分析山岳型風景區(qū)日客流量的影響因素和變化特點。依據(jù)黃山景區(qū)日客流量的變化特點,將其分為平常日客流量和節(jié)假日客流量,從而可以根據(jù)不同時間節(jié)點的客流量數(shù)據(jù)特點,分別構建不同的日客流量預測模型。(2)針對黃山風景區(qū)平常日客流量數(shù)據(jù)似線性的特點,構建基于灰色系統(tǒng)的平常日預測模型。在研究中,引用GM(1,1)模型作為基礎預測模型。在研究中,針對基礎模型存在的不足依次做出以下優(yōu)化:以新陳代謝優(yōu)化提高基礎灰色預測模型預測結果的可靠性;以平滑指數(shù)優(yōu)化樣本序列,提高樣本序列的規(guī)律;以殘差修正優(yōu)化樣本序列,提高預測模型的精度。最后通過幾種優(yōu)化方法的組合,建立基于灰色系統(tǒng)組合優(yōu)化的平常日客流量預測模型。實驗證明,基于灰色預測組合優(yōu)化的平常日客流量預測模型符合預測精度的要求,且預測效果優(yōu)于神經(jīng)網(wǎng)絡模型。(3)針對黃山景區(qū)節(jié)假日客流量數(shù)據(jù)周期性強的特點,構建基于神經(jīng)網(wǎng)絡的節(jié)假日預測模型。選取黃山景區(qū)節(jié)假日客流量為模型樣本,通過對比不同的影響因素和參數(shù)值的預測模型精度,確定模型的構建要素。實驗證明,基于神經(jīng)網(wǎng)絡的預測模型比基于灰色系統(tǒng)的預測模型更適合節(jié)假日預測。
[Abstract]:With the harmonious development of Chinese social environment and the improvement of people's living standard, the tourism industry of our country has also shown its vigorous vitality. However, the rapid development of tourism has increased the difficulty of scientific decision-making of scenic spot managers, especially the mountain scenic spot, because of its unique geomorphological characteristics, the problems in resource scheduling and resource protection are more prominent and more difficult to solve. In order to reduce the difficulty of coordinated management of mountain scenic spots from the root causes, establish the forecasting model of daily passenger flow of mountain type, and provide scientific decision basis for scenic spot managers. The tourism environment of mountain scenic spot can maintain healthy and vigorous vitality in scientific layout and differentiation decision. The main research of this paper is as follows: (1) combing the literature research of domestic and foreign scholars, taking the characteristics of daily passenger flow data of six years in Huangshan scenic spot as the research object, analyzing the influencing factors and changing characteristics of the daily passenger flow of mountain scenic spot. According to the characteristics of daily passenger flow in Huangshan scenic area, it can be divided into normal daily passenger flow and holiday passenger flow, which can be based on the characteristics of passenger flow data of different time nodes. Different daily passenger flow forecasting models are constructed respectively. (2) according to the characteristic that the daily passenger flow data of Huangshan Scenic spot appear linear, the daily forecasting model based on grey system is constructed. In the study, the GM (1 + 1) model is used as the basic prediction model. In the research, the following optimization is made according to the shortcomings of the basic model: to improve the reliability of the prediction results of the basic grey prediction model by metabolic optimization, to optimize the sample sequence by smoothing index, and to improve the regularity of the sample sequence. The precision of the prediction model is improved by modifying the sample sequence with residual error. Finally, through the combination of several optimization methods, a daily passenger flow forecasting model based on grey system combination optimization is established. The experiment proves that the daily passenger flow forecasting model based on grey forecast combination optimization meets the requirement of forecasting precision and the forecasting effect is better than that of neural network model. (3) aiming at the strong periodicity of holiday passenger flow data in Huangshan scenic spot, The holiday prediction model based on neural network is constructed. Huangshan scenic spot holiday passenger flow as model sample, by comparing different factors and parameters of the prediction model accuracy, determine the building elements of the model. Experimental results show that the prediction model based on neural network is more suitable for holiday prediction than that based on grey system.
【學位授予單位】：合肥工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：F592.7
[Abstract]:With the harmonious development of Chinese social environment and the improvement of people's living standard, the tourism industry of our country has also shown its vigorous vitality. However, the rapid development of tourism has increased the difficulty of scientific decision-making of scenic spot managers, especially the mountain scenic spot, because of its unique geomorphological characteristics, the problems in resource scheduling and resource protection are more prominent and more difficult to solve. In order to reduce the difficulty of coordinated management of mountain scenic spots from the root causes, establish the forecasting model of daily passenger flow of mountain type, and provide scientific decision basis for scenic spot managers. The tourism environment of mountain scenic spot can maintain healthy and vigorous vitality in scientific layout and differentiation decision. The main research of this paper is as follows: (1) combing the literature research of domestic and foreign scholars, taking the characteristics of daily passenger flow data of six years in Huangshan scenic spot as the research object, analyzing the influencing factors and changing characteristics of the daily passenger flow of mountain scenic spot. According to the characteristics of daily passenger flow in Huangshan scenic area, it can be divided into normal daily passenger flow and holiday passenger flow, which can be based on the characteristics of passenger flow data of different time nodes. Different daily passenger flow forecasting models are constructed respectively. (2) according to the characteristic that the daily passenger flow data of Huangshan Scenic spot appear linear, the daily forecasting model based on grey system is constructed. In the study, the GM (1 + 1) model is used as the basic prediction model. In the research, the following optimization is made according to the shortcomings of the basic model: to improve the reliability of the prediction results of the basic grey prediction model by metabolic optimization, to optimize the sample sequence by smoothing index, and to improve the regularity of the sample sequence. The precision of the prediction model is improved by modifying the sample sequence with residual error. Finally, through the combination of several optimization methods, a daily passenger flow forecasting model based on grey system combination optimization is established. The experiment proves that the daily passenger flow forecasting model based on grey forecast combination optimization meets the requirement of forecasting precision and the forecasting effect is better than that of neural network model. (3) aiming at the strong periodicity of holiday passenger flow data in Huangshan scenic spot, The holiday prediction model based on neural network is constructed. Huangshan scenic spot holiday passenger flow as model sample, by comparing different factors and parameters of the prediction model accuracy, determine the building elements of the model. Experimental results show that the prediction model based on neural network is more suitable for holiday prediction than that based on grey system.
【學位授予單位】：合肥工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：F592.7
【相似文獻】
相關期刊論文 前10條
1 何堯;;“世博標準”能否帶動升級?[J];商業(yè)文化;2010年12期
2 ;頭條[J];數(shù)據(jù);2010年11期
3 梁媛;;當“噱頭”已成往事[J];紡織服裝周刊;2010年30期
4 孫福;;特色獨具一條街[J];科技致富向導;1996年05期
5 吳寶河;對發(fā)展新華集貿(mào)中心市場的思考[J];經(jīng)濟論壇;1994年02期
6 劉巍;;上海準備好了嗎[J];w，
本文編號：2200288
本文鏈接：http://www.sikaile.net/guanlilunwen/lvyoujiudianguanlilunwen/2200288.html
教材專著
