技术领域technical field
本发明是一种新型的数据分析方法，主要用来帮助决策者选择合适的旅行刺激策略来提高旅游景点的游客数量，增加经济效益。The invention is a new type of data analysis method, which is mainly used to help decision makers choose a suitable travel stimulation strategy to increase the number of tourists in tourist attractions and increase economic benefits.
背景技术Background technique
随着国家经济形式的逐步趋好，居民生活水平的不断提升，旅游需求稳步增长。旅游消费已经成为全球民众的重要生活方式，并成为推动全球经济增长的重要引擎。2017年全球旅游收入占世界GDP的6.7％，而且这一比例还在不断上升。特别是在绿色、可持续发展的背景下，旅游业已经成为各国经济的重要发展方向，一些国家更是将旅游业作为经济发展的重要引擎。如何有效的促进旅游业的发展并且提高旅游收入是各级政府及相关企业的重要研究方向之一。在政府层面，成立相关职能部门专门组织管理区域内的旅游发展及市场管理，以提升旅游业服务水平，增加旅游收入；在市场层面，各个旅游服务公司应运而生，为游客提供各种个性化的服务。With the gradual improvement of the country's economic form and the continuous improvement of residents' living standards, tourism demand has grown steadily. Tourism consumption has become an important way of life for people around the world and an important engine driving global economic growth. Global tourism receipts accounted for 6.7% of world GDP in 2017, and the proportion is rising. Especially in the context of green and sustainable development, tourism has become an important development direction of the economy of various countries, and some countries regard tourism as an important engine of economic development. How to effectively promote the development of tourism and increase tourism revenue is one of the important research directions of governments at all levels and related enterprises. At the government level, relevant functional departments are established to organize and manage tourism development and market management in the region to improve tourism service levels and increase tourism revenue; at the market level, various tourism service companies emerge as the times require to provide tourists with a variety of personalized services. service.
随着计算机与互联网技术的发展，特别是社交网络的发展，各旅游服务平台相继推出了一大批旅游订制服务以为了满足游客的多样性需求。这些订制服务大多面向各个旅游消费个体，以增加平台的访问量及依赖性。旅游线路的智能化推荐是其中的重要内容之一，也是近年来研究的热点问题。不同于企业，政府部门更关注旅游资源的建设以及旅游市场的管理，通过提高旅游服务质量来增加行政区域内的旅游收入。由于客流量受节季影响较大，为了提升游客服务水平，特别是在流量大的时间节点做到旅游管理的有序性和高效性，客流量预测是前提。这一领域吸引了一大批研究热情，相关的成果得到应用。例如，2004年Chao-Hung Wang提出了基于模糊时间序列与合成灰色理论的旅游需求预测模型。李瑶等人提出了一种改进的灰色模型并应用于海南省的旅游需求预测。这种通过提升旅游服务水平，增强游客体验来促进旅游市场发展的方式可以称为被动式需求刺激。With the development of computer and Internet technologies, especially the development of social networks, various travel service platforms have successively launched a large number of customized travel services to meet the diverse needs of tourists. Most of these customized services are oriented to individual travel consumers to increase the number of visits and dependencies on the platform. The intelligent recommendation of tourist routes is one of the important contents, and it is also a hot research topic in recent years. Different from enterprises, government departments pay more attention to the construction of tourism resources and the management of the tourism market, and increase tourism revenue within the administrative region by improving the quality of tourism services. Since the passenger flow is greatly affected by the season, in order to improve the service level of tourists, especially to achieve the orderly and efficient tourism management at the time of heavy traffic, passenger flow forecasting is the premise. This field has attracted a lot of research enthusiasm, and related results have been applied. For example, in 2004 Chao-Hung Wang proposed a tourism demand forecasting model based on fuzzy time series and synthetic grey theory. Li Yao et al. proposed an improved grey model and applied it to tourism demand forecasting in Hainan Province. This way of promoting the development of the tourism market by improving the level of tourism services and enhancing the experience of tourists can be called passive demand stimulation.
随着旅游经济的发展，主动式的需求刺激也越来越受到关注[8,9]，特别是杭州西湖免门票后呈现的巨大经济效益，国内很多地区与景点相继针对某些特定人群发行旅游代金券来吸引游客。然而，民众的旅游出行计划是多种因素共同作用后产生的一种综合的、复杂的决策过程。消费个体在制订旅行计划时，不仅受自身经济水平、教育水平及所地的旅游资源丰富性所影响，同时也与目的地的消费水平、交通便利性和景点特色与分布等因素相关。目前学界大多数工作集中在研究单一因素与旅游需求的关系：朱海艳等人通过分析陕西省10个地市的交通格局变化来分析当地的旅游发展情况，指出入境旅游人数与公路交通高度相关；尹华光等人针对景点分布与游客流量的关系提出了景点空间结构的优化方法。With the development of tourism economy, active demand stimulation has also attracted more and more attention[8,9], especially the huge economic benefits presented by Hangzhou West Lake after free tickets, many regions and scenic spots in China have successively issued tourism to some specific groups of people. Vouchers to attract tourists. However, people's travel plan is a comprehensive and complex decision-making process produced by a combination of factors. When consumers make travel plans, they are not only affected by their own economic level, education level and the richness of tourism resources, but also related to the consumption level of the destination, the convenience of transportation, and the characteristics and distribution of scenic spots. At present, most of the academic work focuses on the study of the relationship between a single factor and tourism demand: Zhu Haiyan et al. analyzed the local tourism development by analyzing the changes in the traffic pattern of 10 cities in Shaanxi Province, and pointed out that the number of inbound tourists is highly correlated with road traffic; Yin Huaguang et al. proposed an optimization method for the spatial structure of scenic spots based on the relationship between the distribution of scenic spots and the flow of tourists.
上述研究聚焦于单一因素对旅游需求的影响。据笔者了解，目前尚显有学者关注显有研究关注各种因素共同作用下目的地的旅游需求变化。特别是在当前各地争相发展旅游经济的背景下，如何有效地应用各种旅游需求刺激手段，提升区域内的游客量是各级政府及旅游管理部门的工作重点之一。因此，建立各种因素与地区旅游需求模型，量化分析各因素对游客人数的影响，对旅游刺激措施的实施具有巨大的应用价值。The above studies focus on the impact of a single factor on tourism demand. As far as the author understands, there are still scholars who pay attention to the changes in tourism demand of destinations under the combined action of various factors. Especially in the current background where various places are scrambling to develop the tourism economy, how to effectively apply various tourism demand stimulation methods and increase the number of tourists in the region is one of the priorities of governments and tourism management departments at all levels. Therefore, the establishment of various factors and regional tourism demand models, quantitative analysis of the impact of various factors on the number of tourists, has a huge application value for the implementation of tourism stimulus measures.
发明内容SUMMARY OF THE INVENTION
为了克服现有的旅游数据分析方法的仅考虑单一因素影响的不足，本发明的目的就是对与旅游相关的历史数据进行分析建模，得到与旅游景点游客数目最相关的因素，这些相关信息既可以为政府决策提供依据，同时也可以为后续旅游经济的发展提供相应的指导。In order to overcome the deficiency of the existing tourism data analysis method that only considers the influence of a single factor, the purpose of the present invention is to analyze and model the historical data related to tourism, and obtain the most relevant factors with the number of tourists in the tourist attractions. It can provide a basis for government decision-making, and can also provide corresponding guidance for the subsequent development of tourism economy.
本发明所采用的技术方案为：The technical scheme adopted in the present invention is:
一种基于客源地属性特征的旅行刺激策略有效性分析方法，包括以下步骤：A method for analyzing the effectiveness of travel stimulation strategy based on the attribute characteristics of tourist source, comprising the following steps:
步骤1、定义游客来源地的出行率ζ来量化刺激策略的有效性：其中：Np指作用地的人口总数，Nt是指来源于需求刺激作用地游客人数，定义为：pold为某一地区的老龄化率，p0为45周岁以上人口比率；Step 1. Define the travel rate ζ of the tourist source to quantify the effectiveness of the stimulus strategy: Among them: Np refers to the total population of the role, Nt refers to the number of tourists from the role of demand stimulation, defined as: pold is the aging rate of a certain area, p0 is the ratio of the population over the age of 45;
步骤2、定义有效出行率ζe描述刺激政策的效果：其中N(Ai)为刺激政策作用地处于Ai年龄段的人口数，为不同年龄群的旅游出行意愿；Step 2. Define the effective travel rate ζe to describe the effect of the stimulus policy: where N(Ai ) is the population in the age group Ai where the stimulus policy acts, Travel willingness for different age groups;
步骤3、以最大化有效出行率ζe为目标来研究最佳刺激措施，流程为：通过已有的游客数据信息，计算各个客源地前往某一目的地的历史有效出行率ζe；提取各客源地游客的属性信自息并进行量化表示(特征提取)；应用算法选择最佳特征；结合各地的出行率数据训练学习器，得到旅游需求刺激模型。进一步，所述步骤3包括以下步骤：Step 3. Research the best stimulus measures with the goal of maximizing the effective travel rate ζe . The process is: calculate the historical effective travel rate ζe of each tourist source to a certain destination through the existing tourist data information; extract The attribute information of tourists in each source place is quantitatively expressed (feature extraction); the algorithm is applied to select the best features; the learner is trained by combining the travel rate data of various places, and the tourism demand stimulation model is obtained. Further, the step 3 includes the following steps:
3.1定义目的地空间距离对出行意愿的影响：中D表示客源地与目的地的距离，而D0＝300km为阻尼作用的阈值距离；3.1 Define the effect of destination spatial distance on travel intention: D represents the distance between the customer source and the destination, and D0 =300km is the threshold distance for damping;
3.2交通便利性指数T来刻画旅游目的地与客源城市之间的交通属性，具体定义为：T＝∑imi·exp(-i)，其中i(＝0,1,2,…)和mi分别表示从客源地出经过i次转车到达目的地的班车次数；3.2 The traffic convenience index T is used to describe the traffic attributes between the tourist destination and the source city, which is specifically defined as: T=∑i mi exp(-i), where i(=0,1,2,…) and mi respectively represent the number of buses from the source place to the destination after i transfers;
3.3为了刻画目的地相对客源的旅游吸引力，定义旅游资源吸引力指数:式中Ti为客源地(i＝s)或目的地(i＝d)的旅游资源数；3.3 In order to describe the tourism attractiveness of the destination relative to the source of tourists, define the tourism resource attractiveness index: In the formula, Ti is the number of tourism resources in the tourist source (i=s) or destination (i=d);
3.4引入消费吸引力指数E，定义为式中Ns和Nd分别表示客源地与目的地的人均年收入，而P为目的地的酒店平无价格水平；3.4 Introduce the consumer attractiveness index E, which is defined as where Ns and Nd represent the per capita annual income of the source and destination, respectively, and P is the price level of the hotel at the destination;
3.5应用随机Lasso特征筛选以及过滤式特征选择方法，提取低冗余、相关性高的特征子集；3.5 Apply random Lasso feature screening and filtering feature selection methods to extract feature subsets with low redundancy and high correlation;
3.6利用已有数据以及通过上述方法提取的特征作为支持向量回归SVR的输入、有效出行率ζe作这SVR的输出，训练SVR得到最优的模型参数；3.6 Use the existing data and the features extracted by the above method as the input of the support vector regression SVR, the effective travel rate ζe as the output of the SVR, and train the SVR to obtain the optimal model parameters;
3.7将出行刺激量化为相应的特征参数，相应训练好的SVR回归模型，计算刺激作用下有效出行率的增量Δζe；3.7 Quantify travel stimuli into corresponding characteristic parameters, correspondingly trained SVR regression model, and calculate the increment Δζe of the effective travel rate under the stimulation;
3.8对比不同刺激策略下的出行率Δζe，最大化Δζe所对应的刺激即为最优策略。3.8 Comparing the travel rate Δζe under different stimulus strategies, the stimulus corresponding to maximizing Δζe is the optimal strategy.
本发明的有益效果表现在：对与旅游相关的历史数据进行分析建模，得到与旅游景点游客数目最相关的因素。这些相关信息既可以为政府决策提供依据，同时也可以为后续旅游经济的发展提供相应的指导。The beneficial effect of the present invention is shown in that: the historical data related to tourism is analyzed and modeled, and the most relevant factor with the number of tourists in tourist attractions is obtained. These relevant information can not only provide a basis for government decision-making, but also provide corresponding guidance for the subsequent development of the tourism economy.
附图说明Description of drawings
图1是基于客源地属性特征的旅行刺激策略有效性分析方法的流程图。Fig. 1 is a flow chart of a method for analyzing the effectiveness of travel stimulation strategies based on the attribute characteristics of customer origin.
具体实施方式Detailed ways
下面结合附图对本发明做进一步说明。The present invention will be further described below with reference to the accompanying drawings.
参照图1，一种基于客源地属性特征的旅行刺激策略有效性分析方法，包括以下步骤：Referring to Fig. 1, a method for analyzing the effectiveness of travel stimulation strategies based on the attribute characteristics of customer origin, comprising the following steps:
步骤1、定义游客来源地的出行率ζ来量化刺激策略的有效性：其中：Np指作用地的人口总数，Nt是指来源于需求刺激作用地游客人数，定义为：pold为某一地区的老龄化率，p0为45周岁以上人口比率；Step 1. Define the travel rate ζ of the tourist source to quantify the effectiveness of the stimulus strategy: Among them: Np refers to the total population of the role, Nt refers to the number of tourists from the role of demand stimulation, defined as: pold is the aging rate of a certain area, p0 is the ratio of the population over the age of 45;
步骤2、定义有效出行率ζe描述刺激政策的效果：其中N(Ai)为刺激政策作用地处于Ai年龄段的人口数，为不同年龄群的旅游出行意愿；Step 2. Define the effective travel rate ζe to describe the effect of the stimulus policy: where N(Ai ) is the population in the age group Ai where the stimulus policy acts, Travel willingness for different age groups;
步骤3、以最大化有效出行率ζe为目标来研究最佳刺激措施，流程为：通过已有的游客数据信息，计算各个客源地前往某一目的地的历史有效出行率ζe；提取各客源地游客的属性信自息并进行量化表示(特征提取)；应用算法选择最佳特征；结合各地的出行率数据训练学习器，得到旅游需求刺激模型。进一步，所述步骤3包括以下步骤：Step 3. Research the best stimulus measures with the goal of maximizing the effective travel rate ζe . The process is: calculate the historical effective travel rate ζe of each tourist source to a certain destination through the existing tourist data information; extract The attribute information of tourists in each source place is quantitatively expressed (feature extraction); the algorithm is applied to select the best features; the learner is trained by combining the travel rate data of various places, and the tourism demand stimulation model is obtained. Further, the step 3 includes the following steps:
3.1定义目的地空间距离对出行意愿的影响：中D表示客源地与目的地的距离，而D0＝300km为阻尼作用的阈值距离；3.1 Define the effect of destination spatial distance on travel intention: D represents the distance between the customer source and the destination, and D0 =300km is the threshold distance for damping;
3.2交通便利性指数T来刻画旅游目的地与客源城市之间的交通属性，具体定义为：T＝∑imi·exp(-i)，其中i(＝0,1,2,…)和mi分别表示从客源地出经过i次转车到达目的地的班车次数；3.2 The traffic convenience index T is used to describe the traffic attributes between the tourist destination and the source city, which is specifically defined as: T=∑i mi exp(-i), where i(=0,1,2,…) and mi respectively represent the number of buses from the source place to the destination after i transfers;
3.3为了刻画目的地相对客源的旅游吸引力，定义旅游资源吸引力指数:式中Ti为客源地(i＝s)或目的地(i＝d)的旅游资源数；3.3 In order to describe the tourism attractiveness of the destination relative to the source of tourists, define the tourism resource attractiveness index: In the formula, Ti is the number of tourism resources in the tourist source (i=s) or destination (i=d);
3.4引入消费吸引力指数E，定义为式中Ns和Nd分别表示客源地与目的地的人均年收入，而P为目的地的酒店平无价格水平；3.4 Introduce the consumer attractiveness index E, which is defined as where Ns and Nd represent the per capita annual income of the source and destination, respectively, and P is the price level of the hotel at the destination;
3.5应用随机Lasso特征筛选以及过滤式特征选择方法，提取低冗余、相关性高的特征子集；3.5 Apply random Lasso feature screening and filtering feature selection methods to extract feature subsets with low redundancy and high correlation;
3.6利用已有数据以及通过上述方法提取的特征作为支持向量回归SVR的输入、有效出行率ζe作这SVR的输出，训练SVR得到最优的模型参数；3.6 Use the existing data and the features extracted by the above method as the input of the support vector regression SVR, the effective travel rate ζe as the output of the SVR, and train the SVR to obtain the optimal model parameters;
3.7将出行刺激量化为相应的特征参数，相应训练好的SVR回归模型，计算刺激作用下有效出行率的增量Δζe；3.7 Quantify travel stimuli into corresponding characteristic parameters, correspondingly trained SVR regression model, and calculate the increment Δζe of the effective travel rate under the stimulation;
3.8对比不同刺激策略下的出行率Δζe，最大化Δζe所对应的刺激即为最优策略。3.8 Comparing the travel rate Δζe under different stimulus strategies, the stimulus corresponding to maximizing Δζe is the optimal strategy.
本实施例以浙江省移动动态人口应用行业平台监测的2016年1月至2016年12月期间杭州各景点的游客数据为例，具体说明本发明的实施。该平台包含了游客数量以及他们的来源地等信息。将游客以来源地城市名进行划分，对照各地年鉴量化游客来源地的属性特征，以及来源地地城市有效出行量。以这些数据的学习样本，训练SVR回归模型。依据刺激手段的不同，将其量化了数据样本的某一特征，SVR对新样本的输入即为刺激作用下的有效出行率。给出最大化出行率的刺激即为所要选择的最佳刺激策略。This embodiment specifically describes the implementation of the present invention by taking the tourist data of various scenic spots in Hangzhou from January 2016 to December 2016 monitored by the Zhejiang Mobile Dynamic Population Application Industry Platform as an example. The platform contains information on the number of tourists and where they come from. The tourists are divided by the name of the city of origin, and the attribute characteristics of the source of tourists and the effective travel volume of the city of the source are quantified against the yearbooks of various places. With the learning samples of these data, the SVR regression model is trained. According to the different stimulation methods, it quantifies a certain characteristic of the data samples, and the input of the SVR to the new samples is the effective travel rate under the stimulation. The stimulus that maximizes the travel rate is the optimal stimulus strategy to be selected.
本实施例的实施步骤如下：The implementation steps of this embodiment are as follows:
步骤1、根据游客来源地城市属性，从该城市年鉴中提取可能影响旅游需求的16个客源地特征，如下：人口、距离、人均年收入、人均GDP、老龄化率、男女比例、城镇化率、直达班车数、非直达班车数、5a景区数、4a景区数、博物馆数。Step 1. According to the city attributes of the tourist source, extract 16 tourist source characteristics from the city yearbook that may affect tourism demand, as follows: population, distance, per capita annual income, per capita GDP, aging rate, male-to-female ratio, urbanization rate, the number of direct buses, the number of non-direct buses, the number of 5a scenic spots, the number of 4a scenic spots, and the number of museums.
步骤2、结合上述来源地属性特征及目的地(杭州)的特殊，计算距离指数、交通指数、旅游资源指数、消费吸引指数。Step 2: Calculate the distance index, traffic index, tourism resource index, and consumption attraction index in combination with the above-mentioned attributes of the source and the speciality of the destination (Hangzhou).
步骤3、稳定性选择(Stability Selection)法即随机Lasso,根据得分将所有特征按其权值进行排序，们选取最优特征：博物馆数、消费吸引指数、距离指数、非直达班车数、交通指数、旅游资源指数作为低冗余度特征子集。Step 3. The Stability Selection method is random Lasso. According to the score, all the features are sorted by their weights, and the optimal features are selected: the number of museums, the consumption attraction index, the distance index, the number of non-direct buses, and the traffic index. , and the tourism resource index as a subset of low-redundancy features.
步骤4、将选出的特征作为SVR回归模型输入，以有效出行率为模型输出，训练SVR获得模型参数及其性能表现。Step 4. Use the selected features as the input of the SVR regression model, use the effective travel rate as the model output, and train the SVR to obtain the model parameters and performance.
步骤5、需求刺激有效性分析Step 5. Demand Stimulation Effectiveness Analysis
量化出行刺激手段，并将它作为某一特征属性参数的增加，如发送旅游代金卷，即可转化为消费吸引指数。利用训练后的SVR模型预测新样本的初出。相同刺激下得到最大初出的刺激即为最佳刺激策略。距离指数、交通指数、消费吸引指数、旅游资源吸引指数4个特征分别每提升0.2％后的结果，分析可知，交通因素对总的客流量提升是最明显的，敏感性最高，若把交通指数特征值提升9％，则可为景区单月提升105万的游客人数；旅游资源吸引指数(创建更多的5A或4A级景点)增长速度次之，若特征指数提升9％后，景区单月提长5万的游客人数；消费吸引指数增长相对缓慢，特征指数提升9％后，可为景区单月提升15万的游客人数；距离指数增长趋于平缓，特征指数提升9％后，可为景区单月提升5万的游客人数。Quantifying travel incentives and taking it as an increase in a certain characteristic attribute parameter, such as sending travel vouchers, can be converted into a consumption attraction index. Use the trained SVR model to predict the first appearance of new samples. The best stimulus strategy is the one that obtains the largest initial stimulus under the same stimulus. The results of each 0.2% increase in the distance index, traffic index, consumption attraction index, and tourism resource attraction index respectively show that the traffic factor is the most obvious and sensitive to the increase in total passenger flow. A 9% increase in the characteristic value can increase the number of tourists to the scenic spot by 1.05 million in a single month; the growth rate of the tourist resource attraction index (creating more 5A or 4A scenic spots) is second, if the characteristic index increases by 9%, the scenic spot will increase by 9%. The number of tourists increased by 50,000; the consumption attraction index increased relatively slowly. After the characteristic index increased by 9%, the number of tourists in the scenic spot could be increased by 150,000 in a single month; the growth of the distance index was flat, and the characteristic index increased by 9%. The scenic spot increases the number of tourists by 50,000 a month.
需要说明的是，以上所述仅为本发明优选实施例，仅仅是解释本发明，并非因此限制本发明专利范围。对属于本发明技术构思而仅仅显而易见的改动，同样在本发明保护范围之内。It should be noted that the above descriptions are only preferred embodiments of the present invention, which are merely to explain the present invention, and not to limit the patent scope of the present invention. Changes that belong to the technical concept of the present invention but are only obvious changes also fall within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910264266.XACN110163408B (en) | 2019-04-03 | 2019-04-03 | An effective analysis method of travel stimulation strategy based on the attribute characteristics of tourist origin |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910264266.XACN110163408B (en) | 2019-04-03 | 2019-04-03 | An effective analysis method of travel stimulation strategy based on the attribute characteristics of tourist origin |
| Publication Number | Publication Date |
|---|---|
| CN110163408Atrue CN110163408A (en) | 2019-08-23 |
| CN110163408B CN110163408B (en) | 2021-10-29 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910264266.XAActiveCN110163408B (en) | 2019-04-03 | 2019-04-03 | An effective analysis method of travel stimulation strategy based on the attribute characteristics of tourist origin |
| Country | Link |
|---|---|
| CN (1) | CN110163408B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852792A (en)* | 2019-10-28 | 2020-02-28 | 海南太美航空股份有限公司 | Big data analysis-based airline value evaluation method and related products |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050251430A1 (en)* | 2004-05-07 | 2005-11-10 | Satish Jindel | System and method for unbundling baggage costs from airfare prices |
| JP2010039833A (en)* | 2008-08-06 | 2010-02-18 | Act Systems:Kk | Demand occurrence forecast system, device, and method |
| CN104850903A (en)* | 2015-05-11 | 2015-08-19 | 中国旅游研究院 | Construction and budget method of local tourism popularity index |
| CN105512996A (en)* | 2015-12-28 | 2016-04-20 | 中国民航信息网络股份有限公司 | Method and system for determining most common place-of-departure |
| CN106779247A (en)* | 2017-01-11 | 2017-05-31 | 陕西师范大学 | The Forecasting Methodology of the tourism demand based on Information Entropy Combinatorial Optimization |
| CN106886911A (en)* | 2015-12-15 | 2017-06-23 | 亿阳信通股份有限公司 | A kind of travelling products method and device for planning based on user's telecommunications behavioural characteristic |
| CN108376260A (en)* | 2018-01-30 | 2018-08-07 | 陕西师范大学 | A kind of SVR tourism demand prediction techniques based on optimal subset optimization |
| CN108648004A (en)* | 2018-04-28 | 2018-10-12 | 东莞市华睿电子科技有限公司 | Excitation method based on cloud computing platform |
| CN108717790A (en)* | 2018-07-06 | 2018-10-30 | 广州市交通运输研究所 | A kind of vehicle driving analysis method based on bayonet license plate identification data |
| CN109214952A (en)* | 2017-06-29 | 2019-01-15 | 辽宁工程技术大学 | A kind of traveller's decision model construction method |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050251430A1 (en)* | 2004-05-07 | 2005-11-10 | Satish Jindel | System and method for unbundling baggage costs from airfare prices |
| JP2010039833A (en)* | 2008-08-06 | 2010-02-18 | Act Systems:Kk | Demand occurrence forecast system, device, and method |
| CN104850903A (en)* | 2015-05-11 | 2015-08-19 | 中国旅游研究院 | Construction and budget method of local tourism popularity index |
| CN106886911A (en)* | 2015-12-15 | 2017-06-23 | 亿阳信通股份有限公司 | A kind of travelling products method and device for planning based on user's telecommunications behavioural characteristic |
| CN105512996A (en)* | 2015-12-28 | 2016-04-20 | 中国民航信息网络股份有限公司 | Method and system for determining most common place-of-departure |
| CN106779247A (en)* | 2017-01-11 | 2017-05-31 | 陕西师范大学 | The Forecasting Methodology of the tourism demand based on Information Entropy Combinatorial Optimization |
| CN109214952A (en)* | 2017-06-29 | 2019-01-15 | 辽宁工程技术大学 | A kind of traveller's decision model construction method |
| CN108376260A (en)* | 2018-01-30 | 2018-08-07 | 陕西师范大学 | A kind of SVR tourism demand prediction techniques based on optimal subset optimization |
| CN108648004A (en)* | 2018-04-28 | 2018-10-12 | 东莞市华睿电子科技有限公司 | Excitation method based on cloud computing platform |
| CN108717790A (en)* | 2018-07-06 | 2018-10-30 | 广州市交通运输研究所 | A kind of vehicle driving analysis method based on bayonet license plate identification data |
| Title |
|---|
| JUAN L. EUGENIO-MARTIN 等: "Climate in the region of origin and destination choice in outbound tourism demand", 《TOURISM MANAGEMENT》* |
| ZHENG XIANG 等: "Mapping environmental change in tourism: A study of the incentive travel industry", 《TOURISM MANAGEMENT》* |
| 李娟 等: "区域旅游交通需求预测研究", 《铁道运输与经济》* |
| 李山 等: "旅游空间相互作用的引力模型及其应用", 《地理学报》* |
| 李瑶: "基于多源数据的旅游需求预测模型研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》* |
| 赵新波: "基于基站位置定位的客源分析系统的研究", 《信息系统工程》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852792A (en)* | 2019-10-28 | 2020-02-28 | 海南太美航空股份有限公司 | Big data analysis-based airline value evaluation method and related products |
| CN110852792B (en)* | 2019-10-28 | 2023-10-03 | 海南太美航空股份有限公司 | Route value evaluation method based on big data analysis and related products |
| Publication number | Publication date |
|---|---|
| CN110163408B (en) | 2021-10-29 |
| Publication | Publication Date | Title |
|---|---|---|
| Shao et al. | Threshold and moderating effects of land use on metro ridership in Shenzhen: Implications for TOD planning | |
| Haustein et al. | European mobility cultures: A survey-based cluster analysis across 28 European countries | |
| Li et al. | The effects of the urban built environment on public transport ridership: similarities and differences | |
| Panas et al. | Evaluation of Athens as a city break destination: Tourist perspective explored via data mining techniques | |
| Button et al. | A note on the effects of the number of low-cost airlines on small tourist airports' efficiencies | |
| CN117408737A (en) | Urban rail transit newly-opened line refined passenger flow prediction method and system | |
| AmilaJayasinghe | ‘Centrality measures’ as a tool to identify the transit demand at public transit stops; a case of Ahmedabad city, India | |
| CN110163408A (en) | A kind of travelling stimulation strategy efficiency analysis method based on Source market attributive character | |
| CN114861975A (en) | A joint prediction method of urban tourism traffic demand based on attraction intensity | |
| Yin et al. | Can TOD help metro station ridership ‘early recovery’from COVID-19? An empirical evidence from Nanjing | |
| Rahman et al. | The impacts of transport infrastructure development on travel route switch behavior in Bangladesh | |
| Thompson et al. | Understanding Transit Ridership Demand for a Multi-Destination, Multimodal Transit Network in an American Metropolitan Area, Research Report 11-06 | |
| Gao | Sustainability assessment of maritime tourism industry based on uncertain evidential reasoning approach in the context of big data and internet | |
| Proost et al. | Skilled cities, regional disparities, and efficient transport: The state of the art and a research agenda | |
| Vijayakumar | Optimal vehicle size for road‐based urban public transport in developing countries | |
| Almassawa et al. | Policy on the Implementation of Smart Mobility in The South Tangerang City, Indonesia Based on Public Transportation Using the Promethee Method | |
| Sharkhuu et al. | The Impact of Transport Infrastructure and Pollutant Emissions in Sustainable Tourism for Mongolia | |
| Okraszewska et al. | The effect of university campuses on the modal split of polish cities | |
| Meribai et al. | Academics' mobility in the agglomeration of Constantine: a transports post-use evaluation | |
| Korneć et al. | Urban transport as an important element of „The Smart City” | |
| Thilakaratne et al. | HopOn: A Personalized Ride-Sharing System based on Socio-Economic Factors | |
| Pulugurtha et al. | Identifying inaccessible areas with potential to enhance transit market | |
| Bian et al. | Analysis of the Influence of Built Environment on Peak Hour Travel Demand of Youth Group Based on Cell Phone Signaling Data: A Case Study of Shanghai | |
| Pappalardi et al. | A Dismissed Train Line as a New Pillar for Sustainable Tourism Development in Corsica:“The Maquis Way” Strategy | |
| Pendyala et al. | Socio-economic and transport trends in India and the United States: a preliminary comparative study |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |