作　　者： ;

机构地区： 广州大学旅游学院

出　　处： 《计算机仿真》 2019年第10期467-471,共5页

摘　　要： 旅游人数的急剧增加,造成游客拥挤、超载等问题,引发安全事故.对景区游客流量数据的实时跟踪预测,可为管理人员提供直接决策信息,最大限度避免事故发生.对景区游客流量数据的准确实时跟踪预测,需要在云计算下考虑景区的持续性客流状态,通过分散性客流数据的状态方程完成景区游客流量数据的实时跟踪.传统景区游客流量数据实时跟踪方法,未考虑景区的持续性客流状态,导致其实时跟踪准确度较差.提出云计算下景区游客流量数据实时跟踪预测方法.对云计算下持续性客流状态参数建模,对单向性客流、集结性客流进行有效估计,获取分散性客流数据的状态方程和观测方程.基于自适应卡尔曼滤波算法监控云计算下景区分散性客流数据信息的动态变化,并修正系统状态噪声和观测噪声方差;最后在数据预测分选和相似聚类的基础上,实现云计算下景区游客流量数据的有效跟踪.仿真数据结果表明,所提方法具有更高的跟踪精度,性能稳定可靠,且耗时较少. With the sharp increase of the number of tourists, the scenic spot is already overcrowded. This can easily lead to accidents. The real-time tracking and forecasting of tourist flow data can provide direct decision information for managers. The traditional method does not take into account the continuous tourist flow, leading to the poor accuracy of real-time tracking. Therefore, this paper puts forward a method to track and predict the tourist flow data in scenic spots based on cloud computing in real time. Firstly, the status parameter of continuous tourist flow in cloud computing was modeled. Secondly, unidirectional passenger traffic and aggregate passenger traffic were effectively estimated to obtain the state equation and observation equation of dispersed tourist flow data. Based on adaptive Kalman filter algorithm, the dynamic change of data information of distributed tourist flow in scenic spot under cloud computing was monitored, and then the variance of state noise and observation noise was corrected. Finally, we achieved the effective tracking of tourist flow data in scenic spot under cloud computing based on data prediction, data sizing and similar clustering. Simulation results show that the proposed method has higher tracking accuracy. Meanwhile, this method has stable and reliable performance, which takes less time.

关 键 词： 云计算 游客流量 实时跟踪 数据预测

领　　域： []