Method and device for judging saturation quantity of tourists in scenic spot

The invention discloses a scenic spot tourist saturation capacity judgment method and device, and the method comprises the steps: carrying out the mining of the correlation of mobile phone mac monitored by a WiFi probe, then setting a prediction step length h, constructing a plurality of learning tasks, constructing a corresponding training set and a corresponding test set for each learning task through a data set sample, optimizing a multi-task model through the training set, and carrying out the prediction of the prediction step length h. And inputting an optimized multi-task prediction model through a test set to obtain tourist prediction data at a set prediction step length moment, thereby accurately predicting the number of tourists in the scenic spot at the next moment, and achieving the purpose of early warning the saturation amount of the scenic spot. 本发明公开了一种景区游客饱和量的判断方法和装置，通过分挖掘WiFi探针监测到的手机mac的相关性，然后设定预测步长h，构造多个学习任务，对每一个学习任务通过数据集样本构造对应的训练集和测试集，通过训练集优化多任务模型，然后通过测试集输入优化的多任务预测模型，得到设定预测步长时刻的游客预测数据，从而实现准