Method for identifying cross-city commuting crowd by using mobile phone data

The invention discloses a method for identifying cross-city commuting crowds by using mobile phone data, which is divided into three parts and processes as follows: 1, acquiring mobile phone data of known user types, marking road type labels on each data set, preprocessing the mobile phone data, extracting user travel OD (Origin-Destination), and screening out users with cross-city travel behaviors; obtaining a related user travel index in the data set as a data model sample; 2, constructing a decision tree model; training the decision tree by using k-fold cross validation, and determining a final crowd category recognition model by comparing model index scores of each time; and 3, acquiring mobile phone data of an unknown user type, preprocessing the mobile phone data, extracting a user travel related index, inputting the travel related index into the identification model obtained in the previous step, and outputting a corresponding user type label, namely identifying the user type. 本发明公开了一种利用手机数据识别跨城通勤人群的方法