Strip mine area function classification method based on depth area embedding

The invention discloses an open-pit mine area function classification method based on depth area embedding, and belongs to the field of open-pit mine management.The open-pit mine area function classification method comprises the steps that firstly, uniform unit area division is conducted on an open-pit mine, then feature information of different unit areas is extracted through trajectory data, and the different unit areas are constructed into a sparse unit area graph; thirdly, learning spatial embedding representation of unit region nodes by utilizing a structured deep network embedding model, and realizing spatial region embedding of unit regions; then, taking the unit region feature time sequence as the input of a bidirectional long-short-term memory neural network so as to obtain unit region time sequence features, and realizing unit region time sequence region embedding so as to make up for the problem of insufficient region time features; thirdly, performing feature fusion on the obtained embedded repres