Geographic grid-based border-crossing driving anomaly detection method and device

The invention discloses a geographical grid-based border-crossing driving anomaly detection method and device, and the method comprises the steps: obtaining the position information of a monitored ship in real time, and enabling the position information to be the position information determined according to a global positioning system; according to the position information, geographic area information of a multi-layer grid structure stored in a distributed database is inquired, geographic area information corresponding to the position information is obtained, and the geographic area information of the multi-layer grid structure is obtained by dividing a geographic area into grids with different sizes and hierarchical structures; all the grids are organized through a multi-way tree structure; and detecting whether the monitored ship has an abnormal border-crossing driving behavior or not according to the geographic area information and based on the recurrent neural network. The problem that an existing space-t