Target port prediction method

Abstract

The invention discloses a target port prediction method, which comprises the following steps: modeling a known port sequence of a ship route by adopting a probability graph model and a recurrent neural network model, and outputting the distribution of a target port to be reached by combining data fusion. The invention provides a target port prediction scheme, which can accurately predict a targetport to be reached by a ship in the future in real time.

Description

technical field [0001] The invention belongs to the technical field of port prediction, and in particular relates to a method for predicting a destination port. Background technique [0002] The detection and motion direction judgment of surface warship targets are widely used in many fields. It is of great significance to the monitoring of the status of transport ships, port management and homeland security. [0003] Traditional port forecasting relies on the log records reported by the crew, but the crew cannot fill in the relevant information in real time or accurately, making it impossible to judge the port that the ship will arrive in the future. [0004] Therefore, in view of the above technical problems, it is necessary to provide a method for predicting the destination port. Contents of the invention [0005] In view of this, the object of the present invention is to provide a prediction method that can predict the destination port that the ship will arrive in th...

AI Technical Summary

Problems solved by technology

[0003] The traditional port forecast relies on the log records reported by the crew, but the crew cannot fill in the relevant information in real time or accurately, making it impossible to judge the port that the ship will arrive in the future

Images