Method and device for predicting mobile trajectory of terminal equipment

Abstract

Embodiments of the present invention provide a method and device for predicting a movement trajectory of a terminal device. Input the eigenvalues ​​corresponding to each historical track point contained in the historical track sequence into the pre-trained logistic regression model to obtain the weight values ​​corresponding to multiple target stay points; each target stay point and the weight corresponding to the target stay point Values ​​are spliced, and the vectors of spliced ​​elements corresponding to each target stay point are input into the pre-trained cyclic neural network model to obtain the predicted trajectory of the terminal device to be predicted in the target area. Because in the embodiment of the present invention, the trajectory behavior characteristics of the terminal device are represented by the weight value of the stay point, and the position characteristics of the terminal device are represented by the user stay point; by combining the stay point and the weight value of the stay point, as a loop The training samples of the neural network model are obtained, and the cyclic neural network model used to predict the trajectory behavior of the terminal device is obtained, so as to accurately predict the mobile trajectory of the terminal device.

Description

technical field [0001] The present invention relates to the technical field of positioning and navigation, in particular to a method and device for predicting a movement track of a terminal device. Background technique [0002] With the development and wide application of positioning technology, location-based services have gradually become an indispensable part of life. By analyzing the trajectory information of the terminal equipment and mining the hidden terminal equipment information to improve the service experience of the terminal equipment, it has become an important field of data mining. Using the trajectory information of the terminal equipment, for example, the GPS (Global Positioning System, Global Positioning System) data of the terminal equipment, predicting the trajectory of the terminal equipment and analyzing the behavior of the terminal equipment is very important for applications such as navigation services and traffic management. [0003] At present, the ...

AI Technical Summary

Problems solved by technology

[0004] Since the existing probabilistic methods ignore the mutual influence between the behavior of the terminal device and the location of the terminal device, the existing probabilistic class that predicts the behavior and location of the terminal device separately based on the GPS track information of the terminal device method, resulting in reduced prediction accuracy of end-device trajectories

Images