Least square method path prediction algorithm based on commensurability idea

Abstract

The invention discloses a least square method path prediction algorithm based on a commensurability idea. Based on a real user trajectory, the algorithm collects a trajectory data set, extracts latitude and longitude data, divides the trajectory according to a time threshold, plans the area where all points from a starting point of the trajectory to a point which not exceeds a distance threshold are located as a moving point, connects each center point between adjacent moving points in the trajectory to form a new trajectory map, obtains angle values corresponding to all adjacent points, obtains a turning angle set according to a angle threshold, verifies the turning angle set through the commensurability, obtains error values of the current trajectory by least square method fitting, predicts a turning angle of a next trajectory of a user according to the error values, and finally plans a path by combining time and speed. Counting and finding out a user movement angle change law can further improve the accuracy of prediction based on the user.

Description

technical field [0001] The invention belongs to the technical field of path prediction, and in particular relates to a least square method path prediction algorithm based on the idea of ​​commensurability. Background technique [0002] For a long time, predicting the trajectory of human movement has been an important topic in scientific research, and it also plays an important role in practical applications, just like in the field of communication, with the development of current communication technology, the needs of users are also gradually improve. Not only must the user's call connectivity be guaranteed, but also the user's online experience needs to be improved with the development of the Internet. To ensure the user experience, the guarantee of mobile connectivity becomes extremely important. If the user's next location can be known and the content can be cached in the corresponding base station in advance, the user's mobile connectivity will be greatly improved, so ...

AI Technical Summary

Problems solved by technology

This method has high accuracy when predicting simple user movement, such as linear movement, but once it involves more complex user movement, because of the simplicity of its prediction model, it is often limited and cannot obtain a more ideal forecast result

Images