Method for predicting next track point of user

Abstract

The invention discloses a method for predicting a next track point of a user. The method comprises the following steps: crawling a certain amount of data: an ID of the user, position information of aseries of short-term and long-term historical track points corresponding to the user, and a timestamp of each track point; constructing a feature interaction self-attention network model based on thecrawled information, and making attention in combination with a result that the position information of the long-term historical track points of each user passes through a self-attention layer; performing optimal training on the parameters by using a cross entropy loss function; for a new user and a series of historical track points thereof, and constructing a series of instances by utilizing theID information, the position information of a series of historical track points corresponding to the user and the timestamp of each track point, and inputting the instances into a trained feature interaction self-attention network model, thereby obtaining a series of sorting scores of predicted positions. According to the method, the problem of predicting the next track point by utilizing the richmetadata of the user and the historical track is solved, and the prediction accuracy is greatly improved.

Description

technical field [0001] The invention relates to the fields of machine learning and trajectory prediction, in particular to a method for predicting the next trajectory point by using the user's historical trajectory. Background technique [0002] With the development of location collection technology and the popularity of smart devices, it is easier to digitize and share human daily affairs with friends on social networking sites. Mobility and prediction are critical in a wide range of applications and services, from urban planning, traffic forecasting and epidemic control to location-based advertising and recommendations. [0003] The key to mobility prediction is how to capture useful mobility patterns from historical trajectories. Previous works on mobility prediction are mainly based on Markov models or cyclic models. The Markov model is mainly based on the frequency of occurrences of locations visited in the past; the success of recurrent neural networks (RNN) in langu...

AI Technical Summary

Problems solved by technology

However, two important challenges are not well addressed in these existing works

First, spatio-temporal features usually include location IDs and time IDs, and do not consider the effects of explicit higher-order interactions between features

This may help distinguish mobility modeling from sequence proposals, and may lead to improvements in mobility prediction; second, network training is time-consuming, especially for long sequences

Images