User track position prediction method based on space-time embedding Self-Attention

Abstract

The invention provides a user track position prediction method based on space-time embedding Self-Attention, and relates to the technical field of user position prediction and space-time data mining.The method comprises the following steps: firstly, reading all user identifiers, POI identifiers, access time and geographical location information of POIs from a user historical track of an originalsign-in record; calculating the space distance cost among all POIs and the time interval and timestamp information among all track points of each user; then establishing a space-time embedded Self-Attention model based on the historical track of the user to obtain probability distribution of the next access point of the user, wherein the established space-time embedded Self-Attention model considers the influence of the geographic position information of the POI and the historical POI access time information of the user on the next access behavior of the user at the same time. According to themethod, the training speed of the track prediction model is remarkably increased, the training time of the track model is greatly shortened, and meanwhile, the prediction precision of the model is also improved.

Description

technical field [0001] The present invention relates to the technical fields of user position prediction and spatio-temporal data mining, in particular to a user track position prediction method based on spatio-temporal embedded Self-Attention. Background technique [0002] In recent years, with the rapid development of wireless communication technology, Global Positioning System (GPS) and smart mobile devices, the widespread use of positioning technology has accumulated a large amount of user trajectory information, which provides convenience for mining user behavior trajectories. Location prediction tasks are the basis of many location-based services. How to effectively use these trajectory data to predict user trajectory locations is of great significance for urban planning, smart transportation, resource planning, location-based recommendations, and advertising push. It has gradually become a research hotspot among scholars. So far, a lot of research has been done in th...

AI Technical Summary

Problems solved by technology

Based on the RNN method, even the RNN variant structure long-term short-term memory network (LSTM) and gated recurrent unit (GRU), which are better at long-term modeling, are still difficult to learn the long-term dependencies between trajectories for a large amount of trajectory data, and because Complex network structure and inability to parallelize make model training more time-consuming

Recently, CNN-based modeling methods have also achieved RNN-like performance in sequence processing tasks, and are highly parallelizable, but limit the interaction paths between elements in the sequence.

Another problem is that user behavior is highly complex, and each user trajectory is sparse, making it difficult to fully train

Images