Prediction method based on mobile Markov model under space-time big data

Abstract

The present invention relates to the technical field of intelligence transportation and space-time big data, and specifically relates to a prediction method based on a mobile Markov model under space-time big data. The method comprises the steps of successively performing de-noising processing and clustering processing on acquired history position data, obtaining a clustering cluster through a joint density clustering algorithm, establishing interest points according to the clustering cluster, performing de-noising processing on the interest points to retain the real interest points, and establishing a mobile Markov model; and extracting interest points of a mobile subscriber after mobile subscriber data are acquired and processed by the above steps, and predicting the next position of themobile subscriber according to the mobile Markov model. The problems that under the space-time big data environment, data storage processing amount is large, and prediction accuracy and precision areunsatisfactory are solved, and precision and accuracy of mobile subscriber position prediction are improved.

Description

technical field [0001] The invention relates to the technical fields of intelligent transportation and spatiotemporal big data, in particular to a prediction method based on a moving Markov model under spatiotemporal big data. Background technique [0002] Due to the inherent characteristics of spatial entities and spatial phenomena in the space in which spatiotemporal data reside in three aspects: time, space, and attributes, spatiotemporal big data presents the complexity of multidimensional, semantic, and spatiotemporal dynamic associations. Spatiotemporal big data includes three-dimensional information of time, space, and thematic attributes, and has the comprehensive characteristics of multi-source, massive, and fast update. Spatio-temporal data has become a key element of smart city resources. By studying the formal expression of multi-dimensional correlation description of spatio-temporal big data, dynamic modeling of correlation and analysis of multi-scale correlatio...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of the prior art, the present invention provides a prediction method based on the moving Markov model under the spatio-temporal big data environment to solve the problem of large amount of data storage and processing in the spatio-temporal big data environment and the prediction accuracy. and precision are not ideal, improve the precision and accuracy of mobile user location prediction

Images