Artificial intelligence method for big data deep learning dynamic variable multistage space-time prediction

Abstract

The invention discloses an artificial intelligence method for big data deep learning dynamic variable multistage space-time prediction. The method comprises the steps of obtaining a single-time single-space variable set; obtaining a to-be-selected input variable set; initializing a to-be-selected single-time single-space model; performing single-time single-space model training; performing single-time single-space model test; performing optimal single-time prediction deep learning model; and performing optimal single-time prediction deep learning model test. According to the method, the system and the robot, the input variable items of each space-time are differently combined, and the variable set of each space-time combination is trained and tested through the deep learning neural network model, so that the optimal space-time variable combination is found, all input variable data do not need to participate in training and prediction, the cost can be saved, and the efficiency is improved. Therefore, the efficiency of space-time training and space-time prediction is improved, and the best space-time prediction effect can be obtained through the space-time prediction deep learning model selected through the space-time prediction effect.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a dynamic variable spatio-temporal prediction method based on deep learning of multi-level spatio-temporal big data. Background technique [0002] In the process of realizing the present invention, the inventors have found at least the following problems in the prior art: different spatio-temporal data influence each other, but the resolutions are different, and the influencing factors that play a major role are also different. Factors affecting the epidemic are different at different spatial and temporal resolutions (for example, a village, a street, a city, a province, and a country). period), different spaces (such as south, north, rural areas, cities) have different factors affecting the epidemic situation, but the input indicator variables of different epidemic spatiotemporal prediction models in the prior art are the same, [0003] Therefore, the prior art ...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to address the defects or insufficiencies of the existing technology and provide a dynamic variable spatio-temporal prediction method based on multi-level spatio-temporal big data deep learning to solve the problem of similar input index variables of different epidemic spatio-temporal prediction models in the prior art

Images