Neural network-based infectious disease prediction method, system and device, and storage medium

Abstract

The invention provides an infectious disease prediction method, system and device based on a neural network and a storage medium; the method comprises the steps: obtaining a test graph feature according to test data corresponding to a target infectious disease and a convolutional neural network model of a prediction neural network model, the convolutional neural network model being a graph convolutional neural network; according to the meteorological environment data influencing the target infectious disease and the convolutional neural network model, acquiring the meteorological chart features, and fusing the meteorological chart features and the test chart features; and according to the test chart features and a recurrent neural network model of the prediction neural network model, acquiring a final prediction value corresponding to the target infectious disease, wherein the recurrent neural network model comprises a gating circulation unit. For the characteristic that infectious disease data is not neighborhood grid structure data, the graph convolutional neural network is used, and even under the condition of less training data, the graph convolutional neural network can well extract features, so that the prediction precision is ensured.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a neural network-based infectious disease prediction method, system, device and storage medium. Background technique [0002] Influenza epidemic has always been a key issue in epidemiology and public health, because influenza virus is very easy to mutate and spreads very fast, it is difficult to generate immunity to mutated strains in time, resulting in different scales of influenza every year epidemic. The use of big data to predict influenza epidemics is also one of the topics of increasing concern in the field of data mining and machine learning. [0003] Influenza is one of the infectious diseases. Traditional methods often use the SEIR infectious disease model to predict the epidemic trend. The SEIR infectious disease model divides the population into four groups: susceptible (Susceptible), exposed (Exposed), sick (Infectious) and recovered (Recover...

AI Technical Summary

Problems solved by technology

But this simplicity also limits the expressiveness of the model

Images