Infectious disease dynamics model based on machine learning algorithm and analysis method

Abstract

The invention provides an infectious disease dynamics model based on a machine learning algorithm and an analysis method. The method comprises the steps: S1, building an SEIR model, and carrying out classification on crowds in a target region according to a virus infection state, the crowds including susceptible crowds, latent crowds, infection confirmation crowds and rehabilitation crowds; S2, according to a preset propagation process, fitting an infection probability, and simulating a virus infection process; and S3, upgrading and optimizing the constructed SEIR model, including: introducingvirus characteristic analysis, and correcting the virus infection process; introducing human intervention factors, and simulating an inter-group infection process; and obtaining a corrected model, generating propagation trend data by using the corrected model, and outputting an infectious disease related population quantity situation curve.

Description

technical field [0001] The invention relates to the technical field of machine learning algorithms, in particular to an infectious disease dynamics model and analysis method based on machine learning algorithms. Background technique [0002] In addition to effective detection and isolation methods, one of the key points of epidemic prevention and control is to predict the trend of virus transmission according to the epidemic situation, and carry out targeted prevention and control work in a timely manner or even in advance. [0003] To achieve trend prediction, it is impossible to rely solely on relevant statistical work. The most direct and effective method is to establish a corresponding data model based on the characteristics of the virus to help people understand the epidemic mechanism of infectious diseases, analyze the virus transmission trend and calculate the corresponding transmission based on the model Data, so as to provide data support and guidance for actual pre...

AI Technical Summary

Problems solved by technology

However, in actual situations, human intervention has a great impact on the spread of the epidemic, such as large-scale isolation measures, crowd movement, etc. If it is not included in the scope of the model, the prediction results of the model will have a large deviation

[0009] 2. Some important parameters of the model depend on expert experience

However, due to factors such as different types of viruses, mutations, and differences in personnel experience, the method of fixed experience values ​​has great chance and error probability, which affects the model results.

Images