Flu prediction model generating method and device and computer readable storage medium

Abstract

The invention discloses a flu prediction model generating method, and the method comprises the steps: determining a to-be-predicted target area and public opinion keywords matched with flu prediction;obtaining a public opinion data sequence of the target area in a plurality of consecutive time units according to the public opinion keywords, and using the public opinion data in the public opiniondata sequence as candidate features to construct a candidate feature set; performing wavelet denoising processing of the candidate features; detrending the candidate features in the candidate featureset after the wavelet denoising processing; determining a preset number of features, and screening out a preset number of features from the candidate feature set to form a prediction feature set; training a prediction model constructed based on the xgboost algorithm according to the prediction feature set as a training sample so as to determine model parameters. The present invention also providesa flu prediction model generating device and a computer readable storage medium. The present invention improves the prediction accuracy of the fu prediction model.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method, device and computer-readable storage medium for generating an influenza prediction model. Background technique [0002] With the development of artificial intelligence technology, the number of related studies on public health incidents by monitoring network data sources has increased. In particular, search service providers and other companies that hold a large amount of user behavior data have made many attempts in this direction. There are also related research follow-ups. However, the prediction accuracy of the influenza prediction model is still limited. The main reason is that public opinion data fluctuates greatly, and trend changes are easily affected by platform user usage. In recent years, the number of blog users has decreased sharply, and the overall trend of the microblog factor has also shown a downward trend. This trend has affected the accurac...

AI Technical Summary

Problems solved by technology

However, the prediction accuracy of the influenza prediction model is still limited. The main reason is that public opinion data fluctuates greatly, and trend changes are easily affected by platform user usage. In recent years, the number of users of Bo has decreased sharply, and the overall trend of Weibo factors has also shown a downward trend. This trend has affected the accuracy of predictions.

The existing flu predictions based on public opinion do not deal with the large fluctuations and trend changes of public opinion factors. Instead, they use simple linear regression or random forest methods to model public opinion factors for flu prediction, resulting in low flu prediction accuracy.

Images