An aggregated population influenza prediction system, storage medium and device

Abstract

The invention discloses an aggregated group influenza prediction system, comprising an LSTM module, a LightGBM module, and a prediction module: the LSTM module is configured to use LSTM to obtain a prediction value n of the number of influenza infections in an aggregated group; the LightGBM module is configured to adopt The LightGBM algorithm predicts the probability that the ith person in the aggregated group is infected with influenza, and obtains an infection probability sequence in descending order; the prediction module is configured to calculate the predicted value n of the number of influenza infections according to the probability obtained by the LightGBM module, and obtain The predicted revised value of the number of influenza infections, and the pre-predicted revised value of the individuals with the highest probability of contracting influenza is determined as a high-risk group. The invention combines the influenza outbreak trend of the aggregated group with the influenza infection probability of each individual in the group, and can accurately predict the susceptible persons in the aggregated group.

Description

technical field [0001] The invention belongs to the fields of artificial intelligence, data statistics, medical informatization, etc., and relates to a method, storage medium and system for predicting influenza in an aggregated population. Background technique [0002] Influenza is an acute respiratory tract infection disease caused by influenza virus. Its clinical manifestations are rapid onset of high fever, pain, fatigue, and mild respiratory symptoms. It can lead to death in severe cases, and its infectivity is strong. However, because the symptoms are easily confused with the common cold and other upper respiratory tract infection diseases, many patients often ignore them in the early stage of the disease, which not only seriously damages their own health, but also easily infects others, causing the outbreak of influenza and causing huge social and national losses. loss. [0003] At present, some progress has been made in the prediction of influenza trends. For example...

AI Technical Summary

Problems solved by technology

[0006] The GBDT algorithm is currently widely used in the industry, but because the GBDT algorithm is a parallel integration algorithm, its efficiency is low, and the efficiency is too low when the feature dimension is high or the amount of data is too large.

Images