Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Epidemic situation prediction method, device and equipment based on ensemble learning model, and medium

A technology of integrated learning and prediction methods, applied in the field of devices, epidemic prediction methods based on integrated learning models, electronic equipment and storage media, can solve the problems of matching epidemic data, unsatisfactory prediction effects, and affecting the accuracy of epidemic prediction results, etc. Achieving the effect of avoiding influence and strong adaptability

Inactive Publication Date: 2020-04-10
TONGDUN HLDG CO LTD
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the prediction effect obtained by using a single model is often not ideal. Moreover, because the epidemic has an incubation period, there is a certain time difference from infection to suspected, confirmed, cured or dead. The obtained epidemic data cannot be completely consistent with the actual situation. , will also affect the accuracy of the epidemic prediction results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Epidemic situation prediction method, device and equipment based on ensemble learning model, and medium
  • Epidemic situation prediction method, device and equipment based on ensemble learning model, and medium
  • Epidemic situation prediction method, device and equipment based on ensemble learning model, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Embodiment 1 provides an epidemic prediction method based on an integrated learning model, which aims to train an integrated learning model including a logistic growth model and a neural network model through epidemic data processed in a time dimension, and further automatically select a prediction model based on the loss value , And then accurately predict the epidemic trend. This method effectively avoids the impact on the epidemic prediction results caused by the time difference in data acquisition, and the integrated learning model adopted is highly adaptable, and can be quickly fine-tuned according to the real-time epidemic data, so that the prediction model selected adaptively according to the loss value can be Accurately make dynamic predictions of future epidemic trends, and the prediction results are in line with actual epidemic development trends.

[0063] Please refer to figure 1 As shown, an epidemic prediction method based on an integrated learning model incl...

Embodiment 2

[0089] The second embodiment is an improvement based on the first embodiment, please refer to figure 2 As shown, according to the epidemic data sequence X in the training set M1 M1 , Train the logistic growth model and V neural network models separately, obtain the trained logistic growth model and the trained V neural network models, and then make the integrated learning model integrate the logistic growth model's characteristics in line with the epidemic development law and neural The network model has the advantages of data abstraction capabilities, so as to more accurately predict the development trend of the epidemic.

[0090] S1301 According to the epidemic data sequence X in the training set M1 M1 , Training logistic growth model.

[0091] There is an incubation period in the epidemic, and there is a certain time difference from infection to suspected, confirmed, cured or accurate judgments of death. In order to avoid the time difference affecting the accuracy of the epidemi...

Embodiment 3

[0108] The third embodiment is a specific application embodiment corresponding to the above-mentioned embodiment 1. This embodiment uses the cumulative number of confirmed diagnoses of 2019nCov nationwide from February 1, 2020 to February 22, 2020, and obtains the prediction model 0222 and calculates it on February 25, 2020. The development trend of the epidemic from January to March 2, 2020 is predicted. The cumulative number of confirmed diagnoses in 2019nCov from February 1 to February 22, 2020 is shown in the table below.

[0109] Table 1. The cumulative number of confirmed cases of 2019nCov nationwide from February 1, 2020 to February 22, 2020

[0110] date The cumulative number of confirmed cases nationwide February 111891 February 214490 February 317341 February 420530 February 524434 February 628138 February 731264 February 834673 February 937289 February 1040262 February 1142747 February 1244765 February 1359907 February 1463950 February 1566581 Februa...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an epidemic situation prediction method based on an ensemble learning model, and relates to the technical field of epidemic situation prediction. The method comprises the following steps: obtaining epidemic situation data; processing the epidemic situation data according to the time dimension to obtain a training set M1 and a verification set M2; training an ensemble learning model according to the training set M1; calculating the verification set M2 according to the trained ensemble learning model to obtain a loss value, selecting the ensemble learning model corresponding to the minimum loss value as a prediction model, and predicting an epidemic situation trend according to the prediction model. According to the method, the influence on an epidemic situation prediction result caused by the time difference of data acquisition is effectively avoided, the future epidemic situation trend can be accurately and dynamically predicted, the model adaptability is high,and rapid fine adjustment can be carried out according to real-time epidemic situation data. The invention further discloses an epidemic situation prediction device based on the ensemble learning model, electronic equipment and a computer storage medium.

Description

Technical field [0001] The present invention relates to the technical field of epidemic situation prediction, in particular to an epidemic situation prediction method, device, electronic equipment and storage medium based on an integrated learning model. Background technique [0002] The outbreak and spread of epidemics have aroused widespread attention from the whole society. For example, the new coronavirus 2019-nCoV is coming fiercely. The current epidemic prevention and control methods are still severe, and the future trend of the epidemic will affect the hearts of hundreds of millions of people. Most of the existing schemes train a single model based on the existing epidemic data to predict the epidemic trend. However, the prediction effect obtained by using a single model is often not ideal, and because the epidemic has an incubation period, there is a certain time difference from infection to suspected, confirmed, cured or accurate judgments, and the acquired epidemic data...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G16H50/80G06N20/20G06N3/04
CPCG16H50/80G06N20/20G06N3/045
Inventor 孟丹李宏宇李晓林
Owner TONGDUN HLDG CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com