Data mining and quarantine method based on Bayesian network

Abstract

The invention provides a data mining and quarantine method based on a Bayesian network. The method comprises the following steps: simulating an infection process through recent social information of people, establishing a Bayesian network g, defining the influence of each person on other persons as an influence function effect (x), obtaining an influence value of each person, and sequencing all persons by using the effect (x), and obtaining people most likely to be infected by utilizing a greedy algorithm. The method is based on data mining application of the Bayesian network, can be used as amonitoring means for epidemic situation development, finds out patients with as few resources as possible, thereby reducing epidemic situation monitoring cost; and in epidemic situation-based normalized monitoring, data in the Bayesian network is naturally matched with real data, so that the method has a good matching degree and has a good effect in a data experiment. On the basis of the method,a unified big data epidemic situation detection engine, a large vehicle-mounted integrated rt-prc large-scale detection instrument and the like can be researched and developed, efficient reaction measures are provided for unknown epidemic situations or biological warfare in the future, and the method has a good market application scene.

Description

technical field [0001] The present invention relates to the field of big data application technology, and more specifically, relates to a Bayesian network-based data mining and quarantine method suitable for epidemic detection and detection. Background technique [0002] When the epidemic spreads in various countries around the world, it has the characteristics of easy transmission, difficult diagnosis, and severe symptoms. In the early stage of the outbreak in various countries, because there was no relevant information before and no targeted detection technology was developed, facing a large number of people who needed to be tested The speed of detection is very slow, so many infected people have not been detected in time, and more people have been infected, which has become part of the reason why the epidemic has gone out of control; in the middle and late stages of epidemic prevention and control, there will be sporadic cases in various places. People who suddenly get si...

AI Technical Summary

Problems solved by technology

Such epidemic prevention and control methods have the disadvantage of high cost; due to cautious and pessimistic speculation about the development trend of the epidemic, the risk of epidemic outbreaks will become the norm in the future, and large-scale detection may become a routine method. In order to reduce the cost of large-scale detection Cost, it is necessary to provide a feasible algorithm that can play a monitoring role to assist in epidemic monitoring

Images