KR101960504B1 - Apparatus and method for epidemic spread prediction modeling - Google Patents

Abstract

The present invention relates to an apparatus for predicting an epidemic spread and a method thereof. The apparatus includes a processor for modelling epidemic model which expresses propagation and spread over restricted areas for any disease and a spreading model which expresses propagation and spread over a plurality of zones through a network according to an execution of an epidemic spread prediction modeling program to output a simulation process over time. The spreading model is modeled based on the probability of the spread between interconnected zones, which is calculated based on population, the number of infected people, and network and weather condition information for each zone and is modeled to spread the disease when the probability of the spread exceeds a predetermined threshold and the number of the infected people on the epidemic model of a spreading area is increased. Thus, a protection model based on the prediction of the epidemic spread can be modeled and analyzed.

Description

[0001] APPARATUS AND METHOD FOR EPIDEMIC SPREAD PREDICTION MODELING [0002]

The present invention relates to an apparatus and method for modeling infectious disease spread prediction.

Predictive analysis is a technique of statistical and data mining areas that extract information from data and use it to predict trends and behavior patterns. This predictive analysis can be applied to all areas of decision making based on the information obtained from the data. The core of predictive analysis is to predict unknown variables after understanding the relationship between variables. To this end, various approaches are used depending on the characteristics of the data and the objects to be predicted.

Among the various fields requiring predictive analysis, studies on the epidemic model that takes place under limited circumstances are actively being conducted. However, the existing disease analysis was dominated by a pandemic model that analyzed the spread of disease in a restricted environment where there is no population flow. Predictive and analytical limitations are limited by the pandemic models that do not take into account the transfer of these diseases. In addition, existing network models do not extend to a local network that describes the spread between people and people, and it is difficult to clearly communicate the path of disease spread, and it is difficult to propose preventive measures against spreading. In the case of a long-distance network, it is hard to see except for a case where an aircraft network is applied. However, in reality, roads are more complex than air, and disease is more likely to spread to road networks than to aircraft networks.

In recent years, infectious disease prognosis prediction software using mathematical models and Big Data has been developed. "FluT" to predict the spread of influenza, "EpiSimS" to identify pathogens and infection pathways, "FRED" to focus on human interactions, GLEAM, "which predicts the spread of infectious diseases in the world, etc. These conventional disease analysis techniques can be applied to epidemic models, airline networks, real road networks, Dispersion Direction, Protection Plan, etc. are implemented as shown in Table 1 below.

EpidemicModel Airline Network Real RoadNetwork Dispersion
Direction Protection Plan GLEAMviz ○ ○ △ × × EpiSIM ○ × × × △ FRED ○ × × × × STEM ○ × △ × △ AnyLogic ○ × × × × Ours (EVAsim) ○ ○ ○ ○ ○

In Table 1, & cir &: implemented, & cir &: partially implemented, and x: not shown.

In this regard, Korean Patent Laid-Open No. 10-2015-0098402 (entitled "Pestilence Diffusion Area Modeling Device and Method") discloses a method for monitoring the occurrence of infectious diseases (plague) in horticultural crops, crops, In a web-based epidemic (plague) monitoring and prediction system, the time-based plague spreading region is modeled before the data is transferred to a visualization apparatus for spreading plague based on coordinate values of plague-affected areas received from the plague-predicting apparatus , An apparatus for storing the modeling data, and a method thereof are disclosed.

On the other hand, it is the most ideal way to block the disease before it spreads, but in reality it is almost impossible to block new viruses and variant viruses in advance. Therefore, the best way to do this is to stop the spread if you have discovered the existence of the disease since the spread began. Protective models that can be applied in the real world can be vaccines, local blockades, and people's movement inhibition. There is also a need for a technique that can analyze information about how much protection and recovery is achieved when applying this protection model.

One embodiment of the present invention is to solve the problems of the prior art described above, and it is possible to set various interfaces such as infectious disease spreading parameters, terrain information setting and infection path, And to provide a method and apparatus for estimating an epidemic proliferation prediction model capable of modeling and analyzing a protection model according to the predicted epidemic proliferation prediction.

In addition, one embodiment of the present invention provides a visual analysis process that allows a user to easily set data related to epidemic proliferation prediction modeling in the course of modeling an epidemic proliferation prediction model and supports visual confirmation of the results of each modeling simulation And to provide a method for predicting an epidemic spreading prediction model and a method thereof.

It should be understood, however, that the technical scope of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to an aspect of the present invention, there is provided an apparatus for modeling an epidemic proliferation prediction model, comprising: a memory for storing an epidemic prognosis prediction modeling program; And a processor for executing the program stored in the memory. At this time, the processor may be an epidemic model expressing propagation and diffusion to a limited area for an arbitrary disease according to the execution of the epidemic prognosis prediction modeling program, and an epidemic model for spreading and spreading And outputs a simulation process according to time. Also, the diffusion model is modeled according to inter-area spreading probabilities calculated based on the number of populations, the number of infectors, network information, and weather condition information for each zone, and if the spreading probability exceeds a predetermined threshold value, To increase the number of infections on the epidemic model of the spreading zone.

In another aspect of the present invention, an epidemic diffusion prediction modeling method includes an epidemic model expressing propagation and diffusion for a limited area for an arbitrary disease, and propagation and diffusion Modeling a spreading model that represents a spreading model; And outputting a simulation process according to time based on the modeling result of any one of the epidemic model and the diffusion model. At this time, the diffusion model is modeled according to inter-area spreading probability calculated based on the number of populations, the number of infected persons, network information, and weather condition information of each zone, and if the spreading probability exceeds a predetermined threshold value, To increase the number of infections on the epidemic model of the spreading zone.

According to any one of the above-described tasks of the present invention, a user can set various predetermined parameters for predicting infectious disease spread, and a visual analysis tool for infectious disease prediction prediction modeling that can be compared and analyzed according to actual data Can be provided.

In addition, according to any one of the tasks of the present invention, by using the functions provided by the epidemic proliferation prediction modeling device, the user can apply the attribute of the disease to be predicted and analyzed, You can simulate in advance. You can also simulate the effects of applying a protection model to a spreading disease, so you can quickly find out what is the most appropriate protection model.

1 is a configuration diagram of an epidemic proliferation prediction modeling apparatus according to an embodiment of the present invention.
2 is a conceptual diagram for explaining an epidemic proliferation prediction modeling method according to an embodiment of the present invention.
FIG. 3 is an exemplary diagram illustrating a method of setting geographical information according to an embodiment of the present invention. Referring to FIG.
FIG. 4 is an example of a method of visually representing an infectious hexagonal tile cell according to an embodiment of the present invention.
5 is an example of a result of simulating a protection model according to an embodiment of the present invention.
6 is an example of applying the infectious disease fitting algorithm according to an embodiment of the present invention.
FIG. 7 is an example of a result of performing an infection fitting algorithm according to an embodiment of the present invention.
FIG. 8 is an example of a visual analysis user interface supporting the epidemic proliferation prediction modeling according to an embodiment of the present invention.
FIG. 9 is a flow chart for explaining an epidemic proliferation prediction modeling method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description in the drawings are omitted, and like parts are denoted by similar reference numerals throughout the specification. In the following description with reference to the drawings, the same reference numerals will be used to designate the same names, and the reference numerals are merely for convenience of description, and the concepts, features, and functions Or the effect is not limited to interpretation.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when a component is referred to as "comprising ", it is understood that it may include other components as well as other components, But do not preclude the presence or addition of a feature, a number, a step, an operation, an element, a component, or a combination thereof.

Herein, the term " part " or " module " means a unit realized by hardware or software, a unit realized by using both, and a unit realized by using two or more hardware Or two or more units may be realized by one hardware.

1 is a configuration diagram of an epidemic proliferation prediction modeling apparatus according to an embodiment of the present invention.

As shown in FIG. 1, the epidemic diffusion prediction modeling apparatus 100 includes a memory 110 and a processor 120.

The epidemic proliferation prediction modeling apparatus 100 according to an embodiment of the present invention sets various interfaces such as infectious disease spreading parameter, topographic information setting and infection path, and predicts infectious disease spread through simulation of the infectious disease spreading prediction modeling result Provides a visual analysis process that can be analyzed.

The memory 110 stores an infectious disease prognosis prediction modeling program for modeling an infectious disease prognosis prediction model.

In addition, the memory 110 may be provided with an infectious disease proliferation prevention model (i.e., a protection model) suitable for setting the conditions (hereinafter referred to as "parameters") necessary for modeling the infectious disease spreading prediction model, And a visual analysis program that provides a visual analytics process that visually supports information that can be used to analyze the results of each modeling. For reference, the epidemic proliferation prediction modeling program and the visual analysis program can operate in conjunction with each other as separate programs. It is also possible that a visual analysis program is included and operated as a subprogram of the epidemic proliferation prediction modeling program.

This memory 110 is collectively referred to as a non-volatile storage device that keeps stored information even when power is not supplied, or a volatile storage device that requires power to maintain stored information.

The processor 120 executes a program stored in the memory 110, and can perform the following processing.

Hereinafter, with reference to Figs. 2 to 6, each operation processed through the processor 120 will be described in detail.

2 is a conceptual diagram for explaining an epidemic proliferation prediction modeling method according to an embodiment of the present invention.

As shown in FIG. 2, the processor 120 processes Multimodal for Epidemic Diffusion Prediction modeling, including an Epidemic Model, a Spreading Model, and a Protection Model.

The processor 120 may also provide the user with visual representations of data associated with modeling and modeling the results of each of these models.

Here, the epidemic model represents propagation and diffusion of disease in a limited area, the diffusion model represents the spread of disease to a large area through the network, and the protection model represents the protection method applied to each diffusion. In addition, the processor 120 supports a Geo-settings mode for setting geographical information applied to epidemic diffusion prediction modeling.

First, a process of setting geographic information to be applied to simulate an epidemic proliferation prediction model (referred to as "Pre-processing for Geometry" in FIG. 2) will be described.

FIG. 3 is an exemplary diagram illustrating a method of setting geographical information according to an embodiment of the present invention. Referring to FIG.

As shown in FIG. 3, in one embodiment of the present invention, each defined space (zone) is represented by one hexagonal tile (Hextile) cell. Specifically, the geographical information in which the actual terrain information is represented by a grid type can be mapped onto an arbitrary map space to which a plurality of hexagonal tile cells are to be included. For reference, geographic and population information is available from NASA's Socioeconomic Data and Applications Center (SEDAC) "grid population" and "grid area" data. Map the actual geographic information to the space that will contain the hexagonal tiles, generate the hexagonal tiles in the area where the terrain exists, and take the population information belonging to the tiles and apply the population number. Accordingly, the area data and the population data are mapped by hexagonal tiles, and one hexagonal tile cell may include the number of people living in the area, that is, population information.

As such, the process of mapping the geographic information to the hexagonal tile cells is performed through the Geo-settings mode. In addition, the geographical information setting mode can be used to adjust the size of a hexagonal tile (road size, road network, Weather Contions) can also be set.

Next, a description will be given of the process (shown as "Model settings" in FIG. 2) in which the processor 120 models predefined models related to the epidemic spread prediction.

Let us describe how the processor 120 models the epidemic model.

As described above, the spread of infection can be expressed using a pandemic model and a diffusion model, which deals with the spread of disease within a limited space. That is, the pandemic model represents the spread of disease within the hexagonal tiles.

At this time, the epidemic model can express the disease spread within the corresponding cell through the SIR model or the SEIR model using the population information in the area. The SIR and SEIR models are mathematical models for infectious disease (infectious disease) modeling. The SIR model and the SEIR model are expressed as shown below.

<SIR Model>

In the SIR model, the host is classified as susceptible (S), infected (I), or recovered (R). In other words, S represents the number of persons susceptible to infection by susceptible number, I represents the number of patients infected with the 'Infectious number', and R represents the number of patients recovered from the disease by 'Recovered (or immune) number' Immune system).

As a result, the disease becomes a form in which the infection spreads through the process of S-> I-> R. The differential equation of the SIR model is expressed by Equation 1 below.

[Equation 1]

In Equation 1 above, β is infection rate, γ denotes a recovery ratio.

<SEIR Model>

The SEIR model is a model of a latent phase disease, with the E (Exposed) step added to the SIR model. In other words, the SEIR model is a model with an infected but still infectious group (E).

At this time, the disease is recovered after spreading the infection through the process of S-> E-> I-> R, and the differential equation of the SEIR model is expressed as Equation 2 below.

&Quot; (2) &quot;

In the above equation (2),? Denotes the latency period,? Denotes the infection rate,? Denotes the recovery rate, and? Denotes the mortality rate.

For reference, the processor 120 may use the MSEIR model as a pandemic model.

A method by which the processor 120 models the diffusion model will be described.

The pandemic model described above is limited in that it can not consider spreading to an outside area beyond a limited space. Thus, the processor 120 uses a diffusion model together with an epidemic model to connect diffusion in a limited space to diffusion in a larger space. At this time, each hexagonal tile is used as an agent, an independent pandemic model is calculated, an infected person according to a pandemic model calculation result is agent-based simulation, Can be expressed.

Indicators used as diffusion probabilities in the diffusion model can be set by population, number of infected persons, network, temperature, wind, and the like. For example, population exchanges between metropolitan cities have more exchanges than those with less populated satellite cities. In addition, when the number of infected persons is large, the probability of disease spreading is affected. Also, depending on the type of disease, temperature or wind (ie, environmental factors) can affect the spreading probability. Accordingly, the spreading factor can be adjusted by adjusting the parameters for each index element affecting the diffusion prediction modeling.

)은 아래의 수학식 3과 같이 정리될 수 있다.The spreading probability for two hexagonal tiles (i, j) to which the network is connected

Can be summarized as Equation (3) below.

 &Quot; (3) &quot;

,

,

은 각각 사용자가 지정한 파라미터로서 확산 확률 조정 변수이다. 이때,

는 두 셀의 감염자 수 이고,

는 두 셀의 총 인구 수 이며,

는 i로부터 j로의 바람 벡터이고,

는 해당 질병의 최적 온도이며,

는 현재 온도이다. 확산 확률 조정 변수는 질병 확산과 관련하여 각 파라미터의 가중치를 설정할 수 있다.In Equation (3)

,

,

Is a spreading probability adjustment variable as a parameter designated by the user. At this time,

Is the number of infectors in two cells,

Is the total population of two cells,

Is a wind vector from i to j,

Is the optimal temperature for the disease,

Is the current temperature. The spreading probability adjustment variable can set the weight of each parameter with respect to disease spread.

)을 이용하여, 연결되어 있는 노드 간의 확산 확률을 연산하고, 연산의 결과가 기설정된 임계값(threshold)을 초과할 경우 질병의 확산이 발생하고 해당 셀의 유행성 모델 상의 감염자 수가 증가한다.This diffusion probability (

) Is used to calculate the spreading probability between the connected nodes, and when the result of the calculation exceeds a predetermined threshold, the spread of the disease occurs and the number of infected persons on the pandemic model of the corresponding cell increases.

Next, the processor 120 simulates the epidemic proliferation prediction model and models the corresponding protection model (denoted by "Simulation" and "Simulation Result" in FIG. 2).

FIG. 4 is an example of a method of visually representing an infectious hexagonal tile cell according to an embodiment of the present invention. 5 is an example of a simulation result of a protection model according to an embodiment of the present invention.

As shown in FIG. 4, each of the hexagonal tiles can express the extent of the spread of the infectious disease using the color inside the cell, the color of the cell edge line, the arrows crossing the inside or outside of the cell, and the cell height. 4) indicates a disease diffusion direction, and a border line ("Border line" in FIG. 4) indicates a protec- tion plan, Quot; Inner cell color " of the cell refers to the spreading phase and the infection rate, and the height of the cell ("Height" As shown in FIG. 4, the color of the border lines can be set differently to distinguish protection policies such as quarantine or vaccination, and the degree of protection policy can be distinguished according to color differences. In addition, as shown in FIG. 4, a diffusion phase and a recovery phase may be expressed according to a difference in chroma saturation inside the cell.

A description will be given of how the processor 120 models the protection model.

The protection model includes an isolation plan and a vaccination plan. In other words, the protection model is an action that the user should take as the spread of the infection progresses, which corresponds to the operation of operating the quarantine or distributing the vaccine. The quarantine policy is an action corresponding to the quarantine station, and no AC flows into the cell. The vaccination policy is to prevent the spread of vaccine by distributing the vaccine. It further reduces the spreading probability of the infection to the relevant cell, thereby reducing the diffusion itself.

FIG. 5 shows an example of a simulation of a protection model, in which the purple border cell represents a quarantine policy and the orange cell represents a vaccination policy. Comparing FIGS. 5 (a) and (b), it can be seen that the effect of slowing the spreading rate of the infection is further reduced when the step b) is carried out. According to the results of the prediction of the spread of these diseases, the user can confirm that it is preferable to apply the protection model in 5 b) to the disease.

In addition, the processor 120 may perform a fitting algorithm that optimizes various model parameters using existing data in order to simulate complex results of the various models described above. This process (indicated by "Optimal Model Fitting" in FIG. 2) will be described.

6 is an example of applying the infectious disease fitting algorithm according to an embodiment of the present invention. And FIG. 7 is an example of a result of performing an infectious disease fitting algorithm according to an embodiment of the present invention.

The pandemic model and the diffusion model described above have various parameters and it is difficult to input appropriate numerical values according to diseases for which diffusion is to be predicted. Thus, the processor 120 performs a fitting algorithm to estimate an appropriate value for various parameters.

Referring to FIG. 6, the initial data (i.e., actual data) as in a) is displayed in the hexagonal tile space without knowing the parameter values necessary for the infectious disease diffusion modeling. In FIG. 6A, the first infected area (Seed Hextile) and the infected area (Data Infected Hextile) among the areas connected to the network are displayed. In FIGS. 6 (b) and 6 (c), the results of Disease diffusion and spatial analysis are shown as time elapses. At this time, the state of disease spread after the time t + 1 has elapsed is shown in Fig. 6 (b), and the Infected Hexile and Infection Candidate Hextile are displayed. 6 (c) shows the spread of the disease after the time point t + 2 has elapsed. In addition to the infected hexagonal tiles and the infected candidate hexagonal tiles, the adjustment candidate hextile ) Are further displayed.

FIG. 7 shows a process of learning data as much as the data through simulation to find a parameter value suitable for the disease in case there is data on infectious diseases according to time.

Meanwhile, the processor 120 may provide a visual analytics user interface for supporting the modeling of the epidemic diffusion prediction model described above.

FIG. 8 is an example of a visual analysis user interface supporting the epidemic proliferation prediction modeling according to an embodiment of the present invention.

The processor 120 provides a visual analysis user interface for modeling the modes described above with reference to FIGS. 2 to 7 and outputting a simulation result by modeling the modes. A visual analytic user interface that supports such predictive modeling and analysis can be implemented as a web-based framework. Visual analysis Through the user interface, it is easy to understand and use the process of establishing and analyzing the modeling conditions of the epidemic proliferation prediction.

Specifically, the user can select a desired mode as shown in FIG. 8 (a). In this case, the simulation mode is a mode in which an actual simulation is applied, and the values of the variables of the epidemic mode and the values of the weights corresponding to the diffusion can be set. The network mode can set a road network, an air network, and the like for a plurality of regions. The Group mode allows the user to create groups of desired regions. The protection mode can apply a desired one of a plurality of predetermined protection models. The tile options (TileOption) allow you to apply other tile options.

In Fig. 8 (b), various information according to the mode selected in (a) is displayed. For example, if the network is selected in (a), the type of the road network or the air network may be displayed. FIG. 8 shows a case where a group is selected in (a), specifically, a type of the selected group is displayed in (b), and a function capable of creating or deleting another group in addition to the group is output.

FIG. 8 (c) shows a map that is actually simulated through the modeling of the epidemic model, diffusion model, and protection model.

In (d) of FIG. 8, the simulation information proceeding in (c) is expressed by a graph of infected rate.

In FIG. 8 (e), data for comparing and analyzing the simulation results are output based on the accumulated results of the simulated graphs. That is, the previous simulation result can be called and output.

In Fig. 8 (f), the text information for the current simulation is output.

Hereinafter, an infectious disease diffusion prediction modeling method according to an embodiment of the present invention will be described in detail with reference to FIG.

FIG. 9 is a flow chart for explaining an epidemic proliferation prediction modeling method according to an embodiment of the present invention.

First, the geographical information to be applied to the simulation of at least one of the epidemic model, the diffusion model, and the protection model is set (S910).

At this time, an arbitrary limited space is represented by one hexagonal tile (Hextile) cell, and geographical information in which the actual terrain information is represented by a grid type is stored in an arbitrary map space including a plurality of hexagonal tile cells at latitude and longitude And then generate a hexagon tile in the portion of the mapped map space where the terrain exists, and apply the population number belonging to each hexagon tile.

Further, the hexagonal tile cell expresses the degree of spread of the infectious disease through at least one of the cell interior color, the cell border line color, the arrows crossing the inside or outside of the cell, and the cell height, the arrows corresponding to the disease diffusion direction, The border line color corresponds to the applied protection policy, the color inside the cell corresponds to the disease spreading phase and infection rate in the area, and the cell height corresponds to the number of infectors in the area.

For reference, the process of setting the geographical information is the same as that described above with reference to FIG. 3 and FIG.

Then, an epidemic model expresses propagation and diffusion for a limited area for any disease, and a spreading model expresses propagation and diffusion for multiple zones through the network ( S920).

As described above with reference to FIG. 2, the epidemic model may be modeled using either the SIR model, the SEIR model, or the MSEIR model.

In addition, the diffusion model is modeled according to the inter-area spreading probability calculated based on the number of populations, the number of infectors, the network information, and the weather condition information of each zone, and the spreading probability is set so that the disease spreads when the spread probability exceeds a predetermined threshold value. It is possible to increase the number of infections on the pandemic model of the spreading area. For reference, the diffusion model can be modeled according to the diffusion probability calculated using Equation (3) described above.

Next, based on the modeling result of any one of the epidemic model and the diffusion model, a simulation process according to time is output (S930).

A protection model representing a result of inhibiting diffusion by applying one or more predetermined protection policies to a result of modeling one of a pandemic model and a diffusion model can be modeled and output as a simulation result S940).

At this time, the protection policy includes at least one of an isolation plan and a vaccination plan.

According to another aspect of the present invention, there is provided a method for predicting an epidemic proliferation prediction method, comprising: performing modeling of an epidemic proliferation process according to any one of the epidemic model and the diffusion model based on actual data on a disease; And outputting a simulation process according to time based on a result of the modeling. At this time, a fitting algorithm for tracking back the parameter values to be applied to the epidemic model and the diffusion model is processed so as to resemble the result of simulating the infectious disease spreading process.

Meanwhile, the process of modeling and simulating the pandemic, diffusion and protection models described above can be handled through a visual analytics user interface.

That is, it is possible to select one of the simulation mode, the network mode, the zone group mode, and the protection mode through the visual analysis user interface as shown in FIG. 8, display a plurality of predetermined information for the selected mode, The simulation results according to the modeling of the epidemic model, the diffusion model and the protection model are displayed at the time of selection, the infection degree according to the advanced simulation is displayed as a graph, and the simulation results And outputs the data which can be compared and analyzed, and the text information preset for the current simulation can be outputted.

The above-described epidemic proliferation prediction modeling method according to an embodiment of the present invention may be implemented in the form of a recording medium including instructions executable by a computer such as a program module executed by a computer. Such a recording medium includes a computer-readable medium, which may be any available medium that can be accessed by a computer, and includes both volatile and non-volatile media, both removable and non-removable media. The computer-readable medium may also include computer storage media, which may be volatile and non-volatile, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data , Both removable and non-removable media.

It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the following claims. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

Furthermore, while the methods and systems of the present invention have been described in terms of specific embodiments, some or all of those elements or operations may be implemented using a computer system having a general purpose hardware architecture.

It is intended that the present invention covers the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. .

100: Epidemic spread prediction modeling device
110: Memory
120: Processor

Claims (17)

An epidemic spread prediction modeling device,
An epidemic proliferation prediction modeling program stored in memory; And
And a processor for executing a program stored in the memory,
The processor is configured to set geographic information to be applied to the simulation according to the execution of the epidemic diffusion prediction modeling program, to set an epidemic model expressing propagation and diffusion for a limited area for a certain disease, A spreading model expressing propagation and diffusion for a region of a region is modeled to output a simulation process according to time,
A protection model representing a result of inhibiting diffusion by applying one or more protection policies preset to a result of modeling the pandemic model and the diffusion model is modeled and output as a simulation result,
The geographic information is applied to simulation of at least one of the epidemic model, the diffusion model, and the protection model. An arbitrary limited space is represented by one hexagonal tile (Hextile) cell, and the actual terrain information is represented by a grid type Mapping the geographical information in accordance with latitude and longitude on an arbitrary map space to which a plurality of hexagonal tile cells are to be included and generating a hexagonal tile in a portion of the mapped map space where the geographical portion exists, Respectively,
Expressing the degree of spread of the infectious disease through at least one of the cell interior color, the cell border line color, the arrow crossing the inside or outside of the cell, and the cell height for each hexagonal tile cell,
Wherein the arrow corresponds to a disease diffusion direction, the border line color corresponds to an applied protection policy, the color inside the cell corresponds to the disease spreading phase and the infection rate in the zone, the height of the cell corresponds to the number of infectors in the zone And,
The diffusion model is modeled according to inter-area spreading probabilities calculated based on the number of populations, the number of infectors, network information, and weather condition information for each zone, and if the spreading probability exceeds a predetermined threshold value, To increase the number of infections on the epidemic model of the area to be modeled and spread,
Wherein the protection policy comprises at least one of an isolation plan and a vaccination plan.
delete delete delete The method according to claim 1,
The processor comprising:
An epidemic spread prediction modeling device that models the epidemic model using either the SIR model, the SEIR model, or the MSEIR model.
The method according to claim 1,
The processor comprising:
Wherein the spreading probability is calculated through the following equation (1).
[Equation 1]

(However,

,

,

Is a spreading probability adjustment variable for adjusting a weight,

Is the number of infected persons in two areas connected to each other,

Is the total population of two areas connected to each other,

Is the wind vector from zone i to zone j,

Is the predetermined optimal temperature for the modeled disease,

Corresponds to the present temperature)
The method according to claim 1,
The processor comprising:
Which processes a fitting algorithm to simulate an epidemic proliferation process based on actual data for an illness, the backward tracking parameter values to be applied to the epidemic model and the diffusion model so as to resemble the result of simulating the epidemic proliferation process, Prediction modeling device.
The method according to claim 1,
The processor comprising:
Providing a visual analytics user interface that supports modeling of the pandemic, diffusion, and protection models,
Wherein the visual analysis user interface allows selection of one of a simulation mode, a network mode, a zone group mode, and a protection mode, displays a plurality of predetermined information for the selected mode, , The diffusion model and the model of the protection model are displayed, the infection degree according to the advanced simulation is displayed as a graph, and the simulation results are compared and analyzed based on the accumulated results of the graphs And outputting predetermined data for the current simulation, and outputting the pre-determined text information.
The epidemic proliferation prediction modeling method performed by the epidemic proliferation predicting modeling apparatus,
Setting geographical information to be applied to the simulation;
Modeling an epidemic model expressing propagation and diffusion for a limited area for any disease, and a spreading model expressing propagation and diffusion for a plurality of zones through a network; And
Outputting a simulation result by modeling a protection model representing a result of inhibiting diffusion by applying one or more predetermined protection policies to a result of modeling the one of the pandemic model and the diffusion model;
And outputting a simulation process according to time based on a modeling result of any one of the epidemic model and the diffusion model,
Wherein the geographical information is applied to simulation of at least one of the epidemic model, the diffusion model, and the protection model, wherein the step of setting the geographical information comprises: expressing an arbitrary limited space as one hexagonal tile (Hextile cell) Maps the geographical information represented by the grid type according to latitude and longitude on an arbitrary map space to which a plurality of hexagonal tile cells are to be included and creates a hexagonal tile in a portion of the mapped map space where the terrain exists The number of the population belonging to each hexagonal tile is applied,
Wherein the hexagonal tile cell expresses the extent of the spread of the epidemic disease through at least one of a cell interior color, a cell border line color, an arrow crossing the inside or outside of the cell, and a cell height,
Wherein the arrow corresponds to a disease diffusion direction, the border line color corresponds to an applied protection policy, the color inside the cell corresponds to the disease spreading phase and the infection rate in the zone, the height of the cell corresponds to the number of infectors in the zone And,
The diffusion model is modeled according to inter-area spreading probabilities calculated based on the number of populations, the number of infectors, network information, and weather condition information for each zone, and if the spreading probability exceeds a predetermined threshold value, To increase the number of infections on the epidemic model of the area to be modeled and spread,
Wherein the protection policy comprises at least one of an isolation plan and a vaccination plan.
delete delete delete 10. The method of claim 9,
The epidemic model includes:
SIR model, the SEIR model, and the MSEIR model.
10. The method of claim 9,
Wherein the spreading probability is calculated by the following equation (2).
&Quot; (2) &quot;

(However,

,

,

Is a spreading probability adjustment variable for adjusting a weight,

Is the number of infected persons in two areas connected to each other,

Is the total population of two areas connected to each other,

Is the wind vector from zone i to zone j,

Is the predetermined optimal temperature for the modeled disease,

Corresponds to the present temperature)
10. The method of claim 9,
Performing infectious disease spreading modeling according to any one of the epidemic model and the spreading model based on actual data on an arbitrary disease; And
Further comprising the step of outputting a simulation process over time based on the result of the modeling,
And processing a fitting algorithm that traces the parameter values to be applied to the epidemic model and the diffusion model so as to resemble the simulation result of the epidemic proliferation process.
10. The method of claim 9,
Providing a visual analytics user interface that supports modeling of the pandemic, diffusion, and protection models,
Wherein the visual analysis user interface allows selection of one of a simulation mode, a network mode, a zone group mode, and a protection mode, displays a plurality of predetermined information for the selected mode, , The diffusion model and the model of the protection model are displayed, the infection degree according to the advanced simulation is displayed as a graph, and the simulation results are compared and analyzed based on the accumulated results of the graphs And outputting pre-determined text information for the current simulation.
A computer-readable recording medium on which a computer program for executing the method according to any one of claims 9 to 13 is recorded.

Images