Method and device for predicting new cases of respiratory infectious diseases based on exposure risk
By obtaining droplet movement information generated by individual movements of the population and respiratory activities of infected people, calculating the exposure risk of respiratory infectious diseases and generating prediction results for new cases of respiratory infectious diseases, the existing model ignores the details of transmission between individuals and lack of scenario applicability is solved. The problem has achieved more accurate and extensive prediction effects.
Patent Information
- Application Number
- CN202210007233.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-05
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2042-01-05
AI Technical Summary
Existing respiratory infectious disease transmission models ignore details when spreading between individuals, overestimate or underestimate the number of high-risk exposed individuals, and most models are established for specific scenarios, cannot be applied to all public places, and lack recognized real data for quantification. test.
By obtaining personal movement information of the population and droplet movement information generated by respiratory activities of infected people, calculate the exposure risk of respiratory infectious diseases of individuals, and generate prediction results based on the relationship between exposure risk and the number of new cases, providing a wide range of application and accurate Methods for forecasting new cases of respiratory infectious diseases.
It improves the accuracy and scope of application of new cases of respiratory infectious diseases, can predict individual transmission trends from a micro perspective, and conduct quantitative inspections based on macro data, and is suitable for a variety of scenario analysis in general public places.
Smart Images

Figure CN114360738B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for predicting new cases of respiratory infectious diseases based on exposure risk. Background Art
[0002] Respiratory infectious diseases are usually very destructive, pose a serious threat to public health, and have a profound impact on people's daily lives. The transmission process of respiratory infectious diseases follows corresponding objective laws, and the epidemic trend can be scientifically predicted, which will help decision makers formulate reasonable prevention and control policies.
[0003] For the prediction of the spread trend of respiratory infectious diseases, most of them are macro models with groups as the research object, and a few are micro models with individuals as the research object. Macro models have made contributions to the prediction of epidemic trends, but they may ignore details when modeling the spread of respiratory infectious diseases between individuals, and most of them require uninterrupted time series data or a large number of samples to obtain the optimal parameters. Micro models can solve these problems better, especially micro models based on pedestrian dynamics, which can combine the time-varying physical distance of pedestrians during movement to describe the spread of infectious diseases. However, micro models based on pedestrian dynamics still have some shortcomings: 1) Some models ignore the necessary factors to simplify the model, and they may overestimate or underestimate the number of high-risk exposed individuals; 2) Some models are established for specific scenarios, such as cruise ships and supermarkets. However, the indoor settings of different scenarios will affect the spread of the virus and bring a lot of model input and computing costs. Therefore, it is necessary to build a model for a general public place that can represent all scenarios; 3) Most of the trend prediction results of the model, that is, the output results (such as individual exposure risk and the number of high-risk exposed individuals), have no recognized real data for comparison, and cannot be quantitatively tested. Summary of the invention
[0004] In view of this, the embodiments of the present invention provide a method and device for predicting new cases of respiratory infectious diseases based on exposure risk, which has high accuracy and wide application range.
[0005] One aspect of the present invention provides a method for predicting new cases of respiratory infectious diseases based on exposure risk, comprising:
[0006] Obtain personal movement information of any individual in the crowd and droplet movement information generated by the respiratory activity of infected persons;
[0007] Determining the personal respiratory infectious disease exposure risk based on the personal movement information and droplet movement information;
[0008] Based on the individual's exposure risk to respiratory infectious diseases, analyze the relationship between the number of individuals with high exposure risk and the number of new cases;
[0009] Based on the relationship between the number of individuals at high risk of exposure and the number of new cases, a prediction result of new cases of respiratory infectious diseases is generated.
[0010] Optionally, determining the personal respiratory infectious disease exposure risk according to the personal movement information and the droplet movement information includes:
[0011] Determine an individual's instantaneous exposure risk based on the mass of droplets from an infected person's cough that they are most exposed to at a given moment;
[0012] Add up the instantaneous exposure risks within the preset time to determine the individual's respiratory infectious disease exposure risk.
[0013] Optionally, the step of adding up the instantaneous exposure risks within a preset time to determine the personal respiratory infectious disease exposure risk includes:
[0014] According to the total number of people in the target area, the number of infected people in the crowd, and the average stay time of the crowd, the location of any individual in the crowd at any time is determined through the pedestrian dynamics model;
[0015] Based on the composition and ejection speed of droplets generated by the respiratory activity of infected people in existing studies, the position and mass information of any droplet at any time are determined by simulation;
[0016] The motion information of the target pedestrian and the motion information of the droplets generated by the respiratory activity of the infected person are coupled, and the mass of the droplets generated by the respiratory activity of the infected person that the target pedestrian is exposed to to the greatest extent when the two are in the same position at the same time is counted as the instantaneous exposure risk of the target pedestrian at that moment;
[0017] The personal respiratory infectious disease exposure risk is calculated based on the instantaneous exposure risk.
[0018] Optionally, the step of adding up the instantaneous exposure risks within a preset time to determine the personal respiratory infectious disease exposure risk further includes:
[0019] By configuring the pedestrian dynamics simulation parameters, the respiratory activities of the infected person are simulated, the spatiotemporal movement of droplets generated by the respiratory activities of the infected person is determined, and the spatiotemporal movement of droplets generated by the respiratory activities of the infected person is fit by the Gaussian distribution function.
[0020] Optionally, generating a prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risk and the number of new cases includes:
[0021] When the target pedestrian's personal exposure risk to respiratory infectious diseases is greater than the risk threshold, the target pedestrian is defined as a high-exposure-risk individual;
[0022] Obtain the total number of individuals entering the target area during the target period and calculate the total number of individuals with high exposure risk;
[0023] The number of new cases is calculated based on the total number of individuals at high risk of exposure.
[0024] Optionally, the total number of individuals with high exposure risk is calculated as follows:
[0025]
[0026] Among them, C risk (α) represents the total number of individuals with high exposure risk; C total Represents the total number of individuals entering the target area during the target period; E i represents the personal respiratory infectious disease exposure risk of pedestrian i during the study period; α represents the risk threshold of high exposure to personal respiratory infectious diseases; ψ(E i , α) represents the judgment E i Is it greater than α? If E i >α,ψ(E i , α)=1; otherwise ψ(E i , α)=0;
[0027] The formula for calculating the number of new cases is:
[0028] C new =F(C risk )
[0029] Among them, C new represents the number of new cases; C risk (α) represents the total number of individuals with high exposure risk; F(C risk ) represents C new It is quantitatively expressed as risk The function can be any function form in which the dependent variable is positively correlated with the independent variable, including linear equations:
[0030] C new =F(C risk )=β*C risk (α)
[0031] Where β represents the linear equation F(C risk ) is the proportionality coefficient.
[0032] Optionally, generating a prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risk and the number of new cases also includes:
[0033] According to the number of historical new cases, the risk threshold and the proportional coefficient in different scenarios are configured.
[0034] Another aspect of the embodiment of the present invention further provides a device for predicting new cases of respiratory infectious diseases based on exposure risk, comprising:
[0035] The first module is used to obtain the personal movement information of any individual in the crowd and the droplet movement information generated by the respiratory activity of the infected person;
[0036] The second module is used to determine the personal respiratory infectious disease exposure risk based on the personal movement information and droplet movement information;
[0037] The third module is used to analyze the relationship between the number of individuals with high exposure risk and the number of new cases according to the individual's exposure risk of respiratory infectious diseases;
[0038] The fourth module is used to generate prediction results of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risks and the number of new cases.
[0039] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;
[0040] The memory is used to store programs;
[0041] The processor executes the program to implement the method described above.
[0042] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.
[0043] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.
[0044] The embodiment of the present invention obtains the personal movement information of any individual in the crowd and the droplet movement information generated by the respiratory activity of the infected person; determines the personal respiratory infectious disease exposure risk according to the personal movement information and the droplet movement information; analyzes the relationship between the number of individuals with high exposure risk and the number of new cases according to the personal respiratory infectious disease exposure risk; generates the prediction result of new cases of respiratory infectious diseases according to the relationship between the number of individuals with high exposure risk and the number of new cases. The present invention improves the accuracy and expands the scope of application. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0046] Figure 1 is a flowchart of steps of an embodiment of the present invention;
[0047] Figure 2 A schematic diagram of a crowd moving in a simulation space provided by an embodiment of the present invention;
[0048] Figure 3 (a) is a schematic diagram of the computational domain with an infected human body model and a susceptible human body model; Figure 3 (b) is a schematic diagram of the numerical simulation calculation domain;
[0049] Figure 4 is a schematic diagram of the evolution of cough droplet size in the computational domain on the yz plane after the cough begins, where: Figure 4 (a) represents 0.05 seconds after the onset of coughing; Figure 4 (b) represents 0.15 seconds after the onset of coughing; Figure 4 (c) represents 0.30 seconds after the onset of coughing; Figure 4 (d) in the figure represents 0.50 seconds after the onset of cough; Figure 4 (e) in the figure represents 1.00 seconds after the onset of cough; Figure 4 (f) in the figure represents 5.00 seconds after the onset of cough; Figure 4 (g) represents 10.00 seconds after the onset of coughing; Figure 4 (h) represents 15.00 seconds after the onset of coughing;
[0050] Figure 5 3D schematic diagram of 15 representative xz planes in the computational domain;
[0051] Figure 6 M is the s (t cg )With t cg Schematic diagram of the changes, where Figure 6 The time step of (a) is T step = 0.02 seconds; Figure 6 The time step of (b) is T step = 0.03 seconds; Figure 6 The time step of (c) is T step = 0.04 seconds; Figure 6 The time step of (d) is T step= 0.05 seconds;
[0052] Figure 7 A schematic diagram of data relationships provided by an embodiment of the present invention;
[0053] Figure 8 A schematic diagram of a simulation space provided by an embodiment of the present invention;
[0054] Fig. 9 A schematic diagram of the distribution of population numbers in different exposure risk value areas on different dates provided by an embodiment of the present invention;
[0055] Fig.10 A schematic diagram of the change of the mean absolute error with α and β provided in an embodiment of the present invention, wherein: Fig.10 (a) is ∈[0.50,100.00]μg and β∈[1.00×10 -5 , 2.00×10 -3 ]’s α-β view; Fig.10 (b) is the main view when MAE is less than 6500; Fig.10 (c) is a side view when MAE is less than 6500; Fig.10 (d) is another side view when MAE is less than 6500. DETAILED DESCRIPTION
[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0057] In view of the problems existing in the prior art, an embodiment of the present invention provides a method for predicting new cases of respiratory infectious diseases based on exposure risk, comprising:
[0058] Obtain personal movement information of any individual in the crowd and droplet movement information generated by the respiratory activity of infected persons;
[0059] Determining the personal respiratory infectious disease exposure risk based on the personal movement information and droplet movement information;
[0060] Based on the individual's exposure risk to respiratory infectious diseases, analyze the relationship between the number of individuals with high exposure risk and the number of new cases;
[0061] Based on the relationship between the number of individuals at high risk of exposure and the number of new cases, a prediction result of new cases of respiratory infectious diseases is generated.
[0062] Optionally, determining the personal respiratory infectious disease exposure risk according to the personal movement information and the droplet movement information includes:
[0063] Determine an individual's instantaneous exposure risk based on the mass of droplets from an infected person's cough that they are most exposed to at a given moment;
[0064] Add up the instantaneous exposure risks within the preset time to determine the individual's respiratory infectious disease exposure risk.
[0065] Optionally, the step of adding up the instantaneous exposure risks within a preset time to determine the personal respiratory infectious disease exposure risk includes:
[0066] According to the total number of people in the target area, the number of infected people in the crowd, and the average stay time of the crowd, the location of any individual in the crowd at any time is determined through the pedestrian dynamics model;
[0067] Based on the composition and ejection speed of droplets generated by the respiratory activity of infected people in existing studies, the position and mass information of any droplet at any time are determined by simulation;
[0068] The motion information of the target pedestrian and the motion information of the droplets generated by the respiratory activity of the infected person are coupled, and the mass of the droplets generated by the respiratory activity of the infected person that the target pedestrian is exposed to to the greatest extent when the two are in the same position at the same time is counted as the instantaneous exposure risk of the target pedestrian at that moment;
[0069] The personal respiratory infectious disease exposure risk is calculated based on the instantaneous exposure risk.
[0070] Optionally, the step of adding up the instantaneous exposure risks within a preset time to determine the personal respiratory infectious disease exposure risk further includes:
[0071] By configuring the pedestrian dynamics simulation parameters, the respiratory activities of the infected person are simulated, the spatiotemporal movement of droplets generated by the respiratory activities of the infected person is determined, and the spatiotemporal movement of droplets generated by the respiratory activities of the infected person is fit by the Gaussian distribution function.
[0072] Optionally, generating a prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risk and the number of new cases includes:
[0073] When the target pedestrian's personal exposure risk to respiratory infectious diseases is greater than the risk threshold, the target pedestrian is defined as a high-exposure-risk individual;
[0074] Obtain the total number of individuals entering the target area during the target period and calculate the total number of individuals with high exposure risk;
[0075] The number of new cases is calculated based on the total number of individuals at high risk of exposure.
[0076] Optionally, the total number of individuals with high exposure risk is calculated as follows:
[0077]
[0078] Among them, C risk (α) represents the total number of individuals with high exposure risk; C total Represents the total number of individuals entering the target area during the target period; E i represents the personal respiratory infectious disease exposure risk of pedestrian i during the study period; α represents the risk threshold of high exposure to personal respiratory infectious diseases; ψ(E i , α) represents the judgment E i Is it greater than α? If E i >α,ψ(E i , α)=1; otherwise ψ(E i , α)=0;
[0079] The formula for calculating the number of new cases is:
[0080] C new =F(C risk )
[0081] Among them, C new represents the number of new cases; C risk (α) represents the total number of individuals with high exposure risk; F(C risk ) represents C new It is quantitatively expressed as risk The function can be any function form in which the dependent variable is positively correlated with the independent variable, including linear equations:
[0082] C new =F(C risk )=β*C risk (α)
[0083] Where β represents the linear equation F(C risk ) is the proportionality coefficient.
[0084] Optionally, generating a prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risk and the number of new cases also includes:
[0085] According to the number of historical new cases, the risk threshold and the proportional coefficient in different scenarios are configured.
[0086] Another aspect of the embodiment of the present invention further provides a device for predicting new cases of respiratory infectious diseases based on exposure risk, comprising:
[0087] The first module is used to obtain the personal movement information of any individual in the crowd and the droplet movement information generated by the respiratory activity of the infected person;
[0088] The second module is used to determine the personal respiratory infectious disease exposure risk based on the personal movement information and droplet movement information;
[0089] The third module is used to analyze the relationship between the number of individuals with high exposure risk and the number of new cases according to the individual's exposure risk of respiratory infectious diseases;
[0090] The fourth module is used to generate prediction results of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risks and the number of new cases.
[0091] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;
[0092] The memory is used to store programs;
[0093] The processor executes the program to implement the method described above.
[0094] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.
[0095] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.
[0096] The specific implementation principle of the present invention is described in detail below in conjunction with the accompanying drawings:
[0097] like Figure 1 As shown, the new addition ratio prediction method of the present invention comprises the following steps:
[0098] Step S1, coupling the movement of any individual in the crowd and the movement of droplets generated by the respiratory activity of the infected person (taking coughing as an example) to determine the individual's exposure risk to respiratory infectious diseases.
[0099] Step S2: According to the individual exposure risk of respiratory infectious diseases, the relationship between the number of individuals with high exposure risk and the number of new cases is analyzed to predict new cases of respiratory infectious diseases.
[0100] In step S1, the movement of any individual in the crowd and the movement of droplets generated by the respiratory activity of the infected person (taking coughing as an example) are coupled to determine the exposure risk of individual respiratory infectious diseases, which specifically includes the following steps:
[0101] Step 101. In the present invention, the instantaneous exposure risk of an individual is defined as the mass of droplets produced by the cough of an infected person that is exposed to the maximum extent at a certain moment. Based on this, the instantaneous exposure risk during the residence time is added to obtain the individual respiratory infectious disease exposure risk.
[0102] Step 102: According to the number of people C total 、The number of infected people in the population C inf and the average stay time T of the crowd dwell , based on the pedestrian dynamics model, the position of any pedestrian at any time is determined. Here, the social force model in the pedestrian dynamics model is used as an example to illustrate. Any pedestrian is represented as a ped The circle, such as Figure 2 As shown, pedestrian i (mass m i ) The moving force at time t is f i The driving of (t) is shown in formula (1):
[0103]
[0104] In formula (1), It represents the self-driving force of pedestrian i, which is mainly used to describe the pedestrian walking at a walking speed. At the relaxation time τ i The tendency to move toward the target point; represents pedestrian i and its neighboring pedestrian i near The social repulsion between people is used to indicate the personal tendency of pedestrians to keep a certain distance from others while walking; represents the repulsive force between pedestrian i and obstacle / wall w. According to Newton’s second law, the velocity v of pedestrian i at time t i (t) and the velocity direction unit vector e i (t) As shown in formula (2), based on this, the position p of pedestrian i at time t can be determined i (t) as formula (3).
[0105]
[0106]
[0107] Step 103: In order to analyze the transmission process of virus-carrying droplets generated by the respiratory activity of the infected person (taking coughing as an example), the droplet composition and injection velocity of a typical cough are determined by the literature method, and numerical simulation is performed based on the relevant content of computational fluid dynamics. The simulation calculation domain is set as Figure 3 As shown, Figure 3 (a) is a schematic diagram of the computational domain with an infected human body model and a susceptible human body model; Figure 3(b) is a schematic diagram of the numerical simulation domain. This embodiment also uses a time step of 0.01 seconds for a total of 15 seconds of simulation to fully study the dynamic characteristics of droplets produced by coughing. The simulation results can determine the position and mass of any droplet at any time. Figure 4 As shown, Figure 4 (a) represents 0.05 seconds after the onset of coughing; Figure 4 (b) represents 0.15 seconds after the onset of coughing; Figure 4 (c) represents 0.30 seconds after the onset of coughing; Figure 4 (d) in the figure represents 0.50 seconds after the onset of cough; Figure 4 (e) in the figure represents 1.00 seconds after the onset of cough; Figure 4 (f) in the figure represents 5.00 seconds after the onset of cough; Figure 4 (g) represents 10.00 seconds after the onset of coughing; Figure 4 The (h) in the figure represents 15.00 seconds after the onset of coughing.
[0108] Step 104, the present invention assumes that when the infected person j is Time at location At the beginning of the g-th cough, the patient is stationary, and the movement of the cough droplets is determined only by the position Physical distance and time The time interval is determined by At time i, at position p i (t) and position The physical distance between i,j,g (t), and at this time The time interval is Therefore, based on the exposure risk theorem of the present invention, when d i,j,g (t) and The infection distance D of a typical cough inf and infection time T inf The instantaneous exposure risk E of pedestrian i exposed to the g-th cough of infected person j is i,j,g (t) as formula (4).
[0109]
[0110] In formula (4), represents the position p of pedestrian i at time t i At (t), the infected person with the greatest exposure has the g-th cough at the beginning Then diffuse to a distance d from the starting point i,j,g (t) Droplet mass at position.
[0111] Step 105: In the present invention, all coughs are assumed to be typical coughs and the propagation process of the virus-carrying droplets is the same as that in step 103. The mathematical formula of , and the simulation result output for a typical cough in step 103 can be obtained. That is, for a typical cough, the analysis at time t cg (≤T inf ) The mass of the droplet M passing through an xz plane at a distance s along the y axis s (t cg ).
[0112] From the position and mass of any droplet at any time determined in step 103, it is difficult to find a suitable deterministic formula to describe the change of the droplet mass with distance at any time. Figure 5 As shown, the present invention selects several representative x--z planes and models the process of the arrival droplet mass of each plane changing with time. Specifically, the value of s starts from 0.1 meters to 2.9 meters and is spaced at 0.2 meters. Therefore, there are 15 representative x--z planes Φ={φ 1 ,φ 2 , ..., φ s , ..., φ 15}.
[0113] At the same time, in order to avoid the pedestrian dynamics simulation in step 102 due to the time step T step The setting results in a small droplet mass. Inner through plane φ s The total droplet mass is taken as M s (t cg ). When the pedestrian dynamics simulation time step T is set in this embodiment step = 0.02 seconds, 0.03 seconds, 0.04 seconds, and 0.05 seconds, the statistical results show that M s (t cg ) cg The change of conforms to Gaussian distribution, such as Figure 6 As shown, Figure 6 The time step of (a) is T step = 0.02 seconds; Figure 6 The time step of (b) is T step = 0.03 seconds; Figure 6 The time step of (c) is T step = 0.04 seconds; Figure 6 The time step of (d) is T step = 0.05 seconds. Therefore, for plane φ s Can determine M s (tcg ) as in formula (5).
[0114]
[0115] In formula (5), a s , b s and c s is the plane φ s Parameters of the Gaussian distribution function fit.
[0116] Step 106: The time interval between pedestrian i and infected person j starting their g-th cough at time t That is a typical cough cg When pedestrian i is at position p at time t i (t), if d i,j,g (t)∈[s-0.1,s+0.1) and It can be determined The mathematical expression of is as shown in formula (6).
[0117]
[0118] Therefore, if d i,j,g (t)∈[s-0.1,s+0.1) and Then the instantaneous exposure risk E of pedestrian i exposed to the g-th cough of infected person j is obtained i,j,g (t) as formula (7).
[0119]
[0120] Step 107: The personal respiratory infectious disease exposure risk of pedestrian i is as shown in formula (8).
[0121]
[0122] In formula (8), and Pedestrian i is the time when it enters the study area and the time it stays in the study area; J(t) represents the number of infected people in the study area at time t, and J(t)≤C inf ; J G (t) represents the number of infectious coughs of infected person j at time t.
[0123] In step S2, according to the individual's exposure risk to respiratory infectious diseases, the relationship between the number of individuals with high exposure risk and the number of new cases is analyzed to predict new cases of respiratory infectious diseases, which specifically includes the following steps:
[0124] Step 201: In the present invention, when α is a high exposure risk threshold for personal respiratory infectious diseases, if the personal respiratory infectious disease exposure risk E of pedestrian i isi >α, pedestrian i is defined as a high-exposure risk individual. At this time, the total number of individuals who enter the study area during the study period is C total , then the number of individuals with high exposure risk C during the study period changes with the high exposure risk threshold α risk As shown in formula (9).
[0125]
[0126] Step 202: Number of new cases C new Usually as the number of individuals at high risk of exposure increases, risk The two show a positive correlation. Therefore, from a mathematical point of view, C new It can be quantitatively expressed as risk The function F is as shown in formula (10).
[0127] C new =F(C risk ) (10)
[0128] Step 203, F(C risk ) represents C new It is quantitatively expressed as ris k, which can be any function form in which the dependent variable is positively correlated with the independent variable, such as a linear equation. risk ) is taken as an example of a linear equation. At the same time, consider an extreme case, that is, if there is no infectious disease, there is no high-risk population and new cases, then C new =C risk = 0. Therefore, the function F(C risk ) is set as a linear equation passing through the origin as shown in equation (11).
[0129] C new =F(C risk )=β*C risk (α) (11)
[0130] In equation (11), β is the proportionality coefficient of the equation.
[0131] Step 204: Based on the number of new cases in history C new Data can be used to determine the values of parameters α and β in different scenarios. and When the predicted value and the actual value are the vth (=1, 2, ..., V)th historical observation group, the mean absolute error (MAE) and other indicators can be used to describe and Here, this embodiment selects MAE as the indicator, and the optimal values of α and β can be obtained by formula (12).
[0132]
[0133] Finally, based on α * and β * , the future number of new cases Cnew can be predicted through formulas (9)-(11).
[0134] The method of the present invention is exemplified below using data from a specific application scenario:
[0135] Example 1
[0136] This example uses the data of country B during the spread of virus A, selects 79 days with complete data from May 1 to July 25, 2020 as the research period (with days as the minimum time), and predicts and tests the number of new cases per day.
[0137] The input data involved in the present invention are introduced as follows: 1) The number of people C total , from the TRIPSBY DISTANCE-NATIONAL dataset; 2) The number of infected people in the population C inf In this implementation, it is assumed that the infected person has at least one trip in a day, so the number of infected people in the crowd can be derived from the dataset UNITED STATES COVID-19 CASES AND DEATHS BY STATE OVER TIME; 3) The average stay time of the crowd T dwell , statistics based on the University of MarylandCOVID-19 Impact Analysis Platform.
[0138] In this embodiment, the study period (79 days selected from May 1 to July 25) is divided into a training set (60 days, from May 1 to July 6) and a test set (the remaining 19 days, i.e., from July 7 to July 25), as shown in Figure 7 As shown. In addition, in order to reduce the computational cost of the simulation, the number of people and the number of infected people in the population are reduced by a ratio of ρ in both the training set and the test set. Of course, the main output of the simulation, namely the number of high-risk exposed individuals and the number of new cases per day, should be expanded by the same ratio ρ. For the ratio ρ, this example uses the first day of the study period (May 1, 2020) as the benchmark, and reduces the number of people on that day by a ratio of ρ to 10,000 for simulation, so the ratio ρ = 10,000 / 245,469,060 = 4.07×10 -5 . Thus, we can determine α in the training set* and β * The values are taken and used in the test set for model verification.
[0139] This embodiment selects the social force model in the pedestrian dynamics model to simulate pedestrian motion. This embodiment sets the function F(C risk ) is a linear equation passing through the origin.
[0140] In this embodiment, a simulation is performed for a general public place: a 22×22 square meter indoor barrier-free room, such as Figure 8 At the same time, this embodiment sets the pedestrian dynamics simulation time step to T step = 0.04 seconds. A pedestrian is represented by a 0.2-meter circle; the relaxation time and expected speed are 0.50 seconds and 1.34 m / s, respectively. The infected person coughs once every 15 seconds after entering the room, and the cough infection duration is a uniform distribution of 0-15 seconds. Based on Figure 6 The results in (c) determined that the maximum infectious distance of a cough is 1.7 meters.
[0141] When determining personal exposure risk, this embodiment takes 4 days (May 1, May 17, July 10, and July 25) as an example to show the simulation input and result statistics (i.e., E i =0 or E i The number of susceptible people C>0 sus ) as shown in Table 1 and Fig. 9 shown.
[0142] Table 1 Example of input, output and result statistics for personal exposure risk determination
[0143]
[0144] According to Table 1 and Fig. 9 The simulation results show that on May 1, E i ∈(0.00,0.50]μg C sus 2722 more people than on July 25 under the same conditions, but on May 1 E i >13 μg C sus This is 1,652 fewer people than on July 25 under the same conditions. At this point, as the spread of infectious diseases increases, more and more individuals are at higher risk of exposure. This trend is consistent with existing knowledge and is in line with reality.
[0145] In this embodiment, after the individual exposure risk E output by the simulation has been determined i After that, we can get the mean absolute error (MAE) in the training set as α and β change as follows: Fig.10 As shown, Fig.10 (a) is ∈[0.50,100.00]μg and β∈[1.00×10 -5 , 2.00×10 -3 ]’s α-β view; Fig.10 (b) is the main view when MAE is less than 6500; Fig.10 (c) is a side view when MAE is less than 6500; Fig.10 (d) is another side view when MAE is less than 6500. Based on the claims of the present invention, we get α * =7.00μg and β * =6.20×10 -4 , the MAE value at this time is 6080.89.
[0146] Based on α * and β * , the number of new cases Cnew in the test set was predicted, and the average absolute error (MAE) was 8140.00, the root mean square error (RMSE) was 9598.17, and the average absolute percentage error (MAPE) was 12.01%. The model prediction effect is better.
[0147] Example 2
[0148] This example uses the data of country B during the spread of virus A, selects 79 days with complete data from May 1 to July 25, 2020 as the research period (with days as the minimum time), and predicts and tests the number of new cases per day.
[0149] The input data involved in the present invention are introduced as follows: 1) The number of people C total , from the TRIPSBY DISTANCE-NATIONAL dataset; 2) The number of infected people in the population C inf In this implementation, it is assumed that the infected person has at least one trip in a day, so the number of infected people in the crowd can be derived from the dataset UNITED STATES COVID-19 CASES AND DEATHS BY STATE OVER TIME; 3) The average stay time of the crowd T dwell , statistics based on the University of MarylandCOVID-19 Impact Analysis Platform.
[0150] In this embodiment, the study period (79 days selected from May 1 to July 25) is divided into a training set (60 days, from May 1 to July 6) and a test set (the remaining 19 days, i.e., from July 7 to July 25), as shown in Figure 7 As shown. In addition, in order to reduce the computational cost of the simulation, the number of people and the number of infected people in the population are reduced by a ratio of ρ in both the training set and the test set. Of course, the main output of the simulation, namely the number of high-risk exposed individuals and the number of new cases per day, should be expanded by the same ratio ρ. For the ratio ρ, this example uses the first day of the study period (May 1, 2020) as the benchmark, and reduces the number of people on that day by a ratio of ρ to 10,000 for simulation, so the ratio ρ = 10,000 / 245,469,060 = 4.07×10 -5 . Thus, we can determine α in the training set * and β * The values are taken and used in the test set for model verification.
[0151] This embodiment selects the social force model in the pedestrian dynamics model to simulate pedestrian motion. This embodiment sets the function F(C risk ) is a linear equation passing through the origin.
[0152] In this embodiment, a simulation is performed for a general public place: a 22×22 square meter indoor barrier-free room, such as Figure 8 At the same time, this embodiment sets the pedestrian dynamics simulation time step to T step = 0.04 seconds. A pedestrian is represented by a 0.2-meter circle; the relaxation time and expected speed are 0.50 seconds and 1.34 m / s, respectively. The infected person coughs once every 15 seconds after entering the room, and the cough infection duration is a uniform distribution of 0-15 seconds. Based on Figure 6 The results of (c) determined that the maximum infection distance of a cough is 1.7 meters.
[0153] When determining personal exposure risk, this embodiment takes 4 days (May 1, May 17, July 10, and July 25) as an example to show the simulation input and result statistics (i.e., E i =0 or E i The number of susceptible people C>0 sus ) as shown in Table 2 and Fig. 9 shown.
[0154] Table 2 Example of input, output and result statistics for personal exposure risk determination
[0155]
[0156] According to Table 2 and Fig. 9The simulation results show that on May 1, E i ∈(0.00,0.50]μg C sus 2722 more people than on July 25 under the same conditions, but on May 1 E i >13 μg C sus This is 1,652 fewer people than on July 25 under the same conditions. At this point, as the spread of infectious diseases increases, more and more individuals are at higher risk of exposure. This trend is consistent with existing knowledge and is in line with reality.
[0157] Example 3
[0158] This embodiment uses the data of country B during the spread of virus A, selects 79 days with complete data from May 1 to July 25, 2020 as the research period (with days as the minimum time), and predicts and tests the new cases in a single day. In this embodiment, the research period (79 days selected from May 1 to July 25) is divided into a training set (60 days, from May 1 to July 6) and a test set (the remaining 19 days, i.e., from July 7 to July 25). In this embodiment, the method described in claim 2 is used to determine the risk of personal exposure.
[0159] In this embodiment, the function F(C risk ) is a linear equation passing through the origin.
[0160] In the training set, after determining the individual exposure risk, the mean absolute error (MAE) in the training set can be obtained as α and β change. Fig.10 As shown, Fig.10 (a) is ∈[0.50,100.00]μg and β∈[1.00×10 -5 , 2.00×10 -3 ]’s α-β view; Fig.10 (b) is the main view when MAE is less than 6500; Fig.10 (c) is a side view when MAE is less than 6500; Fig.10 (d) is another side view when MAE is less than 6500. Based on the method of the present invention, α is obtained. * =7.00μg and β * =6.20×10 -4 , the MAE value at this time is 6080.89. * and β *, the number of new cases Cnew in the test set was predicted, and the average absolute error (MAE) was 8140.00, the root mean square error (RMSE) was 9598.17, and the average absolute percentage error (MAPE) was 12.01%. The model prediction effect is better.
[0161] In summary, compared with the prior art, the present invention has the following advantages:
[0162] 1) The present invention fully considers the details of the spread of respiratory infectious diseases among individuals in motion, and models and couples the movement of individuals and the movement of droplets generated by the respiratory activity of people infected with respiratory infectious diseases, thereby calculating individual exposure risks and predicting new cases of infection; 2) The present invention predicts the spread trend of respiratory infectious diseases from a microscopic perspective with individuals as the research objects, and models a generalized public place. The proposed model can be used to evaluate and analyze the impact of multiple specific factors in real scenes, such as scene setting factors (such as the area of obstacles in the scene), activity pattern factors (such as the entry and exit time distribution of the crowd), and prevention and control strategy factors (such as stay time restrictions). 3) The present invention builds a bridge between the microscopic model at the individual level and the macroscopic respiratory infectious disease transmission data, so the proposed model can be used for quantitative testing and analysis using macroscopic real data (such as the number of new cases).
[0163] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.
[0164] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.
[0165] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0166] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0167] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0168] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0169] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0170] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.
[0171] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.
Claims
1. A method for predicting new cases of respiratory infectious diseases based on exposure risk, characterized in that: include: Obtain personal movement information of any individual in the crowd and droplet movement information generated by the respiratory activity of infected persons; Determining the personal respiratory infectious disease exposure risk based on the personal movement information and droplet movement information; Based on the individual's exposure risk to respiratory infectious diseases, analyze the relationship between the number of individuals with high exposure risk and the number of new cases; generating a prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals at high risk of exposure and the number of new cases; Wherein, determining the personal respiratory infectious disease exposure risk according to the personal movement information and droplet movement information includes: Determine an individual's instantaneous exposure risk based on the mass of droplets from an infected person's cough that they are most exposed to at a given moment; The instantaneous exposure risk of an individual is determined based on the mass of droplets produced by the cough of an infected person that the individual is most exposed to at a certain moment, including: Calculate the instantaneous exposure risk E of pedestrian i exposed to the g-th cough of infected person j i,j,g (t), as shown in the following formula: in, represents the position p of pedestrian i at time t i At (t), the infected person with the greatest exposure has the g-th cough at the beginning Then diffuse to a distance d from the starting point i,j,g (t) The mass of the droplet at position, is the time t and The time interval between moments; If d is satisfied i,j,g (t)∈[s-0.1,s+0.1 and but The mathematical expression of is as follows: Where s is the droplet of a typical cough at time t cg The distance along the y-axis, T inf is the infection time of a typical cough, a s , b s and c s is the plane φ s Gaussian distribution function fitting parameters, plane φ s A typical cough droplet at time t cg A representative xz plane is passed through, t cg ≤T inf .
2. The method for predicting new cases of respiratory infectious diseases based on exposure risk according to claim 1, characterized in that: The step of determining the personal respiratory infectious disease exposure risk based on the personal movement information and the droplet movement information further includes: The instantaneous exposure risks within the preset time are added together to determine the personal respiratory infectious disease exposure risk.
3. The method for predicting new cases of respiratory infectious diseases based on exposure risk according to claim 2, characterized in that: The step of adding up the instantaneous exposure risks within a preset time to determine the personal respiratory infectious disease exposure risk also includes: By configuring the pedestrian dynamics simulation parameters, the respiratory activities of the infected are simulated, the spatiotemporal movement of droplets generated by the respiratory activities of the infected are determined, and the spatiotemporal movement of droplets generated by the respiratory activities of the infected are fitted by the Gaussian distribution function.
4. The method for predicting new cases of respiratory infectious diseases based on exposure risk according to claim 1, characterized in that: The generating of the prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risk and the number of new cases includes: When the target pedestrian's personal exposure risk to respiratory infectious diseases is greater than the risk threshold, the target pedestrian is defined as a high-exposure-risk individual; Obtain the total number of individuals entering the target area during the target period and calculate the total number of individuals with high exposure risk; The number of new cases is calculated based on the total number of individuals at high risk of exposure.
5. The method for predicting new cases of respiratory infectious diseases based on exposure risk according to claim 4, characterized in that: The total number of individuals at high risk of exposure is calculated as follows: Among them, C risk (α) represents the total number of individuals with high exposure risk; C total Represents the total number of individuals entering the target area during the target period; E i represents the personal respiratory infectious disease exposure risk of pedestrian i during the study period; α represents the risk threshold of high exposure to personal respiratory infectious diseases; ψ(E i ,α) represents the judgment E i Is it greater than α? If E i >α,ψ(E i ,α)=1; otherwise ψ(α i ,α)=0; The formula for calculating the number of new cases is: C new =F(C ridk ) Among them, C new represents the number of new cases; C risk (α) represents the total number of individuals with high exposure risk; F(C risk ) represents C new It is quantitatively expressed as risk The function can be any function form in which the dependent variable is positively correlated with the independent variable, including linear equations: C new =F(C risk )=β*C risk (a) Where β represents the linear equation F(C risk ) is the proportionality coefficient.
6. The method for predicting new cases of respiratory infectious diseases based on exposure risk according to claim 5, characterized in that: The generating of the prediction result of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risk and the number of new cases also includes: According to the number of historical new cases, the risk threshold and the proportional coefficient in different scenarios are configured.
7. A device for predicting new cases of respiratory infectious diseases based on exposure risk, characterized in that: include: The first module is used to obtain the personal movement information of any individual in the crowd and the droplet movement information generated by the respiratory activity of the infected person; The second module is used to determine the personal exposure risk of respiratory infectious diseases according to the personal movement information and the droplet movement information; wherein, the determination of the personal exposure risk of respiratory infectious diseases according to the personal movement information and the droplet movement information includes: determining the personal instantaneous exposure risk according to the mass of droplets produced by the cough of the infected person who is in maximum contact at a certain moment; the determination of the personal instantaneous exposure risk according to the mass of droplets produced by the cough of the infected person who is in maximum contact at a certain moment includes: Calculate the instantaneous exposure risk E of pedestrian i exposed to the g-th cough of infected person j i,j,g (t), as shown in the following formula: in, represents the position p of pedestrian i at time t i At (t), the infected person with the greatest exposure has the g-th cough at the beginning Then diffuse to a distance d from the starting point i,j,g (t) The mass of the droplet at position, is the time t and The time interval between moments; If d is satisfied i,j,g (t)∈[s-0.1,s+0.1) and but The mathematical expression of is as follows: Where s is the droplet of a typical cough at time t cg The distance along the y-axis, T inf is the infection time of a typical cough, a s , b s and c s is the plane φ s Gaussian distribution function fitting parameters, plane φ s A typical cough droplet at time t cg A representative xz plane is passed through, t cg ≤T inf ; The third module is used to analyze the relationship between the number of individuals with high exposure risk and the number of new cases according to the individual's exposure risk of respiratory infectious diseases; The fourth module is used to generate prediction results of new cases of respiratory infectious diseases based on the relationship between the number of individuals with high exposure risks and the number of new cases.
8. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 6.
