Infection prediction method, device and equipment in train passenger room and storage medium

Abstract

The embodiment of the invention provides an infection prediction method and device in a train passenger room, equipment and a storage medium. The method comprises the following steps: acquiring environment information, personnel distribution information and pathogen diffusion source information of a train passenger room; according to the environment information, the personnel distribution information and the pathogen diffusion source information, pathogen diffusion distribution data are obtained through a pathogen diffusion distribution database or a trained neural network model; according to the pathogen diffusion source information and the pathogen diffusion distribution data, obtaining an average pathogen amount corresponding to the exposure time in the to-be-predicted region; and calculating the infection probability of the to-be-predicted person in the to-be-predicted area by adopting the optimized infection probability calculation model according to the average pathogen amount and the behavior state information of the to-be-predicted person. Through region division, the average pathogen amount related to the exposure time in different regions can be obtained, and accurate prediction of the infection probability is completed by combining behavior state information of a to-be-predicted person and adopting an optimized infection probability calculation model.

Description

Technical Field

[0001] The present application relates to the technical field of disease risk prediction, and in particular to a method, device, equipment and storage medium for predicting infection in a train passenger compartment. Background Art

[0002] Pathogens of respiratory infectious diseases are usually spread through particles exhaled by the human body, among which particles with smaller particle size evaporate rapidly in the air to form droplet nuclei, which have a longer suspension time and transmission distance. Infectious respiratory diseases, such as tuberculosis, influenza and aspergillosis, seriously threaten public health and socio-economic development due to their rapid spread and wide impact. Therefore, by predicting the risk of infection, a scientific basis can be provided for prevention and control decisions, making various measures more accurate and effective. For example, infection prediction can help to reasonably arrange the distribution of personnel and even set up isolation areas in advance, so as to effectively control the transmission path of pathogens and reduce the risk of large-scale transmission. In addition, infection prediction can quickly identify high-risk areas and populations, so that prevention and control measures can be deployed in a targeted manner in advance to avoid the epidemic from getting out of control in the early stage. At the same time, traffic management departments and public health agencies can also take timely intervention measures to ensure the normal operation of society.

[0003] In the prior art, the calculation of infection probability usually relies on some classic mathematical models, which are based on epidemiological principles and predict the infection risk of individuals or groups by analyzing the transmission path and exposure risk of pathogens. For example, the Mass Action model (MA model) estimates the number of infected people by calculating the contact rate between susceptible individuals and infected individuals in a group. Specifically, the MA model assumes that the probability of infection is proportional to the proportion of infected people in the group and the contact rate, thereby obtaining a preliminary estimate of the probability of infection. Another commonly used model is the dose-response model, which analyzes the infection risk of individuals at different exposure levels by analyzing the relationship between the exposure dose of the pathogen and the probability of infection.

[0004] However, both the MA model and the dose-response model have certain limitations. These models fail to fully consider the propagation characteristics of pathogens in the air and the influence of air flow in the space, and therefore cannot accurately reflect the dynamic propagation process of pathogens in a complex environment. Especially in the special environment of train passenger compartments, these models are overly simplified and cannot effectively deal with the complexity of air flow and pathogen diffusion, resulting in low accuracy of prediction results.

[0005] Based on this, there is an urgent need for an infection prediction method for train passenger compartments to solve the technical problem of poor accuracy of probability prediction in existing technologies. Summary of the invention

[0006] The present application provides a method, device, equipment and storage medium for predicting infection in a train passenger compartment, so as to solve the technical problem of poor accuracy of probability prediction in the prior art.

[0007] In a first aspect, the present application provides a method for predicting infection in a train passenger compartment, comprising:

[0008] Obtain the current train passenger compartment environmental information, personnel distribution information and pathogen spread source information;

[0009] According to the environmental information, personnel distribution information and pathogen diffusion source information, pathogen diffusion distribution data is obtained through a pathogen diffusion distribution database or a trained neural network model;

[0010] Based on the preset area division of the passenger compartment of the current train, according to the pathogen diffusion source information and the pathogen diffusion distribution data, the average amount of pathogens in the area to be predicted corresponding to the exposure time is obtained; wherein the exposure time is the time that the person to be predicted stays in the prediction area;

[0011] Based on the area to be predicted, according to the average amount of pathogens, the behavioral status information of the person to be predicted and the exposure time of the person to be predicted, an optimized infection probability calculation model is used to calculate and obtain the infection probability of the person to be predicted in the area to be predicted;

[0012] Among them, the optimized infection probability calculation model is based on the infection probability model, and the infection probability calculation model is optimized by using the non-uniform diffusion of pathogens in the passenger compartment of the current train.

[0013] Optionally, in the method as described above, the pathogen diffusion distribution data includes the spatiotemporal trajectory of the droplet nuclei;

[0014] Then, based on the preset area division of the current train passenger compartment, according to the pathogen diffusion source information and the pathogen diffusion distribution data, obtaining the average amount of pathogens corresponding to the exposure time in the area to be predicted includes:

[0015] According to the pathogen diffusion source information, query and obtain the pathogen quantum generation rate matching the pathogen type, and obtain the number of droplets released per unit time by the infected person;

[0016] Calculate the amount of pathogens contained in one droplet nucleus according to the number of droplets released by the infected person per unit time and the quantum generation rate of the pathogen;

[0017] Determine the area to be predicted where the person to be predicted is located, and obtain the average number of the droplet nuclei corresponding to the exposure time in the area to be predicted according to the spatiotemporal trajectory of the droplet nuclei;

[0018] The average amount of pathogens is obtained based on the amount of pathogens contained in one droplet nucleus and the average number of the droplet nuclei.

[0019] Optionally, in the method as described above, based on the area to be predicted, according to the average amount of pathogens, the behavioral state information of the person to be predicted and the exposure time of the person to be predicted, an optimized infection probability calculation model is used to calculate and obtain the infection probability of the person to be predicted in the area to be predicted, including:

[0020] According to the behavior state information of the person to be predicted, obtaining the average respiratory rate of the person to be predicted;

[0021] According to the average respiratory rate, the average pathogen amount and the exposure time, an optimized infection probability calculation model is used:

[0022]

[0023] Calculate and obtain the infection probability P of the person to be predicted in the area to be predicted;

[0024] in, is the average amount of pathogens, p is the average respiratory rate, T is the exposure time, and V is the volume of the area to be predicted.

[0025] Optionally, in the method as described above, the environmental information includes at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment;

[0026] The personnel distribution information includes at least one of the current passenger capacity and personnel distribution density of the train passenger compartment;

[0027] The pathogen diffusion source information includes at least one of the pathogen type, the location information of the infected person, the number of infected people, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nucleus;

[0028] According to the environmental information, personnel distribution information and pathogen diffusion source information, pathogen diffusion distribution data is obtained through a pathogen diffusion distribution database or a trained neural network model, including:

[0029] According to at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, according to at least one of the current passenger capacity and population distribution density of the train passenger compartment, and according to at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released per unit time by the infected person, the particle size of the droplet nuclei and the initial speed of the droplet nuclei, query and obtain the pathogen diffusion distribution data through the pathogen diffusion distribution database; or,

[0030] The pathogen diffusion distribution data is acquired using the trained neural network model based on the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, based on at least one of the current passenger capacity and population density of the train passenger compartment, and based on at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei.

[0031] Optionally, in the method as described above, the acquisition of the pathogen diffusion distribution database includes:

[0032] According to the passenger compartment layout and the geometric structure of the passenger compartment of the train, a geometric calculation model matching the train is established, and the geometric calculation model is mesh discretized to obtain a mesh discretized model of the train;

[0033] Based on the grid discrete model, according to the air supply mode, ambient temperature and ambient humidity of the passenger compartment of the train, by setting the boundary conditions of the discrete model, a steady-state flow field model of the train is obtained;

[0034] Based on the steady-state flow field model, by setting the passenger capacity and personnel distribution density of the train passenger compartment, and by setting the location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nuclei, a discrete phase mode is adopted to simulate the propagation path of the droplet nuclei released by the infected person in the train passenger compartment to obtain the spatiotemporal trajectory of the droplet nuclei;

[0035] The spatiotemporal trajectory of each droplet nucleus is recorded and stored, and the environmental information, personnel distribution information and pathogen diffusion source information corresponding to the spatiotemporal trajectory are stored to obtain a pathogen diffusion distribution database.

[0036] Optionally, in the above method, the acquisition of the pathogen diffusion distribution database further includes:

[0037] According to at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, according to at least one of the passenger capacity and population distribution density of the train passenger compartment, and according to at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released per unit time by the infected person, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei, a trained neural network model is used to obtain the spatiotemporal trajectory of the droplet nuclei;

[0038] The spatiotemporal trajectory of each droplet nucleus is recorded and stored, and the environmental condition information, personnel distribution information and pathogen diffusion source information corresponding to the spatiotemporal trajectory are stored in the pathogen diffusion distribution database.

[0039] Optionally, in the method as described above, determining the area to be predicted where the person to be predicted is located, and obtaining the average number of the droplet nuclei corresponding to the exposure time in the area to be predicted according to the spatiotemporal trajectory of the droplet nuclei, comprises:

[0040] The position coordinates of the person to be predicted are obtained through a monitoring system or a sensor pre-installed in the passenger compartment of the train, and the position coordinates are matched with the preset area according to the preset area division of the passenger compartment of the current train to determine the area to be predicted where the person to be predicted is located;

[0041] According to the spatiotemporal trajectory of the droplet nuclei, obtaining a quantity change curve of the droplet nuclei corresponding to the exposure time in the area to be predicted;

[0042] According to the droplet nucleus quantity change curve, the total quantity of the droplet nuclei is obtained by using the integration method, and according to the exposure time, the average quantity of the droplet nuclei is calculated.

[0043] Optionally, in the above method, obtaining the average respiratory rate of the person to be predicted includes:

[0044] Acquiring the basic respiratory rate of the person to be predicted, and determining the speaking frequency and coughing frequency of the person to be predicted according to the exposure time;

[0045] The average respiratory rate of the person to be predicted is calculated and obtained by weighted averaging according to the basic respiratory rate, the speaking frequency and the coughing frequency.

[0046] In a second aspect, the present application provides an infection prediction device, comprising:

[0047] An information acquisition module is used to obtain the current train passenger compartment environmental information, personnel distribution information and pathogen diffusion source information;

[0048] A distribution data acquisition module, used to acquire pathogen diffusion distribution data through a pathogen diffusion distribution database or a trained neural network model according to the environmental information, personnel distribution information and pathogen diffusion source information;

[0049] A pathogen quantity calculation module is used to obtain an average pathogen quantity corresponding to the exposure time in the area to be predicted based on the preset area division of the passenger compartment of the current train, according to the pathogen diffusion source information and the pathogen diffusion distribution data; wherein the exposure time is the time that the person to be predicted stays in the prediction area;

[0050] Infection probability calculation module: used to calculate and obtain the infection probability of the person to be predicted in the area to be predicted based on the area to be predicted, according to the average amount of pathogens, the behavioral status information of the person to be predicted and the exposure time of the person to be predicted, using the optimized infection probability calculation model; wherein the optimized infection probability calculation model is based on the infection probability model, and the infection probability calculation model is optimized by using the non-uniform diffusion of pathogens in the passenger compartment of the current train.

[0051] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0052] The memory stores computer-executable instructions;

[0053] The processor executes the computer-executable instructions stored in the memory to implement the prediction method described above.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the prediction method as described above when executed by a processor.

[0055] The present application provides a method, device, equipment and storage medium for predicting infection in a train passenger compartment. The method can more accurately predict the distribution of pathogens in the train passenger compartment by obtaining the environmental information, personnel distribution information and pathogen diffusion source information of the current train passenger compartment, and adopting a neural network model based on real-time data and a pathogen diffusion distribution database. This prediction method helps to understand the concentration distribution of pathogens in different areas. Based on the preset area division of the train passenger compartment, it is possible to provide an accurate estimate of the amount of pathogens for a specific area to be predicted, ensuring the pertinence and accuracy of the prediction results. By combining the behavioral state information and exposure time of the person to be predicted, the infection probability of an individual is calculated by adopting an optimized infection probability calculation model. The optimized infection probability calculation model can flexibly adapt to complex environmental changes based on the non-uniform diffusion characteristics of pathogens in the train passenger compartment, ensuring that reliable predictions can be provided under various conditions, and improving the adaptability and accuracy of the prediction model. In addition, by timely and accurately predicting the infection probability, it can help reduce the risk of pathogen transmission in the train passenger compartment and provide a safer environment for passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0057] Figure 1 A schematic diagram of a flow chart of a method for predicting infection in a train passenger compartment provided in an embodiment of the present application;

[0058] Figure 2 A schematic flow chart of a method for obtaining an average amount of pathogens provided in an embodiment of the present application;

[0059] Figure 3 A schematic flow chart of a method for obtaining the average number of droplet nuclei provided in an embodiment of the present application;

[0060] Figure 4 A schematic flow chart of a method for obtaining the average respiratory rate of a person to be predicted provided in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of a method flow for obtaining pathogen diffusion distribution data provided in an embodiment of the present application;

[0062] Figure 6 A schematic diagram of a method flow for obtaining a pathogen diffusion distribution database provided in an embodiment of the present application;

[0063] Figure 7 A schematic diagram of a method flow for obtaining a pathogen diffusion distribution database through a neural network provided in an embodiment of the present application;

[0064] Figure 8 A schematic diagram of the structure of an infection prediction device provided in an embodiment of the present application;

[0065] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0066] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0067] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0068] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0069] In the prior art, the classic model based on aerosol transmission is the Wells-Riley model, which is widely used to predict the infection probability of airborne pathogens. The Wells-Riley model assumes that pathogens are evenly distributed in the indoor air, and the infected person is exposed to the air containing pathogens through breathing, so as to calculate the amount of pathogens inhaled per unit time to obtain the infection probability. This model works well in simple indoor environments, but for environments with complex air flow such as train passenger compartments, the limitations of its assumptions make the prediction results inaccurate. The air flow field in the train passenger compartment is extremely complex, which affects the spread of pathogens. High-speed trains mostly use a ventilation method of top air supply and bottom exhaust. In such a narrow space, the unevenness of the supply and exhaust air easily forms a longitudinal airflow. This airflow not only expands the spread range of pathogens, but also accelerates the diffusion of pollutants generated once. Slight changes in the air flow path, or even slight changes in the location of the source of pollutants, may lead to huge differences in the concentration of pathogens at different locations in the car. It can be seen that the Wells-Riley model fails to fully consider the non-uniformity of the air flow field and the dynamic diffusion behavior of pathogens, resulting in insufficient prediction accuracy in complex environments.

[0070] Based on the above technical problems and requirements, the present application improves and optimizes the limitations of the existing aerosol transmission prediction model Wells-Riley model in dealing with complex air flow environments. In high-speed trains, due to the design of top air supply and bottom exhaust, the air flow field exhibits longitudinal flow characteristics, resulting in obvious non-uniformity in the distribution of pathogens in space. The inventive concept of the present application is to provide an infection prediction method in a train passenger compartment, taking into account the dynamic diffusion of indoor air flow and pathogens to accurately predict the probability of passenger infection. Specifically, firstly, environmental information, personnel distribution information and information on pathogen diffusion sources in the train passenger compartment are collected, and a pathogen diffusion distribution database or a neural network model is used to predict the real-time diffusion of pathogens in the train passenger compartment. By dividing the train passenger compartment into preset areas and combining pathogen diffusion data, the pathogen concentration corresponding to the exposure time in each area can be more accurately predicted. Furthermore, the infection probability is calculated by adopting an optimized infection probability calculation model. This not only enhances the reliability of the prediction, but also provides a scientific basis for the control and prevention measures of pathogen transmission in the train passenger compartment. The ultimate goal is to reduce the risk of infectious disease transmission in public transportation and ensure the health and safety of passengers.

[0071] The application scenarios of this application are mainly concentrated in the complex closed or semi-closed environment of the train passenger compartment, especially in public transportation such as high-speed rail and subway. In these scenarios, the air flow field in the train passenger compartment is complex and changeable, the passenger density is high, and the air circulation system in the carriage usually adopts the design of top air supply and bottom exhaust. This unique ventilation mode easily forms a non-uniform air flow path, which in turn affects the propagation behavior of pathogens. By real-time monitoring and predicting the distribution of pathogens in the carriage, the method can accurately calculate the infection probability of passengers in a certain area. Based on the real-time data support provided, it is possible to respond in time and take effective and targeted prevention and control measures to ensure the health and safety of passengers and employees. Specific applications include adjusting the ventilation system of the train and optimizing the air circulation method to reduce the gathering of pathogens in the carriage. In addition, based on the prediction results, passenger seats and itineraries can be arranged more accurately, such as limiting the number of people in the carriage or adding isolation areas during the peak of the epidemic to ensure passenger safety. This method is also suitable for special event response, such as during the flu season or the outbreak of new diseases, by accurately predicting and deploying necessary hygiene and safety measures in advance, thereby reducing the health risks of the public transportation system and improving the safety of public transportation.

[0072] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0073] Figure 1 The following is a flow chart of a method for predicting infection in a train passenger compartment provided in an embodiment of the present application. Figure 1 As shown, including:

[0074] S11, obtaining the current train passenger compartment environmental information, personnel distribution information and pathogen diffusion source information.

[0075] In this embodiment, environmental information involves multiple aspects of the train passenger compartment, including but not limited to temperature, humidity, carbon dioxide concentration, and air circulation. For example, temperature and humidity can directly affect the survival status and transmission speed of pathogens, while carbon dioxide concentration indirectly reflects the ventilation conditions and passenger density in the passenger compartment. By collecting these data, it is possible to distinguish and identify possible high-risk areas, such as areas with poor air circulation, which may become hotspots for pathogen aggregation and transmission. Next, understanding the distribution of personnel is conducive to analyzing the pathogen transmission path and its possible contact network, and is helpful to take targeted prevention and control measures, such as diverting people or designating certain areas as quarantine areas. Exemplarily, personnel distribution information includes the number of passengers, distribution location, and riding layout. Pathogen diffusion source information refers to locating and identifying potential pathogen release sources, such as known infected person locations, activity ranges, and possible pathogen release events (such as coughing or sneezing). Exemplarily, this information can be obtained through health status reports of infected people, medical monitoring equipment, or observations of crew members. In addition, modern train systems may be equipped with biomonitoring technology that can detect the presence of specific pathogens in the air, thereby providing more accurate pathogen source information. It can be seen that obtaining the current train passenger compartment environment information, personnel distribution information and pathogen diffusion source information is the basis for effective infection risk prediction.

[0076] S12, obtaining pathogen diffusion distribution data through a pathogen diffusion distribution database or a trained neural network model according to environmental information, personnel distribution information and pathogen diffusion source information.

[0077] In this embodiment, the pathogen diffusion distribution database contains historical pathogen propagation data based on different train passenger compartment conditions, which are accumulated through a large number of numerical simulations and actual tests. By inputting the current environmental conditions, personnel distribution and pathogen diffusion source information into the database, the pathogen diffusion distribution data that matches the current conditions can be quickly retrieved. This method can provide a relatively fast prediction of pathogen distribution and is suitable for scenarios with high real-time requirements. On the other hand, the trained neural network model is a model trained based on a large amount of historical data and simulation data. The neural network model can predict the spread of pathogens in the train passenger compartment based on the currently input environmental condition information, personnel distribution information and pathogen diffusion source information. Compared with database queries, neural network models can better handle complex multidimensional data and provide more accurate pathogen distribution predictions under nonlinear conditions. This method is particularly suitable for scenarios where multiple complex factors interact with each other, and can make high-precision predictions of pathogen diffusion in complex flow field environments.

[0078] It can be seen that the database provides a wealth of historical and real-time data, while the neural network provides powerful data analysis capabilities. This combination not only enhances the understanding and use efficiency of existing data, but also improves the ability to predict the risk of pathogen transmission through continuous learning and optimization of the prediction model. For example, when the internal environment of the train changes, such as changes in personnel distribution or changes in external environmental factors, the neural network model can quickly adapt to these changes and update the prediction results in real time. In short, through the comprehensive application of the pathogen diffusion distribution database and the trained neural network model, the spread of pathogens in the train passenger compartment can be effectively predicted and controlled, thereby protecting the health of passengers and staff, while providing solid scientific support for train operations.

[0079] S13, based on the preset area division of the current train passenger compartment, according to the pathogen diffusion source information and pathogen diffusion distribution data, obtain the average pathogen quantity corresponding to the exposure time in the area to be predicted; wherein the exposure time is the time the person to be predicted stays in the predicted area.

[0080] In this embodiment, when predicting the infection risk in the train passenger compartment, it is first necessary to determine each analysis area based on the preset area division. For example, the train passenger compartment is usually divided into multiple functional areas, and these area divisions are finely set according to factors such as the geometric structure of the passenger compartment, air flow characteristics, and personnel density to ensure that the air flow and personnel activities in each area can be analyzed independently. Using this division, the spread dynamics of pathogens in specific areas can be analyzed in more detail. Regional division will directly affect the accuracy of pathogen spread prediction. Therefore, when dividing, it is necessary to comprehensively consider factors such as the ventilation system design, seat layout, and passenger activity path in the train passenger compartment to cover all possible infection risk points.

[0081] After determining the area to be predicted, it is necessary to analyze the pathogen concentration in the area based on the acquired pathogen diffusion distribution data. The pathogen diffusion distribution data is a combination of previously acquired environmental condition information, personnel distribution information, and pathogen diffusion source information, reflecting the distribution characteristics of pathogens in different areas and their dynamic behavior over time. In order to accurately analyze the infection risk in the area to be predicted, the key is to determine the average pathogen amount during the exposure time. The exposure time refers to the time that the person to be predicted stays in the area. During this period of time, the pathogen concentration in the area may change due to various factors. During the train running, the concentration of pathogens fluctuates due to air flow, the operation of the ventilation system, and the activities of other passengers. Therefore, by comprehensively analyzing the changes in pathogen concentration during the exposure time, the average pathogen amount can be calculated more accurately. This data reflects the overall exposure of pathogens in the area to be predicted during the exposure time, and is the key to the subsequent infection risk probability calculation. In summary, the process of obtaining the average pathogen amount is a comprehensive calculation based on the preset regional division and pathogen diffusion distribution data combined with the exposure time. Through this process, the diffusion behavior of pathogens in the train passenger compartment can be effectively captured, and the infection risk in a specific area can be accurately predicted, providing a scientific basis for health management and epidemic prevention measures in the train passenger compartment.

[0082] S14, based on the area to be predicted, according to the average amount of pathogens, the behavioral status information of the persons to be predicted and the exposure time of the persons to be predicted, an optimized infection probability calculation model is used to calculate and obtain the infection probability of the persons to be predicted in the area to be predicted; wherein the optimized infection probability calculation model is based on the infection probability model, and the infection probability calculation model is optimized by using the non-uniform diffusion of pathogens in the passenger compartment of the current train.

[0083] In this embodiment, when calculating the infection probability of the person to be predicted in the area to be predicted, it is first necessary to comprehensively consider the average amount of pathogens in the area, the behavioral state information of the person to be predicted, and the exposure time. These factors directly determine the degree of contact and contact time between the pathogen and the person to be predicted. Specifically, the average amount of pathogens reflects the total amount of pathogens present in the area during the exposure period of the person to be predicted, which is directly related to the concentration of pathogens in the air and the inhalation amount of the person to be predicted. The behavioral state information of the person to be predicted provides specific activities of the person during the exposure period, such as breathing rate, speaking frequency, coughing frequency, etc. These behaviors directly affect the inhalation amount of pathogens, and then affect the possibility of infection. For example, a higher breathing rate or frequent coughing may increase the inhalation amount of pathogens, thereby increasing the risk of infection. Therefore, the behavioral state information needs to be quantified and incorporated into the model in the calculation of infection probability. The exposure time refers to the length of time the person to be predicted stays in the area. During this period, pathogens may continue to accumulate or diffuse with air flow. The longer the exposure time, the more pathogens the person to be predicted inhales, and the greater the possibility of infection. Therefore, the exposure time is one of the key parameters in the calculation of infection probability.

[0084] Based on the above information, the optimized infection probability calculation model is used to calculate the infection probability of the predicted person in the area. This optimization model is adjusted based on the non-uniform diffusion characteristics of the pathogen in the current train passenger compartment. Compared with the traditional uniform diffusion model, the non-uniform diffusion model can more truly reflect the distribution characteristics of pathogens in complex air flow fields. In the train passenger compartment, due to the unevenness of air flow, differences in personnel distribution, and dynamic changes in pathogen sources, the concentration distribution of pathogens is usually not uniform. This feature makes the traditional infection probability calculation model have errors in the specific environment of the train passenger compartment. To this end, the optimized infection probability calculation model simulates the spatiotemporal distribution of pathogens more accurately by considering these non-uniform diffusion factors, and can more accurately calculate the infection probability under different conditions, thereby providing a more reliable scientific basis for epidemic prevention and control in the train passenger compartment. Through this optimization model, the infection probability of the predicted person in a specific area can be finally obtained. This probability can not only judge the risk level of the predicted person in this environment, but also provide guidance for train operation management, optimize the ventilation system, adjust the seating arrangement, or take other protective measures to reduce the overall infection risk.

[0085] This application can capture the actual situation in the train passenger compartment in real time by obtaining the environmental information, personnel distribution information and pathogen diffusion source information of the current train passenger compartment. This ensures the accuracy and real-time nature of the data in the prediction process, and helps to more accurately reflect the dynamic changes in the carriage. Using the pathogen diffusion distribution database or the trained neural network model, the spread of pathogens in the train passenger compartment can be effectively simulated and predicted. This not only improves the accuracy of the prediction, but also can cope with complex air flow conditions and ensure the accuracy of the pathogen distribution data. By obtaining the average amount of pathogens corresponding to the exposure time in the predicted area based on the pathogen diffusion source information and the pathogen diffusion distribution data, the analysis of the infection risk is more accurate and targeted. This process takes into account the exposure time of personnel in different areas, thereby improving the accuracy of the infection probability prediction. The optimized infection probability calculation model used is based on the non-uniform diffusion of pathogens in the train passenger compartment, which can more accurately analyze the actual infection risk and is suitable for complex train passenger compartment environments. In summary, this application achieves a more accurate infection probability prediction through multi-level data acquisition and optimized model calculation.

[0086] In one embodiment, the pathogen diffusion distribution data includes the spatiotemporal trajectory of the droplet nuclei.

[0087] In this embodiment, the pathogen diffusion distribution data is one of the core data for infection risk prediction. The spatiotemporal trajectory of droplet nuclei records the dynamic distribution of droplet nuclei in the train passenger compartment over time and space, reflecting the propagation path of pathogens in the air. Droplet nuclei refer to tiny droplets carrying pathogens, which are released into the air when the infected person breathes, speaks, coughs or sneezes. Due to the small particle size of droplet nuclei, they usually stay suspended in the air for a long time and spread with the air flow, which makes them an important medium for the spread of respiratory diseases. In specific applications, the spatiotemporal trajectory of droplet nuclei includes not only its position change in space, but also its movement speed, diffusion range and concentration change over time. These data can reveal the distribution pattern of droplet nuclei in different time periods. For example, during the peak period of passenger activity, the diffusion speed and range of droplet nuclei may increase significantly due to dense crowds and increased air flow. On the contrary, when the air conditioning system is running, the droplet nuclei may be affected by the airflow to form a specific diffusion path, thereby changing their distribution pattern in the passenger compartment.

[0088] The spatiotemporal trajectory data of droplet nuclei can be applied in many aspects. First, the spatiotemporal trajectory data of droplet nuclei can predict the concentration distribution of pathogens at a specific time and place, providing a scientific basis for passenger infection risk analysis. Secondly, by analyzing the diffusion path of droplet nuclei, the design and operation strategy of the train's ventilation system can be optimized to reduce the spread of pathogens in the passenger compartment. Finally, the spatiotemporal trajectory data can also be used to formulate more effective prevention and control measures, such as focusing on disinfection of high-risk areas or strengthening air purification in a specific time period, thereby reducing the probability of passenger infection.

[0089] Figure 2 A flow chart of a method for obtaining the average amount of pathogens provided in an embodiment of the present application. Based on the above embodiment, in the above step S13, the average amount of pathogens corresponding to the exposure time in the predicted area is obtained according to the pathogen diffusion source information and pathogen diffusion distribution data. Herein, an implementation method is provided. Figure 2 As shown, including:

[0090] S21, according to the pathogen diffusion source information, query and obtain the pathogen quantum generation rate matching the pathogen type, and obtain the number of droplets released by the infected person per unit time;

[0091] S22, according to the number of droplets released by the infected person per unit time and the quantum generation rate of the pathogen, the amount of pathogens contained in a droplet nucleus is calculated;

[0092] S23, determining the area to be predicted where the person to be predicted is located, and obtaining the average number of droplet nuclei corresponding to the exposure time in the area to be predicted according to the spatiotemporal trajectory of the droplet nuclei;

[0093] S24, obtaining an average amount of pathogens according to the amount of pathogens contained in one droplet nucleus and the average number of droplet nuclei.

[0094] In this embodiment, the pathogen quantum generation rate matching the pathogen type can be queried and obtained through the pathogen diffusion source information. The pathogen quantum generation rate refers to the number of pathogens with infectious ability released by an infected person through coughing, sneezing or breathing in a unit time. Different types of pathogens may have differences in quantum generation rates, so they need to be matched according to the specific pathogen type. By querying the database or reference corresponding to the pathogen type, these rate data can be obtained, thereby providing a basis for subsequent pathogen quantity calculations. Droplet nuclei become key carriers of infection transmission due to their ability to carry pathogens. Next, the number of droplet nuclei released by the infected person per unit time is obtained. The number of droplets is usually estimated by monitoring the breathing, coughing or sneezing behaviors of the infected person. Exemplarily, the estimation of the number of droplets can be achieved by preset sensing devices and behavior monitoring devices (such as cameras). The device is installed in the train passenger compartment and can collect the behavior data of the infected person in real time and identify these behaviors through corresponding algorithms. First, when the infected person is detected to breathe, cough or sneeze, the number of droplets released per unit time is estimated based on the frequency and intensity of the behavior. This estimation is based on a known behavior model. For example, coughing and sneezing usually release a large amount of droplets, while breathing releases a smaller amount of droplets. The average droplet release rate of different behaviors is estimated, such as each cough can release thousands of droplets, each sneeze can release tens of thousands of droplets, and breathing can release fewer droplets.

[0095] The amount of pathogens contained in a single droplet nucleus can be calculated using the two parameters of the number of droplets released by the infected person and the quantum generation rate of the pathogen.

[0096] For example, the following formula is used:

[0097]

[0098] Calculate the amount of pathogens contained in a single droplet nucleus q d ; Among them, q e is the quantum generation rate of pathogens, N e It is the number of droplets released by an infected person per unit time.

[0099] Next, in order to accurately predict the risk of pathogen transmission in the train passenger compartment, it is also necessary to determine the specific area where the person to be predicted is located. The spatiotemporal trajectory records the position and quantity changes of droplet nuclei at different time points. Once the area where the person to be predicted is located is determined, the average number of droplet nuclei during the exposure time can be calculated by analyzing the spatiotemporal trajectory data of these droplet nuclei. Finally, based on the amount of pathogens contained in a droplet nucleus and the average number of droplet nuclei, the average amount of pathogens in the area is calculated and obtained. This average amount of pathogens represents the total amount of pathogens present in the area to be predicted during the exposure time, which indicates the direct basis for the infection risk in the area.

[0100] For example, the following formula is used:

[0101]

[0102] Calculate the average pathogen load in, is the average number of droplet nuclei in the area to be predicted during the exposure time, q d The amount of pathogens contained in a single droplet nucleus. That is, the average amount of pathogens is obtained by multiplying the average number of droplet nuclei by the amount of pathogens in each droplet nucleus.

[0103] In a specific embodiment, Figure 3 The following is a flow chart of a method for obtaining the average number of droplet nuclei provided in an embodiment of the present application. A specific implementation method is provided for the above step S23. Figure 3 As shown, including:

[0104] S31, obtaining the position coordinates of the person to be predicted through a monitoring system or a preset sensor in the train passenger compartment, and matching the position coordinates with the preset area according to the preset area division of the current train passenger compartment to determine the area to be predicted where the person to be predicted is located;

[0105] S32, obtaining a change curve of the number of droplet nuclei corresponding to the exposure time in the area to be predicted according to the spatiotemporal trajectory of the droplet nuclei;

[0106] S33, according to the droplet nucleus quantity change curve, using the integration method, obtain the total number of droplet nuclei, and according to the exposure time, calculate the average number of droplet nuclei.

[0107] In this embodiment, the specific position coordinates of the passengers can be captured in real time by pre-installing a monitoring system or sensor in the carriage. These coordinate data are then matched with the preset regional divisions in the carriage to ensure that each passenger can be accurately assigned to a specific monitoring area. Once the specific area of ​​the passenger is determined, the next step is to use the collected spatiotemporal trajectory data of the droplet nuclei to determine the pathogen concentration in the area to be predicted by analyzing these spatiotemporal trajectories. In the specific analysis process, it is first necessary to extract the droplet nucleus quantity change curve that changes with exposure time in the area to be predicted from the spatiotemporal trajectory of the droplet nuclei. This curve reflects the concentration change trend of the droplet nuclei in the area to be predicted during the exposure time. Since the spread of pathogens is affected by many factors, such as air flow, passenger activities, and changes in the amount of pathogen release, the number of droplet nuclei is not constant, but will show complex changes over time. Next, according to the obtained droplet nucleus quantity change curve, the total number of droplet nuclei is calculated by the integral method. The integral method is to accumulate the area under the curve to obtain the cumulative number of droplet nuclei during the entire exposure time.

[0108] After obtaining the total number of droplet nuclei, it is necessary to further calculate the average number of droplet nuclei corresponding to the exposure time in the predicted area according to the exposure time and the preset mean calculation formula. Exemplarily, by removing the exposure time, the droplet nuclei and the average number per unit time can be obtained. That is, through this calculation, the average concentration of droplet nuclei in the predicted area during the entire exposure time can be obtained. This average number not only provides an intuitive indicator for analyzing the pathogen concentration level in the area, but also provides a direct input parameter for the subsequent infection probability calculation.

[0109] In one embodiment, a specific implementation method is provided for calculating and obtaining the infection probability of the predicted person in the predicted area in the above step S14. Based on the above embodiment, it includes:

[0110] S141, obtaining the average respiratory rate of the person to be predicted, and using the optimized infection probability calculation model based on the average respiratory rate, average pathogen quantity and exposure time:

[0111]

[0112] S142, calculate and obtain the infection probability P of the person to be predicted in the area to be predicted; wherein, is the average amount of pathogens, p is the average respiration rate, T is the exposure time, and V is the volume of the area to be predicted.

[0113] In this embodiment, when performing infection risk analysis on the person to be predicted, it is first necessary to obtain the average respiratory rate of the person. The average respiratory rate refers to the average respiratory frequency of the person to be predicted within a certain period of time. This data can show the amount of pathogen inhaled. Generally, the average respiratory rate can be calculated by comprehensively measuring the individual's basal respiratory rate, activity status (such as walking, talking or sitting quietly), and other factors affecting breathing (such as emotional tension, ambient temperature). In actual operation, this rate can be analyzed through portable physiological monitoring equipment, motion sensors or clinical data to ensure that it reflects the individual's actual breathing conditions under exposure conditions.

[0114] After obtaining the average respiratory rate of the person to be predicted, the optimized infection probability calculation model is used for further analysis in combination with the average amount of pathogens and exposure time in the area to be predicted. According to the core formula of the optimized infection probability calculation model, the infection probability of the corresponding person to be predicted is calculated. Among them, the average amount of pathogens is calculated by the previous steps, which represents the concentration of pathogens in the area to be predicted during the exposure time. The average respiratory rate of the person to be predicted directly affects the amount of pathogens inhaled during the exposure time. A higher respiratory rate means more air and pathogens are inhaled, which will increase the probability of infection. The exposure time refers to the time the person to be predicted stays in the area. As the exposure time increases, the amount of pathogens inhaled by the person will also increase, which directly leads to an increase in the probability of infection. The volume of the area to be predicted reflects the diffusion range of the pathogen in space. The larger the volume, the lower the concentration of the pathogen under the same number of pathogens, and thus the risk of infection may also be reduced. By substituting these parameters into the optimized infection probability calculation model, the infection probability of the person to be predicted in a specific area can be obtained. Compared with the traditional uniform diffusion model, this model is more adaptable, especially when considering factors such as the complex air flow and high population density in the train passenger compartment, and can provide more accurate infection probability predictions.

[0115] Further, based on the above embodiment, the formula for calculating the amount of pathogens contained in a single droplet nucleus and the formula for calculating the total amount of pathogens are combined with the calculation formula of the above optimized infection probability calculation model to obtain the following formula:

[0116]

[0117] in, is the average number of droplet nuclei in the area to be predicted during the exposure time, q e is the quantum generation rate of the pathogen, p is the average respiration rate, T is the exposure time, N e is the number of droplets released by the infected person per unit time, and V is the volume of the area to be predicted.

[0118] In a specific embodiment, Figure 4 The following is a flow chart of a method for obtaining the average respiratory rate of a person to be predicted provided in an embodiment of the present application. It is a specific description of the implementation method of obtaining the average respiratory rate in the above step S141. Figure 4 As shown, including:

[0119] S41, obtaining the basic respiratory rate of the person to be predicted, and determining the speaking frequency and coughing frequency of the person to be predicted according to the exposure time;

[0120] S42, calculating and obtaining the average respiratory rate of the person to be predicted by weighted average according to the basic respiratory rate, speaking frequency and coughing frequency.

[0121] In this embodiment, the average respiratory rate refers to the average respiratory frequency of a person over a period of time. This indicator directly affects the number of pathogens in the air they inhale, thereby affecting the probability of infection. In order to ensure the accuracy of this data, it is first necessary to obtain the basic respiratory rate, speaking frequency and coughing frequency of the person to be predicted. The basic respiratory rate is the respiratory rate of the person to be predicted in a resting state, usually referring to the number of breaths per minute without any physical activity or emotional excitement. This indicator is usually measured by a respiratory sensor worn on the chest or abdomen, which can record the rhythm and frequency of breathing in real time. Exemplarily, the basic respiratory rate will vary depending on factors such as the age, gender, and health status of the individual, so the specific circumstances of the individual need to be considered when obtaining it. To this end, the basic respiratory rate can be determined by querying the preset table in the form of a preset table through information such as the age and gender of the individual.

[0122] In addition to the basal respiratory rate, it is also necessary to obtain the speaking frequency of the person to be predicted during the exposure period. Speaking frequency refers to the frequency of speech activities performed by a person within a specific period of time. When speaking, the respiratory rate usually increases and may be accompanied by deeper breathing, which causes more air and possible pathogens to be inhaled. This data is usually monitored by voice recognition devices or audio sensors in the environment, which can recognize the speech activities of the person and record the frequency and duration of speaking. Coughing frequency is another important factor to consider. Coughing not only increases the respiratory rate, but also causes greater airflow impact, thereby increasing the number of inhaled pathogens. The coughing frequency can be obtained through cough sensors or audio monitoring devices, which can distinguish coughs from other sounds and record the frequency and intensity of coughs.

[0123] After obtaining the basic respiratory rate, speaking frequency and coughing frequency, the average respiratory rate of the person to be predicted needs to be calculated by weighted average. Weighted average is a calculation method that takes into account the overall impact of different factors. When applied here, weights can be assigned according to the contribution of different activity states to the respiratory rate. For example, if the person to be predicted is in a resting state most of the time during the exposure period, the weight of the basic respiratory rate may be higher; if the person speaks or coughs frequently, the weights of the corresponding speaking frequency and coughing frequency should be increased. By reasonably allocating weights and weighted averaging each respiratory frequency, a more accurate average respiratory rate can be obtained. The average respiratory rate can more truly reflect the respiratory behavior of the person to be predicted under actual exposure conditions, thereby improving the accuracy of infection risk analysis. By accurately calculating the average respiratory rate of the person to be predicted, the amount of pathogens inhaled in the exposure environment can be better predicted, providing scientific basic data support for the final infection probability.

[0124] In a specific embodiment, an exemplary embodiment is provided for the environmental information, personnel distribution information and pathogen diffusion information obtained in the above step S11.

[0125] First, the environmental information includes at least one of the ventilation mode, the environmental temperature and the environmental humidity of the train passenger compartment.

[0126] In this embodiment, the environmental condition information covers various factors related to the air flow and physical environment in the train passenger compartment, which have a direct impact on the transmission path and diffusion rate of the pathogen. Specifically, the environmental condition information includes at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment. The air supply mode refers to how the train air conditioning system delivers air to the passenger compartment, which may include multiple modes such as top air supply, bottom exhaust, and mixed air supply. Different air supply modes will affect the direction and speed of air flow, thereby affecting the transmission trajectory of pathogens. Ambient temperature refers to the temperature conditions in the passenger compartment, which is usually controlled by the air conditioning system. Temperature not only affects the comfort of passengers, but also affects the survival time and transmission efficiency of pathogens. Ambient humidity is also an important factor because humidity affects the evaporation rate of droplet nuclei in the air and the stability of pathogens.

[0127] Secondly, the personnel distribution information includes at least one of the passenger capacity and personnel distribution density of the current train passenger compartment.

[0128] In this embodiment, the personnel distribution information mainly relates to the number and spatial distribution of passengers in the train compartment. This information directly affects the diffusion range and concentration of pathogens. Specifically, the personnel distribution information includes at least one of the passenger capacity and personnel distribution density of the current train compartment. The passenger capacity refers to the total number of passengers in the train compartment at a certain moment. A higher passenger capacity usually means a higher population density, which may lead to an increase in the concentration of pathogens in the air, thereby increasing the risk of infection. The personnel distribution density describes the spatial distribution of passengers in the train compartment, such as whether they are concentrated in a certain area or evenly distributed throughout the compartment. Changes in the personnel distribution density will affect the pattern of air flow and further affect the spread of pathogens.

[0129] Finally, the pathogen diffusion source information includes at least one of the pathogen type, the location information of the infected person, the number of infected people, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nucleus.

[0130] In this embodiment, the pathogen diffusion source information refers to specific data related to the release and diffusion of pathogens, which determines the initial distribution and propagation characteristics of pathogens in space. The pathogen diffusion source information includes at least one of the pathogen type, the location information of the infected person, the number of infected people, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nucleus. The pathogen type refers to a specific pathogen, such as a virus or bacteria. Different types of pathogens have different survival times and propagation capabilities in the air. The location information of the infected person describes the specific location of the infected person in the train passenger compartment, and this information can be used to determine the initial diffusion path of the pathogen. The number of infected people refers to the number of infected people actually present in the train passenger compartment, which directly affects the release amount of the pathogen. The number of droplet nuclei released by the infected person per unit time indicates the total amount of droplet nuclei released by each infected person within a certain period of time. The droplet nucleus particle size and initial velocity are important physical parameters that affect the movement of droplet nuclei in the air. The smaller the particle size, the longer the droplet nucleus is suspended in the air, the greater the initial velocity, and the wider the range of droplet nucleus diffusion. This information together determines the transmission path and diffusion pattern of pathogens within the passenger room.

[0131] By comprehensively analyzing environmental conditions, personnel distribution and pathogen diffusion source information, the infection prediction model can provide dynamic simulation based on real conditions, which can more accurately predict the spread of pathogens in train passenger compartments and further analyze the infection risk of the predicted personnel.

[0132] Furthermore, in a specific embodiment, Figure 5A schematic diagram of a method for obtaining pathogen diffusion distribution data provided in an embodiment of the present application. An implementation method is provided for obtaining pathogen diffusion distribution data in the above step S12. Based on the above embodiment, Figure 5 As shown, including:

[0133] S51, according to the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, at least one of the current passenger capacity and population distribution density of the train passenger compartment, and at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei, query and obtain the pathogen diffusion distribution data through the pathogen diffusion distribution database.

[0134] In this embodiment, the basic mode of air flow is determined according to the air supply mode, ambient temperature and humidity of the train passenger compartment. These environmental parameters will directly affect the propagation path and diffusion speed of the droplet nuclei, and the air supply mode determines how the air circulates in the passenger compartment, thereby affecting the distribution of pathogens. In addition, the passenger capacity represents the total number of passengers in the passenger compartment, and the passenger distribution density indicates the distribution of these passengers in space. This information helps to determine the potential concentration area of ​​pathogens in the passenger compartment, because densely populated areas are often places where pathogens are more likely to gather and spread. On this basis, the specific characteristics of the pathogens and the behavioral information of the infected person need to be considered. Specifically, data such as the type of pathogen, the location information of the infected person, and the number of infected people will affect the initial diffusion range of the pathogen. Factors such as the number of droplet nuclei released by the infected person per unit time, the particle size of the droplet nuclei, and the initial speed determine the propagation efficiency and diffusion range of the pathogen in the air. These data not only describe the state of the pathogen at the initial moment, but also affect its propagation mode in the entire passenger compartment. By integrating the above multiple parameters, it is possible to query and obtain pathogen diffusion data that matches the current train passenger compartment conditions from the pathogen diffusion distribution database. These data are accumulated through a large number of simulations and field tests in the early stage, and include the diffusion pattern and concentration distribution of pathogens under different conditions. By querying these data, the possible distribution of pathogens in the guest room under the current conditions can be quickly obtained, thus providing the necessary scientific basis for subsequent infection risk analysis.

[0135] S52, according to the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, at least one of the current passenger capacity and population distribution density of the train passenger compartment, and at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei, a trained neural network model is used to obtain the pathogen diffusion distribution data.

[0136] In this embodiment, in another implementation, a trained neural network is used. The neural network model can generate distribution data of pathogen diffusion through comprehensive analysis of these multi-dimensional input data. After a lot of training, the model has the ability to accurately predict the spread of pathogens in complex environments. It can handle nonlinear relationships and identify complex interactions between environmental conditions, personnel distribution and pathogen characteristics, thereby providing more accurate diffusion prediction results than traditional methods. Finally, using these predicted data, the distribution of pathogens in the passenger compartment of the train can be obtained. The advantage of the neural network model is that it can handle complex input conditions and provide stable prediction results in a changing environment, thereby helping to formulate more effective prevention and control measures. In summary, these integrated data are processed by two main methods: one is to directly query the pathogen diffusion distribution database, which stores historical and real-time propagation data and provides fact-based support for prediction; the other is to apply neural network models, which are trained to simulate and predict the nonlinear diffusion behavior of pathogens in complex passenger compartment environments. Through real-time updated environmental and personnel data, the model can dynamically adjust the prediction results to ensure the timeliness and accuracy of decision support.

[0137] Here, the training of the neural network is further explained. The neural network is trained through the data stored in the pathogen diffusion database. Specifically, a large amount of data related to the spread of pathogens in train passenger compartments has been stored in the pathogen diffusion database. These data include the spread trajectory and distribution of pathogens in the carriage under different environmental conditions (such as temperature, humidity, air supply mode, etc.), personnel distribution information (such as passenger capacity, personnel density, etc.), and pathogen diffusion source information (such as pathogen type, location and behavior status of the infected person, etc.). These data in the database cover a variety of situations under different train models and passenger compartment layouts, and have a wide range of representativeness and diversity. In the process of training the neural network, these stored pathogen diffusion data are first used as the input of the training set. These data are input into the neural network model as the basis for model learning. During the training process, the neural network gradually learns the laws and patterns of pathogen spread in the train passenger compartment by repeatedly adjusting its internal weights and biases. The neural network will analyze and summarize the characteristics of pathogen diffusion under different environmental and personnel conditions, thereby establishing a model that can predict the distribution of pathogens under given input conditions.

[0138] After a large amount of data training, the neural network gradually reached the expected performance indicators, that is, it can accurately predict the spread of pathogens when faced with new input data. When the training of the neural network reaches the preset accuracy and generalization ability, the model can be called a trained neural network. This trained neural network model can quickly predict the distribution of pathogens in the train passenger compartment based on new environmental conditions, personnel distribution information and pathogen diffusion source information. The prediction of the trained neural network can not only greatly improve the prediction speed, but also effectively reduce the consumption of computing resources, providing technical support for real-time applications.

[0139] In a specific embodiment, Figure 6 A schematic diagram of a method for obtaining a pathogen diffusion distribution database provided in an embodiment of the present application. Figure 6 As shown, including:

[0140] S61, establishing a geometric calculation model matching the train according to the passenger compartment layout and the geometric structure of the passenger compartment, and performing grid discretization on the geometric calculation model to obtain a grid discretization model of the train;

[0141] S62, based on the grid discrete model, according to the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, by setting the boundary conditions of the discrete model, a steady-state flow field model of the train is obtained;

[0142] S63, based on the steady-state flow field model, by setting the passenger capacity and population distribution density of the train passenger compartment, and by setting the location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nucleus, the discrete phase mode is adopted to simulate the propagation path of the droplet nuclei released by the infected person in the train passenger compartment to obtain the spatiotemporal trajectory of the droplet nuclei;

[0143] S64, record and store the spatiotemporal trajectory of each droplet nucleus, and store the environmental information, personnel distribution information and pathogen diffusion source information corresponding to the spatiotemporal trajectory to obtain a pathogen diffusion distribution database.

[0144] In this embodiment, it is first necessary to build a geometric calculation model that matches the train. This model is the basis for accurate fluid dynamics simulation. According to the passenger compartment layout and geometric structure of the train, a detailed three-dimensional geometric calculation model is constructed. This model needs to reflect the actual structure of the train passenger compartment as accurately as possible, including the seat layout, vent location, wall shape and other physical properties that affect air flow. This accurate geometric modeling can ensure that the subsequent fluid dynamics simulation results have high credibility and accuracy. After the geometric calculation model is established, the model needs to be meshed discretized. Mesh discretization is to divide the continuous geometric space into multiple small cells, which constitute the basic unit of the calculation model. Through mesh discretization, complex three-dimensional space problems can be converted into discrete problems that can be handled by computers. In the discrete process, it is necessary to reasonably set the mesh density according to the complexity of the flow field in different areas. For example, in areas where air flow is more complex, such as near the air supply outlet or in passenger-dense areas, a finer mesh should be used to ensure the accuracy of the simulation results.

[0145] Based on the discretized grid model, the next step is to set the boundary conditions of the model according to the air supply mode, ambient temperature and ambient humidity of the train passenger compartment. The air supply mode determines how the air flows in the passenger compartment, including parameters such as the direction, speed and temperature of the air supply. These factors directly affect the propagation path of droplet nuclei in the air. Ambient temperature and humidity affect the physical properties of air, such as density and viscosity, which also affect the way and speed of air flow. By setting these boundary conditions, a stable flow field model can be established, which can reflect the actual situation of air flow in the train passenger compartment and lay the foundation for the subsequent simulation of droplet nucleus propagation. After the steady-state flow field model is established, it is further necessary to set parameters related to pathogen diffusion, including the current passenger capacity and passenger distribution density of the train passenger compartment, the location information of the infected person, the number of infected people, the number of droplet nuclei released by the infected person per unit time, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei. The passenger capacity and passenger distribution density affect the air flow pattern and the concentration distribution of pathogens in the passenger compartment. The location and number of infected people determine the initial distribution state of the droplet nuclei. The particle size and initial velocity of droplet nuclei affect their movement in the air, including sedimentation velocity, diffusion range and residence time. The setting of these parameters provides basic data for the subsequent simulation of the propagation path of droplet nuclei using discrete phase model.

[0146] When the discrete phase mode is used for simulation, the droplet nuclei are regarded as discrete particles moving in the air flow field. Through this simulation, the propagation path of the droplet nuclei in the train passenger compartment can be calculated. The simulation results will generate the spatiotemporal trajectory data of the droplet nuclei, which reflects the distribution of the droplet nuclei at different time points and different spatial positions. Finally, the spatiotemporal trajectory of each droplet nucleus is recorded and stored, and the environmental condition information, personnel distribution information and pathogen diffusion source information corresponding to these trajectories are stored at the same time. These data together constitute the pathogen diffusion distribution database. The database not only includes the movement trajectory of the droplet nuclei, but also covers various environmental and personnel factors that affect these trajectories. These data provide a detailed basis for the subsequent infection probability prediction, and can support the pathogen diffusion prediction and infection probability calculation in complex scenarios. Through this series of steps, a comprehensive and accurate pathogen diffusion distribution database is established, which provides solid data support for the prevention and control of the epidemic in the train passenger compartment.

[0147] In another specific embodiment, Figure 7 A schematic diagram of a method for obtaining a pathogen diffusion distribution database through a neural network provided in an embodiment of the present application. Figure 7 As shown, the acquisition of the pathogen diffusion distribution database also includes:

[0148] S71, according to at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, according to at least one of the passenger capacity and population distribution density of the train passenger compartment, and according to at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released per unit time by the infected person, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei, using a trained neural network model to obtain the spatiotemporal trajectory of the droplet nuclei;

[0149] S72, record and store the spatiotemporal trajectory of each droplet nucleus, and store the environmental condition information, personnel distribution information and pathogen diffusion source information corresponding to the spatiotemporal trajectory into a pathogen diffusion distribution database.

[0150] In this embodiment, a trained neural network model is used to obtain the diffusion distribution data of pathogens based on various parameters collected. The neural network model has the ability to make high-precision predictions in complex environments by learning a large amount of historical data and simulation results. It can process multi-dimensional input data, identify the complex relationship between environmental conditions, personnel distribution, and pathogen characteristics, and thus provide pathogen diffusion predictions. These prediction data reflect the concentration distribution of pathogens at different times and different spatial positions in the passenger room. After obtaining the pathogen diffusion distribution data, the next step is to record and store the spatiotemporal trajectory of each droplet nucleus. These trajectories describe in detail the movement path of the droplet nucleus in the passenger room over time, including its concentration change and diffusion range at different positions. At the same time, it is also necessary to store the environmental condition information, personnel distribution information, and pathogen diffusion source information corresponding to these spatiotemporal trajectories in the pathogen diffusion distribution database. This database not only records the dynamic changes of the droplet nucleus, but also combines various factors that affect these changes, so that subsequent analysis and prediction are more accurate. The various data collected have been described in detail in the above embodiments, and will not be repeated here.

[0151] Figure 8 This is a schematic diagram of the structure of the infection prediction device provided in the embodiment of the present application. As shown in the figure, the prediction device 80 includes:

[0152] Information acquisition module 81, used to obtain the current train passenger compartment environment information, personnel distribution information and pathogen diffusion source information;

[0153] The distribution data acquisition module 82 is used to acquire the pathogen diffusion distribution data through the pathogen diffusion distribution database or the trained neural network model according to the environmental information, the personnel distribution information and the pathogen diffusion source information;

[0154] The pathogen quantity calculation module 83 is used to obtain the average pathogen quantity corresponding to the exposure time in the predicted area based on the preset area division of the current train passenger compartment and the pathogen diffusion source information and pathogen diffusion distribution data; wherein the exposure time is the time that the predicted person stays in the predicted area;

[0155] Infection probability calculation module 84: used to calculate and obtain the infection probability of the person to be predicted in the area to be predicted based on the area to be predicted, according to the average amount of pathogens, the behavioral status information of the person to be predicted and the exposure time of the person to be predicted, using the optimized infection probability calculation model; wherein the optimized infection probability calculation model is based on the infection probability model, and uses the non-uniform diffusion of pathogens in the passenger compartment of the current train to optimize the infection probability calculation model.

[0156] The prediction device provided in this embodiment can execute the prediction method of the above-mentioned embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0157] Fig. 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device 90 includes: at least one processor 91 and a memory 92. The electronic device 9 also includes a communication component 93. The processor 91, the memory 92 and the communication component 93 are connected via a bus 94.

[0158] In a specific implementation process, at least one processor 91 executes the computer-executable instructions stored in the memory 92, so that at least one processor 91 executes the prediction method executed by the electronic device side as above.

[0159] The specific implementation process of the processor 91 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0160] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0161] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0162] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0163] The above-mentioned functions implemented by the electronic device and the main control device introduce the scheme provided by the embodiment of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes a hardware structure and / or software module corresponding to the execution of each function. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the embodiment of the present invention, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present invention.

[0164] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above prediction method is implemented.

[0165] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0166] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0167] The present application also provides a computer program product, which includes: a computer program, which is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0168] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0169] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0170] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0171] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0172] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0173] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0174] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes 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 various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0175] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0176] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0177] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for predicting infection in a train passenger compartment, characterized in that: include: Obtain the current train passenger compartment environmental information, personnel distribution information and pathogen spread source information; According to the environmental information, personnel distribution information and pathogen diffusion source information, pathogen diffusion distribution data is obtained through a pathogen diffusion distribution database or a trained neural network model; Based on the preset area division of the passenger compartment of the current train, according to the pathogen diffusion source information and the pathogen diffusion distribution data, the average amount of pathogens in the area to be predicted corresponding to the exposure time is obtained; wherein the exposure time is the time that the person to be predicted stays in the prediction area; Based on the area to be predicted, according to the average amount of pathogens, the behavioral status information of the person to be predicted and the exposure time of the person to be predicted, an optimized infection probability calculation model is used to calculate and obtain the infection probability of the person to be predicted in the area to be predicted; Among them, the optimized infection probability calculation model is based on the infection probability model, and the infection probability calculation model is optimized by using the non-uniform diffusion of pathogens in the passenger compartment of the current train.

2. The method according to claim 1, characterized in that: The pathogen diffusion distribution data includes the spatiotemporal trajectory of the droplet nuclei; Then, based on the preset area division of the current train passenger compartment, according to the pathogen diffusion source information and the pathogen diffusion distribution data, obtaining the average amount of pathogens corresponding to the exposure time in the area to be predicted includes: According to the pathogen diffusion source information, query and obtain the pathogen quantum generation rate matching the pathogen type, and obtain the number of droplets released per unit time by the infected person; Calculate the amount of pathogens contained in one droplet nucleus according to the number of droplets released by the infected person per unit time and the quantum generation rate of the pathogen; Determine the area to be predicted where the person to be predicted is located, and obtain the average number of the droplet nuclei corresponding to the exposure time in the area to be predicted according to the spatiotemporal trajectory of the droplet nuclei; The average amount of pathogens is obtained based on the amount of pathogens contained in one droplet nucleus and the average number of the droplet nuclei.

3. The method according to any one of claims 1 or 2, characterized in that: The method of calculating and obtaining the infection probability of the person to be predicted in the area to be predicted based on the area to be predicted, according to the average amount of pathogens, the behavior status information of the person to be predicted, and the exposure time of the person to be predicted, using an optimized infection probability calculation model, comprises: According to the behavior state information of the person to be predicted, obtaining the average respiratory rate of the person to be predicted; According to the average respiratory rate, the average pathogen amount and the exposure time, an optimized infection probability calculation model is used: Calculate and obtain the infection probability P of the person to be predicted in the area to be predicted; in, is the average amount of pathogens, p is the average respiratory rate, T is the exposure time, and V is the volume of the area to be predicted.

4. The method according to claim 1, characterized in that: The environmental information includes at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment; The personnel distribution information includes at least one of the current passenger capacity and personnel distribution density of the train passenger compartment; The pathogen diffusion source information includes at least one of the pathogen type, the location information of the infected person, the number of infected people, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nucleus; According to the environmental information, personnel distribution information and pathogen diffusion source information, pathogen diffusion distribution data is obtained through a pathogen diffusion distribution database or a trained neural network model, including: According to at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, according to at least one of the current passenger capacity and population distribution density of the train passenger compartment, and according to at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released per unit time by the infected person, the particle size of the droplet nuclei and the initial speed of the droplet nuclei, query and obtain the pathogen diffusion distribution data through the pathogen diffusion distribution database; or, The pathogen diffusion distribution data is acquired using the trained neural network model based on the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, based on at least one of the current passenger capacity and population density of the train passenger compartment, and based on at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei.

5. The method according to claim 4, characterized in that The acquisition of the pathogen diffusion distribution database includes: According to the passenger compartment layout and the geometric structure of the passenger compartment of the train, a geometric calculation model matching the train is established, and the geometric calculation model is mesh discretized to obtain a mesh discretized model of the train; Based on the grid discrete model, according to the air supply mode, ambient temperature and ambient humidity of the passenger compartment of the train, by setting the boundary conditions of the discrete model, a steady-state flow field model of the train is obtained; Based on the steady-state flow field model, by setting the passenger capacity and personnel distribution density of the train passenger compartment, and by setting the location information of the infected person, the number of infected persons, the number of droplet nuclei released by the infected person per unit time, the droplet nucleus particle size and the initial velocity of the droplet nuclei, a discrete phase mode is adopted to simulate the propagation path of the droplet nuclei released by the infected person in the train passenger compartment to obtain the spatiotemporal trajectory of the droplet nuclei; The spatiotemporal trajectory of each droplet nucleus is recorded and stored, and the environmental information, personnel distribution information and pathogen diffusion source information corresponding to the spatiotemporal trajectory are stored to obtain a pathogen diffusion distribution database.

6. The method according to claim 4, characterized in that The acquisition of the pathogen diffusion distribution database also includes: According to at least one of the air supply mode, ambient temperature and ambient humidity of the train passenger compartment, according to at least one of the passenger capacity and population distribution density of the train passenger compartment, and according to at least one of the pathogen type, location information of the infected person, the number of infected persons, the number of droplet nuclei released per unit time by the infected person, the particle size of the droplet nuclei and the initial velocity of the droplet nuclei, a trained neural network model is used to obtain the spatiotemporal trajectory of the droplet nuclei; The spatiotemporal trajectory of each droplet nucleus is recorded and stored, and the environmental condition information, personnel distribution information and pathogen diffusion source information corresponding to the spatiotemporal trajectory are stored in the pathogen diffusion distribution database.

7. The method according to claim 2, characterized in that The step of determining the area to be predicted where the person to be predicted is located, and obtaining the average number of the droplet nuclei corresponding to the exposure time in the area to be predicted according to the spatiotemporal trajectory of the droplet nuclei, comprises: The position coordinates of the person to be predicted are obtained through a monitoring system or a sensor pre-installed in the passenger compartment of the train, and the position coordinates are matched with the preset area according to the preset area division of the passenger compartment of the current train to determine the area to be predicted where the person to be predicted is located; According to the spatiotemporal trajectory of the droplet nuclei, obtaining a quantity change curve of the droplet nuclei corresponding to the exposure time in the area to be predicted; According to the droplet nucleus quantity change curve, the total quantity of the droplet nuclei is obtained by using the integration method, and according to the exposure time, the average quantity of the droplet nuclei is calculated.

8. The method according to claim 3, characterized in that Obtaining the average respiratory rate of the person to be predicted, including: Acquiring the basic respiratory rate of the person to be predicted, and determining the speaking frequency and coughing frequency of the person to be predicted according to the exposure time; The average respiratory rate of the person to be predicted is calculated and obtained by weighted averaging according to the basic respiratory rate, the speaking frequency and the coughing frequency.

9. An infection prediction device, characterized in that: include: An information acquisition module is used to obtain the current train passenger compartment environmental information, personnel distribution information and pathogen diffusion source information; A distribution data acquisition module, used to acquire pathogen diffusion distribution data through a pathogen diffusion distribution database or a trained neural network model according to the environmental information, personnel distribution information and pathogen diffusion source information; A pathogen quantity calculation module is used to obtain an average pathogen quantity corresponding to the exposure time in the area to be predicted based on the preset area division of the passenger compartment of the current train, according to the pathogen diffusion source information and the pathogen diffusion distribution data; wherein the exposure time is the time that the person to be predicted stays in the prediction area; Infection probability calculation module: used to calculate and obtain the infection probability of the person to be predicted in the area to be predicted based on the area to be predicted, according to the average amount of pathogens, the behavioral status information of the person to be predicted and the exposure time of the person to be predicted, using the optimized infection probability calculation model; wherein the optimized infection probability calculation model is based on the infection probability model, and the infection probability calculation model is optimized by using the non-uniform diffusion of pathogens in the passenger compartment of the current train.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

Images