Prediction Method, Device, Electronic Device and Computer Readable Medium of Data

Abstract

The present disclosure relates to a method, apparatus, electronic device, and computer-readable medium for predicting infectious disease transmission data, belonging to the field of artificial intelligence technology. The method includes: constructing an underlying individual contact model based on social population data and a plurality of preset contact scenarios; obtaining an individual transmission model and a commuting network transmission model, and setting relevant infectious disease transmission parameters and infectious disease intervention parameters; determining the state transition probability of an individual in each preset time period according to the state transition result of the individual in the underlying individual contact model in the commuting network transmission model, and based on the individual transmission model, the infectious disease transmission parameters, and the infectious disease intervention parameters; and obtaining a predicted value of the infectious disease transmission data according to the state transition probability of the individual in each preset time period. By performing microscopic-level modeling and simulation on the infectious disease transmission process, the present disclosure can more scientifically understand the infectious disease transmission law and improve the accuracy of predicting infectious disease transmission data.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more particularly, to a method for predicting infectious disease transmission data, a device for predicting infectious disease transmission data, an electronic device, and a computer-readable medium. Background Art

[0002] Simulation and modeling refer to a system model established by digitizing the physical laws abstracted from things in the real world, which can describe or simulate the structure or behavior of the thing, and is used for virtual testing and early verification of the real world, thereby reducing the cost of direct testing. By combining scientific research literature and actual data, simulation and modeling technologies are playing an increasingly important role in the field of epidemiology.

[0003] Currently, most of the simulation and modeling of the spread of infectious diseases use the method of infectious disease dynamics, and a set of difference equations are used to model infectious diseases. However, due to the overly macroscopic model of infectious disease dynamics, the method of replacing the sum of individual effects with the average effect simplifies the real scenario. In the real scenario depicted at a coarse granularity, it is difficult to reflect the heterogeneity in the population, nor can it closely simulate and analyze specific intervention actions, resulting in a poor prediction effect of the model.

[0004] In view of this, there is an urgent need in the art for a method that can improve the prediction effect of the model.

[0005] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present disclosure is to provide a method for predicting infectious disease transmission data, a device for predicting infectious disease transmission data, an electronic device, and a computer-readable medium, thereby at least to a certain extent improving the accuracy of model prediction.

[0007] According to a first aspect of the present disclosure, there is provided a method for predicting infectious disease transmission data, including:

[0008] Obtaining social population data, and constructing a bottom-layer individual contact model according to the social population data and a plurality of preset contact scenarios;

[0009] Obtaining the individual transmission model and the commuting network transmission model of the infectious disease, and setting relevant infectious disease transmission parameters and infectious disease intervention parameters;

[0010] Based on the state transition results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, the infectious disease transmission parameters, and the infectious disease intervention parameters, determine the state transition probabilities of individuals in each propagation state within each preset time period;

[0011] Based on the state transition probabilities of the individuals within each preset time period, obtain the predicted values of the infectious disease transmission data for each preset time period.

[0012] In an exemplary embodiment of the present disclosure, the constructing the underlying individual contact model according to the social demographic data and multiple preset contact scenarios includes:

[0013] Divide all individuals in the underlying individual contact model into different levels of social contact units according to the social demographic data, and determine the social types of the individuals;

[0014] Divide each preset time period into a first contact time period and a second contact time period;

[0015] Determine the preset contact scenarios of the individuals during the first contact time period according to the social types of the individuals, where the preset contact scenarios include community scenarios, school scenarios, and work scenarios;

[0016] Construct the contact networks of the individuals in each preset contact scenario during the first contact time period, and the contact network of the individuals in the community scenario during the second contact time period, and obtain the underlying individual contact model based on each contact network.

[0017] In an exemplary embodiment of the present disclosure, the determining the state transition probabilities of individuals in each propagation state within each preset time period based on the state transition results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, the infectious disease transmission parameters, and the infectious disease intervention parameters, includes:

[0018] Obtain the propagation states of the individuals at the current prediction time point, where the propagation states include susceptible state, exposed state, infected state, confirmed state, and recovered state;

[0019] If the individuals at the current prediction time point include individuals in the exposed state, then determine the first commuting state transition results of the individuals according to the commuting network propagation model;

[0020] Determine the type of intervention action according to the infectious disease intervention parameters, and determine the target contact scenario of the individuals during the first contact time period according to the type of intervention action and the social types of the individuals;

[0021] Determine a first state transition probability of the individual within the first contact time period according to the first commuting state transition result, the infectious disease intervention parameter, and the infectious disease transmission parameter in the target contact scenario;

[0022] Determine an intermediate prediction time point according to the current prediction time point and the first contact time period, and determine the transmission state of the individual at the intermediate prediction time point according to the first state transition probability;

[0023] If the individuals at the intermediate prediction time point include individuals in the exposed state, determine a second commuting state transition result of the individual according to the commuting network transmission model;

[0024] Determine a second state transition probability of the individual within the second contact time period according to the second commuting state transition result, the infectious disease transmission parameter in the community scenario, and the infectious disease intervention parameter.

[0025] In an exemplary embodiment of the present disclosure, the determining the first commuting state transition result of the individual according to the commuting network transmission model includes:

[0026] Obtain commuting network nodes according to the transmission state of the individual, where the commuting network nodes include susceptible state nodes, exposed state nodes, and infected state nodes;

[0027] Generate an infection parameter through the infected state node, and assign the infection parameter to the susceptible state node adjacent to the infected state node;

[0028] If the infection parameter is less than the infection parameter threshold, convert the susceptible state node to the exposed state node, and put the exposed state node into the current exposed set;

[0029] Time the exposed state nodes in the current exposed set. If the duration of the exposed state node is greater than or equal to the latency time threshold, convert the exposed state node to the infected state node;

[0030] Obtain the first commuting state transition result of the individual according to the conversion result of the commuting network nodes.

[0031] In an exemplary embodiment of the present disclosure, the determining the first state transition probability of the individual within the first contact time period according to the first commuting state transition result, the infectious disease intervention parameter, and the infectious disease transmission parameter in the target contact scenario includes:

[0032] Update the transmission status of the individual according to the first commuting status transition result of the individual;

[0033] Determine the first state transition probability of an individual in the susceptible state within the first contact time period according to the infectious disease intervention parameter and the infectious disease transmission parameter in the target contact scenario;

[0034] According to the infectious disease transmission parameter and the first state transition probability of an individual in the susceptible state, sequentially determine the first state transition probabilities of individuals in the exposed state, the infected state, the diagnosed state, and the recovered state within the first contact time period.

[0035] In an exemplary embodiment of the present disclosure, the determining the first state transition probability of an individual in the susceptible state within the first contact time period according to the infectious disease intervention parameter and the infectious disease transmission parameter in the target contact scenario includes:

[0036] Obtain the vaccine efficiency parameter and the individual protection parameter of an individual in the susceptible state according to the infectious disease intervention parameter;

[0037] Determine the individual contact weight in the target contact scenario according to the infectious disease transmission parameter in the target contact scenario and the individual protection parameter;

[0038] Determine the infection probability of an individual in the infected state and the infection probability of an individual in the susceptible state according to the vaccine efficiency parameter;

[0039] Obtain the first state transition probability of an individual in the susceptible state within the first contact time period according to the individual contact weight in the target contact scenario, the infection probability of an individual in the infected state, and the infection probability of an individual in the susceptible state.

[0040] In an exemplary embodiment of the present disclosure, the determining the individual contact weight in the target contact scenario according to the infectious disease transmission parameter in the target contact scenario and the individual protection parameter includes:

[0041] Obtain the contact probability of the individual with an individual in the infected state in the target contact scenario according to the social type of the individual;

[0042] Determine the individual contact weight in the target contact scenario according to the infectious disease transmission parameter in the target contact scenario, the individual protection parameter, and the contact probability.

[0043] In an exemplary embodiment of the present disclosure, obtaining the predicted value of the infectious disease transmission data for each of the preset time periods according to the state transition probability of the individual in each of the preset time periods includes:

[0044] Obtaining the change value of the number of individuals in each transmission state according to the state transition probability of the individual in each of the preset time periods;

[0045] Obtaining the predicted value of the infectious disease transmission data for each of the preset time periods according to the change value of the number of individuals in each transmission state.

[0046] According to a second aspect of the present disclosure, there is provided a prediction device for infectious disease transmission data, including:

[0047] A bottom - layer model construction module, configured to obtain social population data and construct a bottom - layer individual contact model according to the social population data and a plurality of preset contact scenarios;

[0048] A transmission model acquisition module, configured to obtain the individual transmission model and the commuting network transmission model of the infectious disease, and set relevant infectious disease transmission parameters and infectious disease intervention parameters;

[0049] A transfer probability determination module, configured to determine the state transition probability of individuals in each transmission state in each preset time period according to the state transition result of the individuals in the bottom - layer individual contact model in the commuting network transmission model, and based on the individual transmission model, the infectious disease transmission parameters, and the infectious disease intervention parameters;

[0050] A transmission data prediction module, configured to obtain the predicted value of the infectious disease transmission data for each of the preset time periods according to the state transition probability of the individual in each of the preset time periods.

[0051] According to a third aspect of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the prediction method of the infectious disease transmission data described in any one of the above by executing the executable instructions.

[0052] According to a fourth aspect of the present disclosure, there is provided a computer - readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the prediction method of the infectious disease transmission data described in any one of the above is implemented.

[0053] The exemplary embodiments of the present disclosure may have the following beneficial effects:

[0054] In the method for predicting infectious disease transmission data according to the exemplary embodiments of the present disclosure, by constructing an underlying individual contact model based on social demographic data, and based on the individual transmission model, the commuting network transmission model, as well as relevant infectious disease transmission parameters and infectious disease intervention parameters, the state transition probability of individuals in each transmission state in the underlying individual contact model within each preset time period is determined, so as to obtain the predicted value of infectious disease transmission data within each preset time period. On the one hand, the method for predicting infectious disease transmission data according to the exemplary embodiments of the present disclosure, by being based on an individual model at the micro level, realizes the tracking and analysis of the infection situation of each individual, and conducts micro-level modeling and simulation on the transmission process of infectious diseases in a large-scale population, can more scientifically understand the laws of infectious disease transmission, and improve the accuracy of predicting infectious disease transmission data; on the other hand, by constructing a random graph network as the basic network for staff commuting and embedding it into the simulation model, a more comprehensive infectious disease simulation scenario can be formed; on the one hand, by combining relevant intervention actions for modeling, the infectious disease control effects of various intervention actions can be analyzed at the micro level, and by combining with actual infectious disease data, the ongoing infectious diseases can be digitized, so as to test the effectiveness of various infectious disease intervention actions, and further guide the implementation of relevant intervention actions, achieving the purpose of providing decision-making suggestions and effect simulation for the control of infectious diseases.

[0055] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0057] Figure 1 Shows a schematic flow chart of the method for predicting infectious disease transmission data according to the exemplary embodiments of the present disclosure;

[0058] Figure 2 Shows a schematic flow chart of constructing an underlying individual contact model according to the exemplary embodiments of the present disclosure;

[0059] Figure 3 Shows a schematic diagram of an underlying individual contact model according to a specific embodiment of the present disclosure;

[0060] Figure 4 Shows a schematic diagram of an infectious disease transmission dynamics model according to a specific embodiment of the present disclosure;

[0061] Figure 5 Shows a schematic flow chart for determining the state transition probability of an individual in each preset time period under each propagation state in an exemplary embodiment of the present disclosure;

[0062] Figure 6 Shows a schematic flow chart for determining the first commuting state transition result of an individual in an exemplary embodiment of the present disclosure;

[0063] Figure 7 Shows a schematic flow chart for determining the first state transition probability of an individual under each propagation state in an exemplary embodiment of the present disclosure;

[0064] Figure 8 Shows a schematic flow chart for determining the first state transition probability of an individual in the susceptible state in an exemplary embodiment of the present disclosure;

[0065] Figure 9 Shows a schematic flow chart of a method for predicting infectious disease transmission data according to a specific embodiment of the present disclosure;

[0066] Figure 10 Shows a specific application scenario of an infectious disease individual simulation model according to a specific embodiment of the present disclosure;

[0067] Figure 11 Shows a block diagram of a prediction device for infectious disease transmission data in an exemplary embodiment of the present disclosure;

[0068] Figure 12 Shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present disclosure. Specific Embodiments

[0069] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0070] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein.

[0071] The following exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of the embodiments of this disclosure. However, those skilled in the art will recognize that one or more of the specific details may be omitted in practicing the technical solutions of this disclosure, or other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring the various aspects of this disclosure.

[0072] In addition, the drawings are only schematic illustrations of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0073] Simulation and modeling refer to a system model established by digitizing the physical laws abstracted from things in the real world, which can describe or simulate the structure or behavior of the thing and is used for virtual testing and early verification of the real world, thereby reducing the cost of direct testing.

[0074] By combining scientific research literature and actual data, simulation and modeling technologies are playing an increasingly important role in the field of epidemics. For example, by modeling a certain infectious disease, its transmission law can be analyzed through simulation; by simulating intervention actions, the possible effects after implementing various measures can be analyzed. Further, by using actual infectious disease data for modeling and calibration, the trend of infectious diseases can also be predicted and judged in advance, reducing the impact of infectious diseases on human production and life.

[0075] In some related embodiments, ABM (Agent-Based Modeling, a microscopic model at the individual level) can be used to represent each individual in the simulation environment using a multi-agent method, thereby microscopically simulating the spread of infectious diseases.

[0076] However, the ABM method can achieve micro-level modeling, but its modeling method limits the scale of the simulation object and the simulation of intervention actions. Since the simulation and implementation of intervention actions such as isolating confirmed patients and their close contacts and recommending wearing masks are not carried out, it is not conducive to comprehensively analyzing the effects of various intervention actions. In addition, in the existing individual simulation models, although a simplified description is made based on the real scenario, they mainly focus on scenarios such as communities, families, and workplaces, and do not carefully depict the interaction activities of individuals during the commuting process, which is also an important scenario and route for the spread of epidemics.

[0077] This exemplary embodiment first provides a method for predicting infectious disease transmission data. Refer to Figure 2 As shown, the method for predicting infectious disease transmission data may include the following steps:

[0078] Step S110. Obtain social population data and construct a bottom-layer individual contact model according to the social population data and multiple preset contact scenarios.

[0079] Step S120. Obtain an individual transmission model of the infectious disease and a commuting network transmission model, and set relevant infectious disease transmission parameters and infectious disease intervention parameters.

[0080] Step S130. Determine the state transition probability of individuals in each preset time period in each transmission state according to the state transition results of individuals in the bottom-layer individual contact model in the commuting network transmission model, and based on the individual transmission model, the infectious disease transmission parameters, and the infectious disease intervention parameters.

[0081] Step S140. Obtain the predicted value of the infectious disease transmission data in each preset time period according to the state transition probability of individuals in each preset time period.

[0082] In the method for predicting infectious disease transmission data according to the exemplary embodiments of the present disclosure, by constructing an underlying individual contact model based on social demographic data, and based on the individual transmission model, the commuting network transmission model, as well as relevant infectious disease transmission parameters and infectious disease intervention parameters, the state transition probability of individuals in each transmission state in the underlying individual contact model within each preset time period is determined, so as to obtain the predicted value of infectious disease transmission data within each preset time period. On the one hand, the method for predicting infectious disease transmission data according to the exemplary embodiments of the present disclosure, by being based on an individual model at the micro level, realizes the tracking and analysis of the infection situation of each individual, and conducts micro-level modeling and simulation on the transmission process of infectious diseases in a large-scale population, and can more scientifically understand the law of infectious disease transmission and improve the accuracy of predicting infectious disease transmission data; on the other hand, by constructing a random graph network as the basic network for staff commuting and embedding it into the simulation model, a more comprehensive infectious disease simulation scenario can be formed; on the third hand, by combining relevant intervention actions for modeling, the infectious disease control effect of each intervention action can be analyzed at the micro level. By combining with actual infectious disease data, the ongoing infectious diseases can be digitized, so as to test the effectiveness of various infectious disease intervention actions, and further guide the implementation of relevant intervention actions, achieving the purpose of providing decision-making suggestions and effect simulation for the control of infectious diseases.

[0083] Next, in conjunction with Figures 2 to 8 the above steps of the exemplary embodiments will be described in more detail.

[0084] In step S110, social demographic data is obtained, and an underlying individual contact model is constructed according to the social demographic data and multiple preset contact scenarios.

[0085] In the exemplary embodiments of the present disclosure, the underlying individual contact model is an individual simulation model at the micro level, which can track and analyze the behavior and state of each individual in the preset contact scenario, and can be used to simulate and depict the activity status of people in the real scenario.

[0086] The social demographic data may include age structure, family size, employment rate, workgroup distribution, school size distribution, commuting data, etc., and can be obtained through census results and population vector data.

[0087] In the exemplary embodiments of the present disclosure, as Figure 2 shown, constructing the underlying individual contact model according to the social demographic data and multiple preset contact scenarios may specifically include the following steps:

[0088] Step S210. Divide all individuals in the underlying individual contact model into different levels of social contact units according to the social demographic data, and determine the social types of the individuals.

[0089] Based on basic sociodemographic data, it can be assumed that there are n individuals in common in the underlying individual contact model. First, the population can be divided into D = 1, …, k groups according to geographical administrative regions, and each region is divided into several communities C d = 1, 2, …, and then each community is split into families of different sizes in a certain proportion, through n dc indicating the number of people in the c-th community.

[0090] In the present exemplary embodiment, the family can be used as the smallest and closest social contact unit, and the distance between individuals is divided according to the level of social contact units, and the contact rate decreases as the social contact unit increases. The social contact units are specifically in ascending order: family, family cluster, community, administrative region, and city.

[0091] The social types of individuals mainly include employed persons, students, unemployed persons, etc. Different social types can determine the main activity places of individuals.

[0092] Step S220. Divide each preset time period into a first contact time period and a second contact time period.

[0093] In the present exemplary embodiment, assuming that the model performs data statistics once a day, the preset time period can be set to one day. For example, from 8 am to 8 am the next day is a complete time period.

[0094] Generally, people's daily social interaction patterns are usually two types: day and night. Therefore, each preset time period can be divided into a first contact time period and a second contact time period. Among them, the first contact time period refers to the daytime period, such as from 8 am to 6 pm, and the second contact time period refers to the nighttime period, such as from 6 pm to 8 am the next day.

[0095] Step S230. Determine the preset contact scenarios of individuals during the first contact time period according to the social types of individuals, where the preset contact scenarios include community scenarios, school scenarios, and work scenarios.

[0096] Since different types of individuals have different main activity places during the first contact time period, that is, during the day, it is necessary to determine the preset contact scenarios of individuals during the first contact time period according to the social types of individuals. Among them, the preset contact scenarios include community scenarios, school scenarios, and work scenarios. For example, if an individual's social type is a student, the preset contact scenario of this individual during the first contact time period is the school scenario.

[0097] Step S240. Construct contact networks for an individual in each preset contact scenario during the first contact time period and in the community scenario during the second contact time period, and obtain an underlying individual contact model based on each contact network.

[0098] As Figure 3 shown is a schematic diagram of an underlying individual contact model according to a specific embodiment of the present disclosure. This model adopts a composite structure of a multi-layer contact network to simulate different types of social activities in real-world scenarios. Each layer simulates a contact scenario. Among them, the three social activity networks of the community scenario, school scenario, and work scenario are relatively independent and calculated synchronously.

[0099] The daily activity patterns of individuals in the model are divided into two types: day and night. During the day, contacts between people occur in the following three scenarios: community scenario, school scenario, and work scenario. For the network layer of the school scenario, most students go to school or participate in game groups. Preschool children usually form game groups or community kindergartens. Each community has mixed groups representing two primary schools, one junior high school, and one senior high school. For the network layer of the work scenario, workplaces are allocated to the working-age labor force according to the employment rate, and work destinations are allocated to each employed person according to the actual commuting data. Workers are assigned to the communities within their destination areas to simulate social contacts during the day, and work groups consisting of approximately 20 people represent their close contacts in the workplace. Unemployed people stay within their home communities and have no contacts in the work scenario during the day, except for contacts with other family members who do not work or go to school. And social contacts at night only occur in the contact network of the community scenario, and everyone can contact their family, family cluster, home community, and others in the home community.

[0100] In the community activity network layer, the nodes in the macro graph represent communities, and each node in the micro graph represents a person. The number of nodes in each family is determined by the actual family size distribution. According to the actual age distribution within the family, the association between age groups and each node is set. Referring to the distribution of the education attainment rate and employment rate by age, each node type determines whether it also participates in activities in the school or work layer. Similar to the family layer, the work layer consists of n w disconnected components, each component representing a workplace. The number of nodes in each workplace follows the actual workplace size distribution. The individuals in each workplace are further divided into several work groups, which are the smallest contact units in the workplace layer. The school layer consists of n s disconnected components, each component representing a school. The number of nodes in each school is allocated according to the school type from the actual school size distribution, including preschool education, primary school, junior high school, senior high school, etc.

[0101] In step S120, obtain the individual transmission model and the commuting network transmission model of the infectious disease, and set the relevant infectious disease transmission parameters and infectious disease intervention parameters.

[0102] In the present exemplary embodiment, the individual transmission model of the infectious disease is a model established based on the infectious disease transmission dynamics, and is used to simulate the transmission and transition of states between individuals.

[0103] As Figure 4 shown is a schematic diagram of the infectious disease transmission dynamics model according to a specific embodiment of the present disclosure. The infectious disease transmission process is represented by a discrete-time susceptible-exposed-infected-ascertained-removed (SEIAR) model with a time step t.

[0104] In the present exemplary embodiment, S i，t , E i，t , I i，t , A i，t , R i，t are defined as a state of individual i at time t being a Bernoulli random variable, S i，t +E i，t +I i，t +A i，t +R i，t =1, and the probability of each state occurring The SEIAR disease dynamics can be described as a discrete Markov process in which the transition probability changes over time.

[0105] In the present exemplary embodiment, the commuting network transmission model is constructed based on a random graph algorithm with an approximate Poisson distribution. Since each exposed case has the opportunity to infect susceptible individuals through social contacts during commuting, a commuting-based network needs to be embedded in the simulation model to form a more comprehensive infectious disease simulation scenario.

[0106] In the present exemplary embodiment, the infectious disease transmission parameters may include viral load, contact probability of different groups, etc. The infectious disease transmission parameters and the infectious disease intervention parameters can be used to calculate the state transition probability during the subsequent individual state transition process. The intervention measures may include the setting of the vaccination background and the design of intervention actions, and the specific contents are as follows:

[0107] (1) Vaccination background setting.

[0108] In the present exemplary embodiment, the consideration of vaccination is added. According to the vaccination situation, preventive measures and reactive measures can be set. The former refers to vaccination before the outbreak of the infectious disease, and the latter refers to vaccination during the outbreak of the infectious disease. When neither of the two vaccination methods is adopted, the model returns to the original situation without vaccination.

[0109] For the characteristics of vaccines, the relevant parameters set in the model can include vaccine numbers (used to distinguish multiple vaccines when they coexist), the effectiveness of vaccines for different groups, the vaccination rates of vaccines among different types of people or whether they can be vaccinated (such as the elderly over 65 years old, minors under 18 years old, pregnant women, etc.), the number of doses of vaccines required, and the vaccination cycle of vaccines, etc.

[0110] For vaccine recipients, corresponding parameters are also set in the model, including the vaccination rate of vaccines among the eligible population, the vaccination priorities of different types of people (such as those in high-risk industries need to be vaccinated first, and people with congenital diseases or pregnant women, etc. do not receive vaccines), the effectiveness of vaccines among different age groups (the default effectiveness is the same), etc.

[0111] Vaccine-related parameters can be completed as model inputs during the simulation initialization process, and some parameters can be changed according to conditions during the simulation.

[0112] (2) Settings and enabling of various intervention actions.

[0113] a. Work suspension

[0114] Work suspension is achieved by setting a certain proportion of people to work from home, that is, a certain proportion of practitioners do not participate in contact activities at the work level during the day, but participate in activities at the community level where they live. The start and end times of working from home can be set.

[0115] b. School suspension

[0116] Two school suspension plans are set. The first is to suspend classes in schools in medium- and high-risk areas, and other schools have normal classes. The second is to suspend classes in all schools in the whole region on the second day after a confirmed case appears. The start time and duration of class suspension can be set.

[0117] c. Community lockdown management

[0118] Community lockdown management is achieved by setting a certain proportion of communities. For communities under lockdown management, the contact probability among community members is reduced. The start and end times of community lockdown management can be set.

[0119] d. Isolation

[0120] Two isolation methods are set, one is home isolation and the other is centralized isolation. In the former, there is a virus transmission pathway among family members, and internal family infections may occur. In the latter, close contacts are isolated in a dedicated isolation facility to receive professional medical services, thus preventing further in-family transmission. By default, the model implements centralized isolation for close contacts (such as family members of infected individuals, colleagues in the same office space, etc.) and home isolation for sub-close contacts. The isolation methods for different types of close contacts can be set before the start of the simulation, or the definitions of close contacts and sub-close contacts can be changed to expand or narrow the population that needs to be isolated. Similarly, the isolation duration is adjustable and defaults to 14 days.

[0121] e. Mask wearing

[0122] Mask wearing is set in the model. It is required to wear masks in public places, that is, places other than residences. After wearing a mask, according to the protection rate of the mask, the virus transmission probability is multiplied by a corresponding factor less than 1, indicating that the virus transmission probability decreases after wearing a mask. The relevant parameters set include: mask wearing rate, mask protection rate, the time to start wearing a mask, and the time to relax mask wearing. For mask wearing, the default setting is effective at all times during the simulation.

[0123] In the embodiment of this example, through the setting of the above intervention actions, it is possible to analyze the spread of infectious diseases after vaccination and provide data analysis for how to achieve the normalization of infectious disease prevention and control in the scenario after the vaccine has been developed. By adding appropriate intervention actions, such as centralized isolation and high-popularity mask wearing, the model can quantitatively evaluate the implementation effects of these intervention actions.

[0124] In step S130, based on the state transition results of individuals in the commuting network propagation model in the underlying individual contact model, and based on the individual propagation model, infectious disease transmission parameters, and infectious disease intervention parameters, determine the state transition probabilities of individuals in each propagation state within each preset time period.

[0125] In the embodiment of this example, by embedding the commuting network propagation model and the individual propagation model into the pre-established underlying individual contact model, it is possible to simulate the state transition of individuals through the social activities of individuals during commuting and in multiple scenarios, and calculate the state transition probabilities of individuals within each preset time period. Among them, the state transition probabilities of individuals can be calculated separately for the first contact time period and the second contact time period to obtain the state transition probabilities for the entire preset time period.

[0126] In the embodiment of this example, such as Figure 5As shown, based on the state transition results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, as well as the infectious disease transmission parameters and infectious disease intervention parameters, determine the state transition probabilities of individuals in each propagation state within each preset time period. Specifically, it may include the following steps:

[0127] Step S510. Obtain the propagation state of individuals at the current prediction time point, where the propagation state includes susceptible state, exposed state, infected state, confirmed state, and recovered state.

[0128] The current prediction time point refers to the time point at the start of the preset time period. In the model, the number of individuals in each propagation state can be initialized at the beginning, and then iterative calculations are performed through the model.

[0129] Step S520. If there are individuals in the exposed state among the individuals at the current prediction time point, determine the first commuting state transition result of the individuals according to the commuting network propagation model.

[0130] In this exemplary embodiment, the commuting network is traversed based on a probabilistic breadth-first algorithm. In each time period, if there are individuals in the exposed state in the commuting operation, the situation of state transition during commuting may occur. If there are no individuals in the exposed state, the calculation process of the commuting state transition result is automatically skipped.

[0131] In this exemplary embodiment, as Figure 6 shown, determining the first commuting state transition result of individuals according to the commuting network propagation model may specifically include the following steps:

[0132] Step S610. Obtain commuting network nodes according to the propagation state of individuals. The commuting network nodes include susceptible state nodes, exposed state nodes, and infected state nodes.

[0133] The commuting network propagation model mainly includes susceptible state nodes, exposed state nodes, and infected state nodes. Among them, the exposed state nodes can be further divided into newly exposed nodes and currently exposed nodes. When initializing the commuting network, a certain fixed number of nodes can be set as currently exposed nodes, and the remaining nodes are susceptible state nodes.

[0134] Step S620. Generate an infection parameter through the infected state node and assign the infection parameter to the susceptible state node adjacent to the infected state node.

[0135] For an infected state node, each infected state node can randomly generate an infection parameter with a value of 0 - 1 and assign it to the edge of the susceptible state node adjacent to the infected state node.

[0136] Step S630. If the infection parameter is less than the infection parameter threshold, convert the susceptible state node to an exposed state node and add the exposed state node to the current exposed set.

[0137] If the randomly generated infection parameter is less than a certain infection parameter threshold, convert this susceptible state node to an exposed state node, remove the node from the susceptible node set, add it to the new exposed set, and then move it to the current exposed set.

[0138] Step S640. Time the exposed state nodes in the current exposed set. If the duration of an exposed state node is greater than or equal to the latency time threshold, convert the exposed state node to an infected state node.

[0139] After an exposed state node enters the current exposed set, start timing it. When the timing time is greater than or equal to the latency time threshold, convert the exposed state node to an infected state node.

[0140] Step S650. Obtain the first commuting state transition result of the individual according to the conversion result of the commuting network node.

[0141] After obtaining the first commuting state transition result of the individual according to the conversion result of the commuting network node, input the states of all individuals into the underlying model to complete the entire propagation chain.

[0142] Step S530. Determine the type of intervention action according to the infectious disease intervention parameter, and determine the target contact scenario of the individual during the first contact period according to the type of intervention action and the social type of the individual.

[0143] For different types of intervention actions, the target contact scenario of the individual during the first contact period may change. For example, for an individual with a social type of student, if the type of intervention action is school closure, their activity place during the day changes from school to the community.

[0144] Step S540. Determine the first state transition probability of the individual during the first contact period according to the first commuting state transition result, as well as the infectious disease intervention parameter and the infectious disease transmission parameter in the target contact scenario.

[0145] In the present exemplary embodiment, as Figure 7 shown, determine the first state transition probability of the individual during the first contact period according to the first commuting state transition result, as well as the infectious disease intervention parameter and the infectious disease transmission parameter in the target contact scenario. Specifically, it may include the following steps:

[0146] Step S710. Update the propagation state of the individual according to the first commuting state transition result of the individual.

[0147] Step S720. Determine the first state transition probability of an individual in a susceptible state within the first contact time period according to the infectious disease intervention parameters and the infectious disease transmission parameters in the target contact scenario.

[0148] For the individual transmission model, it is first necessary to calculate the state transition of an individual in a susceptible state.

[0149] In this exemplary embodiment, as Figure 8 shown, determine the first state transition probability of an individual in a susceptible state within the first contact time period according to the infectious disease intervention parameters and the infectious disease transmission parameters in the target contact scenario, which may specifically include the following steps:

[0150] Step S810. Obtain the vaccine efficiency parameter and the individual protection parameter of an individual in a susceptible state according to the infectious disease intervention parameters.

[0151] Among them, the individual protection parameter may represent the protection rate when an individual wears a mask.

[0152] Step S820. Determine the individual contact weight in the target contact scenario according to the infectious disease transmission parameters and the individual protection parameter in the target contact scenario.

[0153] In this exemplary embodiment, the contact probability of an individual with an infected individual in the target contact scenario can be obtained according to the social type of the individual, and then the individual contact weight in the target contact scenario is determined according to the infectious disease transmission parameters, the individual protection parameter and the contact probability in the target contact scenario.

[0154] Individual contact weight θ l is related to the contact location, the age of the individual, and the intervention actions performed within time t. l ∈ L = c, s, w, where L is the set of layers, and c, s, w represent the community, school, and workplace respectively. The specific calculation method of the individual contact weight is as follows:

[0155] If the contact infection of an individual occurs at the community layer, θ c can be expressed as:

[0156]

[0157] where M i ∈ [0, 1] is the protection rate of an individual wearing a mask, that is, the individual protection parameter. The smaller the protection rate, the more effective it is. and are indicator variables. The former indicates whether individual i contacts individual j at the community layer, and the latter indicates whether the suspension of work and school has an impact on individual i. and are Bernoulli random variables. It is stated that individual i has contact with individual j at the community level. It is stated that school and work suspensions act on individual i, and vice versa. CR represents the community contact reduction rate, γ i represents the age group to which individual i belongs, cpcm[γ i represents the probability that individual i is infected by an infected individual in community contact. Among them, the contact probability is related to age. When individual j at layer l infects individual i at time t, all the stored information will help calculate the reproduction number and the final epidemic scale. ω = 2, representing the causal multiplier, which means that when individual i leaves school (school closure) or works from home, the risk of infection at the community level increases.

[0158] If the contact infection of an individual occurs at the work level, θ w can be expressed as:

[0159]

[0160] Among them, cpw[γ i represents the probability that individual i contacts infected j at the work level.

[0161] If the contact infection of an individual occurs at the school level, θ s can be expressed as:

[0162]

[0163] Among them, cps[γ i represents the probability that individual i contacts infected j at the school level.

[0164] Step S830. Determine the infection probability of an individual in the infected state and the probability of an individual in the susceptible state being infected according to the vaccine efficiency parameter.

[0165] The infection probability pri of an individual in the infected state represents the probability that an individual infects others when being infected, and the probability prs of an individual in the susceptible state being infected represents the probability that the individual is infected by other infected individuals. The expression of prs is as follows:

[0166] i. prs = (1 - i.BVEs) * (1 - VEs * EFF[γi])

[0167] Among them, BVEs represents the baseline vaccine efficiency of susceptible individuals, VEs represents the vaccine efficiency of susceptible individuals, and EFF[γi] represents the vaccine efficiency related to the age group. These three parameters are vaccine efficiency parameters.

[0168] Step S840. According to the individual contact weights in the target contact scenario, as well as the individual infection probabilities in the infected state and the individual probabilities of being infected in the susceptible state, obtain the first state transition probability of an individual in the susceptible state within the first contact time period.

[0169] In this exemplary embodiment, an individual i in the susceptible state (S) can be infected by an individual j in the infected state (I) and enter the exposed state (E), and its probability λ is:

[0170]

[0171] For individual i, the probability of its state transitioning from S→E can be expressed as: λ i =∑ j∈E λ i，j，t .

[0172] Step S730. According to the infectious disease transmission parameters and the first state transition probability of an individual in the susceptible state, sequentially determine the first state transition probabilities of individuals in the exposed state, infected state, confirmed state, and recovered state within the first contact time period.

[0173] After determining the first state transition probability of an individual in the susceptible state, the first state transition probabilities of individuals in the exposed state, infected state, confirmed state, and recovered state within the first contact time period can be sequentially determined through the following infectious disease transmission dynamics formula:

[0174]

[0175] Among them, μ is the probability of the transmission state E→I, and P represents the contact probability. T1 and T2 are the time delays of the transmission states I→A and A→R, respectively.

[0176] Step S550. Determine the intermediate prediction time point according to the current prediction time point and the first contact time period, and determine the transmission state of the individual at the intermediate prediction time point according to the first state transition probability.

[0177] The intermediate prediction time point is the time point at the intersection of the first contact time period and the second contact time period. Through the state transition of individuals within the first contact time period, it is necessary to re-statistics the transmission state of each individual at this time at the intermediate prediction time point.

[0178] Step S560. If the individuals at the intermediate prediction time point include individuals in the exposed state, then determine the second commuting state transition result of the individuals according to the commuting network transmission model.

[0179] For the working population, they need to pass through the commuting network twice a day, which is similar to the actual population activity scenario. Therefore, it is necessary to re-embed the commuting network propagation model at the intermediate prediction time point to simulate the commuting process interaction of individuals. The calculation method of the second commuting state transition result is the same as that of the first commuting state transition result, which will not be elaborated here.

[0180] Step S570. Determine the second state transition probability of the individual during the second contact time period according to the second commuting state transition result, as well as the infectious disease transmission parameters and infectious disease intervention parameters in the community scenario.

[0181] After updating the transmission state of the individual again according to the second commuting state transition result of the individual, then calculate the second state transition probability of the individual during the second contact time period, that is, at night. Among them, it is assumed that the individual only contacts in the community scenario during the second contact time period. The calculation method of the second state transition probability is the same as that of the first state transition probability in the community scenario, which will not be elaborated here.

[0182] In step S140, according to the state transition probability of the individual in each preset time period, obtain the predicted value of the infectious disease transmission data in each preset time period.

[0183] Finally, according to the state transition probability of the individual in each preset time period, obtain the change value of the number of individuals in each transmission state, and then according to the change value of the number of individuals in each transmission state, obtain the predicted value of the infectious disease transmission data in each preset time period. For example, the number of newly added exposed people and the number of infected people per day can be counted, etc.

[0184] Infectious diseases such as Figure 9 As shown is the complete flowchart of the method for predicting infectious disease transmission data in a specific embodiment of the present disclosure, which is an illustration of the above steps in this exemplary embodiment. The specific steps of this flowchart are as follows:

[0185] Step S910. Build the underlying model.

[0186] The content of building the underlying model mainly includes commuting situations, venue distributions, and population structures.

[0187] Among them, the venue distributions mainly include work units, schools, and communities, especially the venue settings in high-risk areas; the population structure is mainly obtained through census results and population vector data. The census results include information such as age structure, family size, employment rate, and the ratio of people engaged in high-risk jobs. The population vector data can be fitted based on administrative region statistical data.

[0188] Step S920. Set and verify the parameters related to infectious diseases.

[0189] The parameters related to infectious diseases mainly include the parameters related to the spread of infectious diseases, viral load, contact probabilities of different groups, etc.

[0190] Among them, the parameters related to the spread of infectious diseases can include the basic reproduction number R0, the effective transmission rate beta, etc., which can be determined according to the historical infection situation in a local area; the viral load refers to the amount of virus in an infected case, which can be set based on existing research; the contact probabilities of different groups can be determined according to information such as age distribution, type of group, and degree of closeness of contact.

[0191] Step S930. Adding the vaccination background.

[0192] The vaccination background can include vaccine-related parameters and vaccination situations.

[0193] Among them, the vaccine-related parameters can include vaccine type, effectiveness, number of doses required, vaccination cycle, etc.; the vaccination situations can include vaccine coverage rate, vaccination priority, and vaccination time, such as before or during an infectious disease outbreak.

[0194] Step S940. Designing and implementing intervention actions.

[0195] The intervention actions can include factory closures, school closures, community lockdowns, quarantines, wearing masks, etc.

[0196] Among them, factory closures can include the proportion of factories closed and the closure time, and the specific parameters can be adjusted according to the actual situation; school closures can include the ways of school closures, such as school closures in medium- and high-risk areas or full-region school closures, etc.; community lockdowns can include the proportion of communities locked down and the lockdown time, and the specific parameters can be adjusted according to the actual situation; quarantines can include two quarantine methods: centralized quarantine and home quarantine; wearing masks can include the proportion of people wearing masks and the wearing time, and the specific parameters can be adjusted according to the actual situation.

[0197] In this exemplary embodiment, by embedding the individual transmission model of infectious diseases into the pre-established underlying individual contact model, an overall individual simulation model of infectious diseases can be obtained. After the construction of the individual simulation model of infectious diseases, the parameters can be fitted and verified by combining the real-world infectious disease data, so as to correct the model and give decision-making suggestions, and obtain an individual simulation model of infectious diseases that can be applied to actual scenarios.

[0198] Such as Figure 10The following shows a specific application scenario of the infectious disease individual simulation model in a specific embodiment of the present disclosure. By inputting the age structure data, household size data, employment data, workplace distribution data, school size distribution data, and commuting data of the target area in the real world into the individual simulation model, state parameters such as the number of newly diagnosed cases per day, the cumulative number of diagnosed cases, the number of vaccinated people, and historical intervention actions in the target area can be obtained. After obtaining the above state parameters, they can be input into the intervention action prediction model to obtain the predicted intervention level, and the current intervention action in the target area can be adjusted based on the predicted intervention level. Among them, the intervention action prediction model can be trained based on the reinforcement learning algorithm.

[0199] In this exemplary embodiment, the specific method for inputting the state parameters into the intervention action prediction model to obtain the predicted intervention level is as follows:

[0200] Encode the state parameters based on the Transformer model in the intervention action prediction model to obtain a first encoded vector; wherein, the dimension of the first encoded vector is the same as the dimension of the first input layer of the intervention action prediction model, and the Transformer model includes a first linear fusion layer, an approximate sparse self-attention layer, a splicing layer, and a second linear fusion layer.

[0201] In this exemplary embodiment, first, the structure of the Transformer model is explained and described. The Transformer model may include an input layer, a first linear fusion layer (Linear), an approximate sparse self-attention layer (ProbSparse Self-Attention), a splicing layer (Contact), a second linear fusion layer (Linear), and an output layer; wherein, the input layer, the first linear fusion layer, the approximate sparse self-attention layer, the splicing layer, the second linear fusion layer, and the output layer are connected in sequence.

[0202] Secondly, the state parameters are encoded based on the Transformer model to obtain the first encoded vector, which specifically includes: First, the first linear fusion layer is used to linearly fuse the number of newly confirmed cases per day, the cumulative number of confirmed cases, the number of vaccinated people, and the historical intervention actions to obtain the current input vector; Secondly, the approximate sparse self-attention layer is used to calculate the current input vector to obtain the first importance degree, the second importance degree, the third importance degree, and the fourth importance degree of the number of newly confirmed cases per day, the cumulative number of confirmed cases, the number of vaccinated people, and the historical intervention actions in the current input vector; Then, the connection layer is used to connect the number of newly confirmed cases per day, the cumulative number of confirmed cases, the number of vaccinated people, and the historical intervention actions and the first importance degree, the second importance degree, the third importance degree, and the fourth importance degree to obtain the first sub-vector, the second sub-vector, the third sub-vector, and the fourth sub-vector; Finally, the second linear fusion layer is used to linearly fuse the first sub-vector, the second sub-vector, the third sub-vector, and the fourth sub-vector to obtain the first encoded vector.

[0203] It should be noted here that since the number of newly confirmed cases per day and the cumulative number of confirmed cases are quite different from the number of vaccinated people; Therefore, in order to facilitate feature extraction and calculation, an approximate sparse self-attention layer is used here, which can improve the accuracy of the first importance degree, the second importance degree, the third importance degree, and the fourth importance degree, and finally achieve the purpose of improving the accuracy of the predicted intervention level; And, the dimension of the first encoded vector is limited to be the same as the dimension of the first input layer of the intervention action prediction model here, in order to enable the model to accurately perform mapping processing according to the first encoded vector when the first encoded vector is input into the intervention action prediction model, and then obtain the corresponding output result.

[0204] Then, the DQN (Deep Q-Network) model in the intervention action prediction model is used to perform mapping processing on the first encoded vector to obtain the output result. Specifically, the DQN model can receive the first encoded vector through a three-layer perceptron network with 64 nodes in each hidden layer, and perform mapping processing on it to obtain the output result. The output result can include 3 nodes, which respectively correspond to the adjustment methods of the intervention actions, specifically keeping the current intervention level unchanged, increasing one level, and decreasing one level. The level with the highest probability in the output result is used as the predicted intervention level.

[0205] In addition, other machine learning models can be used in the intervention action prediction model to replace the Transformer model for encoding processing and replace the DQN model for mapping processing, which is not specifically limited in this exemplary embodiment.

[0206] For example, the output results of the above intervention action prediction model can include three levels, namely, keeping the current intervention action unchanged, increasing the current intervention action by one level, and decreasing the current intervention action by one level. After obtaining the predicted intervention level, the current intervention action in the target area can be adjusted based on this predicted intervention level.

[0207] Specifically, the specific adjustment methods for the current intervention action in the target area can include: decreasing the current intervention action in the target area by one level; or keeping the current intervention action in the target area unchanged; or increasing the current intervention action in the target area by one level.

[0208] Among them, the intervention action can indicate whether to perform at least one of the following action items: case isolation, wearing masks, working from home, closing schools, and community lockdown. In some embodiments, the intervention action can include four levels. The first level is: no case isolation, no need to wear masks, no need to work from home, no need to close schools, and no need for community lockdown; the second level is: there is case isolation, must wear masks, no need to work from home, no need to close schools, and no need for community lockdown; the third level is: there is case isolation, must wear masks, must work from home, must close schools, and no need for community lockdown; the fourth level is: there is case isolation, must wear masks, must work from home, must close schools, and must have community lockdown.

[0209] Based on the above settings of various intervention actions and the enabling settings, four different levels of intervention actions can be set as follows, specifically as shown in Table 1 below:

[0210] Intervention level CI WM WH SC CL 0 × × × × × 1 √ √ × × × 2 √ √ √ √ × 3 √ √ √ √ √

[0211] Among them, in Table 1 above, CI: Case Isolation, case isolation; WM: Wearing Masks, mask wearing; WH: Working from Home, working from home; SC: School Closures, school closures; CL: CommunityLockdown, community lockdown.

[0212] In the specific application scenarios of the above-mentioned individual infectious disease simulation model, by combining the individual infectious disease simulation model with the intervention action prediction model and using deep reinforcement learning technology, it is possible to automatically learn the optimal intervention action solution, improve the accuracy of predicting the intervention level, and solve the problem in the prior art that it is impossible to predict the intervention action by combining the regional state data of a certain region, and thus it is impossible to timely adjust the current intervention action according to the predicted intervention action. In addition, since the current intervention action of the target region can be timely adjusted based on the predicted intervention level, the problem of hindering economic development caused by the overly strict current intervention action can be avoided, and the problem of the aggravation of infectious diseases caused by the overly loose current intervention action can also be avoided. It can not only control infectious diseases but also protect economic development.

[0213] It should be noted that although the steps of the methods in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be executed in that specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0214] Furthermore, the present disclosure also provides a prediction device for infectious disease transmission data. Referring to Figure 11 as shown, the prediction device for infectious disease transmission data may include a bottom layer model construction module 1110, a transmission model acquisition module 1120, a transition probability determination module 1130, and a transmission data prediction module 1140. Among them:

[0215] The bottom layer model construction module 1110 may be configured to obtain social population data and construct a bottom layer individual contact model according to the social population data and multiple preset contact scenarios;

[0216] The transmission model acquisition module 1120 may be configured to obtain an individual transmission model and a commuting network transmission model of an infectious disease, and set relevant infectious disease transmission parameters and infectious disease intervention parameters;

[0217] The transition probability determination module 1130 may be configured to determine the state transition probability of individuals in each preset time period in each transmission state according to the state transition result of individuals in the commuting network transmission model in the bottom layer individual contact model, and based on the individual transmission model, the infectious disease transmission parameters, and the infectious disease intervention parameters;

[0218] The transmission data prediction module 1140 may be configured to obtain the predicted value of the infectious disease transmission data in each preset time period according to the state transition probability of individuals in each preset time period.

[0219] In some exemplary embodiments of the present disclosure, the underlying model construction module 1110 may include a social individual division unit, a contact time period division unit, a contact scenario determination unit, and a contact network construction unit. Among them:

[0220] The social individual division unit may be configured to divide all individuals in the underlying individual contact model into different levels of social contact units according to social demographic data, and determine the social types of the individuals;

[0221] The contact time period division unit may be configured to divide each preset time period into a first contact time period and a second contact time period;

[0222] The contact scenario determination unit may be configured to determine a preset contact scenario of an individual during the first contact time period according to the social type of the individual, where the preset contact scenarios include a community scenario, a school scenario, and a work scenario;

[0223] The contact network construction unit may be configured to construct a contact network of an individual in each preset contact scenario during the first contact time period, and a contact network of the individual in the community scenario during the second contact time period, and obtain the underlying individual contact model based on each contact network.

[0224] In some exemplary embodiments of the present disclosure, the transition probability determination module 1130 may include a propagation state acquisition unit, a first commuting result determination unit, a target contact scenario determination unit, a first transition probability determination unit, an intermediate propagation state determination unit, a second commuting result determination unit, and a second transition probability determination unit. Among them:

[0225] The propagation state acquisition unit may be configured to acquire the propagation state of an individual at the current prediction time point, where the propagation state includes a susceptible state, an exposed state, an infected state, a confirmed state, and a recovered state;

[0226] The first commuting result determination unit may be configured to, if there are individuals in the exposed state among the individuals at the current prediction time point, determine the first commuting state transition result of the individuals according to the commuting network propagation model;

[0227] The target contact scenario determination unit may be configured to determine the type of intervention action according to the infectious disease intervention parameter, and determine the target contact scenario of the individual during the first contact time period according to the type of intervention action and the social type of the individual;

[0228] The first transition probability determination unit may be configured to determine the first state transition probability of an individual during the first contact time period according to the first commuting state transition result, and the infectious disease intervention parameter and the infectious disease transmission parameter in the target contact scenario;

[0229] The intermediate transmission state determination unit can be used to determine an intermediate prediction time point according to the current prediction time point and the first contact time period, and determine the transmission state of an individual at the intermediate prediction time point according to the first state transition probability;

[0230] The second commuting result determination unit can be used to, if the individuals at the intermediate prediction time point include individuals in the exposed state, determine the second commuting state transition result of the individuals according to the commuting network transmission model;

[0231] The second transition probability determination unit can be used to determine the second state transition probability of an individual during the second contact time period according to the second commuting state transition result, as well as the infectious disease transmission parameters and infectious disease intervention parameters in the community scenario.

[0232] In some exemplary embodiments of the present disclosure, the first commuting result determination unit may include a commuting network node determination unit, an infection parameter assignment unit, a susceptible state node conversion unit, an exposed state node conversion unit, and a first commuting state transition result determination unit. Among them:

[0233] The commuting network node determination unit can be used to obtain commuting network nodes according to the transmission state of an individual, and the commuting network nodes include susceptible state nodes, exposed state nodes, and infected state nodes;

[0234] The infection parameter assignment unit can be used to generate infection parameters through the infected state nodes and assign the infection parameters to the susceptible state nodes adjacent to the infected state nodes;

[0235] The susceptible state node conversion unit can be used to, if the infection parameter is less than the infection parameter threshold, convert the susceptible state node into an exposed state node and put the exposed state node into the current exposed set;

[0236] The exposed state node conversion unit can be used to time the exposed state nodes in the current exposed set, and if the duration of the exposed state node is greater than or equal to the latency time threshold, convert the exposed state node into an infected state node;

[0237] The first commuting state transition result determination unit can be used to obtain the first commuting state transition result of an individual according to the conversion result of the commuting network nodes.

[0238] In some exemplary embodiments of the present disclosure, the first transition probability determination unit may include a transmission state update unit, a susceptible state transition probability determination unit, and other state transition probability determination units. Among them:

[0239] The transmission state update unit can be used to update the transmission state of an individual according to the first commuting state transition result of the individual;

[0240] The susceptible state transition probability determination unit can be used to determine the first state transition probability of an individual in the susceptible state within the first contact time period according to the infectious disease intervention parameters and the infectious disease transmission parameters in the target contact scenario;

[0241] The other state transition probability determination units can be used to sequentially determine the first state transition probabilities of individuals in the exposed state, infected state, diagnosed state, and recovered state within the first contact time period according to the infectious disease transmission parameters and the first state transition probability of an individual in the susceptible state.

[0242] In some exemplary embodiments of the present disclosure, the susceptible state transition probability determination unit may include an infectious disease intervention parameter determination unit, an individual contact weight determination unit, an individual infection probability determination unit, and a first state transition probability determination unit. Among them:

[0243] The infectious disease intervention parameter determination unit can be used to obtain the vaccine efficiency parameter and the individual protection parameter of an individual in the susceptible state according to the infectious disease intervention parameters;

[0244] The individual contact weight determination unit can be used to determine the individual contact weight in the target contact scenario according to the infectious disease transmission parameters and the individual protection parameter in the target contact scenario;

[0245] The individual infection probability determination unit can be used to determine the individual infection probability of an individual in the infected state and the probability of an individual in the susceptible state being infected according to the vaccine efficiency parameter;

[0246] The first state transition probability determination unit can be used to obtain the first state transition probability of an individual in the susceptible state within the first contact time period according to the individual contact weight in the target contact scenario, the individual infection probability of an individual in the infected state, and the probability of an individual in the susceptible state being infected.

[0247] In some exemplary embodiments of the present disclosure, the individual contact weight determination unit may include a contact probability determination unit and a contact weight determination unit. Among them:

[0248] The contact probability determination unit can be used to obtain the contact probability of an individual with an individual in the infected state in the target contact scenario according to the social type of the individual;

[0249] The contact weight determination unit can be used to determine the individual contact weight in the target contact scenario according to the infectious disease transmission parameters, the individual protection parameter, and the contact probability in the target contact scenario.

[0250] In some exemplary embodiments of the present disclosure, the transmission data prediction module 1140 may include an individual quantity change value determination unit and a transmission data prediction value determination unit. Among them:

[0251] The individual quantity change value determination unit can be used to obtain the individual quantity change values in each propagation state according to the state transition probability of the individual in each preset time period;

[0252] The predicted value determination unit of the propagation data can be used to obtain the predicted value of the infectious disease propagation data in each preset time period according to the individual quantity change values in each propagation state.

[0253] The specific details of each module / unit in the above-mentioned prediction device of the infectious disease propagation data have been described in detail in the corresponding method embodiment part, and will not be elaborated here.

[0254] Figure 12 The structural schematic diagram of the computer system of the electronic device suitable for implementing the embodiment of the present invention is shown.

[0255] It should be noted that Figure 12 The computer system 1200 of the electronic device shown is only an example, and should not bring any limitations to the functions and usage ranges of the embodiments of the present invention.

[0256] As Figure 12 shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1202 or the program loaded from the storage part 1208 into the random access memory (RAM) 1203. In the RAM 1203, various programs and data required for system operation are also stored. The CPU 1201, ROM 1202, and RAM 1203 are connected to each other through a bus 1204. The input / output (I / O) interface 1205 is also connected to the bus 1204.

[0257] The following components are connected to the I / O interface 1205: an input part 1206 including a keyboard, a mouse, etc.; an output part 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part 1208 including a hard disk, etc.; and a communication part 1209 including a network interface card such as a LAN card, a modem, etc. The communication part 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as required. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as required, so that the computer program read from it can be installed into the storage part 1208 as required.

[0258] In particular, according to an embodiment of the present invention, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 1209 and / or installed from the removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, various functions defined in the system of the present application are performed.

[0259] It should be noted that the computer-readable medium shown in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0260] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as combinations of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0261] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device is caused to implement the method as described in the above embodiments.

[0262] It should be noted that although several modules of devices for performing actions are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more of the above-mentioned modules may be embodied in one module. Conversely, the features and functions of one module described above may be further divided and embodied by multiple modules.

[0263] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed by the present disclosure.

[0264] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for predicting infectious disease transmission data, characterized in that, it includes: Obtain social population data, and construct a basic individual contact model according to the social population data and multiple preset contact scenarios. The basic individual contact model is a microscopic individual simulation model used to track and analyze the behavior and status of each individual in the preset contact scenarios. The basic individual contact model adopts a composite structure of multi-layer contact networks to simulate different types of social activities in the real scenario. Each layer of the contact network simulates a preset contact scenario. Among them, the preset contact scenarios include community scenarios, school scenarios, and work scenarios. The social activity networks of each preset contact scenario are relatively independent and calculated synchronously; Obtain the individual transmission model and commuting network transmission model of the infectious disease, and set relevant infectious disease transmission parameters and infectious disease intervention parameters. Among them, the individual transmission model of the infectious disease is a model established based on the dynamics of infectious disease transmission, used to simulate the transmission and transfer of states between individuals. The transmission states of the individuals include susceptible state, exposed state, infected state, confirmed state, and recovered state. The commuting network transmission model is constructed based on the random graph algorithm of approximate Poisson distribution. The commuting network nodes in the commuting network transmission model include susceptible state nodes, exposed state nodes, and infected state nodes; Based on the state transition results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, the infectious disease transmission parameters, and the infectious disease intervention parameters, determine the state transition probabilities of individuals in each propagation state within each preset time period. Among them, the state transition results of individuals in the commuting network propagation model are obtained according to the conversion results of commuting network nodes. The preset time period includes a first contact time period and a second contact time period. The method of determining the state transition probabilities of individuals in each propagation state within each preset time period based on the state transition results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, the infectious disease transmission parameters, and the infectious disease intervention parameters, includes: obtaining the propagation state of the individual at the current prediction time point; if the individuals at the current prediction time point include individuals in the exposed state, then determining the first commuting state transition result of the individual according to the commuting network propagation model; determining the type of intervention action according to the infectious disease intervention parameters, and determining the target contact scenario in which the individual is located during the first contact time period according to the type of intervention action and the social type of the individual; updating the propagation state of the individual according to the first commuting state transition result of the individual; obtaining the vaccine efficiency parameter and the individual protection parameter of the susceptible state individuals according to the infectious disease intervention parameters; determining the individual contact weight in the target contact scenario according to the infectious disease transmission parameters and the individual protection parameter in the target contact scenario; determining the infection probability of individuals in the infected state and the infection probability of susceptible state individuals according to the vaccine efficiency parameter; obtaining the first state transition probability of susceptible state individuals during the first contact time period according to the individual contact weight in the target contact scenario, the infection probability of individuals in the infected state, and the infection probability of susceptible state individuals; successively determining the first state transition probabilities of individuals in the exposed state, the infected state, the confirmed state, and the recovered state during the first contact time period according to the infectious disease transmission parameters and the first state transition probability of susceptible state individuals; determining an intermediate prediction time point according to the current prediction time point and the first contact time period, and determining the propagation state of the individual at the intermediate prediction time point according to the first state transition probability; if the individuals at the intermediate prediction time point include individuals in the exposed state, then determining the second commuting state transition result of the individual according to the commuting network propagation model; determining the second state transition probability of the individual during the second contact time period according to the second commuting state transition result, the infectious disease transmission parameters in the community scenario, and the infectious disease intervention parameters. Based on the state transition probabilities of the individuals within each preset time period, obtain the predicted values of the infectious disease transmission data for each preset time period.

2. The prediction method of infectious disease transmission data according to claim 1, wherein, the construction of the underlying individual contact model according to the social demographic data and multiple preset contact scenarios includes: dividing all individuals in the underlying individual contact model into different levels of social contact units according to the social demographic data, and determining the social types of the individuals; dividing each of the preset time periods into a first contact time period and a second contact time period; determining the preset contact scenarios of the individuals during the first contact time period according to the social types of the individuals; constructing the contact networks of the individuals in each of the preset contact scenarios during the first contact time period, and the contact networks of the individuals in the community scenarios during the second contact time period, and obtaining the underlying individual contact model based on each of the contact networks.

3. The prediction method of infectious disease transmission data according to claim 1, wherein, the determination of the first commuting state transition result of the individual according to the commuting network transmission model includes: obtaining commuting network nodes according to the transmission state of the individual, and the commuting network nodes include susceptible state nodes, exposed state nodes and infected state nodes; generating an infection parameter through the infected state node, and assigning the infection parameter to the susceptible state node adjacent to the infected state node; if the infection parameter is less than the infection parameter threshold, converting the susceptible state node into the exposed state node, and putting the exposed state node into the current exposed set; timing the exposed state nodes in the current exposed set, and if the duration of the exposed state node is greater than or equal to the latency time threshold, converting the exposed state node into the infected state node; obtaining the first commuting state transition result of the individual according to the conversion result of the commuting network nodes.

4. The prediction method of infectious disease transmission data according to claim 1, wherein, the determination of the individual contact weight in the target contact scenario according to the infectious disease transmission parameter and the individual protection parameter in the target contact scenario includes: obtaining the contact probability of the individual with the individual in the infected state in the target contact scenario according to the social type of the individual; determining the individual contact weight in the target contact scenario according to the infectious disease transmission parameter, the individual protection parameter and the contact probability in the target contact scenario.

5. The prediction method of infectious disease transmission data according to claim 1, wherein, the obtaining of the predicted value of the infectious disease transmission data in each preset time period according to the state transition probability of the individual in each preset time period includes: obtaining the change value of the number of individuals in each transmission state according to the state transition probability of the individual in each preset time period; obtaining the predicted value of the infectious disease transmission data in each preset time period according to the change value of the number of individuals in each transmission state.

6. A prediction device for infectious disease transmission data, wherein, it includes: The underlying model construction module is used to obtain social population data and construct an underlying individual contact model according to the social population data and multiple preset contact scenarios. The underlying individual contact model is a microscopic-level individual simulation model used to track and analyze the behaviors and states of each individual in the preset contact scenarios. The underlying individual contact model adopts a composite structure of multi-layer contact networks to simulate different types of social activities in real scenarios. Each layer of the contact network simulates a preset contact scenario. Among them, the preset contact scenarios include community scenarios, school scenarios, and work scenarios. The social activity networks of each preset contact scenario are relatively independent and calculated synchronously; The transmission model acquisition module is used to obtain the individual transmission model of the infectious disease and the commuting network transmission model, and set relevant infectious disease transmission parameters and infectious disease intervention parameters. Among them, the individual transmission model of the infectious disease is a model established based on the infectious disease transmission dynamics, used to simulate the transmission and transfer of states between individuals. The transmission states of the individuals include susceptible state, exposed state, infected state, confirmed state, and recovered state. The commuting network transmission model is constructed based on the random graph algorithm of approximate Poisson distribution. The commuting network nodes in the commuting network transmission model include susceptible state nodes, exposed state nodes, and infected state nodes; A transfer probability determination module, which is used to determine the state transfer probabilities of individuals in each propagation state within each preset time period according to the state transfer results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, the infectious disease propagation parameters, and the infectious disease intervention parameters. The state transfer results of individuals in the commuting network propagation model are obtained according to the conversion results of commuting network nodes. The preset time period includes a first contact time period and a second contact time period. The determination of the state transfer probabilities of individuals in each propagation state within each preset time period according to the state transfer results of individuals in the underlying individual contact model in the commuting network propagation model, and based on the individual propagation model, the infectious disease propagation parameters, and the infectious disease intervention parameters, includes: obtaining the propagation state of the individual at the current prediction time point; if the individuals at the current prediction time point include individuals in the exposed state, determining the first commuting state transfer result of the individual according to the commuting network propagation model; determining the type of intervention action according to the infectious disease intervention parameters, and determining the target contact scenario in which the individual is located during the first contact time period according to the type of intervention action and the social type of the individual; updating the propagation state of the individual according to the first commuting state transfer result of the individual; obtaining the vaccine efficiency parameter and the individual protection parameter of the susceptible state individuals according to the infectious disease intervention parameters; determining the individual contact weight in the target contact scenario according to the infectious disease propagation parameters and the individual protection parameter in the target contact scenario; determining the infection probability of the infected state individuals and the probability of the susceptible state individuals being infected according to the vaccine efficiency parameter; obtaining the first state transfer probability of the susceptible state individuals during the first contact time period according to the individual contact weight in the target contact scenario, the infection probability of the infected state individuals, and the probability of the susceptible state individuals being infected; successively determining the first state transfer probabilities of the exposed state, the infected state, the confirmed state, and the recovered state individuals during the first contact time period according to the infectious disease propagation parameters and the first state transfer probability of the susceptible state individuals; determining an intermediate prediction time point according to the current prediction time point and the first contact time period, and determining the propagation state of the individual at the intermediate prediction time point according to the first state transfer probability; if the individuals at the intermediate prediction time point include individuals in the exposed state, determining the second commuting state transfer result of the individual according to the commuting network propagation model; determining the second state transfer probability of the individual during the second contact time period according to the second commuting state transfer result, the infectious disease propagation parameters in the community scenario, and the infectious disease intervention parameters; A transmission data prediction module, configured to obtain a predicted value of the infectious disease transmission data in each of the preset time periods according to the state transition probability of the individual in each of the preset time periods.

7. An electronic device, characterized in that it includes: a processor; and a memory for storing one or more programs, which when executed by the processor cause the processor to implement the method for predicting infectious disease transmission data according to any one of claims 1 to 5.

8. A computer-readable medium, having stored thereon a computer program, characterized in that when the program is executed by a processor, it implements the method for predicting infectious disease transmission data according to any one of claims 1 to 5.

Images