Method and related equipment for predicting epidemic development trend based on prevention and control measures

Abstract

The present disclosure provides a method, device, electronic device, and computer-readable storage medium for predicting the development trend of an epidemic based on prevention and control measures. The method includes: obtaining a first attribute feature of a first region at a first time; obtaining a first combination of prevention and control measures; generating a target prediction vector based on the first attribute feature and the first combination of prevention and control measures; processing the target prediction vector through a pre-trained neural network model to predict the first effective reproduction number of the number of people with an epidemic corresponding to the first combination of prevention and control measures under the first attribute feature, so as to determine the first effective combination of prevention and control measures corresponding to the first region at the first time through the first effective reproduction number of the number of people with an epidemic. The technical solution provided by the embodiment of the present disclosure can determine the first effective reproduction number of the number of people with an epidemic in the first region in combination with the first attribute feature and the first combination of prevention and control measures, so as to determine the first effective combination of prevention and control measures in the first region.

Description

Technical Field

[0001] The present disclosure relates to the field of computer and Internet technology, and in particular to a method and device, an electronic device, and a computer-readable storage medium for predicting the development trend of an epidemic based on prevention and control measures. Background Art

[0002] For epidemic viruses, in the absence of effective vaccines, countries or regions will take non-drug prevention and control measures to intervene in the virus to suppress the spread of the epidemic virus.

[0003] However, different countries or regions may have different national or regional conditions, which may lead to the same non-drug prevention and control measures having different effects in different countries or regions.

[0004] Therefore, it is crucial to determine an effective combination of prevention and control measures for countries or regions with different national conditions in order to control the epidemic virus in that region or country.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure. Summary of the Invention

[0006] The embodiments of the present disclosure provide a method and device, an electronic device, and a computer-readable storage medium for predicting the development trend of an epidemic based on prevention and control measures, which can determine a first effective combination of prevention and control measures based on the attribute characteristics of a first region.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0008] An embodiment of the present disclosure proposes a method for predicting the development trend of an epidemic based on epidemic prevention and control measures, the method comprising: obtaining a first attribute feature of a first region at a first time; obtaining a first combination of prevention and control measures; generating a target prediction vector based on the first attribute feature and the first combination of prevention and control measures; processing the target prediction vector through a pre-trained neural network model to predict a first effective reproduction number of the number of people with an epidemic corresponding to the first combination of prevention and control measures under the first attribute feature, so as to determine a first effective combination of prevention and control measures corresponding to the first region at the first time through the first effective reproduction number of the number of people with an epidemic.

[0009] In some embodiments, the first combination of prevention and control measures includes at least one prevention and control measure; wherein, the target prediction vector is processed by a pre-trained neural network model to predict the first effective reproduction number of the number of people with an epidemic corresponding to the first combination of prevention and control measures under the first attribute feature, including: processing the target prediction vector by the neural network model; obtaining the influence value of each prevention and control measure in the first combination of prevention and control measures on the effective reproduction number of the first number of people with an epidemic, so as to determine the first effective combination of prevention and control measures according to the influence value of each prevention and control measure on the effective reproduction number of the first number of people with an epidemic.

[0010] In some embodiments, generating a target prediction vector based on the first attribute feature and the first prevention and control measure combination includes: normalizing each prevention and control measure in the first prevention and control measure combination to generate a target measure vector; normalizing each attribute feature in the first attribute feature to generate a target attribute vector; generating the target prediction vector based on the target measure vector and the target attribute vector.

[0011] In some embodiments, each control measure in the first control measure combination is normalized separately to generate a target measure vector, including: normalizing the values ​​corresponding to each control measure in the first control measure combination according to the execution strength of each control measure to generate the target measure vector.

[0012] In some embodiments, the first attribute feature includes at least one of a population density feature, an economic feature, an aging feature, a crowd movement feature, and a geographic location feature.

[0013] In some embodiments, the first combination of prevention and control measures includes at least one of closing schools, closing workplaces, canceling public events, restricting gatherings, suspending public transportation, requiring home quarantine, restricting internal movement, border control, nucleic acid testing, or close contact tracing.

[0014] In some embodiments, the first region adopts the first effective prevention and control measures combination to prevent and control the target epidemic at the first time; wherein, the method for predicting the development trend of the epidemic based on prevention and control measures may also include: obtaining the target number of in-hospital patients in the first region at the first time and the number of confirmed cases in the first region at the first time; determining the daily number of new epidemic cases in the first region after the first time based on the effective reproduction number of the first epidemic population and the number of confirmed cases corresponding to the first effective prevention and control measures combination; predicting the daily number of in-hospital patients after the first time based on the daily number of new epidemic cases and the target number of in-hospital patients; determining the target time point when the number of in-hospital patients exceeds the target number of in-hospital patients based on the daily number of in-hospital patients, so as to adjust the prevention and control measures in the first effective prevention and control measures combination according to the target time point.

[0015] In some embodiments, the target time point at which the number of inpatients exceeds the target inpatient number range is determined based on the daily number of inpatients, so as to adjust the prevention and control measures in the first effective prevention and control measures combination according to the target time point, including: if the number of inpatients on the Nth day after the implementation of the first effective prevention and control measures combination exceeds the target inpatient number range, then the Nth day is the target time point; the second effective prevention and control measures combination corresponding to the target time point is determined according to the impact of each prevention and control measure on the economy of the first region, where N is a positive integer greater than or equal to 1; and according to the second effective prevention and control measures combination, the prevention and control measures in the first effective prevention and control measures combination are adjusted at the target time point.

[0016] The embodiments of the present disclosure propose a device for predicting the development trend of an epidemic based on prevention and control measures. The device for predicting the development trend of an epidemic based on prevention and control measures may include: a first attribute feature acquisition module, a first prevention and control measure combination acquisition module, a target prediction vector generation module, and a prediction module.

[0017] Among them, the first attribute feature acquisition module can be configured to obtain the first attribute feature of the first region at the first time. The first prevention and control measures combination acquisition module can be configured to obtain the first prevention and control measures combination. The target prediction vector generation module can be configured to generate a target prediction vector based on the first attribute feature and the first prevention and control measures combination. The prediction module can be configured to process the target prediction vector using a pre-trained neural network model to predict the first effective reproduction number of the number of people with the epidemic corresponding to the first prevention and control measures combination under the first attribute feature, so as to determine the first effective prevention and control measures combination corresponding to the first region at the first time through the first effective reproduction number of the number of people with the epidemic.

[0018] An embodiment of the present disclosure proposes an electronic device, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-mentioned methods for predicting the development trend of an epidemic based on prevention and control measures.

[0019] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for predicting the development trend of an epidemic based on prevention and control measures as described in any one of the above items is implemented.

[0020] The present disclosure provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the aforementioned methods for predicting epidemic development trends based on prevention and control measures.

[0021] The method, apparatus, electronic device, and computer-readable storage medium provided in the embodiments of the present disclosure use prevention and control measures to predict epidemic development trends. Using a pre-trained neural network model, the method processes first attribute characteristics and a first combination of prevention and control measures for a first region, thereby predicting the effective reproduction number of the first epidemic population in the first region under the intervention of the first combination of prevention and control measures. Using the effective reproduction number of the first epidemic population, the first effective combination of prevention and control measures for the first region can be determined from among various first combinations of prevention and control measures, thereby providing an effective reference for epidemic decision-making in the first region and facilitating epidemic control.

[0022] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, serve to explain the principles of the present disclosure. The drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0024] Figure 1 A schematic diagram shows an exemplary system architecture of a method for predicting an epidemic development trend based on prevention and control measures or an apparatus for predicting an epidemic development trend based on prevention and control measures, which is applied to an embodiment of the present disclosure.

[0025] Figure 2It is a structural diagram of a computer system used in an apparatus for predicting epidemic development trends based on prevention and control measures, according to an exemplary embodiment.

[0026] Figure 3 The present invention is a flowchart showing a method for predicting the development trend of an epidemic based on prevention and control measures according to an exemplary embodiment.

[0027] Figure 4 yes Figure 3 Flowchart of step S4 in an exemplary embodiment.

[0028] Figure 5 yes Figure 4 Flowchart of step S41 in an exemplary embodiment.

[0029] Figure 6 The present invention is a flowchart showing a method for predicting the development trend of an epidemic based on prevention and control measures according to an exemplary embodiment.

[0030] Figure 7 yes Figure 6 Flowchart of step S8 in an exemplary embodiment.

[0031] Figure 8 It is the time for each country and region to implement prevention and control measures for the target epidemic according to an exemplary embodiment.

[0032] Figure 9 The present invention is a block diagram of an apparatus for predicting epidemic development trends based on prevention and control measures according to an exemplary embodiment. DETAILED DESCRIPTION

[0033] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0034] The features, structures or characteristics described in the present disclosure may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0035] The accompanying drawings are merely schematic illustrations of the present disclosure. Identical reference numerals in the drawings denote identical or similar components, and thus their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0036] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all content and steps, nor must they be executed in the order described. For example, some steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0037] In this specification, the terms "a", "an", "the", "said" and "at least one" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising", "including" and "having" are used to express open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first", "second" and "third" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0038] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0039] Figure 1 A schematic diagram shows an exemplary system architecture of a method for predicting an epidemic development trend based on prevention and control measures or an apparatus for predicting an epidemic development trend based on prevention and control measures that can be applied to an embodiment of the present disclosure.

[0040] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0041] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, wearable devices, virtual reality devices, smart homes, etc.

[0042] The server 105 may be a server that provides various services, such as a background management server that provides support for devices operated by users using the terminal devices 101, 102, and 103. The background management server may analyze and process received requests and other data, and feed back the processing results to the terminal device.

[0043] Server 105 may, for example, obtain a first attribute feature of the first region at the first time; server 105 may, for example, obtain a first combination of prevention and control measures; server 105 may, for example, generate a target prediction vector based on the first attribute feature and the first combination of prevention and control measures; server 105 may, for example, process the target prediction vector through a pre-trained neural network model to predict the first effective reproduction number of the number of epidemic people corresponding to the first combination of prevention and control measures under the first attribute feature, so as to determine the first effective combination of prevention and control measures corresponding to the first region at the first time through the first effective reproduction number of the number of epidemic people.

[0044] It should be understood that Figure 1 The number of terminal devices, networks and servers is merely illustrative. The server 105 may be a single physical server or may be composed of multiple servers. It may have any number of terminal devices, networks and servers according to actual needs.

[0045] Reference below Figure 2 , which shows a structural diagram of a computer system 200 of a terminal device suitable for implementing an embodiment of the present application. Figure 2 The terminal device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0046] like Figure 2 As shown, the computer system 200 includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 202 or a program loaded from a storage portion 208 into a random access memory (RAM) 203. Various programs and data required for the operation of the system 200 are also stored in the RAM 203. The CPU 201, the ROM 202, and the RAM 203 are connected to each other via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0047] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, and the like; an output section 207 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 208 including a hard disk; and a communication section 209 including a network interface card such as a LAN card or a modem. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 210 as needed, so that a computer program read therefrom can be installed into the storage section 208 as needed.

[0048] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 209, and / or installed from a removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the above-mentioned functions defined in the system of the present application are executed.

[0049] It should be noted that the computer-readable storage medium shown in this application can be a computer-readable signal medium or 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, device, or device, or any combination of the above. More specific examples of computer-readable storage media 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 this application, a 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, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical cable, RF, or any suitable combination thereof.

[0050] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0051] The modules and / or units and / or sub-units described in the embodiments of the present application may be implemented in software or in hardware. The modules and / or units and / or sub-units described may also be provided in a processor. For example, they may be described as: a processor including a sending unit, an acquiring unit, a determining unit, and a first processing unit. The names of these modules and / or units and / or sub-units do not, in certain circumstances, constitute limitations on the modules and / or units and / or sub-units themselves.

[0052] As another aspect, the present application also provides a computer-readable storage medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by a device, the device can implement functions including: obtaining a first attribute feature of a first region at a first time; obtaining a first combination of prevention and control measures; generating a target prediction vector based on the first attribute feature and the first combination of prevention and control measures; processing the target prediction vector through a pre-trained neural network model to predict the first effective reproduction number of the first epidemic population corresponding to the first combination of prevention and control measures under the first attribute feature, so as to determine the first effective combination of prevention and control measures corresponding to the first region at the first time through the first effective reproduction number of the first epidemic population.

[0053] For epidemic infectious viruses, in the absence of an effective vaccine, different countries or regions will implement some non-drug prevention and control measures against the virus, aiming to reduce the contact rate between the population and thus reduce the spread of the virus.

[0054] However, the rapid spread of the epidemic has forced some countries or regions to implement extremely stringent intervention measures at some point in an effort to quickly curb the spread of the epidemic. However, the stricter and longer the measures, the greater the impact on citizens' lives. Furthermore, once implemented, prevention and control interventions are difficult to reverse. Furthermore, different countries or regions have different national and regional circumstances, and different prevention and control measures will have different effects in different countries or regions. For example, in some countries or regions, the public may not accept the prevention and control measure of wearing masks for various reasons, so mask-wearing prevention and control measures in these countries or regions will not be effective in controlling the epidemic. Similarly, in some countries or regions, economic reasons prevent the closure of social venues such as bars and cinemas, so immediate closures of bars and cinemas in these countries or regions will not achieve the desired results.

[0055] The embodiments of the present disclosure provide a technical solution that can quantify the effectiveness of different combinations of prevention and control measures on the target epidemic in combination with the attribute characteristics of a country or region (such as national conditions or regional characteristics), so as to determine a combination of prevention and control measures that is relatively effective for the target epidemic in the target country or region based on the quantification results, and provide effective suggestions for the country or region to carry out epidemic prevention.

[0056] Figure 3 This is a flow chart of a method for predicting the development trend of an epidemic based on prevention and control measures according to an exemplary embodiment. The method provided by the embodiment of the present disclosure can be processed by any electronic device with computing and processing capabilities, such as the above Figure 1 In the following embodiments, the server 105 and / or the terminal devices 102 and 103 in the embodiment are described with the server 105 as the execution subject, but the present disclosure is not limited thereto.

[0057] Reference Figure 3 The method for predicting the development trend of an epidemic based on prevention and control measures provided in the embodiments of the present disclosure may include the following steps.

[0058] In step S1, a first attribute feature of a first region at a first time is obtained.

[0059] In some embodiments, the first area may refer to a country, a region, or an administrative province, city, county, autonomous region, or municipality in a country. Any country or region where prevention and control measures can be implemented is within the scope of protection of this disclosure, and this disclosure does not impose any restrictions on this.

[0060] In some embodiments, the first time may refer to the time point when the first region begins to change measures, or may refer to the time point before the measures are changed, or may refer to the time point after the measures are changed. This disclosure does not limit this.

[0061] In some embodiments, the first attribute characteristic may refer to national characteristics or regional characteristics of the first region, which is not limited in this disclosure. For example, the first attribute characteristic of the first region at a first time may refer to at least one of the following characteristics: population density, economic characteristics, aging characteristics, population mobility characteristics, and geographic location characteristics of the first region at the first time.

[0062] In some embodiments, the economic characteristics of the first region may refer to characteristics that can measure the economic level of the country or region, such as gross domestic product (GDP) and per capita income, and the present disclosure does not impose any restrictions on this.

[0063] In some embodiments, the aging characteristic may refer to the total number of the aging population in the country or region, or the proportion of the aging population in the total population.

[0064] In some embodiments, the crowd movement feature may refer to movement data (entry and exit data) of the first region at a designated location, where the designated location may be a park, botanical garden, zoo, library, train station, airport, or other place where crowds tend to gather.

[0065] In some embodiments, the geographic location feature may refer to the latitude and longitude information of the first region, or may refer to whether the first region is close to the sea or close to a mountain, etc., and the present disclosure does not impose any limitation on this.

[0066] In some embodiments, the first attribute characteristics of the first region may also include the total population of the first region, per capita land area, major trading countries (or regions), major tourist countries (or regions), etc., which are not limited in this disclosure.

[0067] It is understandable that any indicator that can reflect the attribute characteristics of the first region is within the protection scope of this disclosure.

[0068] In step S2, a first combination of prevention and control measures is obtained.

[0069] In some embodiments, each country or region will take some non-drug prevention and control measures to intervene in the target epidemic (such as an epidemic virus). Among them, non-drug prevention and control measures can be roughly divided into three categories: control and management measures, economic measures, and health system measures. Among them, control and management measures and health system measures may include, for example, C1: closing schools, C2: closing workplaces, C3: canceling public activities, C4: restricting gatherings, C5: public transportation suspension, C6: home isolation requirements, C7: restricting internal movement, C8: border control, H2: nucleic acid testing, H3: close contact tracking, etc.

[0070] In some embodiments, the first combination of prevention and control measures may include at least one prevention and control measure. It is understood that the present disclosure does not limit the number and type of prevention and control measures in the first combination of prevention and control measures. For example, the first combination of prevention and control measures may include at least one of closing schools, closing workplaces, canceling public events, restricting gatherings, suspending public transportation, requiring home quarantine, restricting internal movement, border control, nucleic acid testing, or close contact tracing.

[0071] Generally speaking, if the first region has already taken certain prevention and control measures before the first time, if it is desired to predict the effective prevention and control measure combination at the time point (the first time) when the measures are changed, adjustments can be made based on the prevention and control measures already taken before the first time to obtain the first prevention and control measure combination. For example, if the prevention and control measure combination {A, B, C, D} has been used to prevent and control the target epidemic before the first time (A, B, C, D represent different prevention and control measures, respectively), then the first prevention and control measure combination can be determined by adding or deleting the prevention and control measure combination {A, B, C, D}.

[0072] In step S3, a target prediction vector is generated based on the first attribute feature and the first prevention and control measure combination.

[0073] In some embodiments, a target prediction vector may be generated based on the value of the first attribute feature of the first region and the values ​​of each prevention and control measure in the first prevention and control measure combination.

[0074] In some embodiments, since the values ​​of each first attribute feature and each prevention and control measure in the first prevention and control measure combination cannot be directly used for feature extraction, each first attribute feature and each prevention and control measure can be normalized separately to generate a target prediction vector.

[0075] Among them, the size of the value of the prevention and control measures can be used to describe the enforcement strength of the prevention and control measures. For example, the prevention and control measures for closing schools can be divided into 1, 2, and 3 levels in advance, where level 1 represents that the enforcement strength of the prevention and control measures for closing schools is weak, level 2 represents that the enforcement strength of the prevention and control measures for closing schools is average, and level 3 represents that the enforcement strength of the prevention and control measures for closing schools is strong; the size of the value of the first attribute feature can be used to describe the situation of the first attribute of the first region. For example, the GDP feature of the first region can be divided into 1, 2, and 3 levels in advance, where level 1 represents that the GDP of the first region falls within the first range (greater than 0 and lower than the first threshold), level 2 represents that the GDP of the first region falls within the second range (greater than or equal to the first threshold and lower than the second threshold), and level 3 represents that the GDP of the first region falls within the third range (greater than or equal to the second threshold).

[0076] As shown in Table 1, it is assumed that the target prediction vector includes 7-dimensional data such as [C1, C2, C3, C4, H1, H2, H3], where C1 represents the prevention and control measures of closing schools, C2 represents the prevention and control measures of closing workplaces, C3 represents the prevention and control measures of canceling public activities, C4 represents the prevention and control measures of restricting gatherings, H1 represents the attribute characteristics of population density, H2 represents the attribute characteristics of GDP, and H3 represents the attribute characteristics of the proportion of aging population.

[0077] Assume that the first combination of prevention and control measures taken by the first region at the first time and its corresponding values ​​are [C1=3.5, C2=2.5, C3=2.5] as shown in Table 1. Since C4 is not included in the first combination of prevention and control measures in the first region at the first moment, the value corresponding to C4 in the target prediction vector generated according to the first combination of prevention and control measures should be 0.

[0078] In some embodiments, the values ​​corresponding to each prevention and control measure in the first prevention and control measure combination can be normalized according to the execution strength of each prevention and control measure, and the values ​​of each first attribute feature of the first region can be normalized separately to generate the target measure vector.

[0079] As shown in Table 1, assuming that the difference between the maximum value (for example, 3.5) and the minimum value (for example, 0) of the prevention and control intensity of the prevention and control measure C1 is 3.5, then after normalizing the original value 3.5 of C1, a normalized value of 1 can be obtained.

[0080] It is understandable that the present disclosure does not limit the normalization method, and any method that can achieve the normalization effect is within the protection scope of the present disclosure.

[0081] Table 1

[0082]

[0083] In step S4, the target prediction vector is processed by a pre-trained neural network model to predict the first effective reproduction number of the first epidemic population corresponding to the first prevention and control measure combination under the first attribute feature, so as to determine the first effective prevention and control measure combination corresponding to the first region at the first time through the first effective reproduction number of the first epidemic population.

[0084] In some embodiments, the pre-trained neural network model may refer to a pre-trained convolutional neural network model, or a pre-trained recurrent neural network model, etc. It can be understood that any neural network model that can achieve classification is within the scope of protection of this disclosure, and this disclosure does not impose any restrictions on this.

[0085] In some embodiments, a second combination of prevention and control measures implemented in the second region at the second time and a second attribute feature of the second region at the second time can be obtained, and a target training vector can be generated based on the second combination of prevention and control measures and the second attribute feature (the generation process of the target training vector is similar to the generation process of the target prediction vector and will not be repeated here).

[0086] In some embodiments, a second epidemic control indicator of the second country after the implementation of the second prevention and control measures (for example, the ratio of the effective reproduction number Rt of the epidemic on the tth day after the implementation of the second prevention and control measures to the effective reproduction number R1 of the epidemic on the first day) can be obtained as a training label, where t is a positive integer greater than or equal to 1.

[0087] The effective reproduction number Rt of the epidemic population on day t can refer to the average number of people that a patient at time t can infect within a transmission cycle T, or it can refer to the average number of people that a patient at time t can infect within a day, and this disclosure does not impose any restrictions on this. One transmission cycle can be the sum of the incubation period and the time to diagnosis of the target epidemic. For example, if the average incubation period of the target epidemic is 7 days and the average time to diagnosis is 3 days, then the transmission period of the target epidemic can be 7 + 3 = 10 days.

[0088] The incubation period can refer to the time between a target individual contracting the target disease and developing the disease, while the time to diagnosis can refer to the actual time it takes for a target individual to confirm they have contracted the target disease through medical treatment. It is understood that the incubation period and time to diagnosis of the target disease may vary over time. Generally speaking, the incubation period of the target disease follows a specific distribution, such as the Poisson distribution or the Weibull distribution.

[0089] In some embodiments, the neural grid can be pre-trained with the second epidemic control indicator as the training label of the target training vector to achieve the prediction of the first epidemic control indicator of the first region under the intervention of the first combination of prevention and control measures (for example, the effective reproduction number of the epidemic on the Nth day and the effective reproduction number of the epidemic on the 1st day).

[0090] In some embodiments, the first effective reproduction number of the number of people suffering from the epidemic (such as Rt above) corresponding to the first combination of prevention and control measures under the first attribute characteristics can be determined based on the predicted first epidemic control index, and then the first effective combination of prevention and control measures corresponding to the first region at the first time can be determined based on the first effective reproduction number of the number of people suffering from the epidemic.

[0091] In some embodiments, the first combination of prevention and control measures in which the effective reproduction number of the first epidemic population exceeds the target threshold and has the smallest economic or political impact on the first region or country can be selected as the first effective combination of prevention and control measures.

[0092] The technical solution provided in this embodiment, on the one hand, uses a neural network model to process the first prevention and control measure combination and the first attribute characteristics, which can conveniently and quickly quantify the first prevention and control measure combination; on the other hand, it quantifies the effectiveness of the first prevention and control measure combination in combination with the attribute characteristics of the first region, and effectively predicts the effectiveness of the first prevention and control measure combination in the first region; in addition, based on the processing results of the neural network model, the first effective re-examination number of the first epidemic in the first region under the intervention of the first prevention and control measure combination can be predicted, which is convenient for determining the first effective prevention and control measure combination corresponding to the first region at the first time.

[0093] Figure 4 yes Figure 3 Flowchart of step S4 in an exemplary embodiment.

[0094] In some embodiments, the first combination of control measures may include at least one control measure.

[0095] refer to Figure 4 , the above step S4 may include the following steps.

[0096] In step S41, the target prediction vector is processed by the neural network model.

[0097] In some embodiments, the pre-trained neural network model may refer to a pre-trained Gradient Boost Regression Tree (GBRT).

[0098] GBRT is an iterative regression decision tree algorithm, which consists of multiple regression decision trees. In the embodiment, each regression tree learns the conclusions and residuals (negative gradients) of all previous trees, and fits a current residual regression tree. The weak learners constructed at each step of the iteration are to make up for the shortcomings of the existing model, and each decision branch has data interpretability. GBRT can also automatically interact between multiple groups of features, and can handle the nonlinear correlation problem between prevention and control measures features and country-related features in our data. While fitting the target to be predicted, GBRT can also obtain the importance of the feature based on the average value of the importance of the feature in a single tree.

[0099] In some embodiments, a second combination of prevention and control measures adopted by the second region (or country) after adjusting the prevention and control measures for the target epidemic at the second time, as well as a second attribute feature of the second region (or country) at the second time point can be collected in advance, and a target training vector for training the neural network model is generated based on the second combination of prevention and control measures and the second attribute feature. It is understandable that the target country or region can refer to multiple countries or regions, and this disclosure does not limit this.

[0100] In some embodiments, the neural network model can be trained using the target training vector and the second epidemic control indicator of the second country after the implementation of the second prevention and control measure (for example, the ratio of the effective reproduction number Rt of the epidemic on the tth day after the implementation of the second prevention and control measure to the effective reproduction number R1 of the epidemic on the first day) as training labels, where t is a positive integer greater than or equal to 1.

[0101] In step S42, the impact value of each prevention and control measure in the first prevention and control measure combination on the effective reproduction number of the first epidemic population is obtained, so as to determine the first effective prevention and control measure combination based on the impact value of each prevention and control measure on the effective reproduction number of the first epidemic population.

[0102] In some embodiments, by processing the target prediction vector through a pre-trained GBRT neural network model, not only the first epidemic control index can be obtained (for example, the ratio of the effective reproduction number Rt of the epidemic on the tth day after the implementation of the first prevention and control measure to the effective reproduction number R1 of the epidemic on the first day), but also the influence value of each feature in the target prediction vector (corresponding to each prevention and control measure and each attribute feature in the first prevention and control measure) on the first epidemic control index (which can also be considered as the first effective reproduction number of the epidemic) can be obtained.

[0103] As shown in Table 2, Table 2 shows the influence of each feature in the target prediction vector (including each prevention and control measure and each second attribute feature) on the final first epidemic control index (for example, the ratio of the effective reproduction number Rt of the epidemic on the tth day after the implementation of the first prevention and control measure to the effective reproduction number R1 of the epidemic on the first day), where t is a positive integer greater than or equal to 1.

[0104] As shown in Table 2, the first one indicates the greatest impact on the final target value. For example, in the context of countries / regions characterized by population density, the cancellation of prevention and control measure C4 has the greatest impact on the effective reproduction number of the first epidemic population.

[0105] C4 0.1056517 H3 0.0491506 C5 0.0288271 C1 0.0243832 C2 0.0218051 C8 0.0189261 C6 0.0184697 C7 0.0169168 H2 0.0070437 C3 0.0034341

[0106] In some embodiments, the measures in the first combination of prevention and control measures can be adjusted according to the impact of each prevention and control measure on the effective reproduction number of the first epidemic population, so as to determine the first effective combination of prevention and control measures.

[0107] The technical solution provided in this embodiment can process the first attribute characteristics and the first prevention and control measures combination of the first region through a neural network model, and determine the magnitude of the impact of each prevention and control measure on the final result in the first prevention and control measures combination, so as to adjust each measure in the first prevention and control measures combination according to the magnitude of the impact. For example, if the current effective reproduction number of the first epidemic population is large and is not conducive to the prevention and control of the target epidemic, and it is hoped to tighten the prevention and control measures, then the prevention and control efforts of the prevention and control measures that have a greater impact on the effective reproduction number of the first epidemic population can be increased; if the current effective reproduction number of the first epidemic population is small, and the current first prevention and control measures combination has a greater impact on the economy or politics of the first region, then it can be considered to weaken the prevention and control efforts of the prevention and control measures in the first prevention and control measures combination that have a smaller impact on the effective reproduction number of the first epidemic population, or directly release them.

[0108] It will be understood that the embodiments of the present disclosure do not limit the method for determining the first effective combination of prevention and control measures. Any country or region can determine the optimal first effective combination of prevention and control measures based on the first effective reproduction number of the number of people affected by the epidemic provided by the embodiments of the present disclosure and the actual situation of the country (or region).

[0109] Figure 5 yes Figure 4 Flowchart of step S41 in an exemplary embodiment. Figure 5 , the above step S4 may include the following steps.

[0110] In step S411, each prevention and control measure in the first prevention and control measure combination is normalized to generate a target measure vector.

[0111] As shown in Table 1, each prevention and control measure in the first prevention and control measure combination can be normalized separately. For example, assuming that the maximum prevention and control intensity corresponding to the C5 prevention and control measure is 6, the minimum prevention and control intensity is 1, and the value of C5 in the first prevention and control measure combination is 2, then the normalized value of C5 in the first prevention and control measure combination is 1 / 5. It can be understood that the present disclosure does not limit the normalization method.

[0112] In step S412, normalization is performed on each of the first attribute features to generate a target attribute vector.

[0113] The first attribute feature of the first region is similar to the normalization processing of each prevention and control measure in the first prevention and control measure combination, and the present disclosure does not impose any restrictions on this.

[0114] In step S413 , the target prediction vector is generated according to the target measure vector and the target attribute vector.

[0115] Figure 6The present invention is a flowchart showing a method for predicting the development trend of an epidemic based on prevention and control measures according to an exemplary embodiment.

[0116] In some embodiments, if the first region adopts the first effective combination of prevention and control measures to prevent and control the target epidemic at the first time, then reference Figure 6 The above-mentioned method for predicting the development trend of the epidemic based on prevention and control measures may include the following steps.

[0117] In step S5, the target number of in-hospital patients in the first region at the first time and the number of confirmed cases in the first region at the first time are obtained.

[0118] In some embodiments, the target number of in-hospital patients in the first region at the first time may refer to the number of patients in the first region who have been diagnosed with the target epidemic (eg, epidemic virus) and are being treated in the hospital at the first time.

[0119] In some embodiments, the number of confirmed cases in a first region at a first time may refer to individuals who are somewhat contagious for the target epidemic. It is understood that since some patients, while somewhat contagious, may not be diagnosed or may not exhibit symptoms, it is difficult to accurately count the number of confirmed cases in the first region at the first time. Therefore, those who have been diagnosed through medical means can be used as the number of confirmed cases in this embodiment. Of course, if the number of individuals who are contagious for the target epidemic in the first region at the first time is known, that number can be used as the number of confirmed cases in this embodiment.

[0120] In step S6, the number of new cases of the epidemic in the first region every day after the first time is determined based on the first effective reproduction number of the epidemic population corresponding to the first effective prevention and control measure combination and the number of confirmed cases.

[0121] In some embodiments, the effective reproduction number of the first epidemic population is the average number of people that a patient can infect within a transmission cycle T at time t, where t is the tth day after the first time point, and t is less than or equal to T. Then, the daily number of new cases within the next T days after the first time point can be determined by (the number of confirmed cases at the first time point * the effective reproduction number of the first epidemic population / cycle T).

[0122] It is understandable that the daily number of new people within 2T days from the first time point, the daily number of new people within 3T days, etc., can all be determined by the method provided in this embodiment.

[0123] In some embodiments, since the first region adopts the first combination of prevention and control measures at the first time point, the value of the effective reproduction number of the first epidemic population each day thereafter can be determined, then the daily number of new epidemic cases each day after the first time point can be determined based on the effective reproduction number of the first epidemic population.

[0124] For example, assuming that the effective reproduction number of the first epidemic is the average number of people that a patient can infect within a transmission cycle T at time t, t is the tth day after the first time point, and t is less than or equal to T, then the average daily number of new people within t days (that is, the daily number of new epidemics) can be determined based on the effective reproduction number of the first epidemic.

[0125] In step S7, the number of patients in the hospital each day after the first time is predicted based on the daily number of new cases of the epidemic and the target number of patients in the hospital.

[0126] In some embodiments, since the number of new patients in the daily epidemic is known every day after the first time point, the number of in-hospital patients at the first time point is also known, and the discharge cycle of in-hospital patients (i.e., how long after admission can they be discharged) can also be known, then the number of in-hospital patients per day after the first time point can be calculated (number of in-hospital patients per day = number of new confirmed cases per day + number of in-hospital patients per day - number of discharged patients per day). Generally speaking, the target number of days a patient stays in the hospital for a target epidemic can be roughly determined. For example, for an epidemic virus, the number of days a patient is treated in the hospital is approximately 20 days. Therefore, when the patient's admission time is known, it is only necessary to count the patients whose daily hospitalization time meets the target number of days in the hospital to determine the number of discharged patients per day.

[0127] In step S8, a target time point at which the number of inpatients exceeds a target inpatient number range is determined based on the daily number of inpatients, so that the prevention and control measures in the first effective prevention and control measure combination are adjusted according to the target time point.

[0128] In some embodiments, the medical resources in the first region are limited, and the number of patients that can be treated is also limited. To avoid an excessive number of patients with the target epidemic, the prevention and control measures in the first region can be adjusted according to the medical resource conditions in the first region.

[0129] In some embodiments, the target range of hospitalized patients can be determined by the number of available beds in the first region.

[0130] In some embodiments, a target time point at which the target hospital population range is exceeded for the first time can be determined based on the number of daily hospitalized patients after the first time point. It is understood that if the number of daily hospitalized patients at the target time point is higher than the target hospital population range, then an outbreak of the target epidemic is likely; and if the number of daily hospitalized patients at the target time point is lower than the target hospital population range, then there is an excess of medical resources for the target epidemic in the first region.

[0131] In some embodiments, if the number of inpatients at the target time point exceeds the target inpatient population range, the prevention and control measures for the first region may be adjusted at the target time point.

[0132] The technical solution provided in this embodiment determines the number of patients in the hospital every day in the future in the first region based on the first combination of prevention and control measures in the first region, and determines the target time point of the target epidemic outbreak (the medical resources in the first region cannot bear the given number of patients) or the surplus of medical resources based on the number of patients in the hospital every day in the future, so as to facilitate the adjustment of prevention and control measures according to the target time point, thereby realizing early warning of the epidemic outbreak or surplus of medical resources.

[0133] Figure 7 yes Figure 6 Flowchart of step S8 in an exemplary embodiment. Figure 7 , the above step S8 may include the following steps.

[0134] In step S81, if the number of in-hospital patients on the Nth day after the implementation of the first effective combination of prevention and control measures exceeds the target number of in-hospital patients, the Nth day is the target time point.

[0135] In some embodiments, since the medical resources in the first region are limited, if the number of patients is too large due to lax prevention and control measures, it will have a huge impact on the medical resources in the first region; if the number of patients is small due to overly tight prevention and control measures, resulting in an excess of medical resources, then the overly tight prevention and control measures will have an adverse impact on the economy of the first region or are having an adverse impact.

[0136] Therefore, it is necessary to set a reasonable target range for the number of hospitalized patients. In some embodiments, the target range for the number of hospitalized patients may include an upper limit and a lower limit for the number of hospitalized patients. The upper limit for the number of hospitalized patients may refer to the upper limit of medical resources in the first region, and the lower limit for the number of hospitalized patients may refer to the lower limit of medical resources in the first region. For example, if the number of beds available in the first region is 10,000, then the upper limit for the number of hospitalized patients in the first region may be 10,000*0.9=9,000, and the lower limit for the number of hospitalized patients in the first region may be 10,000*0.3=3,000.

[0137] In step S82, the second effective prevention and control measure combination corresponding to the target time point is determined according to the impact of each prevention and control measure on the economy of the first region, where N is a positive integer greater than or equal to 1.

[0138] In some embodiments, if the number of in-hospital patients in the first region at the target time point is lower than the lower limit of the number of in-hospital patients, the target prevention and control measure combination implemented in the first region at the first time can be obtained; according to the economic impact of each prevention and control measure in the target prevention and control measure combination on the first region, one or more prevention and control measures are cancelled from the target prevention and control measure combination to obtain the second effective prevention and control measure combination, and under the intervention of the second effective prevention and control measure combination, the number of in-hospital patients in the first region within a specified time (e.g., one month) is within the target number of in-hospital patients range.

[0139] For example, the target prevention and control measure combination includes four measures A, B, C, and D, and the economic impact on the first region is A > B > C > D. Then, if the number of in-hospital patients in the first region at the target time point is lower than the lower limit of the number of in-hospital patients, the prevention and control measures can be reduced from the target prevention and control measure combination in the order of A, B, C, and D until, under the intervention of the target prevention and control measure combination, the number of in-hospital patients in the first region within a specified time (e.g., one month) is within the target number of in-hospital patients range. The adjusted target prevention and control measure combination is the second effective prevention and control measure combination.

[0140] In some embodiments, if the number of in-hospital patients in the first region at the target time point is higher than the upper limit of the number of in-hospital patients, the target prevention and control measures available to the first region are obtained (i.e., the prevention and control measures or the intensity of prevention and control measures that the first region has not adopted but can adopt); according to the economic impact of each target prevention and control measure on the first region, the prevention and control measures in the first region are adjusted to obtain the second effective prevention and control measure combination, and under the intervention of the second effective prevention and control measure combination, the number of in-hospital patients in the first region within a specified time (e.g., one month) is within the target number of in-hospital patients range.

[0141] For example, assume that the target prevention and control measures available to the first region include multiple prevention and control measures such as a, b, c, d... and the economic impact on the first region is a < b < c < d.... Then, if the number of in-hospital patients in the first region at the target time point is higher than the lower limit of the number of in-hospital patients, the prevention and control measures can be added to the target prevention and control measure combination in the order of a, b, c, d... until, under the intervention of the adjusted target prevention and control measure combination, the number of in-hospital patients in the first region within a specified time (e.g., one month) is within the target number of in-hospital patients range. The adjusted target prevention and control measure combination is the second effective prevention and control measure combination.

[0142] In some embodiments, the number of countries implementing each prevention and control measure and the implementation time can be counted to determine the economic impact of each prevention and control measure. For example Figure 8As shown in the figure, the prevention and control measure of "restricting international travel" was adopted by many countries or regions at the very beginning of the epidemic, so it can be considered that "restricting international travel" is a prevention and control measure with less impact on the economy of each region; the prevention and control measure of "stay-at-home order" was adopted by fewer countries and was adopted relatively late, so it can be considered that the prevention and control measure of "stay-at-home order" is a prevention and control measure with a greater impact on the economy of each region.

[0143] In some embodiments, the Figure 8 Draw a horizontal line at the target number of countries (for example, 80). It can be assumed that the prevention and control measures from left to right on this horizontal line have an increasingly greater impact on the economy.

[0144] In some embodiments, the following steps can be used to determine whether the number of inpatients in the first region within a specified time period under the intervention of the second effective prevention and control measure combination is within the target inpatient number range.

[0145] Obtain the first attribute feature of the first region at the first time; generate a prediction vector based on the first attribute feature and the second effective prevention and control measure combination; process the prediction vector through a pre-trained neural network model to predict the effective reproduction number of the epidemic population corresponding to the second effective prevention and control measure combination under the first attribute feature; obtain the target number of in-hospital patients in the first region at the first time and the number of confirmed cases in the first region at the first time; determine the daily number of new epidemic cases in the first region within a specified time based on the effective reproduction number of the epidemic population and the number of confirmed cases in the first time; determine the daily number of in-hospital patients in the first region within a specified time based on the daily number of new epidemic cases within the specified time and the number of confirmed cases in the first region at the first time; if the daily number of in-hospital patients in the first region within the specified time is within the target number of in-hospital patients, determine the second effective prevention and control measure combination as the effective prevention and control measure combination that can be adopted by the first region at the target time point.

[0146] In step S83, the control measures in the first effective control measure combination are adjusted at the target time point according to the second effective control measure combination.

[0147] In some embodiments, recommendations can be made to decision makers in the first region based on the second effective prevention and control measure combination at the target time point so that the decision makers in the first region can adjust the prevention and control measures for the target epidemic.

[0148] The technical solution provided in this embodiment, on the one hand, predicts the daily number of hospitalized patients in the first region based on the daily number of new cases of the epidemic in the first region, and predicts the target time point of excess medical resources or outbreak of the epidemic in the first region based on the daily number of hospitalized patients; on the other hand, based on the impact of various prevention and control measures on the economy, the prevention and control measures in the first region are adjusted at the target time point, so as to effectively control the epidemic while minimizing the impact on the economy of the first region as much as possible.

[0149] Figure 9 This is a block diagram of a device for predicting the development trend of an epidemic based on prevention and control measures according to an exemplary embodiment. Figure 9 The device 900 for predicting the development trend of an epidemic based on prevention and control measures provided in an embodiment of the present disclosure may include: a first attribute feature acquisition module 901, a first prevention and control measure combination acquisition module 902, a target prediction vector generation module 903 and a prediction module 904.

[0150] Among them, the first attribute feature acquisition module 901 can be configured to obtain the first attribute feature of the first region at the first time. The first prevention and control measures combination acquisition module 902 can be configured to obtain the first prevention and control measures combination. The target prediction vector generation module 903 can be configured to generate a target prediction vector based on the first attribute feature and the first prevention and control measures combination. The prediction module 904 can be configured to process the target prediction vector through a pre-trained neural network model to predict the first effective reproduction number of the number of people with the epidemic corresponding to the first prevention and control measures combination under the first attribute feature, so as to determine the first effective prevention and control measures combination corresponding to the first region at the first time through the first effective reproduction number of the number of people with the epidemic.

[0151] In some embodiments, the first combination of control measures includes at least one control measure.

[0152] In some embodiments, the prediction module 904 may include: a neural network processing unit and a first effective prevention and control combination acquisition module.

[0153] The neural network processing unit may be configured to process the target prediction vector using the neural network model. The first effective prevention and control combination acquisition module may be configured to obtain the impact value of each prevention and control measure in the first prevention and control measure combination on the first effective reproduction number of the number of people infected with the epidemic, so as to determine the first effective prevention and control measure combination based on the impact value of each prevention and control measure on the first effective reproduction number of the number of people infected with the epidemic.

[0154] In some embodiments, the target prediction vector generation module 903 may include: a target measure vector generation unit, a target attribute vector generation unit, and a target prediction vector generation unit.

[0155] The target measure vector generation unit may be configured to normalize each control measure in the first control measure combination to generate a target measure vector. The target attribute vector generation unit may be configured to normalize each attribute feature in the first attribute feature to generate a target attribute vector. The target prediction vector generation unit may be configured to generate the target prediction vector based on the target measure vector and the target attribute vector.

[0156] In some embodiments, the target measure vector generating unit may include: a normalization processing subunit.

[0157] Among them, the normalization processing subunit can be configured to normalize the values ​​corresponding to each prevention and control measure in the first prevention and control measure combination according to the execution strength of each prevention and control measure, so as to generate the target measure vector.

[0158] In some embodiments, the first attribute feature includes at least one of a population density feature, an economic feature, an aging feature, a crowd movement feature, and a geographic location feature.

[0159] In some embodiments, the first combination of prevention and control measures includes at least one of closing schools, closing workplaces, canceling public events, restricting gatherings, suspending public transportation, requiring home quarantine, restricting internal movement, border control, nucleic acid testing, or close contact tracing.

[0160] In some embodiments, the first region uses the first combination of effective prevention and control measures to prevent and control the target epidemic at the first time.

[0161] In some embodiments, the unit for predicting the development trend of the epidemic based on prevention and control measures also includes: a module for obtaining the number of confirmed cases, a module for obtaining the number of new cases per day, a module for obtaining the number of patients in hospital per day, and an adjustment module.

[0162] Among them, the module for obtaining the number of confirmed patients can be configured to obtain the target number of in-hospital patients in the first region at the first time and the number of confirmed patients in the first region at the first time. The module for obtaining the number of new daily epidemic cases can be configured to determine the number of new daily epidemic cases in the first region after the first time based on the effective reproduction number of the first epidemic case corresponding to the first effective prevention and control measures combination and the number of confirmed cases. The module for obtaining the number of daily in-hospital patients can be configured to predict the number of daily in-hospital patients after the first time based on the daily new epidemic case numbers and the target number of in-hospital patients. The adjustment module can be configured to determine the target time point at which the number of in-hospital patients exceeds the target number of in-hospital patients based on the daily number of in-hospital patients, so as to adjust the prevention and control measures in the first effective prevention and control measures combination according to the target time point.

[0163] In some embodiments, the adjustment module may include: a judgment unit, a second effective prevention and control measure combination acquisition module and an adjustment unit.

[0164] Among them, the judgment unit can be configured so that if the number of in-hospital patients on the Nth day after the implementation of the first effective prevention and control measure combination exceeds the target number of in-hospital patients, then the Nth day is the target time point. The second effective prevention and control measure combination acquisition unit can be configured to determine the second effective prevention and control measure combination corresponding to the target time point according to the impact of each prevention and control measure on the economy of the first region, where N is a positive integer greater than or equal to 1. The adjustment unit can be configured to adjust the prevention and control measures in the first effective prevention and control measure combination at the target time point based on the second effective prevention and control measure combination.

[0165] Since the various functional modules of the device 900 for predicting the development trend of an epidemic based on prevention and control measures in the example embodiment of the present disclosure correspond to the steps of the example embodiment of the method for predicting the development trend of an epidemic based on prevention and control measures, they will not be repeated here.

[0166] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computing device (which can be a personal computer, a server, a mobile terminal, or a smart device, etc.) to execute the method according to the embodiment of the present disclosure, for example Figure 3 One or more of the steps shown.

[0167] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0168] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0169] It should be understood that the present disclosure is not limited to the detailed structures, drawings or implementations shown herein, but rather is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A medical resource early warning method, characterized in that: include: Obtain the target number of in-hospital patients in the first region at the first time and the number of confirmed cases in the first region at the first time; Determine the effective reproduction number of the first epidemic population corresponding to the first response strategy combination; Determine the number of new cases of the epidemic in the first region every day after the first time period based on the first effective reproduction number of the epidemic population corresponding to the first response strategy combination and the number of confirmed cases; Predicting the number of inpatients per day after the first time period based on the daily number of new cases, the target number of inpatients, and the discharge cycle of inpatients; Determine a target time point when the number of inpatients exceeds a target inpatient population range based on the daily number of inpatients, so as to provide an early warning for medical resources based on the target time point; The first effective reproduction number of the number of people in the epidemic corresponding to the first response strategy combination is determined by the following method: Obtaining a first attribute feature and a first response strategy combination of a first region at a first time; Normalizing each response strategy in the first response strategy combination according to the execution strength of each response strategy to generate a target response strategy vector, and normalizing each attribute feature in the first attribute feature to generate a target attribute vector; generating a target prediction vector according to the target response strategy vector and the target attribute vector; The target prediction vector is processed using a pre-trained neural network model to obtain a ratio of the effective reproduction number of the epidemic population corresponding to the first region after the t-th day of implementing the first response strategy combination to the effective reproduction number of the epidemic population corresponding to the first time, and the first effective reproduction number of the epidemic population corresponding to the t-th day of implementing the first response strategy combination in the first region under the first attribute feature is predicted based on the ratio, wherein the neural network model includes a progressive gradient regression tree; The first response strategy combination in which the effective reproduction number of the first epidemic is less than the target threshold is used as the first effective response strategy combination corresponding to the first region at the first time, where t is an integer greater than or equal to 1; When the effective reproduction number of the first epidemic is greater than the target threshold, the influence value of each response strategy in the first response strategy combination on the effective reproduction number of the first epidemic population is obtained, and the response strategies in the first response strategy combination are optimized according to the influence value to obtain the first effective response strategy combination; The pre-trained neural network model is obtained by: Pre-collecting the second response strategy combination adopted by the second region after adjusting the response strategy for the target epidemic at the second time, and the second attribute characteristics of the second region at the second time point; Generate a target training vector for training a neural network model according to the second coping strategy combination and the second attribute feature; The neural network model is trained using the target training vector and the second epidemic control index of the second region after implementing the second response strategy as training labels. The second epidemic control index is used to represent the ratio of the effective reproduction number of the epidemic corresponding to the second region after the implementation of the second response strategy combination on the tth day to the effective reproduction number of the epidemic corresponding to the second time.

2. The method according to claim 1, characterized in that The first response strategy combination includes at least one of closing schools, closing workplaces, canceling public events, restricting gatherings, suspending public transportation, requiring home quarantine, restricting internal movement, border control, nucleic acid testing, or close contact tracing.

3. The method according to claim 1, characterized in that Determining a target time point when the number of inpatients exceeds a target inpatient population range based on the daily number of inpatients, so as to provide an early warning prompt for medical resources based on the target time point, including: If the number of inpatients on the Nth day after the implementation of the first effective coping strategy combination exceeds the target inpatient population range, the Nth day will be the target time point; Determining a second effective response strategy combination corresponding to the target time point according to the impact of each response strategy on the economy of the first region, where N is a positive integer greater than or equal to 1; According to the second effective coping strategy combination, the coping strategies in the first effective coping strategy combination are adjusted at the target time point.

4. A response strategy optimization device, characterized in that: include: A confirmed number acquisition module, configured to acquire a target number of in-hospital patients in a first region at a first time and the number of confirmed cases in the first region at the first time; Determine the effective reproduction number of the first epidemic population corresponding to the first response strategy combination; a daily new epidemic number acquisition module, configured to determine the daily new epidemic number in the first region after the first time period based on the first effective reproduction number of the epidemic number corresponding to the first response strategy combination and the number of confirmed cases; A module for obtaining the number of patients in hospital per day is used to predict the number of patients in hospital per day after the first time period based on the number of new patients in the epidemic per day, the target number of patients in hospital, and the discharge cycle of the patients in hospital; An early warning module is used to determine a target time point when the number of inpatients exceeds a target inpatient number range based on the daily number of inpatients, so as to issue an early warning prompt for medical resources based on the target time point; The module for obtaining the number of confirmed cases includes: A first attribute feature acquisition module configured to acquire a first attribute feature of a first region at a first time; A first prevention and control measures combination acquisition module configured to acquire a first response strategy combination; a target prediction vector generation module configured to normalize each response strategy in the first response strategy combination according to the execution strength of each response strategy to generate a target response strategy vector, and normalize each attribute feature in the first attribute feature to generate a target attribute vector; and generate a target prediction vector based on the target response strategy vector and the target attribute vector; a prediction module configured to process the target prediction vector through a pre-trained neural network model, obtain the ratio of the effective reproduction number of the epidemic population corresponding to the first region after the implementation of the first response strategy combination for the tth day to the effective reproduction number of the epidemic population corresponding to the first time, and predict the first effective reproduction number of the epidemic population corresponding to the first region after the implementation of the first response strategy combination for the tth day under the first attribute feature based on the ratio, wherein the neural network model includes a progressive gradient regression tree; the first response strategy combination whose first effective reproduction number of the epidemic is less than a target threshold is used as the first effective response strategy combination corresponding to the first region at the first time, and t is an integer greater than or equal to 1; when the first effective reproduction number of the epidemic is greater than the target threshold, obtain the influence value of each response strategy in the first response strategy combination on the first effective reproduction number of the epidemic population, and optimize the response strategies in the first response strategy combination according to the influence value; The pre-trained neural network model is obtained by: Pre-collecting the second response strategy combination adopted by the second region after adjusting the response strategy for the target epidemic at the second time, and the second attribute characteristics of the second region at the second time point; Generate a target training vector for training a neural network model according to the second coping strategy combination and the second attribute feature; The neural network model is trained using the target training vector and the second epidemic control index of the second region after implementing the second response strategy as training labels. The second epidemic control index is used to represent the ratio of the effective reproduction number of the epidemic corresponding to the second region after the implementation of the second response strategy combination on the tth day to the effective reproduction number of the epidemic corresponding to the second time.

5. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images