Disease propagation prediction model construction method based on inter-city comprehensive space-time distance

Abstract

The invention provides a disease transmission prediction model construction method based on a comprehensive space-time distance between cities, and the method comprises the steps: matching a station with each city in a plurality of cities on a city scale according to the name of the station in train operation timetable data; according to train number names of the trains, performing type division on the trains; according to the train operation relation and the train type between the cities, the train number of the nonstop trains between the cities is calculated; according to the train operation relation between the cities, the train operation duration between the cities is calculated; calculating a comprehensive space-time distance between the cities according to the train number and the train operation duration of the nonstop trains between the cities; and fitting a disease transmission speed prediction model by taking the comprehensive space-time distance and the direct distance between the cities as independent variables and the disease transmission data between the cities as dependent variables. According to the embodiment of the invention, the disease transmission rule can be accurately predicted from time and space dimensions at the same time.

Description

Technical Field

[0001] The present invention relates to the field of geographic information processing and disease prediction technology, and in particular to a method for constructing a disease spread prediction model based on comprehensive temporal and spatial distances between cities. Background Art

[0002] With the development of intercity transportation, rail transit, particularly railways, has become a major route for the spread of infectious diseases. Using traffic data to predict the spread of diseases, and to rationally allocate disease control resources and implement disease control measures, is a pressing issue.

[0003] Prior art applications include CN110147419A, which discloses a subway-based infectious disease diffusion analysis method and system, and CN114496265A, which discloses a method and system for modeling the spatiotemporal spread of infectious diseases within cities. However, these methods utilize subway card swipe data and mobile phone location data, both of which are private user data, creating challenges in data availability and timeliness.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The present invention provides a method for constructing a disease transmission prediction model based on the comprehensive spatiotemporal distance between cities, and uses open railway traffic data to predict the law of disease transmission.

[0006] In a first aspect, an embodiment of the present invention provides a method for constructing a disease transmission prediction model based on comprehensive spatiotemporal distances between cities, comprising:

[0007] Based on the station names in the train timetable data, the stations are matched with each city in multiple cities at the prefecture-level, thereby building the train operation relationship between the cities;

[0008] According to the train number name, trains are divided into types;

[0009] Calculate the number of direct trains between cities based on the train operation relationship and train types between cities;

[0010] Calculate the train running time between cities based on the train running relationship between cities;

[0011] Calculate the comprehensive time and space distance between cities based on the number of direct trains between cities and the train running time;

[0012] The disease transmission speed prediction model was fitted using the comprehensive spatiotemporal distance and direct distance between cities as independent variables and the disease transmission data between cities as the dependent variable.

[0013] In a second aspect, an embodiment of the present invention provides an electronic device, comprising:

[0014] one or more processors;

[0015] a memory for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for constructing a disease transmission prediction model based on the comprehensive spatiotemporal distance between cities as described in any embodiment.

[0017] In summary, the embodiment of the present invention has adopted a disease medicine method based on the comprehensive spatiotemporal distance between cities. Based on the train timetable data, it fully explores the characteristics of inter-city train operation in the time dimension and the space dimension, and integrates the operation information of different types of trains such as high-speed rail, EMU, and ordinary trains to obtain the comprehensive spatiotemporal distance between cities. This distance takes into account the train operation time and spatial train frequency, conforms to the characteristics of the joint effect of timeliness and accessibility in the actual railway transportation network, and better reflects the population mobility characteristics between cities. Based on this feature, this embodiment uses the historical spread data of the disease to fit the relationship between the disease transmission speed and the comprehensive spatiotemporal distance between cities. The resulting disease prediction model can more accurately reflect the law of disease transmission between cities, and provide data support for the targeted allocation of disease control resources and the implementation of disease control measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a flowchart of a method for constructing a disease transmission prediction model based on comprehensive spatiotemporal distance between cities, provided by an embodiment of the present invention;

[0020] Figure 2 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0022] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0023] In the description of the present invention, it should also be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0024] Figure 1 This is a flow chart of a method for constructing a disease transmission prediction model based on the comprehensive spatiotemporal distance between cities provided by an embodiment of the present invention. This method is applicable to the case of predicting the speed of disease transmission from the source city to surrounding cities, and is executed by an electronic device. Figure 1 As shown, the method specifically includes:

[0025] S110. Match the station names in the train timetable data with each of the multiple cities at the prefecture-level city level, thereby establishing a train operation relationship between the cities.

[0026] This step first obtains the open-source train schedule as the data source for the entire method. Then, based on this data source, we match stations with cities, including location and time matching, to form the train operation relationship between cities.

[0027] Optionally, first, extract the names of the stations that each train passes through from the train timetable data; then, find the city where each station is located based on the name of each station, and establish a corresponding relationship between each station and the city where it is located; finally, determine the time when each train passes through each city based on the corresponding relationship; the corresponding relationship and time together constitute the train operation relationship between the cities.

[0028] S120. Classify trains into types according to train numbers.

[0029] The train types in this embodiment include high-speed trains, motor trains, and ordinary trains. The train types can be divided by the letters in the train numbers.

[0030] Optionally, train numbers starting with the letter G are classified as high-speed rail types; train numbers starting with the letter D or the letter C are classified as EMU types; train numbers starting with other letters (including P, K, T, Z, L, Y, N, A, etc.) are classified as ordinary train types.

[0031] S130. Calculate the number of direct trains between cities based on the train operation relationship and train types between cities.

[0032] This step calculates the number of direct trains between every two cities based on the data obtained in S110 and S120.

[0033] Alternatively, taking any pair of cities a and b as an example, the number of direct trains between cities a and b can be calculated using the following formula:

[0034] SF C,ab =SF G,ab +SF D,ab +SF A,ab (1)

[0035] Among them, SF G,ab Indicates the number of direct high-speed railways between city a and city b, SF D,ab Indicates the number of direct trains between city a and city b, SF A,ab Indicates the number of direct trains between city a and city b, SF C,ab Represents the total number of three types of direct trains between city a and city b.

[0036] S140. Calculate the train running time between cities based on the train running relationship between cities.

[0037] The train travel time between cities represents the time distance between cities. The longer the distance, the easier it is for diseases to spread between cities. In one embodiment, the train travel time can be calculated in two cases:

[0038] Case 1: There are direct trains between cities. In this case, the train travel time between cities can be calculated using the following formula:

[0039] MT i,ab =Tb i,arrive -Ta i,start (2)

[0040] Among them, MT i,ab Tb represents the running time of train i from city a to city b, i,arriveIt represents the time when train i arrives at city b, Ta i,start represents the time when train i departs from city a.

[0041] Case 2: There is no direct train between cities. Considering the situation of transfers within the same city, for cities a and b, first select the transfer city c that meets the following conditions:

[0042] Condition 1: There are direct trains between city A and transit city C, and between transit city C and city A;

[0043] Condition 2: When transferring at the same station, the transfer time must be greater than 30 minutes; when transferring at different stations, the transfer time must be greater than 90 minutes.

[0044] Then, based on the above transit cities, calculate the shortest transit time from city a to city b using the following formula:

[0045] T i,ac =Tc i,arrive -Ta i,start (3)

[0046] T j,cb =Tb j,arrive -Tc j,start (4)

[0047] T k,ab =T i,ac +T ij +T j,cb (5)

[0048] MT ab =min{T 1,ab ,T 2,ab ,,T k,ab} (6)

[0049] Among them, T i,ac Tc represents the running time of train i from city a to transfer city c. i,arrive It is the time for train i to arrive at the transfer city c, Ta i,start represents the time when train i departs from city a; T j,cb Tb represents the running time of train j from transit city c to city a, j,arrive It is the time for train j to arrive at city a, Tc j,start represents the departure time of train j from the transfer city c; T k,ab T represents the total time from city a to city b via transit city c according to transit plan k, ij MF represents the time it takes to transfer from train i to train j; abrepresents the shortest time from city a to city b via transfer. The train i, train j, and transfer city c in each transfer plan k can be different.

[0050] S150. Calculate the comprehensive space-time distances between cities based on the number of direct trains between cities and the train running time, thereby completing the construction of a comprehensive transportation relationship network between cities.

[0051] This example proposes a spatiotemporal distance between cities, comprehensively measuring the relationship between cities from both temporal and spatial dimensions. This distance reflects the ease with which a disease can spread between cities and is inversely proportional to the frequency of intercity train travel and directly proportional to the average intercity train travel time.

[0052] Optionally, the time-space distance between cities can be calculated for different types of trains. Taking the time-space distance of high-speed rail as an example, the specific calculation method is:

[0053]

[0054] Among them, STD G,ab represents the high-speed rail time-space distance between city a and city b, T G,ab represents the average time of high-speed rail operation between city a and city b, SF G,ab Indicates the number of direct high-speed trains between city a and city b, MT i,ab represents the running time of high-speed train number i between city a and city b, MT ab represents the shortest transfer time between cities A and B in the high-speed rail network. The corresponding time and space distances for other types of trains are similar.

[0055] Based on the above method, we can further calculate the comprehensive temporal and spatial distance between cities, which also reflects the difficulty of disease transmission between cities and takes into account various train types. The specific calculation method is as follows:

[0056]

[0057] Among them, STD C,ab represents the comprehensive spatiotemporal distance between city a and city b, SF C,ab The total number of direct trains between city a and city b, SF G,ab Indicates the number of direct high-speed trains between city a and city b, SF D,ab Indicates the number of direct trains between city a and city b, SF A,ab Indicates the number of direct ordinary trains between city a and city b, MT G,i,ab represents the running time of high-speed train number i between city a and city b, MT D,i,abIt represents the running time of train number i between city a and city b, MT A,i,ab It represents the running time of ordinary train No. i between city a and city b, MT C,ab It is the shortest transfer time between city a and city b in the comprehensive transportation relationship network. It should be noted that MT in formula (6) ab It is a universal representation applicable to high-speed rail networks, motor vehicle networks, ordinary train networks and comprehensive space-time distance networks; that is, in high-speed rail networks, MT ab Indicates the shortest transfer time using high-speed trains; in the EMU network, MT ab The shortest transfer time using EMU trains; in the ordinary train network, MT ab Indicates the shortest transfer time using a regular train; in the integrated time-space distance network, MT ab Indicates the shortest transfer time using any type of train. C,ab Specifically refers to the shortest transfer time under the comprehensive transportation relationship network, which is only used in the comprehensive time-space distance network, equivalent to MT in the comprehensive time-space distance network. ab .

[0058] Furthermore, in order to demonstrate the effectiveness of the comprehensive spatiotemporal distance between cities constructed by this embodiment in measuring population mobility, this embodiment uses the train timetable data from 2007 to 2024 as the data source, executes the above steps S110 to S150, and calculates the daily population migration index between cities based on the daily population out-migration index and the daily out-migration population ratio data from October 1 to December 31, 2021. By performing a correlation analysis between the comprehensive spatiotemporal distance between cities and the population migration index between cities, the advantage of the comprehensive spatiotemporal distance between cities in this embodiment over other indicators is verified. Optionally, the specific calculation method of the population migration index between cities is as follows:

[0059] MI i,j =M_out i ×M_pecent i,j (9)

[0060] Among them, MI i,j represents the population migration index from city i to city j, M_out i Indicates the size of the out-migration population of city i, M_pecent i,j The migration index represents the proportion of population migration from city i to city j to the total outflow of population from city i. By averaging the daily migration index, we can obtain the average migration index from October 1 to December 31, 2021.

[0061] Then, the correlation between the inter-city population migration index and the spatiotemporal distance index, the time distance index, and the operation frequency index was calculated. The results showed that the inter-city comprehensive spatiotemporal distance index constructed in this embodiment has the strongest correlation with the actual inter-city population migration (correlation coefficient r = -0.76, significance level p < 0.01), which proves the superiority of the comprehensive spatiotemporal distance constructed in this embodiment in reflecting the intensity of inter-city population mobility.

[0062] Table 1 Correlation between inter-city population migration index and various network indicators

[0063]

[0064] S160. Using the comprehensive spatiotemporal distance and direct distance between cities as independent variables and the disease transmission data between cities as the dependent variable, fit a disease transmission speed prediction model.

[0065] In one specific implementation, historical disease transmission data can be used to first extract the time when infection cases first appeared in multiple cities surrounding the source city. The source city is the city where the earliest case was reported. For ease of distinction and description, the cities surrounding the source city are subsequently referred to as target cities.

[0066] Then, based on the time of each target city, the speed of spread of the disease to each target city is determined. For example, taking the infection case data reported by the surrounding target cities within 14 days after the outbreak of a certain infectious disease in a source city as an example, the 14 days can be divided into multiple time periods connected in sequence, and the disease spread speed of the target city where cases appear in the first time period (such as the first 3 days) is marked as very fast, the disease spread speed of the target city where cases appear in the second time period (such as the 4th to 6th day) is marked as fast, the disease spread speed of the target city where cases appear in the third time period (such as the 7th to 9th day) is marked as slow, and the disease spread speed of the target city where cases appear in the fourth time period (such as the 10th to 14th day) is marked as very slow, thereby obtaining the corresponding spread speed of each target city. Optionally, these spread speed levels can also be quantified by different numbers.

[0067] Based on this data, the speed at which the disease spreads to each target city can be used as the dependent variable, and the comprehensive spatiotemporal distance between cities, direct distance, comprehensive temporal distance, and comprehensive train frequency between cities can be used as independent variables to fit a model of the relationship between the speed of disease spread between cities using the random forest method. If the data for the independent and dependent variables are known, random forest regression modeling can be implemented using the RandomForestRegressor function in the sklearn package in Python.

[0068] The constructed model takes the combined spatiotemporal distance, direct distance, combined temporal distance, and combined train frequency between two cities as input, and outputs the speed at which a disease spreads from one city to the other. In practical applications, when a disease breaks out in a source city, the model can be used to input the combined spatiotemporal distance, direct distance, combined temporal distance, and combined train frequency of each city within a certain distance of the source city. This predicts the speed at which the disease spreads to each city, providing data support for the allocation of disease control resources and the implementation of disease control measures.

[0069] In summary, this embodiment has adopted a disease prediction method based on the comprehensive spatiotemporal distance between cities. Based on train timetable data, it fully explores the characteristics of inter-city train operation in the time and space dimensions, and integrates the operation information of different types of trains such as high-speed rail, EMU, and ordinary trains to obtain the comprehensive spatiotemporal distance between cities. This distance takes into account both the train operation time and spatial train frequency, conforms to the characteristics of the joint action of timeliness and accessibility in the actual railway transportation network, and better reflects the characteristics of population mobility between cities. In addition, this embodiment uses historical disease transmission data to fit the relationship between the disease transmission speed and the comprehensive spatiotemporal distance between cities. The resulting disease prediction model can more accurately reflect the law of disease transmission between cities, providing data support for the targeted allocation of disease control resources and the implementation of disease control measures.

[0070] Figure 2 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more. Figure 2 In the embodiment, a processor 60 is used as an example; the processor 60, the memory 61, the input device 62 and the output device 63 in the device can be connected by a bus or other means. Figure 2 The bus connection is taken as an example.

[0071] Memory 61, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for constructing a disease transmission prediction model based on comprehensive inter-city spatiotemporal distances in the embodiments of the present invention. Processor 60 executes the software programs, instructions, and modules stored in memory 61 to execute various functional applications and data processing functions of the device, thereby implementing the aforementioned method for constructing a disease transmission prediction model based on comprehensive inter-city spatiotemporal distances.

[0072] The memory 61 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. Furthermore, the memory 61 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the memory 61 may further include a memory remotely located relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0073] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

[0074] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for constructing a disease transmission prediction model based on the comprehensive spatiotemporal distance between cities according to any embodiment is implemented.

[0075] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: 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 thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by an instruction execution system, device or device or used in combination with it.

[0076] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable 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.

[0077] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0078] Computer program code for performing the operations of the present invention can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as C or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a disease transmission prediction model based on the comprehensive spatiotemporal distance between cities, characterized in that: include: Based on the station names in the train timetable data, the stations are matched with each city in multiple cities at the prefecture-level, thereby building the train operation relationship between the cities; According to the train number name, trains are divided into types; Calculate the number of direct trains between cities based on the train operation relationship and train types between cities; Calculate the train running time between cities based on the train running relationship between cities; Calculate the comprehensive time and space distance between cities based on the number of direct trains between cities and the train running time; The disease transmission speed prediction model was fitted using the comprehensive spatiotemporal distance and direct distance between cities as independent variables and the disease transmission data between cities as the dependent variable.

2. The method according to claim 1, characterized in that The method of matching the station names in the train timetable data with each of the multiple cities at the prefecture-level scale, thereby establishing a train operation relationship between the cities, includes: Extract the names of the stations that each train passes through from the train timetable data; Find the city where each site is located based on the site name, and establish a corresponding relationship between each site and the city where it is located; According to the corresponding relationship, the time for each train to pass through each city is determined; The corresponding relationship and time together constitute the train operation relationship between cities.

3. The method according to claim 1, characterized in that The trains are divided into types according to the train number name, including: Will be in letters The train numbers starting with are classified as high-speed rail types; Will be in letters or letters The train number starting with is classified as EMU type; Train numbers starting with other letters are classified as ordinary train types.

4. The method according to claim 1, wherein The number of direct trains between cities is calculated based on the train operation relationship and train type between cities, including: The number of direct trains between cities is calculated using the following formula: ； in, Indicates city and cities The number of direct high-speed rail lines between Indicates city and cities Number of direct trains between Indicates city and cities The number of direct trains between Indicates city and cities The total number of direct trains of three types.

5. The method according to claim 1, wherein The calculation of the train running time between cities based on the train running relationship between cities includes: When there are direct trains between cities, the train travel time between cities is calculated using the following formula: ； in, Indicates train From the city To the city The running time, Indicates train Arrival city time, Indicates train From the city Time of departure.

6. The method according to claim 1, characterized in that The calculation of the train running time between cities based on the train running relationship between cities includes: When there is no direct train between cities, and cities , select a transit city that meets the following conditions :City To the transit city Between, transit cities To the city There are direct trains between them; when transferring at the same station, the transfer time is greater than a first threshold; when transferring at different stations, the transfer time is greater than a second threshold, wherein the first threshold is less than the second threshold; Calculate the shortest transit time between cities using the following formula: ， ， ， ， in, Indicates train From the city To the transit city The running time, Indicates train Arrive at the transit city time, Indicates train From the city Time of departure; Indicates train From transit city To the city The running time, Indicates train Reach the city time, Indicates train From transit city Time of departure; Indicates that according to the transfer plan From the city Transit city Reach the city The total duration of Indicates from the train Transfer to train The duration of consumption; Indicates from the city Arrive at the city via transit The shortest duration.

7. The method according to claim 1, characterized in that The above method calculates the comprehensive time and space distance between cities based on the number of direct trains between cities and the train running time, including: The high-speed rail time-space distance between cities is calculated according to the following formula: ， in, Indicates city With the city The high-speed rail time and space distance between Indicates city With the city The average high-speed rail travel time between Indicates city With the city The number of direct high-speed trains between Indicates high-speed rail train number In the city With the city The running time between Represents cities in the high-speed rail network With the city The shortest transfer time between them.

8. The method according to claim 1, characterized in that The above method calculates the comprehensive time and space distance between cities based on the number of direct trains between cities and the train running time, including: ， in, Indicates city With the city The comprehensive space-time distance between Indicates city With the city The total number of direct trains between Indicates city With the city The number of direct high-speed trains between Indicates city With the city Number of direct trains between Indicates city With the city Number of direct trains between Indicates high-speed rail train number In the city With the city The running time between Indicates the train number In the city With the city The running time between Indicates ordinary train number In the city With the city The running time between Represents cities in the comprehensive transportation relationship network With the city Minimum transfer time.

9. The method according to claim 1, characterized in that The method of fitting a disease transmission speed prediction model using the comprehensive spatiotemporal distance and direct distance between cities as independent variables and the disease transmission data between cities as the dependent variable includes: From the historical spread data of a disease, extract the time when the first infection cases appeared in multiple target cities around the source city; Determine the speed at which the disease spreads from the source city to each target city based on the time of each target city; Taking the speed of each target city as the dependent variable and the comprehensive spatiotemporal distance, direct distance, comprehensive time distance and comprehensive train frequency between cities as the independent variables, a disease transmission speed prediction model between cities was fitted.

10. An electronic device, characterized in that: include: one or more processors; a memory 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 for constructing a disease transmission prediction model based on the comprehensive spatiotemporal distance between cities as described in any one of claims 1-9.

Images