Rainy day subway passenger flow early warning method and electronic device

Abstract

The application provides a rain day subway passenger flow early warning method and electronic equipment. The method comprises the following steps: obtaining relevant subway stations and relevant time periods of the relevant subway stations arriving at a target subway station in a target time period. Passengers arriving at the relevant subway stations in the relevant time periods can arrive at the target subway station in the target time period; obtaining the actual umbrella-carrying probability of the passengers arriving at the relevant subway stations in the relevant time periods according to meteorological data; obtaining the off-station probability according to the real-time rainfall of the target subway station in the target time period and the actual umbrella-carrying probability; obtaining the total number of stranded passengers in the target time period based on the off-station probability and the number of passengers arriving at the target subway station in the target time period; and initiating early warning when the total number of stranded passengers is greater than a carrying threshold. In this way, the total number of stranded passengers of the subway station is predicted in real time, and early warning is carried out accordingly, so that the sudden passenger flow can be managed and guided in time and effectively, the passenger flow management level of the subway station under sudden weather conditions is improved, and the safety risk is reduced.

Description

Technical Field

[0001] The present application relates to the field of data processing, and more specifically, to a method and electronic equipment for warning subway passenger flow on rainy days. Background Art

[0002] With the continuous advancement of urbanization, subways have become one of the most important means of public transportation in metropolitan areas. Their passenger volume and operational efficiency are crucial to the efficient operation of cities. Due to the impact of global climate change and urban microclimates, localized showers are becoming more frequent in major cities. The sudden and localized nature of these weather phenomena makes it difficult for subway passengers to obtain timely and comprehensive real-time weather information. It's common for subway passengers to arrive at a station to find clear skies only to be caught in a downpour upon leaving.

[0003] Subway station exits are typically connected directly to the ground level via escalators, but access to sheltered areas is limited. During showers, large numbers of passengers gather near the exits, waiting for the rain to subside or stop before leaving. In these situations, the exits are insufficient to accommodate these large numbers of passengers, hindering their flow and causing congestion within the station. This excessive congestion can easily lead to safety accidents such as stampedes. Currently, relying on manual monitoring and guidance, as well as entrance and exit flow control, makes it difficult to manage and direct sudden passenger flows in a timely and effective manner, and lacks targeted early warning and response mechanisms. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a rainy day subway passenger flow warning method and electronic equipment, which can predict the number of stranded passengers in the subway station in real time and issue targeted warnings, which helps to manage and guide sudden passenger flows in a timely and effective manner.

[0005] In order to achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, the present application provides a method for warning subway passenger flow on rainy days, the method comprising:

[0007] Obtain relevant subway stations that can reach the target subway station within the target time period, as well as relevant time periods for each relevant subway station; wherein, passengers who enter the relevant subway stations during the relevant time periods can reach the target subway station within the target time period;

[0008] For each of the relevant subway stations, obtaining, based on meteorological data, an actual probability of passengers entering the relevant subway station carrying umbrellas during a relevant time period;

[0009] Obtaining a passenger's departure probability within the target period based on the real-time rainfall at the target subway station within the target period and the actual umbrella-carrying probability;

[0010] obtaining a total number of the passengers stranded in the target period based on the off-station probability and the number of passengers arriving at the target subway station in the target period;

[0011] initiating a warning if the total number of the passengers stranded is greater than a carrying threshold.

[0012] Optionally, the step of obtaining the total number of the passengers stranded in the target period based on the off-station probability and the number of passengers arriving at the target subway station in the target period comprises:

[0013] obtaining a number of new passengers stranded in the target period based on the off-station probability and the number of passengers arriving at the target subway station in the target period;

[0014] obtaining an initial total stranded number by integrating the number of new passengers stranded in the target period and a number of original passengers stranded before the target period;

[0015] obtaining the total number of the passengers stranded in the target period based on the off-station probability and the initial total stranded number.

[0016] Optionally, the step of obtaining the actual umbrella-carrying probability of the passengers entering the relevant subway station in the relevant period based on the meteorological data comprises:

[0017] obtaining accumulated rainfall of the relevant subway station up to the relevant period and real-time rainfall of the relevant subway station in the relevant period based on the meteorological data;

[0018] obtaining the actual umbrella-carrying probability of the passengers entering the relevant subway station based on the real-time rainfall of the relevant subway station in the relevant period and the accumulated rainfall.

[0019] Optionally, the step of obtaining the actual umbrella-carrying probability of the passengers entering the relevant subway station based on the real-time rainfall of the relevant subway station in the relevant period and the accumulated rainfall comprises:

[0020] obtaining a no-rain umbrella-carrying probability based on the accumulated rainfall and a historical maximum rainfall in the relevant period if the real-time rainfall of the relevant subway station in the relevant period is greater than a no-rain lower threshold and less than an umbrella-carrying rainfall threshold;

[0021] obtaining the actual umbrella-carrying probability of the passengers entering the relevant subway station based on the no-rain umbrella-carrying probability and a ratio between the real-time rainfall and the umbrella-carrying rainfall threshold.

[0022] Optionally, the step of obtaining the no-rain umbrella-carrying probability based on the accumulated rainfall and a historical maximum rainfall in a target period comprises:

[0023] taking a ratio between the accumulated rainfall and the historical maximum rainfall as a rainfall ratio.

[0024] From the rainfall ratio and one, the minimum value is taken as the probability of wearing an umbrella without rain in the rainless scenario.

[0025] Optionally, the step of obtaining the passenger's departure probability within the target period based on the real-time rainfall at the target subway station within the target period and the actual umbrella-carrying probabilities includes:

[0026] Obtaining a first probability value of passengers leaving the station without umbrellas based on the real-time rainfall at the target subway station during the target period, a light rain threshold, and the passenger's sensitivity to rainfall;

[0027] Obtaining a second probability value of a passenger with an umbrella leaving the station based on the real-time rainfall at the target subway station during the target period, the maximum rainfall tolerance for passengers with umbrellas, and the passenger's sensitivity to rainfall;

[0028] Obtaining a proportion of all passengers arriving at the target subway station carrying umbrellas based on the number of passengers arriving at the target subway station from each of the relevant subway stations and the actual probability of carrying umbrellas;

[0029] The probability of passengers leaving the station within the target time period is obtained according to the proportion of passengers carrying umbrellas, the first probability value, and the second probability value.

[0030] Optionally, the step of obtaining the proportion of all passengers carrying umbrellas arriving at the target subway station based on the number of passengers arriving at the target subway station from each of the relevant subway stations and each actual probability of carrying umbrellas includes:

[0031] For each of the relevant subway stations, a number of passengers carrying umbrellas is obtained according to the number of passengers arriving at the target subway station from the relevant subway station and the actual probability of carrying umbrellas at the relevant subway station;

[0032] The total number of passengers arriving at the target subway station is obtained by summarizing the number of passengers arriving at the target subway station from each of the related subway stations;

[0033] According to the number of people carrying umbrellas and the total number of passengers arriving at the station, the proportion of all passengers arriving at the target subway station carrying umbrellas is obtained.

[0034] Optionally, the calculation formula for the second probability value of the parachute passenger leaving the station includes:

[0035]

[0036] Among them, P leave_with_umbrella (i, t) represents the second probability value of the target subway station i in the target period t, W i (t) represents the real-time rainfall of the target subway station i in the target period t, β represents the second sensitivity coefficient of passengers to rainfall, W comfort Indicates the maximum rainfall an umbrella can withstand.

[0037] Optionally, the calculation formula for the first probability value of the passenger leaving the station without an umbrella includes:

[0038]

[0039] Among them, P leave_no_umbrella (i, t) represents the first probability value of the target subway station i in the target period t, W i (t) represents the real-time rainfall of the target subway station i in the target period t, α represents the first sensitivity coefficient of passengers to rainfall, W small Characterizes the rainfall threshold for light rain days.

[0040] In a second aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method for warning subway passenger flow on rainy days as described in the first aspect.

[0041] In a third aspect, the present application provides a rainy day subway passenger flow warning device, comprising a pre-processing module, a probability prediction module, a detention prediction module and a warning execution module;

[0042] The pre-processing module is used to obtain relevant subway stations that can reach the target subway station within the target time period, and the relevant time period of each relevant subway station; wherein, passengers who enter the relevant subway stations during the relevant time period can reach the target subway station within the target time period;

[0043] The probability prediction module is used to obtain, for each of the relevant subway stations, the actual probability of passengers entering the relevant subway station carrying umbrellas during the relevant time period based on meteorological data;

[0044] The probability prediction module is further configured to obtain a probability of passengers leaving the station within the target period based on the real-time rainfall at the target subway station within the target period and the actual probability of carrying an umbrella;

[0045] The detention prediction module is configured to obtain the total number of stranded passengers in a target period based on the departure probability and the number of passengers arriving at the target subway station in the target period;

[0046] The warning execution module is used to initiate a warning when the total number of stranded passengers is greater than a carrying threshold.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the rainy day subway passenger flow warning method as described in the first aspect.

[0048] The subway passenger flow early warning method and the electronic device provided by the embodiment of the application, the method comprises: obtaining relevant subway stations and relevant time periods of the relevant subway stations arriving at a target subway station in a target time period, passengers arriving at the relevant subway stations in the relevant time periods can arrive at the target subway station in the target time period; for each relevant subway station, obtaining an actual umbrella-carrying probability of the passengers arriving at the relevant subway station in the relevant time period according to meteorological data; obtaining an off-station probability of the passengers in the target time period according to real-time rainfall of the target subway station in the target time period and each actual umbrella-carrying probability; obtaining a total number of stranded passengers in the target time period based on the off-station probability and the number of passengers arriving at the target subway station in the target time period; and initiating early warning in the case that the total number of stranded passengers is greater than a bearing threshold. In this way, the total number of stranded passengers of the target subway station is predicted in real time according to the weather of the relevant subway stations and the real-time rainfall of the target subway station, and early warning is carried out accordingly, thereby helping to timely and effectively manage and guide the sudden passenger flow, improving the passenger flow management level of the subway station under sudden weather conditions, reducing the safety risk, and improving the travel experience of passengers.

[0049] In order to make the above objectives, characteristics and advantages of the present application more apparent, clear and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are referred to for detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0051] Figure 1 The system architecture schematic diagram of the subway passenger flow early warning system provided by the embodiment of the present application is shown.

[0052] Figure 2 The module architecture schematic diagram of the electronic device provided by the embodiment of the present application is shown.

[0053] Figure 3 The flow schematic diagram of the subway passenger flow early warning method provided by the embodiment of the present application is shown.

[0054] Figure 4 The flow schematic diagram of the part of the sub-steps of step 13 in the method is shown. Figure 3 The flow schematic diagram of the part of the sub-steps of step 13 in the method is shown.

[0055] Figure 5 The flow schematic diagram of the part of the sub-steps of step 133 in the method is shown. Figure 4 The flow schematic diagram of the part of the sub-steps of step 133 in the method is shown.

[0056] Figure 6 The flow schematic diagram of the part of the sub-steps of step 133 in the method is shown. Figure 3 2. Flowchart 2 of some sub-steps of step 13.

[0057] Figure 7 Shown Figure 3 One of the flow charts of some sub-steps of step 15 in FIG.

[0058] Figure 8 Shown Figure 7 Flow chart of some sub-steps of step 155.

[0059] Figure 9 Shown Figure 3 One of the flow charts of some sub-steps of step 17 in FIG.

[0060] Figure 10 A schematic diagram of the module architecture of the rainy day subway passenger flow warning device provided in an embodiment of the present application is shown.

[0061] Icons: 10- Passenger flow warning system; 110- Meteorological monitoring equipment; 120- Passenger flow monitoring equipment; 130- Data service equipment; 140- Central service equipment; 150- Warning equipment; 20- Electronic equipment; 210- Memory; 220- Processor; 230- Communication module; 30- Rainy day subway passenger flow warning device; 310- Preprocessing module; 320- Probability prediction module; 330- Detention prediction module; 340- Warning execution module. DETAILED DESCRIPTION

[0062] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0063] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present application.

[0064] It should be noted that the relational terms herein, such as first and second and the like, are used solely to distinguish one from another entity or action, without necessarily requiring or implying any actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element preceded by "comprises... " does not exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0065] The subway passenger flow early warning method provided by the embodiments of the present application can be applied to the passenger flow early warning system 10 shown in the figure. Figure 1 The passenger flow early warning system 10 includes a meteorological monitoring device 110, a passenger flow monitoring device 120, a data service device 130, a central service device 140, and an early warning device 150. The central service device 140 is in communication connection with the meteorological monitoring device 110, the passenger flow monitoring device 120, the data service device 130, and the early warning device 150 through wired or wireless means.

[0066] Each subway station is installed with the meteorological monitoring device 110, the passenger flow monitoring device 120, and the early warning device 150.

[0067] The passenger flow monitoring device can be a camera, an infrared sensor, or any other device capable of human body detection. The early warning device 150 can be an electronic display screen, a broadcast system, a station console, or any other early warning device 150. The central service device 140 can be a standalone server, a server cluster, a cloud server, or any other device capable of data processing and calculation. The data service device 130 can be a server, a computer, or any other device capable of data reading. The meteorological monitoring device 110 can be a rainfall sensor or any other device capable of obtaining rainfall, rainfall intensity, and other information.

[0068] The meteorological monitoring device 110 is installed around the subway station to collect real-time meteorological data, including rainfall, rainfall intensity, and other information.

[0069] The passenger flow monitoring device 120 is installed at the exit of the subway station to count the number of passengers entering the station in real time. In addition, the number of passengers leaving the station and the number of people staying can also be counted.

[0070] The data service device 130 is used to collect real-time meteorological data through Internet of Things technology and transmit it to the central server. It is also used to save historical meteorological data, historical passenger flow data of each subway station, and parameter configuration of the calculation model.

[0071] The central service device 140 is used to implement the rainy day subway passenger flow warning method provided in the embodiment of the present application, including: obtaining relevant subway stations and their relevant time periods that arrive at the target subway station within the target time period, so that passengers entering the station during the relevant time periods at the relevant subway stations can arrive at the target subway station within the target time period; for each relevant subway station, based on meteorological data, obtaining the actual umbrella-carrying probability of passengers entering the relevant subway station during the relevant time period; obtaining the departure probability of passengers during the target time period based on the real-time rainfall at the target subway station during the target time period and the actual umbrella-carrying probability; obtaining the total number of stranded passengers during the target time period based on the departure probability and the number of passengers arriving at the target subway station during the target time period; and initiating a warning to the warning device 150 of the target subway station when the total number of stranded passengers is greater than the load threshold.

[0072] The early warning device 150 is connected to the control terminal of the subway operation center, and is used to issue early warning information and guidance measures when receiving the early warning transmitted by the central service device 140. It can also implement management emergency plans and passenger flow diversion measures.

[0073] Please refer to Figure 2 , is a block diagram of an electronic device 20, which may be Figure 1 The central service device 140 in the passenger flow warning system 10 is shown. The electronic device 20 includes a memory 210, a processor 220, and a communication module 230. The memory 210, processor 220, and communication module 230 are electrically connected to each other, either directly or indirectly, to enable data transmission or interaction. For example, these components can be electrically connected via one or more communication buses or signal lines.

[0074] The memory 210 is used to store programs or data and can be, but is not limited to, a random access memory, a read-only memory, a programmable read-only memory, an erasable read-only memory, an electrically erasable read-only memory, etc.

[0075] The processor 220 is used to read / write data or programs stored in the memory 210 and execute corresponding functions. For example, Figure 1 In the passenger flow warning system 10 shown, the processor 220 of the central service device 140 executes the computer program stored in the memory 210 to implement the rainy day subway passenger flow warning method provided in the embodiment of the present application.

[0076] The communication module 230 is used to establish a communication connection between the electronic device 20 and other communication terminals through the network, and to send and receive data through the network. Figure 1In the passenger flow warning system 10 shown, the communication module 230 of the central service device 140 communicates with the meteorological monitoring device 110, the passenger flow monitoring device 120, the data service device 130 and the warning device 150 through the network to transmit and receive data.

[0077] It should be understood that Figure 2 The structure shown is only a schematic diagram of the structure of the electronic device 20. The electronic device 20 may also include Figure 2 More or fewer components than shown, or with Figure 2 Different configurations shown. Figure 2 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0078] In order to solve the problem that related technologies are difficult to timely and effectively manage and guide the sudden passenger flow of subway stations, and lack targeted early warning and response mechanisms, the embodiment of the present application provides a rainy day subway passenger flow early warning method, referring to Figure 3 , including steps 11 to 19. And, Figure 2 In the passenger flow warning system 10 shown in FIG, the central service device 140 is used to Figure 2 In the structure shown, when the processor 220 reads the computing program stored in the memory 210, steps 11 to 19 are implemented.

[0079] Step 11: Obtain relevant subway stations that can reach the target subway station within the target time period, and the relevant time period of each relevant subway station.

[0080] Among them, passengers who enter the relevant subway stations during the relevant time periods can reach the target subway stations within the target time periods.

[0081] Step 13: For each relevant subway station, based on the meteorological data, obtain the actual probability of passengers carrying umbrellas at the relevant subway station during the relevant time period.

[0082] Step 15: Obtain the probability of passengers leaving the station during the target period based on the real-time rainfall at the target subway station during the target period and the actual probability of carrying an umbrella.

[0083] Step 17: Based on the departure probability and the number of passengers arriving at the target subway station during the target period, the total number of stranded passengers during the target period is obtained.

[0084] Step 19: When the total number of stranded passengers is greater than the carrying threshold, initiate an early warning.

[0085] Exemplarily, for any city with subways, the city has N subway stations, N is a positive integer and N≥2, and in a day, the start time of subway station i is start(i), and the end time of subway station i is end(i). Therefore, the total operation time of the entire subway network of the city is L=max(end(i))-min(start(i)), unit: minute, max(end(i)) represents the latest end time of all subway stations, and min(start(i)) represents the earliest start time of all subway stations.

[0086] The operation time of the subway station is divided into X operation periods, i.e. The operation period number is represented by t, t is a positive integer and 1≤t≤X, where t=1 corresponds to the time range of [min(start(i), min(start(i)+T), t=2 corresponds to the time range of [min(start(i)+T, min(start(i)+2T), t=3 corresponds to the time range of [min(start(i)+2T, min(start(i)+3T), and each operation period is sequentially.

[0087] In combination with Figure 1 The passenger flow early warning system 10 shown in the figure, the meteorological monitoring equipment 110 of each subway station obtains the real-time rainfall of the location of the subway station, the data service equipment 130 obtains the meteorological data of each location in the city, and the passenger flow monitoring equipment 120 of each subway station obtains the number of passengers entering the station in real time.

[0088] At the same time, the central service equipment 140 opens a passenger flow early warning task for each subway station, and takes the upcoming operation period as the target period. For each passenger flow early warning task, the corresponding subway station is the target subway station, and in the passenger flow early warning task, the central service equipment 140 first obtains the relevant subway stations that passengers can reach the target subway station within the target period according to the travel time of the passengers from the remaining subway stations to the target subway station, and obtains the relevant period of each relevant subway station. For example, if the travel time of passengers from subway station j to target subway station i is D ji , and the target period is t, then the relevant period of subway station j can be represented as t-D ji .

[0089] For each passenger flow warning task, the central service device 140, based on meteorological data, determines the actual umbrella-carrying probability of passengers entering each relevant subway station during the target period. Simultaneously, the central service device 140 determines the departure probability of passengers during the target period based on the real-time rainfall at the target subway station and the actual umbrella-carrying probability. Furthermore, the central server can determine the total number of stranded passengers during the target period based on the departure probability and the number of passengers arriving at the target subway station during the target period. If the total number of stranded passengers exceeds the load threshold, the central service device 140 initiates a warning to the warning device 150 at the target subway station.

[0090] The early warning device 150 responds to the early warning issued by the central service device 140, issues early warning information and guidance measures, and implements any one or more of the early warning and guidance mechanisms such as emergency management plans and passenger flow diversion measures to divert passenger flow in the subway station.

[0091] The rainy day subway passenger flow warning method provided in the embodiment of the present application, in the above-mentioned steps 11 to 19, predicts the total number of stranded passengers at the target subway station in real time based on the weather of the relevant subway station and the real-time rainfall at the target subway station, and issues targeted warnings, thereby facilitating timely and effective management and guidance of sudden passenger flows, improving the passenger flow management level of subway stations under sudden weather conditions, reducing safety risks, and improving passengers' travel experience.

[0092] In the above step 11, the central server can obtain the timetable of each train and determine the relevant subway stations where the passenger can reach the target subway station within the target period according to the time when the train arrives at each subway station and the target period. Alternatively, the central server can determine the travel time D of the passenger from subway station j to target subway station i. ji , the target period is t, and tD ji If there is a train from subway station j to target subway station i, subway station j is regarded as the related subway station of target subway station i.

[0093] Alternatively, the travel time from various subway stations to the target subway station, train schedules, and target time periods can be input into a pre-established subway operation model, which can then be used to infer the relevant subway stations for the target subway station. The subway operation model can be generated using digital twins or deep learning techniques to simulate the operation of urban subways.

[0094] The above-mentioned several methods of obtaining related subway stations of the target subway station are merely examples, and the implementation methods are not limited.

[0095] After determining the relevant subway stations for the target subway station within the target time period and the relevant time period for the relevant subway stations using the above method, in step 13, the actual umbrella-carrying probability of passengers entering the relevant subway stations during the relevant time period can be obtained using any feasible method. For example, rainfall can be obtained based on meteorological data, and the actual umbrella-carrying probability corresponding to the rainfall can be retrieved from the subway station's umbrella-carrying probability curve. The umbrella-carrying probability curve is a curve representing the relationship between rainfall and actual umbrella-carrying probability, obtained by fitting historical data and / or experimental data from the railway station. Alternatively, meteorological data can be input into a pre-trained umbrella-carrying simulation model, and the actual umbrella-carrying probability can be inferred using the umbrella-carrying simulation model. The implementation method is not limited.

[0096] In order to make the actual probability of carrying an umbrella more accurate, the concept of combining the real-time rainfall and the accumulated rainfall to obtain the actual probability of carrying an umbrella is introduced in step 13. For example, referring to Figure 4 The process of obtaining the actual probability of carrying an umbrella in step 13 includes steps 131 to 133.

[0097] Step 131 , based on meteorological data, obtain the cumulative rainfall at the relevant subway station up to the relevant time period and the real-time rainfall at the relevant subway station during the relevant time period.

[0098] Step 133 : obtaining the actual probability of passengers carrying umbrellas at the relevant subway station according to the real-time rainfall and cumulative rainfall at the relevant subway station during the relevant time period.

[0099] In step 131, the accumulated rainfall may be the accumulated rainfall from the start of the rain to the relevant period, or the accumulated rainfall from the early morning of the same day to the relevant period.

[0100] When the cumulative rainfall is the cumulative rainfall from the early morning of the same day to the relevant period, the cumulative rainfall is the sum of the real-time rainfall from the early morning to the real-time rainfall before the relevant period, which can be expressed as: T=tD ji , where T represents the relevant time period of the relevant subway station j, R cumulative (j, T-1) represents the cumulative rainfall at the relevant subway station j from early morning to T-1, R0 represents the cumulative rainfall from early morning to the start of operation of the subway station in one day, in millimeters (mm), W j (k) Represents the real-time rainfall before the relevant period.

[0101] When the cumulative rainfall is the cumulative rainfall from the start of the rain to the relevant time period, the calculation method of the cumulative rainfall is consistent with the above method and will not be repeated here.

[0102] After obtaining the cumulative rainfall at the relevant subway station up to the relevant time period in step 131, in step 133, the ratio between the cumulative rainfall and the umbrella-carrying rainfall threshold can be used as the actual umbrella-carrying probability. Alternatively, the coefficient corresponding to the real-time rainfall during the relevant time period can be used as a correction factor, and the ratio between the cumulative rainfall and the umbrella-carrying rainfall threshold can be multiplied by the correction factor to obtain the actual umbrella-carrying probability. The above implementations are merely examples, and the implementation is not limited thereto.

[0103] In order to make the actual probability of carrying an umbrella more consistent with the actual situation, that is, more accurate, in step 133, the concept of obtaining the actual probability of carrying an umbrella based on the cumulative rainfall in a rainless scenario and obtaining the actual probability of carrying an umbrella based on the real-time rainfall and the cumulative rainfall in a rainy scenario is introduced.

[0104] For example, a lower rain threshold and an umbrella-carrying rainfall threshold can be pre-determined based on historical or experimental data. The lower rain threshold can be 0 mm of real-time rainfall, or 2 mm, for example. When the real-time rainfall is greater than the lower rain threshold, it indicates rain; otherwise, it indicates no rain. The umbrella-carrying rainfall threshold indicates that all passengers carry umbrellas. When the real-time rainfall is less than the umbrella-carrying rainfall threshold, it indicates that some passengers carry umbrellas while others do not. Otherwise, all passengers wear umbrellas.

[0105] In step 133, if the real-time rainfall at the relevant metro station during the relevant period is greater than the umbrella-carrying rainfall threshold, the actual umbrella-carrying probability of passengers entering the relevant metro station during the relevant period is set to 1. If the real-time rainfall at the relevant metro station during the relevant period is not greater than the rain lower threshold, that is, if there is no rain during the relevant period, the umbrella-carrying probability in the absence of rain is obtained based on the accumulated rainfall and the historical maximum rainfall. In this case, the umbrella-carrying probability in the absence of rain is the actual umbrella-carrying probability.

[0106] When the real-time rainfall at the relevant subway station during the relevant period is greater than the lower limit threshold for rain and less than the threshold for carrying an umbrella, the idea of ​​combining the probability of carrying an umbrella without rain, the real-time rainfall and the threshold for carrying an umbrella is introduced to obtain the actual probability of carrying an umbrella. Figure 5 , this process includes steps 1331 to 1333.

[0107] Step 1331: Obtain the probability of wearing an umbrella when there is no rain based on the accumulated rainfall and the historical maximum rainfall.

[0108] Step 1333 : Based on the probability of carrying an umbrella when there is no rain and the ratio between the real-time rainfall and the rainfall threshold for carrying an umbrella, obtain the actual probability of passengers entering the relevant subway station carrying an umbrella during the relevant time period.

[0109] Among them, the maximum historical rainfall refers to the maximum rainfall within a historical period of equal length to the relevant time period.

[0110] In the above process, the probability of wearing an umbrella without rain can be the ratio between the accumulated rainfall and the historical maximum rainfall, or any other feasible calculation method.

[0111] In order to avoid the situation where the probability of not wearing an umbrella exceeds the limit when the accumulated rainfall is too large, the idea of ​​taking the smaller of the ratio between the accumulated rainfall and the historical maximum rainfall is introduced in the calculation of the probability of not wearing an umbrella. Figure 6 In the above process of step 13, the probability of wearing an umbrella without rain is obtained through steps 21 to 23.

[0112] Step 21: The ratio between the accumulated rainfall and the historical maximum rainfall is used as the rainfall ratio.

[0113] Step 23, take the minimum value from the rainfall ratio and one as the probability of wearing an umbrella in the rainless scenario.

[0114] The process from step 21 to step 23 can be expressed as follows: R max Represents the maximum rainfall in history, P umb_no_rain (j,T) represents the probability of wearing an umbrella without rain.

[0115] By taking the smaller value, we can avoid exceeding the limit of the probability of wearing an umbrella when there is no rain, and ensure that the probability of wearing an umbrella when there is no rain is consistent with people's actual umbrella-wearing rules, making the probability of wearing an umbrella when there is no rain more accurate.

[0116] Similarly, in order to avoid exceeding the limit and ensure that the probability of carrying an umbrella conforms to people's actual umbrella-carrying rules, in step 1333: obtain the probability difference between one (i.e., the full probability value) and the probability of carrying an umbrella when there is no rain, and take the minimum value from the real-time rainfall and the umbrella-carrying rainfall threshold; calculate the ratio between the minimum value and the umbrella-carrying rainfall threshold, and multiply the ratio by the probability difference to obtain the probability of carrying an umbrella when there is rain; combine the probability of carrying an umbrella when there is rain with the probability of carrying an umbrella when there is no rain to obtain the actual probability of passengers entering the relevant subway station with umbrellas during the relevant time period.

[0117] In this process, the calculation formula for the actual probability of carrying an umbrella can be: Among them, P umb_rain (j,T) represents the probability of carrying an umbrella, W th Characterize the umbrella rainfall threshold, P umb_no_rain (j,T) represents the probability of no rain with umbrella, W j (T) represents the real-time rainfall at the relevant subway station during the relevant period.

[0118] Based on the above process, the actual probability of carrying an umbrella can also be expressed as follows: Among them, W0 represents the lower limit of rain, P umbrella(j,T) represents the actual probability of carrying an umbrella.

[0119] Through steps 131 to 133 and their related implementations, in rainless scenarios, the actual probability of a passenger carrying an umbrella upon entering the station depends on the cumulative rainfall for the day. That is, the greater the cumulative rainfall, the greater the actual probability of carrying an umbrella, and vice versa. In rainy scenarios, however, the actual probability of carrying an umbrella is determined by both the real-time rainfall during the relevant time period and the cumulative rainfall for the day. This makes the actual probability of carrying an umbrella more consistent with people's umbrella-carrying habits, significantly improving its accuracy.

[0120] After obtaining the actual umbrella-carrying probability, any feasible method can be used in step 15 to determine the departure probability of passengers departing the target subway station during the target time period. For example, the real-time rainfall at the target subway station and the actual umbrella-carrying probability of passengers entering each subway station during the relevant time period can be input into a pre-built subway operation model, and the departure probability can be inferred using the subway operation model. Alternatively, the departure probability can be obtained by processing according to preset rules.

[0121] In order to make the departure probability closer to the situation and more accurate, the process of obtaining the departure probability in step 15 introduces the concept of obtaining the first probability value of passengers without umbrellas leaving the station, the second probability value of passengers with umbrellas leaving the station, and the proportion of passengers with umbrellas arriving at the station, and then obtains the departure probability. Figure 7 The process of obtaining the departure probability in step 15 includes steps 151 to 157.

[0122] Step 151 , obtaining a first probability value of a passenger leaving the station without an umbrella based on the real-time rainfall at the target subway station during the target period, the rainfall threshold for light rain, and the passenger's sensitivity to rainfall.

[0123] Step 153 , obtaining a second probability value of the passenger with an umbrella leaving the station based on the real-time rainfall at the target subway station during the target period, the maximum rainfall tolerance for passengers with umbrellas, and the passenger's sensitivity to rainfall.

[0124] Step 155 : Obtain the umbrella-carrying ratio of all passengers arriving at the target subway station based on the number of passengers arriving at the target subway station from the relevant subway station and the actual umbrella-carrying probability of each passenger.

[0125] Step 157: Obtain the probability of passengers leaving the station within the target time period based on the proportion of passengers carrying umbrellas, the first probability value, and the second probability value.

[0126] The "Light Rain Threshold" represents the maximum value within the range of rainfall thresholds for light rain, and the "Maximum Rainfall Capacity with Umbrella" represents the maximum rainfall tolerance for passengers carrying umbrellas. Both the "Light Rain Threshold" and the "Maximum Rainfall Capacity" are derived from statistical analysis of historical or experimental data, and can also be empirically determined. The specific values ​​for both are not restricted.

[0127] In step 151, the ratio between the real-time rainfall and the light rain threshold can be calculated and multiplied by a coefficient corresponding to the sensitivity level to obtain a first probability value for a passenger leaving the station without an umbrella. Alternatively, the first probability value for a passenger leaving the station without an umbrella can be inferred according to preset rules or using a deep learning model. Both of these methods are examples, and their implementation is not limited.

[0128] Considering that whether a passenger without an umbrella immediately leaves the target subway station during the target time period is related to the real-time rainfall, for example, when the real-time rainfall is sufficiently light, the passenger leaves the station immediately regardless of the weather conditions. However, when the real-time rainfall exceeds the light rain threshold, the probability of immediate departure is related to the real-time rainfall and the sensitivity to rainfall. Therefore, to make the first probability value of a passenger without an umbrella leaving the station more realistic, a fitting model is introduced in step 151 to represent the relationship between the probability of a passenger without an umbrella leaving the station immediately, the real-time rainfall, and the sensitivity to rainfall.

[0129] At this time, the calculation formula of the first probability value includes:

[0130] Among them, P leave_no_umbrella (i, t) represents the first probability value of the target subway station i in the target period t (i.e., the probability that a passenger without an umbrella leaves the station immediately), W i (t) represents the real-time rainfall of the target subway station i in the target period t, α represents the first sensitivity coefficient of passengers to rainfall, W small Characterizes the rainfall threshold for light rain days.

[0131] Similarly, whether an umbrella-carrying passenger immediately leaves the target subway station during the target time period is also related to the real-time rainfall. For example, when the real-time rainfall is less than the maximum rainfall tolerance for an umbrella, the passenger immediately leaves the station. When the real-time rainfall exceeds the maximum rainfall tolerance for an umbrella, the probability of immediate departure is related to the real-time rainfall and the passenger's sensitivity to rainfall. Therefore, to make the second probability value of an umbrella-carrying passenger leaving the station more realistic, a fitting model is introduced in step 153 to represent the relationship between the probability of an umbrella-carrying passenger immediately leaving the station, the real-time rainfall, and the passenger's sensitivity to rainfall.

[0132] At this time, the calculation formula of the second probability value includes:

[0133]

[0134] Among them, P leave_with_umbrella (i, t) represents the second probability value of the target subway station i in the target period t, W i (t) represents the real-time rainfall of the target subway station i in the target period t, β represents the second sensitivity coefficient of passengers to rainfall, W comfort Indicates the maximum rainfall an umbrella can withstand.

[0135] Through the above two formulas, we can obtain the first probability and the second probability which are closer to the actual situation and more accurate.

[0136] At the same time, in step 155, the number of passengers arriving at the target subway station from each relevant subway station and the actual probability of carrying an umbrella can be used as input to the subway operation model, and the proportion of passengers carrying umbrellas can be inferred using the model. The proportion of passengers carrying umbrellas can also be obtained according to preset rules, and the implementation method is limited by steps.

[0137] In one possible implementation, refer to Figure 8 In step 155 , the proportion of all passengers carrying umbrellas arriving at the target subway station can be obtained by following steps 1551 to 1555 .

[0138] Step 1551: For each relevant subway station, a number of people carrying umbrellas is obtained based on the number of passengers arriving at the target subway station from the relevant subway station and the actual probability of carrying umbrellas at the relevant subway station.

[0139] Step 1553: The total number of passengers arriving at the target subway station is obtained by summarizing the number of passengers arriving at the target subway station from each related subway station.

[0140] Step 1555: According to the number of passengers carrying umbrellas and the total number of passengers arriving at the station, the proportion of passengers carrying umbrellas arriving at the target subway station is obtained.

[0141] In step 1551, the median or average value of the historical number of passengers in the same time period may be taken as the number of passengers arriving at the target metro station from the relevant metro station. For example, if the target time period is from 17:30 to 18:00, the median or average value of the historical number of passengers from 17:30 to 18:00 of the previous n days may be taken.

[0142] Alternatively, the number of passengers entering the relevant metro station during the relevant period may be obtained through passenger flow monitoring data, and the value obtained by multiplying the number of passengers entering the metro station by a preset ratio may be used as the number of passengers arriving at the target metro station from the relevant metro station.

[0143] Alternatively, the number of passengers entering the relevant subway station during the relevant time period can be obtained through passenger flow monitoring data, and the number of passengers entering the station can be input into a pre-trained passenger flow simulation model, and the passenger flow simulation model can be used to infer the number of passengers arriving at the target subway station from the relevant subway station.

[0144] The above methods of obtaining the number of passengers arriving at the target subway station from the relevant subway stations are all examples, and the implementation methods are not limited.

[0145] Then, in step 1551, the number of passengers arriving at the target station from the relevant subway station is multiplied by the actual umbrella-carrying probability at the relevant subway station to obtain the number of passengers carrying umbrellas at the relevant subway station. In step 1553, the number of passengers arriving at the target subway station corresponding to each relevant subway station is added together to obtain the total number of passengers arriving at the station.

[0146] After obtaining the total number of arrivals and the number of people carrying umbrellas at each relevant subway station, the ratio of the two can be calculated to obtain the umbrella-carrying ratio.

[0147] The umbrella ratio can be expressed as follows: P umbrella_arrival (i, t) represents the proportion of passengers carrying umbrellas who arrive at the target subway station t within the target period t, tD ji =T represents the relevant time period of the relevant subway station j, P umbrella (j,tD ji )=P umbrella (j, T) is the actual probability of carrying an umbrella, Q ji (tD ji ) represents the number of passengers who can reach the target subway station i from the relevant subway station j within the target time period, and N represents the total number of relevant subway stations.

[0148] After obtaining the first probability, the second probability, and the proportion of passengers with umbrellas in the above manner, in step 157, the proportion of passengers without umbrellas is multiplied by the first probability, the proportion of passengers with umbrellas is multiplied by the second probability, and the two products are added together to obtain the departure probability.

[0149] At this time, the probability of leaving the station can be expressed as: P leave (i,t)=P umbrella_arrival (i,t)·P leave_with_umbrella (i,t)+[1-P umbrella_arrival (i,t)]·P leave_no_umbrella (i,t).

[0150] In this way, through the above steps 151 to 157, a more accurate departure probability is obtained.

[0151] Furthermore, the method for obtaining the total number of stranded passengers in step 17 can be flexibly set. For example, the total number of passengers arriving at the target subway station during the target period can be added to the original number of stranded passengers, and the sum of the two can be multiplied by the departure probability to obtain the total number of stranded passengers. The total number of stranded passengers can also be inferred using a model, and the implementation method is not restricted.

[0152] In order to make the total number of stranded passengers in the target period more accurate, the idea of ​​simultaneously considering the number of existing stranded passengers and newly arrived passengers leaving the station is introduced in step 17. For example, referring to Figure 9 In step 17, the total number of stranded passengers in the target period is obtained through steps 171 to 175.

[0153] Step 171 : According to the departure probability and the number of passengers arriving at the target subway station during the target period, the number of newly stranded passengers during the target period is obtained.

[0154] Step 173 , the initial total number of stranded passengers is obtained by combining the number of newly stranded passengers in the target period and the number of stranded passengers before the target period.

[0155] Step 175: Obtain the total number of stranded passengers in the target period according to the departure probability and the initial total number of stranded passengers.

[0156] The total number of stranded passengers during the target period can be expressed as: N stay (i, t) = N′ stay (i, t)-N stay_leave (i, t), N′ stay (i, t) represents the initial total retention number, N stay_leave (i, t) represents the number of passengers who choose to leave among the stranded passengers.

[0157] Among them, N stay_leave (i, t) = N′ stay (i, t)·P leave (i, t), N′ stay (i, t) = N stay (i, t-1)+N stay_new (i, t), N stay_new (i, t) = N arrival (i, t)-N leave (i, t), N leave (i, t) = N arrival (i, t)·P leave (i, t), N stay (i, t-1) represents the original number of stranded passengers, N stay_new (i, t) represents the number of newly stranded passengers, N arrival (i, t) represents the total number of passengers arriving at the target subway station during the target period, N leave (i, t) represents the number of passengers who choose to leave the target subway station among the passengers who arrive at the target subway station during the target period.

[0158] Through the above steps 171 to 175, the total number of passengers arriving at the target subway station during the target period and the passengers who left the original number of stranded passengers are fully considered, so that the total number of stranded passengers during the target period is more accurate.

[0159] Then, in step 19, when N stay (i, t, satisfy N stay When (i, t) ≥ δC(i), an early warning is triggered. δ is the early warning trigger coefficient, which is a fixed value, and C(i) represents the maximum number of passengers allowed to gather at the exit of the target subway station i on rainy days.

[0160] After issuing an early warning, subway management can notify passengers of exit congestion through station announcements and electronic screens, or activate emergency plans and arrange staff to direct passenger flow, restricting exit flow if necessary. They can also set up guidance signs within the station to direct passengers to other exits or temporary shelters.

[0161] Based on the same concept as the rainy day subway passenger flow warning method, refer to Figure 10 The embodiment of the present application also provides a rainy day subway passenger flow warning device 30, including a preprocessing module 310, a probability prediction module 320, a detention prediction module 330 and a warning execution module 340, to implement the rainy day subway passenger flow warning method provided above.

[0162] The pre-processing module 310 is configured to obtain relevant subway stations that can reach the target subway station within the target time period, and the relevant time period of each relevant subway station, wherein passengers who enter the relevant subway stations within the relevant time period can reach the target subway station within the target time period.

[0163] The probability prediction module 320 is used to obtain, for each relevant subway station, the actual probability of passengers carrying umbrellas at the relevant subway station during the relevant time period based on meteorological data.

[0164] The probability prediction module 320 is further configured to obtain the probability of passengers leaving the station within the target period based on the real-time rainfall at the target subway station within the target period and the actual probability of carrying an umbrella.

[0165] The detention prediction module 330 is configured to obtain the total number of stranded passengers in the target period based on the departure probability and the number of passengers arriving at the target subway station in the target period.

[0166] The warning execution module 340 is used to initiate a warning when the total number of stranded passengers is greater than a carrying threshold.

[0167] The above-mentioned rainy day subway passenger flow warning device 30, under the coordinated action of the preprocessing module 310, the probability prediction module 320, the detention prediction module 330 and the warning execution module 340, predicts the total number of stranded passengers at the target subway station in real time based on the weather of the relevant subway station and the real-time rainfall at the target subway station, and issues targeted warnings, thereby helping to manage and guide sudden passenger flows in a timely and effective manner, improving the passenger flow management level of subway stations under sudden weather conditions, reducing safety risks, and improving passengers' travel experience.

[0168] For the specific implementation and effect of the rainy day subway passenger flow warning device 30, please refer to the above description of the implementation of the rainy day subway passenger flow warning method, such as, for the specific implementation and effect of the preprocessing module 310, please refer to the description of the relevant content of step 11 above, for the specific implementation and effect of the probability prediction module 320, please refer to the description of the relevant content of step 13 and step 15 above, for the specific implementation and effect of the detention prediction module 330, please refer to the description of the relevant content of step 17 above, for the specific implementation and effect of the warning execution module 340, please refer to the description of the relevant content of step 17 above, and will not be repeated here.

[0169] Furthermore, each module of the aforementioned rainy day subway passenger flow warning device 30 may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of the processor 220 of the electronic device 20 in hardware form, or may be stored in the memory 210 of the electronic device 20 in software form, so that the processor 220 can call and execute the corresponding operations of each module to implement the rainy day subway passenger flow warning method provided above.

[0170] An embodiment of the present application also provides an electronic device 20, including a processor 220 and a memory 210, wherein the memory 210 stores a computer program that can be executed by the processor 220, and the processor 220 can execute the computer program to implement the rainy day subway passenger flow warning method provided above.

[0171] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 220, the rainy day subway passenger flow warning method proposed in the embodiment of the present application is implemented.

[0172] In summary, the rainy day subway passenger flow warning method and electronic device provided in the embodiments of the present application have at least the following beneficial effects:

[0173] (1) Real-time prediction of passenger gathering risk: Establish an early warning process that combines real-time weather data, the probability of passengers carrying umbrellas, and passenger departure behavior, etc., to calculate and predict in real time the number of passengers gathering at the exit of a specific subway station in the future;

[0174] (2) Improved the accuracy and timeliness of early warnings: By quantitatively analyzing key factors that affect passenger behavior, such as real-time rainfall, historical rainfall conditions, and the probability of passengers carrying umbrellas, the accuracy of early warnings is greatly improved, ensuring that early warnings can be issued in a timely manner before passenger gatherings form;

[0175] (3) Providing scientific passenger flow control strategies: Based on the predicted total number of stranded passengers, corresponding early warning measures and passenger flow diversion plans can be formulated, such as information release, passenger flow guidance, and coordination with ground transportation, to help subway operators effectively manage sudden passenger flows and ensure passenger safety;

[0176] (4) Scalability and adaptability: The rainy day subway passenger flow warning method has good scalability and can adapt to subway networks of different sizes and changing weather conditions. The model parameters can be adjusted according to actual conditions, and the system has extremely high flexibility.

[0177] Through the implementation of this application, it is possible to effectively make up for the shortcomings of existing technologies in terms of real-time, accuracy and pertinence, improve the passenger flow management level of subway stations under sudden weather conditions, reduce safety risks, and improve passengers' travel experience.

[0178] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. 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 consecutive boxes 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 and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0179] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0180] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0181] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A rainy day subway passenger flow early warning method, characterized in that: The method comprises: Obtain relevant subway stations that can reach the target subway station within the target time period, as well as relevant time periods for each relevant subway station; wherein, passengers who enter the relevant subway stations during the relevant time periods can reach the target subway station within the target time period; For each of the relevant subway stations, obtaining, based on meteorological data, an actual probability of passengers entering the relevant subway station carrying umbrellas during a relevant time period; Obtaining a passenger's departure probability within the target period based on the real-time rainfall at the target subway station within the target period and the actual umbrella-carrying probability; Obtaining the total number of stranded passengers in the target period based on the departure probability and the number of passengers arriving at the target subway station in the target period; When the total number of stranded passengers is greater than the carrying threshold, an early warning is initiated.

2. The rainy day subway passenger flow early warning method according to claim 1 is characterized in that: The step of obtaining the total number of stranded passengers in the target period based on the departure probability and the number of passengers arriving at the target subway station in the target period includes: Obtaining the number of newly stranded passengers during the target period based on the departure probability and the number of passengers arriving at the target subway station during the target period; The initial total number of stranded passengers is obtained by combining the number of newly stranded passengers up to the target period and the number of stranded passengers before the target period; The total number of stranded passengers in the target period is obtained according to the departure probability and the initial total number of stranded passengers.

3. The rainy day subway passenger flow early warning method according to claim 1 or 2, characterized in that: The step of obtaining, based on meteorological data, the actual probability of passengers entering the relevant subway station carrying umbrellas during the relevant time period includes: Obtaining, based on meteorological data, the cumulative rainfall at the relevant subway station up to the relevant time period, and the real-time rainfall at the relevant subway station during the relevant time period; According to the real-time rainfall and the accumulated rainfall at the relevant subway station during the relevant time period, the actual probability of passengers entering the relevant subway station carrying umbrellas is obtained.

4. The rainy day subway passenger flow early warning method according to claim 3 is characterized in that: The step of obtaining the actual probability of passengers entering the relevant subway station carrying umbrellas based on the real-time rainfall and the accumulated rainfall at the relevant subway station during the relevant time period includes: When the real-time rainfall at the relevant subway station during the relevant time period is greater than the lower limit threshold for rain and less than the rainfall threshold for carrying an umbrella, the probability of carrying an umbrella in the absence of rain is obtained based on the cumulative rainfall and the historical maximum rainfall; According to the probability of carrying an umbrella when there is no rain and the ratio between the real-time rainfall and the rainfall threshold for carrying an umbrella, the actual probability of passengers entering the relevant subway station carrying an umbrella during the relevant time period is obtained.

5. The rainy day subway passenger flow early warning method according to claim 4 is characterized in that: The step of obtaining the probability of wearing an umbrella without rain according to the accumulated rainfall and the historical maximum rainfall includes: The ratio between the accumulated rainfall and the historical maximum rainfall is taken as the rainfall ratio; From the rainfall ratio and one, the minimum value is taken as the probability of wearing an umbrella without rain in the rainless scenario.

6. The rainy day subway passenger flow early warning method according to claim 1 or 2, characterized in that: The step of obtaining the probability of passengers leaving the station within the target period according to the real-time rainfall at the target subway station within the target period and the actual probability of carrying an umbrella comprises: Obtaining a first probability value of passengers leaving the station without umbrellas based on the real-time rainfall at the target subway station during the target period, a light rain threshold, and the passenger's sensitivity to rainfall; Obtaining a second probability value of a passenger with an umbrella leaving the station based on the real-time rainfall at the target subway station during the target period, the maximum rainfall tolerance for passengers with umbrellas, and the passenger's sensitivity to rainfall; Obtaining a proportion of all passengers arriving at the target subway station carrying umbrellas based on the number of passengers arriving at the target subway station from each of the relevant subway stations and the actual probability of carrying umbrellas; The probability of passengers leaving the station within the target time period is obtained according to the proportion of passengers carrying umbrellas, the first probability value, and the second probability value.

7. The rainy day subway passenger flow early warning method according to claim 6, characterized in that: The step of obtaining the umbrella-carrying ratio of all passengers arriving at the target subway station based on the number of passengers arriving at the target subway station from each of the relevant subway stations and each of the actual umbrella-carrying probabilities includes: For each of the relevant subway stations, a number of passengers carrying umbrellas is obtained according to the number of passengers arriving at the target subway station from the relevant subway station and the actual probability of carrying umbrellas at the relevant subway station; The total number of passengers arriving at the target subway station is obtained by summarizing the number of passengers arriving at the target subway station from each of the related subway stations; According to the number of people carrying umbrellas and the total number of passengers arriving at the station, the proportion of all passengers arriving at the target subway station carrying umbrellas is obtained.

8. The rainy day subway passenger flow early warning method according to claim 6, characterized in that: The calculation formula for the second probability value of the parachute passenger leaving the station includes: in, Characterize target subway stations During the target period The second probability value of Characterize target subway stations During the target period Real-time rainfall, Characterizes the second sensitivity coefficient of passengers to rainfall, Indicates the maximum rainfall an umbrella can withstand.

9. The rainy day subway passenger flow early warning method according to claim 6, characterized in that: The calculation formula for the first probability value of the passenger leaving the station without an umbrella includes: in, Characterize target subway stations During the target period The first probability value of Characterize target subway stations During the target period Real-time rainfall, Characterizes the first sensitivity coefficient of passengers to rainfall, Characterizes the rainfall threshold for light rain days.

10. An electronic device, characterized in that: The system comprises a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the rainy day subway passenger flow warning method according to any one of claims 1 to 9.

Images