An AI perception network-based traffic risk event identification analysis method

Abstract

The application discloses a traffic risk event identification analysis method based on an AI perception network, and relates to the technical field of traffic control. The method comprises the following steps: after a large interval event occurs in a current train, acquiring train data and driving route data of the current train; wherein the train data comprises state data of each train on the same driving route; determining the cause of the large interval event based on a congestion index in the driving route data, a vehicle state of the current train in the train data and a vehicle full load rate; determining an influence station range of the large interval event based on the cause of the large interval event, the driving route data and the train data; and determining a train scheduling strategy of the large interval event based on the cause of the large interval event and the influence station range of the large interval event. Thus, the processing efficiency of the large interval event is improved, the influence of the large interval event is greatly reduced, and user satisfaction is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic control, and particularly relates to a traffic risk event identification and analysis method based on an AI perception network. BACKGROUND

[0002] Large interval events relate to the riding experience of passengers and are one of the main reasons for complaints. Meanwhile, the on-time rate of departure intervals is also an evaluation index of some cities. Therefore, it is necessary to eliminate the adverse effects of large interval events as soon as possible.

[0003] Meanwhile, large interval events are common scenarios that cannot be avoided in public transport operation. However, in the past, only the departure intervals of each train were regulated, and the arrival times of all stations could not be evaluated. In actual operation, there are special situations between different stations. Even if the departure intervals of each train meet the standards, large interval events still occur. In the prior art, dispatchers generally rely on manual experience to determine the affected station, the affected time length, and the affected train, and manually decide to make up for it as much as possible by means of dispatching methods such as turning around and taking a detour. The dispatching ability of dispatchers is extremely high, the efficiency is low, and the effect is not good. SUMMARY

[0004] In the exemplary embodiments of the present application, a traffic risk event identification and analysis method based on an AI perception network is provided to improve the processing efficiency and effect of large interval events, greatly reduce the influence of large interval events, and improve user satisfaction.

[0005] According to a first aspect in the exemplary embodiments, a traffic risk event identification and analysis method based on an AI perception network is provided, comprising:

[0006] After a large interval event occurs in a current train, train data and driving route data of the current train are obtained. The train data includes state data of each train on the same driving route.

[0007] Based on the congestion index in the driving route data, the vehicle state and the vehicle full load rate of the current train in the train data, the cause of the large interval event is determined.

[0008] Based on the cause of the large interval event, the driving route data, and the train data, the affected station range of the large interval event is determined.

[0009] Based on the cause of the large interval event and the affected station range of the large interval event, a train dispatching strategy of the large interval event is determined.

[0010] According to a second aspect in the exemplary embodiments, a vehicle large interval event processing device is provided, which comprises:

[0011] an acquisition module, configured to acquire train data and driving route data of a current train after a large interval event occurs in the current train, wherein the train data comprises state data of each train on a same driving route;

[0012] a first determination module, configured to determine a cause of the large interval event based on a congestion index in the driving route data, a vehicle state of the current train in the train data, and a vehicle full load rate;

[0013] a second determination module, configured to determine an influence station range of the large interval event based on the cause of the large interval event, the driving route data, and the train data;

[0014] a third determination module, configured to determine a train scheduling strategy of the large interval event based on the cause of the large interval event and the influence station range of the large interval event.

[0015] According to a third aspect in the example embodiments, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the traffic intersection problem method by running the executable instructions.

[0016] According to a fourth aspect in the example embodiments, a computer storage medium is provided, and the computer storage medium stores computer program instructions, when the instructions are run on a computer, the computer executes the steps of the traffic intersection problem method.

[0017] In the embodiments of the present application, after a large interval event occurs in a current train, the cause of the large interval event is determined based on a congestion index in acquired driving route data, a vehicle state of the current train in train data, and a vehicle full load rate, and the influence station range of the large interval event is determined according to the cause of the large interval event, thereby improving the accuracy of the determined influence station range. Furthermore, the train scheduling strategy of the large interval event is determined based on the cause of the large interval event and the influence station range of the large interval event, thereby improving the processing efficiency and effectiveness of the large interval event, greatly reducing the influence of the large interval event, and improving user satisfaction. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1An application scenario schematic diagram provided for an embodiment of the present application;

[0020] Figure 2 A flowchart of a traffic risk event identification and analysis method based on an AI perception network provided for an embodiment of the present application;

[0021] Figure 3 A specific flowchart of a traffic risk event identification and analysis method based on an AI perception network provided for an embodiment of the present application;

[0022] Figure 4 A flowchart of a method for determining a cause of a large interval event provided for an embodiment of the present application;

[0023] Figure 5 A flowchart of a method for determining an impact station range of a large interval event when the cause of the large interval event is vehicle breakdown provided for an embodiment of the present application;

[0024] Figure 6 A schematic diagram of a travel route of a current train provided for an embodiment of the present application;

[0025] Figure 7 A flowchart of a method for determining an impact station range of a large interval event when the cause of the large interval event is road congestion provided for an embodiment of the present application;

[0026] Figure 8 A flowchart of a method for determining an impact station range of a large interval event when the cause of the large interval event is vehicle late departure provided for an embodiment of the present application;

[0027] Figure 9 A schematic diagram of a travel route of a current train provided for an embodiment of the present application;

[0028] Figure 10 A flowchart of a method for determining an impact station range of a large interval event when the cause of the large interval event is excessive passenger flow provided for an embodiment of the present application;

[0029] Figure 11 A flowchart of a method for determining an impact train range of a large interval event when the cause of the large interval event is road congestion provided for an embodiment of the present application;

[0030] Figure 12 A flowchart of a method for determining an impact train range of a large interval event when the cause of the large interval event is vehicle breakdown provided for an embodiment of the present application;

[0031] Figure 13 A flowchart of a method for determining a train scheduling strategy of a large interval event when the cause of the large interval event is road congestion provided for an embodiment of the present application;

[0032] Figure 14 A flowchart of a method for determining a corresponding train scheduling strategy based on the relationship between the multiple and the set multiple is provided for the embodiments of the present application.

[0033] Figure 15 A flowchart of a method for determining a train scheduling strategy for a large interval event when the cause of the large interval event is vehicle failure is provided for the embodiments of the present application.

[0034] Figure 16 A flowchart of a method for determining a train scheduling strategy for a large interval event when the cause of the large interval event is vehicle late departure is provided for the embodiments of the present application.

[0035] Figure 17 A structural schematic diagram of a vehicle large interval event processing device is provided for the embodiments of the present application.

[0036] Figure 18 A structural schematic diagram of a vehicle large interval event processing device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0037] To make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0038] Large interval events are related to the passenger riding experience and are one of the main reasons for complaints. At the same time, the on-time rate of departure interval is also an evaluation index in some cities. Therefore, it is necessary to eliminate the adverse effects of large interval events as soon as possible.

[0039] At the same time, large interval events are common scenarios that cannot be avoided in public transportation operation. However, in the past, only the departure interval of each train was specified, and it was impossible to evaluate the arrival time at all stations. In actual operation, there are special situations between different stations. Even if the departure interval of each train meets the standard, large interval events still occur. In the prior art, dispatchers generally rely on manual experience to determine the affected station, the affected time length, and the affected train, and manually decide to compensate as much as possible through scheduling methods such as turning around and taking a detour. The scheduling ability of the dispatcher is extremely high, the efficiency is low, and the effect is not good.

[0040] Therefore, the embodiments of the present application provide a traffic risk event identification and analysis method based on an AI perception network to improve the processing efficiency and effect of large interval events, greatly reduce the impact of large interval events, and improve user satisfaction.

[0041] To further illustrate the technical solutions provided by the embodiments of the present application, the following will describe in detail in conjunction with the drawings and specific embodiments. Although the embodiments of the present application provide the method operation steps as described in the following embodiments or shown in the drawings, more or less operation steps can be included in the method based on conventional or non-creative labor. The execution order of the steps which have no necessary causal relationship in logic is not limited to the execution order provided by the embodiments of the present application.

[0042] First refer to Figure 1 which is a schematic diagram of the application scenario of the embodiments of the present application, including collector 10 and server 11. Among them, the collector 10 can be various traffic detection devices, the collector 10 is used to obtain train data and driving route data of the current train after a large interval event occurs in the current train, wherein the train data includes the state data of each train of the same driving route; the server 11 is used to determine the train scheduling strategy of the large interval event according to the train data and the driving route data.

[0043] In the embodiments of the present application, one implementation of the embodiments of the present application is that the server 11 obtains the train data collected by the collector 10 and the driving route data of the current train after a large interval event occurs in the current train; wherein the train data includes the state data of each train of the same driving route; based on the congestion index in the driving route data, the vehicle state and the vehicle full load rate of the current train in the train data, the cause of the large interval event is determined; based on the cause of the large interval event, the driving route data and the train data, the influence station range of the large interval event is determined; based on the cause of the large interval event and the influence station range of the large interval event, the train scheduling strategy of the large interval event is determined.

[0044] Reference Figure 2 The flowchart of the traffic risk event identification analysis method based on AI perception network shown is used to illustrate the technical solutions provided by the embodiments of the present application.

[0045] Step 201, after a large interval event occurs in the current train, obtaining train data and driving route data of the current train;

[0046] Among them, the train data includes the state data of each train of the same driving route, the train data includes the stop time of each train at each station, the driving speed between two adjacent stations, the passenger flow data at each station, the vehicle state of each train and other data; the driving route data includes the position of each station, the congestion index, the driving direction and other data.

[0047] The method for identifying the large interval event of the current train can be determined by the following two methods. The first method is to determine the large interval event of the current train according to the feedback of passengers. The second method is to determine the interval between the arrival time of the current train and the arrival time of the previous train at the same station, and if the interval is greater than the interval between the departure time of the current train and the departure time of the previous train, the large interval event of the current train occurs. For example, the arrival time of the current train at station 3 is 1:20, the arrival time of the previous train at station 3 is 1:00, the interval between the arrival time of the current train and the arrival time of the previous train is 20 minutes, and if the interval between the departure time of the current train and the departure time of the previous train is 15 minutes, the large interval event of the current train occurs.

[0048] In step 202, the cause of the large interval event is determined based on the congestion index in the driving route data, the vehicle state of the current train in the train data, and the vehicle full load rate.

[0049] The cause of the large interval event includes vehicle failure, road congestion, excessive passenger flow, and late departure of the vehicle. The vehicle failure includes current train failure and vehicle accident, for example, the current train failure can be tire deflation, engine failure, etc., and the vehicle accident can be scratching or collision between the current train and other vehicles.

[0050] In step 203, the range of the stations affected by the large interval event is determined based on the cause of the large interval event, the driving route data, and the train data.

[0051] The range of the stations affected by the large interval event is each station affected by the arrival time of the current train.

[0052] In step 204, the train scheduling strategy of the large interval event is determined based on the cause of the large interval event and the range of the stations affected by the large interval event.

[0053] The train scheduling strategy includes adjusting the departure time of each train, increasing the number of trains passing through some stations on the driving route of the current train, prohibiting some trains from stopping at some stations on the driving route of the current train, and other scheduling strategies.

[0054] The application determines the cause of the large interval event after the current train service encounters the large interval event, determines the cause of the large interval event based on the congestion index in the obtained driving route data, the vehicle state of the current train service in the train service data, and the vehicle full load rate, and determines the influence station range of the large interval event according to the cause of the large interval event, thereby improving the accuracy of the determined influence station range. And the application determines the train service scheduling strategy of the large interval event based on the cause of the large interval event and the influence station range of the large interval event, thereby improving the processing efficiency and effectiveness of the large interval event, greatly reducing the influence of the large interval event, and improving the user satisfaction.

[0055] The AI perception network-based traffic risk event identification and analysis method provided above will be described in detail below, as shown in Figure 3 , which includes:

[0056] Step 301, determining that a large interval event occurs in the current train service based on passenger feedback;

[0057] Step 302, obtaining train service data and driving route data of the current train service;

[0058] The train service data includes the state data of each train service on the same driving route, and the train service data includes the stop duration of each train service at each station, the driving speed between two adjacent stations, the passenger flow data at each station, the vehicle state of each train service, and the like. The passenger flow data of any station includes the predicted number of passengers boarding and the predicted number of passengers alighting at the station; the driving route data includes the location of each station, the congestion index, the driving direction, and the like.

[0059] Step 303, determining the cause of the large interval event based on the congestion index in the driving route data, the vehicle state of the current train service in the train service data, and the vehicle full load rate.

[0060] Figure 4 The flowchart of the method for determining the cause of the large interval event provided by the embodiment of the application is shown in Figure 4 , and the above step 303 at least includes the following steps:

[0061] Step 401, determining whether the vehicle state is a fault state, if yes, executing step 402, otherwise, executing step 403;

[0062] Step 402, determining that the cause of the large interval event is vehicle failure;

[0063] Step 403, determining whether the congestion index is greater than or equal to a set congestion threshold, if yes, executing step 404, otherwise, executing step 405;

[0064] The congestion index is used to represent the congestion degree of the road and can be obtained from the map data of the map navigation application. The congestion threshold can be set according to actual conditions, for example, the congestion threshold can be 4.

[0065] In step 404, the occurrence cause of the large interval event is determined to be road congestion.

[0066] In step 405, it is determined whether the full load rate of the vehicle is greater than or equal to a set full load rate. If yes, step 406 is performed, otherwise, step 407 is performed.

[0067] The full load rate of the vehicle is the ratio of the passenger capacity of the vehicle to the maximum passenger capacity of the vehicle. The set full load rate can be set according to actual conditions, for example, the set full load rate can be 90%.

[0068] In step 406, the occurrence cause of the large interval event is determined to be excessive passenger flow.

[0069] In step 407, the occurrence cause of the large interval event is determined to be late departure of the vehicle.

[0070] In step 304, the influence station range of the large interval event is determined based on the occurrence cause of the large interval event, the travel route data and the train data.

[0071] According to the occurrence cause of the large interval event, the method for determining the influence station range of the large interval event in step 304 includes the following four cases:

[0072] In the first case, when the occurrence cause of the large interval event is vehicle failure, Figure 5 A flow chart of a method for determining the influence station range of the large interval event when the occurrence cause of the large interval event is vehicle failure is provided in the embodiments of the present application, as shown in Figure 5 The influence station range of the large interval event is determined by the following steps:

[0073] In step 501, based on the travel route data, each first influence station located behind the occurrence position of the large interval event in the travel direction of the train is determined.

[0074] In step 502, the influence station range is determined based on the first influence stations.

[0075] For example, Figure 6 A schematic diagram of the travel route of the current train is provided in the embodiments of the present application, as shown in Figure 6 The travel route of the current train includes 10 stations, and the travel direction of the current train is from left to right, Figure 6The gray rectangle in the figure is the occurrence position of the large interval event, and the station positions of the 5th to 10th stations are after the occurrence position of the large interval event, and thus the influence station range is the 5th to 10th stations.

[0076] In the second case, when the occurrence cause of the large interval event is road congestion, Figure 7 A flowchart of a method for determining an influence station range of a large interval event when the occurrence cause of the large interval event is road congestion is provided for the embodiments of the present application, as shown in Figure 7 The influence station range of the large interval event is determined by the following steps, as shown in

[0077] In step 701, the travel time between each two adjacent stations is determined based on the station distance between each two adjacent stations in the travel route data and the travel speed of the train between each two adjacent stations in the train data.

[0078] Since the travel route is divided into a congested section and a non-congested section, the travel speed between each two adjacent stations located in the congested section can be directly obtained from the map data of the map navigation application, and the travel speed between each two adjacent stations located in the non-congested section can be the maximum speed limit between the two adjacent stations.

[0079] The present application can determine the travel time between station i and station i+1 by the following method: if the station distance between station i and station i+1 is S, and the travel speed of the train between station i and station i+1 is V, then the travel time T between station i and station i+1 is S / V.

[0080] In step 702, the passing time between each two adjacent stations is determined based on the travel time between each two adjacent stations and the station stop time of the train at each station in the train data.

[0081] The present application can determine the passing time between station i and station i+1 by the following method: if the travel time between station i and station i+1 is T, and the station stop time of the train at station i is TS, then the passing time TI between station i and station i+1 is T+TS.

[0082] In step 703, when the passing time between each two adjacent stations is greater than the corresponding standard passing time, the station with the earliest arrival time in the two adjacent stations is taken as the second influence station.

[0083] The above standard passing time can be set according to actual conditions, and the standard passing time between different adjacent stations can be different or the same.

[0084] For example, if the passing time between station i and station i+1 is TI, and the standard passing time between station i and station i+1 is ST, if TI>ST, then station i is a second influence station.

[0085] In step 704, the range of influence stations is determined based on each second influence station.

[0086] In the third case, when the cause of the large interval event is late departure of the vehicle, Figure 8 A flowchart of a method for determining the range of influence stations of a large interval event when the cause of the large interval event is late departure of a vehicle is provided in the embodiments of the present application, as shown in Figure 8 The range of influence stations of the large interval event is determined by the following steps, as shown in

[0087] In step 801, based on the route data, each first station located behind the position of the large interval event in the running direction of the train is determined.

[0088] In step 802, based on the distance between each two adjacent first stations in the route data and the running speed of the train between each two adjacent first stations in the train data, the passing time between each two adjacent first stations is determined.

[0089] The running speed of the train between each two adjacent first stations can be the maximum speed limit between the two first stations.

[0090] The distance between each two adjacent first stations can be represented as The running speed between each two adjacent first stations can be represented as The passing time between each two adjacent first stations can be represented as The passing time between the jth two adjacent first stations can be determined by the following formula in the embodiments of the present application :

[0091] ;

[0092] wherein, is the distance between the jth two adjacent first stations, is the running speed between the jth two adjacent first stations, and j ranges from 1 to n, and n is the total number of first stations.

[0093] In step 803, based on the passing time between each two adjacent first stations and the station stop time of the train at each first station in the train data, the passing time between each two adjacent first stations is determined.

[0094] The application can determine the passing time between the first station j and the first station j+1 by the following method: if the travel time between the first station j and the first station j+1 is T, and the stop time of the train at the first station j is TS, then the passing time TI between the first station j and the first station j+1 is T+TS.

[0095] In step 804, when the passing time between each of the two adjacent first stations is greater than the corresponding standard passing time, the first station with the earliest arrival time among the two adjacent first stations is taken as the third influence station.

[0096] The standard passing time can be set according to actual conditions.

[0097] For example, the passing time between the first station j and the first station j+1 is TI, the standard passing time between the first station j and the first station j+1 is ST, if TI>ST, then the first station j is the third influence station.

[0098] In step 805, the influence station range is determined based on each third influence station.

[0099] For example, Figure 9 The schematic diagram of the travel route of the current train provided by the embodiment of the application is shown in FIG. 1. Figure 9 As shown in FIG. 1, the travel route of the current train includes 10 stations, and the travel direction of the current train is from left to right. Figure 9 The gray rectangle in FIG. 1 is the occurrence position of the large interval event, the station positions of the 6th to 10th stations are after the occurrence position of the large interval event, the passing time between the 6th and 7th stations is TI1, the corresponding standard passing time is ST1, the passing time between the 7th and 8th stations is TI2, the corresponding standard passing time is ST2, the passing time between the 8th and 9th stations is TI3, the corresponding standard passing time is ST3, the passing time between the 9th and 10th stations is TI4, the corresponding standard passing time is ST4, if TI1>ST1, TI2>ST2, TI3>ST3, and TI3<ST3, then the influence station range is the 6th to 8th stations.

[0100] In the fourth case, when the occurrence reason of the large interval event is too large passenger flow, Figure 10 The flow chart of the method for determining the influence station range of the large interval event when the occurrence reason of the large interval event is too large passenger flow provided by the embodiment of the application is shown in FIG. 4. Figure 10 The influence station range of the large interval event is determined by the following steps:

[0101] In step 101, based on the travel route data, each second station with a station position after the occurrence position of the large interval event in the travel direction of the train is determined.

[0102] In step 102, a travel time between each two adjacent second stations is determined based on a station distance between the two adjacent second stations in the travel route data and a travel speed of the train between the two adjacent second stations in the train data.

[0103] The specific implementation of steps 101-102 is the same as that of steps 801-802, and thus will not be described in detail here.

[0104] In step 103, a station stop time of each second station is determined based on a relationship between the boarding and alighting passengers and the station stop time and the boarding and alighting predicted passengers of the train at each second station in the train data.

[0105] The boarding and alighting predicted passengers of each second station can be predicted according to an Origin Destination (OD) model, and the specific prediction process is known in the art, and thus will not be described in detail here. The boarding predicted passengers of each second station can be represented as , and the alighting predicted passengers of each second station can be represented as The present application can determine the relationship between the boarding and alighting passengers and the station stop time according to the historical boarding and alighting passengers and the station stop time in historical data, and thus construct a function TS d = F(Y d ,X d ), where TS d is the station stop time of the dth second station, Y d is the boarding predicted passengers of the dth second station, X d is the alighting predicted passengers of the dth second station, and d ranges from 1 to D, where D is the total number of second stations.

[0106] In step 104, a passing time between each two adjacent second stations is determined based on the travel time between the two adjacent second stations and the station stop time of each second station.

[0107] In step 105, when the passing time between each two adjacent second stations is greater than a corresponding standard passing time, the second station with the earliest arrival time among the two adjacent second stations is determined as a fourth influencing station.

[0108] The specific implementation of steps 104-105 is the same as that of steps 803-804, and thus will not be described in detail here.

[0109] In step 106, a predicted passenger capacity of each second station is determined based on a passenger capacity of the train and the boarding and alighting predicted passengers of each second station.

[0110] This application can determine the predicted passenger volume PT of the d-th second station based on the following formula. d :

[0111] PT d =P d +Y d -X d ;

[0112] Among them, P d Y represents the passenger volume of the d-th second station. d Let X be the predicted number of passengers boarding at the d-th second station. d Let d be the predicted number of passengers getting off at the d-th second station, where d ranges from 1 to D, and D is the total number of second stations.

[0113] Step 107: The second station whose predicted passenger volume is greater than the set passenger volume threshold is designated as the fifth affected station.

[0114] The fifth affected station is one where, although there is no significant interval between train arrivals, not all passengers waiting to board have boarded.

[0115] The passenger capacity threshold mentioned above can be set according to the actual situation. For example, the passenger capacity threshold for the current train can be the maximum passenger capacity for the current train.

[0116] If the passenger volume P of the d-th second station d If the passenger capacity exceeds the set passenger capacity threshold P, then the d-th second station becomes the fifth affected station.

[0117] Step 108: Determine the scope of the affected sites based on each fourth and fifth affected site.

[0118] Since large interval events occur due to excessive passenger flow or delayed vehicle departures, they only affect the current train and do not impact other trains; therefore, the prediction of the affected train range is not involved. This application determines the affected train range of large interval events in the following two situations:

[0119] Scenario 1: When the cause of the long interval events is traffic congestion, Figure 11 A flowchart illustrating a method for determining the range of affected trains when the cause of a long interval event is road congestion, as provided in this application embodiment, is shown below. Figure 11 As shown, the affected train range of a large interval event is determined through the following steps:

[0120] In step 111, based on the route data and the train data, each first train with a departure time later than the departure time of the train is determined, and a third station is determined in the route of the train, which is located before the occurrence position of the large interval event and is closest to the occurrence position of the large interval event.

[0121] As shown in FIG. 10, the route of the current train includes 10 stations, and the route direction of the current train is from left to right. Figure 6 The gray rectangle in FIG. 10 is the occurrence position of the large interval event. The first station is the third station because the station position of the first station is located before the occurrence position of the large interval event and is closest to the occurrence position of the large interval event. Figure 6

[0122] In step 112, based on the passing time of the train from the starting station to the third station and the interval between the two adjacent trains in the train data, the passing time of each first train from the starting station to the third station is determined.

[0123] The passing time of the train from the starting station to the third station is determined according to the distance between the two adjacent stations, the speed between the two adjacent stations, and the stopping time of each station.

[0124] For example, if the current train and the first train A are adjacent trains, the interval between the current train and the first train A is T1, and the passing time of the current train from the starting station to the third station is Tv, then the passing time TH1 of the first train A from the starting station to the third station is TH1 = Tv+T1. If the second train B and the first train A are adjacent trains, the interval between the second train B and the first train A is T2, then the passing time TH1 of the first train B from the starting station to the third station is TH1 = Tv+T1+T2.

[0125] In step 113, when the passing time of the first train from the starting station to the third station is less than or equal to the predicted congestion time, the first train is determined as the third influence train.

[0126] The predicted congestion time can be directly obtained from the map data of the map navigation application.

[0127] If the predicted congestion time is TP, and the passing time TH1 of the first train A from the starting station to the third station is TH1 ≤ TP, then the first train A is the third influence train.

[0128] In step 114, for each first train, based on the departure time of the first train, the passing time of the first train from the starting station to the third station, and the passing time between the two adjacent stations, the arrival time of the first train at the terminal station is determined.

[0129] ​The travel time between each two adjacent stations is determined based on the distance between the two stations, the travel speed of the train between the two stations, and the stop time of the train at each station.

[0130] If the departure time of the first train A is TO, the travel time of the first train A from the starting station to the third station is TH1, the travel time of the first train A from the third station to the terminal station is T, and the sum of the stop times of the first train A at each station from the third station to the terminal station is TS, then the arrival time TF of the first train A at the terminal station is TF = TO + TH1 + T + TS.

[0131] Step 115, taking the first train with an arrival time later than the corresponding train re-departure time as the fourth influence train.

[0132] The fourth influence train is a train that cannot return to participate in operation due to road congestion. The arrival time of the first train at the terminal station is compared with the train re-departure time corresponding to the first train to determine the fourth influence train. The train re-departure time corresponding to the first train is the departure time of the first train after arriving at the terminal station.

[0133] For example, the train re-departure time corresponding to the first train A is 2:00, and if the arrival time of the first train A at the terminal station is 2:05, then the first train A is the fourth influence train.

[0134] Step 116, determining the influence train range based on each third influence train and each fourth influence train.

[0135] Case two, when the cause of the large interval event is vehicle failure, Figure 12 A flowchart of a method for determining the influence train range of a large interval event when the cause of the large interval event is vehicle failure is provided in the embodiment of the present application, as shown in Figure 12 The influence train range of the large interval event is determined by the following steps:

[0136] Step 121, determining whether the congestion index is less than the set congestion threshold, if yes, executing steps 122-123, otherwise, executing steps 124-126;

[0137] Step 122, determining each first influence train with a departure time within the fault prediction recovery time interval based on the departure time of each train in the train data.

[0138] The fault prediction recovery time interval can be directly obtained from the map data of the map navigation application.

[0139] Step 123, determining the influence train range based on the first influence trains.

[0140] For example, the fault prediction recovery time interval is 1:00-1:30, the departure time of train A is 1:00, the departure time of train B is 1:10, the departure time of train C is 1:20, and the departure time of train D is 1:35. The departure times of train A, train B and train C are within the fault prediction recovery time interval, so the influence train range includes train A, train B and train C.

[0141] Step 124, determining the first influence trains whose departure times are within the fault prediction recovery time interval based on the departure times of the trains in the train data.

[0142] Step 125, determining the second influence trains corresponding to the road congestion according to the driving route data and the train data.

[0143] The specific process of step 125 can refer to steps 111-116, which will not be described in detail here.

[0144] Step 126, determining the influence train range based on the first influence trains and the second influence trains.

[0145] Step 305, determining the train scheduling strategy of the large interval event based on the cause of the large interval event and the influence station range of the large interval event.

[0146] According to the cause of the large interval event, the method for determining the train scheduling strategy of the large interval event in step 305 includes the following four cases:

[0147] Case 1, when the cause of the large interval event is road congestion, determining the train scheduling strategy corresponding to the road congestion according to the influence station range and the influence train range of the large interval event. Figure 13 A flow chart of a method for determining the train scheduling strategy of the large interval event when the cause of the large interval event is road congestion provided by the embodiment of the application is shown in Figure 13 The road congestion of the large interval event is determined by the following steps.

[0148] Step 131, determining whether the congestion direction is bidirectional congestion, if yes, executing step 132, otherwise, executing step 134.

[0149] Step 132, determining whether the influence station range is within the set station range, if yes, executing step 133, otherwise, executing step 134.

[0150] The application can divide the travel route according to the actual situation, for example, the travel route of train A includes 12 stations, and the range including the 4th to 8th stations can be set as the set station range. If the affected station range includes the 5th to 6th stations, the affected station range is within the set station range; if the affected station range includes the 1st to 3rd stations, the affected station range is outside the set station range; and if the affected station range includes the 8th to 9th stations, the affected station range is outside the set station range.

[0151] In step 133, the train in the affected train range is controlled to make a two-way U-turn.

[0152] Specifically, the application can control the train in the affected train range to make a two-way U-turn when it just arrives at the occurrence position of the large interval event.

[0153] In step 134, based on the travel route data and the train data, the total standard passing time of each station covered by the train passing through the large interval event is determined.

[0154] For example, the travel route of train A includes 12 stations, and the range including the 4th to 8th stations can be set as the set station range. If the affected station range includes the 2nd to 3rd stations, the affected station range is outside the set station range, and the total standard passing time of each station covered by train A passing through the large interval event is equal to the sum of the passing time from the 2nd station to the 3rd station, that is, the sum of the passing time of each station covered by train A passing through the large interval event when no large interval event occurs.

[0155] In step 135, based on the relationship between the total standard passing time and the set multiple and the multiple of the predicted passing time of the large interval event in the travel route data, the corresponding train scheduling strategy is determined.

[0156] The predicted passing time of the large interval event can be directly obtained from the map data of the map navigation application. The set multiple can be set according to the actual situation, and the set multiple includes a first multiple and a second multiple, the first multiple is less than the second multiple, the first multiple can be 1, and the second multiple can be 2.

[0157] Through the vehicle-mounted device, the station sensor and the external map data (such as congestion index), the key information such as train status (whether fault), full load rate, travel speed and station passenger flow prediction is collected in real time. When the system detects that the interval between the arrival time of a train and the previous train is abnormally increased (which can be triggered automatically through passenger feedback or arrival time calculation), it is determined that a large interval event occurs, and the intelligent analysis process is started.

[0158] Based on the preset AI decision rule, combined with the real-time perceived vehicle state, congestion index and full load rate, the root cause of the event is quickly locked - vehicle failure, road congestion, excessive passenger flow or late departure of the vehicle. For example, a high congestion index in a non-failure state points to road congestion, while a low congestion and high full load are attributed to excessive passenger flow. Secondly, the impact range is dynamically evaluated for different root causes: if it is a vehicle failure, the impact range covers all stations after the incident location; if it is due to congestion or late departure, the travel time needs to be calculated by combining the station spacing, real-time speed and station stop time to accurately locate the actual delay station, such as the station that arrives earliest among adjacent stations with excessive travel time; In the scenario of excessive passenger flow, it is also necessary to predict whether the passenger capacity is over the limit to comprehensively judge the risk of station retention.

[0159] For congestion scenarios, vehicles may be triggered to turn around, detour or increase the interval of the affected section according to the congestion direction (one-way / two-way) and the size of the impact range; When a vehicle fails, the subsequent train departure is adjusted or skip-stop operation is enabled according to the congestion degree; In the face of large passenger flow, additional vehicles are directly dispatched and the departure interval is optimized. All strategies are realized through quantitative indicators for fine matching, significantly improving the efficiency of event handling and reducing passenger waiting time.

[0160] Figure 14 A flowchart of a method for determining a corresponding train scheduling strategy based on the relationship between the multiple and the set multiple provided by the embodiments of the present application is shown in FIG. 13. Figure 14 The step 135 at least includes the following steps:

[0161] Step 141, determine whether the multiple is less than or equal to the first multiple, if yes, execute step 142, otherwise execute step 143;

[0162] Step 142, no train scheduling processing is performed;

[0163] Step 143, determine whether the multiple is greater than or equal to the second multiple, if yes, execute step 144, otherwise execute step 145;

[0164] Step 144, control each train in the affected train range to detour;

[0165] Step 145, increase the train passing through part of the stations in the travel route, and / or prohibit each train in the affected train range from stopping at part of the stations in the travel route;

[0166] For example, the travel route includes 12 stations, and the large interval event covers the 4th-8th stations, then the train passing through the 1st-3rd stations and the 9th-12th stations can be increased, or each train in the affected train range can not stop at part of the stations in the travel route, such as stations without waiting passengers, i.e. without picking up passengers.

[0167] Step 146, adjusting the departure time of each train in the affected train range.

[0168] The application can adjust the departure time of each train in the affected train range after adding a train and / or prohibiting the train from stopping at some stations.

[0169] Case 2, when the cause of the large interval event is vehicle failure, determining the train scheduling strategy corresponding to the cause of the large interval event when the cause of the large interval event is vehicle failure based on the affected station range and the affected train range of the large interval event. Figure 15 A flowchart of a method for determining the train scheduling strategy of a large interval event when the cause of the large interval event is vehicle failure provided by an embodiment of the application is shown in Figure 15 The road congestion of the large interval event is determined by the following steps:

[0170] Step 151, determining whether the congestion index is less than a set congestion threshold, if yes, executing step 152, otherwise, executing step 155;

[0171] Step 152, determining whether the size of the affected station range exceeds a set station range size, if yes, executing step 153, otherwise, executing step 154;

[0172] The set station range size can be set according to actual conditions, for example, the set station range size is 1 / 3.

[0173] Step 153, adding a train passing through some stations in the driving route and / or prohibiting each train in the affected train range from stopping at some stations in the driving route;

[0174] Step 154, adjusting the departure time of each train in the affected train range;

[0175] After adjusting the departure time of each train in the affected train range, if the departure interval requirement is still not met, a train passing through some stations in the driving route can be added or each train in the affected train range can not stop at some stations in the driving route, and then the departure time of each train in the affected train range is adjusted.

[0176] Step 155, determining the train scheduling strategy corresponding to the cause of the large interval event when the cause of the large interval event is road congestion based on the affected station range and the affected train range of the large interval event.

[0177] The specific implementation of step 155 can refer to steps 131-135 described above, which will not be described in detail here.

[0178] Case 3, when the cause of the large interval event is too large passenger flow, the train scheduling strategy of the large interval event is determined by the following method: according to the predicted number of passengers getting on and off at each affected station in the affected station range, setting the passenger carrying threshold and the passenger carrying capacity of the train, determining the number of trains that need to be increased, increasing the number of trains of the vehicle, and departing according to the set departure interval.

[0179] The above-mentioned setting of the passenger carrying threshold is the maximum passenger carrying capacity of the train.

[0180] Case 4, when the cause of the large interval event is vehicle late departure, Figure 16 A flowchart of a method for determining the train scheduling strategy of a large interval event when the cause of the large interval event is vehicle late departure is provided for the embodiments of the present application, as shown in Figure 16 The road congestion of the large interval event is determined by the following steps:

[0181] Step 161, determine whether the size of the affected station range exceeds the set station range size, if yes, execute steps 162-163, otherwise, execute step 164;

[0182] The above-mentioned setting of the station range size can be set according to the actual situation, for example, the station range size is set to 1 / 3.

[0183] Step 162, increase the number of trains passing through part of the stations in the travel route, and / or prohibit each train whose departure time is later than or equal to the departure time of the train from stopping at part of the stations in the travel route;

[0184] Step 163, adjust the departure time of each train whose departure time is later than the departure time of the train;

[0185] Step 164, do not perform train scheduling processing.

[0186] Based on the same inventive concept, the embodiments of the present application provide a device for processing vehicle large interval events. Since the above-mentioned device is the device in the method of the embodiments of the present application, and the principle of solving the problem of the device is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described.

[0187] As shown in Figure 17 The above-mentioned device includes the following modules:

[0188] The acquisition module 171 is configured to acquire train data and travel route data of the current train after the occurrence of a large interval event of the train; wherein the train data includes state data of each train on the same travel route;

[0189] The first determining module 172 is configured to determine a cause of the large-interval event based on a congestion index in the travel route data, a vehicle state of a current train in the train data, and a vehicle fullness rate.

[0190] The second determining module 173 is configured to determine a range of affected stations of the large-interval event based on the cause of the large-interval event, the travel route data, and the train data.

[0191] The third determining module 174 is configured to determine a train scheduling strategy of the large-interval event based on the cause of the large-interval event and the range of affected stations of the large-interval event.

[0192] In a possible design, the first determining module 172 is configured to:

[0193] If the vehicle state is a fault state, the cause of the large-interval event is vehicle fault.

[0194] If the vehicle state is a non-fault state and the congestion index is greater than or equal to a set congestion threshold, the cause of the large-interval event is road congestion.

[0195] If the vehicle state is a non-fault state, the congestion index is less than the set congestion threshold, and the vehicle fullness rate is greater than or equal to a set fullness rate, the cause of the large-interval event is excessive passenger flow.

[0196] If the vehicle state is a non-fault state, the congestion index is less than the set congestion threshold, and the vehicle fullness rate of the vehicle is less than the set fullness rate, the cause of the large-interval event is late departure of the vehicle.

[0197] In a possible design, the second determining module 173 is configured to:

[0198] If the cause of the large-interval event is vehicle fault, each first affected station is determined based on the travel route data and located behind a position of occurrence of the large-interval event in a travel direction of the train, and the range of affected stations is determined based on the first affected stations.

[0199] If the occurrence cause of the large interval event is road congestion, determine a travel time length between each two adjacent stations based on a station distance between each two adjacent stations in the travel route data and a travel speed of the train between each two adjacent stations in the train data; determine a passing time length between each two adjacent stations based on the travel time length between each two adjacent stations and a stop time length of the train at each station in the train data; take a station with the earliest arrival time in each two adjacent stations as a second influence station when the passing time length between the two adjacent stations is greater than a corresponding standard passing time length; and determine the influence station range based on each second influence station.

[0200] If the occurrence cause of the large interval event is late departure of the train, determine each first station with a station position behind the occurrence position of the large interval event in the travel direction of the train based on the travel route data; determine a travel time length between each two adjacent first stations based on a station distance between each two adjacent first stations in the travel route data and a travel speed of the train between each two adjacent first stations in the train data; determine a passing time length between each two adjacent first stations based on the travel time length between each two adjacent first stations and a stop time length of the train at each first station in the train data; take a first station with the earliest arrival time in each two adjacent first stations as a third influence station when the passing time length between the two adjacent first stations is greater than a corresponding standard passing time length; and determine the influence station range based on each third influence station.

[0201] In a possible design, the occurrence cause of the large interval event is too large passenger flow, and the second determining module 173 is configured to:

[0202] determine each second station with a station position behind the occurrence position of the large interval event in the travel direction of the train based on the travel route data;

[0203] determine a travel time length between each two adjacent second stations based on a station distance between each two adjacent second stations in the travel route data and a travel speed of the train between each two adjacent second stations in the train data;

[0204] determine a stop time length of each second station based on a relationship between the number of passengers and the stop time length and a predicted number of passengers boarding and alighting at each second station in the train data;

[0205] determine a passing time length between each two adjacent second stations based on the travel time length between each two adjacent second stations and the stop time length of each second station;

[0206] respectively, the second station with the earliest arrival time among the two adjacent second stations is taken as a fourth influence station when the passing time between the two adjacent second stations is greater than the corresponding standard passing time;

[0207] based on the passenger capacity of the train and the predicted number of passengers getting on and off at each second station, a predicted passenger capacity of each second station is determined;

[0208] respectively, a second station with a predicted passenger capacity greater than a set passenger capacity threshold is taken as a fifth influence station;

[0209] based on each fourth influence station and each fifth influence station, the influence station range is determined.

[0210] In a possible design, the occurrence cause of the large interval event is vehicle failure, and before determining the train scheduling strategy of the large interval event, the third determining module 174 is further configured to:

[0211] if the congestion index is less than a set congestion threshold, based on the departure time of each train in the train data, each first influence train with a departure time within a fault predicted recovery time interval is determined; and based on the first influence train, the influence train range is determined;

[0212] if the congestion index is greater than or equal to the set congestion threshold, based on the departure time of each train in the train data, each first influence train with a departure time within the fault predicted recovery time interval is determined; based on the travel route data and the train data, each second influence train corresponding to the occurrence cause of the large interval event when the occurrence cause of the large interval event is road congestion is determined; and based on the first influence train and the second influence train, the influence train range is determined;

[0213] The third determining module 174 is configured to:

[0214] based on the occurrence cause of the large interval event, the influence station range and the influence train range, a train scheduling strategy of the large interval event is determined.

[0215] In a possible design, the occurrence cause of the large interval event is road congestion, and before determining the train scheduling strategy of the large interval event, the third determining module 174 is further configured to:

[0216] based on the travel route data and the train data, each first train with a departure time later than the departure time of the train, and a third station located before the occurrence position of the large interval event and closest to the occurrence position of the large interval event in the travel direction of the train are determined;

[0217] determine, based on the travel time of each first train from the starting station to the third station and the departure interval of two adjacent trains in the train data, the travel time of each first train from the starting station to the third station;

[0218] respectively, when the travel time of the first train from the starting station to the third station is less than or equal to the predicted congestion time, the first train is taken as a third influence train;

[0219] For each first train, based on the departure time of the first train, the travel time of the first train from the starting station to the third station, and the travel time between each two adjacent stations, the arrival time of the first train at the terminal station is determined.

[0220] respectively, the first train with an arrival time later than the corresponding train re-departure time is taken as a fourth influence train;

[0221] Based on each third influence train and each fourth influence train, the influence train range is determined.

[0222] The third determination module 174 is configured to:

[0223] Based on the cause of the large interval event, the influence station range and the influence train range, the train scheduling strategy of the large interval event is determined.

[0224] In a possible design, the third determination module 174 is configured to:

[0225] If the congestion index is less than the set congestion threshold, and the size of the influence station range does not exceed the set station range size, the departure time of each train in the influence train range is adjusted;

[0226] If the congestion index is less than the set congestion threshold, and the size of the influence station range exceeds the set station range size, the train passing through part of the stations in the travel route and / or the train in the influence train range is prohibited from stopping at part of the stations in the travel route, and the departure time of each train in the influence train range is adjusted;

[0227] If the congestion index is greater than or equal to the set congestion threshold, based on the influence station range and the influence train range of the large interval event, the cause of the large interval event is determined as the corresponding train scheduling strategy when the road is congested.

[0228] In a possible design, the third determination module 174 is configured to:

[0229] If it is determined that the congestion is bidirectional congestion based on the congestion direction of the travel route data, and the influence station range is within the set station range, the train in the influence train range is controlled to make bidirectional U-turns.

[0230] If it is determined that the congestion is bidirectional congestion based on the congestion direction of the travel route data, and the influence station range is outside the set station range, or it is determined that the congestion is unidirectional congestion based on the congestion direction of the travel route data, the total standard passing time of each station covered by the large interval event by the train is determined based on the travel route data and the train data, and a corresponding train scheduling strategy is determined based on a relationship between the total standard passing time and a multiple of the predicted passing time of the large interval event in the travel route data and a set multiple.

[0231] In a possible design, the set multiple includes a first multiple and a second multiple, the first multiple is smaller than the second multiple, and the third determining module 174 is configured to:

[0232] If the multiple is smaller than or equal to the first multiple, no train scheduling processing is performed.

[0233] If the multiple is greater than the first multiple and smaller than the second multiple, the train passing through part of the stations in the travel route is increased, and / or each train in the influence train range is prohibited from stopping at the part of the stations in the travel route, and the departure time of each train in the influence train range is adjusted.

[0234] If the multiple is greater than or equal to the second threshold, each train in the influence train range is controlled to make detours.

[0235] In a possible design, the third determining module 174 is configured to:

[0236] If the large interval event is caused by excessive passenger flow, the number of trains that need to be increased is determined according to the predicted number of passengers getting on and off each station in the influence station range, a set passenger carrying threshold, and the passenger carrying capacity of the train, the number of vehicles is increased, and the vehicles are dispatched according to a set departure interval.

[0237] If the large interval event is caused by late departure of the vehicle, and the size of the influence station range does not exceed the size of the set station range, no train scheduling processing is performed.

[0238] If the large interval event is caused by late departure of the vehicle, and the size of the influence station range exceeds the size of the set station range, the train passing through part of the stations in the travel route is increased, and / or each train with a departure time later than or equal to the departure time of the train is prohibited from stopping at the part of the stations in the travel route, and the departure time of each train with a departure time later than the departure time of the train is adjusted.

[0239] In some embodiments, based on the same inventive concept, the application further provides a device for processing a vehicle large interval event, which can implement the vehicle large interval event processing function discussed above. Please refer to Figure 18 The device includes a processor 181 and a memory 182, wherein the memory 182 is used to store program instructions.

[0240] The processor 181 invokes the program instructions stored in the memory and runs the program instructions to implement:

[0241] After a large interval event occurs in the current train, obtain train data and driving route data of the current train; wherein the train data includes state data of each train on the same driving route;

[0242] Determine the cause of the large interval event based on the congestion index in the driving route data, the vehicle state of the current train in the train data, and the vehicle full load rate.

[0243] Determine the impact station range of the large interval event based on the cause of the large interval event, the driving route data, and the train data.

[0244] Determine the train scheduling strategy of the large interval event based on the cause of the large interval event and the impact station range of the large interval event.

[0245] The processor 181 runs the executable instructions to implement the steps of the AI perception network-based traffic risk event identification and analysis method described above, and the repeated parts will not be described again.

[0246] The application further provides a computer storage medium, which stores computer program instructions, and when the instructions run on a computer, the computer executes the steps of the AI perception network-based traffic risk event identification and analysis method described above.

[0247] In some possible implementations, various aspects of the application can also be implemented in the form of a program product, which includes computer program code, and when the computer program code runs on a computer, the computer executes the AI perception network-based traffic risk event identification and analysis method as any of the above. Since the principle of solving problems of the above-mentioned computer program product is similar to the AI perception network-based traffic risk event identification and analysis method, the implementation of the above-mentioned computer program product can be referred to the implementation of the method, and the repeated parts will not be described again.

[0248] Those skilled in the art will appreciate that embodiments of the present application can be devised for a variety of other systems which are currently developed or later developed. Therefore, the present application is intended to cover all such modifications and variations of this application that are within the scope of the appended claims and their equivalents. It is intended that each element of claim 1 is implemented independently of each other element. None of the elements of claim 1, singly or in combination, is intended to be a means-plus-function clause.

[0249] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to this application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 Figure 1

[0250] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 Figure 1

[0251] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 Figure 1

[0252] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.​​​​​​​

Claims

1. An AI perception network-based traffic risk event identification analysis method, characterized in that, The method comprises: after a large interval event occurs in a current train, obtaining train data and running route data of the current train, wherein the train data comprises state data of each train on the same running route; determining a cause of the large interval event based on a congestion index in the running route data, a vehicle state of the current train in the train data, and a vehicle full load rate; determining an influence station range of the large interval event based on the cause of the large interval event, the running route data, and the train data; determining a train scheduling strategy of the large interval event based on the cause of the large interval event and the influence station range of the large interval event; the determination of the cause of the large interval event based on the congestion index in the running route data, the vehicle state of the current train in the train data, and the vehicle full load rate comprises: if the vehicle state is a fault state, the cause of the large interval event is vehicle failure; if the vehicle state is a non-fault state and the congestion index is greater than or equal to a set congestion threshold, the cause of the large interval event is road congestion; if the vehicle state is a non-fault state, the congestion index is less than the set congestion threshold, and the vehicle full load rate is greater than or equal to a set full load rate, the cause of the large interval event is excessive passenger flow; if the vehicle state is a non-fault state, the congestion index is less than the set congestion threshold, and the vehicle full load rate of the vehicle is less than the set full load rate, the cause of the large interval event is late departure of the vehicle; the determination of the influence station range of the large interval event based on the cause of the large interval event, the running route data, and the train data comprises: if the cause of the large interval event is vehicle failure, each first influence station is determined based on the running route data, the station position being after the occurrence position of the large interval event in the running direction of the train; the influence station range is determined based on the first influence stations; if the cause of the large interval event is road congestion, a running time length between each two adjacent stations is determined based on a station distance between each two adjacent stations in the running route data and a running speed of the train between the two stations in the train data; a passing time length between each two adjacent stations is determined based on the running time length between the two stations and a stop time length of the train at each station in the train data; when the passing time length between each two adjacent stations is greater than a corresponding standard passing time length, the station with the earliest arrival time in the two stations is taken as a second influence station; the influence station range is determined based on the second influence stations. If the occurrence cause of the large interval event is that a vehicle is late, based on the travel route data, each first station after the occurrence position of the large interval event in the travel direction of the train is determined; based on the station distance between each two adjacent first stations in the travel route data and the travel speed of the train between the two adjacent first stations in the train data, the travel time between the two adjacent first stations is determined; based on the travel time between the two adjacent first stations and the stop time of the train at each first station in the train data, the passing time between the two adjacent first stations is determined; when the passing time between each two adjacent first stations is greater than the corresponding standard passing time, the first station with the earliest arrival time in the two adjacent first stations is taken as a third influence station; and based on each third influence station, the influence station range is determined.

2. The method of claim 1, wherein, If the occurrence cause of the large interval event is that the passenger flow is too large, the method of determining the influence station range of the large interval event based on the occurrence cause of the large interval event, the travel route data and the train data comprises: based on the travel route data, each second station after the occurrence position of the large interval event in the travel direction of the train is determined; based on the station distance between each two adjacent second stations in the travel route data and the travel speed of the train between the two adjacent second stations in the train data, the travel time between the two adjacent second stations is determined; based on the relationship between the number of passengers and the stop time and the predicted number of passengers at each second station in the train data, the stop time of each second station is determined; based on the travel time between each two adjacent second stations and the stop time of each second station, the passing time between the two adjacent second stations is determined; when the passing time between each two adjacent second stations is greater than the corresponding standard passing time, the second station with the earliest arrival time in the two adjacent second stations is taken as a fourth influence station; based on the carrying capacity of the train and the predicted number of passengers at each second station, the predicted carrying capacity of each second station is determined; each second station with a predicted carrying capacity greater than a set carrying threshold is taken as a fifth influence station; based on each fourth influence station and each fifth influence station, the influence station range is determined.

3. The method of claim 1, wherein, If the occurrence cause of the large interval event is vehicle failure, before determining the train scheduling strategy of the large interval event, the method further comprises: if the congestion index is less than a set congestion threshold, based on the departure time of each train in the train data, each first influence train with a departure time within the fault predicted recovery time interval is determined; based on each first influence train, an influence train range is determined. If the congestion index is greater than or equal to a set congestion threshold, based on departure times of each train in the train data, determine each first affected train whose departure time is within the fault prediction recovery time interval; based on the travel route data and the train data, determine each second affected train corresponding to a cause of the large interval event when the cause is road congestion; based on the first affected train and the second affected train, determine the affected train range; The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event and the affected station range comprises: The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event, the affected station range and the affected train range.

4. The method of claim 3, wherein, If the cause of the large interval event is road congestion, before determining the train scheduling strategy of the large interval event, the method further comprises: Based on the travel route data and the train data, determine each first train whose departure time is later than the departure time of the train, and determine a third station in the travel direction of the train, which is located before the occurrence position of the large interval event and is closest to the occurrence position of the large interval event; Based on the travel time of the train from the starting station to the third station and the departure interval of two adjacent trains in the train data, determine the travel time of each first train from the starting station to the third station; When the travel time of the first train from the starting station to the third station is less than or equal to the predicted congestion time, the first train is determined as a third affected train; For each first train, based on the departure time of the first train, the travel time of the first train from the starting station to the third station and the travel time between each two adjacent stations, determine the arrival time of the first train at the terminal station; Each first train whose arrival time is later than the re-departure time of the corresponding train is determined as a fourth affected train; Based on each third affected train and each fourth affected train, determine the affected train range; The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event and the affected station range comprises: The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event, the affected station range and the affected train range.

5. The method of claim 3, wherein, The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event, the affected station range and the affected train range comprises: If the congestion index is less than the set congestion threshold, and the size of the affected station range does not exceed the set station range size, adjust the departure time of each train in the affected train range; If the congestion index is less than the set congestion threshold, and the size of the affected station range exceeds the set station range size, increase the train passing through part of the stations in the travel route and / or prohibit each train in the affected train range from stopping at part of the stations in the travel route, and adjust the departure time of each train in the affected train range; If the congestion index is greater than or equal to the set congestion threshold, a cause of the large interval event is determined based on an influence station range and an influence train range of the large interval event, and a corresponding train scheduling strategy in a road congestion case is determined.

6. The method of claim 4, wherein, The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event, the influence station range and the influence train range comprises: If it is determined that there is bidirectional congestion based on the congestion direction of the travel route data, and the influence station range is within a set station range, each train in the influence train range is controlled to perform bidirectional U-turn; If it is determined that there is bidirectional congestion based on the congestion direction of the travel route data, and the influence station range is outside the set station range, or it is determined that there is unidirectional congestion based on the congestion direction of the travel route data, a total standard passing time of each station covered by the large interval event is determined based on the travel route data and the train data, and a corresponding train scheduling strategy is determined based on a relationship between the total standard passing time and a multiple of a predicted passing time of the large interval event in the travel route data and a set multiple.

7. The method of claim 6, wherein, The set multiple comprises a first multiple and a second multiple, the first multiple is smaller than the second multiple, and the determination of the corresponding train scheduling strategy based on the relationship between the total standard passing time and the multiple of the predicted passing time of the large interval event in the travel route data and the set multiple comprises: If the multiple is less than or equal to the first multiple, no train scheduling processing is performed; If the multiple is greater than the first multiple and less than the second multiple, a train passing through part of the stations in the travel route is increased, and / or each train in the influence train range is prohibited from stopping at the part of the stations in the travel route, and a departure time of each train in the influence train range is adjusted; If the multiple is greater than or equal to the second threshold, each train in the influence train range is controlled to perform detour.

8. The method of claim 1, wherein, The determination of the train scheduling strategy of the large interval event based on the cause of the large interval event and the influence station range of the large interval event comprises: If the cause of the large interval event is excessive passenger flow, a number of trains to be increased is determined according to a predicted number of passengers getting on and off at each station in the influence station range, a set passenger carrying threshold and a passenger carrying capacity of the train, a vehicle of the number of trains is increased, and departure is performed according to a set departure interval; If the cause of the large interval event is late departure of a vehicle, and a size of the influence station range does not exceed a size of a set station range, no train scheduling processing is performed; If the cause of the large interval event is late departure of a vehicle, and the size of the influence station range exceeds the size of the set station range, a train passing through part of the stations in the travel route is increased, and / or each train with a departure time later than or equal to a departure time of the train is prohibited from stopping at the part of the stations in the travel route, and a departure time of each train with the departure time later than the departure time of the train is adjusted.

Images