Train departure time updating method, system and device and train

Abstract

The invention provides a train departure time updating method which can be applied to the technical field of intelligent transportation. The train departure time updating method comprises the steps that the actual section passenger flow volume of a first time period and the predicted section passenger flow volume of the first time period are obtained; obtaining a plurality of initial departure moments in the first time period obtained by updating the predicted section passenger flow volume of the first time period, and single-point section passenger flow volumes corresponding to the initial departure moments; inputting the actual cross-section passenger flow volume of the first time period into a trained cross-section passenger flow volume prediction model to obtain a predicted cross-section passenger flow volume corresponding to a second time period; updating the initial departure frequency by using the predicted cross-section passenger flow volume of the second time period to obtain a target departure frequency; and updating the plurality of initial departure moments according to the target departure frequency and each single-point cross-section passenger flow volume to obtain a plurality of target departure moments so as to depart according to the target departure moments. The invention further provides a train departure time updating system and device and a train.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent transportation technology, and in particular to a method, system, device and train for updating train departure times. Background Art

[0002] During train scheduling, trains depart in an orderly manner according to the departure plan established for the current time period. Departure planning is based on collecting and analyzing historical passenger flow data to identify cyclical patterns during weekdays, weekends, and different time periods (such as morning and evening peaks). This allows for the development of daily departure plans for each time period, allocating corresponding departure frequencies and capacity. For example, trains may be increased during peak hours and reduced during off-peak hours to accommodate regular passenger demand.

[0003] In implementing the concepts of this disclosure, the inventors discovered at least the following issues with the prior art: Over time, dynamic disruptions such as changes in passenger flow, emergencies, and vehicle status deviations from the planned operation are encountered. These disruptions are real-time and non-periodic. Fixed departure plans, however, are poorly adaptable to these dynamic disruptions, unable to respond in real time to changes in passenger flow, faults, and other factors, resulting in insufficient scheduling flexibility. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides a method, system, device and train for updating train departure time.

[0005] According to the first aspect of the present disclosure, a method for updating train departure times is provided, comprising: obtaining the actual cross-sectional passenger flow in a first time period and the predicted cross-sectional passenger flow in the first time period; obtaining multiple initial departure times in the first time period obtained by updating the predicted cross-sectional passenger flow in the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time; inputting the actual cross-sectional passenger flow in the first time period into a trained cross-sectional passenger flow prediction model to obtain the predicted cross-sectional passenger flow corresponding to the second time period; using the predicted cross-sectional passenger flow in the second time period to update the initial departure frequency to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-sectional passenger flow in the first time period; updating the multiple initial departure times according to the target departure frequency and the single-point cross-sectional passenger flow to obtain multiple target departure times, so as to depart according to the target departure time.

[0006] According to an embodiment of the present disclosure, multiple initial departure times are updated according to the target departure frequency and the passenger flow of each single-point section to obtain multiple target departure times, including: updating the expected passenger capacity of a single vehicle according to the target departure frequency and the passenger flow of each single-point section; obtaining multiple target departure times according to the expected passenger capacity of a single vehicle and multiple initial departure times.

[0007] According to an embodiment of the present disclosure, multiple target departure times are obtained based on the expected passenger capacity of a single vehicle and multiple initial departure times, including: calculating the cumulative passenger flow of the nth section corresponding to the nth initial departure time under the first time period, n≥1; determining the nth predicted passenger capacity corresponding to the nth initial departure time based on the expected passenger capacity of the single vehicle and the cumulative passenger flow of the nth section; determining the nth target departure time from the cumulative passenger flow curve based on the nth predicted passenger capacity.

[0008] According to an embodiment of the present disclosure, the train departure time updating method also includes: drawing a cumulative passenger flow curve based on the N initial departure times in the first time period and the N single-point section passenger flows corresponding to the N initial departure times, wherein the horizontal axis of the cumulative passenger flow curve is time and the vertical axis is the section passenger flow.

[0009] According to an embodiment of the present disclosure, the initial departure frequency is updated using the predicted cross-sectional passenger flow in the second time period to obtain a target departure frequency, including: calculating the length of a congested section where the predicted cross-sectional passenger flow in the second time period is greater than the expected congestion; calculating the proportion of the congested line length in the total line length to obtain the proportion of congested sections; and when the proportion of congested sections is less than or equal to the upper limit of the proportion of congested sections, calculating the target departure frequency based on the predicted cross-sectional passenger flow in the second time period.

[0010] According to an embodiment of the present disclosure, the train departure time updating method further includes: generating a path planning strategy for multiple trains to travel from a first train number to a second train number based on multiple target departure times and predetermined constraints.

[0011] According to an embodiment of the present disclosure, the predetermined constraints include at least one of the following constraints: a first constraint, the first train or the second train is only executed by one train; a second constraint, each train departs from the same yard at most once; a third constraint, a train enters and leaves the first train an equal number of times; a fourth constraint, when a train executes the second train after completing the first train, the departure time of the first train is not earlier than the arrival time of the second train; a fifth constraint, when a train departs from the yard to execute the first train and then executes the second train, the departure station of the first train and the arrival station of the second train are the same.

[0012] The second aspect of the present disclosure provides a train departure time updating device, comprising: a cloud platform, for performing the following operations: obtaining the actual cross-sectional passenger flow in a first time period and the predicted cross-sectional passenger flow in the first time period; obtaining multiple initial departure times in the first time period obtained by updating the predicted cross-sectional passenger flow in the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time; inputting the actual cross-sectional passenger flow in the first time period into a trained cross-sectional passenger flow prediction model to obtain the predicted cross-sectional passenger flow corresponding to the second time period; using the predicted cross-sectional passenger flow in the second time period to update the initial departure frequency to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-sectional passenger flow in the first time period; updating multiple initial departure times according to the target departure frequency and each single-point cross-sectional passenger flow to obtain multiple target departure times, so as to depart according to the target departure time.

[0013] The third aspect of the present disclosure provides a train departure time updating device, comprising: a first acquisition module, used to obtain the actual cross-sectional passenger flow in a first time period and the predicted cross-sectional passenger flow in the first time period; a second acquisition module, used to obtain multiple initial departure times in the first time period obtained by updating the predicted cross-sectional passenger flow in the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time; an input module, used to input the actual cross-sectional passenger flow in the first time period into a trained cross-sectional passenger flow prediction model to obtain the predicted cross-sectional passenger flow corresponding to the second time period; a first updating module, used to update the initial departure frequency using the predicted cross-sectional passenger flow in the second time period to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-sectional passenger flow in the first time period; a second updating module, used to update multiple initial departure times according to the target departure frequency and each single-point cross-sectional passenger flow to obtain multiple target departure times, so as to depart according to the target departure time.

[0014] The fourth aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned train departure time update method.

[0015] The fifth aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned train departure time updating method.

[0016] The sixth aspect of the present disclosure further provides a computer program product, comprising a computer program, which implements the above-mentioned train departure time updating method when executed by a processor.

[0017] The seventh aspect of the present disclosure also provides a train comprising a train departure time updating device to implement the train departure time updating method.

[0018] According to the embodiments of the present disclosure, the planning of the conventional departure time relies on historical experience or fixed planning, and the response to sudden passenger flow is not timely. The present disclosure adjusts the departure frequency and departure time by periodically obtaining the actual section passenger flow in the first time period and predicting the predicted section passenger flow in the second time period, shortens the time difference from perceiving the passenger flow change to adjusting the transport capacity. In the period or section of the second time period with low predicted section passenger flow, the departure frequency can be automatically reduced to reduce the empty or low load operation; when the predicted section passenger flow in the second time period is predicted to surge (such as the early morning peak), the departure frequency (i.e. the updated target departure frequency) can be increased in advance. By increasing the departure frequency in the peak period in advance, the passenger waiting time and the gathering scale on the platform are reduced, and the average waiting time of passengers is shortened. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure taken in conjunction with the accompanying drawings, in which:

[0020] Figure 1 A scenario diagram of application of the train departure time updating method according to the embodiments of the present disclosure is schematically shown;

[0021] Figure 2 A system architecture diagram of the train departure time updating system according to the embodiments of the present disclosure is schematically shown;

[0022] Figure 3 A flowchart of the train departure time updating method according to the embodiments of the present disclosure is schematically shown;

[0023] Figure 4 A curve diagram of the actual section passenger flow in the first time period according to the embodiments of the present disclosure is schematically shown;

[0024] Figure 5 A cumulative passenger flow curve diagram according to the embodiments of the present disclosure is schematically shown;

[0025] Figure 6 A structure block diagram of the train departure time updating device according to the embodiments of the present disclosure is schematically shown; and

[0026] Figure 7 A block diagram of an electronic device suitable for implementing the train departure time updating method according to the embodiments of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0030] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0031] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] The static departure scheduling scheme is a basic blueprint for daily operation of an enterprise. The static departure scheduling scheme usually does not change for a long time until a new timetable is generated, which can cause obvious disadvantages. When the static scheme is executed, a late arrival of a class can cause a corresponding late departure of a subsequent class. In special cases, such as major activities or serious traffic accidents, the operation time of a class can be generally lengthened, and a class chain originally established in the static vehicle scheme can no longer be established, which can cause a phenomenon that the class cannot be normally executed according to the planned scheme. Moreover, when a passenger flow feature changes, the original scheduling scheme cannot usually point to a system optimal target.

[0033] Therefore, an embodiment of the present disclosure provides a train departure time updating method, which comprises: obtaining an actual section passenger flow in a first time period and a predicted section passenger flow in the first time period; obtaining a plurality of initial departure times in the first time period updated by the predicted section passenger flow in the first time period, and a single-point section passenger flow corresponding to each initial departure time; inputting the actual section passenger flow in the first time period into a trained section passenger flow prediction model to obtain a predicted section passenger flow corresponding to a second time period; updating an initial departure frequency by using the predicted section passenger flow in the second time period to obtain a target departure frequency, wherein the initial departure frequency is updated by the predicted section passenger flow in the first time period; updating the plurality of initial departure times according to the target departure frequency and the single-point section passenger flow to obtain a plurality of target departure times, so as to depart according to the target departure times.

[0034] Figure 1 An application scenario diagram of a train departure time updating method, device, equipment, medium, program product and train according to an embodiment of the present disclosure is schematically shown.

[0035] As shown in Figure 1 The application scenario 100 according to the embodiment can comprise a first terminal device 101, a second terminal device 102, a server 103 and a network 104. The network 104 is a medium for providing a communication link between the first terminal device 101, the second terminal device 102 and the server 103. The network 104 can comprise various connection types, such as a wired, wireless communication link or an optical fiber cable, etc. The first terminal device 101 can be a transportation device, such as a train, etc. The second terminal device 102 can be a road testing device installed on both sides of a road, such as a passenger flow counter, etc.

[0036] A user can use the first terminal device 101 and the second terminal device 102 to interact with the server 103 through the network 104 to receive or send messages, etc. Various communication client applications, such as data analysis software, etc. (only as an example), can be installed on the first terminal device 101 and the second terminal device 102.

[0037] The second terminal device 102 may be any electronic device with a display screen, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0038] The server 103 may be a server that provides various services, predicts the actual section passenger flow received, obtains the predicted section passenger flow, and updates the departure frequency and departure time according to the predicted section passenger flow, and performs various data analysis and other processing, and feeds back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0039] It should be noted that the train departure time update method provided by the embodiment of the present disclosure can generally be executed by the server 103. Accordingly, the train departure time update device provided by the embodiment of the present disclosure can generally be set in the server 103. The train departure time update method provided by the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 103 and can communicate with the first terminal device 101, the second terminal device 102 and / or the server 103. Correspondingly, the train departure time update device provided by the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 103 and can communicate with the first terminal device 101, the second terminal device 102 and / or the server 103. In addition, the train departure time update device provided by the embodiment of the present disclosure can also be set in the terminal device and directly executed by the terminal device.

[0040] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0041] Figure 2 The system architecture diagram of the train departure time update system according to an embodiment of the present disclosure is schematically shown.

[0042] like Figure 2 As shown in the figure, the train departure time update system includes on-board equipment, road test equipment and cloud platform.

[0043] The vehicle-side equipment includes the on-board diagnostic system (OBD), infrared passenger flow counter, on-board display terminal and on-board unit (OBU). Among them, the infrared passenger flow counter, OBD and on-board display terminal are connected to the OBU respectively.

[0044] OBD obtains real-time running speed and position data through the train OBD interface.

[0045] Infrared passenger flow counter is deployed at the passenger boarding and alighting position of the train to obtain the section passenger flow. The section passenger flow data includes but is not limited to vehicle ID, start counting time, end counting time, boarding number, and alighting number.

[0046] The on-board display terminal is deployed at the train instrument panel position to display the dispatching instruction and the light group display state.

[0047] The OBU interacts with the road side unit (RSU) through the PC5 interface to realize the transmission of the priority passage request to the RSU at a specific frequency; receives the signal light control state data and transmits the light group display state to the on-board display terminal. The OBU interacts with the cloud dispatching platform to realize the transmission of the train state data to the cloud platform at a specific frequency; and receives the dispatching instruction returned by the cloud platform and transmits it to the on-board display terminal to instruct the driver. The fields of the priority passage request include but are not limited to vehicle ID, time, running speed and position; the train state data includes but is not limited to vehicle ID, time, running speed and position, section passenger flow data, and equipment running state.

[0048] The road side equipment includes a video passenger flow counter, a traffic signal control machine, a multi-access edge computing (MEC), an RSU, and an industrial switch. The video passenger flow counter, the traffic signal control machine, and the RSU are connected with the industrial switch respectively; the industrial switch is connected with the cloud platform through the metropolitan area network; and the traffic signal control machine and the RSU are connected with the MEC respectively.

[0049] The video passenger flow counter is deployed at the site along the line to obtain the site passenger flow data. The site passenger flow data includes but is not limited to site ID, time, and number of people at the site.

[0050] The traffic signal control machine is deployed at the intersection along the line to control the signal light group.

[0051] The MEC is deployed at the intersection along the line to provide edge computing services, receive the priority passage request transmitted by the RSU, predict the time of the rapid rail reaching the intersection based on a preset algorithm, receive the current signal control scheme transmitted by the traffic signal control machine, adjust the signal control scheme in time based on a preset algorithm and return it to the traffic signal control machine for execution, and ensure the priority passage of the rapid rail when it reaches the intersection.

[0052] The RSU is deployed at the intersection and the site along the line and interacts with the OBU through the PC5 interface to receive the priority passage request and transmit the signal light control state data.

[0053] Industrial switches are deployed at intersections and stations along the line as the communication hub of the roadside module, realizing data flow in the roadside LAN and road-cloud interaction. The intersection device or station device transmits the signal lamp control state data or passenger flow state data to the cloud platform terminal through the corresponding switch; the cloud platform terminal transmits the signal lamp control instruction to the traffic signal control machine through the switch. The signal lamp control state data includes but is not limited to intersection ID, time, lamp group display state, signal control scheme, device running state; the passenger flow state data includes but is not limited to station ID, time, station passenger flow data, device running state.

[0054] The cloud platform is connected with the vehicle-mounted device and the roadside device through the LAN to realize data interaction and information transmission. The cloud platform includes a running state monitoring module, a driving plan compilation module and a running task allocation module.

[0055] The running state monitoring module is used to obtain real-time monitoring of vehicle running state, device running state and passenger flow state from the vehicle-mounted device through the LAN, and signal lamp control state data from the roadside device.

[0056] The driving plan compilation module is used to process and predict passenger flow data according to the obtained real-time data, make static and real-time update of the running plan, generate a real-time running plan that meets the operation cost and passenger cost under the constraint of the current vehicle fleet running state, and display in the form of a running graph.

[0057] The running task allocation module is used to allocate tasks to specific vehicles and complete the issuance of dispatch instructions.

[0058] The following will be based on Figure 1 the described scenario and Figure 2 the described system architecture diagram, through Figure 3 a detailed description of the train departure time updating method of the disclosed embodiment.

[0059] Figure 3 A flowchart of a train departure time updating method according to an embodiment of the disclosure is schematically shown.

[0060] As Figure 3 shown, the train departure time updating method of this embodiment includes operations S310-S350.

[0061] In operation S310, the actual section passenger flow of a first time period and the predicted section passenger flow of the first time period are obtained.

[0062] According to an embodiment of the present disclosure, the first time period can be any preset time period, such as one minute, one hour, one day, one week, one month, one quarter, etc. For ease of calculation, any time period in the embodiment of the present disclosure is one hour. Therefore, the actual cross-sectional passenger flow corresponding to any hour can also be directly referred to as the hourly cross-sectional passenger flow. For example, the 7:00-8:00 period during the morning rush hour is one time period, and the 8:00-9:00 period is another time period. The predicted cross-sectional passenger flow for the first time period is obtained by predicting the actual cross-sectional passenger flow in the time period before the first time period.

[0063] According to an embodiment of the present disclosure, the hourly section passenger flow may be actual passenger flow data of each section within the time period collected through devices or channels such as sensors, ticketing systems, or traffic counters.

[0064] In operation S320, a plurality of initial departure times in the first time period, which are updated based on the predicted cross-sectional passenger flow in the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time are obtained.

[0065] According to an embodiment of the present disclosure, an initial driving plan can be preliminarily prepared based on historical data within a historical period. The plan includes multiple initial departure times, and the single-point cross-sectional passenger flow corresponding to each time. For example, the initial departure time from 5:00 to 6:00 on Wednesday can be determined by referring to the driving plan for the same time period on Monday this week. However, because the initial driving plan is based on historical data, it is difficult to accurately reflect the passenger flow conditions on the day or at the current time, so it needs to be updated in combination with the actual cross-sectional passenger flow on the day. Specifically, according to the above operation S310, the actual cross-sectional passenger flow from 5:00 to 6:00 on Wednesday is obtained. And based on the actual cross-sectional passenger flow from 5:00 to 6:00 on Wednesday, the predicted cross-sectional passenger flow from 6:00 to 7:00 on Wednesday is obtained, as well as the single-point cross-sectional passenger flow at each departure time between 6:00 and 7:00.

[0066] Taking the first time period of 7:00-8:00 as an example, the hourly section passenger flow of each section within this time period is shown in Table 1.

[0067] Table 1

[0068]

[0069] In the 7:00-8:00 time period, a plurality of initial departure times can be included, as shown in Table 2, and the 7:00-8:00 time period can include 7:01, 7:19, 7:30, 7:36, 7:51, and the like. Each initial departure time corresponds to a single-point section passenger flow, and these single-point section passenger flows reflect the expected passenger flow at the corresponding time and specific section. The sum of the plurality of single-point section passenger flows is equal to the predicted section passenger flow of the first time period.

[0070] Table 2

[0071]

[0072] In operation S330, the actual section passenger flow of the first time period is input to the trained section passenger flow prediction model to obtain the predicted section passenger flow corresponding to the second time period.

[0073] According to an embodiment of the present disclosure, the section passenger flow prediction model is trained by the following method:

[0074] Step 10: Taking the hourly section passenger flow as input, the input data is feature-extracted by a convolutional neural network (CNN), and the local spatial features of the input data are extracted by a convolutional layer and a pooling layer to capture the passenger flow distribution characteristics of different sections.

[0075] Step 20: The feature sequence extracted by the CNN is input to a long short-term memory network (LSTM), and the time-dependent relationship between the passenger flow sequences is modeled by a recurrent layer.

[0076] Step 30: A supervised learning method is adopted, the section passenger flow of the current time period is taken as the target value, the section passenger flow of the historical time period is used for training, and the station passenger flow change factor is introduced to optimize the model parameters so that the prediction result is as close to the true value as possible. During the training process, the mean square error is used as the loss function to measure the difference between the prediction result and the true value, and the back propagation algorithm is used to update the model parameters.

[0077] According to an embodiment of the present disclosure, thus, the actual section passenger flow of the first time period is input to the model, and the predicted section passenger flow of the second time period is output.

[0078] In operation S340, the initial departure frequency is updated using the predicted section passenger flow of the second time period to obtain the target departure frequency, wherein the initial departure frequency is updated from the predicted section passenger flow of the first time period.

[0079] According to an embodiment of the present disclosure, if the predicted cross-sectional passenger flow in the second time period increases due to a surge in commuters during the morning rush hour, the departure frequency is increased, for example, by shortening the departure interval, to ensure that capacity matches demand and avoid passenger backlogs and delays. If the predicted cross-sectional passenger flow in the second time period is low during the afternoon off-peak period, the departure frequency is reduced, for example, by extending the departure interval, to reduce idle driving and lower operating costs. Thus, by predicting the predicted cross-sectional passenger flow for the immediately following cycle based on the actual cross-sectional passenger flow in the previous cycle, the target departure frequency is more closely aligned with the actual passenger flow demand in the next cycle.

[0080] In operation S350, a plurality of initial departure times are updated according to the target departure frequency and the passenger flow of each single-point section to obtain a plurality of target departure times, so that the train can depart according to the target departure times.

[0081] According to the embodiments of the present disclosure, the departure interval (such as 8 minutes / shift) is determined based on the target departure frequency, and the basic time points need to be replanned according to this interval. Each initial departure time corresponds to a single-point section passenger flow. As shown in Table 2, the passenger flow of Section 1 is expected to be 2 people at the time of departure at 7:19. If the single-point passenger flow at this moment is low, the vehicle can be dispatched when the station is about to reach or has reached the predetermined number of people to avoid empty trips where "the vehicle arrives but the passengers do not". Otherwise, the vehicle needs to be dispatched in advance. The final departure time point not only meets the interval requirements of the target frequency, but also takes into account the real-time pressure of the specific section.

[0082] For example, if the passenger flow at a certain section is predicted to reach 200 people (risk of overloading) when the train departs at 7:16, and the passenger flow at a single point at 7:19 is only 120 people, the departure time of 7:16 will be postponed to 7:19 to avoid insufficient capacity during peak hours; if a small passenger flow peak suddenly occurs at a certain section before the departure of 7:24 (such as the end of a concert), a temporary train can be inserted or the departure time can be advanced to quickly evacuate passengers.

[0083] According to the embodiments of the present disclosure, the traditional planning of departure times relies on historical experience or fixed plans, and does not respond to sudden passenger flow situations in a timely manner. The present disclosure periodically obtains the actual cross-sectional passenger flow of the first time period and predicts the predicted cross-sectional passenger flow of the second time period, and uses the latest actual data to adjust the departure frequency and departure time, thereby shortening the time difference from sensing passenger flow changes to adjusting transport capacity. During the time periods or sections where the predicted cross-sectional passenger flow of the second time period is low, the departure frequency can be automatically reduced to reduce empty or low-load operation; when a surge in the predicted cross-sectional passenger flow of the second time period is predicted (such as the morning rush hour), the departure frequency can be increased in advance (i.e., the updated target departure frequency). By increasing the departure frequency during peak hours in advance, the passenger detention time and gathering size at the platform are reduced, and the average waiting time of passengers is shortened.

[0084] According to an embodiment of the present disclosure, the actual cross-sectional passenger flow of the first time period can also be calculated according to the following method. Specifically, the actual cross-sectional passenger flow of any time period is calculated based on the actual cross-sectional passenger flow of the total period. The actual cross-sectional passenger flow of any time period is the actual number of passengers carried by a certain section during the period, in person / hour. The actual cross-sectional passenger flow of the total period is the actual number of passengers carried by a certain train during the travel on a certain section, in person. According to the direction of travel of the express rail, the directed road entity between station m and the downstream adjacent station m+1 is called section m. The actual cross-sectional passenger flow of any time period is calculated based on the actual cross-sectional passenger flow of the total period, referring to formula (1):

[0085] Formula (1)

[0086] in, is the actual passenger flow of section m on route i and direction j in time period n; is the actual passenger flow of train number k on line i and direction j at section m; Refers to the set of trains whose running time on section m is all within time period n; Refers to the set of trains whose running time on section m is partly within time period n; Refers to the portion of the running time of train number k on line i and direction j on section m that falls within time period n; Refers to the running time of train number k on line i and direction j on section m.

[0087] The actual cross-sectional passenger flow of the total cycle is calculated as follows: based on the number of passengers who boarded the train k at station m, the number of passengers who got off the train k at station m, and the actual cross-sectional passenger flow of the train k at station m-1, the total cross-sectional passenger flow of the train k at station m is calculated. The calculation reference formula (2) is:

[0088] Formula (2)

[0089] in, is the actual passenger flow of train number k on line i and direction j at section m-1; is the number of people who boarded the train number k on route i and direction j at station m; is the number of people who get off at stop m for train number k on route i and direction j. The number of people getting on and off the train is collected by the infrared passenger flow counter in the on-board equipment.

[0090] According to the embodiments of the present disclosure, when there are a large number of people at a station, there may be stranded passengers at the station. On this basis, the actual cross-sectional passenger flow of any time period must be calculated in combination with the crowded cross-sectional passenger flow. The crowded cross-sectional passenger flow refers to the number of passengers stranded at the station due to the crowding effect, in units of people. Based on the passenger flow status data and combined with the train status data, the passenger flow data of the station located at the time step immediately after the end counting time in the cross-sectional passenger flow data is extracted and used as the crowded cross-sectional passenger flow of the station after the corresponding train visit. When calculating the actual cross-sectional passenger flow of the total period, the crowded cross-sectional passenger flow is added to calculate the actual cross-sectional passenger flow of any time period after compensation.

[0091] According to an embodiment of the present disclosure, updating the initial departure frequency using the predicted cross-sectional passenger flow for the second time period to obtain a target departure frequency may include the following steps: Calculating the length of a congested section where the predicted cross-sectional passenger flow for the second time period exceeds the desired congestion level; Calculating the proportion of the congested route length to the total route length to obtain the congested route ratio; and Calculating the target departure frequency based on the predicted cross-sectional passenger flow for the second time period if the congested route ratio is less than or equal to the upper limit of the congested route ratio.

[0092] According to the embodiment of the present disclosure, the proportion of line length of "actual cross-section passenger flow > expected congestion" is used as a constraint condition, that is, the proportion of congested sections is less than or equal to the upper limit of the proportion of congested sections. For example, if the upper limit of the proportion of congested sections is set at 20%, it means that the length of the line that exceeds the expected congestion must be controlled to not exceed one-fifth of the total length. When the proportion of lines that exceed the expected congestion in a certain period of time is too high (such as a surge in passenger flow in some sections during peak hours), the frequency of departure is increased to divert passenger flow and reduce cross-section congestion; conversely, if the proportion is lower than the upper limit of the proportion of congested sections, the frequency of departure can be appropriately reduced to optimize resource allocation. Through this constraint, it is ensured that the train will not be overcrowded on a large scale or for a long time during operation, thereby maintaining service indicators such as passenger waiting comfort, riding space and line punctuality.

[0093] According to an embodiment of the present disclosure, the target departure frequency is calculated based on the predicted cross-sectional passenger flow in the second time period, referring to formula (3):

[0094] Formula (3)

[0095] in, is the departure frequency in time period j (vehicles / h); is the expected passenger capacity of the vehicle in time period j (people); is the total length of the line (m); is the maximum hourly cross-sectional passenger flow in time period j (persons / h); is the statutory minimum expected departure frequency in time period j (vehicles / h); is the distance between station m and the next adjacent station m = 1 (m) ; is the proportion of the total length of the line occupied by the crowded line allowed in period j; is the set of all stations whose hourly cross-section passenger flow is greater than in period j.

[0096] According to an embodiment of the present disclosure, is the passenger-kilometer number (person-km) under the cross-section m passenger flow curve in period j, which reflects the variation of the hourly cross-section passenger flow in different passenger transport cross-sections in a specific period. The passenger-kilometer number under the cross-section m passenger flow curve in period j is equal to the sum of the product of the hourly cross-section passenger flow of each station in period j and the distance between adjacent stations. Exemplarily, taking the period 7:00-8:00 in Table 1 as the first time period, the passenger-kilometer number in the period 7:00-8:00 = 16 x 0.169 + 21 x 0.159 +... + 21 x 0.381.

[0097] Further, taking the period 7:00-8:00 in Table 1 as the first time period, the hourly cross-section passenger flow curve graph in the period 7:00-8:00 is drawn according to the hourly cross-section passenger flow of each station in the first time period.

[0098] Figure 4 The actual cross-section passenger flow curve graph in the first time period according to an embodiment of the present disclosure is schematically shown.

[0099] As shown in Figure 4 , the abscissa is the cross-section number composed of each station, and the ordinate is the actual cross-section passenger flow in the first time period. According to the actual cross-section passenger flow curve graph, the variation trend of the passenger flow of different cross-sections can be clearly obtained.

[0100] Further, in the case that the updated target departure frequency is obtained according to formula (3), the departure according to the target departure frequency needs to update the departure time of each vehicle according to the target departure frequency.

[0101] According to an embodiment of the present disclosure, the plurality of initial departure times are updated according to the target departure frequency and the single-point cross-section passenger flow to obtain a plurality of target departure times, including: updating the single-vehicle expected passenger capacity according to the target departure frequency and the single-point cross-section passenger flow; and obtaining the plurality of target departure times according to the single-vehicle expected passenger capacity and the plurality of initial departure times.

[0102] The expected passenger capacity per vehicle is updated based on the target departure frequency and the passenger flow at each single-point section. Specifically, the station with the largest hourly passenger flow is first determined from each station, and the maximum hourly section passenger flow corresponding to this station is calculated. Based on the maximum hourly section passenger flow corresponding to this station and the target departure frequency, the expected passenger capacity per vehicle is calculated using Formula (4).

[0103] Formula (4)

[0104] For example, taking the time period of 7:00-8:00 as an example, as shown in Table 1, the section corresponding to the maximum hourly section passenger flow is Section 7 (also Station 7), and the maximum hourly section passenger flow is =4+10+6+2+3=25 (people), the target departure frequency determined in the previous step =3.53 (vehicles / h), then the expected passenger capacity =25 / 3.53≈8 (people / vehicle).

[0105] According to an embodiment of the present disclosure, a departure schedule is compiled based on departure frequency to enhance the consistency between vehicle departure times and fluctuating passenger demand. A schedule determination method is adopted that achieves a balance between the hourly maximum passenger flow section and the average passenger capacity.

[0106] Furthermore, before updating the multiple target departure times according to the expected passenger capacity of a single vehicle and the multiple initial departure times, it is necessary to draw a cumulative passenger flow curve to obtain the updated target departure time by drawing.

[0107] Figure 5 The figure schematically shows a cumulative passenger flow curve diagram according to an embodiment of the present disclosure.

[0108] Based on the N initial departure times in the first time period and the N single-point cross-sectional passenger flows corresponding to these N initial departure times, a cumulative passenger flow curve is drawn. The abscissa of the cumulative passenger flow curve represents time, and the ordinate represents cross-sectional passenger flows. N represents the number of departure times in a time period. For example, as shown in Table 1, if the first time period is 7:00–8:00, then N = 5; if the first time period is 8:00–9:00, then N = 3.

[0109] Furthermore, before drawing the cumulative passenger flow curve, it is necessary to first calculate N cumulative section passenger flows corresponding to the N initial departure times based on the N initial departure times and the N single-point section passenger flows corresponding to the N initial departure times.

[0110] According to an embodiment of the present disclosure, multiple target departure times are obtained based on the expected passenger capacity of a single vehicle and multiple initial departure times, including:

[0111] First, calculate the cumulative passenger flow of the nth section corresponding to the nth initial departure time in the first time period, where n≥1.

[0112] Specifically, the nth cumulative cross-sectional passenger flow is equal to the sum of the n single-point cross-sectional passenger flows. As shown in Table 1, the cumulative cross-sectional passenger flow at Station 1 at 7:01 is 2, the cumulative cross-sectional passenger flow at 7:19 is 10, the cumulative cross-sectional passenger flow at 7:30 is 15, and so on. This is not repeated here.

[0113] Therefore, after calculating the N cumulative cross-sectional passenger flows corresponding to the N initial departure times according to the above method, the cumulative passenger flow curve is drawn.

[0114] like Figure 5 As shown, the cumulative cross-sectional passenger flow at 7:00 is 0, the cumulative cross-sectional passenger flow at 7:01 is 4, the cumulative cross-sectional passenger flow at 7:19 is 14, and so on.

[0115] Secondly, according to the expected passenger capacity of a single vehicle and the cumulative passenger flow of the nth section, the nth predicted passenger capacity corresponding to the nth initial departure time is determined.

[0116] When n = 1, at 7:01, the cumulative cross-sectional passenger flow at station 1 is 2. This value indicates that the passenger flow at this time has not yet reached, and is even far below, the expected passenger capacity of 8 for a vehicle. If the vehicle were to depart at this time, it would not be fully loaded. Therefore, to increase the vehicle's full load factor, it is advisable to wait until the predicted passenger flow reaches the expected passenger capacity of 8 before departing. Therefore, at 7:01, the nth predicted passenger capacity is 8.

[0117] When n = 2, at 7:19, the cumulative cross-sectional passenger flow at station 1 is 10. This value indicates that while the passenger flow at this time has reached the expected passenger capacity of one vehicle, it has not yet reached the expected passenger capacity of two vehicles, and is even far below the expected passenger capacity of the second vehicle. If a second vehicle is dispatched at this time, it will not be fully loaded. Therefore, to increase the vehicle load factor, it is advisable to wait until the predicted passenger flow at the second time reaches the expected passenger capacity of 8 before dispatching the vehicle. Therefore, at 7:19, the nth predicted passenger capacity is 16.

[0118] Similarly, the predicted passenger capacity corresponding to other initial departure times (7:30, 7:36, 7:51) within the time period is calculated respectively.

[0119] Finally, the nth target departure time is determined from the cumulative passenger flow curve according to the nth predicted passenger capacity.

[0120] In view of the foregoing steps, we expect to depart when the accumulated section passenger flow at the site reaches or is about to reach the expected passenger capacity. Therefore, the specific operation is as follows: take the intersection of the predicted passenger capacity corresponding to the nth initial departure time on the ordinate as the starting point, draw a line horizontally to the right along the abscissa; when the line intersects the cumulative passenger flow curve, draw a vertical line downward from the intersection point along the ordinate; the time when the vertical line intersects the abscissa is determined as the target departure time. As shown in FIG. 8, when n = 1, the first predicted passenger capacity is 8, find the point with ordinate 8 along the direction of the dashed arrow, draw a line vertically downward when it intersects the cumulative passenger flow curve, and the intersection point with the time axis is the first target departure time corresponding to the first initial departure time. In this way, the target departure time corresponding to each initial departure time is calculated. Figure 5

[0121] According to an embodiment of the present disclosure, on the basis of updating the target departure frequency and the target departure time by using the actual section passenger flow of the first time period, under the condition of a given timetable, optimal execution vehicles are allocated to all trains, and a train chain required to be executed is arranged for each vehicle, so as to achieve optimal allocation of transport resources, and a train operation plan optimization model with the minimum total operation cost as the target is established. Specifically, according to the multiple target departure times and predetermined constraint conditions, a path planning strategy of multiple trains from a first train to a second train is generated.

[0122] The train operation plan optimization model refers to formula (5):

[0123] Formula (5)

[0124] The predetermined constraint conditions include at least one of the following constraint conditions.

[0125] The first constraint condition: there is only one train executing the first train.

[0126] .

[0127] Or, there is only one train executing the second train.

[0128] .

[0129] The second constraint condition: each train departs from the same station at most once.

[0130] 1 =1 d; =1 .

[0131] The third constraint condition: the number of times that a train enters the first train and leaves the first train is equal. ​

[0132] 0 =1 d; =1 ; =1 b.

[0133] The fourth constraint condition: When a train runs the second train after the first train, the departure time of the second train shall not be earlier than the arrival time of the first train.

[0134] =1 d; =1 ; =1 b; =1 b.

[0135] The fifth constraint condition: When a train departs from the yard to perform the first trip and then the second trip, the departure station of the first train and the arrival station of the second train are the same.

[0136] =1,..,d; =1,.., ; =1,..,b; =1,..,b.

[0137] Among them, d is the number of parking lots, k is the parking lot sequence number, is the parking lot capacity of the kth parking lot, a is the vehicle number, b is the number of vehicles, i and j are different vehicle numbers, is the departure time of train number j, is the arrival time of train number i, is the departure station of train number i, is the arrival station of train number j, is the mileage between the arrival station of train number i and the departure station of train number j, is the unit mileage operating cost, in yuan / km, It is the fixed cost for vehicle attendance, in Yuan / vehicle.

[0138] in, , is the decision variable. =1 means that vehicle a departing from parking lot k will take trip i and then take trip j; =0 Conversely, vehicle a departing from parking lot k will not continue to perform trip j after completing trip i. If i is 0, it indicates an exit mission; if j is 0, it indicates a return mission.

[0139] Based on this driving plan optimization model, the optimal vehicle for each train is matched within a given timetable, and the train chain to be executed by each vehicle is planned, achieving optimal allocation of transport resources and effectively controlling total operating costs. The initial driving plan is then updated based on the resulting solution, and the operation diagram is updated based on the updated target driving plan. This is then displayed on the vehicle's display terminal for reference by the driver or the autonomous driving system.

[0140] According to the embodiments of the present disclosure, based on updates to the operational diagram, operational plan change tasks are broken down and assigned to specific vehicles or intersection signals, completing the issuance of dynamic operational scheduling instructions. Specific instructions include passenger waiting times, delayed or advanced departure times, and more. In other words, building on the static vehicle approach, by obtaining the real-time status of available vehicles and, while satisfying certain scheduling objectives, finding feasible dynamic vehicle scheduling solutions minimizes the impact of abnormal interference on the planned solution.

[0141] Based on the above train departure time updating method, the present disclosure also provides a train departure time updating device. Figure 6 The device is described in detail.

[0142] Figure 6 The structural block diagram of the train departure time updating device according to an embodiment of the present disclosure is schematically shown.

[0143] like Figure 6 As shown, the train departure time updating device 600 of this embodiment includes a first acquisition module 610 , a second acquisition module 620 , an input module 630 , a first update module 640 and a second update module 650 .

[0144] The first acquisition module 610 is used to obtain the actual cross-sectional passenger flow in the first time period and the predicted cross-sectional passenger flow in the first time period. In one embodiment, the first receiving module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0145] The second acquisition module 620 is configured to acquire multiple initial departure times for the first time period, updated from the predicted cross-sectional passenger flow for the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time. In one embodiment, the first control module 620 may be configured to perform operation S220 described above, which will not be further described here.

[0146] The input module 630 is used to input the actual cross-sectional passenger flow in the first time period into the trained cross-sectional passenger flow prediction model to obtain the predicted cross-sectional passenger flow corresponding to the second time period. In one embodiment, the first sending module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0147] The first updating module 640 is configured to update the initial departure frequency using the predicted cross-sectional passenger flow during the second time period to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-sectional passenger flow during the first time period. In one embodiment, the second control module 640 may be configured to perform operation S240 described above, which will not be further described here.

[0148] The second updating module 650 is used to update the multiple initial departure times according to the target departure frequency and the passenger flow of each single-point section to obtain multiple target departure times so that the train can depart according to the target departure times. In one embodiment, the second control module 650 can be used to perform the operation S250 described above, which will not be repeated here.

[0149] According to an embodiment of the present disclosure, the second updating module 650 includes: an updating submodule and an obtaining submodule.

[0150] The updating submodule is used to update the expected passenger capacity of a single vehicle based on the target departure frequency and the passenger flow of each single-point section; the obtaining submodule is used to obtain multiple target departure times based on the expected passenger capacity of a single vehicle and multiple initial departure times.

[0151] According to an embodiment of the present disclosure, the obtaining submodule includes: a calculating unit, a first determining unit, and a second determining unit.

[0152] The calculation unit is used to calculate the cumulative passenger flow of the nth section corresponding to the nth initial departure time in the first time period, where n≥1; the first determination unit is used to determine the nth predicted passenger capacity corresponding to the nth initial departure time based on the expected passenger capacity of a single vehicle and the cumulative passenger flow of the nth section; the second determination unit is used to determine the nth target departure time from the cumulative passenger flow curve based on the nth predicted passenger capacity.

[0153] According to an embodiment of the present disclosure, the train departure time updating device further includes: a drawing module.

[0154] The drawing module is used to draw a cumulative passenger flow curve based on the N initial departure times in the first time period and the N single-point section passenger flows corresponding to the N initial departure times, wherein the horizontal axis of the cumulative passenger flow curve is time and the vertical axis is the section passenger flow.

[0155] According to an embodiment of the present disclosure, the first update module 640 includes: a first calculation submodule, a second calculation submodule, and a third calculation submodule.

[0156] The first calculation submodule is used to calculate the length of the congested section where the predicted cross-sectional passenger flow in the second time period is greater than the expected congestion degree; the second calculation submodule is used to calculate the proportion of the congested line length to the total line length to obtain the congested section proportion; and the third calculation submodule is used to calculate the target departure frequency based on the predicted cross-sectional passenger flow in the second time period when the congested section proportion is less than or equal to the upper limit of the congested section proportion.

[0157] According to an embodiment of the present disclosure, the train departure time updating device further includes: a generating module.

[0158] The generation module is used to generate a path planning strategy for multiple trains to travel from a first train to a second train based on multiple target departure times and predetermined constraints.

[0159] According to an embodiment of the present disclosure, the predetermined constraints include at least one of the following constraints: a first constraint, the first train or the second train is only executed by one train; a second constraint, each train departs from the same yard at most once; a third constraint, a train enters and leaves the first train an equal number of times; a fourth constraint, when a train executes the second train after completing the first train, the departure time of the first train is not earlier than the arrival time of the second train; a fifth constraint, when a train departs from the yard to execute the first train and then executes the second train, the departure station of the first train and the arrival station of the second train are the same.

[0160] According to embodiments of the present disclosure, any multiple modules among the first acquisition module 610, the second acquisition module 620, the input module 630, the first update module 640, and the second update module 650 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the first acquisition module 610, the second acquisition module 620, the input module 630, the first update module 640, and the second update module 650 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of software, hardware, and firmware, or any suitable combination of these. Alternatively, at least one of the first acquisition module 610 , the second acquisition module 620 , the input module 630 , the first update module 640 , and the second update module 650 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0161] Figure 7 A block diagram of an electronic device suitable for implementing a method for updating train departure times according to an embodiment of the present disclosure is schematically shown.

[0162] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage portion 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0163] Various programs and data required for the operation of the electronic device 700 are stored in the RAM 703. The processor 701, ROM 702, and RAM 703 are connected to each other via a bus 704. The processor 701 executes the various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than the ROM 702 and RAM 703. The processor 701 may also execute the various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0164] According to an embodiment of the present disclosure, electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to bus 704. Electronic device 700 may also include one or more of the following components connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 708 including a hard disk; and a communication section 709 including a network interface card such as a LAN card or modem. Communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to I / O interface 705 as needed. Removable media 711, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 710 as needed, so that computer programs read from the removable media can be installed into storage section 708 as needed.

[0165] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0166] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above, and / or one or more memories other than ROM 702 and RAM 703.

[0167] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is executed in a computer system, the program code is used to enable the computer system to implement the train departure time update method provided by the embodiments of the present disclosure.

[0168] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 701 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0169] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 709, and / or installed from a removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0170] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 709, and / or installed from a removable medium 711. When the computer program is executed by the processor 701, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0171] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0172] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0173] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways, even if such combinations and / or couplings are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or couplings are intended to fall within the scope of this disclosure.

[0174] The embodiments of the present disclosure are described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be used in combination to advantage. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for updating train departure time, wherein: The method comprises: Obtaining actual cross-sectional passenger flow in a first time period and predicted cross-sectional passenger flow in the first time period; Acquire multiple initial departure times in the first time period, which are updated based on the predicted cross-sectional passenger flow in the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time; Inputting the actual cross-sectional passenger flow in the first time period into the trained cross-sectional passenger flow prediction model to obtain the predicted cross-sectional passenger flow corresponding to the second time period; Using the predicted cross-sectional passenger flow in the second time period to update the initial departure frequency, to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-sectional passenger flow in the first time period; According to the target departure frequency and the passenger flow of each single-point section, the multiple initial departure times are updated to obtain multiple target departure times so that the train can depart according to the target departure times.

2. The method according to claim 1, wherein The multiple initial departure times are updated according to the target departure frequency and the passenger flow of each single-point section to obtain multiple target departure times, including: Update the expected passenger capacity of a single vehicle according to the target departure frequency and the passenger flow of each single-point section; The multiple target departure times are obtained according to the expected passenger capacity of the single vehicle and the multiple initial departure times.

3. The method according to claim 2, wherein: Obtaining the multiple target departure times according to the expected passenger capacity of the single vehicle and the multiple initial departure times includes: Calculate the n-th section cumulative passenger flow corresponding to the n-th initial departure time in the first time period, where n≥1; Determining the nth predicted passenger capacity corresponding to the nth initial departure time according to the expected passenger capacity of the single vehicle and the accumulated passenger flow of the nth section; According to the n-th predicted passenger capacity, the n-th target departure time is determined from the cumulative passenger flow curve.

4. The method according to claim 3, wherein: The method further comprises: The cumulative passenger flow curve is drawn based on the N initial departure times in the first time period and the N single-point section passenger flows corresponding to the N initial departure times, wherein the horizontal axis of the cumulative passenger flow curve is time and the vertical axis is the section passenger flow.

5. The method according to claim 1, wherein The initial departure frequency is updated using the predicted section passenger flow in the second time period to obtain a target departure frequency, including: Calculating the length of the congested road section where the predicted cross-section passenger flow in the second time period is greater than the expected congestion degree; Calculate the proportion of the congested route length to the total route length to obtain the proportion of congested sections; When the proportion of the congested road sections is less than or equal to the upper limit of the proportion of congested road sections, the target departure frequency is calculated according to the predicted section passenger flow in the second time period.

6. The method according to claim 1, wherein The method further comprises: A path planning strategy for multiple trains traveling from a first train number to a second train number is generated based on the multiple target departure times and predetermined constraints.

7. The method according to claim 1, wherein The predetermined constraint condition includes at least one of the following constraint conditions: A first constraint condition is that the first trip or the second trip is performed by only one train; The second constraint is that each train must depart from the same yard at most once; The third constraint condition is that the number of times the train enters and leaves the first train is equal; The fourth constraint condition is that when the train executes the second train after completing the first train, the departure time of the first train shall not be earlier than the arrival time of the second train; The fifth constraint condition is that when the train departs from the yard to perform the first train and then performs the second train, the departure station of the first train and the arrival station of the second train are the same.

8. A train departure time updating system, wherein: The system comprises: A cloud-based platform for: Obtaining actual cross-sectional passenger flow in a first time period and predicted cross-sectional passenger flow in the first time period; Acquire multiple initial departure times in the first time period, which are updated based on the predicted cross-sectional passenger flow in the first time period, and the single-point cross-sectional passenger flow corresponding to each initial departure time; Inputting the actual cross-sectional passenger flow in the first time period into the trained cross-sectional passenger flow prediction model to obtain the predicted cross-sectional passenger flow corresponding to the second time period; Using the predicted cross-sectional passenger flow in the second time period to update the initial departure frequency, to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-sectional passenger flow in the first time period; According to the target departure frequency and the passenger flow of each single-point section, the multiple initial departure times are updated to obtain multiple target departure times so that the train can depart according to the target departure times.

9. A train departure time updating device, wherein: The device comprises: A first acquisition module, configured to acquire the actual cross-sectional passenger flow in a first time period and the predicted cross-sectional passenger flow in the first time period; A second acquisition module is configured to acquire a plurality of initial departure times in the first time period obtained by updating the predicted cross-sectional passenger flow in the first time period, and a single-point cross-sectional passenger flow corresponding to each initial departure time; An input module, configured to input the actual cross-sectional passenger flow in the first time period into the trained cross-sectional passenger flow prediction model to obtain a predicted cross-sectional passenger flow corresponding to a second time period; a first updating module, configured to update an initial departure frequency using the predicted cross-section passenger flow during the second time period to obtain a target departure frequency, wherein the initial departure frequency is obtained by updating the predicted cross-section passenger flow during the first time period; The second updating module is used to update the multiple initial departure times according to the target departure frequency and the passenger flow of each single-point section to obtain multiple target departure times so as to depart according to the target departure times.

10. A train comprising: The train departure time updating device according to claim 8.

Images