Rail transit station peak passenger flow operation generation method

Abstract

The invention provides a rail transit station peak passenger flow operation generation method, and relates to the technical field of rail transit. The method comprises the following steps: acquiring historical passenger flow passage data of a target station in preset rail transit, determining predicted passenger flow passage data of the target station in a preset future time period by adopting a pre-trained target passenger flow passage prediction model according to the historical passenger flow passage data, and then determining the target station in the preset future time period according to the predicted passenger flow passage data. And determining a passenger flow peak period in a preset future time period, and finally, according to the predicted passenger flow passing data and the passenger flow peak period, generating an operation plan of the passenger flow peak period in the preset future time period, the operation plan being used for adjusting a gate operation mode of the target gate in the target station in the passenger flow peak period. A worker does not need to manually adjust a gate operation mode according to actual passenger flow passing data, the problems of time delay and misoperation existing in manual operation are avoided, and the operation efficiency of a target station is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a method for generating peak passenger flow operations at a rail transit station. Background Art

[0002] In the daily passenger flow organization of rail transit subway stations, peak passenger flow operations are an important task for subway staff. During peak passenger flow, if the station is dominated by incoming passenger flow, it is necessary to perform incoming peak passenger flow operations: operate on the integrated monitoring system, play the peak passenger flow broadcast, and adjust the designated outbound gate to a two-way gate; similarly, if the station is dominated by outbound passenger flow, it is necessary to perform outbound peak passenger flow operations: operate on the integrated monitoring system, play the peak passenger flow broadcast, and adjust the designated inbound gate to a two-way gate.

[0003] At present, the traditional practice is to fix the peak period of passenger flow in and out of the station into one or more time periods based on experience. For example, according to the characteristics of the passenger flow in the station, 07:00-09:00 is set as the peak period of passenger flow in and 17:00-19:00 is set as the peak period of passenger flow out. At the corresponding time, the following operations are performed manually on the integrated monitoring system: play the peak passenger flow broadcast and adjust the designated gate operation mode. However, in fact, the peak period of passenger flow in and out of the station every day is dynamically affected by factors such as date type, weather type, and temperature. And relying on manual operation may cause time lag, operation errors and other problems. Summary of the invention

[0004] The purpose of the present invention is to provide a method for generating peak passenger flow operations at rail transit stations in response to the deficiencies in the above-mentioned prior art, so as to predict historical passenger flow traffic data by adopting a pre-trained target passenger flow traffic prediction model, determine the peak passenger flow period of the target station within a preset future time period, and finally generate an operation plan for the peak passenger flow period based on the predicted passenger flow traffic data and the peak passenger flow period.

[0005] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for generating peak passenger flow operations at a rail transit station, comprising:

[0007] Obtain historical passenger flow data of target stations in preset rail transit;

[0008] According to the historical passenger flow data, a pre-trained target passenger flow prediction model is used to determine the predicted passenger flow data of the target station in a preset future time period;

[0009] Determine the peak passenger flow period within the preset future time period according to the predicted passenger flow data;

[0010] Based on the predicted passenger flow data and the peak passenger flow period, an operation plan for the peak passenger flow period in the preset future time period is generated. The operation plan is used to adjust the gate operation mode of the target gate in the target site during the peak passenger flow period. The gate operation modes include: entry mode, exit mode and two-way mode.

[0011] In an optional implementation, the historical passenger flow data includes: historical station entry data and historical station exit data; the target passenger flow prediction model includes: a target station entry prediction model and a target station exit prediction model; the predicted passenger flow data includes: predicted station entry data and predicted station exit data;

[0012] The step of determining predicted passenger flow data of the target station in a preset future time period based on the historical passenger flow data and using a pre-trained target passenger flow prediction model includes:

[0013] According to the historical station-entry volume data, the target station-entry volume prediction model is used to determine the predicted station-entry volume data;

[0014] The predicted outbound volume data is determined based on the historical outbound volume data and using the target outbound volume prediction model.

[0015] In an optional implementation manner, the peak passenger flow period includes: an incoming passenger flow peak period and an outgoing passenger flow peak period; and determining the peak passenger flow period in the preset future time period according to the predicted passenger flow data includes:

[0016] Calculate the average value of the inbound volume and the average value of the outbound volume of the target station in the preset future time period according to the predicted inbound volume data and the predicted outbound volume data;

[0017] Determine the peak period of passenger flow entering the station according to the average passenger flow volume and the predicted passenger flow volume data;

[0018] The peak period of outbound passenger flow is determined according to the average outbound volume and the predicted outbound volume data.

[0019] In an optional implementation manner, generating an operation plan for the peak passenger flow period according to the predicted passenger flow data and the peak passenger flow period includes:

[0020] Determine whether the peak time period of incoming passenger flow and the peak time period of outgoing passenger flow overlap;

[0021] If the peak period of incoming passenger flow and the peak period of outgoing passenger flow do not overlap, generating an operation plan for the peak period of incoming passenger flow according to the predicted incoming passenger flow data and the peak period of incoming passenger flow;

[0022] An operation plan for the peak period of outbound passenger flow is generated based on the predicted outbound volume data and the peak period of outbound passenger flow.

[0023] In an optional implementation manner, generating an operation plan for the peak passenger flow period according to the predicted passenger flow data and the peak passenger flow period further includes:

[0024] If the incoming passenger flow peak period overlaps with the outgoing passenger flow peak period, then determine the overlapping passenger flow peak period of the incoming passenger flow peak period and the outgoing passenger flow peak period, the target incoming passenger flow peak period and the target outgoing passenger flow peak period;

[0025] Determine the target passenger flow state corresponding to the overlapping passenger flow peak period according to the predicted station entry volume data and the predicted station exit volume data;

[0026] Generating an operation plan for the overlapping passenger flow peak period according to the target passenger flow traffic status;

[0027] Based on the predicted inbound volume data and the predicted outbound volume data, operation plans for the target inbound passenger flow peak time period and the target outbound passenger flow peak time period are generated respectively.

[0028] In an optional implementation manner, determining the target passenger flow state corresponding to the overlapping passenger flow peak period according to the predicted station entry volume data and the predicted station exit volume data includes:

[0029] Calculating the cumulative value of incoming passenger flow and the cumulative value of outgoing passenger flow during the overlapping passenger flow peak period respectively according to the predicted incoming passenger flow data and the predicted outgoing passenger flow data;

[0030] If the accumulated value of the incoming passenger flow is greater than or equal to the accumulated value of the outgoing passenger flow, determining that the target passenger flow state is the incoming passenger flow peak state;

[0031] If the accumulated value of the incoming passenger flow is less than the accumulated value of the outgoing passenger flow, it is determined that the target passenger flow state is the outgoing passenger flow peak state.

[0032] In an optional implementation manner, the historical passenger flow data respectively include: historical entry volume data and historical exit volume data within a preset historical date; the historical passenger flow data also include: date type data of the preset historical date, weather type data of the preset historical date and temperature data of the preset historical date, wherein the date type data is used to indicate whether the corresponding historical date is a working day, a holiday or a weekend; the method further includes: determining the target station before the predicted passenger flow data of the preset future time period based on the historical passenger flow data and using a pre-trained target passenger flow prediction model;

[0033] Constructing an inbound volume sample data set and an outbound volume sample data set according to the historical inbound volume data, the historical outbound volume data, the date type data, the weather type data and the temperature data of multiple historical time periods within the preset historical date;

[0034] Model training is performed on the inbound volume sample data set and the outbound volume sample data set respectively to obtain the target inbound volume prediction model and the target outbound volume prediction model. The target passenger flow prediction model includes: the target inbound volume prediction model and the target outbound volume prediction model.

[0035] In an optional embodiment, the method further comprises:

[0036] When the trigger time of the preset future time period arrives, reading the operation plan for the peak passenger flow period in the preset future time period;

[0037] When the preset execution condition of the peak passenger flow period is reached, the operation plan of the peak passenger flow period is executed to adjust the gate operation mode of the target gate during the peak passenger flow period.

[0038] In an optional implementation, the operation plan for the peak passenger flow period includes: an operation plan for the peak passenger flow period of entering the station;

[0039] When the preset execution condition of the passenger flow peak period is reached, executing the operation plan of the passenger flow peak period includes:

[0040] When the preset execution trigger condition of the peak period of passenger flow entering the station is reached, the operation plan of the peak period of passenger flow entering the station is executed.

[0041] In an optional implementation, the operation plan for the peak passenger flow period includes: an operation plan for the peak outbound passenger flow period;

[0042] When the preset execution condition of the passenger flow peak period is reached, executing the operation plan of the passenger flow peak period includes:

[0043] When the preset execution trigger condition of the outbound passenger flow peak period is reached, the operation plan of the outbound passenger flow peak period is executed.

[0044] In a second aspect, the embodiment of the present application further provides a rail transit station peak passenger flow operation generation device, comprising:

[0045] An acquisition module is used to acquire historical passenger flow data of a target station in a preset rail transit;

[0046] A determination module, configured to determine the predicted passenger flow data of the target station in a preset future time period based on the historical passenger flow data and using a pre-trained target passenger flow prediction model;

[0047] The determination module is further used to determine the passenger flow peak period within the preset future time period according to the predicted passenger flow data;

[0048] A generation module is used to generate an operation plan for the peak passenger flow period in the preset future time period based on the predicted passenger flow data and the peak passenger flow period. The operation plan is used to adjust the gate operation mode of the target gate in the target site during the peak passenger flow period. The gate operation modes include: entry mode, exit mode and two-way mode.

[0049] In the third aspect, an embodiment of the present application also provides a computer device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor communicates with the storage medium through the bus, and the processor executes the program instructions to perform the steps of the method for generating peak passenger flow operations at a rail transit station as described in any one of the first aspects.

[0050] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for generating peak passenger flow operations at a rail transit station as described in any one of the first aspects are executed.

[0051] The beneficial effects of this application are:

[0052] An embodiment of the present application provides a method for generating peak passenger flow operations at a rail transit station, including: obtaining historical passenger flow data of a target station in a preset rail transit, determining the predicted passenger flow data of the target station in a preset future time period based on the historical passenger flow data, using a pre-trained target passenger flow prediction model, and then determining the peak passenger flow period in the preset future time period based on the predicted passenger flow data; finally, generating an operation plan for the peak passenger flow period in the preset future time period based on the predicted passenger flow data and the peak passenger flow period, the operation plan being used to adjust the gate operation mode of a target gate in the target station during the peak passenger flow period, and the gate operation modes including: entry mode, exit mode and two-way mode.

[0053] The method of the present application adopts a pre-trained target passenger flow prediction model to predict historical passenger flow data, determine the predicted passenger flow data of the target site in a preset future time period, and determine the passenger flow peak period in the preset future time period, and finally generate an operation plan for the passenger flow peak period based on the predicted passenger flow data and the passenger flow peak period, so as to adjust the gate operation mode of the target gate during the passenger flow peak period, facilitate the passage of pedestrians during the passenger flow peak period, and eliminate the need for staff to manually adjust the gate operation mode according to the actual passenger flow data, thereby reducing the work of staff and avoiding time lags and operational errors in manual operation, thereby effectively improving the operating efficiency of the target site. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 One of the flow charts of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0056] Figure 2 A second flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0057] Figure 3 A third flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of a peak passenger flow period at a station provided in an embodiment of the present application;

[0059] Figure 5A schematic diagram of a peak period of outbound passenger flow provided in an embodiment of the present application;

[0060] Figure 6 A fourth flowchart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0061] Figure 7 A fifth flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0062] Figure 8 A schematic diagram of overlapping passenger flow peak hours provided in an embodiment of the present application;

[0063] Fig. 9 A sixth flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0064] Fig.10 A seventh flowchart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0065] Fig.11 FIG8 is a flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0066] Fig.12 A schematic diagram of functional modules of a device for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application;

[0067] Fig.13 A schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0069] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0070] In the description of the present application, it should be noted that if the terms "upper", "lower", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or is the orientation or position relationship in which the product of the application is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0071] In addition, the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0072] It should be noted that, in the absence of conflict, the features in the embodiments of the present application may be combined with each other.

[0073] In order to achieve automatic adjustment of the target gate operation mode of the target site during future peak passenger flow periods and improve operational efficiency, an embodiment of the present application provides a method for generating peak passenger flow operations at a rail transit site. The historical passenger flow traffic data of the target site is predicted by using a pre-trained target passenger flow traffic prediction model to determine the predicted passenger flow traffic data of the target site in a preset future time period, and the peak passenger flow period in the preset future time period is determined. Finally, based on the predicted passenger flow traffic data and the peak passenger flow period, an operation plan for the peak passenger flow period is generated, so that the gate operation mode of the target gate during the peak passenger flow period can be adjusted to facilitate the passage of personnel during the peak passenger flow period and improve operational efficiency.

[0074] The following is a detailed explanation of a method for generating peak passenger flow operations at a rail transit station provided by an embodiment of the present application through specific examples in conjunction with the accompanying drawings. A method for generating peak passenger flow operations at a rail transit station provided by an embodiment of the present application can be implemented by a computer device pre-installed with: a preset peak passenger flow operation generation algorithm or detection software, by running the algorithm or software. The computer device can be, for example, a server or a terminal, and the terminal can be a user computer. Figure 1 One of the flow charts of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application.

[0075] like Figure 1 As shown, the method includes:

[0076] S101. Obtain historical passenger flow data of a target station in a preset rail transit.

[0077] In this embodiment, the preset rail transit can be a tram, monorail, light rail, subway, etc. The preset rail transit includes multiple stations, each station is equipped with a gate for restricting pedestrians from entering or exiting the station, and historical passenger flow data is obtained based on the passenger flow conditions of the target station at each historical time point.

[0078] S102: Based on historical passenger flow data, a pre-trained target passenger flow prediction model is used to determine predicted passenger flow data for a target station in a preset future time period.

[0079] S103: Determine a peak passenger flow period within a preset future time period based on the predicted passenger flow data.

[0080] Specifically, a pre-trained target passenger flow prediction model is used to predict historical passenger flow data to determine the predicted passenger flow data of the target station in a preset future time period. For example, the predicted passenger flow data of the target station in the next day is obtained, that is, the predicted passenger flow data at each moment in the next day. Then, based on the predicted passenger flow data, the passenger flow peak period in the next day is determined.

[0081] S104. Generate an operation plan for the peak passenger flow period in a preset future time period based on the predicted passenger flow data and the peak passenger flow period. The operation plan is used to adjust the gate operation mode of the target gate in the target site during the peak passenger flow period.

[0082] Among them, the gate operation modes include: entry mode, exit mode and two-way mode.

[0083] Specifically, if the peak passenger flow period includes: the peak entry period and the peak exit period, for example, 6:30-9:30 in the next day is determined to be the peak entry period, that is, the target station has a large passenger flow from 6:30 to 9:30, then the target gate of the target station is adjusted from the exit mode to the two-way mode during the peak entry period, so that pedestrians can enter the station through the target gate, alleviating the operating pressure of other gates in the entry mode. By automatically adjusting the gate operation mode of the target gate, the gates that can be in the entry mode are increased, and the gates in the exit mode are correspondingly reduced, allowing pedestrians to enter the station quickly and avoiding congestion in the entry area.

[0084] Similarly, if it is determined that 17:30-19:30 is the peak exit period in the next day, that is, the target station has a large number of exit passengers during 17:30-19:30, then the target gate of the target station will be adjusted from the entry model to the two-way mode during the peak exit period, so that pedestrians can exit the station through the target gate, alleviating the operating pressure of other gates in exit mode. By automatically adjusting the gate operation mode of the target gate, the number of gates that can be in exit mode is increased, and the number of gates in entry mode is correspondingly reduced, allowing pedestrians to exit the station quickly and avoiding congestion in the exit area.

[0085] To summarize, an embodiment of the present application provides a method for generating peak passenger flow operations at a rail transit station, including: obtaining historical passenger flow data of a target station in a preset rail transit, and based on the historical passenger flow data, using a pre-trained target passenger flow prediction model to determine the predicted passenger flow data of the target station in a preset future time period, and then determining the peak passenger flow period in the preset future time period based on the predicted passenger flow data, and finally generating an operation plan for the peak passenger flow period in the preset future time period based on the predicted passenger flow data and the peak passenger flow period, the operation plan being used to adjust the gate operation mode of the target gate in the target station during the peak passenger flow period, and the gate operation modes including: entry mode, exit mode and two-way mode.

[0086] The method of the present application adopts a pre-trained target passenger flow prediction model to predict historical passenger flow data, determine the predicted passenger flow data of the target site in a preset future time period, and determine the passenger flow peak period in the preset future time period, and finally generate an operation plan for the passenger flow peak period based on the predicted passenger flow data and the passenger flow peak period, so as to adjust the gate operation mode of the target gate during the passenger flow peak period, facilitate the passage of pedestrians during the passenger flow peak period, and eliminate the need for staff to manually adjust the gate operation mode according to the actual passenger flow data, thereby reducing the work of staff and avoiding time lags and operational errors in manual operation, thereby effectively improving the operating efficiency of the target site.

[0087] Based on the above embodiments, the embodiments of the present application also provide another possible implementation method for generating peak passenger flow operations at rail transit stations, wherein historical passenger flow travel data include: historical entry volume data and historical exit volume data, the target passenger flow travel prediction model includes: target entry volume prediction model and target exit volume prediction model, and the predicted passenger flow travel data includes: predicted entry volume data and predicted exit volume data. Figure 2 The second flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application. Figure 2As shown, based on the historical passenger flow data, a pre-trained target passenger flow prediction model is used to determine the predicted passenger flow data of the target station in a preset future time period, including:

[0088] S201. Determine predicted station entry volume data based on historical station entry volume data using a target station entry volume prediction model.

[0089] In this embodiment, historical entry volume data is input into the target entry volume prediction model, and the target entry volume prediction model outputs predicted entry volume data for a preset future time period. For example, if the historical entry volume data for 7 days is input, the predicted entry volume data for the next day is predicted.

[0090] It should be noted that if the target inbound volume prediction model is pre-trained and the inbound volume sample data set only includes historical inbound volume data, the historical inbound volume data is input into the target inbound volume prediction model, and the predicted inbound volume data for a preset future time period is output through the target inbound volume prediction model.

[0091] If the target inbound volume prediction model is pre-trained, the inbound volume sample data set includes historical inbound volume data, date type, weather type, temperature data, etc., then the historical inbound volume data, date type, weather type, temperature data need to be input into the target inbound volume prediction model. For example, input [i t-7k ,d t-7k ,t t-7k ,q t-7k ,......i t-2 ,d t-2 ,t t-2 ,q t-2 ,i t-1 ,d t-1 ,t t-1 ,q t-1 ], and then output the predicted station entry volume data for the preset future time period through the target station entry volume prediction model t , where i t-7k Represents the historical inbound volume data for the 7th day, d t-7k The date type representing the seventh day in history, t t-7k Represents the weather type of the 7th day in history, q t-7k It represents the temperature data of the 7th day in history. The historical station traffic data is collected every 15 minutes. Then k = 96 represents the station traffic data of the 7th day in history. 7k represents the station traffic data of the 7th day in history. The predicted value is i t ,i t+1 ,…,i t+k That is, the 15-minute time series of station arrival volume in the next day.

[0092] S202: Based on historical outbound volume data, a target outbound volume prediction model is used to determine predicted outbound volume data.

[0093] Specifically, historical outbound volume data is input into the target outbound volume prediction model, and the target outbound volume prediction model outputs predicted outbound volume data for a preset future time period. For example, if historical outbound volume data for 7 days is input, predicted outbound volume data for the next day is predicted.

[0094] It should be noted that, if the outbound volume sample data set only includes historical outbound volume data when the target outbound volume prediction model is pre-trained, the historical outbound volume data is input into the target outbound volume prediction model, and the predicted outbound volume data for a preset future time period is output through the target outbound volume prediction model; if the outbound volume sample data set includes historical outbound volume data, date type, weather type, temperature data, etc. when the target outbound volume prediction model is pre-trained, the historical outbound volume data, date type, weather type, temperature data, etc. need to be input into the target outbound volume prediction model. For example, input [o t-7k ,d t-7k ,t t-7k ,q t-7k ,......o t-2 ,d t-2 ,t t-2 ,q t-2 ,o t-1 ,d t-1 ,t t-1 ,q t-1 ], and then output the predicted outbound volume data for the preset future time period through the target outbound volume prediction model. t , where o t-7k Represents the outbound volume data for the 7th day in history, d t-7k The date type representing the seventh day in history, t t-7k Represents the weather type of the 7th day in history, q t-7k It represents the temperature data of the 7th day in history. The historical outbound volume data is collected every 15 minutes. Then k = 96 represents the outbound volume data of the 7th day in history. 7k represents the outbound volume data of the 7th day in history. The prediction is o t ,o t+1 ,…,o t+k That is, the 15-minute outbound volume time series in the next day.

[0095] In the method provided in the embodiment of the present application, a target incoming volume prediction model is adopted based on historical incoming volume data to determine the predicted incoming volume data; a target outgoing volume prediction model is adopted based on historical outgoing volume data to determine the predicted outgoing volume data, and a pre-trained target incoming volume prediction model and a target outgoing volume prediction model are used to accurately predict the predicted incoming volume data and the predicted outgoing volume data for a preset future time period based on the historical incoming volume data and the historical outgoing volume data, respectively.

[0096] The embodiment of the present application also provides another possible implementation method for generating peak passenger flow operations at a rail transit station, wherein the peak passenger flow period includes: a peak inbound passenger flow period and a peak outbound passenger flow period. Figure 3 The third flowchart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application. Figure 4 A schematic diagram of the peak passenger flow period at a station provided in an embodiment of the present application. Figure 5 A schematic diagram of a peak period of outbound passenger flow provided in an embodiment of the present application. Figure 3 As shown, based on the predicted passenger flow data, the passenger flow peak period in the preset future time period is determined, including:

[0097] S301. Calculate the average inbound volume and the average outbound volume of the target station in a preset future time period according to the predicted inbound volume data and the predicted outbound volume data.

[0098] S302: Determine the peak period of passenger flow entering the station based on the average passenger flow and the predicted passenger flow data.

[0099] S303: Determine the peak period of outbound passenger flow based on the average outbound volume and the predicted outbound volume data.

[0100] In this embodiment, based on the predicted station entry volume data, the average station entry volume of the target station in a preset future time period is calculated, and the expression is as follows:

[0101]

[0102] According to the average and predicted station entry volume data, the period when the predicted station entry volume data is greater than the average station entry volume is determined as the peak passenger flow period. Figure 4 As shown, the average number of inbound traffic is 40, and T is determined i1 ~T i2 , T i3 ~T i4 This is the peak passenger flow period.

[0103] Based on the predicted outbound volume data, the average outbound volume of the target site in the preset future time period is calculated. The expression is as follows:

[0104]

[0105] According to the average outbound volume and the predicted outbound volume data, the period when the predicted outbound volume data is greater than the average outbound volume is determined as the outbound passenger flow peak period, such as Figure 5 As shown, the average outbound volume is 38, and T o1 ~T o2 , T o3 ~T o4 This is the peak period for outbound passenger flow.

[0106] In the method provided in the embodiment of the present application, based on the predicted arrival volume data and the predicted exit volume data, the average arrival volume and the average exit volume of the target station in the preset future time period are calculated respectively, and the peak arrival passenger flow period is determined based on the average arrival volume and the predicted arrival volume data. The peak exit passenger flow period is determined based on the average exit volume and the predicted exit volume data, which are used to generate operation plans for the peak arrival passenger flow period and the peak exit passenger flow period respectively.

[0107] The present application embodiment also provides another possible implementation method for generating peak passenger flow operations at rail transit stations: Figure 6 The fourth flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application. Figure 6 As shown in the figure, based on the predicted passenger flow data and passenger flow peak period, an operation plan for the passenger flow peak period is generated, including:

[0108] S401. Determine whether there is overlap between the peak time period of incoming passenger flow and the peak time period of outgoing passenger flow.

[0109] S402: If there is no overlap between the peak period of incoming passenger flow and the peak period of outgoing passenger flow, an operation plan for the peak period of incoming passenger flow is generated according to the predicted incoming passenger flow data and the peak period of incoming passenger flow.

[0110] S403: Generate an operation plan for the peak period of outbound passenger flow based on the predicted outbound volume data and the peak period of outbound passenger flow.

[0111] In this embodiment, whether there is overlap is determined based on the start and end times of the peak inbound passenger flow period and the start and end times of the peak outbound passenger flow period. If there is no overlap, an operation plan for the peak inbound passenger flow period is generated based on the predicted inbound volume data and the peak inbound passenger flow period, that is, at the start time of the peak inbound passenger flow period, the target gate is adjusted from the outbound mode to the two-way mode, and at the end time of the peak inbound passenger flow period, the target gate is restored from the two-way mode to the outbound mode.

[0112] Based on the predicted exit volume data and the peak period of exit passenger flow, an operation plan for the peak period of exit passenger flow is generated, that is, at the beginning of the peak period of exit passenger flow, the target gate is adjusted from the entry mode to the two-way mode, and at the end of the peak period of exit passenger flow, the target gate is restored from the two-way mode to the entry mode.

[0113] The present application embodiment also provides another possible implementation method for generating peak passenger flow operations at rail transit stations: Figure 7 The fifth flowchart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application. Figure 8 A schematic diagram of overlapping passenger flow peak hours provided in an embodiment of the present application. Figure 7 As shown, according to the predicted passenger flow data and the passenger flow peak period, an operation plan for the passenger flow peak period is generated, and the method further includes:

[0114] S501. If there is an overlap between the incoming passenger flow peak period and the outgoing passenger flow peak period, determine the overlapping passenger flow peak period of the incoming passenger flow peak period and the outgoing passenger flow peak period, the target incoming passenger flow peak period and the target outgoing passenger flow peak period.

[0115] In this embodiment, if the peak time period of incoming passenger flow and the peak time period of outgoing passenger flow overlap, such as Figure 8 As shown in the figure, the overlapping passenger flow peak period is determined as T according to the inbound passenger flow peak period and the outbound passenger flow peak period. o1 ~T o2 and T i3 ~T i4 The target passenger flow peak time is T i1 ~T o1 and T o2 ~T i2 , the target outbound passenger flow peak period is T o3 ~T i3 and T i4 ~T o4 .

[0116] S502: Determine the target passenger flow status corresponding to the overlapping passenger flow peak period according to the predicted station entry volume data and the predicted station exit volume data.

[0117] S503: Generate an operation plan for overlapping passenger flow peak hours according to the target passenger flow status.

[0118] Specifically, the predicted inbound traffic data and the predicted outbound traffic data are compared to determine the target passenger flow status corresponding to the overlapping passenger flow peak period, i.e., the inbound passenger flow peak status or the outbound passenger flow peak status. Then, based on the target passenger flow status, an operation plan for the overlapping passenger flow peak period is generated.

[0119] S504: Generate operation plans for target inbound passenger flow peak time periods and target outbound passenger flow peak time periods respectively based on the predicted inbound passenger flow data and the predicted outbound passenger flow data.

[0120] In the method provided in the embodiment of the present application, if there is an overlap between the incoming passenger flow peak period and the outgoing passenger flow peak period, the overlapping peak passenger flow period of the incoming passenger flow peak period and the outgoing passenger flow peak period, the target incoming passenger flow peak period and the target outgoing passenger flow peak period are determined; the target passenger flow traffic state corresponding to the overlapping peak passenger flow period is determined according to the predicted incoming volume data and the predicted outgoing volume data; according to the target passenger flow traffic state, an operation plan for the overlapping peak passenger flow period is generated; according to the predicted incoming volume data and the predicted outgoing volume data, an operation plan for the target incoming passenger flow peak period and the target outgoing passenger flow peak period is generated respectively; if there is an overlap between the incoming passenger flow peak period and the outgoing passenger flow peak period, it is necessary to re-determine the target passenger flow traffic state corresponding to the overlapping peak passenger flow period according to the predicted incoming volume data and the predicted outgoing volume data, that is, the incoming passenger flow peak state or the outgoing passenger flow peak state, and then further determine the operation plan for the overlapping peak passenger flow period.

[0121] The present application embodiment also provides another possible implementation method for generating peak passenger flow operations at rail transit stations: Fig. 9 The sixth flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application. Fig. 9 As shown, according to the predicted station entry volume data and the predicted station exit volume data, the target passenger flow state corresponding to the overlapping passenger flow peak period is determined, including:

[0122] S601. Calculate the cumulative value of incoming passenger flow and the cumulative value of outgoing passenger flow during the overlapping passenger flow peak period according to the predicted incoming passenger flow data and the predicted outgoing passenger flow data.

[0123] In this embodiment, continue to refer to Figure 8 , according to the predicted number of inbound passengers, calculate the cumulative value of inbound passenger flow during the overlapping passenger flow peak period, where the overlapping passenger flow peak period T o1 ~T o2 The cumulative value of inbound passenger flow is expressed as: Overlapping passenger flow peak period T i3 ~T i4 The cumulative value of inbound passenger flow is expressed as:

[0124] According to the predicted number of outbound traffic, the cumulative value of outbound passenger flow during the overlapping passenger flow peak period is calculated, where the overlapping passenger flow peak period T o1 ~T o2 The cumulative value of outbound passenger flow is expressed as: Overlapping passenger flow peak period T i3 ~T i4The cumulative value of outbound passenger flow is expressed as:

[0125] S602: If the cumulative value of the incoming passenger flow is greater than or equal to the cumulative value of the outgoing passenger flow, determine that the target passenger flow state is the incoming passenger flow peak state.

[0126] S603: If the cumulative value of the incoming passenger flow is less than the cumulative value of the outgoing passenger flow, the target passenger flow state is determined to be the outgoing passenger flow peak state.

[0127] For example, if i sum1 ≥o sum1 , then determine the overlapping passenger flow peak period T o1 ~T o2 The target passenger flow status is the peak period of incoming passenger flow.

[0128] If i sum2 <o sum2 , then determine the overlapping passenger flow peak period T i3 ~T i4 The target passenger flow status is the outbound passenger flow peak period.

[0129] In the method provided in the embodiment of the present application, the cumulative value of incoming passenger flow and the cumulative value of outgoing passenger flow during the overlapping passenger flow peak period are calculated respectively based on the predicted incoming passenger flow data and the predicted outgoing passenger flow data; if the cumulative value of incoming passenger flow is greater than or equal to the cumulative value of outgoing passenger flow, the target passenger flow traffic state is determined to be the incoming passenger flow peak state; if the cumulative value of incoming passenger flow is less than the cumulative value of outgoing passenger flow, the target passenger flow traffic state is determined to be the outgoing passenger flow peak state, thereby determining the target passenger flow traffic state corresponding to the overlapping passenger flow peak period based on the cumulative value of incoming passenger flow and the cumulative value of outgoing passenger flow during the overlapping passenger flow peak period.

[0130] The embodiment of the present application also provides another possible implementation method for generating peak passenger flow operations at rail transit stations, wherein the historical passenger flow data respectively include: historical station entry volume data and historical station exit volume data within a preset historical date; the historical passenger flow data also includes: date type data of a preset historical date, weather type data of a preset historical date, and temperature data of a preset historical date, wherein the date type data is used to indicate whether the corresponding historical date is a working day, a holiday, or a weekend. Fig.10 The seventh flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application. Fig.10 As shown, based on historical passenger flow data, a pre-trained target passenger flow prediction model is used to determine the predicted passenger flow data of the target site in a preset future time period, and the method further includes:

[0131] S701. Construct an inbound volume sample data set and an outbound volume sample data set based on historical inbound volume data, historical outbound volume data, date type data, weather type data and temperature data for multiple historical time periods within a preset historical date.

[0132] In this embodiment, historical inbound traffic data, historical outbound traffic data, date type data, which indicates whether the corresponding historical date is a working day, holiday or weekend, weather type data, which indicates whether the weather on the corresponding historical date is sunny, rainy, cloudy, overcast, snowy, with lightning or hail, and temperature data are collected every 15 minutes within the preset historical date, and an inbound traffic data set that can be used for time series prediction is obtained: H = [h t ,h t+1 ......h t+n ], where h t =[i t ,d t ,t t ,q t ],i t represents the inbound traffic data at time t, d t Represents date type data at time point t, t t represents the weather type data at time t, q t Represents the temperature data at time point t.

[0133] Similarly, we get the outbound data set that can be used for time series forecasting: H = [h t ,h t+1 ......h t+n ], where h t =[o t ,d t ,t t ,q t ], o t represents the outbound volume data at time t, d t Represents date type data at time point t, t t represents the weather type data at time t, q t Represents the temperature data at time point t.

[0134] Then one-hot encoding is performed on the date type data field, that is, the date type field is converted into a value of type number, and one-hot encoding is performed on the weather type data field, that is, the weather type field is converted into a value of type number, for easy processing.

[0135] The inbound data set is standardized, that is, the inbound volume data, the value of the date type data field, the value of the weather type data field, and the temperature data are scaled to between 0 and 1, and the outbound data set is standardized, that is, the outbound volume data, the value of the date type data field, the value of the weather type data field, and the temperature data are scaled to between 0 and 1.

[0136] Then the inbound data set H is transformed into supervised learning data, namely, the inbound volume sample data set W = [w t ,w t+ 1......w t+n ], where w t =[i t ,d t, t t ,q t ,i t+1 ,d t+1 ,t t+1 ,q t+1 ,......i t+k ,d t+k ,t t+k ,q t+k ]; k = 96 represents the amount of data for one day, and the first three quarters of the sample data set W for the inbound traffic are divided into the inbound traffic training set W train , the last quarter of the test set W test , and then separate the inbound training set to obtain the input volume W of the inbound training set train_x And the output W train_y , where W train_x =[x t ,x t+1 ......x t+3n / 4 ],W train_y =[y t ,y t+1 ......y t+3n / 4 ], where x t =[i t ,d t ,t t ,q t ,i t+1 ,d t+1 ,t t+1 ,q t+1 ......i t+k-1 ,d t+k-1 ,t t+k-1 ,q t+k-1 ],y t =[i t+k ]. Similarly, we can get the input volume W of the entry test set test_x And the output W test_y .

[0137] Similarly, the outbound data set H is converted into supervised learning data, namely the outbound volume sample data set W = [w t ,w t+1 ......w t+n ], where w t =[o t ,d t ,t t ,q t o t+1 ,d t+1 ,t t+1 ,q t+1 ,......o t+k ,d t+k ,t t+k ,q t+k ]; k = 96 represents the amount of data for one day, and the first three quarters of the outbound sample data set W are divided into the outbound training set W train , the last quarter outbound test set W test , and then separate the outbound training set to obtain the input volume W of the outbound training set train_x And the output W train_y , where W train_x =[x t ,x t+1 ......x t+3n / 4 ],W train_y =[y t ,y t+1 ......y t+3n / 4 ], where x t =[o t ,d t ,t t ,q t ,o t+1 ,d t+1 ,t t ,q t ......o t+k-1 ,d t+k-1 ,t t ,q t ],y t =[i t+k ]. Similarly, we can get the input volume W of the outbound test set test_x And the output W test_y .

[0138] S702: Perform model training on the inbound volume sample data set and the outbound volume sample data set respectively to obtain a target inbound volume prediction model and a target outbound volume prediction model.

[0139] Among them, the target passenger flow prediction model includes: a target entry volume prediction model and a target exit volume prediction model.

[0140] Specifically, the initial passenger flow prediction model is designed as three layers: the first layer is the input layer, the second layer is the hidden layer, and the third layer is the output layer. Set the parameters of each layer: the number of neurons, the initial passenger flow prediction model uses the mean square error MSE as the error calculation method, and uses Adam as the gradient descent optimizer.

[0141] First, the input volume W of the inbound training set is used train_x With output W train_y The initial passenger flow prediction model is trained to obtain the inbound passenger flow prediction model, and the inbound passenger flow prediction model is used for the inbound test set W test_x Make a prediction and get the predicted output W test-predict_y , and then the output W of the incoming test set test_y And the predicted output W test-predict_y The value of is reversely scaled to obtain the actual value. The mean square error between the actual value of the test set output and the actual value of the predicted output is calculated as the evaluation index. The number of neurons in the prediction model is adjusted, and the initial passenger flow prediction model is repeatedly trained to obtain the evaluation indicators of different prediction models. The model with the best evaluation indicator, that is, the smallest mean square error, is selected as the final model for predicting the passenger flow entering the station, and the target passenger flow prediction model is obtained.

[0142] Similarly, using the input volume W of the outbound training set train_x With output W train_y The initial passenger flow prediction model is trained to obtain the outbound passenger flow prediction model, and the outbound test set W test_x Make a prediction and get the predicted output W test-predict_y , and then the output volume W of the outbound test set test_y And the predicted output W test-predict_y The value of is reversely scaled to obtain the actual value. The mean square error between the actual value of the test set output and the actual value of the predicted output is calculated as the evaluation index. The number of neurons in the prediction model is adjusted, and the initial passenger flow prediction model is repeatedly trained to obtain evaluation indicators of different prediction models. The model with the best evaluation indicator, that is, the smallest mean square error, is selected as the final model for predicting the outbound passenger flow, and the target outbound volume prediction model is obtained.

[0143] In the method provided in the embodiment of the present application, an arrival volume sample data set and an exit volume sample data set are constructed according to historical arrival volume data, historical exit volume data, date type data, weather type data and temperature data of multiple historical time periods within a preset historical date; model training is performed on the arrival volume sample data set and the exit volume sample data set respectively to obtain a target arrival volume prediction model and a target exit volume prediction model, and the target passenger flow prediction model includes: a target arrival volume prediction model and a target exit volume prediction model. When training the target arrival volume prediction model and the target exit volume prediction model, the influence of factors such as date type, weather type, temperature, etc. is comprehensively considered, so that the prediction results of the target arrival volume prediction model and the target exit volume prediction model are more accurate.

[0144] The present application embodiment also provides another possible implementation method for generating peak passenger flow operations at rail transit stations: Fig.11 The eighth flow chart of a method for generating peak passenger flow operations at a rail transit station provided in an embodiment of the present application is as follows. Fig.11 As shown, the method also includes:

[0145] S801. When the trigger time of the preset future time period arrives, read the operation plan for the peak passenger flow period in the preset future time period.

[0146] In this embodiment, for example, the operation plan for the peak passenger flow period of the day is read at 2 o'clock in the preset future time to obtain the operation list of the day.

[0147] S802. When the preset execution conditions of the passenger flow peak period are met, the operation plan of the passenger flow peak period is executed to adjust the gate operation mode of the target gate during the passenger flow peak period.

[0148] Specifically, when the start time of the peak passenger flow period is reached, or is within a preset time range with the start time, the operation plan for the peak passenger flow period is executed to adjust the gate operation mode of the target gate during the peak passenger flow period; when the end time of the peak passenger flow period is reached, or is within a preset time range with the end time, the operation plan for the peak passenger flow period is terminated.

[0149] Optionally, the operation plan for the peak passenger flow period includes: an operation plan for the peak passenger flow period entering the station, and when the preset execution trigger condition for the peak passenger flow period entering the station is met, the operation plan for the peak passenger flow period entering the station is executed.

[0150] Specifically, when the start time of the peak period of inbound passenger flow is reached, or is within a preset time range with the start time, the operation plan for the peak period of inbound passenger flow will be executed, that is, the target gate will be adjusted from the exit mode to the two-way mode, and the peak inbound passenger flow broadcast will be played in a loop. When the end time of the peak period of inbound passenger flow is reached, or is within a preset time range with the end time, the operation plan for the peak period of inbound passenger flow will be terminated, that is, the target gate will be restored from the two-way mode to the exit mode, and the broadcast of the peak inbound passenger flow will be stopped.

[0151] Optionally, the operation plan for the peak passenger flow period includes: an operation plan for the peak outbound passenger flow period, and when the preset execution trigger condition for the peak outbound passenger flow period is met, the operation plan for the peak outbound passenger flow period is executed.

[0152] Specifically, when the start time of the peak period of outbound passenger flow is reached, or is within a preset time range with the start time, the operation plan for the peak period of outbound passenger flow is executed, that is, the target gate is adjusted from the entry mode to the two-way mode, and the peak outbound passenger flow broadcast is played in a loop; when the end time of the peak period of outbound passenger flow is reached, or is within a preset time range with the end time, the operation plan for the peak period of outbound passenger flow is terminated, that is, the target gate is restored from the two-way mode to the entry mode, and the broadcast of the peak outbound passenger flow is stopped.

[0153] In the method provided in the embodiment of the present application, when the trigger time of the preset future time period arrives, the operation plan for the peak passenger flow period in the preset future time period is read; when the preset execution conditions of the peak passenger flow period are met, the operation plan for the peak passenger flow period is executed to adjust the gate operation mode of the target gate during the peak passenger flow period, so as to realize the automatic execution of the operation plan for the peak passenger flow period of the target station.

[0154] The following is a corresponding explanation of the rail transit station peak passenger flow operation generation device and computer equipment provided by any of the above embodiments of the present application. Its specific implementation process and the technical effects produced are the same as those of the corresponding method embodiments mentioned above. For the sake of brief description, the parts not mentioned in this embodiment can refer to the corresponding contents in the method embodiment.

[0155] Fig.12 This is a functional module diagram of a rail transit station peak passenger flow operation generation device provided in an embodiment of the present application. Fig.12 As shown, the rail transit station peak passenger flow operation generating device 100 includes:

[0156] An acquisition module 110 is used to acquire historical passenger flow data of a target station in a preset rail transit;

[0157] A determination module 120 is used to determine the predicted passenger flow data of the target station in a preset future time period based on the historical passenger flow data and using a pre-trained target passenger flow prediction model;

[0158] The determination module 120 is further configured to determine a peak passenger flow period within the preset future time period according to the predicted passenger flow data;

[0159] The generation module 130 is used to generate an operation plan for the peak passenger flow period in the preset future time period based on the predicted passenger flow data and the peak passenger flow period. The operation plan is used to adjust the gate operation mode of the target gate in the target site during the peak passenger flow period. The gate operation modes include: entry mode, exit mode and two-way mode.

[0160] Optionally, the historical passenger flow data includes: historical station entry data and historical station exit data; the target passenger flow prediction model includes: a target station entry prediction model and a target station exit prediction model; the predicted passenger flow data includes: predicted station entry data and predicted station exit data;

[0161] The determination module 120 is further used to determine the predicted inbound volume data based on the historical inbound volume data by using the target inbound volume prediction model; and to determine the predicted outbound volume data based on the historical outbound volume data by using the target outbound volume prediction model.

[0162] Optionally, the peak passenger flow period includes: an incoming passenger flow peak period and an outgoing passenger flow peak period; the determination module 120 is also used to calculate the average incoming volume and the average outgoing volume of the target station in the preset future time period according to the predicted incoming volume data and the predicted outgoing volume data; determine the incoming passenger flow peak period according to the average incoming volume and the predicted incoming volume data; determine the outgoing passenger flow peak period according to the average outgoing volume and the predicted outgoing volume data.

[0163] Optionally, the generation module 130 is also used to determine whether there is any overlap between the peak period of inbound passenger flow and the peak period of outbound passenger flow; if there is no overlap between the peak period of inbound passenger flow and the peak period of outbound passenger flow, then an operation plan for the peak period of inbound passenger flow is generated based on the predicted inbound volume data and the peak period of inbound passenger flow; and an operation plan for the peak period of outbound passenger flow is generated based on the predicted outbound volume data and the peak period of outbound passenger flow.

[0164] Optionally, the generation module 130 is also used to determine the overlapping peak passenger flow period of the incoming passenger flow peak period and the outgoing passenger flow peak period, the target incoming passenger flow peak period and the target outgoing passenger flow peak period if there is an overlap between the incoming passenger flow peak period and the outgoing passenger flow peak period; determine the target passenger flow traffic status corresponding to the overlapping peak passenger flow period based on the predicted incoming passenger flow data and the predicted outgoing passenger flow data; generate an operation plan for the overlapping peak passenger flow period based on the target passenger flow traffic status; generate operation plans for the target incoming passenger flow peak period and the target outgoing passenger flow peak period respectively based on the predicted incoming passenger flow data and the predicted outgoing passenger flow data.

[0165] Optionally, the determination module 120 is also used to calculate the cumulative value of incoming passenger flow and the cumulative value of outgoing passenger flow during the overlapping passenger flow peak period according to the predicted incoming passenger flow data and the predicted outgoing passenger flow data; if the cumulative value of incoming passenger flow is greater than or equal to the cumulative value of outgoing passenger flow, then the target passenger flow traffic state is determined to be the incoming passenger flow peak state; if the cumulative value of incoming passenger flow is less than the cumulative value of outgoing passenger flow, then the target passenger flow traffic state is determined to be the outgoing passenger flow peak state.

[0166] Optionally, the historical passenger flow data respectively include: historical entry volume data and historical exit volume data within a preset historical date; the historical passenger flow data also include: date type data of the preset historical date, weather type data of the preset historical date and temperature data of the preset historical date, wherein the date type data is used to indicate whether the corresponding historical date is a working day, a holiday or a weekend, and the device also includes:

[0167] A training module is used to construct an arrival volume sample data set and an exit volume sample data set based on the historical arrival volume data, the historical exit volume data, the date type data, the weather type data and the temperature data of multiple historical time periods within the preset historical date; model training is performed on the arrival volume sample data set and the exit volume sample data set respectively to obtain the target arrival volume prediction model and the target exit volume prediction model, and the target passenger flow prediction model includes: the target arrival volume prediction model and the target exit volume prediction model.

[0168] Optionally, the device further comprises:

[0169] A reading module, used for reading the operation plan of the passenger flow peak period in the preset future time period when the trigger time of the preset future time period arrives;

[0170] The execution module is used to execute the operation plan for the peak passenger flow period when the preset execution conditions for the peak passenger flow period are met, so as to adjust the gate operation mode of the target gate during the peak passenger flow period.

[0171] Optionally, the operation plan for the peak passenger flow period includes: an operation plan for the peak passenger flow period entering the station;

[0172] The execution module is also used to execute the operation plan for the peak period of passenger flow entering the station when the preset execution trigger condition for the peak period of passenger flow entering the station is reached.

[0173] Optionally, the operation plan for the peak passenger flow period includes: an operation plan for the peak outbound passenger flow period;

[0174] The execution module is also used to execute the operation plan for the outbound passenger flow peak period when the preset execution trigger condition for the outbound passenger flow peak period is reached.

[0175] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0176] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors, or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0177] Fig.13 This is a schematic diagram of a computer device provided in an embodiment of the present application, which can be used to generate peak passenger flow operations at rail transit stations. Fig.13 As shown, the computer device includes: a processor 210 , a storage medium 220 , and a bus 230 .

[0178] The storage medium 220 stores machine-readable instructions executable by the processor 210. When the computer device is running, the processor 210 communicates with the storage medium 220 via the bus 230, and the processor 210 executes the machine-readable instructions to perform the steps of the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0179] Optionally, the present application further provides a storage medium 220, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method embodiment are executed. The specific implementation method and technical effect are similar and will not be repeated here.

[0180] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0183] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0184] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating peak passenger flow operations at a rail transit station, characterized in that: include: Obtain historical passenger flow data of target stations in preset rail transit; According to the historical passenger flow data, a pre-trained target passenger flow prediction model is used to determine the predicted passenger flow data of the target station in a preset future time period; Determine the peak passenger flow period within the preset future time period according to the predicted passenger flow data; Based on the predicted passenger flow data and the peak passenger flow period, an operation plan for the peak passenger flow period in the preset future time period is generated. The operation plan is used to adjust the gate operation mode of the target gate in the target site during the peak passenger flow period. The gate operation modes include: entry mode, exit mode and two-way mode.

2. The method according to claim 1, characterized in that: The historical passenger flow data includes: historical station entry data and historical station exit data; the target passenger flow prediction model includes: target station entry prediction model and target station exit prediction model; the predicted passenger flow data includes: predicted station entry data and predicted station exit data; The step of determining predicted passenger flow data of the target station in a preset future time period based on the historical passenger flow data and using a pre-trained target passenger flow prediction model includes: According to the historical station-entry volume data, the target station-entry volume prediction model is used to determine the predicted station-entry volume data; The predicted outbound volume data is determined based on the historical outbound volume data and using the target outbound volume prediction model.

3. The method according to claim 2, characterized in that The peak passenger flow period includes: an incoming passenger flow peak period and an outgoing passenger flow peak period; the peak passenger flow period in the preset future time period is determined according to the predicted passenger flow data, including: Calculate the average value of the inbound volume and the average value of the outbound volume of the target station in the preset future time period according to the predicted inbound volume data and the predicted outbound volume data; Determine the peak period of passenger flow entering the station according to the average passenger flow volume and the predicted passenger flow volume data; The peak period of outbound passenger flow is determined according to the average outbound volume and the predicted outbound volume data.

4. The method according to claim 3, characterized in that The step of generating an operation plan for the peak passenger flow period according to the predicted passenger flow data and the peak passenger flow period includes: Determine whether the peak time period of incoming passenger flow and the peak time period of outgoing passenger flow overlap; If the peak period of incoming passenger flow and the peak period of outgoing passenger flow do not overlap, generating an operation plan for the peak period of incoming passenger flow according to the predicted incoming passenger flow data and the peak period of incoming passenger flow; An operation plan for the peak period of outbound passenger flow is generated based on the predicted outbound volume data and the peak period of outbound passenger flow.

5. The method according to claim 4, characterized in that The step of generating a work plan for the peak passenger flow period according to the predicted passenger flow data and the peak passenger flow period further comprises: If the incoming passenger flow peak period overlaps with the outgoing passenger flow peak period, then determine the overlapping passenger flow peak period of the incoming passenger flow peak period and the outgoing passenger flow peak period, the target incoming passenger flow peak period and the target outgoing passenger flow peak period; Determine the target passenger flow state corresponding to the overlapping passenger flow peak period according to the predicted station entry volume data and the predicted station exit volume data; Generating an operation plan for the overlapping passenger flow peak period according to the target passenger flow traffic status; Based on the predicted inbound volume data and the predicted outbound volume data, operation plans for the target inbound passenger flow peak time period and the target outbound passenger flow peak time period are generated respectively.

6. The method according to claim 5, characterized in that Determining the target passenger flow state corresponding to the overlapping passenger flow peak period according to the predicted station entry volume data and the predicted station exit volume data includes: Calculating the cumulative value of incoming passenger flow and the cumulative value of outgoing passenger flow during the overlapping passenger flow peak period respectively according to the predicted incoming passenger flow data and the predicted outgoing passenger flow data; If the accumulated value of the incoming passenger flow is greater than or equal to the accumulated value of the outgoing passenger flow, determining that the target passenger flow state is the incoming passenger flow peak state; If the accumulated value of the incoming passenger flow is less than the accumulated value of the outgoing passenger flow, it is determined that the target passenger flow state is the outgoing passenger flow peak state.

7. The method according to claim 2, characterized in that The historical passenger flow data respectively include: historical entry volume data and historical exit volume data within a preset historical date; the historical passenger flow data also include: date type data of the preset historical date, weather type data of the preset historical date and temperature data of the preset historical date, wherein the date type data is used to indicate whether the corresponding historical date is a working day, a holiday or a weekend; the method further includes: determining the target station before the predicted passenger flow data of the preset future time period based on the historical passenger flow data and using a pre-trained target passenger flow prediction model; Constructing an inbound volume sample data set and an outbound volume sample data set according to the historical inbound volume data, the historical outbound volume data, the date type data, the weather type data and the temperature data of multiple historical time periods within the preset historical date; Model training is performed on the inbound volume sample data set and the outbound volume sample data set respectively to obtain the target inbound volume prediction model and the target outbound volume prediction model. The target passenger flow prediction model includes: the target inbound volume prediction model and the target outbound volume prediction model.

8. The method according to claim 1, characterized in that The method further comprises: When the trigger time of the preset future time period arrives, reading the operation plan for the peak passenger flow period in the preset future time period; When the preset execution condition of the peak passenger flow period is reached, the operation plan of the peak passenger flow period is executed to adjust the gate operation mode of the target gate during the peak passenger flow period.

9. The method according to claim 8, characterized in that The operation plan during the peak passenger flow period includes: the operation plan during the peak passenger flow period; When the preset execution condition of the passenger flow peak period is reached, executing the operation plan of the passenger flow peak period includes: When the preset execution trigger condition of the peak period of passenger flow entering the station is reached, the operation plan of the peak period of passenger flow entering the station is executed.

10. The method according to claim 8, characterized in that The operation plan during the peak passenger flow period includes: the operation plan during the peak passenger flow period of the outbound passenger flow; When the preset execution condition of the passenger flow peak period is reached, executing the operation plan of the passenger flow peak period includes: When the preset execution trigger condition of the outbound passenger flow peak period is reached, the operation plan of the outbound passenger flow peak period is executed.

Images