WO2022134692A1 - 一种轨道交通智能调度方法及系统 - Google Patents

一种轨道交通智能调度方法及系统 Download PDF

Info

Publication number
WO2022134692A1
WO2022134692A1 PCT/CN2021/120054 CN2021120054W WO2022134692A1 WO 2022134692 A1 WO2022134692 A1 WO 2022134692A1 CN 2021120054 W CN2021120054 W CN 2021120054W WO 2022134692 A1 WO2022134692 A1 WO 2022134692A1
Authority
WO
WIPO (PCT)
Prior art keywords
passenger flow
rail transit
data
transit station
flow data
Prior art date
Application number
PCT/CN2021/120054
Other languages
English (en)
French (fr)
Inventor
胡恩华
林立
裴加富
张兵建
范东明
郭佳峰
杨双磊
Original Assignee
卡斯柯信号有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 卡斯柯信号有限公司 filed Critical 卡斯柯信号有限公司
Priority to EP21908693.1A priority Critical patent/EP4071736A4/en
Priority to US17/793,156 priority patent/US20230062565A1/en
Publication of WO2022134692A1 publication Critical patent/WO2022134692A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis

Definitions

  • the invention relates to the technical field of urban rail transit intelligence, in particular to a rail transit intelligent dispatch method and system.
  • the urban rail transit station is not only a place for passengers to get on and off and transfer, but also a place for vehicles to arrive, depart, turn back and temporarily park. It can be said that the normal operation of an urban rail transit station is the An important guarantee for the smooth flow of rail traffic.
  • the normal operation of urban rail transit stations requires the normal operation of equipment in the station and the orderly circulation of passenger flow to ensure.
  • a corresponding automatic system (such as a comprehensive monitoring system) has been built to monitor the operation status of the equipment in the rail transit station to ensure the normal operation of the equipment.
  • a comprehensive monitoring system For the passenger flow in the rail transit station, it mainly relies on the staff for manual management; however, due to the limited staff, and it is impossible to accurately predict the passenger flow of the rail transit station and timely dispatch the vehicles, large-scale multi-line transfer stations and nearby Rail transit stations in railway stations or airports often have problems of hoarding passengers in the station due to the large passenger flow, which brings potential safety risks to the normal operation of rail transit stations, and also increases the work intensity and difficulty of staff. And reduce the travel efficiency of urban rail transit.
  • the purpose of the present invention is to provide a rail transit intelligent scheduling method and system, which can accurately predict the passenger flow of rail transit stations according to multiple data sources and coordinate and dispatch vehicles and passengers, so as to make the passenger flow of rail transit stations smooth.
  • An intelligent scheduling method for rail transit comprising:
  • the preset range includes: the rail transit station and a circular radiation area centered on the rail transit station and having a radius of 300 to 2500 meters;
  • the original data includes: ticket sales data, station video data, mobile phone signaling data, vehicle-mounted video data and vehicle weighing data.
  • the step of acquiring the passenger flow data of the rail transit station according to the original data includes:
  • the method before executing the step of constructing the passenger flow prediction model of the rail transit station according to the passenger flow data of the rail transit station, the method further includes:
  • the step of constructing the passenger flow prediction model of the rail transit station according to the passenger flow data of the rail transit station includes:
  • a preset method is used to construct the passenger flow of the rail transit station prediction model
  • the preset method includes one or any combination of sliding window averaging method, T-SNE pattern analysis, DBSCAN pattern clustering and random forest algorithm.
  • the step of obtaining the passenger flow of the rail transit station in a preset time period through the passenger flow prediction model includes:
  • the preprocessed real-time entry and exit gate passenger flow data obtain the location of the rail transit station through the passenger flow prediction model. Inbound and outbound passenger flow in the preset time period.
  • the step of coordinating and scheduling vehicles and passengers at the rail transit station according to the passenger flow in the preset time period includes:
  • the capacity matching coefficient of the vehicle to be entered is calculated according to the amount of passengers stranded in the preset period and the capacity of the vehicle to be entered, so as to determine the matching coefficient of the vehicle to be entered and the stranded passengers at the rail transit station. Coordinate scheduling.
  • the step of coordinating and scheduling vehicles and passengers at the rail transit station according to the passenger flow in the preset time period further includes:
  • the transport capacity matching coefficient is greater than 0.8, a yellow warning will be issued to the rail transit station, and the stranded passengers will be dredged;
  • the transport capacity matching coefficient is greater than 1.2, a red warning is given to the rail transit station, the number of the vehicles to be entered is increased, and the running interval of the vehicles to be entered is adjusted.
  • the present invention also provides a rail transit intelligent dispatching system, comprising:
  • a data acquisition module for collecting raw data in a preset range from multiple data sources
  • a data analysis module used for obtaining passenger flow data of the rail transit station according to the original data
  • a model building module for constructing a passenger flow prediction model of the rail transit station according to the passenger flow data of the rail transit station, and obtaining the passenger flow of the rail transit station in a preset time period through the passenger flow prediction model;
  • the command and dispatch module is used to coordinate and dispatch the vehicles and passengers of the rail transit station according to the passenger flow of the preset time period.
  • the rail transit intelligent dispatching system further includes:
  • a data preprocessing module for preprocessing the original data
  • the heat map module is used to generate a passenger flow heat map based on the passenger flow data of the rail transit station.
  • the preset range includes: the rail transit station and a circular radiation area centered on the rail transit station and having a radius of 300 to 2500 meters;
  • the original data includes: ticket sales data, station video data, mobile phone signaling data, vehicle-mounted video data and vehicle weighing data.
  • the data analysis module is specifically configured to acquire historical passenger flow data and real-time passenger flow data entering and exiting the gates of the rail transit station according to the ticket sales and inspection data;
  • the data preprocessing module is specifically configured to analyze the historical entry and exit gate passenger flow data, the real-time entry and exit gate passenger flow data, the historical entry and exit passenger flow data, the real-time entry and exit passenger flow data, and the historical vehicle passenger flow data.
  • the data and the real-time vehicle passenger flow data are preprocessed, and the preprocessing includes deduplication and regression verification.
  • the model building module is specifically configured to use a preset according to the preprocessed historical entry and exit gate passenger flow data, the preprocessed historical entry and exit passenger flow data, and the preprocessed historical vehicle passenger flow data.
  • the method constructs the passenger flow prediction model of the rail transit station;
  • the preprocessed real-time entry and exit gate passenger flow data obtain the location of the rail transit station through the passenger flow prediction model. Inbound and outbound passenger flow in the preset time period.
  • the preset method includes one or any combination of sliding window averaging method, T-SNE pattern analysis, DBSCAN pattern clustering and random forest algorithm.
  • the command and dispatch module is specifically configured to acquire the passenger retention amount of the rail transit station in the preset time period according to the inbound and outbound passenger flow of the preset time period;
  • the capacity matching coefficient of the vehicle to be entered is calculated according to the amount of passengers stranded in the preset period and the capacity of the vehicle to be entered, so as to determine the matching coefficient of the vehicle to be entered and the stranded passengers at the rail transit station. Coordinate scheduling.
  • the transport capacity matching coefficient is greater than 0.8, a yellow warning is given to the rail transit station, and stranded passengers are dredged;
  • the transport capacity matching coefficient is greater than 1.2, a red warning is given to the rail transit station, the number of the vehicles to be entered is increased, and the running interval of the vehicles to be entered is adjusted.
  • the invention provides an intelligent scheduling method and system for rail transit, which can collect original data in a preset range from multiple data sources, and obtain passenger flow data of rail transit stations according to the original data, thereby realizing an all-round view of passenger flow at rail transit stations.
  • the real-time monitoring can not only overcome the shortcomings of the existing technology of single means of obtaining passenger flow data of rail transit stations, but also provide rich data support for the construction of passenger flow prediction models.
  • the present invention can perform preprocessing such as information conversion, data deduplication (including data duplication checking, cleaning and screening, etc.) and regression verification on the passenger flow data of rail transit stations obtained from the original data collected from multiple data sources, so that the acquired rails can be The accuracy of passenger flow data at traffic stations is high.
  • preprocessing such as information conversion, data deduplication (including data duplication checking, cleaning and screening, etc.) and regression verification on the passenger flow data of rail transit stations obtained from the original data collected from multiple data sources, so that the acquired rails can be The accuracy of passenger flow data at traffic stations is high.
  • the passenger retention at the rail transit station obtained from the inbound and outbound passenger flow in the preset period is combined with the transport capacity of the vehicles to be entered in the preset period obtained according to the number of vehicles to enter the station and the real-time vehicle passenger flow data, to obtain The matching coefficient of the transportation capacity of the vehicles to be entered is obtained, and the dynamic correlation between the inbound and outbound passenger flow of the rail transit station and the transportation capacity of the vehicles to be entered is realized.
  • the present invention can also issue different early warnings to rail transit stations according to the matching coefficient of transport capacity of vehicles to enter the station, so that station staff can take different measures, so as to reasonably coordinate and dispatch vehicles and passengers at the rail transit station, and thus have The program should deal with the upcoming large passenger flow to ensure the smooth passenger flow of the rail transit station.
  • the present invention can also be linked with the ground transportation system to guide passengers to take ground transportation or other nearby subway lines according to the ground transportation information, so as to form regional dispatch management, thereby ensuring the smooth flow of passengers at rail transit stations.
  • FIG. 1 is a flowchart of a method for intelligent dispatching of rail transit provided by an embodiment of the present invention
  • FIG. 2 is a logical diagram of coordinated scheduling of vehicles and passengers by a method for intelligent scheduling of rail transit provided by an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a rail transit intelligent dispatching system according to an embodiment of the present invention.
  • this embodiment provides an intelligent scheduling method for rail transit, including: step S110, collecting original data of a preset range from multiple data sources; step S120, acquiring rail transit according to the original data Passenger flow data of the station; Step S130, construct a passenger flow prediction model of the rail transit station according to the passenger flow data of the rail transit station; Step S140, obtain the passenger flow of the rail transit station in a preset time period through the passenger flow prediction model ; and step S150 , coordinate and dispatch the vehicles and passengers of the rail transit station according to the passenger flow of the preset time period, so as to make the passenger flow of the rail transit station smooth.
  • the preset range includes: the rail transit station and a circular radiation area with the rail transit station as the center and a radius of 300 to 2500 meters;
  • the original data includes: Ticket sales data, station video data, mobile phone signaling data, vehicle video data and vehicle weighing data.
  • the step S120 includes: acquiring historical passenger flow data and real-time passenger flow data entering and exiting the gates of the rail transit station according to the ticket sales data;
  • the video data and the mobile phone signaling data are used to obtain historical inbound and outbound passenger flow data and real-time inbound and outbound passenger flow data of the rail transit station;
  • Historical vehicle passenger flow data and real-time vehicle passenger flow data are used to obtain historical inbound and outbound passenger flow data and real-time inbound and outbound passenger flow data of the rail transit station.
  • the surrounding area of the rail transit station can be a circular radiation area with the rail transit station as the center and a radius of 2000 meters, but the present invention does not use this as a limit.
  • the preset range that is, the raw data of the rail transit station and the circular radiation area may be obtained from multiple data sources.
  • the ticket sales and collection system of the rail transit station, the station video system in the preset range (including the platform, the station hall and the surrounding area outside the station, etc.), the video system outside the station and the mobile phone of the mobile operator can be respectively passed
  • the signaling system and the on-board system of the vehicle to be entered obtain the original data of the rail transit station, that is, the ticket sales data, the station video data, the off-station video data, the mobile phone signaling data, the in-vehicle video data and the vehicle weighing data.
  • the passenger flow data of the rail transit station can be obtained, and the all-round real-time monitoring of the passenger flow of the rail transit station can be realized, which can overcome the problems in the prior art.
  • the single defect of obtaining the passenger flow data of the rail transit station can provide rich data support for the subsequent construction of the passenger flow prediction model, but the present invention is not limited to this.
  • the historical entry and exit gate passenger flow data and the real-time entry and exit gate passenger flow data of the rail transit station can be obtained through the ticket sales and inspection data; wherein the real-time entry and exit gate passenger flow data may include stages Through the preset range (including the platform, the station hall and the surrounding area outside the station, etc.) of the station video data, the station video data and the Mobile phone signaling data, combined with passenger flow analysis, the historical entry and exit passenger flow data and real-time entry and exit passenger flow data of the rail transit station can be obtained; it can also be obtained through the on-board video data and the vehicle weighing data.
  • the historical on-board passenger flow data and the real-time on-board passenger flow data of the vehicles to be entered for example, two shifts about to enter the station) in the rail transit station.
  • step S130 further includes: analyzing the historical entry and exit gate passenger flow data, the real-time entry and exit gate passenger flow data, the historical entry and exit passenger flow data, the real-time entry and exit passenger flow data, the The historical vehicle passenger flow data and the real-time vehicle passenger flow data are preprocessed, and the preprocessing includes deduplication and regression verification.
  • the passenger flow data of the rail transit station is obtained by analyzing the original data collected from the multiple data sources, such as passenger flow density, passenger flow direction, passenger flow velocity, and abnormal passenger behavior.
  • the obtained passenger flow data of the rail transit station can be preprocessed by information conversion, data deduplication (including data duplication checking, cleaning and screening, etc.)
  • the accuracy of the acquired passenger flow data of the rail transit station is relatively high, but the present invention is not limited to this.
  • the step S130 includes: according to the preprocessed historical entry and exit gate passenger flow data, the preprocessed historical entry and exit passenger flow data, and the preprocessed historical vehicle passenger flow data, using preprocessing
  • a predetermined method is used to construct the passenger flow prediction model of the rail transit station; the preset method includes one or any combination of sliding window averaging method, T-SNE pattern analysis, DBSCAN pattern clustering and random forest algorithm.
  • the preprocessed historical entry and exit gate passenger flow data, the preprocessed historical entry and exit passenger flow data, and the preprocessed historical vehicle passenger flow data may be used as training data
  • the The DBSCAN pattern clustering method, the random forest algorithm and the sliding window averaging method are combined to construct the passenger flow prediction model of the rail transit station and predict the inbound and outbound passenger flow of the rail transit station in a certain historical period, so as to obtain the above-mentioned The predicted value of the inbound and outbound passenger flow of the rail transit station in the historical period, wherein the inbound and outbound passenger flow of the rail transit station includes the passenger flow in and out of the rail transit station exit and the transfer in and out of the rail transit station. passenger flow.
  • the actual passenger flow value of the rail transit station corresponding to the above historical period can also be obtained from the urban rail transit statistical system, and the passenger flow forecast value of the rail transit station in the above historical period can be compared and analyzed, so as to analyze the passenger flow of the rail transit station in the above historical period.
  • the prediction model is optimized so that the prediction accuracy of the passenger flow prediction model meets the requirements. For example, it can be based on the preprocessed historical entry and exit gate passenger flow data, the preprocessed historical entry and exit passenger flow data, and the preprocessed data of the rail transit station in the morning (06:00-12:00) of a certain day.
  • the historical vehicle passenger flow is described, and the inbound and outbound passenger flow in the afternoon (12:00 ⁇ 18:00) of the day is predicted and compared with the actual value of the inbound and outbound passenger flow in the afternoon (12:00 ⁇ 18:00).
  • Optimizing the passenger flow prediction model also according to the pre-processed real-time on-board passenger flow data of a certain shift vehicle, after predicting the passenger flow of the vehicle getting on and off at the rail transit station for the shift, and comparing the passenger flow with the shift.
  • the actual value of the passenger flow of vehicles getting on and off at the rail transit station is compared to optimize the passenger flow prediction model.
  • external influencing factors can also be superimposed, such as dates (working days, weekends and holidays), weather, travel plans, various activities outside the station, equipment conditions and Other emergencies, etc., to improve the prediction accuracy of the passenger flow prediction model, but the present invention is not limited to this.
  • the step S140 includes: according to the preprocessed real-time entry and exit gate passenger flow data, the preprocessed real-time entry and exit passenger flow data and the preprocessed real-time vehicle passenger flow data, through the The passenger flow prediction model obtains the inbound and outbound passenger flow of the rail transit station in the preset time period.
  • the preset time period may be a certain future time period relative to real-time, or may be the whole day including real-time; for example, real-time is 14:00 on the same day, and the preset time period may be the current day 17:00, can also be the whole day of the day.
  • the passenger flow prediction model can predict a certain 1. Incoming passenger flow, outbound passenger flow and cross-sectional passenger flow in the future period, prediction of morning and evening peak peaks, and prediction of all-day inbound passenger flow, outbound passenger flow and cross-sectional passenger flow, but the present invention is not limited to this.
  • the step S150 includes: acquiring the passenger retention amount of the rail transit station in the preset time period according to the inbound and outbound passenger flow in the preset time period; The number of the vehicles to be entered at the rail transit station within the preset time period; the vehicles to be entered in the preset time period are calculated according to the number of the vehicles to be entered and the real-time vehicle passenger flow data and calculating the matching coefficient of the transportation capacity of the vehicles to be entered according to the passenger retention in the preset time period and the transportation capacity of the vehicles to be entered, so as to adjust the transportation capacity of the vehicles to be entered at the rail transit station. Coordinate dispatch of station vehicles and stranded passengers.
  • the step S150 further includes: the transport capacity matching coefficient is greater than 0.8, giving a yellow warning to the rail transit station, and guiding stranded passengers; the transport capacity If the matching coefficient is greater than 1, the rail transit station is given an orange warning, and the rail transit station is limited in flow; and if the capacity matching coefficient is greater than 1.2, a red warning is given to the rail transit station, and the The number of vehicles to be in the station and the adjustment of the running interval of the vehicles to be in the station.
  • the operation map of the rail transit vehicle may be received from the rail transit signal system to obtain the arrival and departure time information of the vehicle to be entered at the rail transit station, so as to obtain the rail transit vehicle within the preset time period.
  • the number of the vehicles to enter the station at the station is further combined with the real-time vehicle passenger flow data of the vehicles to enter the station to obtain the transportation capacity of the vehicles to enter the preset time period.
  • the ratio of the passenger retention amount in the preset period to the transport capacity of the vehicle to be in the station is the capacity matching coefficient of the vehicle to be in the station.
  • the transport capacity matching coefficient is not greater than 0.8, no scheduling measures are taken; when the transport capacity matching coefficient is greater than 0.8 and less than 1, a yellow warning is given to the rail transit station, and the The stranded passengers are dredged; when the transport capacity matching coefficient is greater than 1 and less than 1.2, an orange warning is given to the rail transit station, and the rail transit station is limited in flow and dredged passengers are dredged; When the capacity matching coefficient is greater than 1.2, a red warning is issued to the rail transit station, the number of vehicles to be entered is increased, and the running interval of the vehicles to be entered is adjusted.
  • It can limit the flow and guide the stranded passengers; it can also be linked with the ground transportation system to guide passengers to change to ground transportation or other nearby subway lines according to the ground transportation information, so as to form regional dispatch management and ensure the rail transportation. Passenger flow at the station is smooth.
  • this embodiment further provides an intelligent rail transit dispatching system, including: a data collection module 110 for collecting raw data in a preset range from multiple data sources; a data analysis module 120, for acquiring passenger flow data of the rail transit station according to the original data; model building module 140, for constructing a passenger flow prediction model of the rail transit station according to the passenger flow data of the rail transit station, and predicting the passenger flow through the passenger flow
  • the model obtains the passenger flow of the rail transit station in a preset period; and the command and dispatch module 150 is configured to coordinate and dispatch vehicles and passengers at the rail transit station according to the passenger flow in the preset period.
  • the rail transit intelligent dispatching system further includes: a data preprocessing module 130 for preprocessing the original data; a heat map module 160 for The passenger flow data of the traffic station generates a passenger flow heat map.
  • the preset range includes: the rail transit station and a circular radiation area centered on the rail transit station and having a radius of 300 meters to 2,500 meters; the raw data includes: ticket sales data , station video data, mobile phone signaling data, vehicle video data and vehicle weighing data.
  • the data collection module 110 can be respectively connected with the ticket collection system of the rail transit station, the station video within the preset range (including the platform, the station hall, and the surrounding area outside the station, etc.) system, the off-site video system and the mobile phone signaling system of the mobile operator and the on-board system of the vehicle to be in the station to obtain and store the original data in the preset range; the data acquisition module 110 can also be separately Connect with the rail transit signal system and the ground transit system to obtain the rail transit vehicle operation map and the ground transit information of the rail transit station; preferably, the data collection module 110 is connected to the ticket collection system, The station video system, the off-station video system, the mobile phone signaling system of the mobile operator, the on-board system of the vehicle to be entered, the rail traffic signal system and the ground transportation system can be set up. Network security protection equipment to ensure the safety of data transmission; the data collection module 110 may be a data collection server, but the present invention is not limited to this.
  • the data analysis module 120 is specifically configured to obtain historical passenger flow data and real-time passenger flow data entering and exiting the gates of the rail transit station according to the ticket sales data; Obtain the historical inbound and outbound passenger flow data and real-time inbound and outbound passenger flow data of the rail transit station from the mobile phone signaling data; and obtain the historical in-vehicle passenger flow data and real-time in-vehicle passenger flow data of the vehicle to be entered according to the on-board video data and the vehicle weighing data. data.
  • the data analysis module 120 can obtain the rail transit information after analyzing the original data in the preset range, such as passenger flow density, passenger flow direction, passenger flow velocity, and abnormal passenger behavior.
  • the passenger flow data of the station namely the historical entry and exit gate passenger flow data, the real-time entry and exit gate passenger flow data, the historical entry and exit passenger flow data, the real-time entry and exit passenger flow data, the historical vehicle passenger flow data and the real-time vehicle passenger flow data data;
  • the data analysis module 120 may be a data analysis server, but the present invention is not limited thereto.
  • the data preprocessing module 130 is specifically configured to analyze the historical entry and exit passenger flow data, the real-time entry and exit passenger flow data, the historical entry and exit passenger flow data, the real-time entry and exit passenger flow data, the The historical vehicle passenger flow data and the real-time vehicle passenger flow data are preprocessed, and the preprocessing includes deduplication and regression verification.
  • the passenger flow data of the rail transit station obtained by the data analysis module 120 includes the historical entry and exit gate passenger flow data, the real-time entry and exit gate passenger flow data, the historical entry and exit data If the passenger flow data, the real-time entry and exit passenger flow data, the historical vehicle passenger flow data and the real-time vehicle passenger flow data) have the problem of data duplication, the data preprocessing module 130 needs to analyze the obtained passenger flow data of the rail transit station.
  • the preprocessing module 130 may be a data preprocessing server, but the present invention is not limited thereto.
  • the heat map module 160 can generate a passenger flow heat flow map according to the preprocessed passenger flow data of the rail transit station, so as to visually display the specific distribution of the passenger flow, but the present invention does not This is the limit.
  • the model building module 140 is specifically configured to use the preprocessed historical entry and exit gate passenger flow data, the preprocessed historical entry and exit passenger flow data, and the preprocessed historical vehicle passenger flow data , using a preset method to construct the passenger flow prediction model of the rail transit station; Real-time vehicle passenger flow data, and the passenger flow in and out of the rail transit station in the preset time period is obtained through the passenger flow prediction model.
  • the preset method includes one or any combination of sliding window averaging method, T-SNE pattern analysis, DBSCAN pattern clustering and random forest algorithm.
  • the model building module 140 constructs the passenger flow prediction model by combining the DBSCAN pattern clustering method, the random forest algorithm and the sliding window averaging method, so as to improve the prediction accuracy of the passenger flow prediction model,
  • the present invention is not limited to this.
  • the command and dispatch module 150 is specifically configured to obtain the passenger retention amount of the rail transit station in the preset time period according to the inbound and outbound passenger flow in the preset time period;
  • the number of the vehicles to be entered at the rail transit station within the preset time period; the vehicles to be entered in the preset time period are calculated according to the number of the vehicles to be entered and the real-time vehicle passenger flow data and calculating the matching coefficient of the transportation capacity of the vehicles to be entered according to the passenger retention in the preset time period and the transportation capacity of the vehicles to be entered, so as to adjust the transportation capacity of the vehicles to be entered at the rail transit station. Coordinate dispatch of station vehicles and stranded passengers.
  • the transport capacity matching coefficient is greater than 0.8, a yellow warning is issued to the rail transit station, and stranded passengers are dredged; the transport capacity matching coefficient is greater than 1, and the If the capacity matching coefficient is greater than 1.2, the rail transit station will be issued an orange early warning, and the rail transit station will be limited; and if the capacity matching coefficient is greater than 1.2, a red early warning will be issued to the rail transit station, and the number of vehicles to be entered will be increased and Adjust the running interval of the vehicles to be in the station.
  • the command and dispatch module 150 may provide a human-machine interface for dispatching the regional command center of the rail transit station, so as to facilitate the dispatching of the rail transit according to the capacity matching coefficient of the vehicles to be entered and the ground traffic information. Vehicles and passengers at the station are reasonably and timely coordinated and dispatched, thereby ensuring smooth passenger flow at the rail transit station; the command and dispatch module 150 may be a command and dispatch workstation, but the present invention is not limited to this.
  • the command and dispatch module 150 if the capacity matching coefficient calculated by the command and dispatch module 150 is not greater than 0.8, the command and dispatch module 150 does not take any dispatch measures; when the capacity matching coefficient is greater than 0.8 and less than At 1:00, the command and dispatch module 150 issues a yellow warning to the rail transit station, and informs the station staff to guide the stranded passengers; when the transport capacity matching coefficient is greater than 1 and less than 1.2, the command and dispatch The module 150 gives an orange warning to the rail transit station, and informs the station staff to limit the flow of the rail transit station and guide the stranded passengers; when the transport capacity matching coefficient is greater than 1.2, the command and dispatch The module 150 gives a red warning to the rail transit station, and notifies the station staff to increase the number of vehicles to be in the station and adjust the running interval of the vehicles to be in the station.
  • the command and dispatch module 150 can also be linked with the ground transportation system to guide passengers to change to ground transportation or other nearby subway lines according to the ground traffic information, so as to form regional dispatch management, thereby ensuring the track The traffic at the station is smooth.
  • this embodiment provides a rail transit scheduling method and system, which can collect original data in a preset range from multiple data sources; acquire passenger flow data of rail transit stations according to the original data;
  • the passenger flow prediction model of the rail transit station is constructed from the data, and the passenger flow of the rail transit station in the preset time period is obtained through the passenger flow prediction model; according to the passenger flow in the preset time period, the vehicles and passengers of the rail transit station can be coordinated and dispatched.
  • the present embodiment provides an intelligent scheduling method and system for rail transit, which can acquire passenger flow data of rail transit stations according to the original data of a preset range collected from multiple data sources and perform preprocessing, so as to realize the complete monitoring of passenger flow of rail transit stations.
  • the real-time monitoring of orientation improves the accuracy of passenger flow data at rail transit stations; it can also issue different early warnings to rail transit stations according to the capacity matching coefficient of vehicles to be in the station, so that station staff can take different measures.
  • the vehicles and passengers at the rail transit station shall be reasonably coordinated and dispatched, so as to deal with the upcoming large passenger flow in an orderly manner and ensure the smooth flow of passengers at the rail transit station.
  • the terms “installed”, “connected”, “connected” and “fixed” should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrated; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of the two elements or the interaction relationship between the two elements.
  • installed should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrated; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of the two elements or the interaction relationship between the two elements.
  • a first feature "on” or “under” a second feature may include the first and second features in direct contact, or may include the first and second features Not directly but through additional features between them.
  • the first feature being “above”, “over” and “above” the second feature includes the first feature being directly above and obliquely above the second feature, or simply means that the first feature is level higher than the second feature.
  • the first feature is “below”, “below” and “below” the second feature includes the first feature being directly below and diagonally below the second feature, or simply means that the first feature has a lower level than the second feature.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开了一种轨道交通智能调度方法及系统，所述方法包括：从多个数据源采集预设范围的原始数据；根据所述原始数据获取轨道交通车站的客流数据；根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型；通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度，以使所述轨道交通车站的客流畅通。本发明通过多个数据源获取原始数据，进而获取客流数据，实现了对轨道交通车站客流的全方位监测，并能够对发出不同的预警，以便对轨道交通车站的车辆和乘客进行合理的协调调度，进而有序应对即将出现的大客流，保证轨道交通车站的客流畅通。

Description

一种轨道交通智能调度方法及系统 技术领域
本发明涉及城市轨道交通智能技术领域，尤其涉及一种轨道交通智能调度方法及系统。
背景技术
城市轨道交通车站作为城市轨道交通系统的重要组成部分之一，既是乘客上下车和换乘的场所，又是车辆到发、折返及临时停车的地点，可以说城市轨道交通车站的正常运营是城市轨道交通畅通的重要保障。而城市轨道交通车站的正常运营则需要车站内设备的正常运行和客流的有序流通来保障。
目前，已建设有相应的自动化系统(例如综合监控系统)对轨道交通车站内设备的运行状态进行监测，以确保设备的正常运行。对于轨道交通车站内的客流，则主要依靠工作人员进行人工管理；但是由于工作人员有限，且无法对轨道交通车站的客流进行准确预测以及对车辆进行及时调度，大型多线路换乘车站以及附近有火车站或机场的轨道交通车站则经常会因出现超大客流而造成车站内客流囤积的问题，给轨道交通车站的正常运营带来潜在的安全风险，同时还增加了工作人员的工作强度和难度，并降低了城市轨道交通的出行效率。
发明的公开
本发明的目的在于提供一种轨道交通智能调度方法及系统，可以根据多个数据源对轨道交通车站的客流量进行准确预测并对车辆和乘客进行协调调度，从而使轨道交通车站的客流畅通。
为了达到上述目的，本发明通过以下技术方案实现：
一种轨道交通智能调度方法，包括：
从多个数据源采集预设范围的原始数据；
根据所述原始数据获取轨道交通车站的客流数据；
根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型；
通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及
根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度，以使所述轨道交通车站的客流畅通。
优选地，所述预设范围包括：所述轨道交通车站以及以所述轨道交通车站为中心且半径为300米～2500米的圆形辐射区域；
所述原始数据包括：售检票数据、车站视频数据、手机信令数据、车载视频数据及车辆称重数据。
优选地，所述根据所述原始数据获取轨道交通车站的客流数据的步骤包括：
根据所述售检票数据获取所述轨道交通车站的历史进出闸机客流数据和实时进出闸机客流数据；
根据所述车站视频数据和所述手机信令数据获取所述轨道交通车站的历史出入客流数据和实时出入客流数据；以及
根据所述车载视频数据及所述车辆称重数据获取待进站车辆的历史车载客流数据和实时车载客流数据。
优选地，执行所述根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型的步骤之前还包括：
对所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据进行预处理，且所述预处理包括去重和回归验证。
优选地，所述根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型的步骤包括：
根据预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据，采用预设方法构建所述轨道交通车站的所述客流预测模型；
所述预设方法包括滑动窗口平均法、T-SNE模式分析、DBSCAN模式聚类以及随机森林算法中的一种或任意一组合。
优选地，所述通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量的步骤包括：
根据预处理后的所述实时进出闸机客流数据、预处理后的所述实时出入客流数据和预处理后的所述实时车载客流数据，通过所述客流预测模型获取所述轨道交通车站在所述预设时段的进出站客流量。
优选地，所述根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度的步骤包括：
根据所述预设时段的进出站客流量获取所述轨道交通车站在所述预设时段的乘客滞留量；
通过轨道交通车辆运行图获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量；
根据所述待进站车辆的数量以及所述实时车载客流数据计算所述预设时段的所述待进站车辆的运能；以及
根据所述预设时段的乘客滞留量和所述待进站车辆的运能计算所述待进站车辆的运能匹配系数，以对所述轨道交通车站的所述待进站车辆和滞留乘客进行协调调度。
优选地，所述根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度的步骤还包括：
所述运能匹配系数大于0.8，对所述轨道交通车站进行黄色预警，并对滞留乘客进行疏导；
所述运能匹配系数大于1，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流；以及
所述运能匹配系数大于1.2，对所述轨道交通车站进行红色预警，并增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔。
另一方面，本发明还提供一种轨道交通智能调度系统，包括：
数据采集模块，用于从多个数据源采集预设范围的原始数据；
数据分析模块，用于根据所述原始数据获取轨道交通车站的客流数据；
模型构建模块，用于根据所述轨道交通车站的客流数据构建所述轨道交 通车站的客流预测模型，并通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及
指挥调度模块，用于根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度。
优选地，所述轨道交通智能调度系统，还包括：
数据预处理模块，用于对所述原始数据进行预处理；
热力图模块，用于根据轨道交通车站的客流数据生成客流热力图。
优选地，所述预设范围包括：所述轨道交通车站以及以所述轨道交通车站为中心且半径为300米～2500米的圆形辐射区域；
所述原始数据包括：售检票数据、车站视频数据、手机信令数据、车载视频数据及车辆称重数据。
优选地，所述数据分析模块具体用于根据所述售检票数据获取所述轨道交通车站的历史进出闸机客流数据和实时进出闸机客流数据；
根据所述车站视频数据和所述手机信令数据获取所述轨道交通车站的历史出入客流数据和实时出入客流数据；以及
根据所述车载视频数据及所述车辆称重数据获取待进站车辆的历史车载客流数据和实时车载客流数据。
优选地，所述数据预处理模块具体用于对所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据进行预处理，且所述预处理包括去重和回归验证。
优选地，所述模型构建模块具体用于根据预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据，采用预设方法构建所述轨道交通车站的所述客流预测模型；以及
根据预处理后的所述实时进出闸机客流数据、预处理后的所述实时出入客流数据和预处理后的所述实时车载客流数据，通过所述客流预测模型获取所述轨道交通车站在所述预设时段的进出站客流量。
优选地，所述预设方法包括滑动窗口平均法、T-SNE模式分析、DBSCAN模式聚类以及随机森林算法中的一种或任意一组合。
优选地，所述指挥调度模块具体用于根据所述预设时段的进出站客流量 获取所述轨道交通车站在所述预设时段的乘客滞留量；
通过轨道交通车辆运行图获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量；
根据所述待进站车辆的数量以及所述实时车载客流数据计算所述预设时段的所述待进站车辆的运能；以及
根据所述预设时段的乘客滞留量和所述待进站车辆的运能计算所述待进站车辆的运能匹配系数，以对所述轨道交通车站的所述待进站车辆和滞留乘客进行协调调度。
优选地，所述运能匹配系数大于0.8，对所述轨道交通车站进行黄色预警，并对滞留乘客进行疏导；
所述运能匹配系数大于1，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流；以及
所述运能匹配系数大于1.2，对所述轨道交通车站进行红色预警，并增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔。
本发明至少具有以下优点之一：
本发明提供的一种轨道交通智能调度方法及系统，可以从多个数据源采集预设范围的原始数据，并根据原始数据获取轨道交通车站的客流数据，实现了对轨道交通车站客流的全方位的实时监测，既可以克服现有技术中获取轨道交通车站客流数据手段单一的缺陷，又可以为客流预测模型的构建提供丰富的数据支撑。
本发明可以对根据多个数据源采集的原始数据得到的轨道交通车站的客流数据进行信息换算、数据去重(包括数据查重、清洗和筛选等)以及回归验证等预处理，使得获取的轨道交通车站的客流数据的准确性较高。
本发明将由预设时段的进出站客流量获取的轨道交通车站的乘客滞留量与根据待进站车辆的数量以及实时车载客流数据得到的预设时段的待进站车辆的运能相结合，得到了待进站车辆的运能匹配系数，实现了轨道交通车站的进出站客流和待进站车辆的运能之间的动态关联。
本发明还可以根据待进站车辆的运能匹配系数，对轨道交通车站发出不同的预警，以便车站工作人员采取不同的措施，从而对轨道交通车站的车辆和乘客进行合理的协调调度，进而有序应对即将出现的大客流，保证轨道交 通车站的客流畅通。
本发明还可以与地面交通系统进行联动，以根据地面交通信息引导乘客改乘地面交通或者附近其他地铁线路，形成区域化调度管理，进而保证轨道交通车站的客流畅通。
附图的简要说明
图1是本发明一实施例提供的一种轨道交通智能调度方法的流程图；
图2是本发明一实施例提供的一种轨道交通智能调度方法对车辆和乘客进行协调调度的逻辑图；
图3是本发明一实施例提供的一种轨道交通智能调度系统的结构示意图。
实现本发明的最佳方式
以下结合附图和具体实施方式对本发明提出的一种轨道交通智能调度方法及系统作进一步详细说明。根据下面说明，本发明的优点和特征将更清楚。需要说明的是，附图采用非常简化的形式且均使用非精准的比例，仅用以方便、明晰地辅助说明本发明实施方式的目的。为了使本发明的目的、特征和优点能够更加明显易懂，请参阅附图。须知，本说明书所附图式所绘示的结构、比例、大小等，均仅用以配合说明书所揭示的内容，以供熟悉此技术的人士了解与阅读，并非用以限定本发明实施的限定条件，故不具技术上的实质意义，任何结构的修饰、比例关系的改变或大小的调整，在不影响本发明所能产生的功效及所能达成的目的下，均应仍落在本发明所揭示的技术内容能涵盖的范围内。
结合附图1～2所示，本实施例提供一种轨道交通智能调度方法，包括：步骤S110、从多个数据源采集预设范围的原始数据；步骤S120、根据所述原始数据获取轨道交通车站的客流数据；步骤S130、根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型；步骤S140、通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及步骤S150、根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度，以使所述轨道交通车站的客流畅通。
请同时参考图1和图2，所述预设范围包括：所述轨道交通车站以及以所述轨道交通车站为中心且半径为300米～2500米的圆形辐射区域；所述原始数据包括：售检票数据、车站视频数据、手机信令数据、车载视频数据及车辆称重数据。
可以理解的是，在一些其他的实施例中，所述步骤S120包括：根据所述售检票数据获取所述轨道交通车站的历史进出闸机客流数据和实时进出闸机客流数据；根据所述车站视频数据和所述手机信令数据获取所述轨道交通车站的历史进出站出入客流数据和实时进出站出入客流数据；以及根据所述车载视频数据及所述车辆称重数据获取待进站车辆的历史车载客流数据和实时车载客流数据。
具体的，在本实施例中，对于具有多条交通线路换乘的所述轨道交通车站，以及附近有火车站、机场、景点、大型展馆或购物商场等场所的所述轨道交通车站，极易出现因超大客流而造成所述轨道交通车站内乘客滞留或客流囤积的问题。因此不仅需要从所述轨道交通车站采集所述原始数据，还需要从所述轨道交通车站周边区域采集所述原始数据，以使根据所述原始数据获取的所述轨道交通车站的客流数据较为准确，进而保证所述轨道交通车站的客流畅通；优选地，所述轨道交通车站周边区域可以为以所述轨道交通车站为中心且半径为2000米的圆形辐射区域，但本发明不以此为限。
具体的，可以从多个数据源获取所述预设范围即所述轨道交通车站和所述圆形辐射区域的所述原始数据。优选地，可以分别通过所述轨道交通车站的售检票系统、所述预设范围(包括站台、站厅及站外周边区域等)内的车站视频系统、站外视频系统和移动运营商的手机信令系统以及待进站车辆的车载系统得到所述轨道交通车站的所述原始数据，即所述售检票数据、所述车站视频数据、所述站外视频数据、所述手机信令数据、所述车载视频数据以及所述车辆称重数据。利用从所述多个数据源采集的所述原始数据泽则可以获取所述轨道交通车站的客流数据，实现了对所述轨道交通车站客流的全方位的实时监测，既可以克服现有技术中获取所述轨道交通车站客流数据手段单一的缺陷，又可以为后续所述客流预测模型的构建提供丰富的数据支撑，但本发明不以此为限。
在本实施例中，可以通过所述售检票数据获取所述轨道交通车站的所述 历史进出闸机客流数据和所述实时进出闸机客流数据；其中所述实时进出闸机客流数据可以包括阶段性(例如5分钟)进出闸机客流数据和断面客流数据；通过所述预设范围(包括站台、站厅及站外周边区域等)内的所述车站视频数据、站外视频数据和所述手机信令数据，并结合客流流向分析，则可以得到所述轨道交通车站的所述历史出入客流数据和所述实时出入客流数据；还可以通过所述车载视频数据及所述车辆称重数据获取所述轨道交通车站内所述待进站车辆(例如即将进站的两个班次)的所述历史车载客流数据和所述实时车载客流数据。
请继续参考图1，执行所述步骤S130之前还包括：对所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据进行预处理，且所述预处理包括去重和回归验证。
具体的，在本实施例中，由于对从所述多个数据源采集的所述原始数据进行客流密度、客流流向、客流流速及乘客异常行为等分析后得到的所述轨道交通车站的客流数据存在数据重复的问题，因此可以对获取的所述轨道交通车站的客流数据进行信息换算、数据去重(包括数据查重、清洗和筛选等)以及数据校核即回归验证等预处理，以使获取的所述轨道交通车站的客流数据的准确性较高，但本发明不以此为限。
请继续参考图1，所述步骤S130包括：根据预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据，采用预设方法构建所述轨道交通车站的所述客流预测模型；所述预设方法包括滑动窗口平均法、T-SNE模式分析、DBSCAN模式聚类以及随机森林算法中的一种或任意一组合。
具体的，在本实施例中，可以将预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据作为训练数据，通过DBSCAN模式聚类方法、随机森林算法以及滑动窗口平均法相结合，构建所述轨道交通车站的所述客流预测模型并对某一历史时段所述轨道交通车站的进出站客流量进行预测，以得到上述历史时段所述轨道交通车站的进出站客流量预测值，其中所述轨道交通车站的进出站客流量包括出入所述轨道交通车站站口的客流量和所述轨道交通车站站内换乘的上下 车客流量。同时还可以从城市轨道交通统计系统获取上述历史时段对应的所述轨道交通车站的客流量实际值，并与上述历史时段所述轨道交通车站的客流量预测值进行对比分析，以对所述客流预测模型进行优化，从而使所述客流预测模型的预测精度满足要求。例如可以根据所述轨道交通车站某日上午(06:00～12:00)的预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流，对该日下午(12:00～18:00)的进出站客流量进行预测后与该日下午(12:00～18:00)的进出站客流量实际值进行对比，以对所述客流预测模型进行优化；还可以根据某班次车辆的预处理后的所述实时车载客流数据，对该班次车辆在所述轨道交通车站的上下车客流量进行预测后，并与该班次车辆在所述轨道交通车站的上下车客流量实际值进行对比，以对所述客流预测模型进行优化。优选地，在构建所述轨道交通车站的所述客流预测模型时，还可以叠加外部影响因素，例如日期(工作日、双休日及节假日)、天气、行车计划、站外各种活动、设备状况及其他突发情况等，以提高所述客流预测模型的预测精度，但本发明不以此为限。
请继续参考图1，所述步骤S140包括：根据预处理后的所述实时进出闸机客流数据、预处理后的所述实时出入客流数据和预处理后的所述实时车载客流数据，通过所述客流预测模型获取所述轨道交通车站在所述预设时段的进出站客流量。
具体的，在本实施例中，所述预设时段可以为相对于实时的某一未来时段，也可以为包含实时的全天；例如实时为当日14:00，所述预设时段可以为当日17:00，也可以为当日全天。更具体的，根据预处理后的所述实时进出闸机客流数据和预处理后的所述实时出入客流数据，以及预处理后的所述实时车载客流数据，通过所述客流预测模型可以预测某一未来时段的进站客流、出站客流和断面客流，预测早、晚高峰峰值，以及预测全天进站客流、出站客流和断面客流，但本发明不以此为限。
请同时参考图1和图2，所述步骤S150包括：根据所述预设时段的进出站客流量获取所述轨道交通车站在所述预设时段的乘客滞留量；通过轨道交通车辆运行图获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量；根据所述待进站车辆的数量以及所述实时车载客流数据计算所述预设时 段的所述待进站车辆的运能；以及根据所述预设时段的乘客滞留量和所述待进站车辆的运能计算所述待进站车辆的运能匹配系数，以对所述轨道交通车站的所述待进站车辆和滞留乘客进行协调调度。
可以理解的是，在一些其他的实施例中，所述步骤S150还包括：所述运能匹配系数大于0.8，对所述轨道交通车站进行黄色预警，并对滞留乘客进行疏导；所述运能匹配系数大于1，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流；以及所述运能匹配系数大于1.2，对所述轨道交通车站进行红色预警，并增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔。
具体的，可以从轨道交通信号系统接收所述轨道交通车辆运行图，以得到所述轨道交通车站的所述待进站车辆的到发时间信息，从而获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量，进而与所述待进站车辆的所述实时车载客流数据结合分析得到所述预设时段的所述待进站车辆的运能。所述预设时段的所述乘客滞留量与所述待进站车辆的运能之比则为所述待进站车辆的运能匹配系数。根据所述待进站车辆的运能匹配系数的大小，则可以对所述轨道交通车站发出不同的预警，以便车站工作人员可以采取不同的措施，从而对所述轨道交通车站的车辆和乘客进行合理的协调调度，以应对即将出现的大客流，但本发明不以此为限。
在本实施例中，若所述运能匹配系数不大于0.8，则不采取任何调度措施；当所述运能匹配系数大于0.8且小于1时，对所述轨道交通车站进行黄色预警，并对所述滞留乘客进行疏导；当所述运能匹配系数大于1且小于1.2时，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流以及对所述滞留乘客进行疏导；当所述运能匹配系数大于1.2时，对所述轨道交通车站进行红色预警，并增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔，同时对所述轨道交通车站进行限流以及对所述滞留乘客进行疏导；还可以与地面交通系统进行联动，以根据地面交通信息引导乘客改乘地面交通或者附近其他地铁线路，形成区域化调度管理，进而保证所述轨道交通车站的客流畅通。
基于同一发明构思，结合附图3所示，本实施例还提供一种轨道交通智能调度系统，包括：数据采集模块110，用于从多个数据源采集预设范围的 原始数据；数据分析模块120，用于根据所述原始数据获取轨道交通车站的客流数据；模型构建模块140，用于根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型，并通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及指挥调度模块150，用于根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度。
可以理解的是，在一些其他的实施例中，所述轨道交通智能调度系统，还包括：数据预处理模块130，用于对所述原始数据进行预处理；热力图模块160，用于根据轨道交通车站的客流数据生成客流热力图。
在一些实施例中，所述预设范围包括：所述轨道交通车站以及以所述轨道交通车站为中心且半径为300米～2500米的圆形辐射区域；所述原始数据包括：售检票数据、车站视频数据、手机信令数据、车载视频数据及车辆称重数据。
具体的，在本实施例中，所述数据采集模块110可以分别与所述轨道交通车站的售检票系统、所述预设范围(包括站台、站厅及站外周边区域等)内的车站视频系统、站外视频系统和移动运营商的手机信令系统以及待进站车辆的车载系统进行连接，以获取所述预设范围的所述原始数据并存储；所述数据采集模块110还可以分别与轨道交通信号系统、地面交通系统进行连接，以得到所述轨道交通车站的所述轨道交通车辆运行图和所述地面交通信息；优选地，所述数据采集模块110与所述售检票系统、所述车站视频系统、所述站外视频系统、所述移动运营商的手机信令系统、所述待进站车辆的车载系统、所述轨道交通信号系统和所述地面交通系统之间可以设置网络安全防护设备，以保证数据传输的安全；所述数据采集模块110可以为数据采集服务器，但本发明不以此为限。
请继续参考图3，所述数据分析模块120具体用于根据所述售检票数据获取所述轨道交通车站的历史进出闸机客流数据和实时进出闸机客流数据；根据所述车站视频数据和所述手机信令数据获取所述轨道交通车站的历史出入客流数据和实时出入客流数据；以及根据所述车载视频数据及所述车辆称重数据获取待进站车辆的历史车载客流数据和实时车载客流数据。
具体的，在本实施例中，所述数据分析模块120通过对所述预设范围的所述原始数据进行客流密度、客流流向、客流流速及乘客异常行为等分析后， 可以获取所述轨道交通车站的客流数据，即所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据；所述数据分析模块120可以为数据分析服务器，但本发明不以此为限。
请继续参考图3，所述数据预处理模块130具体用于对所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据进行预处理，且所述预处理包括去重和回归验证。
具体的，在本实施例中，由于所述数据分析模块120得到的所述轨道交通车站的客流数据(包括所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据)存在数据重复的问题，则需要所述数据预处理模块130对得到的所述轨道交通车站的客流数据进行信息换算、数据去重(包括数据查重、清洗和筛选等)以及数据校核即回归验证等预处理，以使获取的所述轨道交通车站的客流数据的准确性较高；所述数据预处理模块130可以为数据预处理服务器，但本发明不以此为限。
具体的，在本实施例中，所述热力图模块160则可以根据预处理的所述轨道交通车站的客流数据生成客流热流图，以对客流的具体分布情况进行直观的展示，但本发明不以此为限。
请继续参考图3，所述模型构建模块140具体用于根据预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据，采用预设方法构建所述轨道交通车站的所述客流预测模型；以及根据预处理后的所述实时进出闸机客流数据、预处理后的所述实时出入客流数据和预处理后的所述实时车载客流数据，通过所述客流预测模型获取所述轨道交通车站在所述预设时段的进出站客流量。
可以理解的是，在一些其他的实施例中，所述预设方法包括滑动窗口平均法、T-SNE模式分析、DBSCAN模式聚类以及随机森林算法中的一种或任意一组合。
具体的，在本实施例中，所述模型构建模块140通过DBSCAN模式聚类方法、随机森林算法以及滑动窗口平均法相结合来构建所述客流预测模型， 以提高所述客流预测模型的预测精度，但本发明不以此为限。
请继续参考图3，所述指挥调度模块150具体用于根据所述预设时段的进出站客流量获取所述轨道交通车站在所述预设时段的乘客滞留量；通过轨道交通车辆运行图获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量；根据所述待进站车辆的数量以及所述实时车载客流数据计算所述预设时段的所述待进站车辆的运能；以及根据所述预设时段的乘客滞留量和所述待进站车辆的运能计算所述待进站车辆的运能匹配系数，以对所述轨道交通车站的所述待进站车辆和滞留乘客进行协调调度。
可以理解的是，在一些其他的实施例中，所述运能匹配系数大于0.8，对所述轨道交通车站进行黄色预警，并对滞留乘客进行疏导；所述运能匹配系数大于1，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流；以及所述运能匹配系数大于1.2，对所述轨道交通车站进行红色预警，并增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔。
具体的，所述指挥调度模块150可以提供所述轨道交通车站的区域指挥中心调度人机界面，以便于根据所述待进站车辆的运能匹配系数和所述地面交通信息对所述轨道交通车站的车辆和乘客进行合理及时的协调调度，从而保证所述轨道交通车站的客流畅通；所述指挥调度模块150可以为指挥调度工作站，但本发明不以此为限。
在本实施例中，若所述指挥调度模块150计算得到的所述运能匹配系数不大于0.8，则所述指挥调度模块150不采取任何调度措施；当所述运能匹配系数大于0.8且小于1时，所述指挥调度模块150对所述轨道交通车站进行黄色预警，并通知车站工作人员对所述滞留乘客进行疏导；当所述运能匹配系数大于1且小于1.2时，所述指挥调度模块150对所述轨道交通车站进行橙色预警，并通知车站工作人员对所述轨道交通车站进行限流以及对所述滞留乘客进行疏导；当所述运能匹配系数大于1.2时，所述指挥调度模块150对所述轨道交通车站进行红色预警，并通知车站工作人员增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔，同时对所述轨道交通车站进行限流以及对所述滞留乘客进行疏导；所述指挥调度模块150还可以与地面交通系统进行联动，以根据地面交通信息引导乘客改乘地面交通或者附近其他地铁线路，形成区域化调度管理，进而保证所述轨道交通车站的客流畅通。
综上所述，本实施例提供一种轨道交通调度方法及系统，可以从多个数据源采集预设范围的原始数据；根据原始数据可以获取轨道交通车站的客流数据；根据轨道交通车站的客流数据构建轨道交通车站的客流预测模型，并通过所述客流预测模型获取轨道交通车站在预设时段的客流量；根据预设时段的客流量则可以对轨道交通车站的车辆和乘客进行协调调度，以使轨道交通车站的客流畅通。本实施例提供的一种轨道交通智能调度方法及系统，可以根据多个数据源采集的预设范围的原始数据获取轨道交通车站的客流数据并进行预处理，实现了对轨道交通车站客流的全方位的实时监测，提高了轨道交通车站的客流数据的准确性；还可以根据待进站车辆的运能匹配系数，对轨道交通车站发出不同的预警，以便车站工作人员采取不同的措施，从而对轨道交通车站的车辆和乘客进行合理的协调调度，进而有序应对即将出现的大客流，保证轨道交通车站的客流畅通。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
在本发明的描述中，需要理解的是，术语“中心”、“高度”、“厚度”、“上”、“下”、“竖直”、“水平”、“顶”、“底”、“内”、“外”、“轴向”、“径向”、“周向”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。在本发明的描述中，除非另有说明，“多个”的含义是两个或两个以上。
在本发明的描述中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”、“固定”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或成一体；可以是机械连接，也可以是电连接；可以是直接相连，也 可以通过中间媒介间接相连，可以是两个元件内部的连通或两个元件的相互作用关系。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本发明中的具体含义。
在本发明中，除非另有明确的规定和限定，第一特征在第二特征之“上”或之“下”可以包括第一和第二特征直接接触，也可以包括第一和第二特征不是直接接触而是通过它们之间的另外的特征接触。而且，第一特征在第二特征“之上”、“上方”和“上面”包括第一特征在第二特征正上方和斜上方，或仅仅表示第一特征水平高度高于第二特征。第一特征在第二特征“之下”、“下方”和“下面”包括第一特征在第二特征正下方和斜下方，或仅仅表示第一特征水平高度小于第二特征。
尽管本发明的内容已经通过上述优选实施例作了详细介绍，但应当认识到上述的描述不应被认为是对本发明的限制。在本领域技术人员阅读了上述内容后，对于本发明的多种修改和替代都将是显而易见的。因此，本发明的保护范围应由所附的权利要求来限定。

Claims (17)

  1. 一种轨道交通智能调度方法，其特征在于，包括：
    从多个数据源采集预设范围的原始数据；
    根据所述原始数据获取轨道交通车站的客流数据；
    根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型；
    通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及
    根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度，以使所述轨道交通车站的客流畅通。
  2. 如权利要求1所述的轨道交通智能调度方法，其特征在于，
    所述预设范围包括：所述轨道交通车站以及以所述轨道交通车站为中心且半径为300米～2500米的圆形辐射区域；
    所述原始数据包括：售检票数据、车站视频数据、手机信令数据、车载视频数据及车辆称重数据。
  3. 如权利要求2所述的轨道交通智能调度方法，其特征在于，所述根据所述原始数据获取轨道交通车站的客流数据的步骤包括：
    根据所述售检票数据获取所述轨道交通车站的历史进出闸机客流数据和实时进出闸机客流数据；
    根据所述车站视频数据和所述手机信令数据获取所述轨道交通车站的历史出入客流数据和实时出入客流数据；以及
    根据所述车载视频数据及所述车辆称重数据获取待进站车辆的历史车载客流数据和实时车载客流数据。
  4. 如权利要求3所述的轨道交通智能调度方法，其特征在于，执行所述根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型的步骤之前还包括：
    对所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时 车载客流数据进行预处理，且所述预处理包括去重和回归验证。
  5. 如权利要求4所述的轨道交通智能调度方法，其特征在于，所述根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型的步骤包括：
    根据预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据，采用预设方法构建所述轨道交通车站的所述客流预测模型；
    所述预设方法包括滑动窗口平均法、T-SNE模式分析、DBSCAN模式聚类以及随机森林算法中的一种或任意一组合。
  6. 如权利要求5所述的轨道交通智能调度方法，其特征在于，所述通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量的步骤包括：
    根据预处理后的所述实时进出闸机客流数据、预处理后的所述实时出入客流数据和预处理后的所述实时车载客流数据，通过所述客流预测模型获取所述轨道交通车站在所述预设时段的进出站客流量。
  7. 如权利要求6所述的轨道交通智能调度方法，其特征在于，所述根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度的步骤包括：
    根据所述预设时段的进出站客流量获取所述轨道交通车站在所述预设时段的乘客滞留量；
    通过轨道交通车辆运行图获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量；
    根据所述待进站车辆的数量以及所述实时车载客流数据计算所述预设时段的所述待进站车辆的运能；以及
    根据所述预设时段的乘客滞留量和所述待进站车辆的运能计算所述待进站车辆的运能匹配系数，以对所述轨道交通车站的所述待进站车辆和滞留乘客进行协调调度。
  8. 如权利要求7所述的轨道交通智能调度方法，其特征在于，所述根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度的步骤还包括：
    所述运能匹配系数大于0.8，对所述轨道交通车站进行黄色预警，并对滞 留乘客进行疏导；
    所述运能匹配系数大于1，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流；以及
    所述运能匹配系数大于1.2，对所述轨道交通车站进行红色预警，并增加所述待进站车辆的数量以及调整所述待进站车辆的运行间隔。
  9. 一种轨道交通智能调度系统，其特征在于，包括：
    数据采集模块(110)，用于从多个数据源采集预设范围的原始数据；
    数据分析模块(120)，用于根据所述原始数据获取轨道交通车站的客流数据；
    模型构建模块(140)，用于根据所述轨道交通车站的客流数据构建所述轨道交通车站的客流预测模型，并通过所述客流预测模型获取所述轨道交通车站在预设时段的客流量；以及
    指挥调度模块(150)，用于根据所述预设时段的客流量对所述轨道交通车站的车辆和乘客进行协调调度。
  10. 如权利要求9所述的轨道交通智能调度系统，其特征在于，还包括：
    数据预处理模块(130)，用于对所述原始数据进行预处理；
    热力图模块(160)，用于根据轨道交通车站的客流数据生成客流热力图。
  11. 如权利要求10所述的轨道交通智能调度系统，其特征在于，
    所述预设范围包括：所述轨道交通车站以及以所述轨道交通车站为中心且半径为300米～2500米的圆形辐射区域；
    所述原始数据包括：售检票数据、车站视频数据、手机信令数据、车载视频数据及车辆称重数据。
  12. 如权利要求11所述的轨道交通智能调度系统，其特征在于，所述数据分析模块(120)具体用于根据所述售检票数据获取所述轨道交通车站的历史进出闸机客流数据和实时进出闸机客流数据；
    根据所述车站视频数据和所述手机信令数据获取所述轨道交通车站的历史出入客流数据和实时出入客流数据；以及
    根据所述车载视频数据及所述车辆称重数据获取待进站车辆的历史车载客流数据和实时车载客流数据。
  13. 如权利要求12所述的轨道交通智能调度系统，其特征在于，所述数 据预处理模块(130)具体用于对所述历史进出闸机客流数据、所述实时进出闸机客流数据、所述历史出入客流数据、所述实时出入客流数据、所述历史车载客流数据和所述实时车载客流数据进行预处理，且所述预处理包括去重和回归验证。
  14. 如权利要求13所述的轨道交通智能调度系统，其特征在于，所述模型构建模块(140)具体用于根据预处理后的所述历史进出闸机客流数据、预处理后的所述历史出入客流数据以及预处理后的所述历史车载客流数据，采用预设方法构建所述轨道交通车站的所述客流预测模型；以及
    根据预处理后的所述实时进出闸机客流数据、预处理后的所述实时出入客流数据和预处理后的所述实时车载客流数据，通过所述客流预测模型获取所述轨道交通车站在所述预设时段的进出站客流量。
  15. 如权利要求14所述的轨道交通智能调度系统，其特征在于，
    所述预设方法包括滑动窗口平均法、T-SNE模式分析、DBSCAN模式聚类以及随机森林算法中的一种或任意一组合。
  16. 如权利要求14所述的轨道交通智能调度系统，其特征在于，所述指挥调度模块(150)具体用于根据所述预设时段的进出站客流量获取所述轨道交通车站在所述预设时段的乘客滞留量；
    通过轨道交通车辆运行图获取所述预设时段内所述轨道交通车站的所述待进站车辆的数量；
    根据所述待进站车辆的数量以及所述实时车载客流数据计算所述预设时段的所述待进站车辆的运能；以及
    根据所述预设时段的乘客滞留量和所述待进站车辆的运能计算所述待进站车辆的运能匹配系数，以对所述轨道交通车站的所述待进站车辆和滞留乘客进行协调调度。
  17. 如权利要求16所述的轨道交通智能调度系统，其特征在于，
    所述运能匹配系数大于0.8，对所述轨道交通车站进行黄色预警，并对滞留乘客进行疏导；
    所述运能匹配系数大于1，对所述轨道交通车站进行橙色预警，并对所述轨道交通车站进行限流；以及
    所述运能匹配系数大于1.2，对所述轨道交通车站进行红色预警，并增加 所述待进站车辆的数量以及调整所述待进站车辆的运行间隔。
PCT/CN2021/120054 2020-12-25 2021-09-24 一种轨道交通智能调度方法及系统 WO2022134692A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21908693.1A EP4071736A4 (en) 2020-12-25 2021-09-24 METHOD AND SYSTEM FOR INTELLIGENT PLANNING FOR RAIL TRANSPORT
US17/793,156 US20230062565A1 (en) 2020-12-25 2021-09-24 Intelligent dispatching method and system for rail transit

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011559885.0A CN112598182B (zh) 2020-12-25 2020-12-25 一种轨道交通智能调度方法及系统
CN202011559885.0 2020-12-25

Publications (1)

Publication Number Publication Date
WO2022134692A1 true WO2022134692A1 (zh) 2022-06-30

Family

ID=75202047

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/120054 WO2022134692A1 (zh) 2020-12-25 2021-09-24 一种轨道交通智能调度方法及系统

Country Status (4)

Country Link
US (1) US20230062565A1 (zh)
EP (1) EP4071736A4 (zh)
CN (1) CN112598182B (zh)
WO (1) WO2022134692A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081762A (zh) * 2022-08-24 2022-09-20 北京交通大学 基于城市轨道交通的乘客一体化智慧出行方法和系统
CN115565379A (zh) * 2022-12-06 2023-01-03 成都智元汇信息技术股份有限公司 一种替换历史客流数据中异常客流数据的方法及系统
CN115952173A (zh) * 2023-03-13 2023-04-11 北京全路通信信号研究设计院集团有限公司 一种客流数据处理方法、装置、大数据平台及存储介质
CN117494934A (zh) * 2023-10-12 2024-02-02 北京交通大学 轨道交通车站混合交织客流实时解析方法和系统

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112200487B (zh) * 2020-10-27 2024-05-28 中铁第五勘察设计院集团有限公司 一种城市轨道交通换乘车站的客流模拟方法
CN112598182B (zh) * 2020-12-25 2022-11-29 卡斯柯信号有限公司 一种轨道交通智能调度方法及系统
CN113371037A (zh) * 2021-04-30 2021-09-10 北京城建智控科技有限公司 基于gru神经网络的运行图编制方法及系统
CN113487763A (zh) * 2021-05-20 2021-10-08 胡彦霞 一种城市轨道交通安全智能检测系统
CN114240174A (zh) * 2021-12-16 2022-03-25 通控研究院(安徽)有限公司 基于动态客流的城轨线网行车调度辅助决策系统
CN115578697A (zh) * 2022-04-19 2023-01-06 广州地铁集团有限公司 一种基于视频分析的车站智能客流监控系统
CN115689154B (zh) * 2022-09-15 2023-07-25 合肥市轨道交通集团有限公司 基于动态客流的城市轨道交通调度辅助决策系统
CN116128160B (zh) * 2023-04-04 2023-07-28 北京经纬信息技术有限公司 一种铁路车站高峰客流预测方法、系统及设备和介质
CN116432956B (zh) * 2023-04-10 2024-01-23 广东宏志信息技术有限公司 一种基于客流量的公交车调配方法、系统、设备及介质
CN116142264B (zh) * 2023-04-23 2023-09-01 北京全路通信信号研究设计院集团有限公司 一种城市轨道交通运行计划编制方法及系统
CN116910588B (zh) * 2023-06-16 2024-04-05 上海工程技术大学 一种用于城市轨交列车乘降时间的估计方法
CN116523267B (zh) * 2023-06-28 2024-01-12 深圳市海成智联科技有限公司 适用于轨道交通的车辆调度优化方法、系统及存储介质
CN117592638A (zh) * 2023-10-20 2024-02-23 南京新中安物联技术股份有限公司 一种景区客流分析与管控的方法及系统
CN117314504B (zh) * 2023-11-28 2024-03-29 智达信科技术股份有限公司 一种公共交通客流预测方法及系统
CN117575264B (zh) * 2023-11-29 2024-05-07 北京市运输事业发展中心 一种基于视觉识别的车站运输调度方法
CN117407774B (zh) * 2023-12-15 2024-03-26 深圳市地铁集团有限公司 一种基于人工智能的交通数据处理方法及系统
CN117875518A (zh) * 2024-03-06 2024-04-12 北京阿帕科蓝科技有限公司 车辆调度方法、装置、计算机设备和存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650976A (zh) * 2015-10-29 2017-05-10 深圳市综合交通运行指挥中心 出行分析预测方法及系统、基于ic卡的出行分析预测方法及系统
CN110246332A (zh) * 2019-06-05 2019-09-17 北京交通大学 基于多源数据融合的轨道交通实时客流监察方法与系统
CN110348614A (zh) * 2019-06-24 2019-10-18 武汉烽火信息集成技术有限公司 一种获取乘客od的方法及公交客流的预测方法
CN110493816A (zh) * 2019-08-21 2019-11-22 上海工程技术大学 一种用于轨交地铁车站客流量的实时预测方法
US20200065695A1 (en) * 2018-08-24 2020-02-27 General Electric Company Multi-source modeling with legacy data
CN111144727A (zh) * 2019-12-18 2020-05-12 东南大学 一种城市轨道交通进站客流韧性评估系统及方法
CN111667092A (zh) * 2020-04-21 2020-09-15 北京交通大学 基于图卷积神经网络的轨道交通短时客流预测方法和系统
CN112598182A (zh) * 2020-12-25 2021-04-02 卡斯柯信号有限公司 一种轨道交通智能调度方法及系统

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5176082A (en) * 1991-04-18 1993-01-05 Chun Joong H Subway passenger loading control system
US7188057B2 (en) * 2002-08-02 2007-03-06 Kennebec, Inc. Systems and methods for designing, simulating and analyzing transportation systems
DE102005032848A1 (de) * 2005-07-14 2007-01-25 Robert Bosch Gmbh Verfahren und Vorrichtung zur Fahrerunterstützung
EP3040250A4 (en) * 2013-08-26 2017-06-21 Jian Liu Railway train with length exceeding that of platform and configuration system therefor
US20150206427A1 (en) * 2014-01-17 2015-07-23 International Business Machines Corporation Prediction of local and network-wide impact of non-recurrent events in transportation networks
US20150294430A1 (en) * 2014-04-15 2015-10-15 Tomorrow's Transportation Today Dynamic dispatching and schedule management methods for an intelligent transit system with electronic guided buses
CN104700159A (zh) * 2015-02-12 2015-06-10 广州市地下铁道总公司 一种轨道交通客流监测预警系统
US20160335576A1 (en) * 2015-05-12 2016-11-17 Uber Technologies, Inc. Location-based prediction of transport services
US20170178044A1 (en) * 2015-12-21 2017-06-22 Sap Se Data analysis using traceable identification data for forecasting transportation information
CN108216311B (zh) * 2017-07-12 2020-05-05 南京交通职业技术学院 一种基于大数据和物联网的轨道交通调度方法
CN108622142A (zh) * 2018-03-30 2018-10-09 卡斯柯信号有限公司 一种基于实时客流的列车智能运行调整系统及方法
CN109858670B (zh) * 2018-12-24 2022-11-18 哈尔滨工业大学 一种轨道交通车站大客流实时预警方法
CN110544010B (zh) * 2019-07-30 2023-04-07 同济大学 影响轨道交通系统全局效能涌现的关键要素的辨识方法
CN110619422A (zh) * 2019-11-04 2019-12-27 广东工业大学 一种智能车站客流状况预测方法和系统
CN111222744B (zh) * 2019-11-18 2023-10-24 西南交通大学 基于信令数据的建成环境与轨道客流分布关系确定方法
CN111016979A (zh) * 2019-11-29 2020-04-17 卡斯柯信号有限公司 基于实时客流的城市轨道交通列车自动调整方法
CN110901710B (zh) * 2019-12-02 2021-09-10 交控科技股份有限公司 基于动态客流的城市轨道交通行车调度方法及装置
CN110991775B (zh) * 2020-03-02 2020-06-26 北京全路通信信号研究设计院集团有限公司 一种基于深度学习的轨道交通客流需求预测方法和装置
CN111210094A (zh) * 2020-03-06 2020-05-29 青岛海信网络科技股份有限公司 一种基于实时客流预测的机场出租车自动调度方法及装置
CN111354212A (zh) * 2020-03-11 2020-06-30 青岛海信网络科技股份有限公司 应用于车站机场的出租车调度方法、服务器以及调度设备
CN111401643B (zh) * 2020-03-19 2022-10-04 卡斯柯信号有限公司 一种城市轨道交通客流回路自适应的智能列车调度方法
CN111552913B (zh) * 2020-04-24 2023-03-28 东南大学 一种新线接入条件下城市轨道交通运能匹配性评价方法
CN112308332A (zh) * 2020-11-10 2021-02-02 交控科技股份有限公司 轨道交通平行推演系统及方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650976A (zh) * 2015-10-29 2017-05-10 深圳市综合交通运行指挥中心 出行分析预测方法及系统、基于ic卡的出行分析预测方法及系统
US20200065695A1 (en) * 2018-08-24 2020-02-27 General Electric Company Multi-source modeling with legacy data
CN110246332A (zh) * 2019-06-05 2019-09-17 北京交通大学 基于多源数据融合的轨道交通实时客流监察方法与系统
CN110348614A (zh) * 2019-06-24 2019-10-18 武汉烽火信息集成技术有限公司 一种获取乘客od的方法及公交客流的预测方法
CN110493816A (zh) * 2019-08-21 2019-11-22 上海工程技术大学 一种用于轨交地铁车站客流量的实时预测方法
CN111144727A (zh) * 2019-12-18 2020-05-12 东南大学 一种城市轨道交通进站客流韧性评估系统及方法
CN111667092A (zh) * 2020-04-21 2020-09-15 北京交通大学 基于图卷积神经网络的轨道交通短时客流预测方法和系统
CN112598182A (zh) * 2020-12-25 2021-04-02 卡斯柯信号有限公司 一种轨道交通智能调度方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4071736A4 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081762A (zh) * 2022-08-24 2022-09-20 北京交通大学 基于城市轨道交通的乘客一体化智慧出行方法和系统
CN115081762B (zh) * 2022-08-24 2022-11-01 北京交通大学 基于城市轨道交通的乘客一体化智慧出行方法和系统
CN115565379A (zh) * 2022-12-06 2023-01-03 成都智元汇信息技术股份有限公司 一种替换历史客流数据中异常客流数据的方法及系统
CN115952173A (zh) * 2023-03-13 2023-04-11 北京全路通信信号研究设计院集团有限公司 一种客流数据处理方法、装置、大数据平台及存储介质
CN117494934A (zh) * 2023-10-12 2024-02-02 北京交通大学 轨道交通车站混合交织客流实时解析方法和系统

Also Published As

Publication number Publication date
CN112598182A (zh) 2021-04-02
EP4071736A1 (en) 2022-10-12
EP4071736A4 (en) 2024-02-21
US20230062565A1 (en) 2023-03-02
CN112598182B (zh) 2022-11-29

Similar Documents

Publication Publication Date Title
WO2022134692A1 (zh) 一种轨道交通智能调度方法及系统
EP4030365A1 (en) Multi-mode multi-service rail transit analog simulation method and system
CN108242149B (zh) 一种基于交通数据的大数据分析方法
WO2018107510A1 (zh) 公交系统服务质量的评估方法和装置
CN108364494B (zh) 道路交通智能管理方法、系统及平台
WO2018023331A1 (zh) 一种常规公交服务指数实时评价系统及评价方法
CN102819954B (zh) 交通区域动态地图监控预测系统
CN111027888B (zh) 一种基于轨道站点的接驳特征分析方法
CN101706993A (zh) 道路应急疏散能力指标体系的计算方法及系统
CN111653092A (zh) 一种车路协同智慧公交管理监控系统
CN107180403A (zh) 一种公共交通客流量统计管理方法及系统
CN114446076A (zh) 一种基于5g通信技术的智能调度控制系统
CN109409563B (zh) 一种公交运营车辆实时人数的分析方法、系统和存储介质
Andreev et al. Development of strategies for the development of urban passenger transport in EurAsEC countries
CN115578850A (zh) 一种基于交通信息化的城市交通智能控制方法及系统
CN110321982A (zh) 一种轨道交通断面客流量实时计算方法
CN116542404B (zh) 一种客运枢纽场站抵站旅客接续换乘时间的预测方法
Xiong et al. Parallel traffic management system helps 16th Asian games
Taimouri et al. Providing performance evaluation indicators for intelligent transportation systems (The Case Study of Tehran-Karaj Freeway Located in Iran)
Zhong et al. Research on the evaluation index system of the taxi operation and service in airport hubs
CN114648875A (zh) 一种基于城市轨道交通出行大数据的客流特征分析系统
CN109345857B (zh) 一种城市公交系统运行方法以及联网公交站台
CN113569376A (zh) 一种多源数据驱动的交通仿真评估系统
Salanova et al. Use of probe data generated by taxis
ZHANG et al. Intelligent Traffic Management and Control Technology

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021908693

Country of ref document: EP

Effective date: 20220708

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21908693

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE