Methods, systems, equipment, and media for identifying passenger flow between metro and railway in railway-led integrated passenger transport hubs.

Abstract

This invention discloses a method, system, equipment, and medium for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs. The method includes: acquiring subway card swipe data and railway timetable data from the integrated passenger transport hub for multiple consecutive days, and selecting a target date; removing subway card swipe data outside the operating hours of the subway station and data from passengers entering and exiting the same station within the target date, and then dividing the subway card swipe data into two datasets with the integrated passenger transport hub as the starting and ending points; dividing the railway timetable data into two datasets: arriving trains and departing trains; sequentially identifying and removing commuter passenger flow and passenger flow around the hub to obtain initial subway-to-railway passenger flow and initial railway-to-subway passenger flow; setting train time windows, performing probability determination, and obtaining the final transfer passenger flow identification result for the target date. This invention can identify subway-railway transfer passenger flow from daily subway card swipe data in railway-dominated integrated passenger transport hubs.

Description

Technical Field

[0001] This invention relates to the field of passenger flow organization technology for integrated passenger transport hubs, and in particular to a method, system, equipment and medium for identifying passenger flow between subway and railway in a railway-dominated integrated passenger transport hub. Background Technology

[0002] Against the backdrop of the major strategic development of a comprehensive, three-dimensional transportation network, integrated passenger transport hubs, as the "nerve center" connecting different modes of transportation, are becoming increasingly important. They are the core carriers for achieving "smooth travel for people" and improving the overall operational efficiency of the transportation network. Transfers frequently occur at integrated passenger transport hubs, and the efficiency of these transfers directly determines the effectiveness of the hub and even the entire transportation network. Efficient transfers mean that passengers can achieve seamless connections and rapid transfers, significantly reducing travel time costs, improving the travel experience, and thus enhancing passenger service satisfaction.

[0003] Analyzing passenger transfer behavior at integrated passenger transport hubs is fundamental to improving hub operational efficiency. Among these, transfer passenger flow identification refers to using relevant technologies to identify passengers transferring between different public transport systems (such as subway-bus, subway-railway, etc.) from the system's travel data, so that the public transport system can design and plan subsequent operation schemes.

[0004] Existing passenger transfer flow identification technologies mostly focus on urban public transportation systems, such as transfer behavior between urban rail transit and buses. However, there are few methods for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs, which are higher-level nodes in the transportation network.

[0005] Existing technologies include quantitatively analyzing the relationship between various transfer influencing factors and transfer intentions, using a multi-level stochastic intercept time modeling method to identify a passenger's transfer behavior during a trip; or setting transfer time thresholds and identifying passenger flow between the subway and railway rail transit systems in integrated passenger transport hubs based on electronic transportation card transaction data.

[0006] The drawback of existing technologies is their limited universality. Currently, many railway-dominated integrated passenger transport hubs have not yet achieved ticket interoperability between different rail transit systems, making it impossible to accurately identify transfer passenger flow by sharing relevant information fields from transportation card transaction data. Existing technologies are largely limited by this. Summary of the Invention

[0007] In order to overcome the defects in the existing technology, the present invention aims to provide a method, system, equipment and medium for identifying passenger flow between subway and railway in a railway-dominated integrated passenger transport hub, so as to solve the problem that passenger flow cannot be accurately identified due to the lack of interoperability of ticket data between the two rail transit systems in the hub.

[0008] Firstly, a method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs is provided, including the following steps:

[0009] Obtain subway card swiping data and railway timetable data for several consecutive days from the railway-dominated integrated passenger transport hub to be analyzed, and set the date of the last day of the consecutive days as the target date.

[0010] Metro card swiping data outside the operating hours of the metro stations attached to the integrated passenger transport hub within the target date, as well as metro card swiping data entering and exiting the same station, were removed. The removed metro card swiping data was then divided into two metro card swiping datasets: one starting from the integrated passenger transport hub and the other ending at the integrated passenger transport hub. The railway timetable data was divided into two datasets: arriving trains and departing trains.

[0011] Identify commuter flow by utilizing the periodic patterns of subway passengers entering and exiting stations and the times they do so;

[0012] Identify passenger flow around the hub by leveraging the appeal of other key locations within the hub's service area;

[0013] The initial railway-to-metro passenger flow is obtained by excluding commuter traffic and passenger flow around the metro hub from the metro card swipe data set starting from the integrated passenger transport hub; the initial metro-to-railway passenger flow is obtained by excluding commuter traffic and passenger flow around the metro hub from the metro card swipe data set ending at the integrated passenger transport hub.

[0014] Based on two datasets, arriving trains and departing trains, train time windows are set up. After probabilistic determination of the initial subway-to-rail passenger flow and the initial railway-to-subway passenger flow, the final transfer passenger flow identification result for the target date is obtained.

[0015] According to the first aspect, in some possible implementations, the subway card swiping data includes the time of entering and exiting the subway station, the line ID, the station ID, and the passenger ID; the railway timetable data includes the train number, the originating station, the destination station, the station sequence, the number of stops, the arrival time, and the departure time.

[0016] According to the first aspect, in some possible implementations, for trains that stop over, the departure time is considered in the departing train dataset, and the arrival time is considered in the arriving train dataset.

[0017] According to the first aspect, in some possible implementations, the commuter flow is identified by the following method:

[0018] Within the target date, in two subway card swipe datasets, one starting from a comprehensive passenger transport hub and the other ending at a comprehensive passenger transport hub, passenger IDs appearing in both datasets were marked as potential commuter traffic.

[0019] For a potential commuter, continue to search the metro card swipe dataset for the remaining days according to the corresponding passenger ID, and record the total number of days that the passenger appears in both the metro card swipe datasets with the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point for the remaining days.

[0020] Passengers who have commuted for a total of no less than a preset number of days in the remaining dates are identified as commuter passengers.

[0021] According to the first aspect, in some possible implementations, the passenger flow around the hub is identified by the following method:

[0022] Commuter passenger flow was removed from both the metro card swipe datasets for the target date, which started at the integrated passenger transport hub and ended at the integrated passenger transport hub.

[0023] The radius of the service area of ​​the subway station attached to the integrated passenger transport hub shall be determined according to the railway passenger station level of the integrated passenger transport hub;

[0024] Within the service area of ​​the subway station attached to the integrated passenger transport hub, identify other major passenger flow attractors, including stations of other non-rail transit modes and densely populated areas, and calculate their passenger flow attraction weights according to the following formula. :

[0025] ;

[0026] In the formula: This is the sequence number of the main passenger attraction areas around the comprehensive passenger transport hub. For stations using other non-rail transit modes, It is the product of the number of vehicles picked up or dispatched at the station on that day and the standard passenger capacity of the most commonly used vehicle type. For densely populated areas, This represents the number of people leaving or entering the area at each entrance / exit on that day; The total number of other major passenger attraction areas within the service area of ​​the subway station; Train model Standard passenger capacity; For the train models at the railway passenger stations in this integrated passenger transport hub on the target date. The number of trains received or dispatched per day; This refers to the total number of train types at the railway passenger stations within the integrated passenger transport hub on the target date.

[0027] Based on the obtained passenger flow attraction weights, in the two metro card swipe datasets for the target date, which exclude commuter passenger flow and take the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point, the passenger flow attraction of each major passenger flow attraction point within the service area of ​​the metro station attached to the integrated passenger transport hub is calculated. These passenger flows are the passenger flows around the hub.

[0028] According to the first aspect, in some possible implementations, the step of setting train time windows based on two datasets—arriving trains and departing trains—and obtaining the final transfer passenger flow identification result for the target date after probabilistically determining the initial subway-to-rail passenger flow and the initial rail-to-subway passenger flow includes:

[0029] Time windows are set for each train at the railway passenger station in the integrated passenger transport hub: originating trains only have a pre-departure time window, terminating trains only have a post-arrival time window, while stopping trains have both types of time windows; the time windows for each train are set according to the railway passenger station level and train type.

[0030] In the initial metro-to-rail passenger flow and the initial rail-to-metro passenger flow on the target date, what is the probability that each passenger is a transfer passenger? It is related to the position of its entry or exit time within the time window of the corresponding train and follows a truncated normal distribution;

[0031] For subway-to-railway passenger flow Calculate according to the following formula:

[0032] ;

[0033] in, For passenger exit time, This refers to the departure time of a train at a railway passenger station. This refers to the width of the time window before the train's departure.

[0034] For passenger flow transferring between railway and subway Calculate according to the following formula:

[0035] ;

[0036] in, For passenger entry time. This refers to the arrival time of a train at a railway passenger station. This refers to the width of the time window after the train's arrival; in the two formulas above, This represents the cumulative probability function of the standard normal distribution. For standard deviation, take ;

[0037] The probabilities of each passenger across multiple train time windows are summed.

[0038] A time window matching probability accumulation value range is set. Passengers whose time window matching probability accumulation value is lower than the lower limit of the range will be identified as non-transfer passengers. Passengers whose probability accumulation value is within the range will be identified as transfer passengers according to a preset ratio. Passengers whose probability accumulation value is higher than the upper limit will be identified as transfer passengers, thus obtaining the final identification results of subway-to-railway passenger flow and railway-to-subway passenger flow.

[0039] According to the first aspect, in some possible implementations, the upper and lower limits of the time window matching probability accumulation value interval are adjusted and determined by drawing a box plot of the probability accumulation value and observing the distribution of outliers in the plot. Outliers with a preset percentage or higher are below the lower limit value horizontal line, the remaining few outliers are distributed within the interval, and there are no outliers above the upper limit value horizontal line, wherein the preset percentage ranges from 90% to 98%.

[0040] Secondly, a railway-led integrated passenger transport hub metro-railway transfer passenger flow identification system is provided, including:

[0041] The data acquisition module is used to acquire subway card swiping data and railway timetable data of the railway-dominated integrated passenger transport hub for several consecutive days, and set the date of the last day of the consecutive days as the target date;

[0042] The dataset partitioning module is used to remove subway card swiping data outside the operating hours of subway stations attached to the integrated passenger transport hub within the target date, as well as subway card swiping data entering and exiting the same station. The subway card swiping data after removal is divided into two subway card swiping datasets with the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point; the railway timetable data is divided into two datasets: arriving trains and departing trains.

[0043] The commuter passenger flow identification module is used to identify commuter passenger flow by utilizing the periodic patterns of subway passengers entering and exiting stations and the times they enter and exit stations;

[0044] The hub perimeter passenger flow identification module is used to identify passenger flow around the hub by leveraging the attraction of other major locations within the hub's service area.

[0045] The initial transfer passenger flow identification module is used to exclude commuter passenger flow and passenger flow around the hub from the metro card swipe dataset starting from the integrated passenger transport hub to obtain the initial railway transfer metro passenger flow; and to exclude commuter passenger flow and passenger flow around the hub from the metro card swipe dataset ending at the integrated passenger transport hub to obtain the initial metro transfer railway passenger flow.

[0046] The final transfer passenger flow identification module is used to set train time windows based on two datasets: arriving trains and departing trains. After performing probability determination on the initial subway-to-rail passenger flow and the initial railway-to-subway passenger flow, it obtains the final transfer passenger flow identification result for the target date.

[0047] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the aforementioned method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs.

[0048] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the aforementioned method for identifying passenger flow between subway and railway in a railway-dominated integrated passenger transport hub.

[0049] The present invention has the following beneficial effects: The technical solution of the present invention can identify metro-railway transfer passenger flows in daily metro card swipe data of railway-dominated integrated passenger transport hubs. Compared with existing technical solutions, the method of the present invention improves the accuracy of transfer passenger flow identification by excluding commuter passenger flow, hub-peripheral passenger flow, and other non-transfer passenger flows; the data required by the method is relatively easy to obtain, and the data of the two rail transit systems do not need to be shared, reducing the difficulty of implementation and improving universality.

[0050] Therefore, this invention is characterized by its ease of implementation and high versatility. Combined with data mining and applied statistical techniques, it can bring application value to the work of statistically analyzing passenger flow, analyzing passenger flow characteristics, and optimizing operation plans in integrated passenger transport hubs. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating the implementation of the railway-dominated integrated passenger transport hub metro-railway transfer passenger flow identification method provided in this embodiment of the invention.

[0053] Figure 2 This is a schematic diagram of passenger flow composition of a subway station attached to an integrated passenger transport hub, provided in an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0055] To address the problem of inaccurate passenger flow identification due to the lack of interoperability between ticket data from the two rail transit systems in a transportation hub, this invention proposes a method, system, equipment, and medium for identifying subway-railway transfer passenger flow in a railway-dominated integrated passenger transport hub. This solution is highly universal, easy to operate, requires a moderate amount of data, and can exclude non-transfer passenger flow from multiple perspectives. It provides a new approach for accurately identifying subway-railway transfer passenger flow in integrated passenger transport hubs and extracting transfer passenger flow characteristics. The technical solution of this invention will be described in detail below with reference to specific embodiments.

[0056] like Figure 1 As shown in the figure, this invention discloses a method for identifying passenger flow between subway and railway in a railway-dominated integrated passenger transport hub, including the following steps:

[0057] S1: Obtain subway card swiping data and railway timetable data for multiple consecutive days from the railway-dominated integrated passenger transport hub to be analyzed, and set the date of the last day of the multiple consecutive days as the target date.

[0058] In practice, for multiple consecutive days, a period of 7 days or more is generally chosen. In the following embodiment, a period of 30 consecutive days is used as an example. This embodiment obtains subway card swipe data and railway timetable data for September 2023 to identify the subway-railway transfer passenger flow in the subway card swipe data on September 30 (i.e., the target date).

[0059] The acquired subway card swipe data includes fields such as the time of entering and exiting the subway station, line ID, station ID, and passenger ID. The passenger ID is a characteristic field of each subway card swipe data, corresponding to a unique passenger. The station ID represents the station number of the subway station on the subway lines it passes through. Therefore, passenger transport hubs that are served by multiple subway lines will have multiple (line, station) ID combinations. In this embodiment, it is assumed that the (line, station) ID combination of the integrated passenger transport hub is (2,18) and (4,23), indicating that the integrated passenger transport hub is both station number 18 on line 2 and station number 23 on line 4.

[0060] The obtained railway timetable data includes fields such as train number, originating station, destination station, station sequence, number of stops, arrival time, and departure time.

[0061] S2: Preprocess the acquired data: Remove subway card swiping data outside the operating hours of the subway stations attached to the comprehensive passenger transport hub within the target date and subway card swiping data entering and exiting the same station; subway card swiping data entering and exiting the same station refers to the ID combination of the entering line and station and the ID combination of the exit line and station being one of (2,18) or (4,23).

[0062] Based on the (line, station) ID combination, the processed subway card swiping data is divided into two subway card swiping datasets: one starting from a comprehensive passenger transport hub and the other ending at a comprehensive passenger transport hub.

[0063] The railway timetable data is divided into two datasets: arriving trains (including trains that stop and trains that terminate) and departing trains (including trains that stop and trains that originate). For trains that stop, the departure time is considered in the departing train dataset, and the arrival time is considered in the arriving train dataset. The station number of a terminating train is equal to the number of stops, the station number of an originating train is 1, and the rest are trains that stop.

[0064] like Figure 2 As shown, subway passenger flow can be divided into three categories according to passenger flow attributes: transfer passenger flow, commuter passenger flow, and hub-periphery passenger flow. Transfer passenger flow is further divided into two categories according to passenger flow direction: the first category is subway-to-rail passenger flow, i.e., passengers exiting the subway station and taking a train; the second category is railway-to-subway passenger flow, i.e., passengers exiting the railway station and taking a subway train. The subway card swipe dataset originating from a hub corresponds to railway-to-subway passenger flow, and the subway card swipe dataset ending at a hub corresponds to subway-to-railway passenger flow. To identify transfer passenger flow, it is necessary to identify and exclude commuter passenger flow and hub-periphery passenger flow.

[0065] S3: Identify commuter passenger flow by utilizing the periodic patterns of subway passengers entering and exiting stations and the times they enter and exit.

[0066] Specifically, the commuter flow is identified through the following method:

[0067] S31: On September 30, 2023, two sets of subway card swipe data, one starting from a comprehensive passenger transport hub and the other ending at a comprehensive passenger transport hub, were searched according to passenger ID. The passenger IDs that appeared in both sets were marked as potential commuter traffic.

[0068] S32: For a potential commuter, continue to search the metro card swipe dataset for the remaining days of September 2023 according to the corresponding passenger ID, and record the total number of days that the passenger appears in both the metro card swipe datasets with the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point (i.e., commuting behavior occurs).

[0069] S33: Passengers whose total number of commuting days in the remaining dates is not less than a preset number of days are identified as commuter passengers. The preset number of days is adjusted according to the actual situation. In this embodiment, data for 30 consecutive days is obtained, so the preset number of days can be set to 15 days or 16 days, etc.; while in other embodiments, data for 7 consecutive days is obtained, the preset number of days can be set to 2 days or 3 days, etc.

[0070] S4: Identify passenger flow around the hub by leveraging the attraction of other major locations within the hub's service area.

[0071] Specifically, passenger flow around the hub is identified using the following method:

[0072] S41: Commuter passenger flow will be centrally removed from two subway card swipe datasets as of September 30, 2023, one starting from the integrated passenger transport hub and the other ending at the integrated passenger transport hub.

[0073] S42: The service radius of the subway station attached to a comprehensive passenger transport hub is determined based on the railway passenger station's classification. In this embodiment, when the railway passenger station is a special-class station (daily average number of passengers boarding and alighting and transferring exceeds 60,000, and the number of transferred baggage exceeds 20,000), the service radius of its attached subway station is set to 1,000 meters; when the railway passenger station is a first-class station (daily average number of passengers boarding and alighting and transferring exceeds 15,000, and the number of transferred baggage exceeds 1,500), the service radius of its attached subway station is set to 800 meters; for other grades of railway passenger stations, the service radius of their attached subway stations is set to 500 meters. It should be noted that the above service radius setting is only an example, and other values ​​can be set according to actual conditions in other embodiments.

[0074] S43: Within the service area of ​​the subway station attached to the integrated passenger transport hub, identify other major passenger flow attractors, including stations of other non-rail transit modes and densely populated areas (such as residential areas, shopping malls, etc.), and calculate their passenger flow attraction weights in both directions using the following formula. :

[0075] ;

[0076] In the formula: This is the sequence number of the main passenger attraction areas around the comprehensive passenger transport hub. For stations using other non-rail transit modes, It is the product of the number of vehicles picked up or dispatched at the station on that day and the standard passenger capacity of the most commonly used vehicle type. For densely populated areas, This represents the number of people leaving or entering the area at each entrance / exit on that day; The total number of other major passenger attraction areas within the service area of ​​the subway station; Train model Standard passenger capacity; For the train models at the railway passenger stations in this integrated passenger transport hub on the target date. The number of trains received or dispatched per day; This refers to the total number of train types at the railway passenger stations within the integrated passenger transport hub on the target date.

[0077] When calculating the passenger flow attraction weight of a certain passenger flow attraction location in the direction of railway-to-subway passenger flow, for stations using other non-rail transit modes, This is the product of the number of vehicles picked up at the station on that day and the standard passenger capacity of the most commonly used vehicle type. For densely populated areas... This represents the number of people who left the area at each entrance / exit on that day. For the train models at the railway passenger stations in this integrated passenger transport hub on the target date. The number of trains received daily;

[0078] When calculating the passenger flow attraction weight of a certain passenger flow attraction location in the direction of subway-to-rail passenger flow transfer, for stations using other non-rail transit modes, It is the product of the number of vehicles departing from the station on that day and the standard passenger capacity of the most commonly used vehicle type. For densely populated areas, This represents the number of people entering the area through each entrance / exit on that day. For the train models at the railway passenger stations in this integrated passenger transport hub on the target date. The number of trains departing daily;

[0079] This embodiment assumes that a long-distance bus station is found within the service area of ​​the subway station attached to the integrated passenger transport hub. ) and a shopping mall ( The integrated passenger transport hub only handles 8-car CR400BF EMU trains (standard passenger capacity 576 people), with 400 trains arriving and departing on September 30th; the long-distance bus station handled 100 buses with a standard passenger capacity of 45 people each on the same day; the number of people leaving and entering the shopping mall at each entrance and exit was 2500 on the same day; therefore, the passenger attraction weights of each passenger attraction point corresponding to the two passenger flow directions are equal, both being:

[0080] ;

[0081] ;

[0082] It can be determined that the passenger flow attraction weight of each passenger flow direction of this integrated passenger transport hub is [not specified]. ;

[0083] S44: Based on the passenger flow attraction weights of the two passenger flow directions, in the two metro card swipe datasets on September 30, 2023, after excluding commuter passenger flow, calculate the passenger flow attraction of each major passenger flow attraction point within the service area of ​​the metro station attached to the integrated passenger transport hub. These passenger flows are the passenger flows around the hub.

[0084] S5: Exclude commuter traffic and traffic around the hub from the metro card swipe data set starting from the integrated passenger transport hub on September 30, 2023 to obtain the initial railway-to-metro passenger flow; exclude commuter traffic and traffic around the hub from the metro card swipe data set ending from the integrated passenger transport hub on September 30, 2023 to obtain the initial metro-to-railway passenger flow.

[0085] S6: Based on the arrival and departure train datasets, train time windows are set up. After probabilistic determination of the initial subway-to-rail passenger flow and the initial rail-to-subway passenger flow, the final transfer passenger flow identification result for the target date is obtained. Specifically, the following steps are included:

[0086] S61: Time windows are set for each train at railway passenger stations in integrated passenger transport hubs: originating trains only have a pre-departure time window, terminating trains only have a post-arrival time window, while stopping trains have both types of time windows; the time windows for each train are set according to the railway passenger station level and train type: for special-class and first-class railway passenger stations, the pre-departure time window width for originating trains is set to 90 minutes, the post-arrival time window width for terminating trains is set to 30 minutes, the pre-departure time window width for stopping trains is set to 60 minutes, and the post-arrival time window width for stopping trains is set to 20 minutes; for second-class to fifth-class railway passenger stations, the time window widths for the above types of trains are 60 minutes, 15 minutes, 45 minutes, and 10 minutes respectively; it should be noted that the above setting of time window width is only an example, and other values ​​can be set according to actual conditions in other embodiments;

[0087] S62: In the initial metro-to-rail passenger flow and the initial rail-to-metro passenger flow on September 30, 2023, what is the probability that each passenger is a transfer passenger? The passenger flow is related to the position of their entry or exit time within the corresponding train's time window and follows a truncated normal distribution. That is, passengers outside the train's time window are definitely not transfer passengers for that train. For subway-to-rail passenger flow, Calculate according to the following formula:

[0088] ;

[0089] in, For passenger exit time, This refers to the departure time of a train at a railway passenger station. This refers to the time window width before the train's departure; for passenger flow transferring between railway and subway, Calculate according to the following formula:

[0090] ;

[0091] in, For passenger entry time. This refers to the arrival time of a train at a railway passenger station. This refers to the width of the time window after the train's arrival; in the two formulas above, This represents the cumulative probability function of the standard normal distribution. For standard deviation, take ;

[0092] This embodiment assumes that the railway passenger station is a special-class station, and a train departs at 9:00 on September 30. Passenger 1 exits the subway station at 8:15 and passenger 2 exits the subway station at 8:00.

[0093] For ease of calculation, the unit is minutes. ,but (That is, the time when passenger 1 exits the subway station is in the middle of the time window). , , Substituting into the previous equation, we get:

[0094] ;

[0095] ;

[0096] Since this invention uses a truncated probability distribution, the "probability" here is relative. However, the probability density value at the center of the time window is still the largest, which means that the transfer passengers of the originating train are most likely to exit the subway station at the time point corresponding to the center of the time window before its departure.

[0097] Compare This means that passenger 2 is still highly likely to be a transfer passenger from that originating train.

[0098] S63: A passenger's exit (entry) time at the subway station may fall within multiple time windows before departure (after arrival), so the probabilities of each passenger under multiple train time windows are summed.

[0099] S64: Set a time window matching probability accumulation value range. Passengers whose time window matching probability accumulation value is lower than the lower limit of the range will be judged as non-transfer passengers. Passengers whose probability accumulation value is within the range will be judged as transfer passengers according to a preset ratio (such as 50%). Passengers whose probability accumulation value is higher than the upper limit will be judged as transfer passengers, thereby obtaining the final transfer passenger flow identification result. The transfer passenger flow identification result includes two parts: the metro-to-rail passenger flow and the railway-to-metro passenger flow of the integrated passenger transport hub on September 30, 2023.

[0100] The upper and lower limits of the time window matching probability accumulation value interval are adjusted and determined by drawing a box plot of the probability accumulation value and observing the distribution of outliers in the plot. Outliers with a preset percentage or higher are below the lower limit value horizontal line, the remaining few outliers are distributed within the interval, and there are no outliers above the upper limit value horizontal line. The preset percentage ranges from 90% to 98%, and 95% is used in this embodiment.

[0101] The above embodiments disclose a method for identifying metro-railway transfer passenger flow in railway-dominated integrated passenger transport hubs. This method can identify metro-railway transfer passenger flow from daily metro card swipe data in railway-dominated integrated passenger transport hubs. Compared with existing technical solutions, this method improves the accuracy of transfer passenger flow identification by excluding commuter passenger flow, passenger flow around the hub, and other non-transfer passenger flow. The data required by the method is relatively easy to obtain, and the data of the two rail transit systems does not need to be shared, which reduces the difficulty of implementation and improves universality. Therefore, this method is simple to implement and highly universal. Combined with data mining and applied statistical techniques, it can bring application value to the work of statistically analyzing transfer passenger flow, analyzing passenger flow characteristics, and optimizing operation plans in integrated passenger transport hubs.

[0102] This invention also discloses a railway-dominated integrated passenger transport hub metro-railway transfer passenger flow identification system, comprising:

[0103] The data acquisition module is used to acquire subway card swiping data and railway timetable data of the railway-dominated integrated passenger transport hub for several consecutive days, and set the date of the last day of the consecutive days as the target date;

[0104] The dataset partitioning module is used to remove subway card swiping data outside the operating hours of subway stations attached to the integrated passenger transport hub within the target date, as well as subway card swiping data entering and exiting the same station. The subway card swiping data after removal is divided into two subway card swiping datasets with the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point; the railway timetable data is divided into two datasets: arriving trains and departing trains.

[0105] The commuter passenger flow identification module is used to identify commuter passenger flow by utilizing the periodic patterns of subway passengers entering and exiting stations and the times they enter and exit stations;

[0106] The hub perimeter passenger flow identification module is used to identify passenger flow around the hub by leveraging the attraction of other major locations within the hub's service area.

[0107] The initial transfer passenger flow identification module is used to exclude commuter passenger flow and passenger flow around the hub from the metro card swipe dataset starting from the integrated passenger transport hub to obtain the initial railway transfer metro passenger flow; and to exclude commuter passenger flow and passenger flow around the hub from the metro card swipe dataset ending at the integrated passenger transport hub to obtain the initial metro transfer railway passenger flow.

[0108] The final transfer passenger flow identification module is used to set train time windows based on two datasets: arriving trains and departing trains. After performing probability determination on the initial subway-to-rail passenger flow and the initial railway-to-subway passenger flow, it obtains the final transfer passenger flow identification result for the target date.

[0109] It should be understood that the functional unit modules in the various embodiments of the present invention can be concentrated in one processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated into one unit module, and can be implemented in hardware or software.

[0110] Furthermore, embodiments of the present invention also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs.

[0111] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the aforementioned method for identifying passenger flow between subway and railway in railway-dominated integrated passenger transport hubs.

[0112] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0113] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0115] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0117] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for identifying passenger flow between subway and railway in a railway-dominated integrated passenger transport hub, characterized in that, Includes the following steps: Obtain subway card swiping data and railway timetable data for several consecutive days from the railway-dominated integrated passenger transport hub to be analyzed, and set the date of the last day of the consecutive days as the target date. Metro card swiping data outside the operating hours of the metro stations attached to the integrated passenger transport hub within the target date, as well as metro card swiping data entering and exiting the same station, were removed. The removed metro card swiping data was then divided into two metro card swiping datasets: one starting from the integrated passenger transport hub and the other ending at the integrated passenger transport hub. The railway timetable data was divided into two datasets: arriving trains and departing trains. Commuter passenger flow is identified by utilizing the periodic patterns of subway passengers entering and exiting stations and the times they do so; the commuter passenger flow is identified through the following methods: Within the target date, in two subway card swipe datasets, one starting from a comprehensive passenger transport hub and the other ending at a comprehensive passenger transport hub, passenger IDs appearing in both datasets were marked as potential commuter traffic. For a potential commuter, continue to search the metro card swipe dataset for the remaining days according to the corresponding passenger ID, and record the total number of days that the passenger appears in both the metro card swipe datasets with the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point for the remaining days. Passengers who have commuting activity for a total number of days in the remaining dates that is not less than a preset number of days are identified as commuter passengers. By leveraging the attractiveness of other major locations within the hub's service area to passenger flow, passenger flow around the hub is identified; this passenger flow is identified through the following methods: Commuter passenger flow was removed from both the metro card swipe datasets for the target date, which started at the integrated passenger transport hub and ended at the integrated passenger transport hub. The radius of the service area of ​​the subway station attached to the integrated passenger transport hub shall be determined according to the railway passenger station level of the integrated passenger transport hub; Within the service area of ​​the subway station attached to the integrated passenger transport hub, identify other major passenger flow attractors, including stations of other non-rail transit modes and densely populated areas, and calculate their passenger flow attraction weights according to the following formula. : ； In the formula: This is the sequence number of the main passenger attraction areas around the comprehensive passenger transport hub. For stations using other non-rail transit modes, It is the product of the number of vehicles picked up or dispatched at the station on that day and the standard passenger capacity of the most commonly used vehicle type. For densely populated areas, This represents the number of people leaving or entering the area at each entrance / exit on that day; The total number of other major passenger attraction areas within the service area of ​​the subway station; Train model Standard passenger capacity; For the train models at the railway passenger stations in this integrated passenger transport hub on the target date. The number of trains received or dispatched per day; This refers to the total number of train types at the railway passenger stations within the integrated passenger transport hub on the target date. Based on the obtained passenger flow attraction weights, in the two metro card swipe datasets for the target date, which exclude commuter passenger flow and start and end points of the integrated passenger transport hub, the passenger flow attraction of each major passenger flow attraction point within the service area of ​​the metro station attached to the integrated passenger transport hub is calculated. These passenger flows are the passenger flows around the hub. The initial railway-to-metro passenger flow is obtained by excluding commuter traffic and passenger flow around the metro hub from the metro card swipe data set starting from the integrated passenger transport hub; the initial metro-to-railway passenger flow is obtained by excluding commuter traffic and passenger flow around the metro hub from the metro card swipe data set ending at the integrated passenger transport hub. Based on two datasets, arriving and departing trains, a train time window is set up. After probabilistic determination of the initial subway-to-rail passenger flow and the initial rail-to-subway passenger flow, the final transfer passenger flow identification result for the target date is obtained. The process of setting up a train time window based on two datasets, arriving and departing trains, and then probabilistically determining the initial subway-to-rail passenger flow and the initial rail-to-subway passenger flow to obtain the final transfer passenger flow identification result for the target date includes: Time windows are set for each train at the railway passenger station in the integrated passenger transport hub: originating trains only have a pre-departure time window, terminating trains only have a post-arrival time window, while stopping trains have both types of time windows; the time windows for each train are set according to the railway passenger station level and train type. In the initial metro-to-rail passenger flow and the initial rail-to-metro passenger flow on the target date, what is the probability that each passenger is a transfer passenger? It is related to the position of its entry or exit time within the time window of the corresponding train and follows a truncated normal distribution; For subway-to-railway passenger flow Calculate according to the following formula: ； in, For passenger exit time, This refers to the departure time of a train at a railway passenger station. This refers to the width of the time window before the train's departure. For passenger flow transferring between railway and subway Calculate according to the following formula: ； in, For passenger entry time. This refers to the arrival time of a train at a railway passenger station. This refers to the width of the time window after the train's arrival; in the two formulas above, This represents the cumulative probability function of the standard normal distribution. For standard deviation, take ; The probabilities of each passenger across multiple train time windows are summed. A time window matching probability accumulation value range is set. Passengers whose time window matching probability accumulation value is lower than the lower limit of the range will be identified as non-transfer passengers. Passengers whose probability accumulation value is within the range will be identified as transfer passengers according to a preset ratio. Passengers whose probability accumulation value is higher than the upper limit will be identified as transfer passengers, thus obtaining the final identification results of subway-to-railway passenger flow and railway-to-subway passenger flow.

2. The method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs according to claim 1, characterized in that, The subway card swipe data includes the time of entering and exiting the subway station, line ID, station ID, and passenger ID; the railway timetable data includes train number, originating station, destination station, station sequence, number of stops, arrival time, and departure time.

3. The method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs according to claim 1, characterized in that, For trains that stop at other stations, we focus on their departure time in the departing train dataset and their arrival time in the arriving train dataset.

4. The method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs according to claim 1, characterized in that, The upper and lower limits of the time window matching probability accumulation value interval are adjusted and determined by drawing a box plot of the probability accumulation value and observing the distribution of outliers in the plot. Outliers above a preset percentage are below the lower limit value horizontal line, and no outliers are above the upper limit value horizontal line. The preset percentage ranges from 90% to 98%.

5. A railway-dominated integrated passenger transport hub subway-railway transfer passenger flow identification system, characterized in that, The system for implementing the metro-railway transfer passenger flow identification method for railway-dominated integrated passenger transport hubs as described in any one of claims 1 to 4 includes: The data acquisition module is used to acquire subway card swiping data and railway timetable data of the railway-dominated integrated passenger transport hub for several consecutive days, and set the date of the last day of the consecutive days as the target date; The dataset partitioning module is used to remove subway card swiping data outside the operating hours of subway stations attached to the integrated passenger transport hub within the target date, as well as subway card swiping data entering and exiting the same station. The subway card swiping data after removal is divided into two subway card swiping datasets with the integrated passenger transport hub as the starting point and the integrated passenger transport hub as the ending point; the railway timetable data is divided into two datasets: arriving trains and departing trains. The commuter passenger flow identification module is used to identify commuter passenger flow by utilizing the periodic patterns of subway passengers entering and exiting stations and the times they enter and exit stations; The hub perimeter passenger flow identification module is used to identify passenger flow around the hub by leveraging the attraction of other major locations within the hub's service area. The initial transfer passenger flow identification module is used to exclude commuter passenger flow and passenger flow around the hub from the metro card swipe dataset starting from the integrated passenger transport hub to obtain the initial railway transfer metro passenger flow; and to exclude commuter passenger flow and passenger flow around the hub from the metro card swipe dataset ending at the integrated passenger transport hub to obtain the initial metro transfer railway passenger flow. The final transfer passenger flow identification module is used to set train time windows based on two datasets: arriving trains and departing trains. After performing probability determination on the initial subway-to-rail passenger flow and the initial railway-to-subway passenger flow, it obtains the final transfer passenger flow identification result for the target date.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for identifying subway-railway transfer passenger flow in railway-dominated integrated passenger transport hubs as described in any one of claims 1 to 4.

Images