Oversaturated Passenger Flow Pre-Control Method for Urban Rail Transit Stations

Abstract

The present invention relates to the technical field of rail transit management, and particularly relates to an over-saturated passenger flow pre-control method for urban rail transit stations. After the start time of the activity influence, according to the representative outbound of large-scale activities at each station on each subway line and the relative distance between each station and the activity station at each moment, the participation of large-scale activities on each subway line at each moment is obtained; combined with the number of available drivers, the increased transport capacity of each subway line at each moment is obtained; according to the change trend of the representative inbound or representative outbound of large-scale activities at the activity station at different moments, the start time and the end time of the large-scale activity are obtained, and the transport capacity of each subway line at different moments is controlled. The present invention provides reasonable subway transport capacity by accurately analyzing the influence of the passenger flow of large-scale activities on the subway transport capacity, and improves the effectiveness of passenger flow control.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit management, and particularly relates to a pre-control method for oversaturated passenger flow for urban rail transit stations. Background Art

[0002] The subway is the core of urban transportation due to its carrying capacity. When the passenger flow of the subway is oversaturated, the entry and exit of passengers will slow down, resulting in congestion and affecting traffic order. Therefore, effective pre-control measures are needed to reasonably dispatch the subway.

[0003] In the prior art, by analyzing historical passenger flow data and combining the passenger flow trend at the same time of the same year, the passenger flow change on the subway line is roughly predicted to reasonably dispatch subway resources. However, since some large-scale gathering activities are not reported to relevant departments, the change pattern of passenger flow usually does not completely match that in historical time. Relying solely on the analysis of historical passenger flow volume leads to the inability to effectively respond to actual passenger flow fluctuations, insufficient subway capacity, and poor passenger flow control effect. Summary of the Invention

[0004] In order to solve the technical problem that relying solely on the analysis of historical passenger flow volume leads to insufficient subway capacity and poor passenger flow control effect, the purpose of the present invention is to provide a pre-control method for oversaturated passenger flow for urban rail transit stations, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes a pre-control method for oversaturated passenger flow for urban rail transit stations, and the method includes:

[0006] Obtain the passenger entry and exit information of each station on the subway line at each moment of each day;

[0007] According to the passenger entry and exit information of each station within the time neighborhood range at the real-time moment, obtain the representative of large-scale activity outbound and the representative of large-scale activity inbound of each station at the real-time moment, and determine the start time of the activity impact and the activity stations;

[0008] After the start time of the activity impact, according to the representative of large-scale activity outbound of each station on each subway line at each moment and the relative distance between each station and the activity stations, obtain the participation of large-scale activities of each subway line at each moment; according to the participation of large-scale activities of each subway line at each moment and the number of available drivers, obtain the increased capacity of each subway line at each moment;

[0009] According to the change trend of the representative of large-scale activity inbound or the representative of large-scale activity outbound of the activity stations at different moments, obtain the start time and the end time of the large-scale activity;

[0010] According to the increased transport capacity of each subway line at each moment after the start time of the event impact, the start time of the large-scale event, and the end time of the large-scale event, the transport capacity of each subway line at different times is controlled.

[0011] Furthermore, the methods for obtaining the representativeness of the large-scale event for inbound passengers and the representativeness of the large-scale event for outbound passengers include:

[0012] Based on the passenger inbound and outbound information of each station within the time neighborhood range at the real-time moment, obtain the local representativeness of the large-scale event for each passenger corresponding to each station at the real-time moment;

[0013] Obtain the average value of the local representativeness of the large-scale event for all outbound passengers corresponding to each station at the real-time moment, and perform normalization, which is used as the representativeness of the large-scale event for outbound passengers of each station at the real-time moment;

[0014] Obtain the average value of the local representativeness of the large-scale event for all inbound passengers corresponding to each station at the real-time moment, and perform normalization, which is used as the representativeness of the large-scale event for inbound passengers of each station at the real-time moment.

[0015] Furthermore, the method for obtaining the local representativeness of the large-scale event includes:

[0016] Obtain the number of occurrences and the occurrence times of each passenger corresponding to each station within the time neighborhood range at the real-time moment; obtain the average value of the differences between the occurrence times and the real-time moment under different numbers of occurrences, which is used as the first representative coefficient;

[0017] Perform a negative correlation mapping on the number of occurrences corresponding to each passenger, and multiply the result of the negative correlation mapping by the first representative coefficient, which is used as the local representativeness of the large-scale event for each passenger corresponding to each station at the real-time moment.

[0018] Furthermore, the methods for obtaining the start time of the event impact and the event stations include:

[0019] If the representativeness of the large-scale event for outbound passengers of each station at the real-time moment is greater than the representativeness of the large-scale event for inbound passengers, and the representativeness of the large-scale event for outbound passengers is greater than the preset representativeness threshold, the corresponding moment is used as the start time of the event impact, and the corresponding station is used as a possible event station;

[0020] Select the station with the largest value of the representativeness of the large-scale event for outbound passengers among the possible event stations, and use the corresponding station as the event station.

[0021] Furthermore, the method for obtaining the participation of the large-scale event includes:

[0022] After the start time of the event impact, for each subway line, obtain the relative distance between each station and the event station, and perform a negative correlation mapping, which is used as the first participation;

[0023] Obtain the cumulative value of the product of the large-scale activity outbound representativeness and the first participation of all stations at each moment, and use it as the large-scale activity participation of each subway line at each moment.

[0024] Furthermore, the method for obtaining the increased transport capacity includes:

[0025] Normalize the large-scale activity participation of each subway line at each moment, and obtain the product of the normalization result and the number of available drivers as the increased transport capacity of each subway line at each moment.

[0026] Furthermore, the method for obtaining the start time and end time of the large-scale activity includes:

[0027] After the start time of the activity impact, according to the change trend of the large-scale activity inbound representativeness or large-scale activity outbound representativeness of the activity stations at different moments, obtain the large-scale activity start possibility and large-scale activity end possibility at each moment;

[0028] If the large-scale activity start possibility at a certain moment is greater than the preset start threshold, use the corresponding moment as the large-scale activity start time;

[0029] If the large-scale activity end possibility at a certain moment is greater than the preset end threshold, use the corresponding moment as the large-scale activity end time.

[0030] Furthermore, the method for obtaining the large-scale activity start possibility and large-scale activity end possibility includes:

[0031] After the start time of the activity impact, obtain the ratio of the large-scale activity outbound representativeness of each station between each moment and the previous adjacent moment as the first ratio; calculate the difference between the positive integer 1 and the first ratio as the large-scale activity start possibility of each station at each moment;

[0032] Obtain the ratio of the large-scale activity inbound representativeness of each station between each moment and the previous adjacent moment as the large-scale activity end possibility of each station at each moment.

[0033] Furthermore, the method for obtaining the time neighborhood range includes:

[0034] Taking the real-time moment as the benchmark, the range formed with the historical moment is used as the time neighborhood range of the real-time moment.

[0035] Furthermore, use the exponential function with the natural constant as the base for negative correlation mapping.

[0036] The present invention has the following beneficial effects:

[0037] Based on the passenger in-and-out station information of each station within the time neighborhood range at the real-time moment, the present invention obtains the large-scale event outbound representativeness and large-scale event inbound representativeness of each station at the real-time moment, determines the start moment of the event impact and the event stations, which helps to timely adjust the subway lines with insufficient transport capacity and avoid overcrowding of passengers; after the start moment of the event impact, according to the large-scale event outbound representativeness of each station on each subway line and the relative distance between each station and the event stations at each moment, the large-scale event participation of each subway line at each moment is obtained, avoiding relying solely on station data and comprehensively considering the passenger flow impact on the entire subway line; according to the large-scale event participation of each subway line and the number of available drivers at each moment, the increased transport capacity of each subway line at each moment is obtained, avoiding passengers being in an overcrowded state and resulting in crowded carriages; according to the change trend of the large-scale event inbound representativeness or large-scale event outbound representativeness of the event stations at different moments, the start moment and end moment of the large-scale event are obtained, and the transport capacity of each subway line at different moments is controlled. The present invention provides reasonable subway transport capacity by accurately analyzing the impact of the passenger flow of large-scale events on the subway transport capacity, and improves the effectiveness of passenger flow control. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a flowchart of a method for pre-controlling overcrowded passenger flow for an urban rail transit station provided by an embodiment of the present invention.

[0040] Figure 2 It is a flowchart of a method for obtaining the large-scale event inbound representativeness and large-scale event outbound representativeness provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manner, structure, features and effects of a method for pre-controlling overcrowded passenger flow for an urban rail transit station proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0043] The following specifically describes the specific solution of a method for pre-controlling over-saturated passenger flow for urban rail transit stations provided by the present invention in conjunction with the accompanying drawings.

[0044] Please refer to Figure 1 , which shows a flowchart of a method for pre-controlling over-saturated passenger flow for urban rail transit stations provided by an embodiment of the present invention. The specific method includes:

[0045] Step S1: Obtain the passenger in-and-out information of each station on the subway line at each moment of each day.

[0046] In an embodiment of the present invention, considering that large-scale activities are not reported to the relevant departments in advance, there will be differences in the passenger flow at the same time every day, and it is necessary to analyze the passenger flow of the station in real time for pre-control; first, the turnstiles at the subway entrance and exit pass through scanning QR codes, swiping cards or other electronic payment methods, and the electronic system is connected to the passenger's account information to achieve accurate billing and riding records, indicating the situation of passengers entering or leaving the station; obtain the passenger in-and-out information of each station on the subway line at each moment of each day.

[0047] It should be noted that the time interval is 1 minute, that is, every day, obtain the passenger in-and-out information of each station within each minute for analysis; in other embodiments of the present invention, the size of the time interval can be specifically set according to specific circumstances, and will not be limited and elaborated here.

[0048] Step S2: According to the passenger in-and-out information of each station within the time neighborhood range at the real-time moment, obtain the representative of large-scale activity outbound and the representative of large-scale activity inbound at each station at the real-time moment, and determine the start time of the activity impact and the activity stations.

[0049] For passengers participating in large-scale activities, their travel demand is temporarily increased due to the attraction of large-scale activities. Compared with regular commuting customers, they appear at the activity stations less frequently on weekdays, and their travel times are often different from usual. Therefore, analyze the appearance distribution of passengers at each station within the historical time range, and according to the passenger in-and-out information of each station within the time neighborhood range at the real-time moment, obtain the representative of large-scale activity outbound and the representative of large-scale activity inbound at each station at the real-time moment.

[0050] Preferably, in an embodiment of the present invention, for the method of obtaining the representative of large-scale activity inbound and the representative of large-scale activity outbound, please refer to Figure 2 , which shows a flowchart of a method for obtaining the representative of activity inbound and the representative of large-scale activity outbound, including:

[0051] Step S201: Obtain the local representativeness of large-scale events for each passenger corresponding to each station at the real-time moment according to the passenger in-and-out station information of each station within the time neighborhood range at the real-time moment.

[0052] Preferably, in an embodiment of the present invention, the method for obtaining the local representativeness of large-scale events includes:

[0053] Obtain the number of occurrences and the occurrence moments of each passenger corresponding to each station within the time neighborhood range at the real-time moment; obtain the average difference between the occurrence moments and the real-time moment under different numbers of occurrences as the first representative coefficient;

[0054] Perform a negative correlation mapping on the number of occurrences corresponding to each passenger, and multiply the result of the negative correlation mapping by the first representative coefficient as the local representativeness of large-scale events for each passenger corresponding to each station at the real-time moment.

[0055] In an embodiment of the present invention, the formula for the local representativeness of large-scale events is expressed as:

[0056] ;

[0057] where, represents the local representativeness of large-scale events for the th passenger corresponding to the th station at the th moment; represents the number of occurrences of the th passenger at the th station within the time neighborhood range; represents the occurrence moment of the th passenger at the rd time at the th station within the time neighborhood range.

[0058] In the formula for the local representativeness of large-scale events, represents calculating the average difference between the occurrence moments and the real-time moment under different numbers of occurrences, that is, the first representative coefficient. The larger the first representative coefficient, the greater the difference between the occurrence moment and the real-time moment, the less regular the time of appearing at the subway station, the more likely it is a large-scale event, and the smaller the number of occurrences, the greater the local representativeness of large-scale events.

[0059] It should be noted that, in an embodiment of the present invention, the time neighborhood range is a range formed by the real-time moment and the historical moments, where the historical moments are each moment of each day in the past year; in other embodiments of the present invention, the time neighborhood range can be specifically set according to specific situations, which will not be limited and elaborated here.

[0060] Step S202: Obtain the large - scale event local representative mean for all outbound passengers corresponding to each station within the real - time moment, and perform normalization, which is used as the large - scale event outbound representativeness of each station within the real - time moment.

[0061] In an embodiment of the present invention, for outbound passengers, the formula for the large - scale event inbound representativeness is expressed as:

[0062] ;

[0063] where, represents the large - scale event inbound representativeness of the th moment at the th station; represents the large - scale event local representativeness of the th moment at the th station corresponding to the th passenger; represents the number of outbound passengers at the th moment at the th station; represents the maximum - minimum normalization function.

[0064] In the formula for the large - scale event outbound representativeness, represents calculating the average of the large - scale event local representativeness for all outbound passengers corresponding to the th moment at the th station. The more outbound passengers there are at the subway station, the greater the large - scale event outbound representativeness, and the more likely it is the location of a large - scale event.

[0065] Step S203: Obtain the large - scale event local representative mean for all inbound passengers corresponding to each station within the real - time moment, and perform normalization, which is used as the large - scale event inbound representativeness of each station within the real - time moment.

[0066] It should be noted that, in an embodiment of the present invention, the large - scale event inbound representativeness is obtained by the same method as the large - scale event outbound representativeness, analyzing all inbound passengers; normalization is performed using the maximum - minimum normalization function. In other embodiments of the present invention, normalization can also be performed through existing normalization functions such as the arctangent function. The specific normalization function is a well - known technical means for those skilled in the art and will not be elaborated here.

[0067] The distribution trend of the passenger flow at each subway station is reflected through the large - scale event inbound and outbound representativeness. The greater the outbound representativeness, the more likely an event is held at the corresponding station; determine the start time of the event impact and the event station.

[0068] Preferably, in an embodiment of the present invention, the method for obtaining the start time of the event impact and the event station includes:

[0069] If the outbound representativeness of large-scale events at each station within the real-time moment is greater than the inbound representativeness of large-scale events, and the outbound representativeness of large-scale events is greater than the preset representativeness threshold, the corresponding moment is taken as the start moment of the event impact, and the corresponding station is taken as the possible event station;

[0070] Select the station with the largest outbound representativeness value of large-scale events among the possible event stations, and take the corresponding station as the event station.

[0071] It should be noted that, in an embodiment of the present invention, the preset representativeness threshold is 0.8; in other embodiments of the present invention, the size of the preset representativeness threshold can be specifically set according to specific situations, and no limitation and elaboration are made here.

[0072] Step S3: After the start moment of the event impact, according to the outbound representativeness of large-scale events at each station on each subway line and the relative distance between each station and the event station at each moment, obtain the large-scale event participation of each subway line at each moment; according to the large-scale event participation of each subway line and the available number of drivers at each moment, obtain the increased transport capacity of each subway line at each moment.

[0073] Before the large-scale event starts, the passengers participating in the event have strong concentration and purpose. The greater the outbound representativeness of the large-scale event, the more passengers participate in the large-scale event; the relative distance reflects the distance of each station from the event station. The farther the distance, the more dispersed the passenger distribution, and the smaller the contribution to the participation of the line, and the smaller the participation of the station in the large-scale event. After the start moment of the event impact, according to the outbound representativeness of large-scale events at each station on each subway line and the relative distance between each station and the event station at each moment, obtain the large-scale event participation of each subway line at each moment.

[0074] Preferably, in an embodiment of the present invention, the method for obtaining the large-scale event participation includes:

[0075] After the start moment of the event impact, for each subway line, obtain the relative distance between each station and the event station, and perform a negative correlation mapping as the first participation;

[0076] Obtain the cumulative value of the product between the outbound representativeness of large-scale events at all stations and the first participation at each moment as the large-scale event participation of each subway line at each moment.

[0077] In an embodiment of the present invention, the formula for the large-scale event participation is expressed as:

[0078] ;

[0079] Where, Indicates the participation in large-scale activities of the th subway line during the th moment; Indicates the activity site and the relative distance between the th site; Indicates the representativeness of large-scale activities leaving the station of the th site during the th moment; Indicates the exponential function with the natural constant as the base; Indicates the number of sites in the

[0080] th subway line. In the formula for the participation in large-scale activities, through the exponential function with a constant as the base,

[0081] a negative correlation mapping is performed. The greater the relative distance between sites, the farther apart the sites are, the smaller the contribution to the participation in the subway line, the smaller the representativeness of large-scale activities, and the smaller the participation in large-scale activities; the greater the representativeness of large-scale activities leaving the station of a site, the relatively more passengers leaving the station, and possibly affected by large-scale activities, the greater the participation in large-scale activities.

[0082] It should be noted that in some embodiments of the present invention, existing distance calculation methods such as Euclidean distance or approximate spherical distance can be used. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0083] Preferably, in an embodiment of the present invention, the method for obtaining the increased transport capacity includes:

[0084] Normalize the participation in large-scale activities of each subway line at each moment, and obtain the product of the normalization result and the number of available drivers as the increased transport capacity of each subway line at each moment.

[0085] In an embodiment of the present invention, the formula for the increased transport capacity is expressed as:

[0086] ;

[0087] Wherein, indicates the increased transport capacity of the th subway line at the th moment; indicates the During the participation of large-scale events on the th subway line; represents the number of subway lines; During the participation of large-scale events on the th subway line; represents the number of available drivers at the

[0088] In the formula for increasing transport capacity, represents the ratio between the participation of large-scale events on the th subway line during the th time period and the sum of the participation of large-scale events on all subway lines, that is, normalizing the participation of large-scale events on the th subway line during the th time period. The greater the participation of large-scale events on the th subway line during the th time period, the more transport capacity needs to be increased for this subway line.

[0089] Step S4: According to the change trend of the large-scale event inbound representativeness or large-scale event outbound representativeness of the event site at different times, obtain the large-scale event start time and the large-scale event end time.

[0090] After the event influence start time and before the large-scale event starts, passengers participating in the event usually gather at the event site where the large-scale event occurs. As the event starts, the closer to the start time, the smaller the large-scale event outbound representativeness; as the event ends, most of the passengers participating in the event will return and rarely stay at the place where the large-scale event occurs. The closer to the end time, the smaller the inbound representativeness. According to the change trend of the large-scale event inbound representativeness or large-scale event outbound representativeness of the event site at different times, obtain the large-scale event start time and the large-scale event end time.

[0091] Preferably, in an embodiment of the present invention, the method for obtaining the large-scale event start time and the large-scale event end time includes:

[0092] After the event influence start time, according to the change trend of the large-scale event inbound representativeness or large-scale event outbound representativeness of the event site at different times, obtain the large-scale event start possibility and the large-scale event end possibility at each time;

[0093] Preferably, in an embodiment of the present invention, the method for obtaining the large-scale event start possibility and the large-scale event end possibility includes:

[0094] After the start time of the event impact, obtain the ratio of the outbound representativeness of large-scale events at each site between each moment and the previous adjacent moment as the first ratio; calculate the difference between the positive integer 1 and the first ratio as the likelihood of the start of large-scale events at each site within each moment.

[0095] Obtain the ratio of the inbound representativeness of large-scale events at each site between each moment and the previous adjacent moment as the likelihood of the end of large-scale events at each site within each moment.

[0096] In one embodiment of the present invention, the formulas for the likelihood of the start of large-scale events and the likelihood of the end of large-scale events are expressed as:

[0097] ;

[0098] ;

[0099] Wherein, represents the likelihood of the start of large-scale events at each site within the th moment; represents the likelihood of the end of large-scale events at each site within the th moment; represents the outbound representativeness of large-scale events at the th moment and the th site; represents the outbound representativeness of large-scale events at the th moment and the th site; represents the inbound representativeness of large-scale events at the th moment and the th site; represents the inbound representativeness of large-scale events at the th moment and the th site.

[0100] In the formula for the likelihood of the start of large-scale events, represents the ratio of the outbound representativeness of large-scale events at the th moment and the th moment at the th site. The larger the ratio, the greater the outbound representativeness at the later moment is than at the previous moment, that is, the more passengers outbound at the later moment than at the previous moment. At this time, it is less close to the start time. On the contrary, the smaller the ratio, the smaller the outbound representativeness at the later moment is than at the previous moment, that is, the fewer passengers outbound at the later moment than at the previous moment, and the more likely it is to be close to the start time, and the greater the likelihood of the start of large-scale events; in the formula for the likelihood of the end of large-scale events, represents the th moment and the th moment at the The ratio representing the representativeness of large-scale event arrivals at the station. The larger the ratio, the greater the representativeness of arrivals at the next moment compared to the previous moment, that is, the more passengers arrive at the next moment than at the previous moment, indicating that the next moment is closer to the end time and the greater the likelihood of the large-scale event ending.

[0101] If the likelihood of the start of a large-scale event at a certain moment is greater than the preset start threshold, the corresponding moment is taken as the start time of the large-scale event; if the likelihood of the end of a large-scale event at a certain moment is greater than the preset end threshold, the corresponding moment is taken as the end time of the large-scale event.

[0102] It should be noted that the likelihood of the start of a large-scale event reflects the probability of the start of the large-scale event. The greater the likelihood, the greater the probability of the event starting; the likelihood of the end of a large-scale event reflects the probability of the end of the large-scale event. The greater the likelihood, the greater the probability of the event ending. In one embodiment of the present invention, the preset start threshold is 0.8 and the preset end threshold is 5; in other embodiments of the present invention, the preset start threshold and the preset end threshold can both be set according to specific circumstances and are not limited and elaborated herein.

[0103] Based on this, after obtaining the start and end times of the large-scale event, in order to avoid over-saturation of the passenger flow at the station, the transportation capacity of the subway line is adjusted and controlled to cope with the peak passenger situation.

[0104] Step S5: According to the increased transportation capacity of each subway line at each moment after the start time of the event impact, the start time of the large-scale event, and the end time of the large-scale event, the transportation capacity of each subway line at different moments is controlled.

[0105] During large-scale events, the subway passenger flow will show a spatio-temporal uneven distribution, and instantaneous peaks may occur at some lines or stations. Therefore, it is necessary to dynamically adjust the transportation capacity allocation of each line according to the event impact situation to improve the transportation efficiency and avoid passenger congestion.

[0106] It should be noted that in another embodiment of the present invention, based on the increased transportation capacity of each subway line at each moment after the start time of the event impact, the start time of the large-scale event, and the end time of the large-scale event, controlling the transportation capacity of each subway line at different moments includes: after the start time of the event impact, the transportation capacity of the subway line is increased according to the increased transportation capacity of each subway line at each moment obtained until after the start of the large-scale event, when the passenger flow returns to the normal level. Therefore, the transportation capacity of the line is not increased within the range from the start to the end of the large-scale event;

[0107] The time from the start to the end of a large-scale event is definite and relatively short-term. Therefore, the passenger flow shows similar patterns. The influx of passengers before the event and the return journey of passengers after the event are symmetric in time. Thus, the subway capacity is symmetric in time. The return passenger flow on the opposite lines at symmetric times is usually similar to that when coming, and the increased subway capacity required should also be similar. That is, after the end of the large-scale event, the reverse lines of the subway lines are increased, and the increased capacity per minute corresponds to the increased capacity of each subway line at each moment after the start of the event impact in turn.

[0108] In summary, the present invention obtains the representative of large-scale event outbound and the representative of large-scale event inbound for each station within the real-time moment based on the passenger in-out information of each station within the time neighborhood range at the real-time moment, determines the start moment of the event impact and the event stations; after the start moment of the event impact, obtains the participation of each subway line in the large-scale event at each moment according to the representative of large-scale event outbound of each station on each subway line and the relative distance between each station and the event stations at each moment; obtains the increased capacity of each subway line at each moment according to the participation of each subway line in the large-scale event and the number of available drivers at each moment; obtains the start moment and the end moment of the large-scale event according to the change trend of the representative of large-scale event inbound or the representative of large-scale event outbound of the event stations at different moments, and controls the capacity of each subway line at different moments. The present invention provides a reasonable subway capacity by obtaining an accurate time range of the large-scale event and improves the effectiveness of passenger flow control.

[0109] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. An over-saturated passenger flow pre-control method for urban rail transit stations, characterized in that The method includes: Obtaining the passenger in-and-out station information of each station on the subway line at each moment of each day; Based on the passenger in-and-out station information of each station within the time neighborhood range at the real-time moment, obtaining the large event outbound representativeness and large event inbound representativeness of each station at the real-time moment, and determining the start moment of the event influence and the event stations; After the start moment of the event influence, based on the large event outbound representativeness of each station on each subway line at each moment and the relative distance between each station and the event stations, obtaining the large event participation of each subway line at each moment; based on the large event participation of each subway line at each moment and the number of available drivers, obtaining the increased transportation capacity of each subway line at each moment; Based on the change trend of the large event inbound representativeness or large event outbound representativeness of the event stations at different moments, obtaining the start moment and end moment of the large event; Based on the increased transportation capacity of each subway line at each moment after the start moment of the event influence, the start moment of the large event, and the end moment of the large event, performing transportation capacity control on each subway line at different moments.

2. The oversaturated passenger flow pre-control method for urban rail transit stations according to claim 1, characterized in that The method for obtaining the large event inbound representativeness and the large event outbound representativeness includes: Based on the passenger in-and-out station information of each station within the time neighborhood range at the real-time moment, obtaining the large event local representativeness of each station corresponding to each passenger at the real-time moment; Obtaining the average value of the large event local representativeness of each station corresponding to all outbound passengers at the real-time moment, and normalizing it as the large event outbound representativeness of each station at the real-time moment; Obtaining the average value of the large event local representativeness of each station corresponding to all inbound passengers at the real-time moment, and normalizing it as the large event inbound representativeness of each station at the real-time moment.

3. The oversaturated passenger flow pre-control method for urban rail transit stations according to claim 2, wherein, The method for obtaining the large event local representativeness includes: Obtaining the number of occurrences and the occurrence moments of each station corresponding to each passenger within the time neighborhood range at the real-time moment; obtaining the average difference between the occurrence moments and the real-time moment under different numbers of occurrences as the first representative coefficient; Performing a negative correlation mapping on the number of occurrences corresponding to each passenger, and multiplying the negative correlation mapping result by the first representative coefficient as the large event local representativeness of each station corresponding to each passenger at the real-time moment.

4. A method for pre-control of oversaturated passenger flow for urban rail transit stations according to claim 1, characterized in that, The method for obtaining the start moment of the event influence and the event stations includes: If the large event outbound representativeness of each station at the real-time moment is greater than the large event inbound representativeness, and there is a large event outbound representativeness greater than the preset representativeness threshold, taking the corresponding moment as the start moment of the event influence and the corresponding station as the possible event station; Selecting the station with the largest large event outbound representativeness value among the possible event stations as the event station.

5. The oversaturated passenger flow pre-control method for urban rail transit stations according to claim 1, characterized in that The method for obtaining the large event participation includes: After the start moment of the event influence, for each subway line, obtaining the relative distance between each station and the event station, and performing a negative correlation mapping as the first participation; Obtain the cumulative value of the product of the large event outbound representativeness and the first participation of all stations at each moment, and use it as the large event participation of each subway line at each moment.

6. The oversaturated passenger flow pre-control method for urban rail transit stations according to claim 1, characterized in that The method for obtaining the increased transport capacity includes: Normalize the large event participation of each subway line at each moment, and obtain the product of the normalization result and the number of available drivers as the increased transport capacity of each subway line at each moment.

7. A pre-control method for over-saturated passenger flow in urban rail transit stations according to claim 1, characterized in that The method for obtaining the start time and end time of the large event includes: After the start time of the event impact, according to the change trend of the large event inbound representativeness or the large event outbound representativeness of the event stations at different moments, obtain the large event start possibility and the large event end possibility at each moment; If the large event start possibility at a certain moment is greater than the preset start threshold, use the corresponding moment as the large event start time; If the large event end possibility at a certain moment is greater than the preset end threshold, use the corresponding moment as the large event end time.

8. A pre-control method for oversaturated passenger flow facing urban rail transit stations according to claim 7, characterized in that, The method for obtaining the large event start possibility and the large event end possibility includes: After the start time of the event impact, obtain the ratio of the large event outbound representativeness of each station between each moment and the previous adjacent moment as the first ratio; calculate the difference between the positive integer 1 and the first ratio as the large event start possibility of each station at each moment; Obtain the ratio of the large event inbound representativeness of each station between each moment and the previous adjacent moment as the large event end possibility of each station at each moment.

9. The oversaturated passenger flow pre-control method for urban rail transit stations according to claim 1, characterized in that The method for obtaining the time neighborhood range includes: Taking the real-time moment as the benchmark, the range composed of the real-time moment and the historical moment is used as the time neighborhood range of the real-time moment.

10. A pre-control method for over-saturated passenger flow facing urban rail transit stations according to claim 5, characterized in that, Perform a negative correlation mapping using the exponential function with the natural constant as the base.

Images