Urban rail transit station-oriented supersaturated passenger flow pre-control method

Abstract

The invention relates to the technical field of rail transit management, in particular to a supersaturated passenger flow pre-control method for an urban rail transit station. The method comprises the following steps: after an activity influence starting moment, according to the large-scale activity outbound representativeness of each station on each subway line at each moment and the relative distance between each station and an activity station, obtaining the large-scale activity participation of each subway line at each moment; in combination with the number of available drivers, the increased transport capacity of each subway line at each moment is obtained; and according to the change trend of the large-scale activity arrival representativeness or the large-scale activity departure representativeness of the activity stations at different moments, obtaining a large-scale activity starting moment and a large-scale activity ending moment, and carrying out transport capacity control on each subway line at different moments. By accurately analyzing the influence of the passenger flow condition of the large-scale activity on the subway transport capacity, reasonable subway transport capacity is provided, and the effectiveness of passenger flow control is improved.

Description

Technical Field

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

[0002] The subway is called the core of urban transportation due to its carrying capacity. When the subway passenger flow is oversaturated, the number of passengers entering and exiting the station will slow down, resulting in detention and congestion, affecting traffic order. Therefore, effective preventive control measures are needed to reasonably dispatch the subway.

[0003] In the prior art, historical passenger flow data is analyzed and combined with the passenger flow trends in the same year to roughly predict passenger flow changes on subway lines and reasonably dispatch subway resources. However, due to the existence of some large-scale gathering activities that are not reported to relevant departments, the passenger flow change pattern is usually not completely consistent with the historical time. Relying solely on the analysis of historical passenger flow, it is impossible 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 only relying on the analysis of historical passenger flow leads to insufficient subway capacity and poor passenger flow control effect, the purpose of the present invention is to provide a method for pre-controlling oversaturated passenger flow at urban rail transit stations. The technical solution adopted is as follows: The present invention proposes a method for pre-controlling oversaturated passenger flow at an urban rail transit station, the method comprising: Get the passenger entry and exit information of each station on the subway line at every time of the day; According to the passenger entry and exit information of each station in the time neighborhood at the real time, the representativeness of large-scale activities exiting and entering the station at each station at the real time is obtained, and the start time of the activity impact and the activity station are determined; After the event impact starts, the large-scale event participation of each subway line at each moment is obtained based on the large-scale event exit representativeness of each station on each subway line at each moment and the relative distance between each station and the event station; the increased capacity of each subway line at each moment is obtained based on the large-scale event participation and the number of available drivers of each subway line at each moment; According to the changing trend of the representativeness of large-scale activities entering the activity site or the representativeness of large-scale activities leaving the activity site at different times, the start time and the end time of the large-scale activities are obtained; Based on the increased capacity of each subway line at each time after the start time of the event, the start time of large-scale events, and the end time of large-scale events, the capacity of each subway line at different times is controlled.

[0005] Furthermore, the method for obtaining the representativeness of the large-scale event inbound and outbound includes: According to the passenger entry and exit information of each station within the time neighborhood at the real time, the local representativeness of large-scale activities corresponding to each passenger at each station at the real time is obtained; Obtain the local representative mean of large-scale activities corresponding to all outbound passengers at each station in real time, and normalize it as the outbound representativeness of large-scale activities at each station in real time; The local representative mean of large-scale activities corresponding to all passengers entering each station at the real time is obtained and normalized as the representativeness of large-scale activities entering each station at the real time.

[0006] Furthermore, the method for obtaining the local representativeness of the large-scale activity includes: Obtain the number of occurrences of each passenger at each station within the time neighborhood and the time of occurrence within the real time; obtain the mean difference between the time of occurrence and the real time under different numbers of occurrences as the first representative coefficient; The number of occurrences corresponding to each passenger is negatively mapped, and the negative correlation mapping result is multiplied by the first representative coefficient as the local representativeness of large-scale activities corresponding to each passenger at each station in real time.

[0007] Furthermore, the method for obtaining the activity impact start time and activity site includes: If the representativeness of large-scale outbound activities at each site in real time is greater than the representativeness of large-scale inbound activities, and the representativeness of large-scale outbound activities is greater than the preset representativeness threshold, the corresponding moment is taken as the start time of the activity impact, and the corresponding site is taken as the possible site of the activity; The possible activity sites with the largest representative value of large-scale activities are selected and the corresponding site is used as the activity site.

[0008] Furthermore, the method for obtaining the participation of the large-scale activity includes: After the start time of the activity impact, for each subway line, the relative distance between each station and the activity station is obtained and negative correlation mapping is performed as the first participation; The cumulative value of the product of the exit representativeness and the first participation of all stations in large-scale activities at each moment is obtained as the large-scale activity participation of each subway line at each moment.

[0009] Furthermore, the method for obtaining the increased transport capacity includes: The large-scale event participation of each subway line at each moment is normalized, and the product of the normalized result and the number of available drivers is obtained as the increased capacity of each subway line at each moment.

[0010] Furthermore, the method for obtaining the start time and end time of the large-scale activity includes: After the event impact starts, according to the changing trend of the large-scale event entry representativeness or large-scale event exit representativeness of the event site at different times, the possibility of the large-scale event starting and the possibility of the large-scale event ending at each time are obtained; If the probability of a large-scale activity starting at a certain time is greater than the preset start threshold, the corresponding time will be used as the start time of the large-scale activity; If the possibility of a large-scale activity ending at a certain moment is greater than a preset ending threshold, the corresponding moment will be regarded as the ending moment of the large-scale activity.

[0011] Furthermore, the method for obtaining the possibility of the start of a large-scale activity and the possibility of the end of a large-scale activity includes: After the event impact starts, the ratio of the representativeness of large-scale event exits at each station between each moment and the previous adjacent moment is obtained as the first ratio; the difference between the positive integer 1 and the first ratio is calculated as the possibility of the large-scale event starting at each station at each moment; The ratio of the representativeness of large-scale activities entering each station between each moment and the previous adjacent moment is obtained as the possibility of large-scale activities ending at each station at each moment.

[0012] Furthermore, the method for obtaining the time neighborhood range includes: The real-time moment is taken as the benchmark, and the range formed by the historical moment is taken as the time neighborhood range of the real-time moment.

[0013] Furthermore, an exponential function with a natural constant as the base is used for negative correlation mapping.

[0014] The present invention has the following beneficial effects: The present invention obtains the representativeness of large-scale activity exits and entrances of each station at the real time according to the passenger entry and exit information of each station within the time neighborhood at the real time, determines the start time of the activity impact and the activity station, and is helpful to timely adjust the subway line with insufficient capacity to avoid over-saturation of passenger flow; after the start time of the activity impact, according to the representativeness of large-scale activity exits of each station on each subway line at each time and the relative distance between each station and the activity station, obtains the participation of large-scale activities of each subway line at each time, avoids relying solely on station data, and comprehensively considers the passenger flow impact on the entire subway line; according to the participation of large-scale activities and the number of available drivers of each subway line at each time, obtains the increased capacity of each subway line at each time, avoids passengers being subjected to an oversaturated state, and causes crowded carriages; according to the changing trend of the representativeness of large-scale activity entrances or the representativeness of large-scale activity exits of the activity station at different times, obtains the start time and the end time of the large-scale activity, and performs capacity control on each subway line at different times. The present invention provides reasonable subway capacity and improves the effectiveness of passenger flow control by accurately analyzing the impact of passenger flow conditions of large-scale activities on subway capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for pre-controlling oversaturated passenger flow in an urban rail transit station provided by an embodiment of the present invention.

[0017] Figure 2 A flow chart of a method for obtaining representative information of large-scale event entry and exit provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a method for pre-controlling oversaturated passenger flow for urban rail transit stations proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the oversaturated passenger flow pre-control method for urban rail transit stations provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of a method for pre-controlling oversaturated passenger flow in an urban rail transit station provided by an embodiment of the present invention, and the specific method includes: Step S1: Obtain the passenger entry and exit information of each station on the subway line at each time of the day.

[0022] In an embodiment of the present invention, considering that large-scale activities will not be reported to relevant departments in advance, there will be differences in passenger flow changes 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 gates at the entrance and exit of the subway are passed by 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 ride records, indicating the passenger's entry or exit; obtain the passenger entry and exit information of each station in the subway line at each time of the day.

[0023] It should be noted that the time interval is 1 minute, that is, every day, the passenger entry and exit information at each station within every minute is obtained for analysis; in other embodiments of the present invention, the size of the time interval can be set according to the specific situation, and is not limited or elaborated here.

[0024] Step S2: Based on the passenger entry and exit information of each station within the time neighborhood at the real time, obtain the large-scale activity exit representativeness and large-scale activity entrance representativeness of each station at the real time, and determine the activity impact start time and activity station.

[0025] For passengers participating in large-scale events, they temporarily increase their demand for transportation because they are attracted by the large-scale events. Compared with regular commuting customers, they appear less frequently at event sites and their travel time is often different from usual. Therefore, the distribution of passengers appearing at each site within the historical time range is analyzed. According to the passenger entry and exit information of each site within the time neighborhood at the real-time moment, the representativeness of large-scale event exits and entrances at each site at the real-time moment is obtained.

[0026] Preferably, in one embodiment of the present invention, the method for obtaining the representativeness of the large-scale event inbound and the representativeness of the large-scale event outbound can be found in Figure 2 , which shows a flow chart of a method for obtaining the representativeness of an inbound activity and the representativeness of an outbound large-scale activity, including: Step S201: According to the passenger entry and exit information of each station within the time neighborhood at the real time, the local representativeness of large-scale activities corresponding to each passenger at each station at the real time is obtained.

[0027] Preferably, in one embodiment of the present invention, the method for obtaining local representativeness of a large-scale activity includes: Obtain the number of occurrences of each passenger at each station within the time neighborhood and the time of occurrence within the real time; obtain the mean difference between the time of occurrence and the real time under different numbers of occurrences as the first representative coefficient; The number of occurrences corresponding to each passenger is negatively mapped, and the negative correlation mapping result is multiplied by the first representative coefficient as the local representativeness of large-scale activities corresponding to each passenger at each station in real time.

[0028] In one embodiment of the present invention, the formula for the local representativeness of a large-scale activity is expressed as: ; in, Indicates Time The site corresponds to Local representation of large-scale activities with 10 passengers; Indicates Site The number of occurrences of a passenger in the time neighborhood; Indicates Site The passenger is in the time neighborhood The time of appearance.

[0029] In the formula for local representation of large-scale activities, It means calculating the mean difference between the appearance time and the real time under different appearance times, that is, the first representative coefficient. The larger the first representative coefficient, the greater the difference between the appearance time and the real time, the more irregular the time of appearance at the subway station, and the more likely it is a large-scale event. The smaller the number of appearances, the greater the local representativeness of large-scale events.

[0030] It should be noted that, in one embodiment of the present invention, the time neighborhood range is based on the real-time moment and the range formed by the historical moment, wherein the historical moment is every moment of every day in a historical year; in other embodiments of the present invention, the time neighborhood range can be set according to the specific circumstances, and is not limited or elaborated here.

[0031] Step S202: Obtain the local representative mean of large-scale activities corresponding to all outbound passengers at each station in real time, and normalize it as the outbound representativeness of large-scale activities at each station in real time.

[0032] In one embodiment of the present invention, for outbound passengers, a representative formula for large-scale event inbound is expressed as: ; in, Indicates Time Representativeness of large-scale activities at each site; Indicates Time The site corresponds to Local representation of large-scale activities with 10 passengers; Indicates Time The number of outbound passengers at each station; Represents the maximum and minimum normalization function.

[0033] In the formula for large-scale event outbound representation, Indicates the calculation Time The local representativeness of large-scale activities for all exiting passengers at each station is averaged. The more exiting passengers there are at a subway station, the greater the exit representativeness of large-scale activities, and the more likely it is that this is the location of a large-scale event.

[0034] Step S203: Obtain the local representative mean of large-scale activities corresponding to all passengers entering each station at the real time, and normalize it as the representativeness of large-scale activities entering each station at the real time.

[0035] It should be noted that, in one embodiment of the present invention, the representativeness of large-scale event entry is obtained by the same method as the representativeness of large-scale event exit, and all passengers entering the station are analyzed; the maximum and minimum normalization functions are used for normalization. In other embodiments of the present invention, normalization can also be performed using existing normalization functions such as the inverse tangent function. The specific normalization function is a technical means well known to those skilled in the art and will not be elaborated here.

[0036] The representativeness of ingress and egress of large-scale events reflects the distribution trend of passenger flow at each subway station. The greater the representativeness of egress, the more likely it is that an event will be held at the corresponding station; determine the start time of the event and the event site.

[0037] Preferably, in one embodiment of the present invention, the method of selecting the activity impact start time and the activity site includes: If the representativeness of large-scale outbound activities at each site in real time is greater than the representativeness of large-scale inbound activities, and the representativeness of large-scale outbound activities is greater than the preset representativeness threshold, the corresponding moment is taken as the start time of the activity impact, and the corresponding site is taken as the possible site of the activity; The possible activity sites with the largest representative value of large-scale activities are selected and the corresponding site is used as the activity site.

[0038] It should be noted that, in one embodiment of the present invention, a representative threshold of 0.8 is preset; in other embodiments of the present invention, the size of the preset representative threshold may be set according to specific circumstances, which is not limited or elaborated herein.

[0039] Step S3: After the event impact starts, the large-scale event participation of each subway line at each moment is obtained based on the large-scale event exit representativeness of each station on each subway line at each moment and the relative distance between each station and the event site; the increased capacity of each subway line at each moment is obtained based on the large-scale event participation of each subway line at each moment and the number of available drivers.

[0040] Before a large-scale event begins, the passengers participating in the event are highly concentrated and purposeful. The greater the representativeness of the large-scale event exit, the more passengers will participate in the large-scale event. The relative distance reflects the distance of each station relative to the event station. The farther the distance, the more dispersed the passengers are, the smaller the contribution to the line's participation, and the smaller the station's participation in large-scale events. After the event impact begins, the large-scale event participation of each subway line at each moment is obtained based on the representativeness of the large-scale event exit of each station on each subway line at each moment and the relative distance between each station and the event station.

[0041] Preferably, in one embodiment of the present invention, the method for obtaining the participation of a large-scale activity includes: After the start time of the activity impact, for each subway line, the relative distance between each station and the activity station is obtained and negative correlation mapping is performed as the first participation; The cumulative value of the product of the exit representativeness and the first participation of all stations in large-scale activities at each moment is obtained as the large-scale activity participation of each subway line at each moment.

[0042] In one embodiment of the present invention, the formula for large-scale activity participation is expressed as: ; in, Indicates Time The participation in large-scale events on the metro lines; Indicates the active site With The relative distance between the sites; Indicates Time Representativeness of large-scale outbound activities at each site; represents an exponential function with a natural constant as base; Indicates The number of stations on a subway line.

[0043] In the formula for large-scale event participation, the exponential function with a constant as the base is used to convert Negative correlation mapping is performed. The greater the relative distance between stations and the greater the difference between stations, the smaller the contribution to the participation of the subway line, the smaller the representativeness of large-scale events, and the smaller the participation in large-scale events; the greater the representativeness of large-scale events at the station, the more exiting passengers there are, which may be affected by large-scale events and the greater the participation in large-scale events.

[0044] It should be noted that, in some embodiments of the present invention, existing distance calculation methods such as Euclidean distance or approximate spherical distance may be used. The specific means are technical means well known to those skilled in the art and will not be described in detail here.

[0045] After the event impact begins, in order to achieve the most efficient capacity allocation, lines with higher large-scale event participation should obtain more capacity to cope with the possible increase in passenger flow and achieve pre-control of oversaturated passenger flow; based on the large-scale event participation and the number of available drivers of each subway line at each moment, the increased capacity of each subway line at each moment is obtained.

[0046] Preferably, in one embodiment of the present invention, the method for obtaining increased transportation capacity includes: The large-scale event participation of each subway line at each moment is normalized, and the product of the normalized result and the number of available drivers is obtained as the increased capacity of each subway line at each moment.

[0047] In one embodiment of the present invention, the formula for increasing the transport capacity is expressed as: ; in, Indicates Time Increased capacity of subway lines; Indicates Time The participation in large-scale events on the metro lines; Indicates the number of subway lines; Indicates Time The participation in large-scale events on the metro lines; Indicates The number of drivers available at the time.

[0048] In the formula for increasing capacity, Indicates Time The ratio of the participation rate of large-scale activities on the subway line to the sum of the participation rate of large-scale activities on all subway lines, that is, the participation rate of large-scale activities on the first subway line is Time The participation rate of large-scale activities on the subway lines was normalized. Time The more participation there is in large-scale events on a subway line, the more capacity there needs to be added to that subway line.

[0049] Step S4: Obtain the start time and end time of the large-scale activity according to the change trend of the representativeness of the large-scale activity entry or the representativeness of the large-scale activity exit of the activity site at different times.

[0050] After the start time of the event and before the large-scale event, passengers participating in the event usually go to the event site where the large-scale event takes place. As the event begins, the closer to the start time, the smaller the representativeness of the large-scale event exits; as the event ends, most of the passengers participating in the event will return and rarely stay at the event site. The closer to the end time, the smaller the representativeness of the large-scale event entry. According to the changing trend of the large-scale event entry representativeness or large-scale event exit representativeness of the event site at different times, the start time and end time of the large-scale event are obtained.

[0051] Preferably, in one embodiment of the present invention, the method for obtaining the start time and the end time of a large-scale activity includes: After the event impact starts, according to the changing trend of the large-scale event entry representativeness or large-scale event exit representativeness of the event site at different times, the possibility of the large-scale event starting and the possibility of the large-scale event ending at each time are obtained; Preferably, in one embodiment of the present invention, the method for obtaining the possibility of a large-scale activity starting and the possibility of a large-scale activity ending includes: After the event impact starts, the ratio of the representativeness of large-scale event exits at each station between each moment and the previous adjacent moment is obtained as the first ratio; the difference between the positive integer 1 and the first ratio is calculated as the possibility of the large-scale event starting at each station at each moment; The ratio of the representativeness of large-scale activities entering each station between each moment and the previous adjacent moment is obtained as the possibility of large-scale activities ending at each station at each moment.

[0052] In one embodiment of the present invention, the formulas for the probability of a large-scale activity starting and the probability of a large-scale activity ending are expressed as: ; ; in, Indicates The probability of large-scale activities starting at each site at the moment; Indicates The possibility of large-scale activities ending at each site at the moment; Indicates Time The site’s large-scale outbound activity representativeness; Indicates Time The site’s large-scale outbound activity representativeness; Indicates Time The representativeness of the site’s large-scale event entry; Indicates Time The site's large-scale event entry representativeness.

[0053] In the formula for the likelihood of a large event starting, Indicates Moment and The moment between The ratio of the representativeness of the exits of large-scale activities at the station. The larger the ratio, the greater the representativeness of the exits at the next moment than at the previous moment, that is, the more passengers exit at the next moment than at the previous moment, and the closer it is to the start time. On the contrary, the smaller the ratio, the less representativeness of the exits at the next moment than at the previous moment, that is, the less passengers exit at the next moment than at the previous moment, the more likely it is to be close to the start time, and the greater the possibility of the start of a large-scale event. In the formula for the possibility of the end of a large-scale event, Indicates Time and The moment between The larger the ratio is, the more representative the arrivals at the next moment are than those at the previous moment. That is, the more passengers will arrive at the next moment than at the previous moment, which means that the closer the next moment is to the end time, the greater the possibility that the large-scale event will end.

[0054] If the possibility of a large-scale event starting at a certain moment is greater than the preset start threshold, the corresponding moment will be used as the start time of the large-scale event; if the possibility of a large-scale event ending at a certain moment is greater than the preset end threshold, the corresponding moment will be used as the end time of the large-scale event.

[0055] It should be noted that the possibility of a large-scale activity starting reflects the probability of a large-scale activity starting. The greater the possibility, the greater the probability of the activity starting; the possibility of a large-scale activity ending reflects the probability of a large-scale activity ending. The greater the possibility, the greater the probability of the activity 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 be set according to the specific circumstances, which are not limited or elaborated here.

[0056] Based on this, after obtaining the start and end times of large-scale events, in order to avoid oversaturation of passenger flow at the station, the capacity of the subway line is adjusted and controlled to cope with passenger peak conditions.

[0057] Step S5: according to the increased capacity of each subway line at each time after the start time of the activity impact, the start time of the large-scale activity and the end time of the large-scale activity, the capacity of each subway line at different times is controlled.

[0058] During large-scale events, subway passenger flow will show an uneven distribution in time and space, and certain lines or stations may experience instantaneous peaks. Therefore, it is necessary to dynamically adjust the capacity allocation of each line according to the impact of the event to improve transportation efficiency and avoid passenger congestion.

[0059] It should be noted that, in another embodiment of the present invention, based on the acquired increased capacity of each subway line at each time after the start time of the activity impact, the start time of the large-scale activity and the end time of the large-scale activity, the capacity of each subway line at different time is controlled, including: after the start time of the activity impact, the capacity of the subway line is increased according to the acquired increased capacity of each subway line at each time until the passenger flow returns to a normal level after the start of the large-scale activity, and therefore, the line capacity is not increased within the range from the start to the end of the large-scale activity; The time from the start to the end of a large-scale event is clear and relatively short, so the flow of passengers shows a similar pattern. The influx of passengers before the event and the return of passengers after the event are symmetrical in time. Therefore, the subway capacity is symmetrical in time. The return passenger flow on the opposite lines at symmetrical time is usually similar to the arrival flow, and the required increase in subway capacity should also be similar, that is, the reverse line of the subway line is increased after the end of the large-scale event, and the increased capacity in each minute corresponds to the increased capacity of each subway line at each moment after the start of the event.

[0060] In summary, the present invention obtains the representativeness of large-scale activities exiting the station and the representativeness of large-scale activities entering the station at each station in real time according to the passenger entry and exit information of each station in the time neighborhood range at the real time, and determines the start time of the activity impact and the activity station; after the start time of the activity impact, according to the representativeness of large-scale activities exiting the station at each station on each subway line at each time and the relative distance between each station and the activity station, the participation of large-scale activities of each subway line at each time is obtained; according to the participation of large-scale activities of each subway line at each time and the number of available drivers, the increased capacity of each subway line at each time is obtained; according to the changing trend of the representativeness of large-scale activities entering the station or the representativeness of large-scale activities exiting the station at the activity station at different times, the start time of large-scale activities and the end time of large-scale activities are obtained, and the capacity of each subway line at different times is controlled. The present invention provides reasonable subway capacity and improves the effectiveness of passenger flow control by obtaining the accurate time range of large-scale activities.

[0061] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying 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.

[0062] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for pre-controlling oversaturated passenger flow at urban rail transit stations, characterized in that: The method comprises: Get the passenger entry and exit information of each station on the subway line at every time of the day; According to the passenger entry and exit information of each station in the time neighborhood at the real time, the representativeness of large-scale activities exiting and entering the station at each station at the real time is obtained, and the start time of the activity impact and the activity station are determined; After the event impact starts, the large-scale event participation of each subway line at each moment is obtained based on the large-scale event exit representativeness of each station on each subway line at each moment and the relative distance between each station and the event station; the increased capacity of each subway line at each moment is obtained based on the large-scale event participation and the number of available drivers of each subway line at each moment; According to the changing trend of the representativeness of large-scale activities entering or exiting the activity site at different times, the start time and end time of the large-scale activities are obtained; Based on the increased capacity of each subway line at each time after the start time of the event, the start time of large-scale events, and the end time of large-scale events, the capacity of each subway line at different times is controlled.

2. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 1, characterized in that: The method for obtaining the representativeness of the large-scale event inbound and outbound includes: According to the passenger entry and exit information of each station within the time neighborhood at the real time, the local representativeness of large-scale activities corresponding to each passenger at each station at the real time is obtained; Obtain the local representative mean of large-scale activities corresponding to all outbound passengers at each station in real time, and normalize it as the outbound representativeness of large-scale activities at each station in real time; The local representative mean of large-scale activities corresponding to all passengers entering each station at the real time is obtained and normalized as the representativeness of large-scale activities entering each station at the real time.

3. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 2, characterized in that: The method for obtaining the local representativeness of the large-scale activity includes: Obtain the number of occurrences of each passenger at each station within the time neighborhood and the time of occurrence within the real time; obtain the mean difference between the time of occurrence and the real time under different numbers of occurrences as the first representative coefficient; The number of occurrences corresponding to each passenger is negatively mapped, and the negative correlation mapping result is multiplied by the first representative coefficient as the local representativeness of large-scale activities corresponding to each passenger at each station in real time.

4. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 1, characterized in that: The method for obtaining the activity impact start time and activity site includes: If the representativeness of large-scale outbound activities at each site in real time is greater than the representativeness of large-scale inbound activities, and the representativeness of large-scale outbound activities is greater than the preset representativeness threshold, the corresponding moment is taken as the start time of the activity impact, and the corresponding site is taken as the possible site of the activity; The possible activity sites with the largest representative value of large-scale activities are selected and the corresponding site is used as the activity site.

5. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 1, characterized in that: The method for obtaining the participation of the large-scale activity includes: After the start time of the activity impact, for each subway line, the relative distance between each station and the activity station is obtained and negative correlation mapping is performed as the first participation; The cumulative value of the product of the exit representativeness and the first participation of all stations in large-scale activities at each moment is obtained as the large-scale activity participation of each subway line at each moment.

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

7. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 1, characterized in that: The method for obtaining the start time and end time of the large-scale activity includes: After the event impact starts, according to the changing trend of the large-scale event entry representativeness or large-scale event exit representativeness of the event site at different times, the possibility of the large-scale event starting and the possibility of the large-scale event ending at each time are obtained; If the probability of a large-scale activity starting at a certain time is greater than the preset start threshold, the corresponding time will be used as the start time of the large-scale activity; If the possibility of a large-scale activity ending at a certain moment is greater than a preset ending threshold, the corresponding moment will be regarded as the ending moment of the large-scale activity.

8. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 7, characterized in that: The method for obtaining the start possibility and the end possibility of the large-scale activity includes: After the event impact starts, the ratio of the representativeness of large-scale event exits at each station between each moment and the previous adjacent moment is obtained as the first ratio; the difference between the positive integer 1 and the first ratio is calculated as the possibility of the large-scale event starting at each station at each moment; The ratio of the representativeness of large-scale activities entering each station between each moment and the previous adjacent moment is obtained as the possibility of large-scale activities ending at each station at each moment.

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

10. The method for pre-controlling oversaturated passenger flow at urban rail transit stations according to claim 5, characterized in that: An exponential function with a natural constant as the base is used for negative correlation mapping.

Images