Peak period passenger transport organization optimization method and system based on big data

Abstract

The invention provides a peak period passenger transport organization optimization method and system based on big data, and relates to the technical field of passenger transport organization optimization. The method comprises the following steps: acquiring historical peak period passenger transport data of a target station, and performing feature extraction based on price factors to form peak period passenger transport change feature data; collecting ticket booking data of the target station in the current peak period, and performing passenger flow guide adjustment based on price factors in combination with the passenger transport change characteristic data in the peak period to form passenger flow guide adjustment data; and acquiring guide peak ticket booking data of the target station, and performing early warning analysis in combination with station transport capacity data to form peak guide early warning data. According to the method, active consumption guidance is realized through characteristic analysis based on price factors, so that the condition of transport capacity tension caused by peak hours is relieved, the efficiency is high, and the influence on the cost is relatively small.

Description

Technical Field

[0001] The present invention relates to the technical field of optimizing passenger transport organization. Specifically, it relates to a method and system for optimizing passenger transport organization during peak periods based on big data. Background Art

[0002] Transportation affects social development and is also an essential travel need in your daily life. A station is the passenger-loading and unloading service end where transportation vehicles pick up and drop off passengers. For different stations, due to the influence of geographical and human factors, there is a huge gap in the throughput of passenger volume. Especially during peak travel periods, some larger stations will face challenges in passenger transport services.

[0003] Currently, in order to cope with the increased passenger volume during peak periods, most stations use technologies such as artificial intelligence, big data, and the Internet of Things to achieve reasonable scheduling of transportation vehicles, thereby fully ensuring that the station has corresponding matching transport capacity. However, this method mainly passively meets the transport capacity requirements of the station by adjusting the transport capacity. It does not essentially eliminate the impact of peak periods on transport capacity. Moreover, the adjustment of transport capacity involves multiple aspects, which usually complicates the problem in terms of usage and operation costs as well as scheduling, and cannot effectively solve the problem of transport capacity allocation during peak periods.

[0004] Therefore, designing a method and system for optimizing passenger transport organization during peak periods based on big data, which actively guides consumption through feature analysis based on price factors to relieve the transport capacity tension caused by peak periods, is efficient and has less impact on costs. This is an urgent problem to be solved currently. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for optimizing passenger transport organization during peak periods based on big data. By extracting feature information on the relationship between passenger transport prices and passenger volume on different cloud lines from the historical passenger transport data of stations during peak periods, a feature big data of price and passenger volume during peak periods is established. Then, it provides a big data comparison reference for the passenger volume of the next peak period, judges the matching degree between the passenger volume during peak periods and the transport capacity of the station on the corresponding cloud line, and makes price-based adjustments to the periods with low matching degree and large differences, realizing the adjustment of passenger volume mainly based on price changes, changing from passively accepting the increase in passenger volume to actively adjusting the passenger volume to match the transport capacity of the station. On the one hand, it greatly relieves the congestion degree of passenger transport during peak periods and avoids the increase in costs caused by passively accepting changes in passenger volume. On the other hand, it fully caters to the market law, controls the volume with price, effectively ensures the matching of the transport capacity and passenger volume of the station while also enabling efficient real-time monitoring of the cloud line transport capacity and passenger volume situation, providing more timely and accurate data for subsequent real-time optimization.

[0006] The object of the present invention also lies in providing an optimization system for peak - period passenger transport organization based on big data. The system obtains the historical data of the station and the current data during the peak period through a data acquisition unit. The feature extraction unit fully extracts the features of the historical big data to provide a data basis for the optimization of passenger transport organization. The monitoring and early - warning unit then ensures that the current passenger volume is guided and adjusted in the most reasonable way. Multiple different units cooperate closely with each other to achieve efficient and reasonable optimization and adjustment of peak - period passenger transport organization, which is an important position basis for completing the optimization of passenger transport organization.

[0007] In a first aspect, the present invention provides an optimization method for peak - period passenger transport organization based on big data, including: obtaining the historical peak - period passenger transport data of a target station, performing feature extraction based on price factors to form peak - period passenger transport change feature data; collecting the current peak - period ticket - booking data of the target station, and combining the peak - period passenger transport change feature data to perform passenger flow guidance and adjustment based on price factors to form passenger flow guidance and adjustment data; obtaining the guided peak - period ticket - booking data of the target station, and combining the station capacity data to perform early - warning analysis to form peak - period guidance early - warning data.

[0008] In the present invention, the method extracts the characteristic information of the relationship between passenger transport price and passenger volume on different cloud lines from the historical passenger transport data of the station during the peak period, establishes the characteristic big data of price and passenger volume during the peak period, and further provides a big - data comparison reference for the passenger volume in the next peak period, judges the matching degree between the passenger volume during the peak period and the capacity of the station on the corresponding cloud line, and makes price - based adjustments to the periods with low matching degree and large differences, realizes the adjustment of passenger volume mainly based on price changes, changes from passively accepting the increase in passenger volume to actively adjusting the passenger volume to match the capacity of the station. On the one hand, it greatly alleviates the congestion degree of passenger transport during the peak period and avoids the increase in costs caused by passively accepting changes in passenger volume. On the other hand, it fully conforms to the market law, controls the volume with price, while effectively ensuring the matching of station capacity and passenger volume, it also enables the efficient real - time monitoring of the cloud - line capacity and passenger volume situation, providing more timely and accurate data for subsequent real - time optimization.

[0009] As a possible implementation, obtain the historical peak passenger volume data of the target station, perform feature extraction based on price factors, and form the peak passenger volume change feature data, including: according to the historical peak passenger volume data of the target station, extract the simultaneous line passenger volume change data and simultaneous line price change data of different lines under the same type of peak period; for different lines, according to the line passenger volume change data, determine the passenger volume change data of the target station on different lines during the peak periods of the same type but different times, and combine the corresponding simultaneous line price change data to perform price parameter mapping of the price per unit mileage of the line, forming a simultaneous peak line price passenger volume change function; for different lines, perform passenger volume feature extraction of the same price for different simultaneous peak line price passenger volume change functions, forming different simultaneous line period price passenger volume change data; for different lines, according to the corresponding simultaneous line period price passenger volume change data, perform guiding feature analysis of price factors, forming line price guiding feature data.

[0010] In the present invention, when performing feature extraction based on price factors on the historical peak passenger volume data of the station, two main aspects are considered. One is the corresponding relationship between price and passenger volume at different time periods during the peak period. This corresponding relationship not only reflects the change situation of the passenger volume controlled by the price, but also reflects the passenger volume change information under the peak period characteristics. The combination of the two aspects forms the passenger volume change data during the peak period under historical data. Of course, for the station, the different destinations of different people traveling determine that there are significant differences in the boarding volume of the station on different transport lines. Therefore, when extracting features, the situations of different lines need to be fully considered to avoid affecting the accuracy and rationality of big data analysis. Moreover, the passenger volume of the station changes significantly at different time periods. For example, during legal holidays, the passenger volumes on the first day, the middle day, and the last day of the holiday are different, and the influence of time factors on the passenger volume needs to be fully considered. On the other hand, it is necessary to establish the relationship between the influence degree of price on passenger volume. It can be understood that to a certain extent, people's travel time is affected by price. Usually, when the price is higher, the passenger volume decreases, and when the price is lower, the passenger volume increases. Therefore, the influence of price on passenger volume needs to be fully considered. Since it is necessary to consider the influence of both time factors and price factors on passenger volume at the same time, in this way, in order to match the discreteness of time data, it is reasonable to establish a mutual relationship between price data and passenger volume data with discrete time periods as a reference. For example, if there are multiple holidays during the peak period, then the first day of the holiday is the bottom-level time factor data. In addition, since the price factor plays an important role in optimizing passenger transport organization in this application, it is necessary to reflect the change influence of price data on passenger volume to form important reference data for actively adjusting passenger volume.

[0011] As a possible implementation, for different transport lines, the passenger volume characteristics at the same price are extracted from the passenger volume change functions of different peak transport line prices in the same period, forming the passenger volume change data of different transport line time periods at the same price in the same period, including: for the passenger volume change functions of different peak transport line prices in the same period, the passenger volume is divided based on the statistical time period to determine the total passenger volume in different statistical time periods under each passenger volume change function of the peak transport line price in the same period; for the passenger volume change functions of different peak transport line prices in the same period, according to the price per unit mileage of the corresponding transport line in the statistical time period, all statistical time periods with the same price are clustered, and based on the total passenger volume corresponding to the clustered statistical time periods, the average passenger volume of the time period at the corresponding price per unit mileage of the transport line is determined; according to the average passenger volume of different time periods corresponding to different prices in different statistical time periods, the passenger volume change function F of the transport line time period at the same price in the same period is established n (P, V, T k ), where n represents the numbers of different transport lines, P is the price per unit mileage of the transport line, V represents the passenger volume of the transport line, T is the time period of the peak period, and k represents the numbers of different statistical time periods under the time period of the peak period; the passenger volume change functions F of the transport line time period at the same price in the same period corresponding to different statistical time periods are aggregated n (P, V, T k ) to form the passenger volume change data of the transport line corresponding to the transport line time period at the same price in the same period.

[0012] In the present invention, for the same transportation line, the historical peak passenger volume data includes the passenger volume data of all different periods under the same peak period on the transportation line. Therefore, these data are first comprehensively processed to express the relationship between the passenger volume, price, and time period in terms of big data. It can be understood that under the same statistical period, since the passenger volume data includes the corresponding data of each period, a data set corresponding to different prices and different passenger volumes will be formed under this statistical period. Of course, due to the huge amount of big data, there will also be data with the same price. It should be noted here that since a small change in price will not cause a substantial change in the passenger volume, the understanding of the same price here is that a price group within a certain fluctuation range can be considered the same price. Of course, for the booking price, basically, the price adjustment is relatively large, so different identical price groups can be quickly identified. Similarly, there will also be fluctuations in the passenger volume corresponding to the same price. Therefore, the average price of the price group in each statistical period is used as the price value for analysis reference, and the average value of all passenger volumes corresponding to the price group is used as the effective passenger volume reference value corresponding to this price group, thereby establishing reasonable relationship data between price and passenger volume. In addition, for price data, it is not the booking price of each passenger. Considering that no matter which station on the same transportation line is reached, passengers will board the vehicle from the target station, it is not reasonable to use the booking price as the price data on the transportation line. Different arrival stations will have different prices. Therefore, converting the booking price to the price per unit mileage on the transportation line can better represent the price data information of the transportation line. Although there are different price data in the same statistical period, the sample data itself has discreteness, so the relationship data between the formed price change data and the passenger volume is also discrete statistical data. To ensure that the subsequent price adjustment can perform reasonable curve fitting after obtaining the data and then form the continuous change relationship data of the passenger volume corresponding to the continuous change of the price data, there are various ways of curve fitting, which can be the least squares method, polynomial fitting, etc.

[0013] As a possible implementation method, for different transportation lines, according to the corresponding price-passenger volume change data of the transportation line period in the same period, the guiding feature analysis of the price factor is carried out to form the transportation line price guiding feature data, including: for the different price-passenger volume change functions F of the transportation line period in the same period n (P, V, T k ), the price change value of adjacent pricing and the corresponding passenger volume change value are determined; the different price change values are arranged in ascending order, and according to the corresponding passenger volume change values, the period price adjustment passenger volume change function W of the corresponding statistical period is established k (U), where U represents the price change value and W represents the passenger volume change value; the period price adjustment passenger volume change functions W corresponding to different statistical periods are aggregatedk (U) forms the price guidance characteristic data of the transport line.

[0014] In the present invention, the purpose of big data feature analysis is to estimate the corresponding passenger volume under the price data for the subsequent peak period based on the big data feature information, and adjust the real-time ticket price based on the passenger volume feature information corresponding to different prices to guide the passenger volume to match the capacity to change. Therefore, it is necessary to extract the passenger volume change relationship characteristics caused by the price change amount for the passenger volume change data obtained according to big data. Considering that the price and volume change function of the same period of the line period is fitted based on the obtained discrete data, the discrete data has a relatively real nature. Therefore, when performing the relationship analysis and extraction of the passenger volume change caused by the price change amount, the collected discrete data is analyzed, the price change value and the corresponding passenger volume change value are obtained for the adjacent prices, and the sorting data of the passenger volume change caused by the change in the order of the price change amount is established according to the size relationship of the price change value, and then the characteristic data of the relationship between the price change value and the passenger volume change value is obtained on the basis of a reasonable fitting analysis, which provides important guiding reference data for subsequent price adjustments to match the station capacity.

[0015] As a possible implementation method, the current peak-period ticket booking data of the target station is collected, and the passenger flow guidance adjustment based on the price factor is performed in combination with the peak-period passenger traffic change characteristic data to form the passenger flow guidance adjustment data, including: collecting the current peak-period ticket booking data before the peak period, and extracting the current ticket booking data of different lines respectively; for the current ticket booking data of different lines, determining the current period price of the line corresponding to different statistical periods and the corresponding current period ticket booking volume of the line; according to the current period price of the line corresponding to the statistical period, combining the passenger traffic change function F of the corresponding line in the same statistical period with the line period price of the corresponding line n (P, V, T k ) to conduct the following analysis: If the ticket volume of the current period of the line does not exceed the passenger volume change function F of the line price during the same period of time under the current period of the line price n (P, V, T k ) is the product of the corresponding total passenger volume value and the passenger flow limit ratio, then it is determined that the statistical period is in a normal passenger flow state under the current situation; if the ticket volume of the current period of the line exceeds the passenger flow change function F of the line price during the same period under the current period of the line price n (P, V, T k ) is the product of the corresponding total passenger volume value and the passenger flow limit ratio, then it is determined that the statistical period is in an abnormal passenger flow state under the current circumstances; for all statistical periods determined to be in an abnormal passenger flow state, the passenger flow guidance adjustment of the price factor is performed in combination with the corresponding route price guidance characteristic data to form passenger flow guidance adjustment data.

[0016] In the present invention, the current peak booking data can be obtained at an appropriate time point after the booking channel of the open target site and before the peak time arrives. Obtaining the data too early will result in untrue extraction of the passenger volume data, and obtaining it too late will cause no obvious passenger flow guidance in subsequent price adjustments. Therefore, by analyzing historical data, the time point can be determined after which collecting the data at the latest can still adjust the price significantly to satisfy the functional relationship between the passenger volume change in the time period of price adjustment. Of course, whether the current peak booking data reaches the passenger volume data corresponding to the price in the passenger volume change function of the same-period transport line time period at each statistical time period determines whether there will be a shortage of transport capacity in that statistical time period. However, when making an analysis and judgment, it cannot be directly compared with the passenger volume data corresponding to the price in the passenger volume change function of the same-period transport line time period, because the time point for collecting the current peak booking data is not within the statistical time period, and there is still a period of time before reaching the corresponding statistical time period, and there will inevitably be an increase in the passenger volume during this period. Therefore, for reasonable guidance, it is necessary to make an advance prediction and judgment. So, it should be determined whether the passenger volume provided by the booking data is close to the passenger volume data corresponding to the price in the passenger volume change function of the same-period transport line time period. If so, there is a risk that the passenger volume will exceed the transport capacity at the statistical time period. Furthermore, it is necessary to consider adjusting the booking price in advance to guide the passengers who have planned or already booked tickets during the statistical time period to change their tickets or rebook tickets to other statistical time periods with sufficient remaining transport capacity. Here, the passenger flow limit ratio can be determined according to the actual situation or based on big data analysis.

[0017] As a possible implementation method, for all statistical time periods determined to be in an abnormal passenger volume state, combined with the corresponding transport line price guidance characteristic data, passenger flow guidance adjustment for price factors is carried out to form passenger flow guidance adjustment data, including: marking the statistical time periods determined to be in an abnormal passenger volume state as the time periods to be adjusted, and determining the passenger volume exceeding the product of the total passenger volume value corresponding to the same-period transport line time period price passenger volume change function F n (P, V, T k ) and the passenger flow limit ratio, and recording it as the passenger volume q to be adjusted adj ; for other statistical time periods except the time periods to be adjusted, determining the passenger volume not exceeding the product of the total passenger volume value corresponding to the same-period transport line time period price passenger volume change function F n (P, V, T k ) and the passenger flow limit ratio, and recording it as the passenger volume q to be absorbed in the time period abs ; according to the passenger volume q to be adjusted in the time periods to be adjusted and the passenger volume q to be absorbed in the time period of the statistical time period, carry out passenger flow guidance adjustment in the following way: if the sum of the passenger volumes q adj to be adjusted in all time periods to be adjusted is not greater than the sum of the passenger volumes q to be absorbed in all time periodsabs If it is the sum, then adjust the passenger volume change function W according to the period price corresponding to the period to be adjusted k (U) and the passenger volume q to be adjusted adj Determine the price to be adjusted corresponding to different periods to be adjusted, and evenly distribute the passenger volume q to be adjusted to other statistical periods, and adjust the passenger volume change function W according to the corresponding period price adj (U) to determine the corresponding absorption adjustment price; if the sum of the passenger volumes q to be adjusted in all periods to be adjusted is greater than the sum of the passenger volumes q to be absorbed in all periods k (U) and the passenger volume q to be adjusted adj Sum, then adjust the passenger volume change function W according to the period price corresponding to the period to be adjusted abs (U) and the passenger volume q to be adjusted k Determine the price to be adjusted corresponding to different periods to be adjusted, and adjust the passenger volume change function W according to the corresponding period price for other statistical periods adj (U) and the passenger volume q to be absorbed in the period to determine the corresponding absorption adjustment price; obtain all the prices to be adjusted and the absorption adjustment prices to form passenger flow guidance adjustment data k (U) and the passenger volume q to be absorbed in the period to determine the corresponding absorption adjustment price; obtain all the prices to be adjusted and the absorption adjustment prices to form passenger flow guidance adjustment data abs Determine the corresponding absorption adjustment price; obtain all the prices to be adjusted and the absorption adjustment prices to form passenger flow guidance adjustment data

[0018] In the present invention, when the passenger volume data of a statistical period has exceeded the passenger volume data of the passenger volume change function of the same period's line segment price at the corresponding price in the upcoming peak period, the price adjustment method adopted is to determine the excess passenger volume, and use this passenger volume as a reference to take the unsaturated transport capacity of other statistical periods as the object to be guided. By evenly distributing the excess passenger volume to other statistical periods where the passenger volume does not exceed, the corresponding increased passenger volume to be increased in other statistical periods where the passenger volume does not exceed is determined, and then the price adjustment amount is determined in the period price adjustment passenger volume change function according to this passenger volume increase value to adjust the price of the corresponding statistical period. For the excess passenger volume, the corresponding price to be adjusted is determined according to the period price adjustment passenger volume change function. Finally, passenger flow guidance adjustment data corresponding to the situation where the transport capacity on the line segment cannot match during the peak period is formed, realizing the purpose of reasonable and efficient price drainage

[0019] As a possible implementation method, for all statistical periods determined to be in an abnormal passenger volume state, conduct passenger flow guidance adjustment of price factors in combination with the corresponding line segment price guidance characteristic data of the line segment to form passenger flow guidance adjustment data, including: marking the statistical periods determined to be in an abnormal passenger volume state as periods to be adjusted, and determining the total passenger volume value corresponding to the passenger volume change function F of the same period's line segment price n (P, V, T k ) The passenger flow volume exceeding the product of the passenger flow limit ratio is recorded as the passenger volume q to be adjusted adj; For other statistical periods except the period to be adjusted, determine the passenger volume change function F of the statistical period relative to the price of the operation line period in the same period n (P, V, T k ) The product of the total passenger volume value corresponding to the passenger flow limit ratio is not exceeded, and the passenger flow is recorded as the passenger volume q to be absorbed in the period abs ; According to the passenger volume to be adjusted in the period to be adjusted and the passenger volume to be absorbed in the statistical period, conduct passenger flow guidance and adjustment in the following way: If the sum of the passenger volumes q adj to be adjusted in all periods to be adjusted is not greater than the sum of the passenger volumes q abs to be absorbed in all periods, then according to the passenger volume change function W k (U) corresponding to the period to be adjusted and the passenger volume q adj to be adjusted, determine the prices to be adjusted corresponding to different periods to be adjusted, and make the following price adjustment selection for other statistical periods; taking the period to be adjusted as the benchmark, select statistical periods in sequence according to the time dimension direction, and according to the passenger volume q abs to be absorbed in the statistical period, cover the passenger volume q adj to be adjusted until the sum of the passenger volumes q abs to be absorbed in all selected statistical periods is greater than the sum of the passenger volumes q adj to be adjusted; and when selecting statistical periods in sequence according to the time dimension direction, take the forward time dimension direction as the first selected direction until all statistical periods in the direction are obtained and the passenger volume q adj to be adjusted is not covered. Then, take the backward time dimension direction as the selection direction to continue obtaining statistical periods until the sum of the passenger volumes q abs to be absorbed in all selected statistical periods is greater than the sum of the passenger volumes q adj to be adjusted; for the selected statistical periods, determine the corresponding absorption adjustment prices in sequence according to the selected order based on the corresponding passenger volume change function W k (U) and the passenger volume q abs to be absorbed in the period. For the last selected statistical period, determine the corresponding absorption adjustment price according to the remaining passenger volume q adj and the corresponding passenger volume change function W k (U); If the sum of the passenger volumes q adj to be adjusted in all periods to be adjusted is greater than the sum of the passenger volumes q abs to be absorbed in all periods, then according to the passenger volume change function W k (U) corresponding to the period to be adjusted and the passenger volume q adj to be adjusted, determine the prices to be adjusted corresponding to different periods to be adjusted, and for other statistical periods, according to the corresponding passenger volume change function Wk (U) and the passenger volume q to be absorbed in a time period abs Determine the corresponding absorption adjustment price; obtain all the prices to be adjusted and the absorption adjustment prices to form passenger flow guidance adjustment data.

[0020] In the present invention, a method for obtaining passenger flow guidance adjustment data is also provided. First, determine the passenger volume to be adjusted. Secondly, considering that the adjacent statistical time periods during the diversion of other normal passenger volume statistical time periods are more effective for diversion. After all, for the peak period, passengers' ticket changes basically occur in the adjacent front and back time periods of the target time period. Therefore, after determining the price adjustment amount of the time period to be adjusted according to the passenger volume to be adjusted and the passenger volume change function of the time period price adjustment, conduct sequential passenger volume diversion confirmation around the time period to be adjusted in the order of the time dimension. The confirmation method is to first go in the forward direction along the time dimension order. After all, generally passengers will handle ticket changes in advance, that is, change to an earlier date. And all the remaining absorbable passenger volumes need to be provided for each statistical time period in sequence, so as to absorb the passenger volume to be adjusted one by one. Of course, the price adjustment for the statistical time period can be determined based on the absorbed passenger volume and the passenger volume change function of the time period price adjustment.

[0021] As a possible implementation method, obtain the guiding peak period booking data of the target station, and combine it with the station capacity data for early warning analysis to form peak period guiding early warning data, including: determine the corresponding line guiding booking data on different lines according to the guiding peak period booking data of the target station; for different line guiding booking data, determine the line guiding booking volume corresponding to different statistical time periods; according to the simultaneous line time period price passenger volume change function F n (P, V, T k )、the price after guiding adjustment and the line guiding booking volume for early warning analysis to form peak period guiding early warning data.

[0022] In the present invention, of course, it is not possible to completely solve the situation of the mismatch between the peak period passenger volume and the transport capacity by relying on the passenger flow guidance adjustment data. Therefore, it is also necessary to determine whether the actual booking volume in the statistical time period exceeds the passenger volume data of the simultaneous line time period price passenger volume change function at the corresponding price. In order to provide reference data for subsequent passenger flow response processing for over-capacity.

[0023] As a possible implementation method, according to the simultaneous line time period price passenger volume change function F corresponding to different time periods of the line n (P, V, T k) Perform early warning analysis on the guided adjusted price and the ticket booking volume guided by the transportation line to form peak period guidance early warning data, including: for different transportation lines, if the ticket booking volume guided by the transportation line does not exceed the total passenger volume corresponding to the passenger transportation change function F n (P, V, T k ) at the guided adjusted price during the same period, it is determined that the corresponding transportation line is operating normally, and the normal operation information of the transportation line is formed; for different transportation lines, if there is any statistical period during which the ticket booking volume guided by the transportation line exceeds the total passenger volume corresponding to the passenger transportation change function F n (P, V, T k ) at the guided adjusted price during the same period, it is determined that the corresponding transportation line is operating in excess, and the over - volume early warning information of the transportation line is formed.

[0024] In the present invention, the early warning analysis mainly focuses on whether the ticket booking volume on different transportation lines exceeds the passenger volume data of the passenger transportation change function at the corresponding price during the same period of the transportation line time period. Since this analysis targets different transport capacities, it can more accurately determine the object with excessive passenger volume, that is, calibrate the over - standard transportation line, providing reference data for subsequent targeted adjustment of transport capacity.

[0025] In the second aspect, the present invention provides a peak - period passenger transportation organization optimization system based on big data, including: a data acquisition unit for obtaining historical peak - period passenger transportation data, current peak - period ticket booking data, and guided peak - period ticket booking data of the target station; a feature extraction unit for extracting features based on the historical peak - period passenger transportation data obtained by the data acquisition unit to form peak - period passenger transportation change feature data; a monitoring and early warning unit for obtaining the current peak - period ticket booking data obtained by the data acquisition unit, performing passenger flow guidance and adjustment in combination with the peak - period passenger transportation change feature data formed by the feature extraction unit to form passenger flow guidance and adjustment data, and performing early warning analysis on the guided peak - period ticket booking data obtained by the data acquisition unit after adjustment in combination with the peak - period passenger transportation change feature data to form peak - period guidance early warning data.

[0026] In the present invention, the system completes the acquisition of station historical data and current peak - period data through the data acquisition unit. The feature extraction unit fully realizes the extraction of historical big - data features, providing a reference data basis for the optimization of passenger transportation organization. The monitoring and early warning unit ensures that the current passenger volume is guided and adjusted in the most reasonable way. Multiple different units cooperate closely with each other to achieve efficient and reasonable optimization and adjustment of peak - period passenger transportation organization, which is an important position basis for completing the optimization of passenger transportation organization.

[0027] The beneficial effects of the peak - period passenger transportation organization optimization method and system based on big data provided by the present invention are:

[0028] This method extracts the characteristic information of the relationship between the passenger transport price and the passenger volume on different cloud lines from the historical passenger transport data of the station during the peak period, establishes the characteristic big data of the price and the passenger volume during the peak period, and then provides a comparison reference of big data for the passenger volume in the next peak period, judges the matching degree between the passenger volume during the peak period and the transport capacity of the station on the corresponding transport line, and adjusts the periods with low matching degree and large differences based on the price, so as to realize the adjustment of the passenger volume mainly based on the price change, change the passive acceptance of the increase in the passenger volume to the active adjustment of the passenger volume to match the transport capacity of the station. On the one hand, it greatly alleviates the passenger transport congestion during the peak period and avoids the increase in costs caused by passively accepting the change in the passenger volume. On the other hand, it fully caters to the market law, controls the volume with price, effectively ensures the matching of the station's transport capacity and the passenger volume, and also enables the efficient real-time monitoring of the cloud line's transport capacity and passenger volume situation, providing more timely and accurate data for subsequent real-time optimization.

[0029] This system completes the acquisition of the station's historical data and the current data during the peak period through the data acquisition unit. The feature extraction unit fully realizes the extraction of the features of the historical big data to provide a data basis for the optimization of passenger transport organization. The monitoring and early warning unit then ensures that the current passenger volume is guided and adjusted in the most reasonable way. Multiple different units cooperate closely with each other to achieve the efficient and reasonable optimization and adjustment of the passenger transport organization during the peak period, which is an important location basis for completing the optimization of passenger transport organization. Brief Description of the Drawings

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0031] Figure 1 It is a step diagram of the optimization method for peak-period passenger transport organization based on big data provided by the embodiments of the present invention;

[0032] Figure 2 It is a schematic structural diagram of the optimization system for peak-period passenger transport organization based on big data provided by the embodiments of the present invention. Detailed Embodiments

[0033] Next, the technical solutions in the embodiments of the present invention will be described in conjunction with the drawings in the embodiments of the present invention.

[0034] Transportation affects social development and is also an essential means of travel in your daily life. A station is the passenger service terminal where transportation vehicles pick up and drop off passengers. For different stations, due to the influence of geographical and human factors, there is a huge gap in the throughput of passenger volume. Especially during peak travel periods, some larger stations will face challenges in passenger transportation services.

[0035] Currently, in order to cope with the increase in passenger volume during peak periods, most stations use technologies such as artificial intelligence, big data, and the Internet of Things to achieve reasonable scheduling of transportation vehicles, thereby fully ensuring that the station has corresponding matching transport capacity. However, this method mainly passively meets the transport capacity requirements of the station by adjusting the transport capacity, and does not essentially eliminate the impact of peak periods on the transport capacity. In addition, the adjustment of transport capacity involves multiple aspects, and usually complicates the problem in terms of usage and operation costs and scheduling, and cannot effectively solve the problem of transport capacity adjustment during peak periods.

[0036] Reference Figure 1 - Figure 2 , the embodiment of the present invention provides an optimization method for peak - period passenger transportation organization based on big data. This method extracts characteristic information on the relationship between passenger transportation prices and passenger volume on different cloud lines from the historical passenger transportation data of the station during peak periods, establishes characteristic big data on prices and passenger volume during peak periods, and then provides a big - data comparison reference for the passenger volume of the next peak period, determines the matching degree between the passenger volume during peak periods and the transport capacity of the station on the corresponding cloud line, and makes price - based adjustments to the periods with low matching degree and large differences, realizes the adjustment of passenger volume mainly based on price changes, changes from passively accepting the increase in passenger volume to actively adjusting the passenger volume to match the transport capacity of the station. On the one hand, it greatly alleviates the congestion of passenger transportation during peak periods and avoids the increase in costs caused by passively accepting changes in passenger volume. On the other hand, it fully conforms to market rules, controls the volume with price, while effectively ensuring the matching of the transport capacity and passenger volume of the station, it also enables efficient real - time monitoring of the cloud - line transport capacity and passenger volume conditions, providing more timely and accurate data for subsequent real - time optimization.

[0037] The optimization method for peak - period passenger transportation organization based on big data specifically includes the following steps:

[0038] S1: Obtain the historical peak - period passenger transportation data of the target station, perform feature extraction based on price factors, and form peak - period passenger transportation change feature data.

[0039] Obtain the historical peak passenger volume data of the target station, perform feature extraction based on price factors, and form the peak passenger volume change feature data, including: according to the historical peak passenger volume data of the target station, extract the simultaneous line passenger volume change data and simultaneous line price change data of different lines under the same type of peak period; for different lines, according to the line passenger volume change data, determine the passenger volume change data of the target station on different lines within the peak periods of the same type but different times, and combine the corresponding simultaneous line price change data to perform price parameter mapping of the price per unit mileage of the line to form the simultaneous peak line price passenger volume change function; for different lines, perform passenger volume feature extraction of the same price for different simultaneous peak line price passenger volume change functions to form different simultaneous line period price passenger volume change data; for different lines, according to the corresponding simultaneous line period price passenger volume change data, perform guiding feature analysis of price factors to form line price guiding feature data.

[0040] Perform feature extraction based on price factors on the historical peak passenger volume data of the station, mainly considering two aspects. One is the corresponding relationship between price and passenger volume at different time periods within the peak period. This corresponding relationship not only reflects the change in the passenger volume controlled by the price, but also reflects the passenger volume change information under the peak period characteristics. The combination of these two aspects forms the passenger volume change data within the peak period under historical data. Of course, for the station, different people have different travel destinations, which determines that there are significant differences in the boarding volume of the station on different transport lines. Therefore, when extracting features, the situations of different lines need to be fully considered to avoid affecting the accuracy and rationality of big data analysis. Moreover, the passenger volume of the station changes significantly at different time periods. For example, during legal holidays, the passenger volumes on the first day, the middle day, and the last day of the holiday are different, and the influence of time factors on the passenger volume needs to be fully considered. On the other hand, it is necessary to establish the relationship between the influence degree of price on passenger volume. It can be understood that people's travel time is to a certain extent affected by price. Usually, when the price is higher, the passenger volume decreases, and when the price is lower, the passenger volume increases. Therefore, the influence of price on passenger volume needs to be fully considered. Since it is necessary to consider the influence of both time factors and price factors on passenger volume, in this way, in order to match the discreteness of time data, it is reasonable to establish a mutual relationship data between price data and passenger volume data with discrete time periods as a reference. For example, if there are multiple holidays during the peak period, then the first day of the holiday is the bottom-level time factor data. In addition, since the price factor plays an important role in optimizing passenger transport organization in this application, it is necessary to reflect the change influence of price data on the passenger volume to form important reference data for actively adjusting the passenger volume.

[0041] For different transport lines, extract the passenger volume characteristics at the same price from the passenger volume change functions of different peak transport lines in the same period, and form the passenger volume change data of different transport lines at different times and prices, including: divide the passenger volume of different peak transport lines in the same period according to the statistical period for the passenger volume change functions of different peak transport lines in the same period, and determine the total passenger volume in different statistical periods under each passenger volume change function of the peak transport lines in the same period; for the passenger volume change functions of different peak transport lines in the same period, cluster all statistical periods with the same price according to the price per unit mileage of the corresponding transport line in the statistical period, and determine the average passenger volume of the statistical period at the corresponding price per unit mileage of the transport line according to the total passenger volume corresponding to the clustered statistical period; establish the passenger volume change function F of the transport line at different times and prices in the same period according to the average passenger volume of different statistical periods corresponding to different prices n (P, V, T k ), where n represents the numbers of different transport lines, P is the price per unit mileage of the transport line, V represents the passenger volume of the transport line, T is the time period of the peak period, and k represents the numbers of different statistical periods under the time period of the peak period; aggregate the passenger volume change functions F of the transport lines at different times and prices in the same period corresponding to different statistical periods n (P, V, T k ) to form the passenger volume change data of the transport line corresponding to different times and prices in the same period.

[0042] For the same transportation line, the historical peak passenger volume data includes the passenger volume data of all different periods under the same peak period on the transportation line. Therefore, first, comprehensively process these data to express the relationship between passenger volume, price, and time period in big data. It can be understood that under the same statistical period, since the passenger volume data includes the corresponding data of each period, a data set corresponding to different prices and different passenger volumes will be formed under this statistical period. Of course, due to the huge amount of big data, there will also be data with the same price. Here, it should be noted that since a small change in price will not cause a substantial change in passenger volume, the understanding of the same price here is that a price group within a certain fluctuation range can be considered the same price. Of course, for the booking price, basically, the price adjustment is relatively large, so different groups of the same price can be quickly identified. Similarly, there will also be fluctuations in the passenger volume corresponding to the same price. Therefore, for each statistical period, the average price of the price group is used as the reference price value for analysis, and the average value of all passenger volumes corresponding to the price group is used as the effective passenger volume reference value corresponding to this price group, so as to establish a reasonable relationship data between price and passenger volume. In addition, for price data, it is not the booking price of each passenger. Considering that no matter which station on the same transportation line a passenger arrives at, they will board the vehicle from the target station, it is not reasonable to use the booking price as the price data on the transportation line. Different arrival stations will have different prices, so converting the booking price into the price per unit mileage on the transportation line can better represent the price data information of the transportation line. Although there are different price data in the same statistical period, the sample data itself has discreteness, so the relationship data between the formed price change data and passenger volume is also discrete statistical data. In order to ensure that the subsequent price adjustment can perform reasonable curve fitting after obtaining the data and then form the relationship data between the continuous change of passenger volume corresponding to the continuous change of price data, there are various ways of curve fitting, which can be least squares, polynomial fitting, etc.

[0043] For different transportation lines, according to the corresponding price-passenger volume change data of the transportation line period in the same period, conduct an analysis of the guiding characteristics of price factors to form transportation line price guiding characteristic data, including: for the different price-passenger volume change functions F of the transportation line period in the same period n (P, V, T k ), determine the price change value and the corresponding passenger volume change value of adjacent pricing; arrange the different price change values in ascending order, and based on the corresponding passenger volume change values, establish the period price adjustment passenger volume change function W of the corresponding statistical period k (U), where U represents the price change value and W represents the passenger volume change value; collect the period price adjustment passenger volume change functions W corresponding to different statistical periods k(U), form the operation line price guidance feature data.

[0044] The purpose of big data feature analysis is to estimate the passenger volume corresponding to the price data during the subsequent peak period based on big data feature information, and at the same time adjust the real-time booking price based on the passenger volume feature information corresponding to different prices, thereby guiding the passenger volume to match the transport capacity and change. Therefore, it is necessary to extract the feature of the relationship between the change in passenger volume caused by the change in price from the passenger volume change data obtained from big data. Considering that the price-volume change function of the operation line period in the same period is fitted based on the obtained discrete data, and the discrete data has the property of relative authenticity. Therefore, when analyzing and extracting the relationship between the change in passenger volume caused by the change in price, only analyze the collected discrete data, obtain the price change value and the corresponding passenger volume change value for adjacent prices, sort according to the magnitude relationship of the price change values, establish the sorted data of the change in passenger volume caused by the sequential change in the price change amount, and then obtain the feature data of the relationship between the price change value and the passenger volume change value on the basis of reasonable fitting analysis, providing important guiding reference data for subsequent price adjustment to match the transport capacity of the station.

[0045] S2: Collect the current peak period booking data of the target station, and combine it with the peak period passenger transport change feature data to conduct passenger flow guidance adjustment based on price factors, forming passenger flow guidance adjustment data.

[0046] Collect the current peak period booking data of the target station, and combine it with the peak period passenger transport change feature data to conduct passenger flow guidance adjustment based on price factors, forming passenger flow guidance adjustment data, including: collecting the current peak period booking data before the peak period, and respectively extracting the current booking data of different operation lines; for the current booking data of different operation lines, determine the current period price of the operation line corresponding to different statistical periods and the corresponding current period booking volume of the operation line; according to the current period price of the operation line corresponding to the statistical period, combine the price-volume change function F of the operation line in the same statistical period at the same time n (P, V, T k ) to conduct the following analysis: If the current period booking volume of the operation line does not exceed the product of the total passenger volume value corresponding to the price-volume change function F of the operation line period in the same period and the passenger flow limit ratio at the current period price of the operation line, it is determined that the statistical period is in a normal passenger flow state under the current situation; if the current period booking volume of the operation line exceeds the price-volume change function F of the operation line period in the same period at the current period price of the operation line n (P, V, T k ) n (P, V, T k) If the product of the total passenger volume value corresponding to the above and the passenger flow limit ratio is obtained, it is determined that the statistical period is in an abnormal passenger flow state under the current situation; for all statistical periods determined to be in an abnormal passenger flow state, the passenger flow guidance adjustment of price factors is combined with the corresponding line price guidance characteristic data to form passenger flow guidance adjustment data.

[0047] The current peak-period ticket-booking data can be obtained at an appropriate time point after opening the ticket-booking channel of the target station and before the peak period arrives. Obtaining it too early will result in untrue extraction of passenger volume data, and obtaining it too late will cause no obvious passenger flow guidance in subsequent price adjustments. Therefore, through analysis of historical data, the time point can be determined such that after collecting this data at the latest, the price can still be adjusted to significantly satisfy the functional relationship between the passenger volume change in the time period of price adjustment. Of course, whether the current peak-period ticket-booking data reaches the passenger volume data of the corresponding price in the passenger volume change function of the line time period price in the same period for each statistical period determines whether there will be a situation of insufficient transport capacity in this statistical period. However, when making an analysis and judgment, it cannot be directly compared with the passenger volume data of the corresponding price in the passenger volume change function of the line time period price in the same period. After all, the time point for collecting the current peak-period ticket-booking data is not within the statistical time period, and there is still a period of time before reaching the corresponding statistical period, and there will inevitably be an increase in passenger volume during this period. Therefore, for reasonable guidance, an early prediction and judgment are required. So, it should be determined whether the passenger volume provided by the ticket-booking data is close to the passenger volume data of the corresponding price in the passenger volume change function of the line time period price in the same period. If so, there is a risk that the passenger volume will exceed the transport capacity at the statistical period. Furthermore, it is necessary to consider adjusting the ticket price in advance to guide passengers who have planned or already booked tickets during the statistical period to change their tickets or rebook to other statistical periods with sufficient remaining transport capacity. Here, the passenger flow limit ratio can be determined according to the actual situation or based on big data analysis.

[0048] For all statistical periods determined to be in an abnormal passenger flow state, the passenger flow guidance adjustment of price factors is combined with the corresponding line price guidance characteristic data to form passenger flow guidance adjustment data, including: marking the statistical periods determined to be in an abnormal passenger flow state as periods to be adjusted, and determining the passenger flow volume exceeding the product of the total passenger volume value corresponding to the passenger volume change function F of the line time period price in the same period for the periods to be adjusted n (P, V, T k ) and the passenger flow limit ratio, and recording it as the passenger volume q to be adjusted adj ; for other statistical periods except the periods to be adjusted, determining the passenger flow volume not exceeding the product of the total passenger volume value corresponding to the passenger volume change function F of the line time period price in the same period for the statistical periods n (P, V, T k ) and the passenger flow limit ratio, and recording it as the passenger volume q to be absorbed in the periodabs ; According to the passenger volume to be adjusted in the time period to be adjusted and the passenger volume to be absorbed in the statistical time period, the following methods are used for passenger flow guidance and adjustment: If the sum of the passenger volumes q ddj to be adjusted in all time periods to be adjusted is not greater than the sum of the passenger volumes q abs to be absorbed in all time periods, then according to the passenger volume change function W k (U) corresponding to the time period to be adjusted and the passenger volume q adj to be adjusted, the prices to be adjusted corresponding to different time periods to be adjusted are determined, and the passenger volume q adj to be adjusted is evenly distributed to other statistical time periods, and the absorption adjustment prices are determined according to the passenger volume change function W k (U) corresponding to the corresponding time period prices; If the sum of the passenger volumes q adj to be adjusted in all time periods to be adjusted is greater than the sum of the passenger volumes q abs to be absorbed in all time periods, then according to the passenger volume change function W k (U) corresponding to the time period to be adjusted and the passenger volume q adj to be adjusted, the prices to be adjusted corresponding to different time periods to be adjusted are determined, and for other statistical time periods, the absorption adjustment prices are determined according to the passenger volume change function W k (U) corresponding to the corresponding time period prices and the passenger volume q abs to be absorbed in the time period; Obtain all the prices to be adjusted and the absorption adjustment prices to form passenger flow guidance and adjustment data.

[0049] When in the upcoming peak period, there is a situation where the passenger volume data of a statistical time period has exceeded the passenger volume data of the passenger volume change function of the transport line time period price at the corresponding price, the price adjustment method adopted is to determine the excess passenger volume, and use this passenger volume as a reference to take the unsaturated transport capacity of other statistical time periods as the object of guidance. By evenly distributing the excess passenger volume to other statistical time periods where the passenger volume has not exceeded, the increased passenger volume that needs to be added to the corresponding statistical time periods is determined, and then according to this increased passenger volume value, the price adjustment amount is determined in the passenger volume change function of the time period price to adjust the price of the corresponding statistical time period. For the excess passenger volume, the corresponding price to be adjusted is determined according to the passenger volume change function of the time period price. Finally, the passenger flow guidance and adjustment data corresponding to the situation where the transport capacity on the transport line cannot match during the peak period is formed to achieve the purpose of reasonable and efficient price diversion.

[0050] For all statistical time periods determined to be in an abnormal passenger volume state, combined with the corresponding transport line price guidance characteristic data, passenger flow guidance and adjustment for price factors are carried out to form passenger flow guidance and adjustment data, including: Marking the statistical time periods determined to be in an abnormal passenger volume state as time periods to be adjusted, and determining the relative passenger volume change function F of the time periods to be adjusted with respect to the transport line time period price in the same period.n (P, V, T k ) The passenger flow that exceeds the product of the total passenger volume value corresponding to it and the passenger flow limit ratio is recorded as the passenger volume to be adjusted q naj ; For other statistical periods except the period to be adjusted, determine the passenger flow change function F of the statistical period relative to the price of the operation line period in the same period n (P, V, T k ) The passenger flow that does not exceed the product of the total passenger volume value corresponding to it and the passenger flow limit ratio is recorded as the passenger volume to be absorbed in the period q abs ; According to the passenger volume to be adjusted in the period to be adjusted and the passenger volume to be absorbed in the statistical period, conduct the following passenger flow guidance and adjustment: If the sum of the passenger volumes to be adjusted q ddj in all periods to be adjusted is not greater than the sum of the passenger volumes to be absorbed q abs in all periods, then determine the prices to be adjusted corresponding to different periods to be adjusted according to the passenger volume change function W k (U) and the passenger volume to be adjusted q adj ; Select the statistical periods in turn in the order of the time dimension direction with the period to be adjusted as the benchmark. According to the passenger volume to be absorbed q abs in the statistical period, cover the passenger volume to be adjusted q adj until the sum of the passenger volumes to be absorbed q abs in all selected statistical periods is greater than the sum of the passenger volumes to be adjusted q adj ; And when selecting the statistical periods in turn in the order of the time dimension direction, take the forward time dimension direction as the first selected direction until all the statistical periods in the direction are obtained and the passenger volume to be adjusted q adj is not covered yet. Then take the backward time dimension direction as the selected direction to continue obtaining the statistical periods until the sum of the passenger volumes to be absorbed q abs in all selected statistical periods is greater than the sum of the passenger volumes to be adjusted q adj ; For the selected statistical periods, determine the corresponding absorption and adjustment prices in turn according to the corresponding passenger volume change function W k (U) and the passenger volume to be absorbed q abs in the period. For the last selected statistical period, determine the corresponding absorption and adjustment price according to the remaining passenger volume to be adjusted q adj and the corresponding passenger volume change function W k (U); If the sum of the passenger volumes to be adjusted q adj in all periods to be adjusted is greater than the sum of the passenger volumes to be absorbed q abs in all periods, then according to the passenger volume change function W corresponding to the period to be adjustedk (U) and the passenger volume q to be adjusted naj Determine the prices to be adjusted corresponding to different periods to be adjusted, and adjust the passenger volume change function W according to the corresponding period prices for other statistical periods k (U) and the passenger volume q to be absorbed in the period abs Determine the corresponding absorption adjustment prices; obtain all the prices to be adjusted and absorption adjustment prices to form passenger flow guidance adjustment data

[0051] A method for obtaining passenger flow guidance adjustment data is also provided. First, determine the passenger volume to be adjusted. Secondly, considering that among the statistical periods of other normal passenger volume situations, these adjacent statistical time periods during the diversion have better diversion effects. After all, for the peak period, passengers basically change their tickets in the adjacent time periods before and after the target time period. Therefore, after determining the price adjustment amount of the period to be adjusted according to the passenger volume to be adjusted and the passenger volume change function adjusted by the period price, conduct sequential passenger volume diversion confirmation around the period to be adjusted in the order of the time dimension. The confirmation method is to first go in the direction along the time dimension forward. After all, generally passengers will handle the ticket change in advance, that is, change the ticket to an earlier date. And all the remaining absorbable passenger volumes need to be provided for each statistical period in turn, so as to absorb the passenger volume to be adjusted one by one. Of course, the price adjustment for the statistical period can be determined based on the absorbed passenger volume and the passenger volume change function adjusted by the period price

[0052] S3: Obtain the guided peak period ticket booking data of the target station, and conduct early warning analysis in combination with the station capacity data to form peak period guidance early warning data

[0053] Obtain the guided peak period ticket booking data of the target station, and conduct early warning analysis in combination with the station capacity data to form peak period guidance early warning data, including: according to the guided peak period ticket booking data of the target station, determine the corresponding line-guided ticket booking data on different lines; for different line-guided ticket booking data, determine the line-guided ticket booking volumes corresponding to different statistical periods; according to the simultaneous period line period price passenger volume change function F n (P, V, T k )), the adjusted price after guidance, and the line-guided ticket booking volume for early warning analysis to form peak period guidance early warning data

[0054] Of course, it is not possible to completely solve the mismatch between the peak period passenger volume and the capacity by relying on the passenger flow guidance adjustment data. Therefore, it is also necessary to determine whether the actual ticket booking volume in the statistical period exceeds the passenger volume data of the simultaneous period line period price passenger volume change function at the corresponding price. So as to provide reference data for subsequent passenger flow response processing for overcapacity

[0055] According to the passenger volume change function F of the same period corresponding to different time periods of the transportation line n (P, V, T k ), the adjusted price and the guided booking volume of the transportation line are used for early warning analysis to form peak period guidance early warning data, including: for different transportation lines, if the guided booking volume of the transportation line does not exceed the total passenger volume corresponding to the passenger volume change function F of the same period of the transportation line at the adjusted price during all statistical time periods n (P, V, T k ), it is determined that the corresponding transportation line operates normally, and normal operation information of the transportation line is formed; for different transportation lines, if there is any statistical time period during which the guided booking volume of the transportation line exceeds the total passenger volume corresponding to the passenger volume change function F of the same period of the transportation line at the adjusted price n (P, V, T k ), it is determined that the corresponding transportation line operates in excess, and over - quantity early warning information of the transportation line is formed.

[0056] The early warning analysis mainly focuses on whether the booking volume on different transportation lines exceeds the passenger volume data corresponding to the passenger volume change function of the same period of the transportation line at the corresponding price. Since this analysis targets different transport capacities, it can more accurately determine the object with excessive passenger volume, that is, calibrate the over - standard transportation lines, providing reference data for subsequent targeted adjustment of transport capacity.

[0057] The present invention also provides a peak - period passenger transport organization optimization system based on big data. The system includes: a data acquisition unit for obtaining historical peak - period passenger transport data, current peak - period booking data, and guided peak - period booking data of a target station; a feature extraction unit for extracting features based on the historical peak - period passenger transport data obtained by the data acquisition unit to form peak - period passenger volume change feature data; a monitoring and early warning unit for obtaining the current peak - period booking data obtained by the data acquisition unit, combining the peak - period passenger volume change feature data formed by the feature extraction unit to perform passenger flow guidance adjustment to form passenger flow guidance adjustment data, and performing early warning analysis on the guided peak - period booking data obtained by the data acquisition unit after adjustment in combination with the peak - period passenger volume change feature data to form peak - period guidance early warning data.

[0058] The system completes the acquisition of station historical data and current peak - period data through the data acquisition unit. The feature extraction unit fully realizes the extraction of historical big - data features, providing a data basis for the optimization of passenger transport organization. The monitoring and early warning unit ensures that the current passenger volume is guided and adjusted in the most reasonable way. Multiple different units cooperate closely with each other to achieve efficient and reasonable optimization and adjustment of peak - period passenger transport organization, which is an important position basis for completing the optimization of passenger transport organization.

[0059] In summary, the beneficial effects of the method and system for optimizing peak-period passenger transport organization based on big data provided by the embodiments of the present invention are as follows:

[0060] By extracting the characteristic information of the relationship between passenger transport prices and passenger volumes on different cloud lines from the historical passenger transport data of stations during peak periods, this method establishes the characteristic big data of prices and passenger volumes during peak periods, and then provides a big data comparison reference for the passenger volume in the next peak period, determines the matching degree between the passenger volume during peak periods and the transport capacity of the station on the corresponding transport line, and makes price-based adjustments to the periods with low matching degree and large differences, realizing the adjustment of passenger volume mainly based on price changes, changing the passive acceptance of the increase in passenger volume to actively adjusting the passenger volume to match the transport capacity of the station. On the one hand, it greatly alleviates the congestion degree of passenger transport during peak periods and avoids the increase in costs caused by passive acceptance of changes in passenger volume. On the other hand, it fully caters to the market law, controls the volume with price, effectively ensures the matching of the transport capacity of the station and the passenger volume, and also enables the efficient real-time monitoring of the transport capacity and passenger volume of the cloud line, providing more timely and accurate data for subsequent real-time optimization.

[0061] This system obtains the historical data of the station and the current data during peak periods through the data acquisition unit. The feature extraction unit fully realizes the extraction of the features of historical big data to provide a data basis for the optimization of passenger transport organization. The monitoring and early warning unit ensures the guidance and adjustment of the current passenger volume in the most reasonable way. Multiple different units cooperate closely with each other to achieve efficient and reasonable optimization and adjustment of peak-period passenger transport organization, which is an important position basis for completing the optimization of passenger transport organization.

[0062] In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain piece of information is called the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated. For example, but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated, etc. It is also possible to indirectly indicate the information to be indicated by indicating other information, where there is an association relationship between the other information and the information to be indicated. It is also possible to only indicate a part of the information to be indicated, while the other parts of the information to be indicated are known or pre-agreed. For example, it is also possible to realize the indication of specific information by relying on the arrangement order of each piece of information pre-agreed (such as protocol regulations), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each piece of information can be identified and indicated uniformly to reduce the indication overhead caused by separately indicating the same information.

[0063] In addition, the specific indication method can also be various existing indication methods, such as, but not limited to, the above-mentioned indication methods and their various combinations, etc. The specific details of various indication methods can refer to the prior art and will not be elaborated herein. As can be seen from the above description, for example, when multiple pieces of information of the same type need to be indicated, it may occur that the indication methods of different pieces of information are different. In the specific implementation process, the required indication method can be selected according to specific needs, and the embodiments of the present application do not limit the selected indication method. In this way, the indication methods involved in the embodiments of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0064] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending periods and / or sending times of these sub-information can be the same or different. The embodiments of the present application do not limit the specific sending method. Among them, the sending periods and / or sending times of these sub-information can be predefined, such as predefined according to a protocol, or can be configured by the sending device by sending configuration information to the receiving device.

[0065] "Predefined" or "pre-configured" can be implemented by pre-saving corresponding codes, tables or other ways that can be used to indicate relevant information in the device, and the embodiments of the present application do not limit its specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be separately provided, or can be integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partly separately provided and partly integrated in a decoder, a processor, or a communication device. The type of the memory can be any form of storage medium, and the embodiments of the present application do not limit this.

[0066] The "protocol" involved in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol with a frame structure similar to that of a protocol family, or a relevant protocol applied to a future communication system. The embodiments of the present application do not make specific limitations on this.

[0067] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if", and "when" all refer to that the device will perform corresponding processing under a certain objective situation, which does not limit the time, and does not require the device to have a judgment action when implementing, nor does it mean that there are other limitations.

[0068] In the description of the embodiments of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or its similar expression refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solution of the embodiments of the present application, in the embodiments of the present application, the words "first" and "second" are used to distinguish the same or similar items with basically the same functions and effects. Those skilled in the art will appreciate that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0069] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0070] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0071] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0072] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship. The specific meaning can be understood by referring to the context.

[0073] In the present application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0074] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0075] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0076] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0077] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0078] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0080] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0081] As described above, the above are only specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An optimization method for peak-period passenger transport organization based on big data, characterized in that, Including: Obtain the historical peak passenger transport data of the target station, perform feature extraction based on price factors, and form peak passenger transport change feature data; Collect the current peak booking data of the target station, and combine the peak passenger transport change feature data to perform passenger flow guidance adjustment based on price factors to form passenger flow guidance adjustment data; Obtain the guided peak booking data of the target station, and combine the station capacity data to perform early warning analysis to form peak period guidance early warning data.

2. The optimization method for peak passenger transport organization based on big data according to claim 1, characterized in that The obtaining of the historical peak passenger transport data of the target station, performing feature extraction based on price factors, and forming peak passenger transport change feature data includes: According to the historical peak passenger transport data of the target station, extract the simultaneous period line passenger volume change data and simultaneous period line price change data of different lines under the same type of peak period; For different lines, according to the line passenger volume change data, determine the passenger volume change data of the target station on different lines within the same type of different periods of the peak period, and perform price parameter mapping of the price per unit mileage of the line in combination with the corresponding simultaneous period line price change data to form a simultaneous period peak line price passenger volume change function; For different lines, perform passenger volume feature extraction at the same price for different simultaneous period peak line price passenger volume change functions to form different simultaneous period line time period price passenger volume change data; For different lines, according to the corresponding simultaneous period line time period price passenger volume change data, perform guidance feature analysis of price factors to form line price guidance feature data.

3. The optimization method for peak-period passenger transport organization based on big data according to claim 2, wherein The performing of passenger volume feature extraction at the same price for different simultaneous period peak line price passenger volume change functions for different lines to form different simultaneous period line time period price passenger volume change data includes: Perform passenger volume division based on the statistical time period for different simultaneous period peak line price passenger volume change functions to determine the total passenger volume of different statistical time periods under each simultaneous period peak line price passenger volume change function; For different simultaneous period peak line price passenger volume change functions, cluster all statistical time periods with the same price according to the price per unit mileage of the line corresponding to the statistical time period, and determine the average passenger volume of the time period corresponding to the clustered statistical time period under the corresponding price per unit mileage of the line; Based on the average total passenger volume corresponding to different prices during different statistical periods, establish a function F for the change in passenger volume with respect to the price and time period of the transportation line during the same period n (P, V, T k ), where n represents the number of different transportation lines, P is the price per unit mileage of the transportation line, V represents the passenger volume of the transportation line, T is the time period of the peak period, and k represents the number of different statistical periods under the time period of the peak period; Aggregate the function F of the price and passenger volume changes during the same-period operating line time periods corresponding to different said statistical time periods n (P, V, T k ), to form the data of the price and passenger volume changes during the same-period operating line time periods corresponding to the operating line.

4. The method for optimizing peak passenger transport organization based on big data according to claim 3, wherein, The performing of guidance feature analysis of price factors for different lines according to the corresponding simultaneous period line time period price passenger volume change data to form line price guidance feature data includes: For different simultaneous route period price passenger volume change functions F of the simultaneous route period price passenger volume change data during the same period, n (P, V, T k ), determine the price change value between adjacent pricing and the corresponding passenger volume change value; Arrange the different price change values in ascending order, and establish the time period price adjustment passenger volume change function W corresponding to the statistical period according to the corresponding passenger volume change values k (U), where U represents the price change value and W represents the passenger volume change value; Aggregate the period price-adjusted passenger volume change functions W corresponding to different statistical periods to form the route price guidance characteristic data. k (U).

5. The optimization method for peak-period passenger transportation organization based on big data according to claim 4, wherein The collecting of the current peak booking data of the target station, and combining the peak passenger transport change feature data to perform passenger flow guidance adjustment based on price factors to form passenger flow guidance adjustment data includes: Collect the current peak booking data before the peak period, and respectively extract the current booking data of different lines; For different current booking data of the lines, determine the current line price and the corresponding current booking volume of the line for different statistical time periods; Based on the current period price of the transportation line corresponding to the statistical period, combined with the passenger transportation change function F of the corresponding transportation line at the same statistical period n (P, V, T k ) for the following analysis: If, at the price of the current period of the transportation line, the ticket booking volume of the current period of the transportation line does not exceed the product of the total passenger volume value corresponding to the passenger volume change function F n (P, V, T k ) at the same period of the transportation line and the passenger flow limit ratio, it is determined that the statistical period is in a normal passenger flow state under the current situation; If, at the current period price of the transportation line, the ticket booking volume for the current period of the transportation line exceeds the product of the total passenger volume value corresponding to the passenger transport change function F n (P, V, T k ) at the same time period of the transportation line and the passenger flow limit ratio, it is determined that the statistical period is in a state of abnormal passenger flow under the current situation; For all the statistical periods determined to be in the abnormal passenger flow state, combine the corresponding route price guidance characteristic data to conduct passenger flow guidance adjustment for price factors, and form passenger flow guidance adjustment data.

6. The optimization method for peak-period passenger transport organization based on big data according to claim 5, wherein, The step of, for all the statistical periods determined to be in the abnormal passenger flow state, combining the corresponding route price guidance characteristic data to conduct passenger flow guidance adjustment for price factors and form passenger flow guidance adjustment data includes: Calibrate the statistical period determined as the abnormal passenger flow state as the period to be adjusted, and determine the passenger transport change function F of the period to be adjusted relative to the same-period transport line period price n (P, V, T k ) corresponding to the product of the total passenger volume value and the passenger flow limit ratio that exceeds the passenger flow, and record it as the passenger volume q to be adjusted adj ; For other statistical periods except the period to be adjusted, determine the passenger volume change function F of the statistical period relative to the price of the same-period operation line period n (P, V, T k ) corresponding to the product of the total passenger volume value and the passenger flow limit ratio that does not exceed the passenger flow volume, and record it as the passenger volume to be absorbed in the period q abs ; According to the passenger volume to be adjusted in the period to be adjusted and the passenger volume to be absorbed in the statistical period, conduct passenger flow guidance adjustment in the following manner: If the sum of the passenger volumes q to be adjusted during all the said time periods to be adjusted adj is not greater than the sum of the passenger volumes q to be absorbed during all the said time periods abs , then according to the passenger volume change function W k (U) corresponding to the time periods to be adjusted and the passenger volumes q to be adjusted adj , the prices to be adjusted corresponding to different time periods to be adjusted are determined, and the passenger volumes q to be adjusted adj are evenly distributed to the other said statistical time periods, and the absorption adjustment prices corresponding thereto are determined according to the passenger volume change function W k (U); If the sum of the passenger volumes q to be adjusted during all the periods to be adjusted adj is greater than the sum of the passenger volumes q to be absorbed during all the periods abs , then, according to the passenger volume change function W k (U) corresponding to the periods to be adjusted and the passenger volumes q to be adjusted adj , determine the prices to be adjusted for different periods to be adjusted, and for other statistical periods, according to the passenger volume change function W k (U) corresponding to the periods and the passenger volumes q to be absorbed during the periods abs determine the corresponding absorption adjustment prices; Obtain all the prices to be adjusted and the absorption adjustment prices to form the passenger flow guidance adjustment data.

7. The optimization method for peak-period passenger transport organization based on big data according to claim 5, characterized in that The step of, for all the statistical periods determined to be in the abnormal passenger flow state, combining the corresponding route price guidance characteristic data to conduct passenger flow guidance adjustment for price factors and form passenger flow guidance adjustment data includes: Calibrate the statistical period determined as the abnormal passenger flow state as the period to be adjusted, and determine the passenger transport change function F of the period to be adjusted relative to the same-period transport line period price n (P, V, T k ) corresponding to the product of the total passenger volume value and the passenger flow limit ratio that exceeds, and record it as the passenger volume q to be adjusted adj ; For other statistical periods except the period to be adjusted, determine the passenger volume change function F of the statistical period relative to the price of the same-period operation line period n (P, V, T k ) corresponding to the product of the total passenger volume value and the passenger flow limit ratio that does not exceed the passenger flow volume, and record it as the passenger volume q to be absorbed in the period abs ; According to the passenger volume to be adjusted in the period to be adjusted and the passenger volume to be absorbed in the statistical period, conduct passenger flow guidance adjustment in the following manner: If the sum of the to-be-adjusted passenger volumes q for all the to-be-adjusted time periods adj is not greater than the sum of the to-be-absorbed passenger volumes q for all the time periods abs then, according to the time period price adjustment passenger volume change function W k (U) corresponding to the to-be-adjusted time periods and the to-be-adjusted passenger volume q adj the to-be-adjusted prices corresponding to different to-be-adjusted time periods are determined, and price adjustment selections are made for the other statistical time periods in the following manner; Taking the to-be-adjusted time period as a reference, sequentially select the statistical time periods in the order of the time dimension direction, and according to the passenger volume q to be absorbed in the statistical time period abs For the passenger volume q to be adjusted adj Perform coverage until the sum of the passenger volumes q to be absorbed in all the selected statistical time periods abs is greater than the sum of the passenger volumes q to be adjusted adj sum; When sequentially selecting the statistical periods in the order of the time dimension direction, the forward time dimension direction is the first selected direction until all the statistical periods in the direction are obtained. If the adjusted passenger volume q has not been covered adj , then the backward time dimension direction is used as the selection direction to continue obtaining the statistical periods until the sum of the passenger volumes q to be absorbed in the periods of all the selected statistical periods abs is greater than the passenger volume q to be adjusted adj sum; Based on the selected order for the selected statistical time period, sequentially adjust the passenger volume change function W according to the corresponding time period price k (U) and the passenger volume q to be absorbed during the time period abs Determine the corresponding absorption adjustment price. For the last selected statistical time period, according to the remaining adjusted passenger volume q adj and the corresponding passenger volume change function W of the time period k (U) determine the corresponding absorption adjustment price; If the sum of the passenger volumes q to be adjusted during all the periods to be adjusted adj is greater than the sum of the passenger volumes q to be absorbed during all the periods abs then, based on the passenger volume change function W k (U) corresponding to the periods to be adjusted and the passenger volumes q to be adjusted adj determine the prices to be adjusted for the different periods to be adjusted, and for the other statistical periods, based on the passenger volume change function W k (U) corresponding to the periods and the passenger volumes q to be absorbed during the periods abs determine the corresponding absorption adjustment prices; Obtain all the prices to be adjusted and the absorption adjustment prices to form the passenger flow guidance adjustment data.

8. The optimization method for peak-period passenger transport organization based on big data according to claim 5, characterized in that, The step of obtaining the booking data during the peak guidance period of the target station and combining it with the station capacity data for early warning analysis to form peak period guidance early warning data includes: According to the booking data during the peak guidance period of the target station, determine the corresponding route guidance booking data on different routes; For different route guidance booking data, determine the corresponding route guidance booking volumes in different statistical periods; According to the function F of the passenger transport change of the simultaneous line operation period price corresponding to different periods of the operation line n (P, V, T k ), the price after guidance adjustment and the guided booking volume of the operation line are used for early warning analysis to form the early warning data for guidance during the peak period.

9. The method for optimizing peak passenger transportation organization based on big data according to claim 8, wherein The simultaneous period line period price passenger transport change function F corresponding to different periods of the line n (P, V, T k ) is used to perform early warning analysis on the adjusted price and the ticket booking volume guided by the line, and form the peak period guided early warning data, including: For different transport lines, if during all the said statistical periods, the ticket booking volume guided by the transport line does not exceed the total passenger volume corresponding to the transport line period price passenger transport change function F n (P, V, T k ) at the corresponding adjusted guided price, it is determined that the corresponding transport line is operating normally, and normal operation information of the transport line is formed; For different transportation lines, if there is any of the said statistical periods in which the ticket booking volume guided by the transportation line exceeds the total passenger volume corresponding to the passenger transport change function F of the transportation line period price during the same period n (P, V, T k ) at the corresponding total passenger volume at the guided adjusted price, it is determined that the corresponding transportation line is operating in excess, and an early warning information of transportation line excess is formed.

10. The peak passenger transport organization optimization system based on big data adopts the peak passenger transport organization optimization method based on big data described in any one of claims 1-9, characterized in that, including: A data acquisition unit for obtaining the historical peak period passenger data, current peak period booking data, and booking data during the peak guidance period of the target station; A feature extraction unit for extracting features based on the historical peak period passenger data obtained by the data acquisition unit to form peak period passenger volume change feature data; A monitoring and early warning unit for obtaining the current peak period booking data obtained by the data acquisition unit, combining the peak period passenger volume change feature data formed by the feature extraction unit to conduct passenger flow guidance adjustment to form passenger flow guidance adjustment data, and conducting early warning analysis on the booking data during the peak guidance period obtained by the data acquisition unit after adjustment in combination with the peak period passenger volume change feature data to form peak period guidance early warning data.

Images