Railway intelligent operation management scheduling plan generation method and system

Abstract

The invention discloses a railway intelligent operation management scheduling plan generation method and system, relates to the technical field of railway operation, solves the problem that the utilization rate of seats in train carriages is unbalanced, and comprises a train marking and historical data collection module used for setting ticket classification rules; the ticket classification and initial seat distribution setting module is used for setting an initial seat distribution rule and dividing middle and end positions; the ticket selling data statistics and analysis module is used for collecting selling data, marking stations, counting the number of tickets sold at the stations and analyzing the ratio of short-distance tickets to long-distance tickets. The seat distribution adjustment and optimization module is used for comprehensively analyzing the adjustment deviation of the middle and end positions; according to the method, the automation and precision of ticket classification, seat distribution setting and dynamic adjustment are realized through an intelligent means, the balance of the train seat utilization rate is improved, the comfort experience of passengers is improved, and the railway operation efficiency is also optimized.

Description

Technical Field

[0001] The present invention relates to the field of railway operation technology, and more specifically, to a method and system for generating a railway intelligent operation management scheduling plan. Background Art

[0002] With the rapid development of railway transportation, railway operations management is becoming increasingly complex and challenging. Traditional methods for generating railway operations management scheduling plans often rely on manual experience and analysis of historical data. This approach is not only inefficient but also difficult to accurately predict and meet the diverse needs of passengers. In particular, traditional methods lack intelligent and automated means for ticket classification, seat distribution, and dynamic adjustment. This results in low train seat utilization, poor passenger comfort, and difficulty improving railway operational efficiency. To address these issues, existing technologies have begun to introduce computer technology and data analysis methods to optimize railway operations management scheduling plans.

[0003] However, most of these methods are still in their infancy and have many shortcomings. For example, the seat distribution setting lacks a scientific basis, resulting in uneven seat utilization within the carriage; the dynamic adjustment strategy is not flexible and intelligent enough, making it difficult to respond to changes in passenger demand in a timely manner, resulting in a low passenger comfort experience. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for generating a railway intelligent operation management scheduling plan to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for generating a railway intelligent operation management scheduling plan comprises the following steps: S1, marking trains on different routes differently, collecting historical traffic of trains with different markings, counting the number of occupied seats on the trains and calculating the occupancy rate of the marked trains, and setting ticket classification rules based on the historical traffic and historical occupancy rate of trains with different markings; S2, classifying tickets into short-distance tickets and long-distance tickets according to the ticket classification rules, setting initial seat distribution rules for train carriages according to the proportion of short-distance tickets and long-distance tickets in the total number of train tickets and the comfort level of carriage positions, and dividing the middle position and end position of seats according to the initial seat distribution rules; S3, collecting sales data of short-distance tickets and long-distance tickets on trains that have been put on sale, marking each station on the train differently, counting the number of station tickets sold with different marked stations as destinations, and analyzing the proportion of short-distance tickets and long-distance tickets sold at the marked stations in the number of station tickets sold; S4, comprehensively analyzing the adjustment bias of the middle position and end position of different marked stations based on the change in the distance from the ticket sales stop time and the proportion of short-distance tickets and long-distance tickets sold at the marked stations in the number of station tickets sold.

[0007] In a preferred embodiment, the number of passengers at different stations is obtained based on the historical traffic of different stations, and the number of passengers at each station of the train is counted and added and then divided by the number of stations to obtain the average passenger volume; the historical occupancy rate is calculated as follows: The historical number of tickets sold indicates the number of tickets sold between one station and another. The historical number of tickets sold is obtained from the ticketing system. The historical total number of seats refers to the total number of available seats on the train. The historical total number of seats is obtained from the train's operation and management system. A threshold P for the historical occupancy rate is set, and ticket classification rules are set based on the threshold P and the average passenger volume.

[0008] In a preferred embodiment, tickets are classified into short-distance tickets and long-distance tickets according to ticket classification rules. If the historical occupancy rate in the interval from one station to another is greater than a threshold value P, and the number of passengers in the interval is higher than the average passenger volume, the tickets in the interval are marked as long-distance tickets, and the interval below the threshold value P or the average passenger volume is marked as short-distance tickets.

[0009] Specifically, the historical occupancy rate is calculated based on historical traffic and seat occupancy data, and a threshold P is set to formulate ticket classification rules. By quantitatively analyzing historical data, short-distance tickets and long-distance tickets are divided more scientifically, which improves the accuracy and rationality of ticket classification, further refines ticket classification, and makes ticket types more in line with passengers' travel needs and preferences.

[0010] In a preferred embodiment, the marked long-distance tickets and short-distance tickets are counted, and the proportion of long-distance tickets and short-distance tickets in the total number of train tickets is calculated. The comfort of the carriage seats is obtained by comprehensive analysis of the stability and noise interference level. The carriage is divided into multiple small positions with equal distances, and the position comfort of each small position is calculated. The stability is quantified by the stability index. The specific formula is: S index =α×a avg +β×d avg ; Among them, a avg is the average value of acceleration; d avg is the average value of vibration displacement; α and β are the weight coefficients of the average value of acceleration and the average value of vibration displacement; the degree of noise interference is quantified by the noise level, and the specific formula is: Among them, SPL i is the noise intensity of each small position, n is the number of small positions; the comprehensive comfort index is obtained by comprehensively considering the stability and noise, and the specific formula is: C index =ω1×S index +ω2×N indexAmong them, C index is the comprehensive comfort index, S index is the stationarity index, N index is the noise level, ω1 and are the weight coefficients of smoothness and noise, which are adjusted according to the user's comfort needs.

[0011] Specifically, by comprehensively considering the smoothness and noise level to calculate the comfort of the carriage seats and setting the initial seat distribution rules, the balance of the carriage seat utilization is improved, while the comfort experience of passengers is enhanced.

[0012] In a preferred embodiment, the ticket sales data interface of the railway system is directly accessed through the API to obtain the real-time ticket sales data of the train, each station of the train is marked differently, the number of station tickets sold with different marked stations as destinations is counted, and the proportion of short-distance tickets and long-distance tickets sold at the marked stations in the number of station tickets is analyzed; when analyzing each marked station, the "destination" station can be identified according to different marks; for each marked station, the number of tickets sold is counted, according to the following steps: Step 1: derive ticket classification rules based on the historical traffic and historical occupancy rate of the train, and mark the train's travel range as short-distance tickets and long-distance tickets; Step 2: For each marked station, count the number of short-distance tickets and long-distance tickets sold; Step 3: For each marked station, calculate the proportion of short-distance tickets and long-distance tickets in the total number of tickets.

[0013] Specifically, it collects ticket sales data in real time and analyzes the proportion of short-distance and long-distance tickets sold at stations, providing real-time data support for dynamically adjusting seat distribution, making the adjustment strategy more flexible and intelligent.

[0014] In a preferred embodiment, a time-ticket type distribution model is established to describe the demand changes for short-distance and long-distance tickets in different time periods. The demand function is used to characterize the relationship between time and ticket type. A linear or nonlinear model is set to represent the sales changes between time and ticket type. The demand function D(t, P) represents the demand at time t and ticket type P. The formula is: D(t, P) = α P t+β P ; Among them, α P is the sensitivity coefficient of time t to the change in demand for ticket type P; β P is the baseline demand for ticket type P at time t=0; specifically for short-distance tickets and long-distance tickets, we obtain the short-distance ticket demand D(t,short) and long-distance ticket demand D(t,long) respectively; define an "adjustment bias index" to measure the adjustment demand of the station, and define an indicator A(i) to measure the adjustment bias of the station. The adjustment bias index A(i) formula is: Among them, P sh ort (i) and P long (i) is the ratio of short-distance tickets to long-distance tickets at station i; D(t,short) and D(t,long) are the demand for short-distance tickets and long-distance tickets in a specific time period t; the adjustment bias of the station is determined according to the adjustment bias index A(i).

[0015] Specifically, by establishing a time-ticket type distribution model to describe the changes in demand for short-distance and long-distance tickets in different time periods, and defining an adjustment bias index to measure the adjustment demand of stations, the changing trend of passenger demand can be predicted more accurately, providing a scientific basis for the dynamic adjustment of seat distribution.

[0016] A railway intelligent operation management and scheduling plan generation system includes a train marking and historical data collection module, a ticket classification and initial seat distribution setting module, a ticket sales data statistics and analysis module, and a seat distribution adjustment and optimization module; the train marking and historical data collection module is used to mark trains on different routes and continue subsequent data management and analysis. At the same time, it is used to collect and store historical traffic data of these trains, including the number of passengers and seat occupancy, and formulate ticket classification rules based on these data; the ticket classification and initial seat distribution setting module divides tickets into short-distance tickets and long-distance tickets based on the data provided by the train marking and historical data collection module, and adjusts the seat distribution according to the proportion of short-distance tickets and long-distance tickets in the total number of train tickets, as well as the different seats in the carriage. The module is used to collect and store the sales data of short-distance and long-distance tickets of trains in real time, mark each stop, count the number of tickets sold with these stops as destinations, and analyze the proportion of short-distance and long-distance tickets sold at the marked stops in the total number of tickets sold at the stops; the module is used to comprehensively analyze the adjustment bias of the middle and end positions of different marked stops based on the results of the module and the time change from the stop of ticket sales, dynamically adjust the seat distribution at different stops, and formulate an optimized seat distribution strategy.

[0017] The technical effects and advantages of the railway intelligent operation management scheduling plan generation method and system of the present invention are as follows: the automation and precision of ticket classification, seat distribution setting and dynamic adjustment are realized through intelligent means, which not only improves the balance of train seat utilization, enhances the passenger comfort experience, but also optimizes railway operation efficiency.

[0018] The present invention scientifically divides ticket types by quantitatively analyzing historical data; calculates carriage seat comfort by comprehensively considering stability and noise levels, and optimizes seat distribution settings; and flexibly adjusts seat distribution strategies by collecting ticket sales data in real time and establishing a time-ticket type distribution model. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of the structure of a method for generating a railway intelligent operation management scheduling plan according to the present invention;

[0020] Figure 2 The figure is a schematic diagram of the structure of a railway intelligent operation management scheduling plan generation system according to the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] The present invention is collected.

[0023] Example 1

[0024] The present invention discloses a method for generating a railway intelligent operation management scheduling plan, comprising the following steps:

[0025] S1. Mark trains on different routes differently, collect historical traffic of trains with different markings, count the number of occupied seats on the trains and calculate the occupancy rate of the marked trains, and set ticket classification rules based on the historical traffic and historical occupancy rate of the marked trains;

[0026] S2. Classify the tickets into short-distance tickets and long-distance tickets according to the ticket classification rules, set the initial seat distribution rules for the train carriages based on the proportion of short-distance tickets and long-distance tickets in the total number of train tickets and the comfort level of the carriage seats, and divide the seats into middle positions and end positions according to the initial seat distribution rules;

[0027] S3. Collect sales data for short-distance and long-distance tickets on the trains, mark each station on the train differently, count the number of station tickets sold with the marked stations as destinations, and analyze the proportion of short-distance and long-distance tickets for the marked stations in the total number of station tickets sold;

[0028] S4. Based on the changes in the distance to the stop of ticket sales and the proportion of short-distance tickets and long-distance tickets in the number of tickets sold at the marked stations, a comprehensive analysis is made of the adjustment bias of the middle and end positions of different marked stations.

[0029] In this embodiment, S1 includes the following processes:

[0030] By accessing the railway company's operation management system, detailed information on all trains is obtained, and trains on different routes are marked differently. By accessing the historical ticket sales data in the ticketing system, the historical traffic flow between different stations of each train is obtained. Based on the historical number of tickets sold and the total number of seats in the train, the historical occupancy rate between different stations of the train is calculated.

[0031] It needs to be explained that the railway company's operation management system is a complex and comprehensive system that covers all aspects of railway operations, including train scheduling, passenger and freight transportation management, vehicle maintenance, safety management, financial management, etc.; the ticketing system records the sales of tickets for each train, including the number of tickets sold, ticket sales time, passenger information, etc.

[0032] The number of passengers at each station is obtained based on the historical traffic volume of each station. The number of passengers at each station on the train is added together and divided by the number of stations to obtain the average passenger volume. The historical occupancy rate is calculated as follows: The historical number of tickets sold indicates the number of tickets sold between one station and another. The historical number of tickets sold is obtained from the ticketing system. The historical total number of seats refers to the total number of available seats on the train. The historical total number of seats is obtained from the train's operation and management system. A threshold P for the historical occupancy rate is set, and ticket classification rules are set based on the threshold P and the average passenger volume.

[0033] In this embodiment, S2 includes the following process:

[0034] According to the ticket classification rules, tickets are classified into short-distance tickets and long-distance tickets. If the historical occupancy rate of the interval from one station to another is greater than the threshold P, and the number of passengers in the interval is higher than the average passenger volume, the tickets in this interval are marked as long-distance tickets, and the interval below the threshold P or the average passenger volume is marked as short-distance tickets; assuming that the threshold P is 75% and the average passenger volume is 100 people, assuming that the historical occupancy rate of a certain interval is 80%, and the passenger volume of this time period is 150 people, then it meets the conditions, the historical occupancy rate>75%, and the passenger volume>100, then the system classifies the tickets in this interval as long-distance tickets; assuming that the occupancy rate of a certain interval is 70% and the passenger volume is 50 people, then this interval does not meet the long-distance ticket conditions, and the system classifies the tickets in this interval as short-distance tickets;

[0035] The system counts the marked long-distance and short-distance tickets and calculates the proportion of long-distance and short-distance tickets in the total number of train tickets. The comfort of the carriage seats is obtained through a comprehensive analysis of stability and noise interference. The carriage is divided into multiple small positions with equal distances, and the position comfort of each small position is calculated. Stability is quantified by the stability index. The specific formula is: S index =α×a avg +β×d avg ; Among them, a avg is the average value of acceleration; d avg is the average value of vibration displacement; α and β are the weight coefficients of the average value of acceleration and the average value of vibration displacement. A lower stability index means a more comfortable seat, which is suitable for passengers with long-distance tickets. The degree of noise interference is quantified by the noise level. The specific formula is: Among them, SPL i is the noise intensity of each small location, n is the number of small locations, and a lower noise level indicates a quieter environment, which is usually suitable for passengers with long-distance tickets. The comprehensive comfort index is obtained by comprehensively considering the stability and noise. The specific formula is: C index =ω1×S index +ω2×N index Among them, C index is the comprehensive comfort index, S index is the stationarity index, N index is the noise level, ω1 and are the weight coefficients of stability and noise, which are adjusted according to the user's comfort needs; assuming that the stability index of a small location is 0.1, the noise level is 65dB, and the weights of stability and noise are 0.6 and 0.4 respectively, the comprehensive comfort index of a small location is: C index=0.6×0.1+0.4×65=6.6; The comfort of the carriage position is obtained by calculation. The initial seat distribution rule of the train carriage is set according to the proportion of short-distance tickets and long-distance tickets in the total number of train tickets and the comfort of the carriage position. After calculating the comfort index of all small positions, the small positions are divided into middle positions and end positions according to the comfort index. The threshold of the comfort index is obtained based on the proportion of short-distance tickets and long-distance tickets in the total number of train tickets in historical data. The comfort index of the small position is divided into an interval from 1 to 10, representing from the most uncomfortable to the most comfortable. Assume that there are 10 seats in a carriage, and the comfort index of the carriage is as follows (1 represents the most uncomfortable and 10 represents the most comfortable ): Position 1, comfort index 3; Position 2, comfort index 4; Position 3, comfort index 8; Position 4, comfort index 9; Position 5, comfort index 10; Position 6, comfort index 9; Position 1, comfort index 7; Position 8, comfort index 4; Position 9, comfort index 3; Position 10, comfort index 2; Assume that short-distance tickets account for 60% and long-distance tickets account for 40%; It can be concluded that positions with a comfort index greater than or equal to 6 are positions with high comfort, and positions with a comfort index less than 6 are positions with low comfort. At this time, the initial seat distribution rule is to divide positions with a comfort index greater than or equal to 6 into middle positions, and positions with a comfort index less than 6 into end positions.

[0036] In this embodiment, S3 includes the following process:

[0037] Directly access the railway system's ticketing data interface through the API to obtain real-time train ticket sales data. It should be explained that the railway system's ticketing data interface refers to a method that allows developers, partners or third-party applications to interact with the railway ticketing system to obtain, submit or process information about train tickets; API (Application Programming Interface) is a way for different software components to communicate and interact with each other.

[0038] The system marks each station on the train differently, counts the number of station tickets sold with different marked stations as destinations, and analyzes the proportion of short-distance tickets and long-distance tickets sold at the marked stations. When analyzing each marked station, the "destination" station can be identified according to different marks. Assuming that there are multiple station data, and the starting point, end point and sequence of the stations passed by each train have been marked; mark each station as a destination. Suppose, for a train, assuming its station sequence is A→B→C→D, then the destination of station A can be B, C, D; the destination of station B can be C, D; the destination of station C can be D; station D has no subsequent stations, so it has no destination. Based on this, add a marked station for each station.

[0039] For each marked station, the number of tickets sold is counted using the following steps: Step 1: Based on the train's historical traffic and occupancy rates, a ticket classification rule is developed, and the train's travel range is marked as short-distance or long-distance tickets. Step 2: For each marked station, the number of short-distance and long-distance tickets sold is counted. Step 3: For each marked station, the proportion of short-distance and long-distance tickets to the total number of tickets sold is calculated. Suppose that for marked station D, if 500 short-distance tickets and 300 long-distance tickets were sold, then the total number of tickets sold for destination D is 800. The proportion of short-distance tickets is 500 / 800 = 62.5%, and the proportion of long-distance tickets is 300 / 800 = 37.5%.

[0040] In this embodiment, S4 includes the following process:

[0041] Based on the changes in the time from the end of ticket sales and the proportion of short-distance tickets and long-distance tickets sold at the destination marked station, a comprehensive analysis is made of the adjustment bias of the middle and end positions of different marked stations.

[0042] The system calculates the sales ratio of short-distance tickets and long-distance tickets for each marked station as follows: Among them, N sh ort (i) is the number of short-distance tickets sold at station i, N total (i) is the sum of all tickets (short-distance and long-distance) sold at station i; the proportion of long-distance tickets Among them, N long (i) is the number of long-distance tickets sold by station i.

[0043] By establishing a time-ticket type distribution model, we can describe the demand changes for short-distance and long-distance tickets in different time periods. Specifically, we use the demand function to characterize the relationship between time and ticket type. By setting a linear or nonlinear model to represent the sales changes between time and ticket type, the demand function D(t, P) represents the demand at time t and ticket type P. The formula is: D(t, P) = αP t+β P ; Among them, α P is the sensitivity coefficient of time t to the change in demand for ticket type P; β P is the baseline demand for ticket type P at time t=0; specifically for short-distance tickets and long-distance tickets, the short-distance ticket demand D(t,short) and long-distance ticket demand D(t,long) are obtained respectively; the system defines an "adjustment bias index" to measure the adjustment demand of the station. Specifically, an indicator A(i) is defined to measure the adjustment bias of the station. The adjustment bias index A(i) formula is: Among them, P sh ort (i) and P long (i) is the ratio of short-distance tickets to long-distance tickets at station i; D(t,short) and D(t,long) are the demands for short-distance tickets and long-distance tickets in a specific time period t; the adjustment bias of the station is determined according to the adjustment bias index A(i): if A(i)>0, the station is biased towards short-distance tickets, that is, the end positions need to be adjusted to expand the range; if A(i)<0, the station is biased towards long-distance tickets, that is, the middle positions need to be adjusted to expand the range; if A(i)=0, the adjustment bias of the station is relatively balanced, that is, there is no need to adjust the middle and end positions.

[0044] In summary, the present invention realizes the automation and precision of ticket classification, seat distribution setting and dynamic adjustment through intelligent means, which not only improves the balance of train seat utilization, enhances passengers' comfort experience, but also optimizes railway operation efficiency; through quantitative analysis of historical data, ticket types are scientifically divided; by comprehensively considering stability and noise levels to calculate the comfort of carriage seats, the seat distribution setting is optimized; by real-time collection of ticket sales data and establishing a time-ticket type distribution model, the seat distribution strategy can be flexibly adjusted.

[0045] Example 2

[0046] The present invention discloses a railway intelligent operation management scheduling plan generation system, which includes a train marking and historical data collection module, a ticket classification and initial seat distribution setting module, a ticket sales data statistics and analysis module, and a seat distribution adjustment and optimization module;

[0047] The train marking and historical data collection module is used to mark trains on different routes and conduct subsequent data management and analysis. At the same time, it is used to collect and store the historical traffic data of these trains, including the number of passengers and seat occupancy, and formulate ticket classification rules based on this data;

[0048] The ticket classification and initial seat distribution setting module divides tickets into short-distance tickets and long-distance tickets based on the data provided by the train marking and historical data collection module. The classification criteria for short-distance tickets and long-distance tickets can be comprehensively considered based on multiple factors such as the train's travel distance, passengers' travel habits, and the seat utilization rate of the carriage. Then, based on the proportion of short-distance tickets and long-distance tickets in the total number of train tickets, as well as the comfort level of different positions in the carriage, an initial seat distribution rule is formulated. The initial seat distribution rule will clearly divide the middle and end positions of the carriage seats, as well as the proportion of the number of different seat types, to maximize passenger comfort and train operating efficiency;

[0049] The ticket sales data statistics and analysis module is used to collect and store real-time sales data for short-distance and long-distance train tickets, including information such as ticket sales time, number of tickets sold, and seat locations selected by passengers. It also marks each stop and counts the number of tickets sold to these stops. It also analyzes the proportion of short-distance and long-distance tickets sold at the marked stops in the total number of tickets sold at the stops. Based on this, the module conducts an in-depth analysis of the proportion of short-distance and long-distance tickets sold at each stop, as well as ticket sales for different time periods and seat types. This information will help the system more accurately understand passengers' travel needs and preferences, providing data support for subsequent adjustments to seat distribution.

[0050] The seat distribution adjustment and optimization module is used to dynamically adjust the seat distribution at different stations based on the results of the ticket sales data statistics and analysis module and the time changes before ticket sales stop. It comprehensively analyzes the adjustment bias of the middle and end positions of different marked stations, dynamically adjusts the seat distribution at different stations, and formulates an optimized seat distribution strategy.

[0051] In summary, the above modules together constitute a complete and efficient train seat management and optimization system. Through data analysis, intelligent decision-making and dynamic adjustment, it provides passengers with a more convenient and comfortable travel experience, while also improving the train's operational efficiency and service quality.

[0052] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0053] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0054] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0055] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0056] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0057] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating a railway intelligent operation management scheduling plan, characterized in that: The steps include: S1. Mark trains on different routes differently, collect historical traffic of trains with different markings, count the number of occupied seats on the trains and calculate the occupancy rate of the marked trains, and set ticket classification rules based on the historical traffic and historical occupancy rate of the marked trains; S2. Classify the tickets into short-distance tickets and long-distance tickets according to the ticket classification rules, set the initial seat distribution rules for the train carriages based on the proportion of short-distance tickets and long-distance tickets in the total number of train tickets and the comfort level of the carriage seats, and divide the seats into middle positions and end positions according to the initial seat distribution rules; S3. Collect sales data for short-distance and long-distance tickets on the trains, mark each station on the train differently, count the number of station tickets sold with the marked stations as destinations, and analyze the proportion of short-distance and long-distance tickets for the marked stations in the total number of station tickets sold; S4. Based on the changes in the distance to the stop of ticket sales and the proportion of short-distance tickets and long-distance tickets in the number of tickets sold at the marked stations, a comprehensive analysis is made of the adjustment bias of the middle and end positions of different marked stations.

2. A method for generating a railway intelligent operation management scheduling plan according to claim 1, characterized in that: The number of passengers at each station is obtained based on the historical traffic volume of each station. The number of passengers at each station on the train is added together and divided by the number of stations to obtain the average passenger volume. The historical occupancy rate is calculated as follows: The historical number of tickets sold indicates the number of tickets sold between one station and another. The historical number of tickets sold is obtained from the ticketing system. The historical total number of seats refers to the total number of available seats on the train. The historical total number of seats is obtained from the train's operation and management system. A threshold P for the historical occupancy rate is set, and ticket classification rules are set based on the threshold P and the average passenger volume.

3. The method for generating a railway intelligent operation management scheduling plan according to claim 2, characterized in that: According to the ticket classification rules, tickets are classified into short-distance tickets and long-distance tickets. If the historical occupancy rate between one station and another is greater than the threshold P and the number of passengers in this interval is higher than the average passenger volume, the tickets in this interval are marked as long-distance tickets, and the interval below the threshold P or the average passenger volume is marked as short-distance tickets.

4. A method for generating a railway intelligent operation management scheduling plan according to claim 3, characterized in that: The marked long-distance tickets and short-distance tickets are counted, and the proportion of long-distance tickets and short-distance tickets in the total number of train tickets is calculated. The comfort of the carriage seats is obtained by comprehensive analysis of stability and noise interference. The carriage is divided into multiple small positions with equal distances, and the position comfort of each small position is calculated. Stability is quantified by the stability index. The specific formula is: S index =α×a avg +β×d avg ; Among them, a avg is the average value of acceleration; d avg is the average value of vibration displacement; α and β are the weight coefficients of the average value of acceleration and the average value of vibration displacement; the degree of noise interference is quantified by the noise level, and the specific formula is: Among them, SPL i is the noise intensity of each small position, n is the number of small positions; the comprehensive comfort index is obtained by comprehensively considering the stability and noise, and the specific formula is: C index =ω1×S index +ω2×N index Among them, C index is the comprehensive comfort index, S index is the stationarity index, N index is the noise level, ω1 and are the weight coefficients of smoothness and noise, which are adjusted according to the user's comfort needs.

5. The method for generating a railway intelligent operation management scheduling plan according to claim 4, characterized in that: Directly access the railway system's ticket sales data interface through the API to obtain real-time train ticket sales data, mark each station on the train differently, count the number of station tickets sold with different marked stations as destinations, and analyze the proportion of short-distance tickets and long-distance tickets sold at the marked stations; when analyzing each marked station, the "destination" station can be identified according to different marks; for each marked station, count the number of tickets sold, according to the following steps: Step 1: derive ticket classification rules based on the historical train traffic and historical occupancy rate, and mark the train's travel range as short-distance tickets and long-distance tickets; Step 2: For each marked station, count the corresponding short-distance tickets and long-distance tickets sold; Step 3: For each marked station, calculate the proportion of short-distance tickets and long-distance tickets in the total number of tickets.

6. A method for generating a railway intelligent operation management scheduling plan according to claim 5, characterized in that: By establishing a time-ticket type distribution model to describe the demand changes for short-distance and long-distance tickets in different time periods, the demand function is used to characterize the relationship between time and ticket type. A linear or nonlinear model is set to represent the sales changes between time and ticket type. The demand function D(t,P) represents the demand at time t and ticket type P. The formula is: D(t,P) = α P t+β P ; Among them, α P is the sensitivity coefficient of time t to the change in demand for ticket type P; β P is the baseline demand for ticket type P at time t=0; specifically for short-distance tickets and long-distance tickets, we obtain the short-distance ticket demand D(t,short) and long-distance ticket demand D(t,long) respectively; define an "adjustment bias index" to measure the adjustment demand of the station, and define an indicator A(i) to measure the adjustment bias of the station. The adjustment bias index A(i) formula is: Among them, p short (i) and P long (i) is the ratio of short-distance tickets to long-distance tickets at station i; D(t,short) and D(t,long) are the demand for short-distance tickets and long-distance tickets in a specific time period t; the adjustment bias of the station is determined according to the adjustment bias index A(i).

7. A railway intelligent operation management scheduling plan generation system, used to implement the railway intelligent operation management scheduling plan generation method according to any one of claims 1 to 6, characterized in that: It includes a train marking and historical data collection module, a ticket classification and initial seat distribution setting module, a ticket sales data statistics and analysis module, and a seat distribution adjustment and optimization module; The train marking and historical data collection module is used to mark trains, collect traffic, count the number of occupied seats, calculate the occupancy rate, and set ticket classification rules; The ticket classification and initial seat distribution setting module classifies tickets into short-distance and long-distance tickets based on the data provided by the train marking and historical data collection module, sets the initial seat distribution rules based on the proportion and comfort level, and divides the seats into middle and end positions; The ticket sales data statistics and analysis module is used to collect sales data, mark stations, count station ticket sales data, and analyze the proportion of short-distance and long-distance tickets; The seat distribution adjustment and optimization module is used to comprehensively analyze the adjustment bias of the middle and end positions based on changes in ticket sales time and the proportion of short-distance and long-distance tickets.

Images