An intelligent bus station scheduling system based on passenger flow big data

Abstract

The present invention discloses an intelligent bus station scheduling system based on passenger flow big data, and relates to the field of bus station scheduling. The intelligent bus station scheduling system based on passenger flow big data includes a data acquisition subsystem for acquiring historical passenger flow data, bus vehicle data, and future weather data; a data division subsystem for dividing historical passenger flow data into historical holiday passenger flow data and historical non-holiday passenger flow data by identifying holidays; and a data division subsystem for performing comprehensive analysis on historical holiday passenger flow data and historical non-holiday passenger flow data according to weather conditions. The present invention can optimize vehicle use and reduce the situation of empty or overcrowded vehicles by analyzing historical and predicted passenger flow data in real time. In particular, by comprehensively considering the passenger flow changes and weather factors of each route, the intelligent scheduling subsystem can adjust vehicle deployment, thereby reducing unnecessary operating costs and improving energy efficiency, and also reducing the overall operating cost of the public transportation system.

Description

Technical Field

[0001] The present invention relates to the field of bus station scheduling, and in particular to an intelligent bus station scheduling system based on passenger flow big data. Background Art

[0002] In modern cities, public transportation systems are an important part of urban infrastructure, and they are responsible for alleviating urban traffic congestion, reducing environmental pollution, and providing convenient transportation services. With the acceleration of urbanization and the growth of urban population, the challenges facing public transportation systems are also increasing, especially how to efficiently and accurately manage and dispatch vehicles to meet the changing needs of passengers.

[0003] The limitations of existing technologies include at least the following problems: First, traditional bus scheduling systems are often based on fixed historical data models and are unable to dynamically adjust to real-time passenger flow data and sudden weather conditions. This static scheduling model is often difficult to respond in time when facing holidays, special events or extreme weather, resulting in insufficient buses during peak passenger flow periods or too many vacant vehicles during off-peak periods, which wastes resources and fails to meet passenger needs. Secondly, the lack of detailed route analysis and time period demand forecasting makes it impossible for the bus system to accurately match the actual needs of each route in planning and operation. For example, some busy routes may be overloaded due to insufficient vehicles during peak hours, while some relatively idle routes may have excess vehicles. This unbalanced resource allocation not only increases operating costs, but also reduces the overall efficiency of the bus system. In addition, traditional systems have obvious shortcomings in predicting and handling passenger flow fluctuations caused by sudden weather changes. Under extreme weather conditions, such as heavy rain or snow, passenger flow patterns may be very different from usual. Due to the lack of flexible weather adjustment factor analysis, traditional systems find it difficult to accurately predict and adjust vehicle deployment, which may lead to service interruptions or shortages, affecting passenger travel safety and comfort. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a bus station intelligent scheduling system based on passenger flow big data. By real-time analysis of historical and predicted passenger flow data, it is possible to optimize vehicle usage and reduce the situation of empty or overcrowded vehicles. In particular, by comprehensively considering the passenger flow changes and weather factors of each route, the intelligent scheduling subsystem can adjust vehicle deployment, thereby reducing unnecessary operating costs and improving energy utilization efficiency, and also reducing the overall operating cost of the public transportation system.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] A bus station intelligent scheduling system based on passenger flow big data includes: a data acquisition subsystem, a data division subsystem, a weather analysis subsystem, a passenger flow analysis subsystem, and an intelligent scheduling subsystem; the data acquisition subsystem is used to acquire historical passenger flow data, bus vehicle data, and future weather data; the data division subsystem is used to identify holidays for historical passenger flow data and divide it into historical holiday passenger flow data and historical non-holiday passenger flow data; the weather analysis subsystem is used to perform comprehensive analysis on historical holiday passenger flow data and historical non-holiday passenger flow data according to weather conditions, and obtain holiday weather adjustment factor data and non-holiday weather adjustment factor data; the passenger flow analysis subsystem is used to identify holidays for each day in the future, and perform predictive analysis based on historical holiday passenger flow data and historical non-holiday passenger flow data, holiday weather adjustment factor data, and non-holiday weather adjustment factor data to obtain future passenger flow data; the intelligent scheduling subsystem is used to perform comprehensive analysis based on future passenger flow data and bus vehicle data, and generate future bus vehicle scheduling information, and perform real-time adjustment at the same time.

[0007] Furthermore, the historical passenger flow data specifically include historical passenger flow values ​​for each time period on each bus route every day in history, the bus vehicle data specifically include the total number of vehicles at bus stations and the maximum carrying capacity of buses, the future weather data specifically include weather conditions for each time period on each day in the future, the historical holiday passenger flow data specifically include historical holiday time period passenger flow values ​​for each historical time period of each holiday on each bus route, the historical non-holiday passenger flow data specifically include historical non-holiday time period passenger flow values ​​for each historical time period of each non-holiday on each bus route, the holiday weather adjustment factor data specifically include weather adjustment factors for each holiday for each bus route, the non-holiday weather adjustment factor data specifically include weather adjustment factors for each non-holiday for each bus route, and the future passenger flow data specifically include predicted holiday time period passenger flow values ​​for each future time period of each holiday on each bus route, and predicted non-holiday time period passenger flow values ​​for each future time period of each non-holiday on each bus route.

[0008] Furthermore, the weather analysis subsystem includes: a historical holiday passenger flow analysis module, a historical non-holiday passenger flow analysis module, a holiday weather adjustment factor analysis module, and a non-holiday weather adjustment factor analysis module; the historical holiday passenger flow analysis module is used to comprehensively analyze the historical holiday period passenger flow values ​​of each historical period of each holiday on each bus route to obtain the total mean historical holiday passenger flow of each bus route; the historical non-holiday passenger flow analysis module is used to comprehensively analyze the historical non-holiday period passenger flow values ​​of each historical period of each non-holiday on each bus route to obtain the total mean historical non-holiday passenger flow of each bus route. The holiday weather adjustment factor analysis module is used to perform statistical analysis on the historical holiday period passenger flow values ​​of each historical period of each holiday on each bus route, and perform comprehensive analysis in combination with the total mean value of the historical holiday passenger flow of each bus route to obtain each holiday weather adjustment factor of each bus route; the non-holiday weather adjustment factor analysis module is used to perform statistical analysis on the historical non-holiday period passenger flow values ​​of each historical period of each non-holiday on each bus route, and perform comprehensive analysis in combination with the total mean value of the historical non-holiday passenger flow of each bus route to obtain each non-holiday weather adjustment factor of each bus route.

[0009] Furthermore, the specific steps for obtaining the total mean historical holiday passenger flow and the total mean historical non-holiday passenger flow for each bus route are as follows: perform a mean analysis on the historical holiday period passenger flow values ​​for each historical period of each holiday on each bus route to obtain the historical holiday passenger flow mean for each holiday in history for each bus route; perform a mean analysis on the historical holiday passenger flow mean for each holiday in history for each bus route using the moving exponential averaging method to obtain the total mean historical holiday passenger flow for each bus route; perform a mean analysis on the historical non-holiday period passenger flow values ​​for each historical period of each non-holiday on each bus route to obtain the historical non-holiday passenger flow mean for each non-holiday in history for each bus route; perform a mean analysis on the historical non-holiday passenger flow mean for each non-holiday in history for each bus route using the weighted average method to obtain the total mean historical non-holiday passenger flow for each bus route.

[0010] Furthermore, the specific formula for calculating the total mean of historical holiday passenger flow and the total mean of historical non-holiday passenger flow for each bus route is as follows:

[0011] ;

[0012] in, For the The total average of historical holiday passenger flow on bus routes, For the The history of bus routes The historical holiday passenger flow average for each holiday, For the The history of bus routes The history of the holiday Historical holiday period passenger flow value for each period, For the The history of bus routes The weighted coefficient of the historical holiday passenger flow mean of each holiday, For the The history of bus routes The historical holiday passenger flow average for each holiday, For the The history of bus routes The weighted coefficient of the historical holiday passenger flow mean of each holiday, , is the number of historical holidays, For the The total average of the historical non-holiday passenger flow of bus routes, For the The history of bus routes The historical non-holiday passenger flow average of non-holidays, For the The history of bus routes Non-holiday historical The historical non-holiday passenger flow value of each period, For the The history of bus routes The weighted coefficient of the historical non-holiday passenger flow average of non-holidays, , is the number of historical non-holidays, , is the total number of time periods, , is the number of bus routes.

[0013] Furthermore, the specific steps for obtaining each holiday weather adjustment factor and each non-holiday weather adjustment factor for each bus route are as follows: statistically analyze the historical holiday period passenger flow values ​​of each historical period of each holiday for each bus route according to weather conditions, and obtain the total number of holidays in each historical period and the total number of periods of each holiday in history under each weather condition for each bus route; perform mean analysis on the total number of periods of each holiday in history under each weather condition for each bus route and the corresponding historical holiday period passenger flow values, and obtain the mean weather holiday passenger flow for each holiday under each weather condition for each bus route; perform mean analysis on the mean weather holiday passenger flow for each holiday under each weather condition for each bus route and the total number of holidays in each historical period under each weather condition for the corresponding bus route, and obtain the total mean weather holiday passenger flow under each weather condition for each bus route; perform comprehensive analysis based on the total mean historical holiday passenger flow and the total mean weather holiday passenger flow under each weather condition for each bus route, and obtain the weather holiday passenger flow for each holiday under each weather condition for each bus route. Weather adjustment factors for each holiday of the route; statistical analysis of the historical non-holiday passenger flow values ​​for each historical period of each non-holiday of each bus route according to weather conditions to obtain the total number of non-holidays and the total number of periods in history under each weather condition for each bus route; mean analysis of the total number of periods in history under each non-holiday and the corresponding historical non-holiday passenger flow values ​​to obtain the mean value of weather non-holiday passenger flow for each non-holiday under each weather condition for each bus route; mean analysis of the mean value of weather non-holiday passenger flow for each non-holiday under each weather condition for each bus route and the total number of non-holidays in history for each period under each weather condition for each bus route to obtain the total mean value of weather non-holiday passenger flow under each weather condition for each bus route; comprehensive analysis based on the total mean value of historical non-holiday passenger flow and the total mean value of weather non-holiday passenger flow under each weather condition for each bus route to obtain the weather adjustment factor for each non-holiday of each bus route.

[0014] Furthermore, the specific formulas for each holiday weather adjustment factor and each non-holiday weather adjustment factor for each bus route are as follows:

[0015] ;

[0016] in, For the The bus route holiday weather adjustment factors, For the The bus route The total average passenger flow on weather holidays under various weather conditions, For the The total average of historical holiday passenger flow on bus routes, For the The bus route The first time in history that weather conditions The weather and holiday passenger flow average for each holiday, , is the number of holidays under the weather conditions, For the The bus route The first time in history that weather conditions The history of the holiday Historical holiday period passenger flow value for each period, , is the number of holiday periods under weather conditions, For the The bus route non-holiday weather adjustment factors, For the The bus route The total average of non-holiday passenger flow under various weather conditions, For the The total average of the historical non-holiday passenger flow of bus routes, , is the number of weather conditions, For the The bus route The first time in history that weather conditions The average passenger flow of non-holiday weather is , is the number of non-holidays under the weather conditions, For the The bus route The first time in history that weather conditions Non-holiday historical The historical non-holiday passenger flow value of each period, , is the number of non-holiday periods under weather conditions, , is the number of bus routes.

[0017] Furthermore, the specific steps for obtaining future passenger flow data are as follows: perform mean analysis on the historical holiday period passenger flow values ​​for each historical period of each holiday on each bus route, and the historical non-holiday period passenger flow values ​​for each historical period of each non-holiday on each bus route, respectively, to obtain the holiday passenger flow mean for each historical period of holidays on each bus route, and the non-holiday passenger flow mean for each historical period of non-holidays on each bus route; perform holiday recognition for each day in the future; when a certain day in the future is a holiday, read the holiday passenger flow mean for each historical period of holidays on each bus route as the initial holiday period passenger flow value for each period of each bus route on that day, The weather conditions for the corresponding time period of the day are read from the future weather data, and a comprehensive analysis is performed based on the holiday weather adjustment factors of the corresponding bus routes to obtain the predicted holiday time period passenger flow value for each future time period on each bus route of the day; when a future day is a non-holiday, the average non-holiday passenger flow for each non-holiday time period of each bus route is read as the initial non-holiday time period passenger flow value for each time period of each bus route of the day, and the weather conditions for the corresponding time period of the day are read from the future weather data, and a comprehensive analysis is performed based on the non-holiday weather adjustment factors of the corresponding bus routes to obtain the predicted non-holiday time period passenger flow value for each future time period on each bus route of the day.

[0018] Furthermore, the specific formula for calculating the historical holiday passenger flow average and the historical non-holiday passenger flow average for each period of each bus route on a future day is as follows:

[0019] ;

[0020] in, For the future day The bus route The historical holiday passenger flow average for each period, For the The history of holidays on bus routes The average holiday passenger flow in each period, For the future day The bus route The holiday weather adjustment factor corresponding to the weather conditions in each period, For the The history of bus routes The first holiday Historical holiday period passenger flow value for each period, , is the number of historical holidays, For the future day The bus route The historical non-holiday passenger flow average for each period, For the The bus routes are operated on non-holidays. The average non-holiday passenger flow in each period, For the future day The bus route The non-holiday weather adjustment factor corresponding to the weather conditions in each period, For the The history of bus routes The non-holiday The historical non-holiday passenger flow value of each period, , is the number of historical non-holidays, , is the total number of time periods, , is the number of bus routes.

[0021] Furthermore, the specific steps for generating future bus scheduling information are as follows: read the predicted holiday period passenger flow value for each future period of each holiday on each bus route, the predicted non-holiday period passenger flow value for each future period of each non-holiday on each bus route, the total number of vehicles at the bus station and the maximum carrying capacity of the bus, and conduct a comprehensive analysis to obtain the number and frequency of waiting vehicles at the bus station for each future holiday and non-holiday period on each bus route.

[0022] The present invention has the following beneficial effects:

[0023] (1) The intelligent bus station scheduling system based on passenger flow big data can optimize vehicle utilization and reduce the situation of empty or overcrowded vehicles by analyzing historical and predicted passenger flow data in real time. In particular, by comprehensively considering the passenger flow changes and weather factors of each route, the intelligent scheduling subsystem can adjust vehicle deployment, thereby reducing unnecessary operating costs and improving energy efficiency. This not only reduces the overall operating cost of the bus system, but also minimizes the impact on the environment.

[0024] (2) The intelligent bus station scheduling system based on passenger flow big data analyzes the historical passenger flow data of each bus route on different holidays and non-holidays, and makes predictions based on weather adjustment factors. The system can accurately adjust services to match passenger flow demand during specific periods of time. For example, during holidays or inclement weather conditions, the system can predict passenger flow peaks and dispatch enough vehicles in advance to ensure that services are not affected. This targeted service adjustment significantly improves passenger satisfaction and avoids the inconvenience caused by congestion or long waiting times.

[0025] (3) The intelligent bus station scheduling system based on passenger flow big data not only provides operational support, but also provides a scientific basis for the long-term planning of the bus system by collecting and analyzing large amounts of data. For example, by analyzing long-term passenger flow trends and weather impacts, management can better plan new routes, adjust existing routes, or optimize vehicle configurations. This in-depth data analysis and prediction capability greatly enhances the bus system's adaptability to future challenges and planning accuracy.

[0026] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a block diagram of an intelligent scheduling system for bus stations based on passenger flow big data in the present invention.

[0028] Figure 2 The present invention is a flowchart of the specific steps for obtaining the total mean value of historical holiday passenger flow for each bus route in a bus station intelligent scheduling system based on passenger flow big data.

[0029] Figure 3 The present invention is a flowchart of the specific steps for obtaining the total mean value of historical non-holiday passenger flow for each bus route in a bus station intelligent scheduling system based on passenger flow big data. DETAILED DESCRIPTION

[0030] The embodiment of the present application solves the problem that the traditional bus scheduling system is often based on a fixed historical data model and has no ability to dynamically adjust the real-time changing passenger flow data and sudden weather conditions through a bus station intelligent scheduling system based on passenger flow big data. This static scheduling model is often difficult to respond in time when facing holidays, special events or extreme weather, resulting in insufficient buses during peak passenger flow periods or too many vacant vehicles during off-peak periods, which wastes resources and fails to meet passenger needs. Secondly, the lack of detailed route analysis and time period demand forecasting makes it impossible for the bus system to accurately match the actual situation of each route in planning and operation. Demand, for example, some busy routes may be overloaded due to insufficient vehicles during peak hours, while some relatively idle routes may have excess vehicles. This unbalanced resource allocation not only increases operating costs, but also reduces the overall efficiency of the public transportation system. In addition, the traditional system has obvious shortcomings in predicting and handling passenger flow fluctuations caused by sudden weather changes. Under extreme weather conditions, such as heavy rain or heavy snow, passenger flow patterns may be very different from usual. Due to the lack of flexible weather adjustment factor analysis, the traditional system is difficult to accurately predict and adjust vehicle deployment, which may lead to service interruptions or shortages, affecting the safety and comfort of passengers.

[0031] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0032] First, the system collects historical passenger flow data, bus vehicle data, and future weather data through the data acquisition subsystem. These data include passenger flow for each bus route at different times, the number of buses and their maximum carrying capacity, and predicted weather conditions. Then, the data classification subsystem classifies the historical passenger flow data based on holidays and non-holidays. The weather analysis subsystem further analyzes these data to obtain weather adjustment factors under different weather conditions. The passenger flow analysis subsystem uses historical passenger flow data and weather adjustment factors to predict the future daily passenger flow, for each period of holidays and non-holidays. Finally, the intelligent scheduling subsystem formulates and optimizes the bus scheduling plan based on the predicted passenger flow data and bus vehicle information. This includes adjusting the frequency and number of vehicle departures to ensure that there are enough vehicles to serve during high-demand periods, while avoiding resource waste during low-demand periods.

[0033] See also Figure 1The embodiment of the present invention provides a technical solution: a bus station intelligent scheduling system based on passenger flow big data, including: a data acquisition subsystem, a data division subsystem, a weather analysis subsystem, a passenger flow analysis subsystem, and an intelligent scheduling subsystem; the data acquisition subsystem is used to acquire historical passenger flow data, bus vehicle data, and future weather data; the data division subsystem is used to identify holidays for historical passenger flow data and divide it into historical holiday passenger flow data and historical non-holiday passenger flow data; the weather analysis subsystem is used to perform comprehensive analysis on historical holiday passenger flow data and historical non-holiday passenger flow data according to weather conditions, and obtain holiday weather adjustment factor data and non-holiday weather adjustment factor data; the passenger flow analysis subsystem is used to identify holidays for each day in the future, and perform predictive analysis based on historical holiday passenger flow data and historical non-holiday passenger flow data, holiday weather adjustment factor data, and non-holiday weather adjustment factor data to obtain future passenger flow data; the intelligent scheduling subsystem is used to perform comprehensive analysis based on future passenger flow data and bus vehicle data, and generate future bus vehicle scheduling information, and make real-time adjustments at the same time.

[0034] The specific steps of real-time adjustment are as follows: continuously monitor real-time passenger flow data, which may be achieved through passenger flow monitoring systems (such as cameras, infrared sensors, etc.) installed on buses and stations; monitor real-time weather conditions and obtain updates by connecting to the weather service API; compare the monitored passenger flow data with the predicted passenger flow data in real time, identify significant deviations or anomalies, and analyze whether weather changes are factors that cause abnormal passenger flow. If the passenger flow is detected to be greater than expected, the system automatically proposes to increase vehicle input or reduce the departure interval; if the passenger flow is lower than expected, the system proposes to reduce vehicle input or increase the departure interval; dynamically adjust the bus schedule based on real-time data and intelligent decision-making, and notify passengers and drivers of the real-time updated schedule information through various platforms (such as mobile applications, bus station display screens, etc.); collect feedback from passengers and drivers on the adjusted schedule, and use this feedback to further optimize the response algorithm and decision logic of the scheduling system.

[0035] The historical passenger flow data specifically refers to the historical passenger flow values ​​for each time period on each bus route every day in history collected by using sensors (such as infrared sensors and cameras) installed on buses and stations. The bus vehicle data specifically refers to the total number of vehicles at bus stations and the maximum carrying capacity of buses obtained from the bus vehicle management system. The future weather data specifically refers to the weather conditions for each time period of each day in the future obtained through the meteorological service API, such as sunny days, rainy days, snowy days, etc. The historical holiday passenger flow data specifically refers to the historical holiday time period passenger flow values ​​for each historical holiday period on each bus route. The historical non-holiday passenger flow data specifically refers to the historical non-holiday time period passenger flow values ​​for each historical non-holiday period on each bus route. The holiday weather adjustment factor data specifically refers to the weather adjustment factors for each holiday for each bus route. The non-holiday weather adjustment factor data specifically refers to the weather adjustment factors for each non-holiday for each bus route. The future passenger flow data specifically refers to the predicted holiday time period passenger flow values ​​for each future holiday for each bus route and the predicted non-holiday time period passenger flow values ​​for each future non-holiday for each bus route.

[0036] Specifically, the weather analysis subsystem includes: a historical holiday passenger flow analysis module, a historical non-holiday passenger flow analysis module, a holiday weather adjustment factor analysis module, and a non-holiday weather adjustment factor analysis module; the historical holiday passenger flow analysis module is used to comprehensively analyze the historical holiday period passenger flow values ​​of each historical period of each holiday on each bus route, and obtain the total mean value of the historical holiday passenger flow of each bus route; the historical non-holiday passenger flow analysis module is used to comprehensively analyze the historical non-holiday period passenger flow values ​​of each historical period of each non-holiday on each bus route, and obtain the total mean value of the historical non-holiday passenger flow of each bus route; The holiday weather adjustment factor analysis module is used to perform statistical analysis on the historical holiday passenger flow values ​​of each historical period of each holiday on each bus route, and conduct a comprehensive analysis based on the total mean historical holiday passenger flow of each bus route to obtain each holiday weather adjustment factor of each bus route; the non-holiday weather adjustment factor analysis module is used to perform statistical analysis on the historical non-holiday passenger flow values ​​of each historical period of each non-holiday on each bus route, and conduct a comprehensive analysis based on the total mean historical non-holiday passenger flow of each bus route to obtain each non-holiday weather adjustment factor of each bus route.

[0037] In this implementation scheme, by conducting an in-depth analysis of historical holiday and non-holiday passenger flow data and combining the actual passenger flow impact under each weather condition, the system can more accurately predict future passenger flow changes. This analysis ensures the adaptability and accuracy of the service plan, enabling bus services to better adapt to sudden weather events and different holiday scenarios, thereby improving the efficiency and responsiveness of the entire bus system. By analyzing the specific impact of weather on passenger flow and predicting passenger flow changes under different weather conditions, bus managers can optimize vehicle deployment based on the prediction results. For example, when predicting that passenger flow may increase due to severe weather (such as heavy rain or heavy snow), the system can adjust the number of vehicles and operating frequency in advance, which not only avoids the waste of vehicles and human resources, but also effectively responds to increased passenger flow demand. The system can predict future service needs based on historical data analysis to ensure that appropriate services are provided when needed, reducing passenger waiting time and inconvenience caused by weather changes. Especially in extreme weather conditions, by adjusting the schedule in advance, passengers can enjoy more consistent and reliable services. This improvement in predictability and responsiveness directly enhances passengers' travel experience and overall satisfaction with the bus system.

[0038] Specifically, the specific steps for obtaining the total mean of historical holiday passenger flow and the total mean of historical non-holiday passenger flow for each bus route are as follows: Figure 2 As shown in , the historical holiday passenger flow values ​​of each historical period of each holiday on each bus route are analyzed by means, and the historical holiday passenger flow mean of each holiday in the history of each bus route is obtained; the historical holiday passenger flow mean of each holiday in the history of each bus route is analyzed by means of the moving exponential average method, and the total mean of the historical holiday passenger flow of each bus route is obtained; as shown in Figure 3 As shown, the historical non-holiday passenger flow values ​​of each non-holiday period on each bus route are analyzed by mean, and the historical non-holiday passenger flow mean of each non-holiday period on each bus route is obtained; the weighted average method is used to analyze the historical non-holiday passenger flow mean of each non-holiday period on each bus route, and the total mean of the historical non-holiday passenger flow of each bus route is obtained.

[0039] The specific formula for calculating the total mean of historical holiday passenger flow and the total mean of historical non-holiday passenger flow for each bus route is as follows:

[0040] ;

[0041] in, For the The total average of historical holiday passenger flow on bus routes, For the The history of bus routes The historical holiday passenger flow average for each holiday, For the The history of bus routes The history of the holiday Historical holiday period passenger flow value for each period, For the The history of bus routes The weighted coefficient of the historical holiday passenger flow mean of each holiday, For the The history of bus routes The historical holiday passenger flow average for each holiday, For the The history of bus routes The weighted coefficient of the historical holiday passenger flow mean of each holiday, , is the number of historical holidays, For the The total average of the historical non-holiday passenger flow of bus routes, For the The history of bus routes The historical non-holiday passenger flow average of non-holidays, For the The history of bus routes Non-holiday historical The historical non-holiday passenger flow value of each period, For the The history of bus routes The weighted coefficient of the historical non-holiday passenger flow average of non-holidays, , is the number of historical non-holidays, , is the total number of time periods, , is the number of bus routes.

[0042] and The specific calculation steps are as follows: The history of bus routes , The historical holiday passenger flow averages of the holidays are added together to obtain the The first passenger flow and value of the bus route, and then The history of bus routes , The historical holiday passenger flow averages of the first and second holidays are The first passenger flow and value of the bus routes are ratio-calculated, and the ratio results are used as the respective weighted coefficients.

[0043] The specific calculation steps are as follows: The historical holiday passenger flow average of each non-holiday of the bus route is added together to get the The second passenger flow and value of the bus route, and then The historical holiday passenger flow averages of each non-holiday of the bus routes are respectively The second passenger flow and value of the bus routes are ratio calculated, and the ratio results are used as the respective weighted coefficients.

[0044] In this implementation scheme, the system calculates the total average holiday and non-holiday passenger flow of each bus route under different weather conditions, so that the bus company can more accurately predict the passenger flow demand in different time periods. This accurate prediction allows the bus company to optimize resource allocation, such as adjusting the number of vehicles and schedules, thereby reducing resource waste and improving operational efficiency. By ensuring that there are sufficient vehicles to serve during peak passenger flow, passenger waiting time is significantly reduced and the travel experience is improved. In addition, the system can dynamically adjust vehicle deployment according to weather changes to ensure continuous and reliable service even in severe weather conditions, thereby improving the overall passenger satisfaction and the credibility of the bus system. During holidays or special events, passenger flow often fluctuates unconventionally. By analyzing these special circumstances in historical data, the system provides better preparation for similar events in the future. This foresight is not limited to weather influences, but also includes special needs of public activities and holidays, enabling the bus system to quickly and effectively adjust its operating strategy to cope with sudden passenger flow peaks.

[0045] Specifically, the specific steps for obtaining each holiday weather adjustment factor and each non-holiday weather adjustment factor for each bus route are as follows: statistically analyze the historical holiday period passenger flow values ​​for each historical period of each holiday for each bus route according to weather conditions, and obtain the total number of holidays in each historical period and the total number of periods for each holiday in history under each weather condition for each bus route. For example, for rainy days, the first period in the historical holidays of the bus route is the total number of rainy days, and the total number of rainy periods in each holiday in history for the bus route in days; for each weather condition for each bus route, the total number of rainy periods in each holiday in history The total number of holiday periods and the corresponding historical holiday period passenger flow values ​​are analyzed on a mean basis to obtain the weather holiday passenger flow mean for each holiday under each weather condition for each bus route; the mean weather holiday passenger flow mean for each holiday under each weather condition for each bus route and the total number of holidays in each historical period under each weather condition for the corresponding bus route are analyzed on a mean basis to obtain the total mean weather holiday passenger flow under each weather condition for each bus route; a comprehensive analysis is performed based on the total mean historical holiday passenger flow and the total mean weather holiday passenger flow under each weather condition for each bus route to obtain the weather adjustment factor for each holiday for each bus route.

[0046] According to the weather conditions, the historical non-holiday passenger flow values ​​of each non-holiday historical period of each bus route are statistically analyzed to obtain the total number of non-holidays in each historical period under each weather condition of each bus route and the total number of time periods in each non-holiday historical period. For example, for rainy days, the first time period in the historical non-holidays of the bus route is the total number of non-holidays, and the total number of rainy time periods in each non-holiday historical period of the bus route in days; the total number of each non-holiday time period in history under each weather condition of each bus route and the corresponding historical non-holiday passenger flow values ​​are statistically analyzed to obtain the total number of non-holidays in each historical period under each weather condition of each bus route and the total number of non-holiday time periods in history. Mean analysis is performed to obtain the mean non-holiday passenger flow under each weather condition for each non-holiday on each bus route; mean analysis is performed on the mean non-holiday passenger flow under each weather condition for each bus route and the total number of non-holidays in each historical period under each weather condition for each bus route to obtain the total mean non-holiday passenger flow under each weather condition for each bus route; comprehensive analysis is performed based on the total mean historical non-holiday passenger flow and the total mean non-holiday passenger flow under each weather condition for each bus route to obtain each non-holiday weather adjustment factor for each bus route.

[0047] The specific formula for calculating each holiday weather adjustment factor and each non-holiday weather adjustment factor for each bus route is as follows:

[0048] ;

[0049] in, For the The bus route holiday weather adjustment factors, For the The bus route The total average passenger flow on weather holidays under various weather conditions, For the The total average of historical holiday passenger flow on bus routes, For the The bus route The first time in history that weather conditions The weather and holiday passenger flow average for each holiday, , is the number of holidays under the weather conditions, For the The bus route The first time in history that weather conditions The history of the holiday Historical holiday period passenger flow value for each period, , is the number of holiday periods under weather conditions, For the The bus route non-holiday weather adjustment factors, For the The bus route The total average of non-holiday passenger flow under various weather conditions, For the The total average of the historical non-holiday passenger flow of bus routes, , is the number of weather conditions, For the The bus route The first time in history that weather conditions The average passenger flow of non-holiday weather is , is the number of non-holidays under the weather conditions, For the The bus route The first time in history that weather conditions Non-holiday historical The historical non-holiday passenger flow value of each period, , is the number of non-holiday periods under weather conditions, , is the number of bus routes.

[0050] In this implementation scheme, by analyzing the actual impact of each weather condition on passenger flow in detail, the system can more accurately predict the changes in passenger flow under various weather conditions on holidays and non-holidays. This high-precision prediction enables the bus system to adjust vehicle deployment and service frequency in a timely manner to match actual passenger demand. This not only optimizes resource utilization and reduces waiting time, but also improves passenger satisfaction. According to the passenger flow adjustment factors under different weather conditions, bus managers can make more informed decisions, such as adding more vehicles or adjusting the vehicle's route when it is predicted that rainy or hot weather will lead to an increase in passenger flow. Such dynamic adjustments not only reduce the waste or shortage of vehicles caused by passenger flow fluctuations, but also significantly improve operational efficiency and economic benefits. By understanding the passenger flow forecast under various weather conditions in advance, the bus system can ensure that sufficient transportation services are provided when needed, avoiding long waiting and congestion for passengers under severe weather conditions. This predictive service improvement significantly improves the travel experience of passengers, especially in extreme weather conditions, which can significantly reduce travel inconvenience.

[0051] Specifically, it is characterized in that the specific steps for obtaining future passenger flow data are as follows: perform mean analysis on the historical holiday period passenger flow values ​​for each historical period of each holiday on each bus route, and the historical non-holiday period passenger flow values ​​for each historical period of each non-holiday on each bus route, to obtain the holiday passenger flow mean for each historical period of holidays for each bus route, and the non-holiday passenger flow mean for each historical period of non-holidays for each bus route; perform holiday identification for every day in the future; when a future day is a holiday, read the holiday passenger flow mean for each historical period of holidays for each bus route as the initial holiday period passenger flow for each period of each bus route on that day. value, and read the weather conditions of the corresponding time period of the day from the future weather data, and conduct a comprehensive analysis based on the holiday weather adjustment factors of the corresponding bus routes to obtain the predicted holiday period passenger flow value for each future time period on each bus route of the day; when a future day is a non-holiday, read the historical average non-holiday passenger flow for each non-holiday time period of each bus route as the initial non-holiday time period passenger flow value for each time period of each bus route of the day, and read the weather conditions of the corresponding time period of the day from the future weather data, and conduct a comprehensive analysis based on the non-holiday weather adjustment factors of the corresponding bus routes to obtain the predicted non-holiday time period passenger flow value for each future time period on each bus route of the day.

[0052] The specific formula for calculating the historical holiday passenger flow average and the historical non-holiday passenger flow average for each bus route in each period on a future day is as follows:

[0053] ;

[0054] in, For the future day The bus route The historical holiday passenger flow average for each period, For the The history of holidays on bus routes The average holiday passenger flow in each period, For the future day The bus route The holiday weather adjustment factor corresponding to the weather conditions in each period, For the The history of bus routes The first holiday Historical holiday period passenger flow value for each period, , is the number of historical holidays, For the future day The bus route The historical non-holiday passenger flow average for each period, For the The bus routes are operated on non-holidays. The average non-holiday passenger flow in each period, For the future day The bus route The non-holiday weather adjustment factor corresponding to the weather conditions in each period, For the The history of bus routes The non-holiday The historical non-holiday passenger flow value of each period, , is the number of historical non-holidays, , is the total number of time periods, , is the number of bus routes.

[0055] In this implementation scheme, by combining historical passenger flow data with weather forecasts, the system can dynamically adjust the deployment of public transportation vehicles. This prediction-based approach enables the public transportation system to better respond to changing demands on holidays and non-holidays, especially under extreme weather conditions. This responsiveness not only reduces congestion and inconvenience caused by the failure to provide adequate services during peak passenger flow periods, but also improves the overall reliability of public transportation. Accurately predicting passenger flow in each time period can help public transportation companies reasonably arrange the number of vehicles and departure frequency, reduce empty driving and overcrowding, which can not only optimize fuel use and reduce maintenance costs, but also reduce overall operating costs through more reasonable vehicle use while maintaining service quality. When the public transportation system is able to adjust services according to actual passenger flow conditions and weather changes, passenger waiting time is reduced, travel experience is improved, and passenger satisfaction is naturally improved. This improvement can not only enhance the loyalty of existing passengers, but also attract more new users to choose public transportation as a mode of travel, thereby increasing public transportation utilization and revenue.

[0056] Specifically, the specific steps for generating future bus scheduling information are as follows: read the predicted holiday period passenger flow value for each future period of each holiday on each bus route, the predicted non-holiday period passenger flow value for each future period of each non-holiday on each bus route, the total number of vehicles at the bus station and the maximum carrying capacity of the bus, and conduct a comprehensive analysis to obtain the number of buses waiting to be dispatched and the frequency of buses waiting to be dispatched at the bus station for each future holiday and non-holiday period on each bus route. The specific calculation process is: divide the predicted holiday period passenger flow value for each future period of each holiday on each bus route and the predicted non-holiday period passenger flow value for each future period of each non-holiday on each bus route by the maximum carrying capacity of the bus, respectively, to obtain the number of buses waiting to be dispatched for each future holiday and non-holiday on each bus route, and determine whether the number of vehicles required for each period exceeds the total number of vehicles at the station. If so, the system needs to be adjusted, such as allocating vehicles from other routes or using double-decker buses. Measures are used to increase the carrying capacity, and the frequency of buses waiting to be dispatched on each bus route is obtained by dividing the divided time period by the number of buses waiting to be dispatched. For example, for a certain bus route, the time period is 1 hour and the number of buses waiting to be dispatched is 6, then the departure frequency is one bus every ten minutes; when the number of buses waiting to be dispatched at a bus station on each future holiday on a certain bus route and in each future period on non-holidays on a certain bus route is higher than the total number of vehicles at the bus station, the number of buses dispatched each time is adjusted. For example, if two buses depart at the same time, If the adjustment measures are still not required, analyze whether there are spare buses on other bus routes, and the departure time of the bus is higher than the round-trip time of the current bus route. If there are spare buses, call the spare buses to the current bus route for emergency dispatch. If not, identify the bus route with the least frequency and number of buses to be dispatched, and adjust the frequency and number of buses to be dispatched on the bus route. Specifically, make emergency dispatch on the current bus route without affecting the frequency and number of buses to be dispatched on the bus route. And formulate a dispatch plan for each bus route based on the number of buses to be dispatched and the frequency of dispatch. This plan should be detailed to the vehicle dispatch for each time period and each route.

[0057] In this implementation scheme, by analyzing the predicted passenger flow data for each time period and route in detail, the system can allocate vehicles more effectively to ensure that the utilization efficiency of each bus is maximized, which not only reduces vehicle idling and unnecessary operating costs, but also ensures that resources are optimally utilized. Accurate adjustment of departure frequency and allocation of vehicle quantity minimizes passenger waiting time, avoids overcrowding, and greatly improves passengers' travel experience. This improvement in prediction accuracy can significantly enhance the public's trust in and satisfaction with the public transportation system. During holidays or special weather conditions, passenger flow often fluctuates greatly. The system can adjust the departure frequency and the number of vehicles in real time, especially in emergency situations to quickly allocate resources to adapt to sudden increases in passenger flow demand. This flexible adjustment capability is unmatched by traditional static scheduling systems. When the passenger flow demand on a certain route exceeds the norm, the system can immediately allocate vehicles from other low-load routes to ensure that services in high-demand areas are not affected. This cross-route resource optimization enhances the response capability of the entire public transportation network and reduces service delays caused by vehicle shortages.

[0058] In summary, this application has at least the following effects:

[0059] By analyzing historical and predicted passenger flow data in real time, it is possible to optimize vehicle utilization and reduce the situation of empty or overcrowded vehicles. In particular, by comprehensively considering passenger flow changes and weather factors on each route, the intelligent scheduling system can adjust vehicle deployment, thereby reducing unnecessary operating costs and improving energy efficiency. This not only reduces the overall operating cost of the public transportation system, but also minimizes the impact on the environment.

[0060] By analyzing the historical passenger flow data of each bus route on different holidays and non-holidays, and combining it with weather adjustment factors for prediction, the system can accurately adjust services to match passenger flow demand during specific periods of time. For example, on holidays or under severe weather conditions, the system can predict passenger flow peaks and dispatch enough vehicles in advance to ensure that services are not affected. This targeted service adjustment significantly improves passenger satisfaction and avoids inconveniences caused by congestion or long waiting times.

[0061] It not only provides support at the operational level, but also provides a scientific basis for the long-term planning of the public transportation system by collecting and analyzing a large amount of data. For example, by analyzing long-term passenger flow trends and weather impacts, management can better plan new routes, adjust existing routes, or optimize vehicle configuration. This in-depth data analysis and prediction capabilities greatly enhance the public transportation system's adaptability to future challenges and planning accuracy.

[0062] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0063] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent bus station scheduling system based on passenger flow big data, characterized in that: include: Data acquisition subsystem, data division subsystem, weather analysis subsystem, passenger flow analysis subsystem, intelligent scheduling subsystem; The data acquisition subsystem is used to acquire historical passenger flow data, public transportation vehicle data, and future weather data; The data division subsystem is used to classify the historical passenger flow data into historical holiday passenger flow data and historical non-holiday passenger flow data by identifying holidays; The weather analysis subsystem is used to perform comprehensive analysis on historical holiday passenger flow data and historical non-holiday passenger flow data according to weather conditions to obtain holiday weather adjustment factor data and non-holiday weather adjustment factor data; The passenger flow analysis subsystem is used to identify holidays every day in the future, and to perform forecast analysis based on historical holiday passenger flow data and historical non-holiday passenger flow data, holiday weather adjustment factor data and non-holiday weather adjustment factor data to obtain future passenger flow data; The intelligent scheduling subsystem is used to conduct comprehensive analysis based on future passenger flow data and public transport vehicle data, generate future public transport vehicle scheduling information, and make real-time adjustments; The historical passenger flow data specifically include the historical passenger flow values ​​for each time period on each bus route on each historical day, the bus vehicle data specifically include the total number of vehicles at the bus station and the maximum carrying capacity of the bus vehicles, the future weather data specifically include the weather conditions for each time period on each future day, the historical holiday passenger flow data specifically include the historical holiday time period passenger flow values ​​for each historical time period of each holiday on each bus route, the historical non-holiday passenger flow data specifically include the historical non-holiday time period passenger flow values ​​for each historical time period of each non-holiday on each bus route, the holiday weather adjustment factor data specifically include the weather adjustment factors for each holiday on each bus route, the non-holiday weather adjustment factor data specifically include the weather adjustment factors for each non-holiday on each bus route, the future passenger flow data specifically include the predicted holiday time period passenger flow values ​​for each future time period of each holiday on each bus route, and the predicted non-holiday time period passenger flow values ​​for each future time period of each non-holiday on each bus route; The weather analysis subsystem includes: a historical holiday passenger flow analysis module, a historical non-holiday passenger flow analysis module, a holiday weather adjustment factor analysis module, and a non-holiday weather adjustment factor analysis module; The historical holiday passenger flow analysis module is used to comprehensively analyze the historical holiday passenger flow values ​​of each historical period of each holiday on each bus route to obtain the total mean value of the historical holiday passenger flow of each bus route; The historical non-holiday passenger flow analysis module is used to comprehensively analyze the historical non-holiday passenger flow values ​​of each historical period of each non-holiday on each bus route to obtain the total mean value of the historical non-holiday passenger flow of each bus route; The holiday weather adjustment factor analysis module is used to perform statistical analysis on the historical holiday passenger flow values ​​of each historical period of each holiday on each bus route, and to perform comprehensive analysis in combination with the total mean value of the historical holiday passenger flow of each bus route to obtain the weather adjustment factor for each holiday of each bus route; The non-holiday weather adjustment factor analysis module is used to perform statistical analysis on the historical non-holiday passenger flow values ​​of each historical period of each non-holiday on each bus route, and to perform comprehensive analysis in combination with the total mean of the historical non-holiday passenger flow of each bus route to obtain each non-holiday weather adjustment factor of each bus route; The specific steps to obtain the total mean of historical holiday passenger flow and the total mean of historical non-holiday passenger flow for each bus route are as follows: Perform mean analysis on the historical holiday passenger flow values ​​of each period of each holiday on each bus route to obtain the mean value of the historical holiday passenger flow of each holiday on each bus route; Combined with the moving exponential average method, the mean value of the historical holiday passenger flow of each bus route on each holiday is analyzed to obtain the total mean value of the historical holiday passenger flow of each bus route; Perform mean analysis on the historical non-holiday passenger flow values ​​of each non-holiday historical period on each bus route to obtain the historical non-holiday passenger flow mean of each non-holiday historical period on each bus route; Combined with the weighted average method, the historical non-holiday passenger flow average of each bus route is analyzed to obtain the total historical non-holiday passenger flow average of each bus route; The specific formula for calculating the total mean of historical holiday passenger flow and the total mean of historical non-holiday passenger flow for each bus route is as follows: Among them, JkZ h is the total mean of historical holiday passenger flow on the h-th bus route, JkJ hi is the historical holiday passenger flow mean of the h-th bus route on the i-th holiday, Lk hij is the historical holiday period passenger flow value of the historical j-th period of the historical i-th holiday of the h-th bus route, α hi1 is the weighted coefficient of the historical holiday passenger flow mean of the h-th bus route on the i-th holiday, JkJ h ( i+1 ) is the historical holiday passenger flow average of the hth bus route on the i+1th holiday, α hi2 is the weighted coefficient of the historical holiday passenger flow mean of the hth bus route on the i+1th holiday, i=1,2,3,…,N, N is the number of historical holidays, FkZ h is the total mean of the historical non-holiday passenger flow of the h-th bus route, JkF ha is the historical non-holiday passenger flow average of the ath non-holiday of the hth bus route, LFk haj is the historical non-holiday passenger flow value of the a-th non-holiday period of the h-th bus route, and β ha is the weighted coefficient of the average non-holiday passenger flow of the ath non-holiday of the hth bus route, a=1,2,3,…,A, A is the number of non-holidays in history, j=1,2,3,…,M, M is the total number of time periods, h=1,2,3,…,H, H is the number of bus routes; The specific steps for obtaining each holiday weather adjustment factor and each non-holiday weather adjustment factor for each bus route are as follows: According to the weather conditions, the historical holiday passenger flow values ​​of each period of each holiday in the history of each bus route are statistically analyzed to obtain the total number of holidays in each period in the history and the total number of time periods of each holiday in the history under each weather condition of each bus route; Perform mean analysis on the total number of time periods for each holiday in history under each weather condition for each bus route and the corresponding passenger flow value for each holiday period in history, and obtain the weather holiday passenger flow mean for each holiday under each weather condition for each bus route; Perform mean analysis on the weather holiday passenger flow mean value of each holiday under each weather condition of each bus route and the total number of holidays in each historical period under each weather condition of the corresponding bus route to obtain the total mean weather holiday passenger flow under each weather condition of each bus route; Based on the total mean of historical holiday passenger flow of each bus route and the total mean of weather holiday passenger flow under each weather condition, a comprehensive analysis is conducted to obtain the weather adjustment factor for each holiday of each bus route; According to the weather conditions, the historical non-holiday passenger flow values ​​of each non-holiday period of each bus route are statistically analyzed to obtain the total number of non-holiday passenger flow values ​​of each non-holiday period and the total number of non-holiday period in each weather condition of each bus route; Perform mean analysis on the total number of historical non-holiday periods under each weather condition for each bus route and the corresponding historical non-holiday period passenger flow values ​​to obtain the mean non-holiday passenger flow value for each non-holiday weather condition for each bus route; Perform mean analysis on the weather non-holiday passenger flow mean value for each non-holiday under each weather condition of each bus route and the total number of non-holidays in each historical period under each weather condition of each bus route to obtain the total weather non-holiday passenger flow mean value for each weather condition of each bus route; Based on the total mean of historical non-holiday passenger flow of each bus route and the total mean of weather non-holiday passenger flow under each weather condition, a comprehensive analysis is conducted to obtain each non-holiday weather adjustment factor of each bus route; The specific formula for calculating each holiday weather adjustment factor and each non-holiday weather adjustment factor for each bus route is as follows: Among them, Jt hq is the qth holiday weather adjustment factor for the hth bus route, TJz hq is the total mean passenger flow on weather holidays under the qth weather condition on the hth bus route, JkZ h is the total mean of historical holiday passenger flow on the h-th bus route, TJk hqu is the weather holiday passenger flow average of the h-th bus route under the q-th weather condition on the u-th holiday in history, u=1,2,3,…,V, V is the number of holidays under the weather condition, TJks hqur is the historical holiday period passenger flow value of the historical u-th holiday period under the q-th weather condition of the h-th bus route, r = 1, 2, 3, ..., R, R is the number of holiday periods under the weather conditions, FJt hq is the qth non-holiday weather adjustment factor for the hth bus route, TFz hq is the total mean of non-holiday passenger flow under the qth weather condition on the hth bus route, FkZ h is the total mean of the historical non-holiday passenger flow of the h-th bus route, q = 1, 2, 3, ..., Q, Q is the number of weather conditions, TFk hqb is the historical non-holiday passenger flow average of the bth non-holiday under the qth weather condition of the hth bus route, b=1,2,3,…,B, B is the number of non-holidays under the weather condition, TFks hqbd is the historical non-holiday period passenger flow value of the bth non-holiday historical dth period under the qth weather condition of the hth bus route, d = 1, 2, 3, ..., D, D is the number of non-holiday periods under the weather conditions, h = 1, 2, 3, ..., H, H is the number of bus routes.

2. According to claim 1, the intelligent bus station scheduling system based on passenger flow big data is characterized in that: The specific steps to obtain future passenger flow data are as follows: Perform mean analysis on the historical holiday passenger flow values ​​for each historical period of each holiday on each bus route, and the historical non-holiday passenger flow values ​​for each historical period of each non-holiday on each bus route, to obtain the mean holiday passenger flow value for each historical period of holidays on each bus route, and the mean non-holiday passenger flow value for each historical period of non-holidays on each bus route; Identify holidays for every day in the future; When a certain day in the future is a holiday, the average holiday passenger flow of each period of the holiday on each bus route is read as the initial holiday period passenger flow value of each period of each bus route on that day, and the weather conditions of the corresponding period of that day are read from the future weather data, and a comprehensive analysis is performed based on the holiday weather adjustment factor of the corresponding bus route to obtain the predicted holiday period passenger flow value of each period in the future on each bus route on that day; When a future day is a non-holiday, the historical average non-holiday passenger flow for each time period of each bus route is read as the initial non-holiday passenger flow value for each time period of each bus route on that day, and the weather conditions for the corresponding time period of the day are read from the future weather data. A comprehensive analysis is performed based on the non-holiday weather adjustment factors of the corresponding bus routes to obtain the predicted non-holiday passenger flow value for each future time period on each bus route on that day.

3. The intelligent bus station scheduling system based on passenger flow big data according to claim 2 is characterized in that: The specific formula for calculating the historical holiday passenger flow average and the historical non-holiday passenger flow average for each period of each bus route on a future day is as follows: Among them, Jsy hj is the historical holiday passenger flow mean of the jth period of the hth bus route on a future day, JsJ hj is the average holiday passenger flow of the jth period of the holiday on the hth bus route, Jt hj is the holiday weather adjustment factor corresponding to the weather conditions of the jth period of the hth bus route on a certain day in the future, JsL hij is the historical holiday period passenger flow value of the jth period of the i-th holiday in the history of the h-th bus route, i = 1, 2, 3, ..., N, N is the number of historical holidays, Fsy hj is the historical non-holiday passenger flow mean of the jth period of the hth bus route on a future day, FsJ hj FJt is the average non-holiday passenger flow of the jth period of the non-holiday period of the hth bus route, hj FsL is the non-holiday weather adjustment factor corresponding to the weather conditions of the jth period of the hth bus route on a certain day in the future, haj is the historical non-holiday passenger flow value of the j-th period of the a-th non-holiday of the h-th bus route, a=1,2,3,…,A, A is the number of historical non-holidays, j=1,2,3,…,M, M is the total number of periods, h=1,2,3,…,H, H is the number of bus routes.

4. The intelligent bus station scheduling system based on passenger flow big data according to claim 2 is characterized in that: The specific steps for generating future bus scheduling information are as follows: read the predicted holiday period passenger flow value for each future period of each holiday on each bus route, the predicted non-holiday period passenger flow value for each future period of each non-holiday on each bus route, the total number of vehicles at the bus station and the maximum carrying capacity of the bus, and conduct a comprehensive analysis to obtain the number and frequency of waiting vehicles at the bus station for each future holiday and non-holiday period on each bus route.

Images