Demand response type bus management system based on artificial intelligence

Abstract

The invention discloses a demand response type bus management system based on artificial intelligence, and particularly relates to the field of traffic transportation engineering. Comprising a demand data acquisition module, a demand data preprocessing module, a response type bus management system database, a demand data analysis module, a response decision making module, a response type bus management system optimization module and a response type bus feedback module. According to the invention, the decision making module comprehensively analyzes passenger behavior parameters, operation efficiency parameters and service response parameters to generate an optimal scheduling and resource allocation scheme so as to realize a service target; through real-time data analysis by a response type bus management system optimization module, lines and service frequency can be dynamically adjusted, and optimal matching between operation efficiency and passenger behaviors is ensured. The service bottleneck and the improvement point can be accurately identified through analyzing the use habits of the passengers and investigating the satisfaction degree through the response type bus feedback module, and the continuous upgrading of the service quality is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation engineering, and more specifically, to a demand-responsive public transportation management system based on artificial intelligence. Background Art

[0002] With the rapid development of intelligent transportation systems and big data analysis technologies, urban traffic management is undergoing a profound change. In densely populated urban environments, efficient public transportation systems are particularly important for alleviating traffic congestion, reducing carbon emissions, and improving the quality of life of citizens. Although the traditional fixed-route bus system has a wide coverage, it is difficult to meet the growing demand for personalized travel in terms of flexibility and response speed. Therefore, the demand-responsive bus management system came into being, which uses advanced information technology and data analysis capabilities to provide passengers with more flexible, efficient, and personalized travel services.

[0003] The demand-responsive bus management system integrates passenger demand with real-time traffic conditions and dynamically adjusts bus routes and departure times, significantly improving the flexibility and efficiency of public transportation. This technological innovation not only improves passengers' travel experience, reduces waiting time and the number of transfers, but also effectively optimizes the allocation of bus resources and reduces operating costs. In addition, the demand-responsive bus management system promotes the popularization of public transportation, especially in low-density residential areas and remote areas, makes up for the shortcomings of the traditional bus network, enhances the connectivity and accessibility of the entire urban transportation network, and lays a solid foundation for building a smart and green urban transportation system.

[0004] However, there are still some shortcomings in its actual use. For example, high initial investment and complex technical integration requirements are a major obstacle for many small and medium-sized cities, limiting the widespread application of this technology. The development of accurate demand forecasting and scheduling algorithms remains an industry challenge, especially in dealing with sudden large passenger flows or extreme weather conditions. The ability to respond needs to be improved. Data privacy and network security are also issues that cannot be ignored. Protecting the security and integrity of passenger information is the key to the sustainable development of demand-responsive bus management systems. The public's acceptance of new technologies and changes in habits will also affect the promotion of demand-responsive bus management systems. Education and publicity are needed to enhance user awareness and participation. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a demand-responsive bus management system based on artificial intelligence, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An artificial intelligence-based demand-responsive bus management system, comprising:

[0008] Demand data collection module: used to collect information related to passenger demand for demand-responsive public transportation, including passenger behavior data, operational efficiency data, and service response data, to form a demand data information set, and transmit it to the demand data preprocessing module;

[0009] Demand data preprocessing module: used to clean, format, standardize and process outliers of the demand data information set transmitted in the demand data acquisition module, and transmit it to the demand data analysis module and the responsive bus management system database;

[0010] Responsive bus management system database: used to store the passenger demand data information set collected from the demand data acquisition module, the data cleaned and converted by the demand data preprocessing module, and the passenger behavior parameters, operation efficiency parameters and service response parameters generated by the demand data analysis module;

[0011] Demand data analysis module: used to analyze the demand data information set transmitted by the demand data preprocessing module, analyze the passenger behavior data, the bus operation efficiency data and the system service response data, obtain the passenger behavior parameters, operation efficiency parameters and service response parameters, and transmit them to the response decision making module; the demand data analysis module includes a passenger behavior analysis unit, an operation efficiency analysis unit and a service response analysis unit;

[0012] Response decision-making module: used to analyze the passenger behavior parameters, operation efficiency parameters and service response parameters transmitted by the demand data analysis module, establish a calculation model for response decision-making, generate response decision indicators, and transmit them to the responsive bus management system optimization module;

[0013] Responsive bus management system optimization module: used to analyze the response decision indicators transmitted by the response decision-making module and the demand data transmitted by the responsive bus management system database, identify service advantages and disadvantages, and optimize key indicators;

[0014] Responsive Bus Feedback Module: Used for passenger interaction and monitoring of demand-responsive bus service quality, delivering information and responding quickly to issues and providing timely notification and solutions in emergency situations.

[0015] Preferably, the passenger demand related information, including the passenger behavior data information, includes a time series represented as a set of passenger number and passenger behavior information per day, per week or per hour.

[0016] Preferably, the data information on operational efficiency includes a passenger demand data set, a vehicle quantity data set, a time step data set, fixed costs, and variable costs.

[0017] Preferably, the fixed costs include depreciation expenses, management expenses, advertising and marketing expenses, and maintenance expenses.

[0018] Preferably, the variable costs include fuel costs, maintenance costs, and road taxes calculated based on kilometres or bridge tolls in certain places.

[0019] Preferably, the data information of the service response includes the average number of reservations per unit time, the average time from passengers getting on to getting off the vehicle, the average number of passengers arriving at passenger vehicles per unit time, the average number of passengers that can be served by a single passenger vehicle per unit time, and the number of vehicles that can be served simultaneously, wherein the unit time is a constant preset in the database.

[0020] Preferably, the demand data preprocessing module receives raw data from the demand data acquisition module, performs data cleaning, removes invalid and duplicate data, identifies and properly processes outliers, corrects errors, converts the data into a unified format, prepares for data loading, and loads the cleaned and converted data into a database.

[0021] Preferably, the demand data preprocessing module receives each raw data from the demand data acquisition module and records them as observation values. When the observation value is numerical data, the missing value is filled with the average value of the column; when the observation value is categorical data, the missing value is filled with the category with the largest number of occurrences.

[0022] Preferably, the demand data preprocessing module can remove irrelevant and erroneous data through data cleaning to ensure the purity and accuracy of the data set; by formatting and standardizing data, it can ensure that all data follow a unified format and metric standard to facilitate subsequent data analysis and processing; through outlier processing, it can identify and appropriately adjust or delete abnormal data points to avoid outliers from biasing the data analysis results; through missing value filling, it can use reasonable statistical methods to fill data gaps and reduce the impact of data incompleteness on the analysis effect; through data loading, the preprocessed data can be efficiently imported into the database to provide an immediately available data source for real-time analysis and decision-making; through the automation of the preprocessing process, it can reduce human intervention, reduce the error rate of data processing, and improve the efficiency and reliability of data processing; through data quality control, it can ensure the high quality of data before the data enters the analysis stage, providing a solid data foundation for subsequent business decisions; through data preprocessing, it can improve the accuracy and timeliness of data analysis, so that the demand-responsive bus management system can more accurately predict demand and optimize scheduling.

[0023] Preferably, the demand data analysis module includes a passenger behavior analysis unit, an operation efficiency analysis unit and a service response analysis unit.

[0024] Preferably, the passenger behavior analysis unit is used to analyze the passenger behavior data transmitted in the demand data preprocessing module, establish a calculation model of passenger behavior, generate passenger demand parameters, and transmit them to the response decision-making module.

[0025] Preferably, the calculation model of the passenger behavior is specifically expressed as: γ 1 =φ(B)(1-B) d X t -θ(B)∈ t , where γ 1 is represented by the passenger behavior parameter, and B is represented by the backshift operator, denoted by BX t =X t-1 , φ(B) represents the autoregressive polynomial of passenger behavior, θ(B) represents the moving average polynomial of passenger behavior, d represents the degree of difference, X t is the time series of the passenger behavior information set at time t, ε t is the error term.

[0026] Preferably, the autoregressive polynomial φ(B)=α 1 X t-1 +α 2 X t-2 +...+α p X t-p +∈ t , where α 1 , α 2 , ..., α p is represented by the autoregressive coefficient, and p is represented by the order of the autoregressive polynomial; the autoregressive coefficient

[0027] Preferably, the moving average polynomial in, It is represented as the mean of the time series of passenger behavior information set, β 1 , β 2 , ..., β q It is expressed as a moving average coefficient, q is the order of the moving average multi-top formula; the moving average coefficient β 1 , β 2 ,...,β q =([ε t-1 ε t-2 … ε t-q ] T [ε t-1 ε t-2 ... ε t-q]) -1 [ε t-1 ε t-2 ... ε t-q ]

[0028] Preferably, the number of times of the difference d=X t -X t-1 , the autoregressive polynomial order p = α t -α t-1 , the order of the moving average polynomial is q=ε t -ε t-1 ; The difference When ε t =0, the model fitting iteration makes the error term of the sequence approach white noise.

[0029] Preferably, the passenger behavior analysis unit helps predict future demand by analyzing the passenger demand analysis set; can identify travel patterns and modes by analyzing historical passenger behavior data; can help bus companies arrange shifts and vehicles reasonably and reduce passenger waiting time by identifying peak hours; can optimize line layout and increase shift frequency and improve passenger satisfaction by identifying popular routes; can plan vehicle maintenance and procurement in advance and reduce operating costs by predicting future demand; and can adjust departure frequency in real time to cope with sudden changes in passenger flow by monitoring passenger flow in real time.

[0030] Preferably, the operation efficiency analysis unit is used to analyze the operation efficiency data transmitted in the demand data preprocessing module, establish a calculation model of operation efficiency, generate operation efficiency parameters, and transmit them to the response decision-making module.

[0031] Preferably, the calculation model of the operational efficiency is specifically expressed as: where γ 2 is the operational efficiency parameter, I is the passenger demand set, J is the vehicle set, T is the time step set, and C ijt Denote the cost of assigning vehicle j to passenger i at time t, x ijt Denotes the decision variable for assigning vehicle j to passenger i at time t, F jt It is expressed as the cost of vehicle j being idle at time t, y jt Denote as the decision variable for vehicle j being idle at time t.

[0032] Preferably, the decision variable for allocating vehicle j to passenger i at time t and the decision variable for vehicle j being idle at time t both take values ​​of 0 or 1, and the cost of vehicle j being idle at time t includes fuel consumption, driver's salary, etc.

[0033] Preferably, the operational efficiency needs to satisfy all constraints, including: satisfying the routes of all passengers: The number of passengers does not exceed the vehicle capacity: Comply with time requirements: Meeting the continuity requirements of passenger vehicles: Ensure vehicle status:

[0034] Preferably, the r i Denotes the i-th passenger route, k j It is represented by the capacity of the jth vehicle, r j Denotes the service rate of the jth vehicle, represents the reservation time and estimated arrival time of the passenger, z ijti′jt′ =1 means that vehicle j serves passenger i at time t and serves another passenger i′ at the same time period t′.

[0035] Preferably, the operation efficiency analysis unit can establish a refined operation efficiency calculation model by receiving and parsing the operation efficiency data transmitted by the demand data preprocessing module, and construct a multidimensional analysis framework including a passenger demand set, a vehicle set, and a time step set, so as to comprehensively evaluate the comprehensive performance of the operation system and ensure the rationality of resource allocation; by quantifying costs and decision variables, it can accurately calculate the actual expenses of each business, optimize the cost control strategy, and improve the overall operation efficiency; by ensuring that all decision variables take the value of 0 or 1, it can implement clear and unambiguous scheduling instructions and avoid resource conflicts; by meeting the route needs of all passengers, it can ensure that the itineraries of all passengers are properly arranged and the service quality is improved; by complying with vehicle capacity restrictions, it can prevent overloading and ensure driving safety and passenger comfort; by complying with time requirements, it can accurately match passenger reservations with actual service times, reduce waiting, and improve customer satisfaction; by maintaining the continuity of passenger vehicles, it can ensure the continuity of vehicle service processes, avoid invalid driving, and improve operational fluency; by monitoring vehicle status, it can timely discover and resolve potential faults and keep the fleet in good operating condition.

[0036] Preferably, the service response analysis unit is used to analyze the service response data transmitted in the demand data preprocessing module, establish a calculation model of the service response, generate service response parameters, and transmit them to the response decision-making module.

[0037] Preferably, the computing model of the service response is specifically expressed as Among them 3 It is represented as the service response parameter; λ is the average number of passengers arriving at the passenger vehicle per unit time; μ is the average number of passengers that can be served by a single passenger vehicle per unit time, and n is the number of vehicles that can be served at the same time.

[0038] Preferably, the service response analysis unit can accurately evaluate the service efficiency and passenger demand matching by deeply analyzing and modeling the received service response data, and optimize the response mechanism. By calculating the average number of passengers arriving at passenger vehicles per unit time, it can gain insight into passenger flow trends, predict peak hours, and deploy resources in advance; by analyzing the average number of passengers that can be served by a single passenger vehicle per unit time, it can evaluate the vehicle service capacity and rationally plan the vehicle configuration; by analyzing the number of vehicles that can be served at the same time, it can dynamically adjust vehicle scheduling to ensure maximum service coverage and meet passengers' immediate needs.

[0039] Preferably, the computational model for response decision making is specifically expressed as Where Ψ represents the response decision indicator, represents the additional revenue generated by shortening passenger waiting time, It is represented by the average shortening of the waiting time of passengers, σ is represented by the additional revenue brought by the improvement of vehicle utilization, Δσ is represented by the average improvement of vehicle utilization, Represents the additional revenue generated by shortening service response time, is the average shortened service response time, τ is the cost saved by reducing vehicle failure rate, Δτ is the average reduced vehicle failure rate, W j Denoted as the failure rate of the jth vehicle.

[0040] Preferably, the additional revenue brought by shortening the passenger waiting time in the response decision-making module includes improved passenger satisfaction. Faster service response can improve passenger satisfaction and reduce passenger churn, thereby increasing the long-term passenger base and revenue; increased passenger loyalty. Satisfied passengers are more likely to become repeat customers and use services frequently, bringing in a continuous revenue stream; word-of-mouth marketing effect. Positive recommendations from satisfied passengers can attract new passengers without or with reduced advertising costs, thereby indirectly increasing revenue; and reducing passenger churn costs, avoiding passengers who turn to other means of transportation due to long waiting times, saving the cost of re-acquiring new passengers.

[0041] Preferably, the additional income brought by improving vehicle utilization in the response decision-making module includes improved operational efficiency, where higher vehicle utilization means that each vehicle can serve more passengers, reducing unit passenger costs; increased revenue, where more service shifts can attract more passengers, directly increasing ticket revenue; and reduced idle driving costs, reduced idle mileage, and reduced unnecessary fuel consumption and maintenance costs, indirectly increasing revenue.

[0042] Preferably, the additional revenue brought by shortening the service response time in the response decision-making module includes improving service competitiveness. Faster response time can attract time-sensitive passengers, especially business people or those with urgent travel needs; increasing market share. Compared with competitors, faster service response time can attract market share and increase revenue; enhancing brand image. Efficient service response time helps to shape the brand, attract advertising sponsorship and partners, and bring in additional revenue.

[0043] Preferably, the cost savings from reducing the vehicle failure rate in the response decision-making module include reducing maintenance costs: preventive maintenance can reduce expensive emergency repairs and parts replacement costs; avoid downtime losses, reduce downtime due to failures, avoid passenger loss and revenue loss; reduce operational interruption costs, avoid temporary scheduling adjustment costs and passenger compensation costs caused by vehicle failures; improve passenger trust, stable vehicle performance can enhance passenger trust, reduce complaint handling costs, and indirectly save expenses.

[0044] Preferably, the decision-making module can ensure the rational allocation of vehicles and human resources during peak demand periods through resource allocation strategies, avoid waste of resources, and improve operational efficiency; through risk assessment tools, it can identify potential service interruption risks, formulate emergency plans, and enhance the risk resistance of the public transportation system; through multi-objective optimization technology, it can find the best balance between satisfying passenger behavior, controlling costs, and improving service quality; through continuous learning and self-optimization mechanisms, it can gradually improve decision-making quality over time and adapt to the ever-changing market and passenger behavior.

[0045] Preferably, the key indicators include passenger behavior parameters, operational efficiency parameters, service response parameters and response decision indicators; the optimization measures of the responsive bus management system optimization module include algorithm optimization, which improves prediction accuracy and scheduling efficiency through iterative scheduling algorithms; in terms of user experience, the service of responsive buses is adjusted according to passenger feedback to meet passenger behavior; and methods for reducing operating costs, thereby ensuring the economic sustainability of the bus system while improving passenger satisfaction.

[0046] Preferably, the responsive bus management system optimization module can optimize vehicle maintenance plans, reduce unplanned downtime, and ensure high availability of the fleet by integrating historical data with current trends; through a refined cost control model, it can effectively reduce fuel consumption and human resource costs and maximize economic benefits.

[0047] Preferably, the responsive bus feedback module monitors and evaluates the quality and performance of bus services by collecting passenger feedback and providing real-time bus operation information; back-end personnel quickly respond to passengers' questions and complaints, and adjust service advantages and disadvantages through the optimization scheme in the responsive bus management system optimization module, and provide passengers with notifications and alternatives in a timely manner in emergency situations to improve passenger satisfaction and the responsiveness of the bus system.

[0048] Preferably, the responsive bus feedback module can quickly notify all relevant parties, including passengers, drivers and control centers, in an emergency through alarm reminders in emergency situations, ensuring rapid response and passenger safety; through automated report generation, it can regularly provide detailed service performance analysis to management, provide data support for decision-making, and promote efficient allocation of resources; through real-time updates of bus operation status and estimated arrival time, it can help passengers plan their trips reasonably, reduce waiting anxiety, and enhance travel confidence.

[0049] Technical effects and advantages of the present invention:

[0050] 1. The present invention can generate the optimal scheduling and resource allocation scheme to achieve the service goal by comprehensively analyzing the passenger behavior parameters, operation efficiency parameters and service response parameters through the decision-making module;

[0051] 2. The present invention uses a responsive bus management system optimization module to dynamically adjust routes and service frequencies through real-time data analysis to ensure that operational efficiency and passenger behavior are optimally matched;

[0052] 3. The present invention can accurately identify service bottlenecks and improvement points by analyzing passengers' usage habits and satisfaction surveys through the responsive bus feedback module, thereby promoting the continuous upgrading of service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0055] As attached Figure 1The demand-responsive bus management system based on artificial intelligence shown includes a demand data collection module, a demand data preprocessing module, a responsive bus management system database, a demand data analysis module, a response decision-making module, a responsive bus management system optimization module and a responsive bus feedback module.

[0056] The demand data collection module is used to collect information related to passenger demand of demand-responsive public transportation, including passenger behavior data, operational efficiency data, and service response data, to form a demand data information set, and transmit it to the demand data preprocessing module.

[0057] The passenger demand related information, including passenger behavior data information, includes a time series represented by the number of passengers per day, per week or per hour and a set of passenger behavior information.

[0058] The data information of the operational efficiency includes a passenger demand data set, a vehicle quantity data set, a time step data set, fixed costs, and variable costs.

[0059] The fixed costs include depreciation, administrative expenses, advertising and marketing expenses, and maintenance expenses.

[0060] The variable costs include fuel, maintenance, and road tax calculated by kilometer or bridge tolls in some places.

[0061] The data information of the service response includes the average number of reservations per unit time, the average time from when passengers get on to when they get off the vehicle, the average number of passengers arriving at passenger vehicles per unit time, the average number of passengers that can be served by a single passenger vehicle per unit time, and the number of vehicles that can be served simultaneously. The unit time is a constant preset in the database.

[0062] The demand data preprocessing module is used to clean, format, standardize and process outliers on the demand data information set transmitted in the demand data acquisition module, and transmit it to the demand data analysis module and the responsive public transportation management system database.

[0063] The demand data preprocessing module receives raw data from the demand data acquisition module, performs data cleaning, removes invalid and duplicate data, identifies and properly processes outliers, corrects errors, converts the data into a unified format, prepares for data loading, and loads the cleaned and converted data into the database.

[0064] The demand data preprocessing module receives each raw data from the demand data acquisition module and records them as observation values. When the observation value is numerical data, the missing value is filled with the average value of the column; when the observation value is categorical data, the missing value is filled with the category with the largest number of occurrences.

[0065] The demand data preprocessing module can remove irrelevant and erroneous data through data cleaning to ensure the purity and accuracy of the data set; by formatting and standardizing data, it can ensure that all data follows a unified format and measurement standard to facilitate subsequent data analysis and processing; through outlier processing, it can identify and appropriately adjust or delete abnormal data points to avoid outliers from biasing the data analysis results; through missing value filling, it can use reasonable statistical methods to fill data gaps and reduce the impact of data incompleteness on the analysis effect; through data loading, it can efficiently import preprocessed data into the database to provide an immediately available data source for real-time analysis and decision-making; through the automation of the preprocessing process, it can reduce human intervention, reduce the error rate of data processing, and improve the efficiency and reliability of data processing; through data quality control, it can ensure the high quality of data before the data enters the analysis stage, providing a solid data foundation for subsequent business decisions; through data preprocessing, it can improve the accuracy and timeliness of data analysis, so that the demand-responsive bus management system can more accurately predict demand and optimize scheduling.

[0066] The responsive bus management system database is used to store the passenger demand data information set collected from the demand data acquisition module, the data cleaned and converted by the demand data preprocessing module, and the passenger behavior parameters, operation efficiency parameters and service response parameters generated by the demand data analysis module.

[0067] The demand data analysis module is used to analyze the demand data information set transmitted by the demand data preprocessing module, analyze the passenger behavior data, the bus operation efficiency data and the system service response data, obtain the passenger behavior parameters, operation efficiency parameters and service response parameters, and transmit them to the response decision making module.

[0068] The demand data analysis module includes a passenger behavior analysis unit, an operation efficiency analysis unit and a service response analysis unit.

[0069] The passenger behavior analysis unit is used to analyze the passenger behavior data transmitted in the demand data preprocessing module, establish a calculation model of passenger behavior, generate passenger demand parameters, and transmit them to the response decision making module.

[0070] The calculation model of the passenger behavior is specifically expressed as: γ 1 =φ(B)(1-B) d X t -θ(B)∈ t , where Υ 1 is represented by the passenger behavior parameter, and B is represented by the backshift operator, denoted by BX t =X t-1, φ(B) represents the autoregressive polynomial of passenger behavior, θ(B) represents the moving average polynomial of passenger behavior, d represents the degree of difference, X t is the time series of the passenger behavior information set at time t, ε t is the error term.

[0071] The autoregressive polynomial φ(B) = α 1 X t-1 +α 2 X t-2 +...+α p X t-p +∈ t , where α 1 , α 2 , ..., α p is represented by the autoregressive coefficient, and p is represented by the order of the autoregressive polynomial; the autoregressive coefficient

[0072] The moving average polynomial in, It is represented as the mean of the time series of passenger behavior information set, β 1 , β 2 , ..., β q Expressed as a moving average coefficient, q is the order of the moving average polynomial; the moving average coefficient β 1 ,β 2 ,...,β q

[0073] =([ε t-1 ε t-2 ... ε t-q ] T [ε t-1 ε t-2 ... ε t-q ]) -1 [ε t-1 ε t-2 ... ε t-q ]

[0074] The number of differences d = X t -X t-1 , the autoregressive polynomial order p = α t -α t-1 , the order of the moving average polynomial is q=ε t -ε t-1 ; The difference When ε t =0, the model fitting iteration makes the error term of the sequence approach white noise.

[0075] The passenger behavior analysis unit helps predict future demand by analyzing the passenger demand analysis set; by analyzing historical passenger behavior data, it can identify travel patterns and modes; by identifying peak hours, it can help bus companies reasonably arrange shifts and vehicles and reduce passenger waiting time; by identifying popular routes, it can optimize line layout and increase the frequency of shifts to improve passenger satisfaction; by predicting future demand, it can plan vehicle maintenance and procurement in advance to reduce operating costs; by real-time monitoring of passenger flow, it can instantly adjust the departure frequency to cope with sudden changes in passenger flow.

[0076] The operation efficiency analysis unit is used to analyze the operation efficiency data transmitted in the demand data preprocessing module, establish a calculation model of operation efficiency, generate operation efficiency parameters, and transmit them to the response decision-making module.

[0077] The calculation model of the operational efficiency is specifically expressed as follows: Among them 2 is the operational efficiency parameter, I is the passenger demand set, J is the vehicle set, T is the time step set, and C ijt Denote the cost of assigning vehicle j to passenger i at time t, x ijt Denotes the decision variable for assigning vehicle j to passenger i at time t, F jt It is expressed as the cost of vehicle j being idle at time t, y jt Denote as the decision variable for vehicle j being idle at time t.

[0078] The decision variable for allocating vehicle j to passenger i at time t and the decision variable for vehicle j being idle at time t both have values ​​of 0 or 1. The cost of vehicle j being idle at time t includes fuel consumption, driver wages, etc.

[0079] The operational efficiency needs to meet all constraints, including: routes that meet the needs of all passengers: The number of passengers does not exceed the vehicle capacity: Comply with time requirements: Meeting the continuity requirements of passenger vehicles: Ensure vehicle status:

[0080] The r i Denotes the i-th passenger route, k j It is represented by the capacity of the jth vehicle, r j Denotes the service rate of the jth vehicle, represents the reservation time and estimated arrival time of the passenger, z ijti′jt′ =1 means that vehicle j serves passenger i at time t and serves another passenger i′ at the same time period t′.

[0081] The operation efficiency analysis unit can establish a refined operation efficiency calculation model by receiving and parsing the operation efficiency data transmitted by the demand data preprocessing module, and construct a multi-dimensional analysis framework including a passenger demand set, a vehicle set, and a time step set, so as to comprehensively evaluate the comprehensive performance of the operation system and ensure the rationality of resource allocation; by quantifying costs and decision variables, it can accurately calculate the actual expenses of each business, optimize the cost control strategy, and improve the overall operation efficiency; by ensuring that all decision variables take the value of 0 or 1, it can implement clear and unambiguous scheduling instructions and avoid resource conflicts; by meeting the route needs of all passengers, it can ensure that the itineraries of all passengers are properly arranged and the service quality is improved; by complying with vehicle capacity restrictions, it can prevent overloading and ensure driving safety and passenger comfort; by complying with time requirements, it can accurately match passenger reservations with actual service times, reduce waiting, and improve customer satisfaction; by maintaining the continuity of passenger vehicles, it can ensure the continuity of vehicle service processes, avoid invalid driving, and improve operational fluency; by monitoring vehicle status, it can timely discover and solve potential faults and keep the fleet in good operating condition.

[0082] The service response analysis unit is used to analyze the service response data transmitted in the demand data preprocessing module, establish a calculation model of the service response, generate service response parameters, and transmit them to the response decision-making module.

[0083] The calculation model of the service response is specifically expressed as where γ 3 It is represented as the service response parameter; λ is the average number of passengers arriving at the passenger vehicle per unit time; μ is the average number of passengers that can be served by a single passenger vehicle per unit time, and n is the number of vehicles that can be served at the same time.

[0084] The service response analysis unit can accurately evaluate the service efficiency and passenger demand matching by deeply analyzing and modeling the received service response data, and optimize the response mechanism. By calculating the average number of passengers arriving at passenger vehicles per unit time, it can gain insight into passenger flow trends, predict peak hours, and deploy resources in advance; by analyzing the average number of passengers that can be served by a single passenger vehicle per unit time, it can evaluate the vehicle service capacity and reasonably plan the vehicle configuration; by analyzing the number of vehicles that can be served at the same time, it can dynamically adjust vehicle scheduling to ensure maximum service coverage and meet the immediate needs of passengers.

[0085] The response decision-making module is used to analyze the passenger behavior parameters, operation efficiency parameters and service response parameters transmitted by the demand data analysis module, establish a calculation model for response decision-making, generate response decision indicators, and transmit them to the responsive public transportation management system optimization module.

[0086] The computational model for response decision making is specifically expressed as Where Ψ represents the response decision indicator, represents the additional revenue generated by shortening passenger waiting time, is the average shortened waiting time of passengers, σ is the additional revenue brought by the improved vehicle utilization, Δσ is the average improved vehicle utilization, ζ is the additional revenue brought by the shortened service response time, Δζ is the average shortened service response time, τ is the cost saved by reducing the vehicle failure rate, Δτ is the average reduced vehicle failure rate, and W j Denoted as the failure rate of the j-th vehicle.

[0087] The additional revenue brought by shortening the waiting time of passengers in the response decision-making module includes improved passenger satisfaction. Faster service response can improve passenger satisfaction and reduce passenger churn, thereby increasing the long-term passenger base and revenue; increased passenger loyalty. Satisfied passengers are more likely to become repeat customers and use the service frequently, bringing in a continuous revenue stream; word-of-mouth marketing effect. Positive recommendations from satisfied passengers can attract new passengers without or with reduced advertising costs, thereby indirectly increasing revenue; and reduced passenger churn costs, avoiding passengers who turn to other means of transportation due to long waiting times, saving the cost of re-acquiring new passengers.

[0088] The additional revenue brought by improving vehicle utilization in the response decision-making module includes improved operational efficiency. Higher vehicle utilization means that each vehicle can serve more passengers, reducing unit passenger costs; revenue growth. More service shifts can attract more passengers, directly increasing ticket revenue; reducing idle driving costs, reducing idle mileage, and reducing unnecessary fuel consumption and maintenance costs, indirectly increasing revenue.

[0089] The additional revenue brought by shortening the service response time in the response decision-making module includes improving service competitiveness. Faster response time can attract time-sensitive passengers, especially business people or those with urgent travel needs; increasing market share. Compared with competitors, faster service response time can attract market share and increase revenue; and enhancing brand image. Efficient service response time helps to shape the brand, attract advertising sponsorship and partners, and bring in additional revenue.

[0090] The cost savings from reducing the vehicle failure rate in the response decision-making module include reducing maintenance costs: preventive maintenance can reduce expensive emergency repairs and parts replacement costs; avoid downtime losses, reduce downtime due to failures, avoid passenger loss and revenue loss; reduce operational interruption costs, avoid temporary scheduling adjustment costs and passenger compensation costs caused by vehicle failures; improve passenger trust, stable vehicle performance can enhance passenger trust, reduce complaint handling costs, and indirectly save expenses.

[0091] The decision-making module can generate the optimal scheduling and resource allocation plan to achieve service goals by comprehensively analyzing passenger behavior parameters, operational efficiency parameters and service response parameters; through resource allocation strategies, it can ensure the rational allocation of vehicles and human resources during peak demand periods, avoid resource waste and improve operational efficiency; through risk assessment tools, it can identify potential service interruption risks, formulate emergency plans and enhance the risk resistance of the public transportation system; through multi-objective optimization technology, it can find the best balance between satisfying passenger behavior, controlling costs and improving service quality; through continuous learning and self-optimization mechanisms, it can gradually improve decision-making quality over time and adapt to the ever-changing market and passenger behavior.

[0092] The responsive public transport management system optimization module is used to identify service advantages and disadvantages and optimize key indicators through the analysis response decision indicators transmitted by the response decision making module and the demand data transmitted by the responsive public transport management system database.

[0093] The key indicators include passenger behavior parameters, operational efficiency parameters, service response parameters and response decision indicators; the optimization measures of the responsive bus management system optimization module include algorithm optimization, which improves prediction accuracy and scheduling efficiency through iterative scheduling algorithms; in terms of user experience, the responsive bus service is adjusted according to passenger feedback to meet passenger behavior; methods to reduce operating costs, thereby ensuring the economic sustainability of the bus system while improving passenger satisfaction.

[0094] The responsive bus management system optimization module can dynamically adjust routes and service frequencies through real-time data analysis to ensure that operational efficiency and passenger behavior are optimally matched; by integrating historical data with current trends, it can optimize vehicle maintenance plans, reduce unplanned outages, and ensure high availability of the fleet; through a refined cost control model, it can effectively reduce fuel consumption and human resource costs to maximize economic benefits.

[0095] The responsive bus feedback module is used for passenger interaction and monitoring of demand-responsive bus service quality, delivering information and quickly responding to problems and providing timely notification and solutions in emergency situations.

[0096] The responsive bus feedback module monitors and evaluates the quality and performance of bus services by collecting passenger feedback and providing real-time bus operation information; back-end personnel quickly respond to passengers' questions and complaints, and adjust service advantages and disadvantages through the optimization plan in the responsive bus management system optimization module, and provide passengers with notifications and alternative plans in a timely manner in emergency situations to improve passenger satisfaction and the responsiveness of the bus system.

[0097] The responsive bus feedback module can accurately identify service bottlenecks and improvement points by analyzing passengers' usage habits and satisfaction surveys, thereby promoting the continuous upgrading of service quality. Through emergency alarm reminders, it can quickly notify all relevant parties, including passengers, drivers and control centers, to ensure rapid response and passenger safety. Through automated report generation, it can regularly provide detailed service performance analysis to management, provide data support for decision-making, and promote efficient allocation of resources. Through real-time updates of bus operation status and estimated arrival time, it can help passengers plan their trips reasonably, reduce waiting anxiety, and enhance travel confidence.

[0098] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0099] 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 protection scope of the present invention.

Claims

1. A demand-responsive public transportation management system based on artificial intelligence, characterized in that: include: Demand data collection module: used to collect information related to passenger demand for demand-responsive public transportation, including passenger behavior data, operational efficiency data, and service response data, to form a demand data information set, and transmit it to the demand data preprocessing module; Demand data preprocessing module: used to clean, format, standardize and process outliers of the demand data information set transmitted in the demand data acquisition module, and transmit it to the demand data analysis module and the responsive bus management system database; Responsive bus management system database: used to store the passenger demand data information set collected from the demand data acquisition module, the data cleaned and converted by the demand data preprocessing module, and the passenger behavior parameters, operation efficiency parameters and service response parameters generated by the demand data analysis module; Demand data analysis module: used to analyze the demand data information set transmitted by the demand data preprocessing module, analyze the passenger behavior data, bus operation efficiency data and system service response data, obtain passenger behavior parameters, operation efficiency parameters and service response parameters, and transmit them to the response decision making module; The demand data analysis module includes a passenger behavior analysis unit, an operation efficiency analysis unit and a service response analysis unit; Response decision-making module: used to analyze the passenger behavior parameters, operation efficiency parameters and service response parameters transmitted by the demand data analysis module, establish a calculation model for response decision-making, generate response decision indicators, and transmit them to the responsive bus management system optimization module; Responsive bus management system optimization module: used to analyze the response decision indicators transmitted by the response decision-making module and the demand data transmitted by the responsive bus management system database, identify service advantages and disadvantages, and optimize key indicators; Responsive Bus Feedback Module: Used for passenger interaction and monitoring of demand-responsive bus service quality, delivering information and quickly responding to issues and providing timely notification and solutions in emergency situations.

2. The demand-responsive public transportation management system based on artificial intelligence according to claim 1 is characterized by: The passenger demand-related information includes passenger behavior data information including a time series of the number of passengers per day, week or hour and a passenger behavior information set; the operational efficiency data information includes a passenger demand data set, a vehicle quantity set, a time step data set, fixed costs and variable costs; the service response data information includes the average number of reservations per unit time, the average time from the passenger getting on to the passenger getting off the vehicle, the average number of passengers arriving at a passenger vehicle per unit time, the average number of passengers that can be served by a single passenger vehicle per unit time, and the number of vehicles that can be served simultaneously, wherein the unit time is a constant preset in the database.

3. The demand-responsive public transportation management system based on artificial intelligence according to claim 1 is characterized by: The demand data preprocessing module receives raw data from the demand data acquisition module, performs data cleaning, removes invalid and duplicate data, identifies and appropriately processes outliers, corrects errors, converts the data into a unified format, prepares for data loading, and loads the cleaned and converted data into the database; The demand data preprocessing module receives each raw data from the demand data acquisition module and records them as observation values. When the observation value is numerical data, the missing value is filled with the average value of the column; when the observation value is categorical data, the missing value is filled with the category with the largest number of occurrences.

4. The demand-responsive public transportation management system based on artificial intelligence according to claim 1 is characterized by: The calculation model of the passenger behavior is specifically expressed as: γ1 = φ(B)(1-B) d X t -θ(B)∈ t , where Υ1 represents the passenger behavior parameter, B represents the backshift operator, denoted by BX t =X t-1 , φ(B) represents the autoregressive polynomial of passenger behavior, θ(B) represents the moving average polynomial of passenger behavior, d represents the degree of difference, X t is the time series of the passenger behavior information set at time t, ε t is the error term.

5. The demand-responsive public transportation management system based on artificial intelligence according to claim 1 is characterized by: The computational model of passenger behavior, where the autoregressive polynomial φ(B) = α1X t-1 +α2X t-2 +...+α p X t-p +∈ t , where α1, α2, ..., α p is represented by the autoregressive coefficient, and p is represented by the order of the autoregressive polynomial; the autoregressive coefficient The moving average polynomial in, It is represented as the mean of the time series of passenger behavior information set, β1,β2,...,β q Expressed as a moving average coefficient, q is the order of the moving average polynomial; the moving average coefficient 6. The demand-responsive public transportation management system based on artificial intelligence according to claim 1, characterized in that: The calculation model of the operational efficiency is specifically expressed as follows: Where Υ2 represents the operational efficiency parameter, I represents the passenger demand set, J represents the vehicle set, T represents the time step set, and C ijt Denote the cost of assigning vehicle j to passenger i at time t, x ijt Denotes the decision variable for assigning vehicle j to passenger i at time t, F jt It is expressed as the cost of vehicle j being idle at time t, y jt Denote as the decision variable for vehicle j being idle at time t.

7. The demand-responsive public transportation management system based on artificial intelligence according to claim 1 is characterized by: The calculation model of the operational efficiency needs to satisfy all constraints, including: satisfying the routes of all passengers: The number of passengers does not exceed the vehicle capacity: Comply with time requirements: Meeting the continuity requirements of passenger vehicles: Ensure vehicle status:

8. The demand-responsive public transportation management system based on artificial intelligence according to claim 1 is characterized by: The calculation model of the service response is specifically expressed as Where Υ3 represents the service response parameter; λ represents the average number of passengers arriving at a passenger vehicle per unit time; μ represents the average number of passengers that a single passenger vehicle can serve per unit time, and n represents the number of vehicles that can be served at the same time.

9. The demand-responsive public transportation management system based on artificial intelligence according to claim 1, characterized in that: The computational model for response decision making is specifically expressed as Where Ψ represents the response decision indicator, represents the additional revenue generated by shortening passenger waiting time, It is represented by the average shortening of the waiting time of passengers, σ is represented by the additional revenue brought by the improvement of vehicle utilization, Δσ is represented by the average improvement of vehicle utilization, Represents the additional revenue generated by shortening service response time, is the average shortened service response time, τ is the cost saved by reducing vehicle failure rate, Δτ is the average reduced vehicle failure rate, W j Denoted as the failure rate of the jth vehicle.

Images