Dynamic public transport scheduling optimization system and method based on artificial intelligence

Abstract

The invention discloses a dynamic public transport scheduling optimization system based on artificial intelligence, and the system comprises a mobile application program which is used for collecting the feedback of passengers, and displaying the real-time bus information, predicted arrival time, route suggestions and ticket price information to the passengers; the background management module is used for monitoring the state of the optimization system, adjusting a scheduling strategy and managing for feedback, and regularly maintaining and updating the optimization system; the data collection module is used for collecting vehicle GPS data, traffic flow monitoring data, weather conditions, special event information and historical and real-time data fed back in real time on social media; and the multi-modal traffic data fusion processing module is used for fusing the historical and real-time data collected by the data collection module and preprocessing the historical and real-time data. The invention also discloses a dynamic public transport scheduling optimization method based on artificial intelligence. According to the invention, the operation efficiency and the passenger satisfaction degree of public transportation are improved.

Description

Technical Field

[0001] The invention relates to a dynamic public transportation scheduling optimization system and method based on artificial intelligence. Background Art

[0002] Most existing public transportation scheduling systems operate based on fixed schedules and routes, and these systems often lack sufficient flexibility to cope with real-time changes in passenger flow and unpredictable traffic conditions. Traditional scheduling methods rely on manual experience and historical data, but these methods cannot effectively handle large-scale real-time data streams and are difficult to adapt to rapidly changing traffic needs. In addition, traditional systems are usually unable to fully integrate data from different sources, such as on-board GPS, traffic cameras, mobile applications, and social media information, thus missing the opportunity to improve scheduling efficiency through multimodal data analysis. Passenger behavior prediction and personalized services are often not considered in existing systems, resulting in the inability to provide passengers with more accurate and personalized travel recommendations.

[0003] In terms of fare strategies, most systems use static pricing and cannot be adjusted dynamically based on real-time passenger flow and vehicle congestion, which may lead to overcrowding during peak hours and waste of resources during off-peak hours. In emergencies, existing systems often lack rapid response mechanisms, making it difficult to quickly re-plan routes and schedule to minimize the impact on passenger travel. Finally, existing systems rarely consider the impact of scheduling decisions on the environment, such as carbon emissions, energy consumption, and noise pollution, which is particularly important in the current context of the global promotion of green travel and sustainable development.

[0004] Existing public transportation dispatching systems have obvious limitations in real-time data processing, forecast accuracy, personalized services, dynamic pricing, emergency response, and environmental assessment.

[0005] Therefore, a dynamic public transportation scheduling optimization system and method based on artificial intelligence is provided. Summary of the invention

[0006] The purpose of the present invention is to overcome the existing defects and provide a dynamic public transportation scheduling optimization system and method based on artificial intelligence, thereby improving the operational efficiency of public transportation and passenger satisfaction.

[0007] The technical solution to achieve the above purpose is: The present invention provides a dynamic public transportation dispatch optimization system based on artificial intelligence, comprising: Data collection module, which collects historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media; A multimodal traffic data fusion processing module, used to fuse the historical and real-time data collected by the data collection module and preprocess the data, and the preprocessing methods include but are not limited to data cleaning and formatting; The demand behavior analysis module is used to predict the passenger demand results in the next few hours through the constructed passenger behavior prediction model based on historical passenger travel data and real-time information. The historical passenger travel data includes travel time, route and frequency. Dynamic scheduling adjustment module, used to dynamically adjust the departure interval and route of public transportation vehicles through route optimization scheduling algorithm model according to passenger demand results; Dynamic fare adjustment module, used to dynamically adjust fares through a preset algorithm based on real-time passenger flow and vehicle congestion; Emergency response and dispatch module, which is used to identify events and trigger preset dispatch plans in emergency situations based on vehicle GPS data, traffic flow monitoring data, weather conditions, special event information and real-time feedback on social media, and quickly re-plan routes and dispatch; An environmental impact assessment module, used to assess the potential impact of the dispatching schemes generated by the dynamic dispatching adjustment module, the dynamic fare adjustment module and the emergency response and dispatching module on the environment, and select the dispatching scheme with the least environmental impact; A dispatch execution module, which is used to communicate in real time to public transportation vehicles the selected route optimization dispatch plan with the least environmental impact, the dynamic adjustment of fare plan, or the identification of events in emergency situations and the triggering of preset dispatch plans, wherein public transportation vehicles include but are not limited to buses and subways; A mobile app to collect feedback from passengers and show passengers real-time bus information, estimated arrival times, route suggestions and fare information; The background management module is used to monitor the optimization system status, adjust the scheduling strategy and manage feedback, and regularly maintain and update the optimization system.

[0008] Preferably, the optimization system adopts a modular design and can be customized according to the specific needs of different cities and transportation operators. Customization solutions include but are not limited to adding new transportation tools, service areas or scheduling strategies.

[0009] Preferably, the optimization system can also collect opinions and suggestions from operators through the vehicle-mounted system.

[0010] Preferably, in the demand behavior analysis module, the passenger behavior prediction model is constructed by an adaptive learning algorithm, and the adaptive learning algorithm includes but is not limited to machine learning and deep learning techniques, and algorithms that can process time series data and spatial data.

[0011] Preferably, in the environmental impact assessment module, the impact on the environment includes but is not limited to carbon emissions, energy consumption and noise pollution.

[0012] Preferably, the optimization system also includes a security protocol for ensuring that data transmission and processing comply with security standards.

[0013] The second method of the present invention for optimizing dynamic public transportation scheduling based on artificial intelligence includes: Step S1, collecting historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media; Step S2, integrating historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media, and pre-processing them; Step S3, predicting the passenger demand results in the next few hours through the constructed passenger behavior prediction model based on the historical passenger travel data and real-time information, wherein the historical passenger travel data includes travel time, route and frequency; Step S4, according to the passenger demand results, dynamically adjust the departure interval and route of public transportation through the route optimization scheduling algorithm model to generate a corresponding route optimization scheduling plan; Step S5, dynamically adjusting the fare through a preset algorithm according to the real-time passenger flow and vehicle congestion, and generating a corresponding dynamically adjusted fare plan; Step S6, in an emergency, based on vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media, identify events and trigger preset dispatch plans, quickly re-plan routes and dispatch, and generate corresponding emergency events and trigger preset dispatch plans; Step S7, evaluating the potential environmental impact of different route optimization scheduling schemes, dynamic fare adjustment schemes, or emergency events identified and triggered by preset scheduling schemes, and selecting the scheduling scheme with the least environmental impact; Step S8, transmitting the selected route optimization scheduling scheme with the least environmental impact, the dynamic fare adjustment scheme, or the emergency event recognition and triggering preset scheduling scheme to public transportation in real time, and implementing the scheduling scheme, wherein the public transportation includes but is not limited to buses and subways; Step S9, collecting feedback from passengers and operators through the mobile application and the vehicle system respectively; Step S10, integrating the feedback from passengers and operators, and optimizing the system based on the feedback from users and operators.

[0014] Preferably, in step S4, the time window of the route optimization scheduling algorithm model is set to 15 minutes, considering that the vehicle utilization rate is not less than 70%; the route optimization scheduling plan considers content including but not limited to vehicle operating costs, passenger waiting time and vehicle load rate, so as to achieve the best balance between operating costs and passenger satisfaction.

[0015] Preferably, in step S5, a carriage congestion threshold is set, and when the set threshold exceeds 90%, a fare reduction mechanism for vehicles on other routes or schedules is automatically triggered to attract passengers to choose other routes or schedules, that is, during peak hours, the fare will be appropriately increased to disperse passenger flow, and during non-peak hours, the fare will be reduced to attract more passengers.

[0016] The beneficial effects of the present invention are: The present invention can realize efficient dispatching and route planning of public transportation, improve transportation efficiency, reduce resource waste, and significantly enhance passengers' travel experience. At the same time, the system is designed with scalability and flexibility in mind, and can adapt to the specific needs of different cities and transportation operators, thus having broad application prospects. The present invention solves a number of key technical problems in the field of public transportation scheduling by adopting advanced data collection technology, machine learning algorithm, optimization algorithm, emergency response mechanism, environmental assessment module, user feedback analysis, modular design and safety protocol, including real-time large-scale traffic data processing, accurate prediction of passenger demand, automation of dynamic scheduling, provision of personalized travel services, dynamic pricing strategy based on real-time traffic, rapid response in emergency situations, comprehensive assessment of environmental impact, effective integration of user feedback, scalability and customization of system architecture, as well as data security and passenger privacy protection; the present invention not only improves the scheduling efficiency and passenger satisfaction of public transportation vehicles, but also enhances the flexibility and customizability of services, while ensuring the safety of operations and the protection of passenger privacy, providing an effective solution for the modernization and intelligence of urban public transportation systems; The present invention includes real-time multi-source data collection and processing technology, adaptive learning algorithm, multimodal data fusion, dynamic scheduling and route planning, real-time dynamic pricing, emergency response mechanism, environmental impact assessment, user feedback integration, modular system architecture, and security and privacy protection measures, and builds an efficient, intelligent, and customizable public transportation scheduling optimization system. Through accurate demand forecasting, flexible scheduling adjustment, personalized service provision, environmentally friendly operation strategy, and enhanced data security and privacy protection, it significantly improves the operation efficiency and passenger satisfaction of public transportation, while ensuring the sustainable development of the system and adapting to the diverse needs of different cities and operators; The present invention significantly improves the transportation efficiency of the public transportation system, reduces vehicle idling and passenger waiting time through real-time data analysis and dynamic scheduling optimization; enhances passenger experience and increases the attractiveness of public transportation through personalized travel suggestions and dynamic pricing strategies; modular design improves the adaptability and flexibility of the system to meet the customized needs of different cities and operators; environmental impact assessment supports green travel and promotes sustainable development; enhanced security and privacy protection measures increase user trust in the system; optimized resource allocation reduces operating costs and increases operating income; system reliability and stability are enhanced, reducing service interruptions; finally, the present invention promotes the modernization of intelligent transportation systems, provides innovative technical solutions for the intelligentization of urban transportation, and brings extensive social and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a module diagram of the dynamic public transportation dispatch optimization system based on artificial intelligence of the present invention; Figure 2 It is a flow chart of the dynamic public transportation scheduling optimization method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] like Figure 1 As shown, the dynamic public transportation scheduling optimization system based on artificial intelligence includes: a data collection module 1, a multimodal traffic data fusion processing module 2, a demand behavior analysis module 3, a dynamic scheduling adjustment module 4, a dynamic fare adjustment module 5, an emergency response and scheduling module 6, an environmental impact assessment module 7, a scheduling execution module 8, a mobile application 9 and a background management module 10.

[0021] The optimization system is deployed on a cloud server, equipped with a high-performance multi-core processor, large-capacity memory, and high-speed SSD storage devices; the operating system is Linux, the development environment uses Python language, and integrates machine learning frameworks such as TensorFlow and PyTorch, as well as PostgreSQL database for data storage and processing; the server configuration includes a high-speed multi-core CPU, at least 16GB of RAM, and a high-speed NVMe SSD to ensure that the system can quickly process large amounts of real-time data.

[0022] The data collection module 1 is used to collect historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media. Specifically, the vehicle location data is collected at a frequency of 5 seconds through the vehicle-mounted GPS and traffic monitoring equipment, and the traffic flow monitoring data is collected once a minute. These data are used for subsequent traffic flow analysis and passenger demand prediction, and the data collection frequency can be adjusted according to the data type and availability. For example, the vehicle location data is updated every 2 seconds, while the weather data is updated every 30 minutes.

[0023] The multimodal traffic data fusion processing module 2 is used to fuse the historical and real-time data collected by the data collection module 1 and preprocess them. The preprocessing methods include but are not limited to data cleaning and formatting. By setting a 95% data cleaning threshold to remove noise and exclude outliers, the accuracy and reliability of the data set are ensured. After that, the data is sent to the analysis engine, which uses a variety of adaptive learning algorithms to identify and predict traffic patterns.

[0024] The demand behavior analysis module 3 is used to predict the passenger demand results in the next few hours through the constructed passenger behavior prediction model based on historical passenger travel data and real-time information, wherein the historical passenger travel data includes travel time, route and frequency.

[0025] In an embodiment, a passenger behavior prediction model is constructed by an adaptive learning algorithm, and the adaptive learning algorithm includes but is not limited to machine learning and deep learning techniques, and algorithms that can process time series data and spatial data.

[0026] The dynamic scheduling adjustment module 4 is used to dynamically adjust the departure interval and route of public transportation vehicles according to the passenger demand results through the route optimization scheduling algorithm model.

[0027] In the embodiment, the time window of the route optimization scheduling algorithm model is set to 15 minutes, and the vehicle utilization rate is considered to be no less than 70%; the route optimization scheduling plan considers but is not limited to vehicle operating costs, passenger waiting time and vehicle load rate, so as to achieve the best balance between operating costs and passenger satisfaction.

[0028] The dynamic fare adjustment module 5 is used to dynamically adjust the fare through a preset algorithm according to the real-time passenger flow and vehicle congestion.

[0029] In the embodiment, a carriage congestion threshold is set. When the set threshold is exceeded by 90%, a fare reduction mechanism for vehicles on other routes or schedules is automatically triggered to attract passengers to choose other routes or schedules. That is, during peak hours, the fare will be appropriately increased to disperse passenger flow, and during non-peak hours, the fare will be reduced to attract more passengers.

[0030] The emergency response and dispatch module 6 is used to identify events and trigger preset dispatch plans in emergency situations based on vehicle GPS data, traffic flow monitoring data, weather conditions, special event information and real-time feedback on social media, and quickly re-plan routes and dispatch. That is, by simulating a scenario in which a route is interrupted due to a traffic accident, the system completes route re-planning and dispatch adjustment within 5 minutes.

[0031] The environmental impact assessment module 7 is used to assess the potential impact of the dispatching schemes generated by the dynamic dispatching adjustment module 4, the dynamic fare adjustment module 5 and the emergency response and dispatching module 6 on the environment, and select the dispatching scheme with the least environmental impact.

[0032] In an embodiment, the impact on the environment includes but is not limited to carbon emissions, energy consumption and noise pollution.

[0033] The dispatch execution module 8 is used to communicate the selected route optimization dispatch plan with the least environmental impact, the dynamic fare adjustment plan, or the identification of events in emergency situations and triggering of preset dispatch plans in real time to public transportation, where public transportation includes but is not limited to buses and subways.

[0034] Mobile application 9, which is used to collect feedback from passengers and display real-time bus information, estimated arrival time, route suggestions and fare information to passengers.

[0035] The background management module 10 is used to monitor the optimization system status, adjust the scheduling strategy and manage the feedback, and regularly maintain and update the optimization system.

[0036] In an embodiment, the optimization system may also collect opinions and suggestions from operators through the vehicle-mounted system.

[0037] In the embodiment, by collecting passenger feedback and operator feedback, natural language processing technology is used to analyze passenger and operator opinions, and the collected feedback is used to optimize system services.

[0038] In the embodiment, the optimization system adopts a modular design and can be customized according to the specific needs of different cities and transportation operators. The customization scheme includes but is not limited to adding new transportation tools, service areas or scheduling strategies.

[0039] In an embodiment, the optimization system further includes a security protocol for ensuring that data transmission and processing between modules comply with security standards.

[0040] In the embodiment, after the system is built, the system is fully tested in a simulation environment, including unit testing, integration testing, and stress testing, to ensure that the system runs stably during a continuous 72-hour stability test.

[0041] The system of the present invention can realize efficient dispatching and route planning of public transportation, improve transportation efficiency, optimize passenger experience, and support sustainable and environmentally friendly transportation development. At the same time, the modular design and user interface of the system provide good user experience and operational convenience, while the powerful security protocol ensures the security of data and the protection of passenger privacy.

[0042] like Figure 2 As shown, the dynamic public transportation scheduling optimization method based on artificial intelligence includes: Step S1, collect historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media.

[0043] Specifically, vehicle location data is collected at a frequency of 5 seconds through on-board GPS and traffic monitoring equipment, and traffic flow monitoring data is collected once a minute. These data are used for subsequent traffic flow analysis and passenger demand prediction, and the data collection frequency can be adjusted according to the data type and availability. For example, vehicle location data is updated every 2 seconds, while weather data is updated every 30 minutes.

[0044] Step S2, integrates historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media, and preprocesses them. The preprocessing methods include but are not limited to data cleaning and formatting. By setting a 95% data cleaning threshold to remove noise and exclude outliers, the accuracy and reliability of the data set are ensured. After that, the data is sent to the analysis engine, which uses a variety of adaptive learning algorithms to identify and predict traffic patterns.

[0045] Step S3, based on historical passenger travel data and real-time information, the passenger demand results in the next few hours are predicted by the constructed passenger behavior prediction model, wherein the historical passenger travel data includes travel time, route and frequency.

[0046] Step S4, according to the passenger demand results, the departure interval and route of public transportation are dynamically adjusted through the route optimization scheduling algorithm model to generate a corresponding route optimization scheduling plan.

[0047] In the embodiment, the time window of the route optimization scheduling algorithm model is set to 15 minutes, and the vehicle utilization rate is considered to be no less than 70%; the route optimization scheduling plan considers content including but not limited to vehicle operating costs, passenger waiting time and vehicle load rate, so as to achieve the best balance between operating costs and passenger satisfaction.

[0048] Step S5, dynamically adjusting the ticket price through a preset algorithm according to the real-time passenger flow and vehicle congestion, and generating a corresponding dynamically adjusted ticket price plan.

[0049] In the embodiment, a carriage congestion threshold is set. When the set threshold is exceeded by 90%, a fare reduction mechanism for vehicles on other routes or schedules is automatically triggered to attract passengers to choose other routes or schedules. That is, during peak hours, the fare will be appropriately increased to disperse passenger flow, and during non-peak hours, the fare will be reduced to attract more passengers.

[0050] Step S6, in an emergency, identify events and trigger preset dispatch plans based on vehicle GPS data, traffic flow monitoring data, weather conditions, special event information and real-time feedback on social media, quickly re-plan routes and dispatch, generate corresponding emergency events, identify events and trigger preset dispatch plans, and notify passengers and staff.

[0051] Step S7, evaluate the potential impact of different route optimization scheduling schemes, dynamic fare adjustment schemes or emergency events identification and triggering of preset scheduling schemes on the environment, and select the scheduling scheme with the least environmental impact.

[0052] Step S8, the route optimization scheduling plan with the least environmental impact, the dynamic fare adjustment plan, or the identification of events in emergency situations and the triggering of preset scheduling plans are communicated to public transportation in real time, and the scheduling plan is implemented. Public transportation includes but is not limited to buses and subways. The scheduling instructions are sent to the vehicle's on-board system through a wireless communication network to ensure the accurate execution of the scheduling plan.

[0053] Step S9, collecting feedback from passengers and operators through the mobile application and the vehicle system respectively, as a basis for continuous improvement of the system.

[0054] Step S10, integrating the feedback from passengers and operators, and optimizing the system based on the feedback from users and operators.

[0055] In the embodiment, during operation, system performance indicators such as response time, error rate and user satisfaction are tracked in real time. Regular maintenance and updates ensure long-term stable operation of the system.

[0056] Through the above method, not only can efficient public transportation dispatch services be provided, but also the operation strategy can be dynamically adjusted according to real-time data and passenger demand, thereby improving the operation efficiency of the entire public transportation network and the travel experience of passengers. At the same time, the system's real-time monitoring and user feedback mechanism ensure the continuous optimization and improvement of services.

[0057] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some or all of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. Dynamic public transportation scheduling optimization system based on artificial intelligence, characterized by: include: Data collection module, which collects historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media; A multimodal traffic data fusion processing module, used to fuse the historical and real-time data collected by the data collection module and preprocess the data, and the preprocessing methods include but are not limited to data cleaning and formatting; The demand behavior analysis module is used to predict the passenger demand results in the next few hours through the constructed passenger behavior prediction model based on historical passenger travel data and real-time information. The historical passenger travel data includes travel time, route and frequency. Dynamic scheduling adjustment module, used to dynamically adjust the departure interval and route of public transportation vehicles through route optimization scheduling algorithm model according to passenger demand results; Dynamic fare adjustment module, used to dynamically adjust fares through a preset algorithm based on real-time passenger flow and vehicle congestion; Emergency response and dispatch module, which is used to identify events and trigger preset dispatch plans in emergency situations based on vehicle GPS data, traffic flow monitoring data, weather conditions, special event information and real-time feedback on social media, and quickly re-plan routes and dispatch; An environmental impact assessment module, used to assess the potential impact of the dispatching schemes generated by the dynamic dispatching adjustment module, the dynamic fare adjustment module and the emergency response and dispatching module on the environment, and select the dispatching scheme with the least environmental impact; A dispatch execution module, which is used to communicate in real time to public transportation vehicles the selected route optimization dispatch plan with the least environmental impact, the dynamic adjustment of fare plan, or the identification of events in emergency situations and the triggering of preset dispatch plans, wherein public transportation vehicles include but are not limited to buses and subways; A mobile app to collect feedback from passengers and show passengers real-time bus information, estimated arrival times, route suggestions and fare information; The background management module is used to monitor the optimization system status, adjust the scheduling strategy and manage feedback, and regularly maintain and update the optimization system.

2. According to claim 1, a dynamic public transportation scheduling optimization system based on artificial intelligence is characterized in that: The optimization system adopts a modular design and can be customized according to the specific needs of different cities and transportation operators. Customization solutions include but are not limited to adding new transportation tools, service areas or scheduling strategies.

3. The dynamic public transportation scheduling optimization system based on artificial intelligence according to claim 1 is characterized in that: The optimization system can also collect opinions and suggestions from operators through the on-board system.

4. The dynamic public transportation scheduling optimization system based on artificial intelligence according to claim 1 is characterized in that: In the demand behavior analysis module, a passenger behavior prediction model is constructed by an adaptive learning algorithm, and the adaptive learning algorithm includes but is not limited to machine learning and deep learning technologies, as well as algorithms that can process time series data and spatial data.

5. The dynamic public transportation scheduling optimization system based on artificial intelligence according to claim 1 is characterized in that: In the environmental impact assessment module, the impact on the environment includes but is not limited to carbon emissions, energy consumption and noise pollution.

6. The dynamic public transportation scheduling optimization system based on artificial intelligence according to claim 1 is characterized in that: The optimized system also includes a security protocol to ensure that data transmission and processing comply with security standards.

7. A dynamic public transportation scheduling optimization method based on artificial intelligence, characterized in that: include: Step S1, collecting historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media; Step S2, integrating historical and real-time data of vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media, and pre-processing them; Step S3, predicting the passenger demand results in the next few hours through the constructed passenger behavior prediction model based on the historical passenger travel data and real-time information, wherein the historical passenger travel data includes travel time, route and frequency; Step S4, according to the passenger demand results, dynamically adjust the departure interval and route of public transportation through the route optimization scheduling algorithm model to generate a corresponding route optimization scheduling plan; Step S5, dynamically adjusting the fare through a preset algorithm according to the real-time passenger flow and vehicle congestion, and generating a corresponding dynamically adjusted fare plan; Step S6, in an emergency, based on vehicle GPS data, traffic flow monitoring data, weather conditions, special event information, and real-time feedback on social media, identify events and trigger preset dispatch plans, quickly re-plan routes and dispatch, and generate corresponding emergency events and trigger preset dispatch plans; Step S7, evaluating the potential environmental impact of different route optimization scheduling schemes, dynamic fare adjustment schemes, or emergency events identified and triggered by preset scheduling schemes, and selecting the scheduling scheme with the least environmental impact; Step S8, transmitting the selected route optimization scheduling scheme with the least environmental impact, the dynamic fare adjustment scheme, or the emergency event recognition and triggering preset scheduling scheme to public transportation in real time, and implementing the scheduling scheme, wherein the public transportation includes but is not limited to buses and subways; Step S9, collecting feedback from passengers and operators through the mobile application and the vehicle system respectively; Step S10, integrating the feedback from passengers and operators, and optimizing the system based on the feedback from users and operators.

8. The method for dynamic public transportation scheduling optimization based on artificial intelligence according to claim 7 is characterized in that: In step S4, the time window of the route optimization scheduling algorithm model is set to 15 minutes, and the vehicle utilization rate is considered to be no less than 70%; the route optimization scheduling plan considers but is not limited to vehicle operating costs, passenger waiting time and vehicle load rate, so as to achieve the best balance between operating costs and passenger satisfaction.

9. The method for optimizing dynamic public transportation scheduling based on artificial intelligence according to claim 7 is characterized in that: In step S5, a carriage congestion threshold is set. When the set threshold exceeds 90%, the fare reduction mechanism for vehicles on other routes or schedules is automatically triggered to attract passengers to choose other routes or schedules. That is, during peak hours, the fare will be appropriately increased to disperse passenger flow, and during non-peak hours, the fare will be reduced to attract more passengers.

Images