Vehicle transport capacity scheduling method, system and device for smart traffic, and storage medium

By receiving and analyzing real-time ride demand information, predicting changes in ride demand, and dynamically adjusting the vehicle scheduling plan, the problem of insufficient real-time and emergency response capabilities of vehicle capacity scheduling plans in the existing technology is solved, and more efficient Operation and resource utilization.

CN119047666AInactive Publication Date: 2024-11-29EASY POINT WORRY (BEIJING) NETWORK TECH CO LTD

Patent Information

Application Number
CN202411549600.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-01
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing vehicle capacity scheduling schemes have shortcomings in real-time, prediction accuracy, optimization capabilities and emergency response capabilities, and it is difficult to meet the complex needs of modern urban transportation systems, especially in the face of emergencies, which is difficult to quickly adjust vehicle scheduling strategies.

Method used

By receiving real-time ride demand information from multiple traffic stations, combining current vehicle distribution and historical data, predict future ride demand changes, and dynamically adjust vehicle scheduling plans to optimize vehicle allocation and maximize operational efficiency. When an emergency occurs, monitor and adjust the vehicle scheduling frequency in real time to ensure the effective utilization of resources.

Benefits of technology

Improve the optimization capability and emergency response capability of vehicle capacity scheduling scheme, can predict passenger demand more accurately, dynamically adjust vehicle allocation, ensure that passenger demand meets and maximizes operational efficiency, especially in the event of emergencies, effectively deal with traffic abnormalities. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047666A_ABST
    Figure CN119047666A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle transport capacity scheduling method, system and device for smart traffic, and a storage medium. The method comprises the following steps: receiving real-time riding demand information from a plurality of traffic stations, the real-time riding demand information comprising departure places, destinations and predicted travel time of passengers; according to the real-time riding demand information, in combination with the current vehicle distribution condition of each traffic station and historical riding data, predicting the riding demand change trend of each station in a future time period; dynamically adjusting a vehicle scheduling scheme according to the riding demand quantity change trend and the obtained current position, state and carrying capacity of the vehicle so as to optimize vehicle distribution; the influence degree of different vehicle scheduling schemes on the operation efficiency is evaluated, and a target vehicle scheduling scheme is selected and implemented, so that the operation efficiency is maximized while the requirements of passengers are met. According to the technical scheme provided by the invention, the optimization capability and the emergency response capability of the vehicle transport capacity scheduling scheme are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart transportation technology, and in particular, to a vehicle capacity scheduling method, system, device and storage medium for smart transportation. Background Art

[0002] With the acceleration of urbanization, urban traffic problems have become increasingly prominent, especially during peak hours and when emergencies occur. How to efficiently and accurately dispatch vehicle resources to meet the travel needs of passengers has become an important issue in the intelligent transportation system. Modern urban transportation systems need to have real-time response capabilities, be able to quickly process passenger demand information from multiple transportation stations, and dynamically adjust vehicle scheduling plans based on this information. Specifically, the system needs to be able to receive real-time passenger demand information including the passenger's departure point, destination, and expected travel time, combine the current vehicle distribution of each transportation station with historical passenger data, predict the trend of passenger demand changes at each station in the future time period, and optimize vehicle allocation accordingly. In addition, the system also needs to evaluate the impact of different vehicle scheduling plans on operational efficiency, select and implement the target vehicle scheduling plan, and ensure that operational efficiency is maximized while meeting passenger needs.

[0003] Existing vehicle capacity dispatching schemes usually dispatch vehicles based on fixed schedules or preset routes. These schemes rely on pre-collected historical data and empirical rules, use simple algorithms to predict future ride demand, and formulate dispatching plans accordingly. For example, some systems use statistical models (such as time series analysis) to predict future ride demand and dispatch vehicles based on the predicted results. In addition, some systems have introduced real-time data processing capabilities and can dynamically adjust vehicle dispatching schemes to a certain extent, but these adjustments are often based on simple rules and limited data sources.

[0004] Existing dispatching schemes can usually only balance between a limited number of objectives, such as reducing waiting time and reducing operating costs, and cannot achieve multi-objective optimization. This makes it difficult for dispatching schemes to simultaneously meet passenger needs and maximize operational benefits in practical applications. Existing schemes often lack effective emergency response mechanisms when facing emergencies. When an emergency occurs in a specific area and causes abnormal traffic flow, it is difficult for the existing system to quickly adjust the vehicle dispatching strategy in the area and its surrounding areas, thereby affecting the safe evacuation and normal travel of passengers. In summary, the existing vehicle capacity dispatching schemes have obvious deficiencies in real-time performance, prediction accuracy, optimization capabilities, and emergency response capabilities, and are difficult to meet the complex needs of modern urban transportation systems. Summary of the invention

[0005] The embodiments of the present application provide a vehicle capacity scheduling method, system, device and storage medium for smart transportation, which are used to solve the problems of poor optimization capability and poor emergency response capability in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a vehicle capacity dispatching method for smart transportation, including: Receiving real-time ride demand information from multiple transportation stations, the real-time ride demand information including the departure place, destination and estimated travel time of passengers; According to the real-time ride demand information, combined with the current vehicle distribution of each transportation station and historical ride data, the ride demand change trend of each station in the future time period is predicted; Dynamically adjust the vehicle dispatch plan according to the changing trend of the ride demand and the acquired current position, status and carrying capacity of the vehicle to optimize vehicle allocation; Evaluate the impact of different vehicle dispatching plans on operational efficiency, select and implement the target vehicle dispatching plan to ensure that operational efficiency is maximized while meeting passenger needs.

[0007] In a second aspect, the embodiment of the present application provides a vehicle capacity dispatching system for smart transportation, including: A receiving module, used to receive real-time ride demand information from multiple transportation stations, wherein the real-time ride demand information includes the departure place, destination and estimated travel time of the passenger; A prediction module is used to predict the change trend of the ride demand at each station in the future time period based on the real-time ride demand information, combined with the current vehicle distribution at each transportation station and the historical ride data; An optimization module, used to dynamically adjust the vehicle dispatching plan according to the change trend of the ride demand and the acquired current position, status and carrying capacity of the vehicle, so as to optimize the vehicle allocation; The evaluation module is used to evaluate the impact of different vehicle scheduling schemes on operational efficiency, select and implement the target vehicle scheduling scheme to ensure that operational efficiency is maximized while meeting passenger needs.

[0008] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a vehicle capacity scheduling method for smart transportation as described in any one of the first aspects.

[0009] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a vehicle capacity scheduling method for smart transportation as described in any one of the first aspects.

[0010] In the embodiment of the present application, real-time ride demand information is received from multiple transportation stations, and the real-time ride demand information includes the departure place, destination and estimated travel time of the passengers; based on the real-time ride demand information, combined with the current vehicle distribution of each transportation station and historical ride data, the change trend of the ride demand at each station in the future time period is predicted; based on the change trend of the ride demand and the current position, status and carrying capacity of the acquired vehicle, the vehicle dispatching plan is dynamically adjusted to optimize vehicle allocation; the impact of different vehicle dispatching plans on operational efficiency is evaluated, and the target vehicle dispatching plan is selected and implemented to ensure that operational efficiency is maximized while meeting passenger needs. The technical solution provided by the present application improves the optimization capability of vehicle capacity dispatching plans and emergency response capabilities.

[0011] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 A flow chart of a vehicle capacity dispatching method for smart transportation provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a vehicle capacity dispatching system for smart transportation provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0015] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0017] Figure 1 A flow chart of a vehicle capacity dispatching method for smart transportation is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes: 101. Receive real-time ride demand information from multiple transportation stations; In this step, the system receives real-time ride demand information from different transportation stations. This information is usually collected and sent to the system by applications or transportation service terminals. Specifically, real-time ride demand information includes but is not limited to the following aspects: Departure point: The location where the passenger plans to start the journey, such as a bus stop, subway station, or a specific address.

[0018] Destination: The place where the passenger wishes to arrive.

[0019] Estimated travel time: When the passenger plans to start their trip.

[0020] Once the system receives this information, it can use it to do many different things, such as: adjusting the routes or frequency of public transportation based on passenger demand; or ensuring that there are enough vehicles or drivers to meet passenger needs when needed; or providing the best travel plan based on the specific needs of passengers; or analyzing historical data to predict future ride demand patterns and make corresponding preparations accordingly.

[0021] This real-time processing and analysis can help improve the efficiency and service quality of public transportation systems, while also providing passengers with a better travel experience.

[0022] 102. Based on the real-time ride demand information, combined with the current vehicle distribution at each transportation station and historical ride data, predict the change trend of the ride demand at each station in the future time period; In this step, the system collects instant ride requests from passengers through various channels (such as mobile applications, telephone call centers, smart bus stops, etc.), which include the passengers' departure point, destination and estimated travel time; the system obtains the current number, location, status (such as idle, carrying passengers, under maintenance) and carrying capacity of vehicles at each transportation station through the vehicle status monitoring system. This information is used to understand the current available resources so that they can be reasonably allocated during scheduling; predicting the changing trend of ride demand at each station in the future time period refers to using statistical models and machine learning algorithms, combining real-time ride demand information, current vehicle distribution and historical ride data, to predict the changing trend of ride demand at each station in the future time period.

[0023] This application proposes a further optional solution, which aims to combine vehicle distribution data to predict future trends in passenger demand changes and predict passenger demand trends for individual stations in future time periods, thereby improving passenger demand and operational efficiency.

[0024] The options are as follows: Optionally, the method in step 102 predicts the changing trend of the ride demand at each station in the future time period based on the real-time ride demand information, combined with the current vehicle distribution situation at each transportation station and the historical ride data, including: collecting the current vehicle distribution information of each transportation station in real time, including the number, location, status and carrying capacity of vehicles; analyzing the acquired historical ride data to extract the temporal regularity of ride demand, spatial distribution pattern and the impact of holidays and weather factors on ride demand; and using a time series prediction model to predict the changing trend of the ride demand at each station in the future time period based on the real-time ride demand information, combined with the analysis results of the real-time collected vehicle distribution information and the historical ride data.

[0025] Among them, real-time ride demand information refers to real-time data such as passengers' departure place, destination and estimated travel time collected by the system; current vehicle distribution refers to information such as the current number, location, status (such as idle, carrying passengers, under maintenance) and carrying capacity of vehicles at each transportation station obtained through the vehicle status monitoring system; historical ride data refers to historical ride records stored in the system, including the ride demand at each station in the past period of time, the impact of peak hours, off-peak hours, holidays, weather and other factors on ride demand.

[0026] The above optional solution specifically includes the following process: First, through time series analysis of historical ride data, identify the temporal patterns of ride demand, such as different demand patterns on weekdays and weekends, and peak demand during morning and evening rush hours. Analyze the distribution of ride demand at different stations in different time periods to identify hot and cold areas. Consider the impact of external factors on ride demand, such as weather conditions (sunny, rainy, snowy), holidays, large-scale events, etc. These factors can be comprehensively analyzed by introducing external data sources (such as meteorological data, event schedules, etc.).

[0027] Secondly, use time series analysis methods (such as ARIMA, SARIMA, LSTM, etc.) to predict the changing trend of ride demand at each station in the future time period. These models can capture the seasonal, cyclical and trend components in the data. Use machine learning algorithms (such as random forests, gradient boosting trees, neural networks, etc.) to build prediction models. These models can handle complex nonlinear relationships and can combine multiple features for prediction. Combining the advantages of time series models and machine learning models, build a more powerful hybrid prediction model to improve the accuracy and robustness of predictions.

[0028] Furthermore, the demand forecast for rides in the next few hours or days is generated for real-time scheduling decisions. The demand forecast for rides in the next few weeks or months is generated for planning and resource allocation.

[0029] The following is a specific application scenario: Based on the prediction results, the system can adjust the vehicle dispatch plan in advance to ensure that there are enough vehicles to meet passenger demand during peak hours and reduce unnecessary empty trips during off-peak hours. The prediction results can help operators arrange logistics work such as vehicle maintenance, refueling / charging, and improve overall operational efficiency. In the event of an emergency, the dispatch strategy can be quickly adjusted based on the prediction results to ensure the safe evacuation and normal travel of passengers in the affected area.

[0030] The solution uses big data processing platforms (such as Hadoop, Spark, etc.) to clean, integrate and analyze large-scale data. It uses machine learning frameworks (such as TensorFlow, PyTorch, etc.) to train models and evaluate model performance through methods such as cross-validation. The system regularly updates the prediction model and retrains it with the latest data to ensure the timeliness and accuracy of the model.

[0031] Through this step, the system can predict the changing trend of passenger demand at each station in the future time period based on real-time data and historical data, providing a scientific basis for subsequent vehicle scheduling and resource optimization. This not only improves passenger satisfaction, but also improves the operating efficiency and service quality of the entire transportation system.

[0032] Here is a specific example: Collect the current vehicle distribution information of each traffic station in real time: Through the vehicle status monitoring system, the number, location, status and carrying capacity of vehicles at each traffic station can be obtained in real time. For example, at a certain traffic station A, there are 5 idle vehicles, 3 passenger vehicles, and 1 vehicle under maintenance at a certain moment.

[0033] Analyze the historical ride data to extract the temporal pattern and spatial distribution pattern of ride demand and the impact of holidays and weather factors on ride demand: By analyzing the historical ride data in time series, we can identify the temporal patterns of ride demand. For example, the demand during the morning peak hours (7:00-9:00) and evening peak hours (17:00-19:00) on weekdays is significantly higher than that during other hours.

[0034] Through spatial data analysis, hot spots and cold spots are identified. For example, the business district in the city center has high demand during peak hours on weekdays, while the demand in the suburbs is low.

[0035] Consider the impact of external factors (such as weather, holidays, etc.) on ride demand. For example, ride demand on rainy days is 20% higher than on sunny days; during holidays, ride demand near tourist attractions increases significantly.

[0036] According to the real-time ride demand information, combined with the real-time collected vehicle distribution information and the analysis results of historical ride data, a time series prediction model is used to predict the change trend of the ride demand at each station in the future time period: Use a time series forecasting model (such as the ARIMA model) to predict the demand for rides at each station in the future time period. For example, suppose an ARIMA (1,1,1) model is used to predict the demand for rides in the next hour.

[0037] The input data includes real-time ride demand information, current vehicle distribution information, and analysis results of historical ride data. For example, a transportation station B has 10 ride requests at the current moment, and historical data shows that the average demand for the station in the same time period is 15 people. Considering that it is sunny and there are no special events that day, the demand for the next hour is predicted to be 18 people.

[0038] Assume that a city transportation system needs to dispatch vehicles within the next hour to meet passenger demand. The following are the specific implementation steps: Collect the current vehicle distribution information of each traffic station in real time: The system obtains the vehicle distribution information of traffic station A through the vehicle status monitoring system: 5 idle vehicles, 3 passenger vehicles, and 1 vehicle under maintenance.

[0039] At the same time, the vehicle distribution information of traffic station B is obtained: 4 idle vehicles, 2 passenger vehicles, and no maintenance vehicles.

[0040] Analyze the historical ride data to extract the temporal pattern and spatial distribution pattern of ride demand and the impact of holidays and weather factors on ride demand: Through time series analysis, it was found that the average demand for transportation station A during the morning peak period (7:00-9:00) on weekdays was 20 people, and the average demand during the evening peak period (17:00-19:00) was 25 people.

[0041] Through spatial data analysis, it was found that the average demand for transportation station B during peak hours on weekdays is 15 people.

[0042] Considering that it was a sunny day and there were no special events, historical data shows that demand on sunny days is 10% higher than on cloudy days.

[0043] According to the real-time ride demand information, combined with the real-time collected vehicle distribution information and the analysis results of historical ride data, a time series prediction model is used to predict the change trend of the ride demand at each station in the future time period: Use the ARIMA(1,1,1) model to predict the ride demand for the next hour.

[0044] For transportation station A, there are currently 15 ride requests. Historical data shows that the average demand for this station in the same time period is 20 people. Considering that it is a sunny day, the demand in the next hour is predicted to be 22 people.

[0045] For transportation station B, there are currently 10 ride requests. Historical data shows that the average demand for this station in the same time period is 15 people. Considering that it is a sunny day, the demand in the next hour is predicted to be 16 people.

[0046] Through the above options, the system can more accurately predict the changing trend of passenger demand at each station in the future time period.

[0047] 103. Dynamically adjust the vehicle dispatch plan according to the change trend of the ride demand and the acquired current position, status and carrying capacity of the vehicle to optimize vehicle allocation; In this step, the changing trend of the passenger demand at each transportation station in the future time period is predicted by the previous step (step 102). These prediction results provide an estimate of future passenger demand and are the basis for vehicle scheduling. The system obtains the number, location, status (such as idle, carrying passengers, and under maintenance) of vehicles at each transportation station and the carrying capacity of each vehicle through the vehicle status monitoring system. This information is used to understand the current available resources so that they can be reasonably allocated during scheduling.

[0048] First, the predicted trend of passenger demand and the current vehicle distribution are integrated into a comprehensive data set. Then, the scheduling objectives are clarified, such as minimizing passenger waiting time, reducing vehicle empty driving rate, balancing vehicle distribution between stations, etc. Secondly, the constraints of the scheduling plan are set, such as the maximum driving distance, maximum passenger capacity, service time window, etc., and appropriate scheduling algorithms are selected, such as greedy algorithm, genetic algorithm, particle swarm optimization algorithm, etc., to generate multiple feasible scheduling plans, evaluate the generated scheduling plans, and select the optimal plan. Evaluation indicators can include passenger satisfaction, operating costs, response speed, etc. Finally, according to the selected optimal plan, actual vehicle scheduling operations are carried out, and the execution effect is monitored and fine-tuned when necessary.

[0049] The present application proposes a further optional solution, which aims to combine multiple vehicle transportation data to improve the flexibility of the scheduling strategy in dealing with complex environments, thereby making the scheduling strategy more feasible in practical applications.

[0050] The options are as follows: Optionally, the step 103 dynamically adjusts the vehicle dispatching plan according to the changing trend of the ride demand and the obtained current position, status and carrying capacity of the vehicle to optimize vehicle allocation, including: constructing a multi-objective optimization model according to the changing trend of the ride demand and the obtained current position, status and carrying capacity of the vehicle, the multi-objective optimization model is used to minimize passenger waiting time, reduce vehicle empty driving rate, and balance vehicle distribution between stations; in the multi-objective optimization model, setting constraints to achieve dynamic adjustment of the vehicle dispatching plan through the constraints, the constraints include the maximum driving distance, maximum passenger capacity, and service time window of the vehicle, so as to ensure the rationality of the dispatching plan.

[0051] The method of dynamically adjusting the vehicle dispatching scheme to optimize vehicle allocation also includes: using the following calculation formula to construct a multi-objective optimization model, and generating a plurality of vehicle dispatching schemes through the multi-objective optimization model: Define a first objective function, which is used to minimize the average waiting time of passengers , the corresponding calculation formula is: ; in, is a weighting factor used to balance the difference between individual passenger waiting time and the average waiting time; is the average waiting time of all passengers; is a weight factor that represents the impact of emergencies on waiting time; In the passenger seat and time The impact of emergencies on waiting time; in, The event impact function can represent the impact of sudden events on waiting time. Assume that the impact depends on the location and time of the event: ; The meaning of this function is: If the passenger Location In time If an event occurs, the value of the EventImpact function is ; If not affected, the function value is 0. Is a predefined positive value that represents the increase in waiting time when the position is affected by an event.

[0052] Define a second objective function, which is used to minimize the vehicle idle rate , the corresponding calculation formula is: ; in, is a weight factor used to control the degree to which the passenger travel distance deviates from the average value; It is The actual distance travelled by the vehicle carrying passengers; is the average of the actual passenger-carrying distances traveled by all vehicles; is a weight factor, which indicates the influence of maintenance status on the empty driving rate; is a function based on the maintenance status of the vehicle Calculate impact factor; in, The maintenance status impact factor can be used to reflect the impact of the vehicle's maintenance status on the idle rate. Assuming that a good maintenance status will reduce the idle rate, and vice versa, it will increase: ; The meaning of this function is: If the vehicle Good maintenance status ( Indicates vehicle Maintenance status), then the value of the MaintenanceFactor function is 0; if the vehicle The maintenance status is not good, then the value of the function is . It is a predefined positive value, which represents the increase in the idle rate when the vehicle is in poor maintenance condition.

[0053] Define a third objective function, which is used to balance the distribution of vehicles between the stations , the corresponding calculation formula is: ; in, is a weight factor used to consider the deviation between the current number of vehicles and historical data; It is The current number of vehicles at each station; is the average number of vehicles at all stations; It is The average number of vehicles in the history of each station; is a weight factor that represents the impact of demand fluctuations on vehicle distribution; It is on site and time Demand volatility index; Among them, the Demand Fluctuation (s, t) demand fluctuation index can be used to measure the demand changes at a specific site and time.

[0054] Assume that the greater the demand volatility compared to historical demand, the higher the volatility index: ; in, It is on site and time demand, is the historical average demand for the site.

[0055] It should be noted that the specific implementation details of the above functions can be adjusted according to actual conditions.

[0056] Define a first constraint condition, the first constraint condition includes: the maximum driving distance of the vehicle Limitations: ; Define a second constraint condition, which includes: the maximum passenger capacity of the vehicle Limitations: ; Define a third constraint condition, the third constraint condition includes: service time window Limitations: ; Define a fourth constraint condition, the fourth constraint condition includes: vehicle maintenance time Limitations: ,in, It is The maintenance time required for the vehicle.

[0057] Define a fifth constraint condition, the fifth constraint condition includes: vehicle charging / refueling time Limitations: ,in, It is The time required to charge / refuel the vehicle; The above formulas together constitute a multi-objective optimization problem, and multiple vehicle scheduling solutions are generated by weighted combination of multiple objective functions and multiple constraints.

[0058] Multi-objective optimization model: A mathematical model used to optimize multiple objective functions simultaneously to find the optimal solution set.

[0059] Average waiting time for passengers : The average waiting time of all passengers.

[0060] Vehicle idle rate : The ratio of the vehicle’s distance traveled without passengers to the total distance traveled.

[0061] Vehicle Distribution :The distribution of the number of vehicles between each traffic station.

[0062] Constraints: Restrictions on the scheduling plan to ensure the feasibility and rationality of the plan.

[0063] According to the changing trend of the ride demand and the current position, status and carrying capacity of the vehicle, a multi-objective optimization model is constructed: Generate multiple vehicle dispatching solutions: The above formulas are combined into a multi-objective optimization problem, and multiple feasible vehicle dispatching solutions are generated by weighted combination of multiple objective functions and multiple constraints.

[0064] In the embodiment of the present application, it is assumed that a certain city transportation system needs to dispatch vehicles within the next hour to meet passenger demand.

[0065] Real-time ride demand information: A total of 50 passengers submitted ride requests, distributed at different transportation stations.

[0066] Current vehicle distribution information: There are 20 vehicles distributed at various stations, of which 10 are idle, 5 are carrying passengers, and 5 are under maintenance.

[0067] Historical ridership data shows that during the morning rush hour on weekdays (7:00-9:00), the average demand at transportation station A is 20 people, and the average demand at transportation station B is 15 people.

[0068] Considering that it was a sunny day and there were no special events, historical data shows that demand on sunny days is 10% higher than on cloudy days.

[0069] Constructing a multi-objective optimization model: First objective function: Minimize the average waiting time of passengers : ; Assumptions Minutes (impact of emergencies).

[0070] Second objective function: Minimize vehicle idle rate : ; Assumptions (Maintenance status impact).

[0071] The third objective function: balance the distribution of vehicles between stations : ; Assumptions (Demand Volatility Index).

[0072] Set constraints: The first constraint: the maximum driving distance of the vehicle kilometer.

[0073] Second constraint: Maximum vehicle capacity people.

[0074] Third Constraint: Service Time Window minute.

[0075] Fourth constraint: vehicle maintenance time Hour.

[0076] Fifth constraint: Vehicle charging / refueling time Hour.

[0077] Generate multiple vehicle dispatch solutions: Through multi-objective optimization algorithms (such as genetic algorithm, particle swarm optimization algorithm, etc.), multiple feasible vehicle scheduling schemes are generated, for example, scheme A, scheme B, scheme C, etc.

[0078] Through the above optional solutions, the system can dynamically adjust the vehicle scheduling plan more effectively.

[0079] 104. Evaluate the impact of different vehicle dispatching schemes on operational efficiency, select and implement the target vehicle dispatching scheme to ensure that operational efficiency is maximized while meeting passenger needs.

[0080] In this step, the system will use the different vehicle dispatching plans generated previously to conduct a comprehensive evaluation and select the target vehicle dispatching plan. The specific process is as follows: The system receives multiple vehicle dispatching solutions generated by the multi-objective optimization model. These solutions are generated based on factors such as the trend of passenger demand, the current location, status and carrying capacity of the vehicle.

[0081] Use evaluation algorithms (such as weighted scoring method, hierarchical analysis method, etc.) and combine multiple operational efficiency indicators (such as passenger satisfaction, operating costs, response speed, etc.) to give each vehicle dispatch plan a comprehensive score.

[0082] Measure the passenger's satisfaction with the ride experience, including factors such as waiting time and ride comfort; calculate the various expenses incurred during the operation of the vehicle, including fuel costs, maintenance costs, labor costs, etc.; calculate the time interval from the passenger submitting a ride request to the actual ride.

[0083] Based on the comprehensive scoring results, the vehicle dispatch plan with the highest comprehensive score is selected as the optimal plan. If there are multiple plans with the same score, other secondary indicators can be further compared, or the selection can be made based on business priorities.

[0084] Finally, based on the selected optimal plan, actual vehicle dispatch operations are carried out, the execution effect is monitored, and fine-tuning is performed when necessary to ensure the effective implementation of the plan.

[0085] The present application proposes a further optional solution, which aims to select the best solution from multiple scheduling solutions, thereby improving the implementation efficiency of the solution.

[0086] The options are as follows: Optionally, the evaluation of the impact of different vehicle scheduling schemes on operational efficiency in step 104, selecting and implementing a target vehicle scheduling scheme to ensure that operational efficiency is maximized while meeting passenger needs, includes: solving the multi-objective optimization model to generate multiple vehicle scheduling schemes; performing a comprehensive evaluation on the multiple vehicle scheduling schemes generated, and selecting the vehicle scheduling scheme with the highest comprehensive score as the target vehicle scheduling scheme, wherein the evaluation indicators include passenger satisfaction, operating costs, and response speed; and scheduling vehicles according to the target vehicle scheduling scheme to ensure that operational efficiency is maximized while meeting passenger needs.

[0087] In this step, the system will generate multiple vehicle dispatching schemes by solving the multi-objective optimization model, and conduct a comprehensive evaluation of these schemes, and finally select a target vehicle dispatching scheme. The specific process is as follows: Based on the trend of passenger demand, the current location, status and carrying capacity of the vehicle, a multi-objective optimization model is constructed. The model aims to optimize multiple objectives at the same time, such as minimizing passenger waiting time, reducing vehicle empty driving rate, and balancing the distribution of vehicles between stations. Using multi-objective optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.), the above model is solved to generate multiple feasible vehicle dispatching schemes. Each scheme is a set of specific vehicle dispatching strategies, including vehicle allocation, route planning, etc. Comprehensively evaluate the generated multiple vehicle dispatching schemes, and select the vehicle dispatching scheme with the highest comprehensive score as the target vehicle dispatching scheme. According to the selected optimal scheme, actual vehicle dispatching operations are carried out. This includes adjusting vehicle allocation, replanning driving routes, increasing or decreasing vehicle frequency in specific areas, etc. During the implementation process, the system will continuously monitor the execution effect and make fine adjustments when necessary to ensure the effectiveness and adaptability of the scheme.

[0088] Among them, evaluate the impact of different vehicle dispatching schemes on operational efficiency, select and implement the target vehicle dispatching scheme, including: The following calculation formula is used to evaluate the passenger satisfaction of each scheduling scheme: , operating costs and response speed , to determine the target vehicle scheduling plan: Passenger satisfaction The calculation formula is: ; in, represents the total number of passengers; It is Waiting time for passengers; It is The actual arrival time of passengers; is the maximum acceptable waiting time set by the system; is a penalty factor related to the passenger's historical behavior, used to adjust the additional waiting time caused by frequent cancellations or changes in itineraries; It is The historical reputation score of the passenger, ranging from 0 to 1; is a weight factor indicating the impact of weather conditions on waiting time; It is Weather condition index for the passengers' location; Operating costs The calculation formula is: ; in, Represents the number of all vehicles; It is The cost per kilometre of the vehicle; It is The distance travelled by the vehicle; It is The fixed cost of the vehicle; is an adjustment factor used to control the degree to which the vehicle's driving distance deviates from the average value; is the average distance travelled by all vehicles; is a weighting factor that represents the change in fuel cost; is a function based on the distance traveled and average speed Calculate fuel costs, , and It is a constant and can be set according to requirements.

[0089] Response speed The calculation formula is: ; in, Indicates the number of services requested by all; It is The time from when a service request is issued to when it is completed; is a weight factor used to consider the distance difference between service requests; It is The distance from the starting point to the end point of a service request; is a weight factor that represents the impact of traffic congestion on response speed; It is the real-time traffic congestion index when the service request occurs, where the traffic congestion index can be expressed as a variable related to time and location, which is simplified here to be only related to time.

[0090] Assume that the traffic congestion index is higher during peak hours and lower during off-peak hours: , which means the function Returns different values ​​under different conditions: If the time If it is in peak period, the function returns 1; otherwise, When it is not during peak hours, the function returns a value of 0.5.

[0091] Overall Rating The calculation formula is: ; in, are the weight coefficients of passenger satisfaction, operating cost, response speed, score variance and stability in the total score; is the standard deviation of passenger satisfaction, operating cost and response speed, which is used to measure the consistency of each indicator; It is a function used to measure the stability and reliability of the scheduling scheme in different time periods; It is the maximum operating cost threshold preset by the system.

[0092] in, Standard deviation can be used to measure the dispersion of a set of values. , operating costs and response speed The standard deviation of can be calculated separately and then averaged or weighted averaged: ; in, express The average value of .

[0093] The stability function can be used to measure the consistency of the scheduling plan in different time periods. Here it is simplified to measure the average degree of change in each time period: ; in, is the total number of time periods, Respectively indicate the time period Passenger satisfaction, operating costs and responsiveness within the company.

[0094] It should be noted that the specific implementation details of the above functions can be adjusted according to actual conditions.

[0095] In this step, the multi-objective optimization model refers to a mathematical model used to optimize multiple objective functions simultaneously to find the optimal solution set. Passenger satisfaction refers to the degree of satisfaction of passengers with the riding experience, including waiting time, riding comfort and other factors. Operating costs refer to the various expenses incurred during the operation of the vehicle, including fuel costs, maintenance costs, labor costs, etc. Response speed refers to the time interval from the passenger submitting a ride request to the actual ride. The comprehensive score refers to the overall score calculated by weighted combination of multiple evaluation indicators. Solving the multi-objective optimization model and generating a variety of vehicle scheduling solutions refers to solving the multi-objective optimization model through a multi-objective optimization algorithm (such as a genetic algorithm, a particle swarm optimization algorithm, etc.) to generate a variety of feasible vehicle scheduling solutions.

[0096] Comprehensively evaluate the generated multiple vehicle dispatching schemes and select the vehicle dispatching scheme with the highest comprehensive score as the target vehicle dispatching scheme, including: Evaluation Metrics: Passenger satisfaction : ; in, represents the total number of passengers; It is Waiting time for passengers; It is The actual arrival time of passengers; is the maximum acceptable waiting time set by the system; is a penalty factor related to the passenger's historical behavior, used to adjust the additional waiting time caused by frequent cancellations or changes in itineraries; It is The historical reputation score of the passenger, ranging from 0 to 1; is a weight factor indicating the impact of weather conditions on waiting time; It is Weather condition index for the passengers' location; Operating costs : ; in, Represents the number of all vehicles; It is The cost per kilometre of the vehicle; It is The distance travelled by the vehicle; It is The fixed cost of the vehicle; is an adjustment factor used to control the degree to which the vehicle's driving distance deviates from the average value; is the average distance travelled by all vehicles; is a weighting factor that represents the change in fuel cost; is a function based on the distance traveled and average speed Calculate fuel costs; Response speed : ; in, Indicates the number of services requested by all; It is The time from when a service request is issued to when it is completed; is a weight factor used to consider the distance difference between service requests; It is The distance from the starting point to the end point of a service request; is a weight factor that represents the impact of traffic congestion on response speed; It is the real-time traffic congestion index when the service request occurs; Overall Rating : ; in, are the weight coefficients of passenger satisfaction, operating cost, response speed, score variance and stability in the total score; is the standard deviation of passenger satisfaction, operating cost and response speed, which is used to measure the consistency of each indicator; It is a function used to measure the stability and reliability of the scheduling scheme in different time periods; It is the maximum operating cost threshold preset by the system.

[0097] Vehicle dispatch is performed according to the target vehicle dispatch plan to ensure that the operation efficiency is maximized while meeting the passenger demand: According to the vehicle dispatch plan with the highest comprehensive score, actual vehicle dispatch operations are carried out to ensure the effective implementation of the plan.

[0098] Suppose a city transportation system needs to dispatch vehicles within the next hour to meet passenger demand.

[0099] Collect real-time data: Real-time ride demand information: A total of 50 passengers submitted ride requests, distributed at different transportation stations.

[0100] Current vehicle distribution information: There are 20 vehicles distributed at various stations, of which 10 are idle, 5 are carrying passengers, and 5 are under maintenance.

[0101] Analyzing historical data: Historical ridership data shows that during the morning rush hour on weekdays (7:00-9:00), the average demand at transportation station A is 20 people, and the average demand at transportation station B is 15 people.

[0102] Considering that it was a sunny day and there were no special events, historical data shows that demand on sunny days is 10% higher than on cloudy days.

[0103] Constructing a multi-objective optimization model: First objective function: Minimize the average waiting time of passengers : ; Assume that the waiting time for passengers is 10 minutes, 15 minutes, 20 minutes, etc.

[0104] Second objective function: Minimize vehicle idle rate : ; Assume that the driving distance of each vehicle is 50 kilometers, 60 kilometers, 70 kilometers, etc., and the actual passenger driving distance is 30 kilometers, 40 kilometers, 50 kilometers, etc.

[0105] The third objective function: balance the distribution of vehicles between stations : ; Assume that the number of vehicles at each station is 2, 3, 4, etc., and the average number of vehicles is 2.5.

[0106] Set constraints: The first constraint: the maximum driving distance of the vehicle kilometer.

[0107] Second constraint: Maximum vehicle capacity people.

[0108] Third Constraint: Service Time Window minute.

[0109] Generate multiple vehicle dispatch solutions: Through multi-objective optimization algorithms (such as genetic algorithm, particle swarm optimization algorithm, etc.), multiple feasible vehicle scheduling schemes are generated, for example, scheme A, scheme B, scheme C, etc.

[0110] Comprehensive evaluation of the generated multiple vehicle dispatching solutions: Passenger satisfaction : ; Assumptions minute, (Sunny day effect).

[0111] Operating costs : ; Assumptions Yuan / km, Yuan, , , Yuan.

[0112] Response speed : ; Assumptions .

[0113] Overall Rating : ; Assumptions Yuan.

[0114] Select the vehicle dispatch solution with the highest overall score: By calculating the comprehensive scores of different solutions, the solution with the highest comprehensive score is selected as the optimal solution. For example, if the comprehensive score of solution A is 0.85, the comprehensive score of solution B is 0.80, and the comprehensive score of solution C is 0.75, then solution A is selected as the optimal solution.

[0115] Carry out vehicle dispatch according to the target vehicle dispatch plan: Carry out actual vehicle dispatch operations according to Plan A to ensure the effective implementation of the plan.

[0116] Through the above optional solutions, the system can dynamically adjust the vehicle scheduling plan more effectively.

[0117] This application takes into account that in existing vehicle capacity scheduling schemes, fixed scheduling plans or dynamic adjustments based on conventional needs are usually adopted. These methods have the following problems: existing schemes often do not have emergency response mechanisms specifically for emergencies (such as traffic accidents, bad weather, large-scale events, etc.). When an emergency occurs in a specific area and causes abnormal traffic flow, the system cannot make adjustments quickly, resulting in longer waiting times for passengers and reduced service quality. Existing schemes may rely on simple statistical models to predict ride demand, while ignoring the impact of emergencies on traffic flow, resulting in inaccurate prediction results. Existing schemes are difficult to flexibly allocate resources when emergencies occur, especially during peak hours or when the scope of the impact of emergencies is large, which may lead to waste of resources and low operational efficiency. In order to solve the above problems, this application proposes a further optional scheme, which aims to improve the emergency response capability and prediction capability of the vehicle capacity scheduling scheme, thereby saving operating resources and improving operational efficiency.

[0118] The plan is as follows: Optionally, the method further includes: when an emergency is detected in a specific area causing abnormal traffic flow, adjusting the vehicle dispatching plan of the specific area and its surrounding areas; When an emergency is detected in a specific area causing abnormal traffic flow, the vehicle dispatch plan of the specific area and its surrounding areas is adjusted, including: real-time monitoring of emergencies, immediately initiating an emergency response mechanism when an emergency is detected in the specific area, and evaluating the impact of the emergency on traffic flow; predicting the abnormal change trend of traffic flow in the specific area and its surrounding areas based on the real-time passenger demand information, vehicle distribution and historical traffic data within the impact range of the emergency; adjusting the vehicle dispatch plan of the specific area and its surrounding areas based on the prediction results; the adjustment of the vehicle dispatch plan of the specific area and its surrounding areas at least includes: increasing the vehicle dispatch frequency of the specific area and its surrounding areas.

[0119] Emergency: refers to an event that occurs suddenly and may cause abnormal traffic flow, such as traffic accidents, bad weather, large-scale events, etc.

[0120] Emergency response mechanism: A rapid response mechanism used to take immediate measures when an emergency is detected to mitigate the impact of the incident on the transportation system.

[0121] Abnormal traffic flow change trend: refers to the difference between traffic flow caused by emergencies and normal conditions, including increasing or decreasing trends.

[0122] Vehicle dispatch frequency: refers to the number of times vehicles are dispatched in a specific area per unit time.

[0123] Real-time monitoring of emergencies. When emergencies are detected in specific areas, the emergency response mechanism is immediately activated, and the impact of emergencies on traffic flow is assessed: Real-time monitoring: Use sensors, cameras, mobile applications and other means to collect and analyze traffic data in real time and detect the occurrence of emergencies.

[0124] Emergency response mechanism: Once an emergency is detected, the emergency response mechanism is immediately activated to assess the impact of the emergency on traffic flow. For example, using GIS (Geographic Information System) technology, combining historical data and real-time data, to determine the specific areas affected.

[0125] Combined with the real-time ride demand information, vehicle distribution and historical traffic data within the impact area of ​​the emergency, the abnormal change trend of traffic flow in the specific area and surrounding areas is predicted: Real-time ride demand information: Collect real-time ride requests within the affected area, including passengers’ origin, destination, and estimated travel time.

[0126] Vehicle distribution: Obtain the number, location, status and carrying capacity of vehicles at each current transportation station.

[0127] Historical traffic data: Analyze the impact of similar emergencies on traffic flow in historical data and identify common traffic patterns and rules.

[0128] Prediction model: Use machine learning or time series analysis methods, combined with the above data, to predict abnormal changes in traffic flow in a specific area and surrounding areas. For example, ARIMA models or LSTM neural networks can be used for prediction.

[0129] Based on the prediction results, adjust the vehicle dispatch plan for the specific area and its surrounding areas: Increase vehicle dispatch frequency: Based on forecast results, increase the frequency of vehicle dispatch in and around a specific area to ensure there are enough vehicles to meet passenger demand.

[0130] Optimize vehicle allocation: Dynamically adjust vehicle allocation and prioritize idle vehicles to the affected areas to reduce passenger waiting time.

[0131] Adjust route planning: Replan vehicle routes to avoid congested sections and improve operational efficiency.

[0132] Suppose a city's traffic system needs to respond to a sudden traffic accident: Through the traffic monitoring system, it was detected that a serious traffic accident occurred in Area A in the city center, resulting in the closure of multiple roads and abnormal traffic flow.

[0133] The emergency response mechanism was immediately activated, and the specific areas affected by the accident were determined through GIS technology, including Area A and its surrounding Areas B and C.

[0134] Real-time ride requests within Area A, Area B, and Area C were collected, and a total of 80 passengers submitted ride requests.

[0135] Currently there are 5 idle vehicles in area A, 3 idle vehicles in area B, and 2 idle vehicles in area C.

[0136] By analyzing historical data, it was found that when similar traffic accidents occurred, the demand in area A would increase by 50%, and the demand in areas B and C would increase by 30%.

[0137] Using the LSTM neural network model, combined with real-time data and historical data, the abnormal change trend of traffic flow in Area A, Area B and Area C in the next hour is predicted.

[0138] The forecast results show that the demand in area A will increase from the usual 20 people to 30 people, the demand in area B will increase from the usual 15 people to 20 people, and the demand in area C will increase from the usual 10 people to 13 people.

[0139] Increase the vehicle dispatch frequency in Zone A from 6 times per hour to 9 times per hour, in Zone B from 4 times per hour to 6 times per hour, and in Zone C from 3 times per hour to 5 times per hour.

[0140] Dispatch idle vehicles in other areas to Area A, Area B, and Area C to ensure there are enough vehicles to meet passenger demand.

[0141] Re-plan vehicle routes to avoid congested sections near the accident site and choose alternative routes to improve operational efficiency.

[0142] Through the above options, the system can respond to emergencies more effectively.

[0143] Figure 2 A schematic diagram of the structure of a vehicle capacity dispatching system for smart transportation is provided for the embodiment of the present application, such as Figure 2 As shown, the device comprises: The receiving module 21 is used to receive real-time ride demand information from multiple transportation stations, wherein the real-time ride demand information includes the departure place, destination and estimated travel time of the passenger; The prediction module 22 is used to predict the change trend of the ride demand at each station in the future time period based on the real-time ride demand information, combined with the current vehicle distribution at each transportation station and the historical ride data; The optimization module 23 is used to dynamically adjust the vehicle dispatching plan according to the change trend of the ride demand and the acquired current position, state and carrying capacity of the vehicle to optimize the vehicle allocation; The evaluation module 24 is used to evaluate the impact of different vehicle dispatching schemes on operational efficiency, select and implement a target vehicle dispatching scheme to ensure that operational efficiency is maximized while meeting passenger demand.

[0144] Figure 2 The vehicle capacity dispatching system of the intelligent transportation can execute Figure 1 The implementation principle and technical effect of the vehicle capacity dispatching method for smart transportation described in the illustrated embodiment will not be described in detail. The specific way in which each module and unit performs operations in the vehicle capacity dispatching system for smart transportation in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0145] In one possible design, Figure 2 The vehicle capacity dispatching system of the smart transportation of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0146] The processing component 32 is used to: receive real-time ride demand information from multiple transportation stations, the real-time ride demand information including the passengers' departure place, destination and expected travel time; predict the changing trend of ride demand at each station in the future time period based on the real-time ride demand information, combined with the current vehicle distribution of each transportation station and historical ride data; dynamically adjust the vehicle dispatch plan based on the changing trend of ride demand and the acquired current position, status and carrying capacity of the vehicle to optimize vehicle allocation; evaluate the impact of different vehicle dispatch plans on operational efficiency, select and implement the target vehicle dispatch plan to ensure that operational efficiency is maximized while meeting passenger needs.

[0147] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0148] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0149] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0150] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device, an input device, etc.

[0151] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0152] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0153] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The vehicle capacity scheduling method for smart transportation in the illustrated embodiment.

[0154] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0155] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0156] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle capacity dispatching method for smart transportation, characterized in that: include: Receiving real-time ride demand information from multiple transportation stations, the real-time ride demand information including the departure place, destination and estimated travel time of passengers; According to the real-time ride demand information, combined with the current vehicle distribution of each transportation station and historical ride data, the ride demand change trend of each station in the future time period is predicted; Dynamically adjust the vehicle dispatch plan according to the changing trend of the ride demand and the acquired current position, status and carrying capacity of the vehicle to optimize vehicle allocation; Evaluate the impact of different vehicle dispatching plans on operational efficiency, select and implement the target vehicle dispatching plan to ensure that operational efficiency is maximized while meeting passenger needs.

2. The method according to claim 1, characterized in that The method of predicting the change trend of the ride demand at each station in the future time period based on the real-time ride demand information and combining the current vehicle distribution at each transportation station with the historical ride data includes: Collect the current vehicle distribution information of each traffic station in real time, including the number, location, status and carrying capacity of vehicles; Analyze the historical ride data to extract the temporal pattern and spatial distribution pattern of ride demand and the impact of holidays and weather factors on ride demand; According to the real-time ride demand information, combined with the real-time collected vehicle distribution information and the analysis results of historical ride data, a time series prediction model is used to predict the changing trend of the ride demand at each station in the future time period.

3. The method according to claim 1, characterized in that The dynamically adjusting the vehicle dispatching scheme according to the changing trend of the ride demand and the acquired current position, state and carrying capacity of the vehicle to optimize the vehicle allocation includes: According to the changing trend of the demand for rides and the acquired current position, status and carrying capacity of the vehicles, a multi-objective optimization model is constructed, wherein the multi-objective optimization model is used to minimize the waiting time of passengers, reduce the empty driving rate of vehicles, and balance the distribution of vehicles between the stations; In the multi-objective optimization model, constraints are set to achieve dynamic adjustment of the vehicle scheduling plan through the constraints. The constraints include the maximum driving distance, maximum passenger capacity, and service time window of the vehicle to ensure the rationality of the scheduling plan.

4. The method according to claim 1, characterized in that: It also includes: when an emergency is detected in a specific area causing abnormal traffic flow, adjusting the vehicle dispatching plan for the specific area and its surrounding areas; When an emergency is detected in a specific area causing abnormal traffic flow, adjusting the vehicle dispatching plan for the specific area and its surrounding areas includes: Monitor emergencies in real time, immediately activate emergency response mechanisms when emergencies are detected in specific areas, and assess the impact of emergencies on traffic flow; Combined with the real-time ride demand information, vehicle distribution and historical traffic data within the impact area of ​​the emergency, predict the abnormal change trend of traffic flow in the specific area and surrounding areas; Based on the prediction results, adjusting the vehicle dispatch plan for the specific area and its surrounding areas; The adjusting the vehicle dispatching plan of the specific area and its surrounding areas at least includes: increasing the vehicle dispatching frequency of the specific area and its surrounding areas.

5. The method according to claim 3, characterized in that: The assessment of the impact of different vehicle dispatching schemes on operational efficiency, the selection and implementation of the target vehicle dispatching scheme to ensure that operational efficiency is maximized while meeting passenger demand, includes: Solving the multi-objective optimization model to generate multiple vehicle scheduling solutions; Comprehensively evaluate the generated multiple vehicle dispatch plans and select the vehicle dispatch plan with the highest comprehensive score as the target vehicle dispatch plan. The evaluation indicators include passenger satisfaction, operating cost, and response speed. Vehicle dispatch is performed according to the target vehicle dispatch plan to ensure that operational efficiency is maximized while meeting passenger demand.

6. The method according to claim 5, characterized in that The evaluation of the impact of different vehicle dispatching schemes on operational efficiency and the selection and implementation of the target vehicle dispatching scheme include: The following calculation formula is used to evaluate the passenger satisfaction of each scheduling scheme: , operating costs and response speed , to determine the target vehicle scheduling plan: Passenger satisfaction The calculation formula is: ; in, represents the total number of passengers; It is Waiting time for passengers; It is The actual arrival time of passengers; is the maximum acceptable waiting time set by the system; is a penalty factor related to the passenger's historical behavior, used to adjust the additional waiting time caused by frequent cancellations or changes in itineraries; It is The historical reputation score of the passenger, ranging from 0 to 1; is a weight factor indicating the impact of weather conditions on waiting time; It is Weather condition index for the passengers' location; Operating costs The calculation formula is: ; in, Represents the number of all vehicles; It is The cost per kilometre of the vehicle; It is The distance travelled by the vehicle; It is The fixed cost of the vehicle; is an adjustment factor used to control the degree to which the vehicle's driving distance deviates from the average value; is the average distance travelled by all vehicles; is a weighting factor that represents the change in fuel cost; is a function based on the distance traveled and average speed Calculate fuel costs; Response speed The calculation formula is: ; in, Indicates the number of services requested by all; It is The time from when a service request is issued to when it is completed; is a weight factor used to consider the distance difference between service requests; It is The distance from the starting point to the end point of a service request; is a weight factor that represents the impact of traffic congestion on response speed; It is the real-time traffic congestion index when the service request occurs; Overall Rating The calculation formula is: ; in, , , , , are the weight coefficients of passenger satisfaction, operating cost, response speed, score variance and stability in the total score; is the standard deviation of passenger satisfaction, operating cost and response speed, which is used to measure the consistency of each indicator; It is a function used to measure the stability and reliability of the scheduling scheme in different time periods; It is the maximum operating cost threshold preset by the system.

7. The method according to any one of claims 1 to 5, characterized in that: The dynamic adjustment of the vehicle dispatching scheme to optimize vehicle allocation also includes: The following calculation formula is used to construct a multi-objective optimization model, and a variety of vehicle scheduling solutions are generated through the multi-objective optimization model: Define a first objective function, which is used to minimize the average waiting time of passengers , the corresponding calculation formula is: ; in, is a weighting factor used to balance the difference between individual passenger waiting time and the average waiting time; is the average waiting time of all passengers; is a weight factor that represents the impact of emergencies on waiting time; In the passenger seat and time The impact of unexpected events on waiting time; Define a second objective function, which is used to minimize the vehicle idle rate , the corresponding calculation formula is: ; in, is a weight factor used to control the degree to which the passenger travel distance deviates from the average value; It is The actual distance travelled by the vehicle carrying passengers; is the average of the actual passenger-carrying distances traveled by all vehicles; is a weight factor, which indicates the influence of maintenance status on the empty driving rate; is a function based on the maintenance status of the vehicle Calculate impact factor; Define a third objective function, which is used to balance the distribution of vehicles between the stations , the corresponding calculation formula is: ; in, is a weight factor used to consider the deviation between the current number of vehicles and historical data; It is The current number of vehicles at each station; is the average number of vehicles across all stations; It is The average number of vehicles in the history of each station; is a weight factor that represents the impact of demand fluctuations on vehicle distribution; It is on site and time Demand volatility index; Define a first constraint condition, the first constraint condition includes: the maximum driving distance of the vehicle Limitations: ; Define a second constraint condition, which includes: the maximum passenger capacity of the vehicle Limitations: ; Define a third constraint condition, the third constraint condition includes: service time window Limitations: ; Define a fourth constraint condition, the fourth constraint condition includes: vehicle maintenance time Limitations: ,in, It is The maintenance time required for the vehicle; Define a fifth constraint condition, the fifth constraint condition includes: vehicle charging / refueling time Limitations: ,in, It is The time required to charge / refuel the vehicle; The above formulas together constitute a multi-objective optimization problem, and multiple vehicle scheduling solutions are generated by weighted combination of multiple objective functions and multiple constraints.

8. A vehicle capacity dispatching system for intelligent transportation, characterized in that: include: A receiving module, used to receive real-time ride demand information from multiple transportation stations, wherein the real-time ride demand information includes the departure place, destination and estimated travel time of the passenger; A prediction module is used to predict the change trend of the ride demand at each station in the future time period based on the real-time ride demand information, combined with the current vehicle distribution at each transportation station and the historical ride data; An optimization module, used to dynamically adjust the vehicle dispatching plan according to the change trend of the ride demand and the acquired current position, status and carrying capacity of the vehicle, so as to optimize the vehicle allocation; The evaluation module is used to evaluate the impact of different vehicle scheduling schemes on operational efficiency, select and implement the target vehicle scheduling scheme to ensure that operational efficiency is maximized while meeting passenger needs.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a vehicle capacity scheduling method for smart transportation as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a vehicle capacity dispatching method for intelligent transportation as described in any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Intelligent bus scheduling method based on hybrid heuristic algorithm

    CN104504229A

  • Bus peak period intelligent scheduling method and system

    CN111311950A

  • Simulation system and method applied to intelligent bus demand balanced scheduling

    CN116151538A

  • New energy bus service system based on mobile internet

    CN118428574A

  • Public transport vehicle scheduling method and device, electronic equipment and storage medium

    CN118762517A

Cited By

  • Evaluation system about environmental sanitation service

    CN119338289A

  • Demand response type scheduling management method and system applied to intelligent public transportation system

    CN119809233A

  • Intelligent subway monitoring system

    CN120018072A

  • Multi-modal service strategy making method and device based on user travel trajectory

    CN120338561A

  • Streaming data processing method and system applied to smart city management

    CN120412285A