A vehicle dispatching method for a road passenger transport management system in a transportation hub.

Abstract

This invention discloses a vehicle dispatching method for a road passenger transport management system in a transportation hub, relating to the field of traffic control technology. The method includes: acquiring real-time operating status information and road traffic information for each vehicle; evaluating the passenger experience factor of each vehicle at the current moment based on the operating status information and road traffic information, and evaluating the driving hazard of each vehicle at the current moment based on the operating status information; determining the dispatching priority factor for each vehicle based on the passenger experience factor and driving hazard; and performing resource dispatching for each vehicle based on the dispatching priority factor to obtain the vehicle dispatching result. This invention effectively compensates for the problem of unreasonable dispatching caused by neglecting individual vehicle differences in traditional dispatching methods, thereby improving the rationality of vehicle dispatching.

Description

Technical Field

[0001] This invention relates to the field of traffic control technology, and specifically to a vehicle dispatching method for a road passenger transport management system in a transportation hub. Background Technology

[0002] In the context of today's ever-increasing and complex transportation demands, the vehicle dispatching methods used in road passenger transport management systems at transportation hubs have become a key measure to improve passenger service quality and operational efficiency. This method, supported by multi-source data fusion and cutting-edge intelligent technologies, aims to build a standardized, automated, and visualized management system for the entire road passenger transport business chain, from initial planning to end-user service.

[0003] In current vehicle dispatching methods, dynamically updating vehicle dispatching results based on real-time data is an essential step, enabling timely responses to various emergencies and constantly changing traffic conditions.

[0004] However, due to the differences in the real-time status of passengers in each vehicle, the vehicle's own driving status, and the traffic conditions encountered, these differences have led to an inadequate vehicle scheduling to some extent. Summary of the Invention

[0005] This invention provides a vehicle scheduling method for a road passenger transport management system in a transportation hub, which can improve the rationality of vehicle scheduling.

[0006] A first aspect of this invention provides a vehicle dispatching method for a road passenger transport management system in a transportation hub center, the method comprising:

[0007] Real-time acquisition of operational status information for each vehicle and road traffic information;

[0008] Based on the operational status information of each vehicle and road traffic information, the passenger adverse experience factors of each vehicle at the current moment are evaluated, and based on the operational status information of each vehicle, the driving danger of each vehicle at the current moment is evaluated.

[0009] Based on the negative passenger experience factors and driving hazards of each vehicle, the dispatch priority factors of each vehicle are determined respectively.

[0010] Based on the scheduling priority factor of each vehicle, resource scheduling is performed on each vehicle separately to obtain the vehicle scheduling result.

[0011] Furthermore, this invention also proposes to evaluate the passenger negative experience factors of each vehicle at the current moment based on the operating status information and road traffic information of each vehicle, including:

[0012] Based on the operational status information of each vehicle and road traffic information, the passenger anxiety level of each passenger in each vehicle is determined, and based on the operational status information of each vehicle and road traffic information, the future congestion influencing factors of each vehicle are predicted.

[0013] Based on the passenger anxiety level of each passenger in each vehicle and the passenger's travel time in each vehicle, the current congestion influencing factors of each vehicle are determined. The travel time is used to represent the time from the passenger's boarding time to the current time.

[0014] The future congestion impact factor of each vehicle is averaged with the current congestion impact factor to obtain the passenger negative experience factor of each vehicle at the current moment.

[0015] Furthermore, the present invention also proposes that the operational status information includes passenger boarding time, number of passengers and vehicle speed, and the road traffic information includes the congestion level of each route segment;

[0016] Based on the operational status information of each vehicle and road traffic information, the passenger anxiety level of each passenger in each vehicle is determined, including:

[0017] The time period from the boarding time of each passenger on the target vehicle to the current time is determined as the travel time of each passenger. The target vehicle is any vehicle.

[0018] The congestion levels of each passenger on the target vehicle during their travel time are used to construct a congestion level sequence for each passenger in chronological order.

[0019] The ratio of the number of passengers to the maximum load capacity at each moment is used to construct a sequence of passenger percentages for the target vehicle in chronological order.

[0020] Using the passenger percentage sequence as the weight sequence, a straight line is fitted to each congestion sequence to obtain the slope of the fitted straight line for each passenger.

[0021] Based on the target congestion mean, the slope of the fitted line, and the vehicle speed at each time point, the passenger anxiety level of each passenger is determined. The target congestion mean is the mean of each congestion level in the passenger's congestion sequence.

[0022] Furthermore, this invention proposes determining the passenger anxiety level for each passenger based on the mean target congestion level, the slope of the fitted straight line, and the vehicle speed at each time point, including:

[0023] The congestion evaluation value for each passenger is determined by multiplying the mean target congestion level for each passenger by the slope of the fitted line.

[0024] The ratio of vehicle speed to road speed limit at each time point is used to construct a speed percentage sequence of the target vehicle in chronological order.

[0025] By using each passenger's travel distance, congestion assessment value, travel time, and the speed ratio of the target vehicle, the passenger anxiety level of each passenger is determined. The travel distance is used to represent the distance the vehicle has traveled from the time the passenger boarded the vehicle to the current time.

[0026] Furthermore, the present invention also proposes that the operating status information includes the preset total driving time, the preset driving route, the driving time already traveled, and the current location of the vehicle, and the road traffic information includes the congestion level of each route segment and the predicted driving time to continue.

[0027] Based on the operational status information of each vehicle and road traffic information, the future congestion influencing factors for each vehicle are predicted, including:

[0028] Divide the predicted continuing travel time of the target vehicle by the difference between the preset total travel time and the travel time already traveled to obtain the travel timeout of the target vehicle. The target vehicle can be any vehicle.

[0029] Based on the target vehicle's preset driving route and its current location, determine the target vehicle's subsequent driving path.

[0030] By using the target vehicle's travel timeout, the route length and congestion of each segment in the subsequent travel path, the future congestion impact factors of the target vehicle can be determined.

[0031] Furthermore, this invention proposes determining the current congestion influencing factors for each vehicle based on the passenger anxiety level of each passenger and the duration of their journey, including:

[0032] The total travel time of each passenger in the target vehicle is added up to obtain the total travel time of the target vehicle. The target vehicle can be any vehicle.

[0033] Divide each passenger's travel time by the cumulative travel time to obtain the percentage of travel time for each passenger.

[0034] The current congestion impact factor of the target vehicle is obtained by summing the product of each passenger's travel time percentage and passenger anxiety level.

[0035] Furthermore, the present invention also proposes that the operating status information includes the vehicle's historical location;

[0036] Based on the operational status information of each vehicle, the driving hazard of each vehicle at the current moment is assessed, including:

[0037] Based on the direction and distance between the target vehicle's historical position at each moment in the reference time period and the vehicle's historical position at the next moment, the driving vector at each moment is determined. The target vehicle is any vehicle, and the reference time period is the preset time period before the current moment and closest to the current moment.

[0038] Arrange the driving vectors in chronological order to construct a driving vector sequence;

[0039] Based on the included angle value and the difference in magnitude between two adjacent driving vectors in the driving vector sequence, the included angle sequence and the difference in magnitude sequence are constructed respectively.

[0040] The driving hazard of the target vehicle at the current moment is determined based on the included angle sequence and the modulus difference sequence.

[0041] Furthermore, this invention also proposes determining the driving hazard of a target vehicle at the current moment based on the included angle sequence and the modulus difference sequence, including:

[0042] The mean value of each included angle value in the included angle sequence is averaged with the corresponding modulus difference value in the modulus difference sequence to obtain the driving change sequence;

[0043] The mean value of each driving change in the driving change sequence is obtained by averaging the driving change values.

[0044] The amount of driving change in the driving change sequence that exceeds the preset change threshold is marked as a dangerous driving change.

[0045] By using the average value of driving changes and the changes in driving at various dangerous conditions, the driving hazard of the target vehicle at the current moment can be determined.

[0046] Furthermore, the present invention also proposes that, after determining the scheduling priority factor for each vehicle based on the passenger negative experience factor and driving hazard of each vehicle, the method further includes:

[0047] Based on the road direction information of the target vehicle in the reference time period, the scheduling priority factor of the target vehicle is corrected to obtain the scheduling resource allocation degree of the target vehicle. The target vehicle is any vehicle, and the reference time period is the preset time period before the current time and closest to the current time.

[0048] Based on the scheduling priority factor of each vehicle, resource scheduling is performed on each vehicle separately to obtain the vehicle scheduling results, including:

[0049] Based on the resource allocation degree of each vehicle, resource scheduling is performed on each vehicle separately to obtain the vehicle scheduling result.

[0050] Furthermore, this invention also proposes to modify the scheduling priority factor of the target vehicle based on the road direction information of the target vehicle during the reference time period to obtain the scheduling resource allocation degree of the target vehicle, including:

[0051] Obtain the road centerline of the target vehicle during the reference time period;

[0052] Draw perpendicular lines from the historical positions of the target vehicle at various times during the reference period to the center line of the road to construct a sequence of intersection points, which includes the intersection points of each perpendicular line with the center line of the road.

[0053] Based on the direction and distance between two adjacent intersection points in the intersection point sequence, a road extension vector sequence is constructed, which includes the road extension vector formed by the direction and distance between two adjacent intersection points.

[0054] Based on the road extension vector sequence and the driving vector sequence of the target vehicle, the scheduling priority factor of the target vehicle is corrected to obtain the scheduling resource allocation degree of the target vehicle.

[0055] The present invention has the following beneficial effects:

[0056] The vehicle dispatching method of the road passenger transport management system in the transportation hub center provided in this embodiment of the invention first acquires the real-time operating status information and road traffic information of each vehicle to comprehensively grasp the real-time dynamics of vehicles and roads. Then, based on this information, it assesses the passenger experience factors and driving hazards of each vehicle at the current moment, considering vehicle conditions from both passenger experience and driving safety dimensions to accurately identify factors that may affect the rationality of dispatching. Next, based on the passenger experience factors and driving hazards, it determines the dispatching priority factors for each vehicle, assigning each vehicle a reasonable dispatching priority, fully considering the dispatching needs of different vehicles under different circumstances. Finally, it performs resource dispatching based on the dispatching priority factors of each vehicle to obtain the vehicle dispatching result. Thus, this dispatching method, which uses real-time data as a basis and comprehensively considers passenger experience and driving safety to determine dispatching priorities, can perform differentiated dispatching based on the actual situation of each vehicle, promptly responding to various emergencies and constantly changing traffic conditions. It effectively compensates for the unreasonable dispatching problems caused by traditional dispatching methods that ignore individual vehicle differences, thereby improving the rationality of vehicle dispatching. Attached Figure Description

[0057] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating a vehicle dispatching method for a road passenger transport management system at a transportation hub, as provided in an embodiment of the present invention.

[0059] Figure 2 This is a first process diagram of S102 provided in an embodiment of the present invention;

[0060] Figure 3 This is a second schematic diagram of the process S102 provided in one embodiment of the present invention. Detailed Implementation

[0061] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a vehicle dispatching method for a road passenger transport management system in a transportation hub center according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0063] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with the relevant provisions of laws and regulations.

[0064] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of the present invention. However, they do not mean that the applicant has used or necessarily used the solution.

[0065] In traditional road passenger transport management systems, dynamic dispatching decisions rely on real-time vehicle operating status information and road traffic information collection, but lack a comprehensive quantitative assessment mechanism for passenger experience and driving risks. The system cannot establish a correlation model between passenger anxiety and vehicle performance fluctuations, resulting in dispatching priority determination relying solely on single-dimensional data, which fails to accurately reflect the dynamic changes in the actual operating status of vehicles. This directly leads to a deviation of dispatching resource allocation from actual needs, causing delays in high-priority vehicle dispatching and redundancy in low-priority vehicle resources, reducing overall dispatching efficiency and passenger satisfaction.

[0066] Faced with the aforementioned problems, this invention first recognized the fundamental contradiction in existing road passenger transport management systems, which fail to effectively integrate multi-dimensional dynamic data, leading to decision-making biases. Traditional methods rely solely on single-dimensional parameters such as location and congestion levels, failing to capture the non-linear characteristics of passenger experience changes with travel duration and road conditions, nor to identify the cumulative effect of driving behavior patterns on safety risks. To address this, this invention attempts to establish a two-dimensional evaluation model, where passenger negative experience factors are correlated with real-time travel environment and individual anxiety evolution, and driving hazard should reflect abnormal fluctuations in vehicle trajectory. Analysis revealed that simply increasing data collection frequency or adding sensor types does not solve the core problem; the key lies in establishing evaluation indicators that can simultaneously quantify passenger comfort and driving safety, and dynamically integrating these two to form the basis for scheduling decisions. After multiple rounds of scheme verification, it was finally determined that dynamically adjusting scheduling priorities by calculating the composite evaluation value of each vehicle in real time avoids the one-sidedness of a single indicator and achieves dynamic optimization of resource allocation.

[0067] In this regard, such as Figure 1 As shown, a flowchart of a vehicle dispatching method for a road passenger transport management system in a transportation hub center is provided. This vehicle dispatching method for a road passenger transport management system in a transportation hub center can be applied to the road passenger transport management system in a transportation hub center. The vehicle dispatching method for the road passenger transport management system in a transportation hub center may include the following steps S101 to S104.

[0068] S101, which obtains real-time operating status information and road traffic information for each vehicle;

[0069] S102, based on the operating status information of each vehicle and road traffic information, assess the passenger adverse experience factor of each vehicle at the current moment, and based on the operating status information of each vehicle, assess the driving hazard of each vehicle at the current moment.

[0070] S103, based on the passenger negative experience factors and driving hazards of each vehicle, determine the dispatch priority factor of each vehicle respectively;

[0071] S104. Based on the scheduling priority factor of each vehicle, resource scheduling is performed on each vehicle separately to obtain the vehicle scheduling result.

[0072] In this embodiment, the operating status information refers to the real-time data generated by the vehicle during operation. Specifically, it can be achieved by using onboard sensors or Global Positioning System (GPS) devices to collect information such as vehicle location, vehicle speed, number of passengers, and driving time, which is used to reflect the current actual operating status of the vehicle.

[0073] Road traffic information refers to traffic condition data along a vehicle's route. Specifically, it can be obtained through traffic monitoring systems or real-time navigation platforms, such as information on the congestion level of a route segment and the predicted duration of continued travel, in order to assess road traffic efficiency.

[0074] Passenger negative experience factor refers to an indicator that quantifies the degree of discomfort caused to passengers during their journey due to factors such as congestion and delays. Specifically, it can be calculated by analyzing passenger anxiety, length of the journey, and parameters related to future congestion impact factors, and is used to reflect the current negative impact of the vehicle on the passenger experience.

[0075] Driving hazard refers to the level of safety risk that a vehicle poses while driving. It can be specifically assessed by analyzing data such as changes in the vehicle's driving vector and its rapid acceleration and deceleration behavior, and is used to determine the safety level of the vehicle's current driving state.

[0076] The scheduling priority factor is a comprehensive evaluation value used to determine the priority of vehicle resource allocation. Specifically, it can be calculated by weighting or combining passenger negative experience factors and driving hazards, and is used to dynamically adjust the scheduling order of different vehicles.

[0077] Resource scheduling refers to operations such as route planning and schedule adjustment for vehicles based on priority. Specifically, it can be achieved by using intelligent algorithms to match available resources with vehicle demand, thereby optimizing the overall operational efficiency of the passenger transport system.

[0078] The core innovation of this invention lies in establishing a dual-dimensional evaluation model for passenger experience and driving safety by collecting real-time vehicle operation status information and road traffic information, dynamically calculating scheduling priorities and implementing differentiated resource allocation, thereby achieving vehicle scheduling decisions that balance service quality and safety efficiency in complex traffic environments.

[0079] As an example, the road passenger transport management system first collects real-time data on vehicle location, vehicle speed, passenger boarding and alighting information, and road congestion through onboard terminals and roadside equipment. Specifically, vehicle location is obtained via GPS positioning, speed is measured by vehicle speed sensors, passenger information is obtained through onboard cameras and passenger card swipe data, and road congestion is derived from roadside cameras and vehicle driving data analysis.

[0080] The collected data is then transmitted to the data center in real time. In the data center, the data undergoes preprocessing: data cleaning is performed to remove duplicate records, correct erroneous data, and fill in missing values ​​to ensure data quality and accuracy; data integration is then performed to merge data from different sources and formats into a unified dataset; finally, the cleaned and integrated data is stored in a database or data lake to prepare for subsequent analysis.

[0081] Then, the road passenger transport management system uses machine learning algorithms to process the collected data and calculate the passenger negative experience factor for each vehicle. Specifically, factors such as passenger travel time, vehicle crowding, and road congestion can be input into a trained neural network model, which outputs the passenger negative experience factor. Simultaneously, by analyzing changes in vehicle acceleration and direction, a driving hazard index is calculated.

[0082] Next, the passenger negative experience factor and the driving hazard index are multiplied to obtain the dispatch priority factor for each vehicle. Finally, vehicles are ranked according to their dispatch priority factors, and high-priority vehicles are dispatched first, with measures such as arranging detours or priority passage. The road passenger transport management system recalculates and updates the vehicle dispatch results at regular intervals to adapt to the dynamically changing traffic environment.

[0083] This embodiment first acquires real-time operational status information and road traffic information for each vehicle, comprehensively understanding the real-time dynamics of vehicles and roads. Then, based on this information, it assesses the passenger experience factors and driving hazards of each vehicle at the current moment, considering vehicle conditions from both passenger experience and driving safety perspectives to accurately identify factors that may affect the rationality of dispatching. Next, based on the passenger experience factors and driving hazards, it determines the dispatching priority factors for each vehicle, assigning each vehicle a reasonable dispatching priority, fully considering the dispatching needs of different vehicles under different circumstances. Finally, it performs resource dispatching based on the dispatching priority factors of each vehicle, obtaining the vehicle dispatching result. Thus, this dispatching method, based on real-time data and comprehensively considering passenger experience and driving safety to determine dispatching priorities, can perform differentiated dispatching according to the actual situation of each vehicle, promptly responding to various emergencies and constantly changing traffic conditions. It effectively compensates for the unreasonable dispatching problems caused by traditional dispatching methods neglecting individual vehicle differences, thereby improving the rationality of vehicle dispatching.

[0084] In some of the solutions described above, the present invention proposes to assess passenger negative experience factors based on vehicle operating status information and road traffic information. However, in this process, relying solely on static data at the current moment may result in assessment results that fail to fully reflect the dynamic changes in passenger experience during the ride, such as the potential impact of future congestion not being effectively considered.

[0085] In this regard, such as Figure 2 As shown, the present invention further proposes that S102 includes the following S201 to S203:

[0086] S201, based on the operating status information of each vehicle and road traffic information, determines the passenger anxiety level of each passenger in each vehicle, and based on the operating status information of each vehicle and road traffic information, predicts the future congestion influencing factors of each vehicle.

[0087] S202, based on the passenger anxiety level of each passenger in each vehicle and the passenger's travel time in each vehicle, determine the current congestion influencing factor for each vehicle. The travel time is used to characterize the time from the passenger's boarding time to the current time.

[0088] S203, the future congestion impact factor of each vehicle is averaged with the current congestion impact factor to obtain the passenger negative experience factor of each vehicle at the current moment.

[0089] In this embodiment, passenger anxiety level is an indicator used to quantify the degree of anxiety experienced by passengers during a ride. It comprehensively considers the impact of vehicle operating conditions and road traffic conditions on passenger psychology. For example, frequent braking and prolonged traffic jams may cause passengers to feel anxious. This indicator uses a certain algorithm to convert these factors into specific numerical values ​​to measure the degree of anxiety.

[0090] The future congestion impact factor is a quantitative prediction of the degree of congestion that vehicles may cause over a future period due to changes in road traffic conditions and their own operational status. It estimates the impact of vehicles on congestion within a specific future timeframe based on current operational and road traffic information and using a specific predictive model.

[0091] The travel time indicates the length of time elapsed from the moment a passenger boarded the vehicle to the current moment. This time parameter is used to measure the length of time a passenger spends on the vehicle, and is combined with passenger anxiety levels to assess the impact of current congestion on passengers.

[0092] The current congestion impact factor is a quantitative indicator that reflects the impact of current traffic congestion on passengers, calculated based on the passenger anxiety level and the duration of each passenger's journey. It embodies the direct impact of current traffic congestion on the passenger experience.

[0093] As an example, a passenger anxiety assessment model is established. This model, based on extensive experimental data and psychological research, correlates different operating conditions and road traffic factors with passenger anxiety levels. For instance, a higher anxiety weight is assigned when the vehicle brakes frequently and is in heavily congested traffic, and a lower anxiety weight is assigned when the vehicle travels smoothly in uncongested traffic. For each passenger, relevant information based on the vehicle's operating condition and the surrounding road traffic environment is input into the assessment model to calculate that passenger's anxiety level.

[0094] Simultaneously, a congestion prediction model is constructed based on historical and current vehicle operating status information and road traffic information. This congestion prediction model can employ machine learning algorithms, such as time series analysis and neural networks. Historical data is used to train the model, enabling it to learn the relationship between different operating states and road traffic information and future congestion levels. Then, the currently collected vehicle operating status information and road traffic information are input into the trained congestion prediction model to predict the future congestion impact factor for vehicles over a future period. This future congestion impact factor can be quantified according to different levels of congestion severity; for example, mild congestion corresponds to a lower factor value, and severe congestion corresponds to a higher factor value.

[0095] Then, for each vehicle, collect the passenger anxiety level and travel time for each passenger. Establish a current congestion impact factor calculation model. This model can consider the weighted relationship between passenger anxiety level and travel time on the impact of current congestion. For example, higher passenger anxiety level and longer travel time result in a greater contribution to the current congestion impact factor. For each passenger in the vehicle, calculate their contribution to the current congestion impact factor based on their passenger anxiety level and travel time, according to the current congestion impact factor calculation model. Summarize the contribution values ​​of all passengers in the vehicle (e.g., by averaging or weighted summation) to obtain the current congestion impact factor for that vehicle.

[0096] Finally, for each vehicle, its future congestion impact factor and current congestion impact factor have been obtained. The arithmetic mean of these two factors is then calculated, yielding the passenger negative experience factor for that vehicle at the current moment.

[0097] This embodiment enables a comprehensive assessment of passenger experience across all vehicles, considering both current conditions and potential future changes. This allows for a more accurate understanding of passenger needs, providing a more reliable basis for subsequent vehicle dispatching decisions. This approach not only improves passenger satisfaction but also optimizes overall operational efficiency, reducing complaints and negative impacts caused by passenger dissatisfaction.

[0098] In some of the solutions described above in this invention, a method for determining passenger anxiety based on operational status information and road traffic information has been proposed. However, in the specific implementation process, there is still a lack of accuracy in quantifying the degree of anxiety of each passenger during the ride due to traffic congestion and changes in vehicle load. Existing methods fail to effectively combine the trend of congestion changes and the dynamic changes in vehicle load during the passenger's ride time, resulting in insufficient accuracy in passenger anxiety assessment.

[0099] In response, this invention further proposes that the operational status information includes passenger boarding time, number of passengers, and vehicle speed, and the road traffic information includes the congestion level of each route segment;

[0100] S201 may specifically include:

[0101] The time period from the boarding time of each passenger on the target vehicle to the current time is determined as the travel time of each passenger. The target vehicle is any vehicle.

[0102] The congestion levels of each passenger on the target vehicle during their travel time are used to construct a congestion level sequence for each passenger in chronological order.

[0103] The ratio of the number of passengers to the maximum load capacity at each moment is used to construct a sequence of passenger percentages for the target vehicle in chronological order.

[0104] Using the passenger percentage sequence as the weight sequence, a straight line is fitted to each congestion sequence to obtain the slope of the fitted straight line for each passenger.

[0105] Based on the target congestion mean, the slope of the fitted line, and the vehicle speed at each time point, the passenger anxiety level of each passenger is determined. The target congestion mean is the mean of each congestion level in the passenger's congestion sequence.

[0106] In this embodiment, the congestion sequence records the trend of congestion changes on each route segment traversed by passengers during their travel time. The passenger percentage sequence reflects the dynamic changes in vehicle load over time. The linear regression method is used to calculate the weighted rate of change of congestion over time in the linear fitting process. The slope of the fitted line represents the overall upward or downward trend of congestion during the passenger's travel time. The target congestion mean is the average value of the congestion sequence. Vehicle speed is used to measure the impact of vehicle driving efficiency on passenger anxiety.

[0107] Specifically, for each passenger on the target vehicle, the travel time from their boarding time to the current time is first extracted. The real-time congestion levels of each route segment within that time period are then obtained in chronological order, forming a congestion sequence. Simultaneously, a passenger percentage sequence is generated based on the ratio of the number of passengers to the vehicle's maximum capacity at each moment. The passenger percentage sequence is then used as weights to perform a weighted linear fit on the congestion sequence. The slope of the fitted line reflects the weighted trend of congestion changes.

[0108] As an example, for each passenger on the target vehicle, first record their boarding time and current time. The time interval from the passenger's boarding time to the current time is defined as the passenger's travel period. For example, if passenger A boarded at 9:00 AM and the current time is 10:30 AM, then passenger A's travel period is 9:00 AM - 10:30 AM.

[0109] Then, during the target vehicle's journey, the congestion information of the route segment the vehicle is on is obtained in real time. In this solution, we can set the congestion level value to a range of 1-10. A higher congestion level value indicates a more congested route segment, while a lower value indicates smoother traffic.

[0110] Specifically, congestion levels can be obtained through data interfaces with traffic management departments, vehicle sensors (such as cameras and radar), and traffic flow analysis algorithms. For each passenger, the congestion levels of the route segments they have traveled during their travel time are arranged chronologically to form a congestion level sequence. For example, if passenger B's travel time is 8:00-9:00, and the vehicle traveled through route segment 1 (8:00-8:20, congestion level 3), route segment 2 (8:20-8:50, congestion level 5), and route segment 3 (8:50-9:00, congestion level 4), then passenger B's congestion level sequence is [3, 5, 4].

[0111] Simultaneously, the number of passengers on the vehicle at each moment is counted in real time during the vehicle's operation. This can be achieved through a passenger counting system inside the vehicle (such as one based on weight sensors or infrared sensors). The ratio of the number of passengers at each moment to the maximum load capacity is arranged in chronological order to form a passenger percentage sequence. For example, if the target vehicle has a maximum load capacity of 50 people, and there are 30 passengers at time t1, 40 passengers at time t2, and 35 passengers at time t3, then the passenger percentage sequence is [30 / 50, 40 / 50, 35 / 50], which is [0.6, 0.8, 0.7].

[0112] Then, using the passenger percentage sequence as the weight sequence, a straight line is fitted to each congestion sequence to obtain the slope of the fitted line for each passenger. The straight line fitting can employ mathematical methods such as the least squares method. Next, the target congestion mean is calculated for each passenger, which is the average of the congestion levels in their congestion sequence. For example, if passenger C's congestion sequence is [2,4,3,5], then the target congestion mean is (2+4+3+5) / 4 = 3.5.

[0113] The more passengers in a vehicle and the more congested the traffic, the more likely passengers are to experience anxiety. This is because a larger number of passengers compresses personal space, potentially causing feelings of crowding and discomfort. It also leads to poorer air circulation, increased carbon dioxide concentration, and a relative decrease in oxygen levels. Furthermore, multiple passengers may generate more noise and disturbances, such as conversations and ringing phones, which can be more jarring in the enclosed space, increasing passenger irritation. If traffic is congested at this time, passenger anxiety will be further amplified. Therefore, the ratio of the number of passengers to the maximum load capacity at each moment is used as the weight for the congestion level at that moment, and a weighted linear regression is performed.

[0114] Finally, taking into account the target congestion mean, the slope of the fitted line, and the vehicle speed at each time point, a passenger anxiety calculation model is established. By substituting the target congestion mean, the slope of the fitted line, and the vehicle speed at each time point for each passenger into the passenger anxiety calculation model, the passenger anxiety level for each passenger is obtained.

[0115] This embodiment enables a more accurate assessment of each passenger's anxiety level. This allows for more rational vehicle scheduling and improved passenger satisfaction. Specifically, by considering multiple factors such as passenger boarding time, passenger numbers, vehicle speed, and route congestion, the actual passenger experience can be comprehensively reflected. Furthermore, by constructing congestion and passenger percentage sequences, the dynamic changes in congestion and passenger numbers can be captured. Finally, through linear fitting and comprehensive consideration of multiple indicators, a more objective and accurate assessment of passenger anxiety levels can be obtained. This method provides a more reliable basis for subsequent vehicle scheduling, thereby optimizing the overall quality of passenger transport services.

[0116] In some of the solutions described above in this invention, a method is proposed to calculate the slope of a fitted straight line by using passenger congestion sequence and passenger percentage sequence, and then combine this with the target congestion mean and vehicle speed to determine passenger anxiety. However, in this process, the volatility of vehicle speed is not effectively quantified, resulting in the assessment of passenger anxiety failing to accurately reflect the dynamic impact of speed changes during actual travel, thus affecting the accuracy of vehicle scheduling priority factors.

[0117] To address this, the present invention further proposes a method for determining the passenger anxiety level of each passenger based on the mean target congestion level, the slope of the fitted straight line, and the vehicle speed at each time point, including:

[0118] The congestion evaluation value for each passenger is determined by multiplying the mean target congestion level for each passenger by the slope of the fitted line.

[0119] The ratio of vehicle speed to road speed limit at each time point is used to construct a speed percentage sequence of the target vehicle in chronological order.

[0120] By using each passenger's travel distance, congestion assessment value, travel time, and the speed ratio of the target vehicle, the passenger anxiety level of each passenger is determined. The travel distance is used to represent the distance the vehicle has traveled from the time the passenger boarded the vehicle to the current time.

[0121] In this embodiment, the congestion assessment value quantifies the cumulative effect and trend of congestion during passenger travel by multiplying the target congestion mean by the slope of the fitted straight line; the speed ratio sequence constructs a dynamic indicator of the psychological impact of speed fluctuations on passengers by using the ratio of vehicle speed to road speed limit; the distance traveled combined with the duration of travel is used to measure the comprehensive perception of spatial displacement and time consumption during vehicle travel; the collaborative calculation of the speed ratio sequence and the congestion assessment value realizes a multi-dimensional dynamic assessment of passenger anxiety.

[0122] Specifically, firstly, the mean of each passenger's congestion sequence is multiplied by the slope of the fitted straight line to generate a congestion assessment value reflecting the degree and rate of change of congestion. Next, the ratio of vehicle speed to road speed limit is arranged chronologically to form a speed proportion sequence, which characterizes the compliance fluctuation of vehicle speed relative to the road speed limit during travel. Then, the distance already traveled is used as a spatial dimension parameter and weighted with the time dimension parameter of the congestion assessment value. This weighted sum is then combined with the cumulative effect of travel time, and finally corrected using a dynamic adjustment factor for the speed proportion sequence to obtain the final assessment value of passenger anxiety.

[0123] As an example, a passenger's passenger anxiety level can be determined using the following formula 1:

[0124] Formula 1

[0125] In Formula 1, F represents the passenger's anxiety level, L represents the distance the passenger has traveled, and T represents the duration the passenger has traveled. The mean speed percentage of the target vehicle speed percentage sequence is used to characterize the speed percentage of the target vehicle, D is used to characterize the congestion evaluation value of passengers, and norm is used to characterize the linear normalization process.

[0126] in, The smaller the value, the longer the travel time within a short distance, and the more likely it is to cause anxiety. The closer a value is to 1, the closer the vehicle speed is to the road speed limit. This indicates that the vehicle is following traffic rules, resulting in a longer travel time over a short distance, which is normal. The larger it is, the more it needs to be Turn it down.

[0127] Furthermore, since the calculated passenger anxiety level may have an unreasonable range of values, it can be normalized to make the results easier to understand and compare. The normalization method can be minimization, a well-known technique that will not be elaborated upon here. Through this normalization process, the passenger anxiety level values ​​become more standardized and reasonable, better meeting the needs of practical applications.

[0128] This embodiment comprehensively considers multiple factors such as the passenger's travel distance, traffic congestion, travel time, and vehicle speed to more accurately assess the passenger's anxiety level. This provides a more reliable basis for subsequent vehicle dispatching decisions, helping to improve the passenger experience and enhance the quality of passenger transport services.

[0129] In some of the solutions described above in this invention, a method is proposed to predict future congestion influencing factors based on vehicle operating status information and road traffic information. However, the prediction process fails to combine the risk of vehicle travel time delays with the congestion distribution of subsequent travel routes, resulting in a deviation between the predicted results of future congestion impacts and the actual traffic conditions.

[0130] In response, the present invention further proposes that the operating status information includes the preset total driving time, the preset driving route, the driving time already traveled, and the current location of the vehicle, and the road traffic information includes the congestion level of each route segment and the predicted driving time to continue.

[0131] S201 may also include:

[0132] Divide the predicted continuing travel time of the target vehicle by the difference between the preset total travel time and the travel time already traveled to obtain the travel timeout of the target vehicle. The target vehicle can be any vehicle.

[0133] Based on the target vehicle's preset driving route and current location, determine the target vehicle's subsequent driving path;

[0134] By using the target vehicle's travel timeout, the route length and congestion of each segment in the subsequent travel path, the future congestion impact factors of the target vehicle can be determined.

[0135] In this embodiment, the trip timeout rate is calculated as the ratio of the predicted continued travel time to the remaining planned travel time, used to quantify the risk of trip delay. The subsequent travel route is determined by the topological relationship between the preset travel route and the vehicle's current location, ensuring the accuracy of the route prediction.

[0136] Specifically, the trip timeout rate for the target vehicle is obtained by dividing the predicted continued travel time by the difference between the preset total travel time and the travel time already taken. For example, if the vehicle has traveled for 2 hours, the preset total travel time is 5 hours, and the predicted continued travel time is 3.5 hours, then the trip timeout rate is 3.5 / (5-2) = 1.17, indicating a 17% risk of timeout. The subsequent travel path is determined by the unfinished sections of the preset travel route. For example, if the vehicle's current location is at route point A, and the preset route is A→B→C→D, then the subsequent path is B→C→D.

[0137] As an example, the future congestion impact factor of vehicles can be determined using the following formula 2:

[0138] Formula 2

[0139] In formula 2, Factors used to characterize the future impact of vehicle congestion Used to characterize the predicted driving time of a vehicle, Used to characterize the preset total driving time of the vehicle, Used to represent the time a vehicle has traveled. The length of the j-th route segment in the subsequent travel path is represented by N, and the total length of the subsequent travel path is represented by N. The congestion level of the j-th route segment in the subsequent travel path is used to characterize the congestion level, and J is used to characterize the total number of route segments in the subsequent travel path.

[0140] in, The larger the value, the more severe the trip timeout and the worse the passenger experience. The larger, The larger; with As The weight of the congested route segment is determined by its length; the longer the congested route segment, the greater its congestion impact, thus leading to... The larger.

[0141] This embodiment accurately predicts potential future traffic congestion for vehicles, providing crucial information for subsequent vehicle dispatching. This multi-dimensional data-driven prediction method considers factors such as vehicle journey progress, route planning, and road congestion, enabling a more comprehensive assessment of future vehicle performance. By introducing the concept of journey timeout, the solution effectively reflects the risk of vehicle delays, allowing for priority consideration of these vehicles in dispatching decisions. Furthermore, by incorporating the specific circumstances of subsequent travel routes, the solution weights the congestion impact of different road segments, improving the accuracy and relevance of the prediction. This prediction method provides vehicle dispatching systems with more refined and dynamic decision-making support, contributing to improved overall dispatching efficiency, reduced passenger waiting times, and optimized road resource utilization.

[0142] In some of the solutions described above in this invention, it is proposed to determine the current congestion influencing factors by combining passenger anxiety level and travel time. However, when combining the passenger anxiety levels of multiple passengers, it is difficult to accurately reflect the difference in the contribution of different passengers to the overall congestion impact due to differences in travel time if only simple summation or averaging is performed.

[0143] In this regard, the present invention further proposes that S202 may specifically include:

[0144] The total travel time of each passenger in the target vehicle is added up to obtain the total travel time of the target vehicle. The target vehicle can be any vehicle.

[0145] Divide each passenger's travel time by the cumulative travel time to obtain the percentage of travel time for each passenger.

[0146] The current congestion impact factor of the target vehicle is obtained by summing the product of each passenger's travel time percentage and passenger anxiety level.

[0147] In this embodiment, the calculation of the cumulative travel time quantifies the overall load of the passenger group's travel status through the time dimension; the determination of the travel time percentage transforms the individual travel time into a weighting coefficient relative to the whole; the cumulative summation operation achieves the quantitative superposition of individual impact differences through a linear combination of the weighting coefficient and the passenger's anxiety level. For example, when a passenger's travel time accounts for 30% of the total cumulative value and their passenger anxiety level is 0.8, the passenger's contribution to the current congestion impact factor is 0.24.

[0148] Specifically, the target vehicle collects the boarding time of each passenger in real time through the onboard terminal and calculates the travel time from boarding time to the current time. The travel times of all passengers are summed to form a total cumulative value, which reflects the cumulative effect of the vehicle's current passenger load. The percentage of each passenger's travel time represents their relative weight in the overall time load; when a passenger's travel time is significantly longer than other passengers, their percentage will increase significantly. Multiplying each passenger's anxiety level by their percentage and summing the results strengthens the contribution of passengers with long travel times and high anxiety levels to the current congestion impact factor. For example, if there are two passengers in the vehicle with travel times of 60 minutes and 30 minutes respectively, the cumulative value is 90 minutes, and their percentages are 66.7% and 33.3% respectively. If their passenger anxiety levels are 0.9 and 0.6 respectively, the current congestion impact factor is calculated as 0.9 × 0.667 + 0.6 × 0.333 = 0.8, which more accurately reflects the actual difference in impact compared to the 0.75 obtained by the simple averaging method.

[0149] As an example, first add up the travel time of each passenger in the target vehicle to get the total travel time of the target vehicle. For example, suppose there are 3 passengers in the target vehicle, and their travel time is 20 minutes, 30 minutes and 40 minutes respectively, then the total travel time is 90 minutes.

[0150] Then divide each passenger's travel time by the cumulative travel time to obtain the percentage of travel time for each passenger. Continuing with the example above, the percentages of travel time for the three passengers are 2 / 9, 1 / 3, and 4 / 9, respectively.

[0151] Finally, the product of each passenger's travel time percentage and their anxiety level is summed to obtain the current congestion impact factor for the target vehicle. Assuming the passenger anxiety levels of the three passengers are 0.6, 0.8, and 0.7 respectively, the current congestion impact factor is (2 / 9 × 0.6 + 1 / 3 × 0.8 + 4 / 9 × 0.7) = 0.7.

[0152] This embodiment allows for a more accurate assessment of the current congestion impact by comprehensively considering the travel time and anxiety levels of each passenger on the vehicle. This provides a more rational basis for subsequent vehicle dispatching decisions, contributing to improved overall passenger service quality and passenger satisfaction.

[0153] In some of the solutions described above in this invention, the assessment of driving hazards mainly relies on the real-time operating status information of the vehicle, but fails to effectively capture the abrupt changes in direction and speed during driving, resulting in insufficient accuracy in identifying dynamic changes in driving behavior hazards and affecting the accuracy of scheduling priority factors.

[0154] In this regard, such as Figure 3 As shown, the present invention further proposes that the operating status information includes the vehicle's historical location;

[0155] S102 may also include the following S301 to S304:

[0156] S301, Based on the direction and distance between the historical vehicle position of the target vehicle at each time in the reference time period and the historical vehicle position at the next time, determine the driving vector at each time. The target vehicle is any vehicle, and the reference time period is the preset time period before the current time and closest to the current time.

[0157] S302, Arrange the driving vectors in chronological order to construct a driving vector sequence;

[0158] S303, based on the included angle value and the magnitude difference value formed between two adjacent driving vectors in the driving vector sequence, the included angle sequence and the magnitude difference value sequence are constructed respectively;

[0159] S304, based on the included angle sequence and the modulus difference sequence, determines the driving hazard of the target vehicle at the current moment.

[0160] In this embodiment, the driving vector is generated from time-series data of the vehicle's historical location, including both direction and distance dimensions. The driving vector sequence is constructed using a time window mechanism, selecting historical location data within the most recent preset time period. The included angle sequence reflects the drastic change in the vehicle's driving direction, while the magnitude difference sequence characterizes the suddenness of speed changes.

[0161] Specifically, the vehicle-mounted positioning device continuously collects historical location data of the target vehicle within a reference time period, and the position difference between adjacent moments constitutes a driving vector. After sorting the driving vector sequence by time, the directional angle and magnitude difference between adjacent driving vectors are calculated to form a feature sequence reflecting the dynamic changes in driving behavior.

[0162] As an example, the most recent 5 minutes can be selected as the reference time period. For the target vehicle, the vehicle's historical position is recorded every 10 seconds, resulting in 30 historical position points. The direction angle and distance between two adjacent historical position points are calculated, resulting in 29 driving vectors. These driving vectors are then arranged in chronological order to form a driving vector sequence.

[0163] Furthermore, the included angle between two adjacent driving vectors is calculated, resulting in 28 included angle values, forming an included angle sequence. Simultaneously, the difference in magnitude between two adjacent driving vectors is calculated, resulting in 28 magnitude difference values, forming a magnitude difference sequence.

[0164] Therefore, a driving hazard assessment model can be trained using machine learning algorithms based on the included angle sequence and the modulus difference sequence. By inputting the current included angle sequence and modulus difference sequence into the driving hazard assessment model, the driving hazard score of the target vehicle at the current moment can be obtained.

[0165] This embodiment enables a comprehensive characterization of a vehicle's trajectory based on historical location data, by constructing driving vector sequences, angle sequences, and magnitude difference sequences. These sequence data can then be used to assess driving hazards, accurately reflecting the vehicle's actual driving conditions and effectively identifying dangerous driving behaviors. This method avoids the limitations of single-indicator assessments, improving the accuracy and reliability of driving hazard assessment. Furthermore, using a fixed reference time period for assessment allows for timely detection of changes in driving behavior, enabling dynamic monitoring of driving hazards. This provides crucial information for subsequent vehicle dispatching decisions, contributing to improved road traffic safety.

[0166] In some of the solutions described above in this invention, an angle sequence and a modulus difference sequence are constructed based on the included angle value and the modulus difference value formed between two adjacent driving vectors in the driving vector sequence, respectively, to determine the driving hazard. However, in this process, it is difficult to effectively distinguish between normal driving changes and dangerous driving changes by relying solely on the independent analysis of the included angle and modulus difference values, which may lead to errors in the assessment of driving hazards.

[0167] In this regard, the present invention further proposes that S304 may specifically include:

[0168] The mean value of each included angle value in the included angle sequence is averaged with the corresponding modulus difference value in the modulus difference sequence to obtain multiple driving change values;

[0169] Arrange the various changes in driving speed in chronological order to construct a driving speed change sequence;

[0170] The mean value of each driving change in the driving change sequence is obtained by averaging the driving change values.

[0171] The amount of driving change in the driving change sequence that exceeds the preset change threshold is marked as a dangerous driving change.

[0172] By constructing a quantum sequence of dangerous driving changes from the continuous dangerous driving changes in the driving change sequence;

[0173] By using the mean of driving changes and the quantum sequence of driving changes at each dangerous moment, the driving hazard of the target vehicle at the current moment can be determined.

[0174] In this embodiment, the mean value processing employs the arithmetic mean of the angle value and the difference in modulus, ensuring that the change in driving range simultaneously reflects the combined effects of changes in direction and speed. The mean value of driving range is calculated using a sliding window or overall sequence averaging algorithm to characterize the overall driving stability of the target vehicle within a reference time period. A preset change threshold is set based on historical accident data or experimental data to filter out driving ranges that deviate from normal driving patterns. The quantity and degree of deviation of dangerous driving ranges are used as quantitative indicators, combined with the mean value of driving ranges to determine driving hazard.

[0175] Specifically, the angle and magnitude difference between adjacent vectors in the driving vector sequence are merged into a single driving change, eliminating the limitations of single-parameter analysis. The driving change sequence is averaged to obtain the overall trend, which serves as a benchmark for judging hazard. The markers for hazardous driving changes are based on preset thresholds, effectively identifying abnormal driving behaviors such as sharp turns, rapid acceleration, or sudden deceleration. The combined assessment of the driving change mean and hazardous driving changes considers both overall driving stability and captures sudden dangerous maneuvers.

[0176] As an example, the driving hazard of a vehicle at the current moment can be specifically determined using the following formula 3:

[0177] Formula 3

[0178] In Formula 3, W is used to characterize the driving hazard of the vehicle at the current moment. The value of e is used to characterize the mean of driving changes. e is used to identify the index of the quantum sequence of dangerous driving changes constructed from continuous dangerous driving changes. Specifically, we divide multiple consecutive dangerous driving changes into a subsequence, thus obtaining multiple quantum sequences of dangerous driving changes. Each quantum sequence of dangerous driving changes corresponds to an index, and the value of e ranges from 1 to E. E is used to characterize the total number of quantum sequences of dangerous driving changes constructed from continuous dangerous driving changes. The maximum value of the dangerous driving change in the quantum sequence of dangerous driving changes constructed to characterize continuous dangerous driving changes. The length of the dangerous driving change quantum sequence constructed to characterize the continuous dangerous driving change amount.

[0179] in, The larger the value, the longer the continuous emergency steering and braking occurred. The larger the value, the greater the degree of continuous emergency steering and braking during the period of continuous emergency steering and braking. Therefore, with... As The weight.

[0180] This embodiment enables the dynamic identification of abrupt behavioral characteristics during vehicle operation. By quantitatively analyzing directional changes and speed fluctuations between continuous driving vectors, it accurately distinguishes between normal driving modes and potentially dangerous driving behaviors. This solution can determine driving risk levels based on objective data, avoiding subjective errors from human experience-based judgments, thereby providing accurate risk assessment basis for vehicle dispatching decisions.

[0181] In some of the solutions described above in this invention, a scheduling priority factor for each vehicle is determined based on the passenger's negative experience factor and the driving hazard of each vehicle, and resources are directly scheduled for each vehicle based on the scheduling priority factor. However, this approach does not consider the scheduling resource allocation deviation caused by the inconsistency between the vehicle's driving trajectory and the road direction, resulting in low accuracy of the scheduling priority factor.

[0182] In response, this invention further proposes that, following S103, the vehicle dispatching method of the road passenger transport management system in the transportation hub center may also include:

[0183] Based on the road direction information of the target vehicle in the reference time period, the scheduling priority factor of the target vehicle is corrected to obtain the scheduling resource allocation degree of the target vehicle. The target vehicle is any vehicle, and the reference time period is the preset time period before the current time and closest to the current time.

[0184] S104 may specifically include:

[0185] Based on the resource allocation degree of each vehicle, resource scheduling is performed on each vehicle separately to obtain the vehicle scheduling result.

[0186] In this embodiment, the target vehicle refers to any passenger vehicle to be dispatched and managed in the road passenger transport management system of the transportation hub center. In actual operation, each vehicle entering the management scope is identified and tracked in order to carry out dispatch-related operations for each vehicle individually.

[0187] The reference time period is set to the preset time period closest to the current time. For example, the preset time period can be 15 minutes, 30 minutes, etc., and the specific duration can be adjusted according to actual needs and system performance. This time period is selected to obtain road condition information recently traveled by the vehicle, which can better reflect the impact of the current road environment on driving.

[0188] As an example, one can first use the positioning devices and sensors (such as gyroscopes and accelerometers) installed on the vehicle to collect road direction information. The positioning devices can accurately obtain the vehicle's position coordinates, and by using continuous position coordinate points, the vehicle's driving trajectory can be drawn, thereby determining the curvature of the road, the number of curves, etc.

[0189] Sensors such as gyroscopes and accelerometers can measure a vehicle's attitude and motion, such as steering angle and acceleration changes. This data helps to more accurately analyze a vehicle's driving situation on the road, especially its dynamic information when turning. For example, when a vehicle frequently experiences large changes in steering angle, it may mean that the vehicle is driving on a road with many curves.

[0190] Based on historically collected road alignment information, a model is established to adjust the scheduling priority factor, thereby obtaining the scheduling resource allocation degree based on the target vehicle's road alignment information during the reference time period. This model can consider multiple factors related to road alignment, such as the number of curves, curve curvature, and road gradient.

[0191] This embodiment effectively solves the problem of scheduling resource allocation deviation caused by the inconsistency between vehicle travel trajectories and road directions. By accurately identifying the degree of deviation between the vehicle's travel path and the planned road direction, the scheduling priority factor is corrected in real time. Therefore, vehicles deviating from the planned road direction are prioritized during resource allocation, avoiding waste of scheduling resources due to abnormal vehicle travel and improving the matching accuracy between resource allocation results and the actual road direction.

[0192] In some of the solutions described above in this invention, the scheduling priority factor is corrected based on the road direction information of the target vehicle in the reference time period. However, the degree of deviation between the actual driving trajectory of the vehicle and the center line of the road is not fully considered in the correction process, resulting in insufficient accuracy of the corrected scheduling resource allocation.

[0193] To address this, the present invention further proposes to modify the scheduling priority factor of the target vehicle based on the road direction information of the target vehicle during the reference time period, thereby obtaining the scheduling resource allocation degree of the target vehicle, including:

[0194] Obtain the road centerline of the target vehicle during the reference time period;

[0195] Draw perpendicular lines from the historical positions of the target vehicle at various times during the reference time period to the center line of the road to construct a sequence of intersection points, which includes the intersection points of each perpendicular line with the center line of the road.

[0196] Based on the direction and distance between two adjacent intersection points in the intersection point sequence, a road extension vector sequence is constructed, which includes the road extension vector formed by the direction and distance between two adjacent intersection points.

[0197] Based on the road extension vector sequence and the driving vector sequence of the target vehicle, the scheduling priority factor of the target vehicle is corrected to obtain the scheduling resource allocation degree of the target vehicle.

[0198] In this embodiment, the road centerline is extracted using a geographic information system or high-precision map data, representing the standard geometric centerline of the road. The intersection sequence is generated by projecting the vehicle's historical position perpendicularly to the road centerline; each intersection point corresponds to the projected position of the vehicle at a certain moment within a reference time period. The road extension vector sequence consists of the direction and distance between adjacent intersection points; the direction is calculated using the azimuth angle between the two points, and the distance is calculated using the coordinate difference. The driving vector sequence consists of the direction and distance between the vehicle's historical position and its next position.

[0199] Specifically, within the reference time period, the actual driving trajectory of the target vehicle is represented by a driving vector sequence, while the road orientation is represented by a road extension vector sequence. By comparing the differences between the two vector sequences, the degree of deviation of the vehicle's driving trajectory from the road centerline can be quantified. If the deviation is high, it indicates that the vehicle may frequently change lanes or deviate from the planned route, requiring priority allocation of scheduling resources.

[0200] As an example, the allocation of vehicle scheduling resources can be determined using the following formula 4:

[0201] Formula 4

[0202] In Formula 4, V is used to characterize the degree of vehicle scheduling resource allocation. Y is used to characterize the mean angle between the road extension vector in the road extension vector sequence and the corresponding driving vector in the driving vector sequence, and Y is used to characterize the vehicle scheduling priority factor.

[0203] in, The smaller the value, the more the driving direction conforms to the road's extension direction, thus requiring a reduction in the scheduling priority factor. The adjustment value of the scheduling priority factor for vehicles at the current moment is used to obtain the scheduling resource allocation degree.

[0204] This embodiment effectively solves the problem that traditional scheduling methods do not consider the matching degree between the actual vehicle trajectory and the planned road direction. By quantitatively analyzing the spatial relationship between the vehicle's travel path and the road centerline, abnormal driving behavior that deviates from the predetermined route can be accurately identified. The resulting dynamic correction mechanism optimizes the spatial distribution of station scheduling resources and reduces the misallocation of scheduling resources caused by vehicles deviating from the planned route.

[0205] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0206] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0207] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A vehicle dispatching method for a road passenger transport management system in a transportation hub center, characterized in that, The method includes: Real-time acquisition of operational status information for each vehicle and road traffic information; Based on the operating status information and road traffic information of each vehicle, the passenger adverse experience factor of each vehicle at the current moment is evaluated, and based on the operating status information of each vehicle, the driving hazard of each vehicle at the current moment is evaluated. Based on the passenger negative experience factors and driving hazards of each vehicle, the scheduling priority factors of each vehicle are determined respectively. Based on the scheduling priority factor of each vehicle, resource scheduling is performed on each vehicle to obtain the vehicle scheduling result. The method of evaluating the passenger negative experience factors of each vehicle at the current moment based on the operating status information and road traffic information of each vehicle includes: Based on the operating status information and road traffic information of each vehicle, the passenger anxiety level of each passenger in each vehicle is determined, and based on the operating status information and road traffic information of each vehicle, the future congestion influencing factors of each vehicle are predicted. Based on the passenger anxiety level of each passenger in each vehicle and the travel time of each passenger in each vehicle, the current congestion impact factor of each vehicle is determined, wherein the travel time is used to characterize the time from the passenger's boarding time to the current time. The future congestion impact factor of each vehicle is averaged with the current congestion impact factor to obtain the passenger negative experience factor of each vehicle at the current moment. The operational status information includes the vehicle's historical location; The assessment of the driving hazard of each vehicle at the current moment based on the operating status information of each vehicle includes: Based on the direction and distance between the historical vehicle position of the target vehicle at each moment in the reference time period and the historical vehicle position at the next moment, the driving vector at each moment is determined. The target vehicle is any vehicle, and the reference time period is a preset time period before the current moment and closest to the current moment. Arrange the driving vectors in chronological order to construct a driving vector sequence; Based on the included angle value and the modulus difference value formed between two adjacent driving vectors in the driving vector sequence, the included angle sequence and the modulus difference value sequence are constructed respectively. Based on the included angle sequence and the modulus difference sequence, the driving hazard of the target vehicle at the current moment is determined.

2. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to claim 1, characterized in that, The operational status information includes passenger boarding time, number of passengers, and vehicle speed; the road traffic information includes congestion levels for each route segment. The method of determining the passenger anxiety level of each passenger in each vehicle based on the operating status information and road traffic information of each vehicle includes: The time period from the passenger's boarding time to the current time is determined as the travel time of each passenger in the target vehicle, where the target vehicle is any vehicle. The congestion levels of each passenger on the target vehicle during their travel time are used to construct a congestion level sequence for each passenger in chronological order. The ratio of the number of passengers to the maximum load capacity at each time moment is used to construct a passenger percentage sequence for the target vehicle in chronological order. Using the passenger percentage sequence as the weight sequence, a straight line is fitted to each of the congestion degree sequences to obtain the slope of the fitted straight line corresponding to each passenger. Based on the target congestion mean for each passenger, the slope of the fitted straight line, and the vehicle speed at each time point, the passenger anxiety level for each passenger is determined. The target congestion mean is the mean of each congestion level in the passenger's congestion sequence.

3. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to claim 2, characterized in that, The passenger anxiety level is determined based on the average target congestion level for each passenger, the slope of the fitted straight line, and the vehicle speed at each time point, including: The congestion evaluation value for each passenger is determined by multiplying the mean target congestion level for each passenger by the slope of the fitted straight line. The ratio of the vehicle's speed to the road speed limit at each time point is used to construct a speed percentage sequence of the target vehicle in chronological order. The passenger anxiety level of each passenger is determined by using the distance traveled, the congestion evaluation value, the travel time, and the speed ratio sequence of the target vehicle. The distance traveled is used to characterize the distance the vehicle has traveled from the time the passenger boarded the vehicle to the current time.

4. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to claim 1, characterized in that, The operational status information includes the preset total driving time, the preset driving route, the driving time already traveled, and the vehicle's current location. The road traffic information includes the congestion level of each route segment and the predicted continuing driving time. The prediction of future congestion influencing factors for each vehicle based on its operating status information and road traffic information includes: The trip timeout of the target vehicle is obtained by dividing the predicted continued driving time of the target vehicle by the difference between the preset total driving time and the driving time already traveled. The target vehicle can be any vehicle. Based on the preset driving route of the target vehicle and the current position of the vehicle, determine the subsequent driving path of the target vehicle; By using the travel timeout of the target vehicle, the route length and congestion of each segment in the subsequent travel path, the future congestion impact factor of the target vehicle is determined.

5. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to claim 1, characterized in that, The current congestion influencing factors for each vehicle are determined based on the passenger anxiety level of each passenger in each vehicle and the duration of their journey, including: The total travel time of each passenger in the target vehicle is summed to obtain the total travel time of the target vehicle, where the target vehicle is any vehicle. Divide the travel time of each passenger by the cumulative travel time to obtain the travel time percentage of each passenger. The current congestion impact factor of the target vehicle is obtained by summing the product of the percentage of travel time of each passenger and the passenger's anxiety level.

6. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to claim 1, characterized in that, The step of determining the driving hazard of the target vehicle at the current moment based on the included angle sequence and the modulus difference sequence includes: The mean value of each included angle value in the included angle sequence is averaged with the corresponding modulus difference value in the modulus difference sequence to obtain multiple driving change values; Arrange the various driving changes in chronological order to construct a driving change sequence; The mean value of each driving change in the driving change sequence is obtained by averaging the driving change amounts. The driving change amount in the driving change sequence that is greater than a preset change threshold is marked as a dangerous driving change amount; A dangerous driving change quantum sequence is constructed by continuously analyzing the dangerous driving changes in the driving change sequence. The driving hazard of the target vehicle at the current moment is determined by using the mean value of driving changes and the quantum sequences of each dangerous driving change.

7. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to any one of claims 1-5, characterized in that, After determining the dispatch priority factor for each vehicle based on the passenger negative experience factor and the driving hazard of each vehicle, the method further includes: Based on the road direction information of the target vehicle in the reference time period, the scheduling priority factor of the target vehicle is corrected to obtain the scheduling resource allocation degree of the target vehicle. The target vehicle is any vehicle, and the reference time period is a preset time period before the current time and closest to the current time. The process of scheduling resources for each vehicle based on its scheduling priority factor to obtain vehicle scheduling results includes: Based on the scheduling resource allocation degree of each vehicle, resource scheduling is performed on each vehicle to obtain the vehicle scheduling result.

8. The vehicle dispatching method of the road passenger transport management system for transportation hub centers according to claim 7, characterized in that, The step of adjusting the scheduling priority factor of the target vehicle based on its road travel information during the reference time period to obtain the scheduling resource allocation degree of the target vehicle includes: Obtain the road centerline of the target vehicle during the reference time period; Draw perpendicular lines from the historical positions of the target vehicle at various times during the reference time period to the center line of the road to construct an intersection sequence, which includes the intersection points of each perpendicular line with the center line of the road. Based on the direction and distance between two adjacent intersection points in the intersection point sequence, a road extension vector sequence is constructed, which includes a road extension vector formed by the direction and distance between two adjacent intersection points. Based on the road extension vector sequence and the driving vector sequence of the target vehicle, the scheduling priority factor of the target vehicle is corrected to obtain the scheduling resource allocation degree of the target vehicle.

Images