A vehicle dispatching method based on big data

Abstract

The present application relates to the technical field of intelligent transportation, and provides a vehicle scheduling method based on big data, which comprises establishing a vehicle scheduling system model and obtaining a performance function thereof; deducing a system performance parameter expression, a first theoretical threshold expression of load balancing and a relationship between an idle rate and a load rate based on the performance function; obtaining a second theoretical threshold expression of load balancing by combining vehicle maximum load capacity and response time design parameters; calculating a divergence threshold under load balancing output according to vehicle design parameters and the two load balancing threshold expressions; and simulating a load response curve within the threshold and corresponding performance parameter values through a simulation system. The system model comprises a demand input feedback module including demand processing, task allocation, coordinate conversion and position feedback submodules, and vehicle scheduling adjustment is realized through a multi-stage feedback mechanism. The present application can improve system response efficiency and resource utilization.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and more specifically, to a vehicle dispatching method based on big data. Background Technology

[0002] In today's society, with the rapid development of the transportation industry, vehicle demand is becoming increasingly diversified and complex. Traditional vehicle dispatching methods mainly rely on human experience or simple algorithms. These methods often have many shortcomings when facing large-scale, dynamically changing vehicle demand. For example, manual dispatching is easily affected by subjective factors, leading to low dispatching efficiency, long response times, and difficulty in achieving optimal resource allocation. While some simple algorithms can improve dispatching efficiency to a certain extent, they often fail to fully consider factors such as the actual load capacity of vehicles, response time, and dynamic changes during task execution, resulting in inaccurate dispatching results, low resource utilization, and even the possibility of vehicle overloading or idleness.

[0003] Most existing vehicle dispatching systems are based on fixed rules or simple mathematical models for task allocation and vehicle scheduling. These systems typically assume that vehicle performance and task requirements are constant, neglecting the variations in vehicle load capacity, the uncertainty of task execution time, and the impact of external interference factors in real-world scenarios. Therefore, when faced with complex real-world vehicle usage environments, these systems often fail to meet users' needs for efficient and accurate dispatching.

[0004] In implementing the embodiments of the present invention, the inventors discovered at least the following problems or defects in the prior art: First, traditional scheduling methods cannot effectively handle dynamically changing vehicle demand, resulting in delayed scheduling results and an inability to respond promptly to users' real-time needs; second, existing scheduling systems fail to fully consider the actual load capacity and task execution efficiency of vehicles when allocating resources, easily leading to resource waste or vehicle overload; finally, the prior art lacks an effective mechanism for handling external interference factors during vehicle scheduling, significantly affecting the accuracy and stability of scheduling results. These problems seriously affect the performance and user experience of the vehicle scheduling system and urgently need to be solved through technological innovation. Summary of the Invention

[0005] This invention provides a vehicle dispatching method based on big data, comprising:

[0006] Establish a vehicle dispatch system model based on the mechanism of the vehicle dispatch system;

[0007] Based on the vehicle dispatching system model, the performance function of the vehicle dispatching system is obtained;

[0008] Based on the performance function of the vehicle dispatching system, we obtain the performance parameter expression of the vehicle dispatching system, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the relationship between the idle rate and the load rate of the vehicle dispatching system.

[0009] Based on the performance function of the vehicle dispatching system, and combined with the maximum load capacity and maximum response time of the vehicle design, the second theoretical threshold expression for load balancing of the vehicle dispatching system is obtained.

[0010] Based on the design parameter values ​​of the vehicles to be dispatched, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the second theoretical threshold expression for load balancing of the vehicle dispatching system, the divergence threshold under load balancing of the vehicles to be dispatched is calculated and output.

[0011] A simulation system with a vehicle dispatching system model is used to simulate and output the load response curves of the vehicles to be dispatched within the divergence threshold, and output the corresponding performance parameter values ​​of the vehicles to be dispatched under load balancing.

[0012] Furthermore, the vehicle dispatching system model specifically includes,

[0013] The vehicle usage demand input feedback module processes the input demand to obtain vehicle dispatch adjustment parameters. The vehicle usage demand input feedback loop includes a demand processing module, an inner-loop task allocation feedback module, a location feedback module, and a coordinate transformation module.

[0014] The requirement processing module is used to sort the inputs by priority and output the processed requirements, and then input the processed requirements into the inner loop task allocation feedback module.

[0015] The inner ring task allocation feedback module outputs vehicle scheduling adjustment tasks based on the processed requirements.

[0016] The coordinate transformation module is used to convert vehicle dispatch adjustment tasks into vehicle dispatch adjustment locations, and then input the vehicle dispatch adjustment locations into the location feedback module.

[0017] The location feedback module is used to multiply the vehicle dispatch adjustment position by the feedback output sensor proportional coefficient and output the location feedback. The difference between the location feedback and the input vehicle usage command is then used as the input to the demand processing module.

[0018] Furthermore, the inner-loop task allocation feedback module includes a vehicle load calculation module, a task execution time calculation module, an inner-loop resource allocation feedback module, and a real-time data feedback module, among which...

[0019] The vehicle load calculation module is used to calculate and obtain the current load of the vehicle, and then output the vehicle load to the task execution time calculation module;

[0020] The task execution time calculation module is used to calculate and obtain the task execution time based on the vehicle load, and then output the task execution time to the inner ring resource allocation feedback module.

[0021] The inner ring resource allocation feedback module outputs vehicle scheduling adjustment tasks based on task execution time;

[0022] The real-time data feedback module calculates real-time vehicle data feedback based on the vehicle scheduling adjustment task, and uses the difference between the real-time data feedback and the processed demand as the input to the vehicle load calculation module.

[0023] Furthermore, the inner-ring resource allocation feedback module includes a task allocation priority calculation module, a vehicle scheduling calculation module, and an external interference feedback module, among which...

[0024] The task allocation priority calculation module is used to calculate the task allocation priority and output it to the vehicle scheduling calculation module;

[0025] The vehicle scheduling calculation module calculates and obtains the vehicle scheduling location based on the task allocation priority, and outputs the vehicle scheduling location to the coordinate transformation module and the external interference feedback module.

[0026] The external interference feedback module calculates the external interference feedback based on the vehicle scheduling location, and uses the difference between the external interference feedback and the task execution time as the input to the task allocation priority calculation module.

[0027] Furthermore, the performance function of the vehicle dispatching system is specifically expressed as follows:

[0028]

[0029] In the formula, s is the transfer function operator of the vehicle dispatching system, and K p It is the proportional gain of vehicle dispatch instructions, K t η is the vehicle task execution coefficient, J is the vehicle resource allocation efficiency, D is the vehicle task execution inertia, and D is the vehicle scheduling damping coefficient.

[0030] Furthermore, considering that the vehicle task execution inertia is much smaller than the vehicle dispatching damping coefficient, the vehicle task execution inertia is simplified to 0, and the performance function expression of the vehicle dispatching system is simplified to the following expression:

[0031]

[0032] In the formula, G(s) is the gain of the vehicle dispatching system, expressed as:

[0033]

[0034] S is the inherent frequency of the vehicle dispatching system, expressed as a formula:

[0035]

[0036] D is the inherent damping coefficient of the vehicle dispatching system, expressed as a formula:

[0037]

[0038] Among them, the vehicle dispatching system gain, the vehicle dispatching system inherent frequency, and the vehicle dispatching system inherent damping coefficient are the performance parameters of the vehicle dispatching system.

[0039] Furthermore, the expression for the first theoretical threshold for load balancing in the vehicle dispatching system is obtained based on the Routh criterion and the performance function of the vehicle dispatching system, and is specifically expressed as follows:

[0040]

[0041] Furthermore, the relationship between the idle rate and load rate of the vehicle dispatch system specifically includes:

[0042] The load rate of the vehicle dispatching system increases to times the idle rate of the vehicle dispatching system;

[0043] The response time of the vehicle dispatching system is reduced to the idle rate of the vehicle dispatching system.

[0044] The resource utilization rate of the vehicle dispatching system increases to the idle rate of the vehicle dispatching system.

[0045] The increase in task latency difference in the vehicle dispatching system can be expressed as a formula:

[0046]

[0047] In the formula, ω0 is the inherent frequency corresponding to the idle rate of the vehicle dispatching system, ω is the inherent frequency corresponding to the load rate of the vehicle dispatching system, and ξ0 is the inherent damping coefficient corresponding to the idle rate of the vehicle dispatching system.

[0048] Furthermore, the expression for the second theoretical threshold for load balancing in the vehicle dispatching system specifically includes:

[0049]

[0050] In the formula, I max It is the maximum load capacity designed for the vehicle, T max It is the maximum response time designed for the vehicle, P req θ is the input vehicle usage request power, and θ is the load balancing coefficient of the vehicle usage dispatching system.

[0051] Furthermore, based on the design parameter values ​​of the vehicles to be dispatched, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the second theoretical threshold expression for load balancing of the vehicle dispatching system, the divergence threshold under load balancing of the vehicles to be dispatched is calculated and output, specifically including:

[0052] Substitute the design parameter values ​​of the vehicles to be dispatched into the expression for the first theoretical threshold of load balancing in the vehicle dispatching system to calculate the first theoretical threshold of the load rate of the vehicle dispatching system.

[0053] Substitute the design parameter values ​​of the vehicles to be dispatched, the maximum design load capacity of the vehicles, and the maximum design response time of the vehicles into the expression for the second theoretical threshold of load balancing of the vehicle dispatching system to calculate the second theoretical threshold of load rate of the vehicle dispatching system.

[0054] The larger of the first theoretical threshold and the second theoretical threshold of the load rate of the vehicle dispatching system is taken as the divergence threshold of the load rate of the vehicle dispatching system.

[0055] The above embodiments of the present invention have at least the following beneficial effects: The vehicle dispatching method of the present invention can improve the efficiency and accuracy of the vehicle dispatching system. By establishing a vehicle dispatching system model based on big data, combined with vehicle design parameters and system performance functions, the divergence threshold under load balancing can be accurately calculated, thereby providing a scientific basis for vehicle dispatching. This method can effectively avoid vehicle overload or idleness, optimize resource utilization, and ensure that vehicles operate efficiently within a reasonable load range. Simultaneously, by simulating the load response curve of vehicles within the divergence threshold using a simulation system, this method can predict vehicle performance in advance, providing strong support for dispatching decisions and further improving the reliability and stability of the dispatching system.

[0056] Furthermore, this invention can dynamically adapt to complex vehicle usage environments and changing demands. Its vehicle usage demand input feedback module and inner-loop task allocation feedback module can process user needs in real time and flexibly adjust scheduling tasks based on task priority and vehicle load, ensuring the timeliness and accuracy of scheduling results. By simplifying the system performance function and introducing load balancing theoretical thresholds, this invention can allocate resources and schedule tasks more efficiently, reduce system response time, and improve overall system performance. These improvements enable this invention to better meet users' real-time needs and enhance user experience when facing large-scale, dynamically changing vehicle usage demands. Attached Figure Description

[0057] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated in the drawings by way of example, not limitation, in which:

[0058] Figure 1 This is a flowchart illustrating a vehicle dispatching method based on big data, provided in an embodiment of the present invention. Detailed Implementation

[0059] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided to make the invention more thorough and complete, and to fully convey the scope of the invention to those skilled in the art.

[0060] Those skilled in the art will understand that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0061] It should be noted that the number of any elements in the accompanying drawings is for illustrative purposes only and not as a limitation, and any naming is for distinction only and has no limiting meaning.

[0062] The following is for reference. Figure 1 , Figure 1 This is a flowchart illustrating a big data-based vehicle dispatching method according to an embodiment of the present invention. Figure 1 As shown, a big data-based vehicle dispatching method includes:

[0063] S1. Establish a vehicle dispatching system model based on the mechanism of the vehicle dispatching system;

[0064] S2. Based on the vehicle dispatching system model, obtain the vehicle dispatching system performance function;

[0065] S3. Based on the performance function of the vehicle dispatching system, obtain the performance parameter expression of the vehicle dispatching system, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the relationship between the idle rate and the load rate of the vehicle dispatching system.

[0066] S4. Based on the performance function of the vehicle dispatching system, combined with the maximum load capacity and maximum response time of the vehicle design, the second theoretical threshold expression for load balancing of the vehicle dispatching system is obtained.

[0067] S5. Based on the design parameter values ​​of the vehicles to be dispatched, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the second theoretical threshold expression for load balancing of the vehicle dispatching system, calculate and output the divergence threshold under load balancing of the vehicles to be dispatched.

[0068] S6. Use a simulation system with a vehicle dispatching system model to simulate and output the load response curve of the vehicle to be dispatched within the divergence threshold, and output the corresponding performance parameter values ​​of the vehicle to be dispatched under load balancing.

[0069] It should be noted that this invention proposes a big data-based vehicle dispatching method, the core of which lies in optimizing the vehicle dispatching process by establishing a vehicle dispatching system model. The vehicle dispatching system model refers to a mathematical model that reflects the system's operational characteristics by analyzing and modeling the mechanism of the vehicle dispatching system. The purpose of this model is to better understand and predict the system's performance, thereby providing a scientific basis for dispatching decisions. The performance function is a function derived from this model, used to quantify system performance indicators, such as response time and load balancing. The performance parameter expressions are further derived from the performance function, used to specifically describe the parameter formulas of the system performance. The first and second theoretical threshold expressions for load balancing are derived through theoretical analysis and are used to determine whether the system load is balanced. The divergence threshold refers to the maximum load value that the system can withstand under load balancing conditions. By calculating the divergence threshold, system overload can be avoided, ensuring stable system operation. The simulation system is used to simulate the response of vehicles under different load conditions. Through simulation, the effectiveness of the dispatching strategy can be verified in advance, and performance parameters can be optimized.

[0070] Specifically, the vehicle dispatching system model comprises multiple modules, with the vehicle demand input feedback module being one of the core components. This module receives user vehicle demands, prioritizes them through the demand processing module, and then passes the prioritized results to the inner-loop task allocation feedback module. The inner-loop task allocation feedback module further generates vehicle dispatch adjustment tasks based on the prioritized demands, combined with vehicle load capacity and task execution time. The vehicle load calculation module calculates the current vehicle load in real time, while the task execution time calculation module estimates the task execution time based on the vehicle load. The inner-loop resource allocation feedback module allocates vehicle resources based on the task execution time and converts the task into a specific vehicle dispatch location through the coordinate transformation module. The location feedback module compares the dispatch location with the actual demand, forming a feedback loop to optimize the dispatching results. The performance function is derived through the interaction and data flow of these modules, reflecting the system's performance under different parameter settings. For example, performance parameters such as system gain, natural frequency, and damping coefficient are calculated using the performance function, and these parameters directly affect the system's response speed and stability.

[0071] Preferably, the construction of a vehicle dispatching system model can be achieved through the following steps: First, collect a large amount of vehicle dispatching data, including information such as vehicle load capacity, response time, and task execution time. Then, analyze and process this data to extract key features, such as the average load rate of vehicles and the distribution of task response times. Next, establish a mathematical model based on these features. The model's input parameters include the maximum designed load capacity and maximum response time of the vehicles, while the outputs are the system's performance parameters and load balancing thresholds. During data processing, data mining techniques, such as cluster analysis, can be used to classify vehicles according to their load capacity for more accurate dispatching. For simplifying the performance function, when the vehicle task execution inertia is much smaller than the dispatching damping coefficient, the influence of inertia can be ignored, thereby simplifying the calculation process and improving the model's efficiency. Through these refined operational steps, a vehicle dispatching system model can be constructed more effectively, and the vehicle dispatching process can be optimized.

[0072] In some embodiments, the vehicle dispatching system model specifically includes:

[0073] The vehicle usage demand input feedback module processes the input demand to obtain vehicle dispatch adjustment parameters. The vehicle usage demand input feedback loop includes a demand processing module, an inner-loop task allocation feedback module, a location feedback module, and a coordinate transformation module.

[0074] The requirement processing module is used to sort the inputs by priority and output the processed requirements, and then input the processed requirements into the inner loop task allocation feedback module.

[0075] The inner ring task allocation feedback module outputs vehicle scheduling adjustment tasks based on the processed requirements.

[0076] The coordinate transformation module is used to convert vehicle dispatch adjustment tasks into vehicle dispatch adjustment locations, and then input the vehicle dispatch adjustment locations into the location feedback module.

[0077] The location feedback module is used to multiply the vehicle dispatch adjustment position by the feedback output sensor proportional coefficient and output the location feedback. The difference between the location feedback and the input vehicle usage command is then used as the input to the demand processing module.

[0078] It should be noted that the vehicle demand input feedback module in the vehicle dispatching system model mentioned in this invention is the core part of the entire dispatching system. It is responsible for receiving and processing users' vehicle demands and transforming them into vehicle dispatching adjustment parameters. This module achieves efficient processing and response to vehicle demands through the collaborative work of multiple sub-modules. Specifically, the demand processing module prioritizes the input vehicle demands according to certain rules to ensure that high-priority demands are processed first. The inner-loop task allocation feedback module generates specific vehicle dispatching tasks based on the prioritized vehicle demands. The location feedback module and coordinate transformation module work together to convert vehicle dispatching tasks into specific vehicle dispatching locations and continuously optimize the dispatching results through a feedback mechanism. This modular structure enables the system to flexibly respond to complex vehicle demands and improve the accuracy and efficiency of dispatching.

[0079] Specifically, the demand processing module within the vehicle demand input feedback module receives user requests and prioritizes them based on urgency, user level, or other preset criteria. For example, emergency rescue tasks might be assigned the highest priority, while regular commuting needs might be assigned a lower priority. The inner-loop task allocation feedback module, upon receiving the prioritized demands, generates vehicle dispatch adjustment tasks based on the vehicle's current status and task execution capabilities. The coordinate transformation module converts these tasks into specific vehicle dispatch location information, such as determining the vehicle's driving path and target location using a geographic coordinate system. The location feedback module then compares the vehicle's actual dispatch location with the target location and feeds back the deviation information to the demand processing module for adjustments to subsequent dispatch tasks. This closed-loop feedback mechanism ensures the accuracy and timeliness of dispatch tasks while effectively responding to dynamically changing vehicle demands.

[0080] Preferably, the construction of the vehicle usage demand input feedback module can be further refined. For example, in the demand processing module, a multi-dimensional priority ranking algorithm can be used to comprehensively consider factors such as task urgency, user reputation, and task distance to more accurately determine task priorities. The inner-loop task allocation feedback module can dynamically adjust the task allocation strategy based on real-time vehicle data (such as current load and remaining battery power). The coordinate transformation module can combine high-precision map data to optimize vehicle driving path planning and reduce unnecessary detours. The location feedback module can utilize advanced sensor technology to acquire precise vehicle location information in real time and improve the accuracy of feedback data through data fusion technology. Through these refined steps and optimization measures, the vehicle usage demand input feedback module can handle complex vehicle usage demands more efficiently, improving the performance and user experience of the entire vehicle dispatching system.

[0081] In some embodiments, the inner-loop task allocation feedback module includes a vehicle load calculation module, a task execution time calculation module, an inner-loop resource allocation feedback module, and a real-time data feedback module, wherein...

[0082] The vehicle load calculation module is used to calculate and obtain the current load of the vehicle, and then output the vehicle load to the task execution time calculation module;

[0083] The task execution time calculation module is used to calculate and obtain the task execution time based on the vehicle load, and then output the task execution time to the inner ring resource allocation feedback module.

[0084] The inner ring resource allocation feedback module outputs vehicle scheduling adjustment tasks based on task execution time;

[0085] The real-time data feedback module calculates real-time vehicle data feedback based on the vehicle scheduling adjustment task, and uses the difference between the real-time data feedback and the processed demand as the input to the vehicle load calculation module.

[0086] It should be noted that the inner-loop task allocation feedback module mentioned in this invention is a key component of the vehicle dispatching system model. Its main function is to further refine and optimize vehicle dispatching tasks based on the processed vehicle demand. This module achieves accurate allocation and dynamic adjustment of vehicle dispatching tasks through the collaborative work of the vehicle load calculation module, task execution time calculation module, inner-loop resource allocation feedback module, and real-time data feedback module. The vehicle load calculation module monitors the current load of vehicles in real time, the task execution time calculation module estimates the task execution time based on the vehicle load, the inner-loop resource allocation feedback module allocates vehicle resources based on the task execution time, and the real-time data feedback module compares the actual operating data of vehicles with the dispatching demand to form a feedback loop to optimize the dispatching results. This modular structure enables the system to flexibly respond to complex vehicle demand while ensuring the rational allocation and efficient utilization of vehicle resources.

[0087] Specifically, the vehicle load calculation module within the inner-loop task allocation feedback module is responsible for real-time monitoring of the vehicle's current load status, including information such as passenger numbers and cargo weight. The task execution time calculation module estimates the time required to complete the task based on the vehicle's current load status and performance parameters (such as maximum load capacity and speed). The inner-loop resource allocation feedback module rationally allocates vehicle resources based on the task execution time, such as selecting suitable vehicles for the task and determining their dispatch locations. The real-time data feedback module compares the vehicle's actual operating data (such as location, speed, and remaining battery power) with the dispatch requirements, generating feedback information for dynamic adjustments to the dispatch tasks. For example, if the vehicle's actual load is close to its maximum capacity, or the task execution time exceeds expectations, the system can reassign tasks or adjust the vehicle dispatch plan based on the feedback information. This dynamic feedback mechanism effectively improves the system's flexibility and adaptability, ensuring that vehicles operate efficiently within a reasonable load range.

[0088] Preferably, the construction of the inner-loop task allocation feedback module can be further refined. For example, the vehicle load calculation module can collect vehicle load data in real time through sensors installed on the vehicle and send the data to the dispatch center through the data transmission module. The task execution time calculation module can combine historical data and real-time traffic information, and use machine learning algorithms to make more accurate predictions of task execution time. The inner-loop resource allocation feedback module can dynamically adjust vehicle dispatch tasks according to the real-time status of the vehicle (such as location, remaining battery power, current task completion status, etc.), for example, prioritizing the allocation of tasks to vehicles that are closer and have lighter loads. The real-time data feedback module can utilize advanced sensor technology and data processing algorithms to monitor the vehicle's operating status in real time and adjust the dispatch strategy in a timely manner through the feedback mechanism. Through these refined steps and optimization measures, the inner-loop task allocation feedback module can handle complex vehicle usage needs more efficiently, improving the performance and user experience of the entire vehicle dispatch system.

[0089] In some embodiments, the inner-loop resource allocation feedback module includes a task allocation priority calculation module, a vehicle scheduling calculation module, and an external interference feedback module, wherein...

[0090] The task allocation priority calculation module is used to calculate the task allocation priority and output it to the vehicle scheduling calculation module;

[0091] The vehicle scheduling calculation module calculates and obtains the vehicle scheduling location based on the task allocation priority, and outputs the vehicle scheduling location to the coordinate transformation module and the external interference feedback module.

[0092] The external interference feedback module calculates the external interference feedback based on the vehicle scheduling location, and uses the difference between the external interference feedback and the task execution time as the input to the task allocation priority calculation module.

[0093] It should be noted that the inner-loop resource allocation feedback module mentioned in this invention is a key component of the vehicle dispatching system used to optimize vehicle resource allocation and task scheduling. This module, through the collaborative work of the task allocation priority calculation module, the vehicle dispatching calculation module, and the external interference feedback module, achieves priority ranking of vehicle dispatching tasks, calculation of dispatching positions, and dynamic compensation for external interference. The task allocation priority calculation module calculates task priorities based on factors such as task urgency and vehicle status; the vehicle dispatching calculation module generates vehicle dispatching positions based on priorities; and the external interference feedback module handles the impact of external environmental changes on dispatching tasks. Through this modular design, the system can more flexibly respond to complex and ever-changing vehicle usage scenarios, ensuring the efficiency and stability of vehicle dispatching.

[0094] Specifically, the task allocation priority calculation module in the inner-loop resource allocation feedback module comprehensively considers factors such as task urgency, vehicle current load, and user specific needs to calculate the priority of each task. The vehicle scheduling calculation module calculates the optimal vehicle scheduling location based on task priorities and the real-time location and status of vehicles. The external disturbance feedback module monitors changes in the external environment, such as traffic congestion and weather conditions, and dynamically adjusts vehicle scheduling locations. For example, if traffic congestion occurs in a certain area, the external disturbance feedback module will feed this information back to the task allocation priority calculation module, recalculate task priorities, and adjust vehicle scheduling paths and locations through the vehicle scheduling calculation module. This dynamic feedback mechanism effectively improves the system's adaptability and stability, ensuring efficient vehicle operation in complex environments.

[0095] Preferably, the construction of the inner-loop resource allocation feedback module can be further refined. The task allocation priority calculation module can quantify different factors by setting weights. For example, the weight of emergency tasks can be set to the highest, while the weight of vehicle load is adjusted according to the maximum design load capacity of the vehicle. The vehicle scheduling calculation module can combine Geographic Information System (GIS) data to calculate the optimal driving route for vehicles in real time. The external interference feedback module can obtain real-time traffic information through sensors installed on vehicles and traffic monitoring systems, and analyze and process this information through data processing algorithms. For example, when a sudden increase in traffic flow in a certain area is detected, the system can adjust the vehicle scheduling route to avoid congested areas, thereby improving scheduling efficiency. Through these refined steps and optimization measures, the inner-loop resource allocation feedback module can handle complex vehicle usage demands more efficiently, improving the performance and user experience of the entire vehicle scheduling system.

[0096] In some embodiments, the performance function of the vehicle dispatching system is specifically represented by the following expression:

[0097]

[0098] In the formula, S is the transfer function operator of the vehicle dispatching system, and K... p It is the proportional gain of vehicle dispatch instructions, K t η is the vehicle task execution coefficient, J is the vehicle resource allocation efficiency, D is the vehicle task execution inertia, and D is the vehicle scheduling damping coefficient.

[0099] It should be noted that the vehicle dispatching system performance function mentioned in this invention is a mathematical expression established through in-depth analysis of the vehicle dispatching system model, used to describe the dynamic performance characteristics of the system. This performance function is based on key system parameters, such as the proportional gain K of the vehicle dispatching instructions. p Vehicle task execution coefficient K t The performance function is constructed using parameters such as vehicle resource allocation efficiency η, vehicle task execution inertia J, and vehicle scheduling damping coefficient D. This performance function allows for quantitative analysis of key performance indicators such as system response speed, stability, and load balancing capability, thus providing a theoretical basis for optimizing scheduling strategies. Establishing this performance function is a crucial step in achieving precise scheduling and optimized resource allocation, helping the scheduling system better adapt to dynamically changing vehicle demand.

[0100] Specifically, each parameter in the performance function of the vehicle dispatching system has a clear physical meaning and function. The proportional gain K of the vehicle dispatching command... p This reflects the system's responsiveness to scheduling commands. A higher gain value means the system responds more quickly to commands, but it may also lead to decreased system stability. Vehicle task execution coefficient K t The vehicle's ability to complete a task is represented by its performance and load capacity. Vehicle resource allocation efficiency (η) measures the system's efficiency in allocating resources; efficient resource allocation improves overall system performance. Vehicle task execution inertia (J) reflects the vehicle's inertial characteristics during task execution; a larger inertia means the vehicle needs more time to adjust. The vehicle scheduling damping coefficient (D) describes the system's damping characteristics during scheduling; a higher damping coefficient helps improve system stability but may reduce response speed. By appropriately setting these parameters, the system's performance function can be optimized to achieve optimal performance in different application scenarios.

[0101] Preferably, the performance function of the vehicle dispatching system can be constructed through the following steps. First, collect a large amount of actual operating data, including vehicle load, task execution time, and dispatch instruction response time, to determine the reasonable range of values ​​for each parameter. Then, through data analysis and modeling techniques, such as regression analysis or machine learning algorithms, establish a relationship model between the performance function and system performance indicators. For example, the relationship between parameters such as system gain, natural frequency, and damping coefficient and vehicle load and task execution time can be fitted using historical data. In practical applications, the values ​​of these parameters can be dynamically adjusted according to the real-time status of the vehicles and task requirements to optimize system performance. For example, when the vehicle load is heavy, the task execution coefficient K can be appropriately reduced. t To avoid vehicle overload; when the system requires a rapid response, the proportional gain K of the dispatch command can be appropriately increased. p However, it is also necessary to pay attention to the stability of the system. Through these detailed steps and optimization measures, the performance function of the vehicle dispatching system can be constructed more effectively, thereby improving the system's dispatching efficiency and resource utilization.

[0102] In some embodiments, considering that the vehicle task execution inertia is much smaller than the vehicle dispatching damping coefficient, the vehicle task execution inertia is simplified to 0, and the performance function expression of the vehicle dispatching system is simplified to the following expression:

[0103]

[0104] In the formula, G(s) is the gain of the vehicle dispatching system, expressed as:

[0105]

[0106] S is the inherent frequency of the vehicle dispatching system, expressed as a formula:

[0107]

[0108] D is the inherent damping coefficient of the vehicle dispatching system, expressed as a formula:

[0109]

[0110] Among them, the vehicle dispatching system gain, the vehicle dispatching system inherent frequency, and the vehicle dispatching system inherent damping coefficient are the performance parameters of the vehicle dispatching system.

[0111] It should be noted that in this invention, the vehicle dispatching system performance function has been simplified to more efficiently describe the system's dynamic characteristics. This simplification is based on the assumption that the vehicle task execution inertia is much smaller than the vehicle dispatching damping coefficient. Under this condition, the system performance function can be simplified to a form that is easier to calculate and analyze. The simplified performance function not only retains the main dynamic characteristics of the system but also more intuitively reflects the relationship between key performance parameters such as system gain, natural frequency, and natural damping coefficient. This simplification enables faster evaluation and optimization of system performance in practical applications, while reducing computational complexity and improving the system's real-time performance and adaptability.

[0112] Specifically, the vehicle task execution inertia J refers to the inertial characteristics exhibited by the vehicle during task execution, reflecting the ease with which the vehicle's state changes. When the vehicle task execution inertia is much smaller than the vehicle dispatch damping coefficient D, it means that the vehicle's state changes relatively easily, and the system responds more quickly to dispatch instructions. In this case, the vehicle task execution inertia can be simplified to zero, thus simplifying the performance function. In the simplified performance function, the system gain G(s) represents the amplification factor of the system to the input signal, which is determined by the proportional gain K of the vehicle dispatch instruction. p Vehicle task execution coefficient K t The system performance function is obtained by multiplying the vehicle resource allocation efficiency η by the vehicle scheduling damping coefficient D. The natural frequency S and the natural damping coefficient D are key parameters describing the system's stability and response speed. Through this simplification, the system performance function can more intuitively reflect the system's main dynamic characteristics, facilitating rapid evaluation and optimization in practical applications.

[0113] Preferably, the simplified vehicle dispatching system performance function can be constructed using the following steps: First, determine through experiments or data analysis whether the condition that the vehicle task execution inertia is much smaller than the vehicle dispatching damping coefficient holds true. If the condition holds true, the vehicle task execution inertia can be simplified to zero. Next, based on the actual operating data of the system, determine the proportional gain K of the vehicle dispatching instructions. p Vehicle task execution coefficient K t The specific values ​​of parameters such as vehicle resource allocation efficiency η are determined through analysis of historical scheduling data, vehicle performance testing, and evaluation of the actual operating environment. For example, the proportional gain K of vehicle dispatch instructions... p The vehicle task execution coefficient K can be determined by analyzing the relationship between dispatch instructions and vehicle responses. tThe parameters can be set based on the actual performance and load capacity of the vehicles; the vehicle resource allocation efficiency η can be determined by evaluating the efficiency loss during the resource allocation process. Finally, these parameters are substituted into the simplified performance function to calculate key performance parameters such as system gain, natural frequency, and natural damping coefficient. Through these refined steps, the simplified vehicle dispatching system performance function can be constructed more accurately, thus providing strong support for system optimization and dispatching.

[0114] In some embodiments, the first theoretical threshold expression for load balancing in the vehicle dispatching system is obtained based on the Routh criterion and the performance function of the vehicle dispatching system, and is specifically expressed as the following expression:

[0115]

[0116] It should be noted that the first theoretical threshold expression for load balancing in the vehicle dispatching system mentioned in this invention is derived based on system performance functions and stability theory. This threshold expression is used to determine under what conditions the system can maintain stable operation, avoiding system instability or performance degradation due to excessive load. This threshold provides theoretical guidance for vehicle dispatching, ensuring efficient system operation within a reasonable load range. System gain is an important parameter in the performance function, reflecting the system's response strength to dispatching commands, while the damping coefficient is closely related to system stability. By setting these parameters appropriately, stable system operation under load balancing can be ensured.

[0117] Specifically, the system gain is determined by multiple parameters, including the proportional gain of vehicle dispatch instructions, the vehicle task execution coefficient, and the vehicle resource allocation efficiency. The proportional gain of vehicle dispatch instructions reflects the system's response speed and intensity to dispatch instructions; the vehicle task execution coefficient is related to the actual performance and load capacity of the vehicles, reflecting their ability to complete tasks; and the vehicle resource allocation efficiency measures the system's efficiency in allocating resources. The damping coefficient is related to the system's stability; a higher damping coefficient helps improve system stability but may reduce response speed. The Routh criterion can be used to analyze the relationships between these parameters, thereby deriving the conditions for system stability. In this invention, the condition for system stability is that the ratio of system gain to damping coefficient is greater than 1. This means that when the ratio of system gain to damping coefficient is greater than 1, the system can maintain stable operation and load balancing.

[0118] Preferably, in practical applications, the first theoretical threshold for load balancing of the vehicle dispatching system can be determined through the following steps. First, collect actual system operating data, including vehicle load, task execution time, and dispatch command response time, to determine the specific values ​​of parameters such as the proportional gain of vehicle dispatch commands, the vehicle task execution coefficient, and the vehicle resource allocation efficiency. These parameters can be determined through analysis of historical dispatch data, vehicle performance testing, and evaluation of the actual operating environment. For example, the proportional gain of vehicle dispatch commands can be determined by analyzing the relationship between dispatch commands and vehicle responses; the vehicle task execution coefficient can be set based on the actual performance and load capacity of the vehicles; and the vehicle resource allocation efficiency can be determined by evaluating the efficiency loss during resource allocation. Next, determine the value of the vehicle dispatching damping coefficient based on the system's design parameters. Finally, substitute these parameters into the threshold expression to calculate the first theoretical threshold for system load balancing. This threshold allows for determination of whether the system is in a stable operating state, and accordingly, adjustments to the vehicle dispatching strategy can be made to ensure efficient system operation within a reasonable load range.

[0119] In some embodiments, the relationship between the idle rate and load rate of the vehicle dispatching system specifically includes:

[0120] The load rate of the vehicle dispatching system increases to times the idle rate of the vehicle dispatching system;

[0121] The response time of the vehicle dispatching system is reduced to the idle rate of the vehicle dispatching system.

[0122] The resource utilization rate of the vehicle dispatching system increases to the idle rate of the vehicle dispatching system.

[0123] The increase in task latency difference in the vehicle dispatching system can be expressed as a formula:

[0124]

[0125] In the formula, ω0 is the inherent frequency corresponding to the idle rate of the vehicle dispatching system, ω is the inherent frequency corresponding to the load rate of the vehicle dispatching system, and ξ0 is the inherent damping coefficient corresponding to the idle rate of the vehicle dispatching system.

[0126] It should be noted that the relationship between idle rate and load rate in the vehicle dispatching system mentioned in this invention is derived through in-depth analysis of system performance. Idle rate refers to the proportion of unused resources in the system, while load rate refers to the proportion of occupied resources. The relationship between the two reflects the efficiency of system resource utilization and task execution. When the load rate increases, the idle rate decreases accordingly, which usually means that system resources are being utilized more fully, but may also lead to increased response time and the risk of task delays. Therefore, reasonably controlling the balance between load rate and idle rate is crucial for optimizing system performance. Furthermore, the calculation of task delay difference further quantifies the delay of task execution under different load conditions, providing a basis for optimizing scheduling strategies.

[0127] Specifically, the relationship between idle rate and load rate in a vehicle dispatching system can be explained from the following aspects. Idle rate refers to the proportion of unused resources in the system, typically reflecting the system's idle capacity. Load rate, on the other hand, refers to the proportion of occupied resources in the system, reflecting the system's activity level. When the load rate increases, the system's resource utilization also increases accordingly, meaning more resources are used to complete tasks, thereby improving the overall efficiency of the system. However, an increase in load rate may also lead to a longer system response time, as the system needs to handle more tasks. Furthermore, task latency difference is calculated by comparing task latency under different load conditions, reflecting the performance differences of the system under different load states. For example, when the load rate is high, task latency may increase, while when the idle rate is high, task latency may decrease. This relationship can be further quantified and optimized through the analysis and modeling of system performance data.

[0128] Preferably, in practical applications, the relationship between idle rate and load rate of a vehicle dispatching system can be optimized through the following steps. First, data analysis is used to determine the system's performance under different load conditions, including key indicators such as response time and task latency. Then, a system performance model is established based on this data. The model's input parameters can include vehicle load capacity, task execution time, and dispatch command response time, while the output is the system's load rate and idle rate. Through model analysis, the optimal operating state of the system under different load conditions can be determined. For example, by adjusting the dispatching strategy and rationally allocating tasks, the system can maintain a short response time even under high load. Furthermore, by monitoring system performance in real time, the balance between load rate and idle rate can be dynamically adjusted to cope with dynamically changing vehicle demand. For example, when the system load rate is detected to be too high, the load rate can be reduced by increasing vehicle resources or optimizing task allocation, thereby improving system stability and response speed. Through these detailed steps and optimization measures, the system's load rate and idle rate can be managed more effectively, improving the overall system performance and user experience.

[0129] In some embodiments, the second theoretical threshold expression for load balancing in the vehicle dispatching system specifically includes:

[0130]

[0131] In the formula, I max It is the maximum load capacity designed for the vehicle, T max It is the maximum response time designed for the vehicle, P req θ is the input vehicle usage request power, and θ is the load balancing coefficient of the vehicle usage dispatching system.

[0132] It should be noted that the second theoretical threshold expression for load balancing in the vehicle dispatching system mentioned in this invention is determined based on vehicle design parameters and the input power of vehicle requests. This threshold expression is used to evaluate whether the system can maintain load balancing under design conditions, thereby ensuring the efficient operation of the vehicle dispatching system. The maximum design load capacity of a vehicle refers to the maximum load that a vehicle can withstand during its design, while the maximum design response time of a vehicle refers to the maximum time required for a vehicle to complete a task from receiving a dispatch instruction. The input power of vehicle requests reflects the intensity of user demand for vehicle resources. Through these parameters, a theoretical load balancing coefficient can be calculated to determine whether the system can reasonably allocate tasks within its design range, avoiding overload or resource idleness.

[0133] Specifically, the vehicle's maximum designed load capacity I max This refers to the maximum load a vehicle can withstand during its design phase; it reflects the vehicle's load-bearing capacity. The maximum design response time T is also a factor. max This refers to the maximum time required for a vehicle to complete a task from receiving a dispatch instruction; it reflects the vehicle's response speed. The input vehicle request power P req This refers to the intensity of user demand for vehicle resources, reflecting real-time user needs. The load balancing coefficient θ of a vehicle dispatching system is a parameter used to evaluate the system's load balancing status. It is determined by comparing the relationship between the maximum load capacity and response time of vehicles and the power requested by users. When the ratio of the maximum designed load capacity and maximum response time of vehicles to the input power of vehicle requests is greater than the load balancing coefficient, the system is considered to be able to reasonably allocate tasks within its design range and maintain load balance.

[0134] Preferably, in practical applications, the second theoretical threshold for load balancing in a vehicle dispatching system can be determined through the following steps. First, based on the vehicle's design parameters, determine the vehicle's maximum design load capacity I. max And the vehicle's maximum response time T max These parameters are typically provided by the vehicle manufacturer and clearly stated in the vehicle's design documents. Secondly, based on the user's actual needs, the input vehicle usage request power P is determined.req This parameter can be obtained by analyzing user vehicle request data, for example, by statistically analyzing the number of vehicles and task types requested by users within a certain period. Finally, the load balancing coefficient θ of the vehicle dispatching system is calculated based on these parameters and compared with the ratio of the vehicle's maximum designed load capacity and maximum response time to the power of the input vehicle requests. If the ratio is greater than the load balancing coefficient, it indicates that the system can reasonably allocate tasks within its design range and maintain load balance. This method effectively evaluates the system's load balancing status and optimizes vehicle dispatching strategies accordingly, ensuring the system operates efficiently within a reasonable load range.

[0135] In some embodiments, the divergence threshold under load balancing for the vehicles to be dispatched is calculated and output based on the design parameter values ​​of the vehicles to be dispatched, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the second theoretical threshold expression for load balancing of the vehicle dispatching system. Specifically, this includes:

[0136] Substitute the design parameter values ​​of the vehicles to be dispatched into the expression for the first theoretical threshold of load balancing in the vehicle dispatching system to calculate the first theoretical threshold of the load rate of the vehicle dispatching system.

[0137] Substitute the design parameter values ​​of the vehicles to be dispatched, the maximum design load capacity of the vehicles, and the maximum design response time of the vehicles into the expression for the second theoretical threshold of load balancing of the vehicle dispatching system to calculate the second theoretical threshold of load rate of the vehicle dispatching system.

[0138] The larger of the first theoretical threshold and the second theoretical threshold of the load rate of the vehicle dispatching system is taken as the divergence threshold of the load rate of the vehicle dispatching system.

[0139] It should be noted that the divergence threshold calculation under load balancing for vehicles to be dispatched mentioned in this invention is derived from the first and second theoretical threshold expressions for load balancing in a vehicle dispatching system. The divergence threshold refers to the maximum load value the system can withstand under load balancing conditions. Calculating the divergence threshold can prevent system overload and ensure stable system operation. In practical applications, the calculation of the divergence threshold needs to comprehensively consider factors such as vehicle design parameters, the vehicle's maximum designed load capacity, the vehicle's maximum designed response time, and the power of the input vehicle request. By comparing the first and second theoretical load rate thresholds, the larger value is selected as the divergence threshold, thereby providing a scientific basis for vehicle dispatching and ensuring that vehicles operate efficiently within a reasonable load range.

[0140] Specifically, vehicle design parameters refer to the various performance indicators determined during the vehicle's design phase, including the vehicle's maximum load capacity and maximum response time. Maximum load capacity of the vehicle design (I) maxThis refers to the maximum load a vehicle can withstand during its design phase, reflecting its load-bearing capacity. The vehicle's maximum design response time, T... max This refers to the maximum time required for a vehicle to complete a task from receiving a dispatch instruction, reflecting the vehicle's response speed. The input vehicle request power P req This refers to the intensity of user demand for vehicle resources, reflecting real-time user needs. The first theoretical threshold for load factor is calculated based on the ratio of system gain to damping coefficient, used to determine under what conditions the system can maintain stable operation. The second theoretical threshold for load factor is calculated based on the ratio of the vehicle's maximum design load capacity and maximum response time to the input vehicle usage request power, used to assess whether the system can maintain load balance under design conditions. By comparing these two thresholds, the larger value is selected as the divergence threshold, thereby ensuring that the system operates efficiently within a reasonable load range.

[0141] Preferably, in practical applications, the divergence threshold under load balancing for the vehicles to be scheduled can be calculated through the following steps. First, based on the vehicle's design parameters, determine the vehicle's maximum design load capacity I. max And the vehicle's maximum response time T max These parameters are typically provided by the vehicle manufacturer and clearly stated in the vehicle's design documents. Secondly, based on the user's actual needs, the input vehicle usage request power P is determined. req This parameter can be obtained by analyzing user vehicle request data, for example, by statistically analyzing the number of vehicles and task types requested by users within a certain period. Then, the vehicle design parameters are substituted into the first theoretical threshold expression for load balancing to calculate the first theoretical threshold for load rate. Next, the maximum load capacity of the vehicle design, the maximum response time, and the power of the input vehicle requests are substituted into the second theoretical threshold expression for load balancing to calculate the second theoretical threshold for load rate. Finally, these two thresholds are compared, and the larger value is selected as the divergence threshold. This method effectively evaluates the system's load balancing status and optimizes vehicle scheduling strategies accordingly, ensuring the system operates efficiently within a reasonable load range.

[0142] The various embodiments of the present invention have the following beneficial effects: By constructing a multi-level feedback vehicle dispatching system model, the present invention can accurately establish the mathematical relationship between the performance function and the load balancing threshold, providing a quantitative basis for vehicle resource allocation. The first theoretical threshold derived based on the Routh criterion ensures system stability, while the second theoretical threshold, combined with vehicle design parameters, takes into account actual operational needs. This dual-threshold mechanism can dynamically optimize the dispatching strategy. Through the synergistic effect of the coordinate transformation module and real-time data feedback, the vehicle dispatching position can be precisely controlled, effectively improving the system response accuracy.

[0143] By establishing a system architecture that includes modules for task priority calculation and resource allocation feedback, intelligent processing and efficient allocation of vehicle usage demands can be achieved. A simplified performance function model reduces computational complexity while maintaining an accurate description of the system's dynamic characteristics. The quantitative relationship between load rate and idle rate guides optimized resource allocation, and simulation verification ensures the practical feasibility of the scheduling scheme. This scheme can significantly improve vehicle utilization, reduce response latency, and enhance the system's resilience to disturbances through an external interference feedback mechanism.

[0144] Furthermore, the storage medium in the embodiments of this application stores program instructions capable of implementing all the above methods. These program instructions can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0145] The above description is merely a selection of preferred embodiments of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention as described in the embodiments is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A vehicle dispatching method based on big data, characterized in that the method... include: Establish a vehicle dispatch system model based on the mechanism of the vehicle dispatch system; Based on the vehicle dispatching system model, the performance function of the vehicle dispatching system is obtained; Based on the performance function of the vehicle dispatching system, we obtain the performance parameter expression of the vehicle dispatching system, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the relationship between the idle rate and the load rate of the vehicle dispatching system. Based on the performance function of the vehicle dispatching system, and combined with the maximum load capacity and maximum response time of the vehicle design, the second theoretical threshold expression for load balancing of the vehicle dispatching system is obtained. Based on the design parameter values ​​of the vehicles to be dispatched, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the second theoretical threshold expression for load balancing of the vehicle dispatching system, the divergence threshold under load balancing of the vehicles to be dispatched is calculated and output. A simulation system with a vehicle dispatching system model is used to simulate and output the load response curves of the vehicles to be dispatched within the divergence threshold, and to output the corresponding performance parameter values ​​of the vehicles to be dispatched under load balancing. The performance function of the vehicle dispatching system is specifically expressed as follows: ； In the formula, It is a transfer function operator for the vehicle dispatching system. It is the proportional gain of vehicle dispatch instructions. It is the vehicle task execution coefficient. It's about the efficiency of vehicle resource allocation. It is the vehicle's task execution inertia. It is the vehicle dispatching damping coefficient.

2. A vehicle dispatching method based on big data according to claim 1, characterized in that, The vehicle dispatching system model specifically includes... The vehicle usage demand input feedback module processes the input demand to obtain vehicle dispatch adjustment parameters. The vehicle usage demand input feedback loop includes a demand processing module, an inner-loop task allocation feedback module, a location feedback module, and a coordinate transformation module. The requirement processing module is used to sort the inputs by priority and output the processed requirements, and then input the processed requirements into the inner loop task allocation feedback module. The inner ring task allocation feedback module outputs vehicle scheduling adjustment tasks based on the processed requirements. The coordinate transformation module is used to convert vehicle dispatch adjustment tasks into vehicle dispatch adjustment locations, and then input the vehicle dispatch adjustment locations into the location feedback module. The location feedback module is used to multiply the vehicle dispatch adjustment position by the feedback output sensor proportional coefficient and output the location feedback. The difference between the location feedback and the input vehicle usage command is then used as the input to the demand processing module.

3. A vehicle dispatching method based on big data according to claim 2, characterized in that, The inner-loop task allocation feedback module includes a vehicle load calculation module, a task execution time calculation module, an inner-loop resource allocation feedback module, and a real-time data feedback module. The vehicle load calculation module is used to calculate and obtain the current load of the vehicle, and then output the vehicle load to the task execution time calculation module; The task execution time calculation module is used to calculate and obtain the task execution time based on the vehicle load, and then output the task execution time to the inner ring resource allocation feedback module. The inner ring resource allocation feedback module outputs vehicle scheduling adjustment tasks based on task execution time; The real-time data feedback module calculates real-time vehicle data feedback based on the vehicle scheduling adjustment task, and uses the difference between the real-time data feedback and the processed demand as the input to the vehicle load calculation module.

4. A vehicle dispatching method based on big data according to claim 3, characterized in that, The inner-loop resource allocation feedback module includes a task allocation priority calculation module, a vehicle scheduling calculation module, and an external interference feedback module. The task allocation priority calculation module is used to calculate the task allocation priority and output it to the vehicle scheduling calculation module; The vehicle scheduling calculation module calculates and obtains the vehicle scheduling location based on the task allocation priority, and outputs the vehicle scheduling location to the coordinate transformation module and the external interference feedback module. The external interference feedback module calculates the external interference feedback based on the vehicle scheduling location, and uses the difference between the external interference feedback and the task execution time as the input to the task allocation priority calculation module.

5. A vehicle dispatching method based on big data according to claim 4, characterized in that, Considering that the vehicle task execution inertia is much smaller than the vehicle dispatching damping coefficient, the vehicle task execution inertia is simplified to 0. The performance function expression of the vehicle dispatching system is then simplified to the following expression: ； In the formula, It is the gain of the vehicle dispatching system. This is the inherent frequency of the vehicle dispatching system, expressed as a formula: ； It is the inherent damping coefficient of the vehicle dispatching system, expressed as a formula: ； Among them, the vehicle dispatching system gain, the vehicle dispatching system inherent frequency, and the vehicle dispatching system inherent damping coefficient are the performance parameters of the vehicle dispatching system.

6. A vehicle dispatching method based on big data according to claim 5, characterized in that, The first theoretical threshold expression for load balancing in the vehicle dispatching system is obtained based on the Routh criterion and the performance function of the vehicle dispatching system, and is specifically expressed as follows: 。 7. A vehicle dispatching method based on big data according to claim 6, characterized in that, The relationship between idle rate and load rate in a vehicle dispatching system includes: The load rate of the vehicle dispatching system increases to times the idle rate of the vehicle dispatching system; The response time of the vehicle dispatching system is reduced to the idle rate of the vehicle dispatching system. The resource utilization rate of the vehicle dispatching system increases to the idle rate of the vehicle dispatching system. The increase in task latency difference in the vehicle dispatching system can be expressed as a formula: ； In the formula, The idle rate of the vehicle dispatching system corresponds to the inherent frequency. The load rate of the vehicle dispatching system corresponds to the inherent frequency. It is the inherent damping coefficient corresponding to the idle rate of the vehicle dispatching system. The inherent damping coefficient corresponding to the load rate of the vehicle dispatching system.

8. A vehicle dispatching method based on big data according to claim 7, characterized in that, The expression for the second theoretical threshold for load balancing in a vehicle dispatching system specifically includes: ； In the formula, It is the maximum load capacity designed for the vehicle. This is the maximum response time designed for the vehicle. This is the input power of the vehicle usage request. It is the load balancing coefficient of the vehicle dispatching system.

9. A vehicle dispatching method based on big data according to claim 8, characterized in that, Based on the design parameter values ​​of the vehicles to be dispatched, the first theoretical threshold expression for load balancing of the vehicle dispatching system, and the second theoretical threshold expression for load balancing of the vehicle dispatching system, the divergence threshold under load balancing of the vehicles to be dispatched is calculated and output, specifically including: Substitute the design parameter values ​​of the vehicles to be dispatched into the expression for the first theoretical threshold of load balancing in the vehicle dispatching system to calculate the first theoretical threshold of the load rate of the vehicle dispatching system. Substitute the design parameter values ​​of the vehicles to be dispatched, the maximum design load capacity of the vehicles, and the maximum design response time of the vehicles into the expression for the second theoretical threshold of load balancing of the vehicle dispatching system to calculate the second theoretical threshold of load rate of the vehicle dispatching system. The larger of the first theoretical threshold and the second theoretical threshold of the load rate of the vehicle dispatching system is taken as the divergence threshold of the load rate of the vehicle dispatching system.

Images