An enterprise vehicle resource dynamic management and optimization platform

Abstract

The present invention discloses an enterprise vehicle resource dynamic management and optimization platform, which relates to the technical field of vehicle resource management and includes: a data collection module for collecting historical multi-dimensional data and processing it to form a unified time series data set; an order prediction module for constructing a time series density field based on the time series data set to predict the order request distribution within a future time window; a path optimization module for calculating the path complexity and delay potential terms based on the predicted order request distribution, constructing a comprehensive cost function, and using a multi-objective non-linear optimization algorithm to dynamically optimize the vehicle path; and a dynamic adjustment module for updating the order prediction results and path optimization solutions according to real-time data to achieve dynamic management and optimization of enterprise vehicle resources. Precise order prediction is achieved by constructing a time series density field, and the comprehensiveness and diversity of the optimization results are improved by comprehensively considering the complexity of the path length and the delay potential terms, thereby realizing the efficient dynamic management and optimization of enterprise vehicle resources.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle resource management, and particularly to a dynamic management and optimization platform for enterprise vehicle resources. Background Art

[0002] With the acceleration of urbanization and the continuous growth of logistics demand, the management and optimization of enterprise vehicle resources have become an important link to improve operational efficiency and competitiveness. Traditional vehicle scheduling methods mostly rely on manual experience and static planning, and it is difficult to cope with real-time changing order demands, traffic conditions and environmental factors. This not only leads to low resource utilization rate, but may also cause service delays and operational risks, thus affecting the overall performance of the enterprise.

[0003] Existing vehicle management systems usually include basic functions such as data collection, order processing and route planning. However, these systems have deficiencies in the following aspects: inaccurate order prediction: Traditional systems mostly use simple statistical analysis or linear models based on historical data for order prediction, and it is difficult to capture complex spatio-temporal patterns and dynamic changes, resulting in insufficient accuracy of prediction results and affecting subsequent resource scheduling and route planning. Single route optimization: Existing route planning algorithms often only consider single factors such as route length or travel time, ignoring multi-dimensional factors such as route complexity, service delay potential and operation risks. This single optimization strategy is difficult to achieve comprehensive optimization in a changing environment, and may lead to resource waste and service quality decline. Limited dynamic adjustment ability: Many existing systems lack an effective dynamic adjustment mechanism in the face of real-time data changes and cannot respond in a timely manner to fluctuations in order demands and emergencies. This static scheduling method performs poorly in a complex dynamic environment and is difficult to maintain the high efficiency and flexibility of the system. Insufficient multi-objective optimization: Traditional optimization methods usually focus on a single objective, such as the shortest route or the lowest cost, ignoring the trade-off relationships between multiple objectives. With the increasing demands of enterprises in multiple aspects such as operational efficiency, service quality and risk control, single-objective optimization methods are no longer able to meet the requirements of comprehensive optimization. Summary of the Invention

[0004] Based on the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide a dynamic management and optimization platform for enterprise vehicle resources to solve the above technical problems.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A dynamic management and optimization platform for enterprise vehicle resources, comprising:

[0006] A data collection module, used for collecting historical order data, vehicle operation data and road network information, cleaning, aligning and fusing the collected data to form a unified time series data set;

[0007] An order prediction module, based on the time series data set, constructs a time series density field and predicts the order request distribution in the future time window;

[0008] The route optimization module calculates the route complexity and delay potential based on the predicted order request distribution, constructs a comprehensive cost function based on the route complexity and delay potential, and uses a multi-objective nonlinear optimization algorithm to dynamically optimize the vehicle route;

[0009] The dynamic adjustment module is used to update order prediction results and route optimization plans based on real-time data, realizing dynamic management and optimization of enterprise vehicle resources.

[0010] The present invention is further configured to: in the time series data set, the order data , each order Include timestamp ,Location , order type and order amount, the vehicle operation data , each car Including location, load and status information, the road network information W includes road nodes, edges, distances and road grades.

[0011] The present invention is further configured such that the order prediction module comprises: a time series density field construction unit and an order request distribution prediction unit;

[0012] The time series density field construction unit is used to map the order position into a density field according to the order data through a preset spatiotemporal density field function;

[0013] The order request distribution prediction unit predicts the order distribution in a future time window according to the density field.

[0014] The present invention is further configured to map the order position into a density field through a preset spatiotemporal density field function, and the calculation logic is: ,in, For historical time slices Inside, location The order density field at , is the kernel function used to smooth the contribution of order positions to the density field, , is a variable, is the diffusion parameter, which is used to control the decay rate and diffusion range of the kernel function.

[0015] The present invention is further configured to predict the order distribution in the future time window based on the density field, and the calculation logic is: ,in, For the future time window Internal position The prediction result of the order request probability density distribution at is the first amplification parameter, is the sensitivity parameter, and is the shape adjustment parameter.

[0016] The present invention is further configured such that the path optimization module includes: a path complexity calculation unit, a delay potential term calculation unit, a comprehensive cost function construction unit, and an optimization algorithm unit;

[0017] The path complexity calculation unit is used to calculate the path complexity according to the tortuosity of the path and the road grade change rate;

[0018] The delay potential term calculation unit is used to accumulate the delay potential on the path according to the order distribution in the future time window predicted by the density field to obtain the delay potential term;

[0019] The comprehensive cost function construction unit is used to construct a comprehensive cost function according to the path complexity and the delay potential term; [[ID=Q19]]

[0020] The optimization algorithm unit is used to adopt a multi-objective nonlinear optimization algorithm to dynamically optimize the vehicle path.

[0021] The present invention is further configured such that the calculation logic of the path complexity is: , where is the path length is the path complexity of is the path parameter, indicating the position ratio on the path, and the value range is [0,1], is the exponential weight of the tortuosity of the path to the complexity, is the tortuosity of the path at the arc length , , is the tortuosity of the path at the arc length at the node , , is the node with two-dimensional coordinates, is the road grade change rate of the path at the arc length , , is the road grade change rate of the path at the arc length at the node , is the road grade of the path at the arc length at the node .

[0022] The present invention is further configured such that the calculation logic of the delay potential term is: , where is the path length is the latency potential term of is the second amplification parameter is the latency potential accumulation of the path at the arc length where and, is the latency potential accumulation at the path parameter where is a two-dimensional real number space is the future time window is the predicted result of the order request probability density distribution at the position within is the path parameter is the corresponding position at is the Gaussian kernel width parameter, which is used to control the diffusion range and influence range of the kernel function

[0023] The present invention is further configured such that the construction logic of the comprehensive cost function is where is the comprehensive cost function is the adjustment parameter is the non-linear power parameter

[0024] The present invention is further configured such that the multi-objective non-linear optimization algorithm includes: non-dominated sorting genetic algorithm, multi-objective differential evolution algorithm, and the hybrid of genetic algorithm and local search

[0025] The present invention provides an enterprise vehicle resource dynamic management and optimization platform, including: a data collection module, which is used to collect historical order data, vehicle operation data, and road network information, clean, align, and fuse the collected data to form a unified time series data set; an order prediction module, which constructs a time series density field based on the time series data set and predicts the order request distribution within the future time window; a path optimization module, which calculates the path complexity and latency potential term based on the predicted order request distribution, constructs a comprehensive cost function according to the path complexity and latency potential term, and dynamically optimizes the vehicle path by using a multi-objective non-linear optimization algorithm; a dynamic adjustment module, which is used to update the order prediction result and path optimization scheme according to real-time data, realize the dynamic management and optimization of enterprise vehicle resources, and the beneficial effects generated include

[0026] Accurate order prediction ability: By constructing a time series density field and applying an advanced spatio-temporal density field function, the historical order data is accurately mapped to the density field, and combined with a non-linear aggregation method, complex spatio-temporal patterns and dynamic changes are effectively captured, thereby improving the accuracy of the prediction of the future order request distribution

[0027] Comprehensively consider multi-dimensional cost factors: In the process of path optimization, not only consider the complexity of path length, but also consider the latency potential term to comprehensively reflect the multi-faceted characteristics of the path. By precisely defining path complexity and latency potential, ensure that the optimization result achieves the best balance between path geometric complexity and service latency potential, and avoid resource waste and service quality degradation caused by single-objective optimization;

[0028] Efficient multi-objective non-linear optimization algorithm: Adopt a multi-objective non-linear optimization algorithm to effectively handle multiple conflicting optimization objectives, improve the comprehensiveness and diversity of the optimization results. The optimization algorithm has good global search ability and population diversity maintenance mechanism, and can quickly converge in a complex search space to find a high-quality optimal solution set.

[0029] The above description is only an overview of the technical solution of this application. In order to be able to more clearly understand the technical means of this application, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Brief Description of the Drawings

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. In the drawings:

[0031] Figure 1 It is a schematic structural diagram of an enterprise vehicle resource dynamic management and optimization platform shown in an exemplary embodiment of the present invention. Detailed Description of the Preferred Embodiments

[0032] The following will describe the embodiments of the present invention with reference to the drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention, rather than for limiting the protection scope of the present invention.

[0033] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape and size of the components in actual implementation. The type, number and proportion of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0034] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0035] An enterprise vehicle resource dynamic management and optimization platform, as Figure 1 shown, includes:

[0036] A data collection module for collecting historical order data, vehicle operation data, and road network information, cleaning, aligning, and fusing the collected data to form a unified time-series data set;

[0037] An order prediction module for constructing a time-series density field based on the time-series data set and predicting the order request distribution within a future time window;

[0038] A path optimization module for calculating path complexity and delay potential terms based on the predicted order request distribution, constructing a comprehensive cost function according to the path complexity and delay potential terms, and dynamically optimizing the vehicle path using a multi-objective non-linear optimization algorithm;

[0039] A dynamic adjustment module for updating the order prediction result and path optimization scheme based on real-time data to achieve dynamic management and optimization of enterprise vehicle resources.

[0040] The present invention is further configured such that in the time-series data set, the order data , each order includes a timestamp , location , order type, and order amount. The vehicle operation data , each vehicle includes location, load, and status information. The road network information W includes road nodes, edges, distances, and road grades. Specifically, in the order data, the timestamp means the specific time when the order is generated or requested, which is used for time-series analysis to capture the time patterns and trends of order demands, and the location location The geographic coordinates of an order request are typically represented in a two-dimensional Cartesian coordinate system and are used for spatial analysis to determine the geographic distribution and concentration of orders. The order type describes the nature or category of an order, such as delivery, pickup, or service request, helping to categorize order demand and develop optimization strategies for different order types. The order amount represents the economic value or transaction amount of an order and is used to measure the importance and priority of an order, optimizing resource allocation to maximize economic benefits. In vehicle operation data, location refers to the current geographic location of the vehicle and is represented in a two-dimensional Cartesian coordinate system. This allows for real-time monitoring of vehicle distribution and optimization of vehicle scheduling and route planning. Load capacity refers to the current load status of the vehicle, typically expressed in units of weight. This is used to ensure that the vehicle is properly loaded during transportation and avoid overloading or resource waste. Status information describes the current state of the vehicle, such as idle, in motion, or under maintenance. This information is used to dynamically manage vehicle status and optimize resource utilization and response speed. In road network information, road nodes represent the geographic coordinates of key points in the road network, such as intersections and turning points. These serve as the basis for constructing road network maps and support path search and optimization algorithms. Edges are road segments connecting road nodes, typically represented as directed or undirected edges. They are used to define road network connectivity and support path calculation and traffic flow analysis. Distances are the lengths of road edges, typically measured in kilometers or meters. They are used to calculate the total length and travel time of routes, supporting route optimization and cost assessment. Road classes, such as highway, main road, or secondary road, represent the importance and capacity of roads and are used to influence vehicle speeds and priorities, optimizing route selection for improved efficiency and safety.

[0041] The present invention is further configured such that the order prediction module comprises: a time series density field construction unit and an order request distribution prediction unit;

[0042] The time series density field construction unit is used to map the order position into a density field according to the order data using a preset spatiotemporal density field function. The present invention is further configured to map the order position into a density field using a preset spatiotemporal density field function, and the calculation logic is: ,in, For historical time slices Inside, location The order density field at , is the kernel function used to smooth the contribution of order positions to the density field, , is a variable, is the diffusion parameter, which is used to control the decay rate and diffusion range of the kernel function. Specifically, first obtain the enterprise’s historical time slice All order data in , each order Include timestamp ,Location , order type and order amount; Gaussian kernel function is used ,in Indicates a waypoint With order Location The square of the Euclidean distance between Is the diffusion parameter, which is used to control the decay rate and diffusion range of the kernel function. Each order within , calculate its position The contribution of the order density field at , all orders Position The contributions at the locations are added up to get the original density accumulation value , by performing exponential transformation on the cumulative value, a smooth and continuous order density field is obtained The above calculation logic constructs a time-series density field and applies advanced spatiotemporal density field functions to accurately map historical order data into a smooth order density field. Combined with nonlinear aggregation methods, it precisely captures complex spatiotemporal patterns and dynamic changes. This calculation logic not only improves the accuracy and stability of order forecasts but also provides high-quality data support for multi-objective nonlinear optimization algorithms, ensuring efficient and dynamic management and optimization of the company's vehicle resources. By flexibly adjusting key parameters, it can adapt to different business needs and operating environments, significantly improving the company's operational efficiency and resource utilization.

[0043] The order request distribution prediction unit predicts the order distribution in the future time window based on the density field. The present invention is further configured to predict the order distribution in the future time window based on the density field, and the calculation logic is: ,in, For the future time window Internal position The predicted result of the probability density distribution of order requests at , is the first amplification parameter, is the sensitivity parameter, is the morphological adjustment parameter. Specifically, after obtaining the historical time slice Inside, location Order density field Then, through the sensitivity parameter , , used to adjust the impact of historical order density on forecast results, morphological adjustment parameters , , a nonlinear aggregation method used to control order density, weighting the order density of all historical time slices and performing power transformation to accumulate the comprehensive impact value , by taking the power of the comprehensive influence value and taking the natural logarithm, non-linear aggregation features are extracted , through the first amplification parameter , , which is used to adjust the influence of the aggregation features on the final prediction result, perform an exponential transformation on the non-linear aggregation features, and subtract 1 to obtain the order request probability density distribution prediction result at the position within the future time window . The above calculation logic constructs a time series density field and applies an advanced spatio-temporal density field function to accurately map historical order data into a continuous and smooth order density field. Combining non-linear aggregation methods and exponential transformation, it realizes accurate prediction of order request distribution within the future time window. By flexibly adjusting key parameters, the platform can adapt to different business requirements and operating environments, significantly improving the accuracy of order prediction, the comprehensiveness and diversity of optimized path selection, and ultimately achieving efficient dynamic management and optimization of enterprise vehicle resources, enhancing the operation efficiency and resource utilization rate of the enterprise.

[0044] The present invention is further configured such that the path optimization module includes: a path complexity calculation unit, a delay potential term calculation unit, a comprehensive cost function construction unit, and an optimization algorithm unit;

[0045] The path complexity calculation unit is used to calculate the path complexity according to the tortuosity of the path and the road grade change rate; the present invention is further configured such that the calculation logic of the path complexity is: , where is the path length of the path complexity, is the path parameter, indicating the position ratio on the path, with a value range of [0, 1], is the exponential weight of the tortuosity of the path on the complexity, is the tortuosity of the path at the arc length , , is the tortuosity of the path at the node on the arc length , , is the node of the two-dimensional coordinates, is the road grade change rate of the path at the arc length , , is the road grade change rate of the path at the node on the arc length , is the road grade change rate of the path at the node on the arc length The road grade at a specific location. Specifically, the vehicle driving path is discretized into a series of continuous nodes , and the road grade at each node is obtained . Through the coordinates of three consecutive nodes , and , the tortuosity at node is calculated. The rate of change of the road grade between adjacent nodes is calculated, and the path complexity is quantified using the tortuosity and the rate of change of the road grade. The tortuosity is a geometric feature that describes the degree of bending of the path at a certain point. The greater the tortuosity, the more curved the path is at that point; the rate of change of the road grade is used to measure the degree of fluctuation of the road grade of the path at a certain point; the path complexity comprehensively evaluates the tortuosity and the rate of change of the road grade of the path, quantifies the geometric complexity of the path, and controls the exponential weight of the tortuosity of the path on the complexity is greater than 0. Through the path complexity calculation unit, based on the tortuosity and the rate of change of the road grade of the path, the integral method is used to quantify the geometric complexity of the path. This method not only accurately reflects the driving difficulty and resource consumption of the path, but also supports the efficient operation of the multi-objective non-linear optimization algorithm through flexible parameter adjustment, realizing the intelligent dynamic management and optimization of enterprise vehicle resources

[0046] [[ID=FIG. ]]The delay potential term calculation unit is used to predict the order distribution within the future time window according to the density field and accumulate the delay potential on the path to obtain the delay potential term; The present invention is further configured that the calculation logic of the delay potential term is: , where is the path length is the delay potential term of is the second amplification parameter is the delay potential accumulation at the arc length of the path , where is the delay potential accumulation at the path parameter of the path is the two-dimensional real number space is the future time window The prediction result of the order request probability density distribution at the position within is the path parameter The corresponding position at is the Gaussian kernel width parameter, which is used to control the diffusion range and influence range of the kernel function. Specifically, according to the prediction result of the order request probability density distribution at the position within the future time window , the position corresponding to the path parameter is The distances to all positions are weighted by a Gaussian kernel function to generate the cumulative delay potential at the path parameter . , smoothing the order request distribution through a Gaussian kernel function to ensure that the influence of the order density in the area around the path point on the delay potential gradually decays. Integrating the cumulative delay potential of all path points from the starting point to the parameter along the path length, combining the second amplification parameter , quantifying the delay potential term of the entire path segment . The value of the second amplification parameter is greater than 0. Through the delay potential term calculation unit, based on the prediction of the order distribution within the future time window, using the Gaussian kernel function and the non - linear integral method, the service delay potential on the path is accurately quantified. This method not only improves the accuracy and sensitivity of the delay risk assessment, but also ensures the efficient dynamic management and optimization of the enterprise vehicle resources through flexible parameter adjustment and comprehensive multi - objective optimization strategies. Thus, it significantly improves the operation efficiency and service quality of the enterprise, reduces the operation cost, and enhances the adaptability and competitiveness of the system.

[0047] The comprehensive cost function construction unit is used to construct a comprehensive cost function according to the path complexity and the delay potential term; The present invention is further set such that the construction logic of the comprehensive cost function is: , where is the comprehensive cost function, is the adjustment parameter, is the non - linear power parameter. Specifically, the construction of the comprehensive cost function aims to integrate multiple optimization objectives (path complexity and delay potential) into a unified evaluation index, so as to consider these factors simultaneously during the path optimization process and achieve the balanced optimization of multiple objectives. For each optimization objective (path complexity and delay potential term ), the adjustment parameter and the non - linear power parameter are respectively introduced to adjust their weights and sensitivities in the comprehensive cost function. The single - objective cost terms are combined using the multiplication operation, and the non - linear integration of multiple objectives is achieved through the power transformation to ensure the balance and coordination between different objectives. Integrating the path parameter from 0 to 1, accumulating the comprehensive cost on the entire path, obtaining the final comprehensive cost function. By constructing the comprehensive cost function, multi - dimensional cost factors such as path complexity and delay potential are integrated into a unified optimization index, and a multi - objective non - linear optimization algorithm is used for dynamic optimization, realizing the efficient dynamic management and optimization of the enterprise vehicle resources.

[0048] The optimization algorithm unit is used to dynamically optimize the vehicle route by using a multi-objective non-linear optimization algorithm. The present invention is further configured that the multi-objective non-linear optimization algorithm includes: non-dominated sorting genetic algorithm, multi-objective differential evolution algorithm, and the hybrid of genetic algorithm and local search. Specifically, the optimization algorithm unit is used to dynamically optimize the driving route of enterprise vehicles by using a multi-objective non-linear optimization algorithm. This optimization algorithm unit integrates a variety of advanced multi-objective optimization algorithms, including non-dominated sorting genetic algorithm (NSGA-II), multi-objective differential evolution algorithm (MODE), and the hybrid method of genetic algorithm and local search (GA-LS). Through the application of these algorithms, the system can efficiently balance and optimize multiple conflicting objectives in a complex and changing operating environment, thereby realizing the intelligent management and optimization of enterprise vehicle resources. The non-dominated sorting genetic algorithm II (NSGA-II) is an evolutionary algorithm widely used in multi-objective optimization problems, known for its efficient non-dominated sorting mechanism and crowding distance sorting method. It aims to optimize multiple objective functions simultaneously and generate a high-quality solution set covering the Pareto front; the multi-objective differential evolution algorithm (MODE) is a multi-objective extension of the differential evolution algorithm (DE), combining non-dominated sorting and diversity maintenance strategies, suitable for dealing with multiple conflicting optimization objectives. Its main features are efficient search ability and good population diversity; the hybrid of genetic algorithm and local search (GA-LS) is a hybrid optimization method that combines the genetic algorithm (Genetic Algorithm, GA) and local search (Local Search, LS). It combines the global search ability of the genetic algorithm and the fine optimization ability of local search, aiming to improve the quality and convergence speed of the optimization results; the above optimization algorithms are all prior arts and will not be elaborated here. By using a multi-objective non-linear optimization algorithm through the optimization algorithm unit, including non-dominated sorting genetic algorithm (NSGA-II), multi-objective differential evolution algorithm (MODE), and the hybrid method of genetic algorithm and local search (GA-LS), the comprehensive, flexible and efficient optimization of enterprise vehicle routes is achieved. By comprehensively considering multiple key factors such as route complexity and latency potential, and using advanced optimization algorithms to handle conflicting objectives, the present invention significantly improves the dynamic management and optimization ability of enterprise vehicle resources, enhances the adaptability and operation efficiency of the system, and has broad application prospects and significant economic benefits.

[0049] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0050] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context.

[0051] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0052] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0053] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0054] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0055] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical, or other forms.

[0056] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units. That is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0057] In addition, the functional units in each embodiment of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0058] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0059] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A dynamic management and optimization platform for enterprise vehicle resources, characterized by: include: The data collection module is used to collect historical order data, vehicle operation data, and road network information, and clean, align, and fuse the collected data to form a unified time series data set; An order prediction module, based on the time series data set, constructs a time series density field to predict the distribution of order requests in a future time window; the module includes: mapping the order location into a time series density field using a preset spatiotemporal density field function according to the order data; and predicting the distribution of order requests in the future time window based on the time series density field; The route optimization module calculates the route complexity and delay potential based on the predicted order request distribution, constructs a comprehensive cost function based on the route complexity and delay potential, and uses a multi-objective nonlinear optimization algorithm to dynamically optimize the vehicle route. This includes: calculating the route complexity based on the tortuosity of the route and the rate of change of the road grade; accumulating the delay potential on the route to obtain the delay potential term based on the order distribution within the future time window predicted by the density field; constructing a comprehensive cost function based on the route complexity and delay potential term; and dynamically optimizing the vehicle route using a multi-objective nonlinear optimization algorithm. The calculation logic of the delay potential term is as follows: ,in, is the path length The delayed potential term, is a path parameter, which identifies the position ratio on the path, and its value range is [0,1]. is the second amplification parameter, The arc length of the path The potential for delay accumulation at ,in, For path parameters The potential for delay accumulation at is a two-dimensional real space, For the future time window Internal position The predicted result of the probability density distribution of order requests at , For path parameters At the corresponding position, is the Gaussian kernel width parameter, which is used to control the diffusion range and influence range of the kernel function; The dynamic adjustment module is used to update order prediction results and route optimization plans based on real-time data, realizing dynamic management and optimization of enterprise vehicle resources.

2. The enterprise vehicle resource dynamic management and optimization platform according to claim 1 is characterized in that: In the time series data set, the order data , each order Include timestamp ,Location , order type and order amount, the vehicle operation data , each car Including location, load and status information, the road network information Includes road nodes, edges, distances, and road levels.

3. The enterprise vehicle resource dynamic management and optimization platform according to claim 1 is characterized in that: The order position is mapped to a density field through the preset space-time density field function. The calculation logic is as follows: ,in, For historical time slices Inside, location The order density field at , is the kernel function used to smooth the contribution of order positions to the density field, , is a variable, is the diffusion parameter, which is used to control the decay rate and diffusion range of the kernel function.

4. The enterprise vehicle resource dynamic management and optimization platform according to claim 3 is characterized in that: The order distribution in the future time window is predicted based on the density field. The calculation logic is: ,in, For the future time window Internal position The predicted result of the probability density distribution of order requests at , is the first amplification parameter, is the sensitivity parameter, is the morphology adjustment parameter.

5. The enterprise vehicle resource dynamic management and optimization platform according to claim 1 is characterized in that: The calculation logic of the path complexity is: ,in, is the path length The path complexity of To control the exponential weight of the tortuosity of the path to the complexity, The arc length of the path The tortuosity of , The arc length of the path Previous node The tortuosity of For nodes The two-dimensional coordinates of The arc length of the path The road grade change rate at , The arc length of the path Previous node The road grade change rate, The arc length of the path Previous node Road grade.

6. The enterprise vehicle resource dynamic management and optimization platform according to claim 5 is characterized in that: The construction logic of the comprehensive cost function is: ,in, is the comprehensive cost function, To adjust the parameters, is the nonlinear power parameter.

7. The enterprise vehicle resource dynamic management and optimization platform according to claim 6 is characterized in that: Multi-objective nonlinear optimization algorithms include: non-dominated sorting genetic algorithm, multi-objective differential evolution algorithm and a hybrid of genetic algorithm and local search.

Images