Method, medium and electronic device for determining a vehicle dispatching scheme

Abstract

This application provides a method, medium, and electronic device for determining a vehicle scheduling scheme, which can be applied to the field of vehicle scheduling technology. The method includes: aiming to maximize the loading capacity corresponding to each of multiple vehicle identifiers in the scheduling scheme to be determined and to minimize the total number of vehicle identifiers corresponding to the scheduling scheme to be determined; adjusting the vehicle identifiers corresponding to each cargo information based on scheduling parameters according to the transportation route and cargo category of each cargo information until multiple candidate scheduling schemes are obtained; determining a quality score for each candidate scheduling scheme based on at least one of the loading capacity, transportation route, and cargo category corresponding to each vehicle identifier, as well as the loading rate corresponding to each vehicle identifier in each candidate scheduling scheme; determining a target scheduling scheme from the multiple candidate scheduling schemes based on the quality scores of each candidate scheduling scheme; and adjusting the target scheduling scheme based on optimization parameters with the aim of maximizing the quality score of the target scheduling scheme until an optimized vehicle scheduling scheme is obtained.

Description

Technical Field

[0001] This application relates to the field of vehicle dispatching technology, and more specifically to a method, medium, and electronic device for determining a vehicle dispatching scheme. Background Technology

[0002] In complex business scenarios (such as logistics and transportation), in order to ensure delivery efficiency, it is necessary to find the optimal vehicle scheduling scheme for the goods to be transported.

[0003] In related technologies, vehicle scheduling schemes are generated through traditional optimization algorithms, but the effectiveness of these schemes in actual business scenarios needs to be improved. Summary of the Invention

[0004] In view of the above problems, embodiments of this application provide a method, apparatus, device, medium, and program product for determining a vehicle scheduling scheme.

[0005] According to a first aspect of this application, a method for determining a vehicle scheduling scheme is provided. The method includes: in response to receiving multiple cargo information, with the objective of maximizing the loading capacity corresponding to each of multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, adjusting the vehicle identifiers corresponding to each cargo information based on scheduling parameters according to the transport route and cargo category of each cargo information until multiple candidate scheduling schemes are obtained, wherein the scheduling parameters are used to control the number of candidate scheduling schemes; determining a quality score for each candidate scheduling scheme based on at least one of the loading capacity, transport route, and cargo category corresponding to the vehicle identifier and the loading rate corresponding to the vehicle identifier in each candidate scheduling scheme; determining a target scheduling scheme from the multiple candidate scheduling schemes based on the quality scores of each candidate scheduling scheme; and adjusting the target scheduling scheme based on optimization parameters with the objective of maximizing the quality score of the target scheduling scheme until an optimized vehicle scheduling scheme is obtained, wherein the optimization parameters are used to control the number of adjustments to the target scheduling scheme.

[0006] According to an embodiment of this application, the scheduling parameters include a baseline number of first scheduling schemes; with the goal of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, the vehicle identifiers corresponding to each cargo information are adjusted based on the scheduling parameters according to the transportation route and cargo category of each cargo information until multiple candidate scheduling schemes are obtained, including: in response to receiving N cargo information, performing the following operations until the number of first scheduling schemes reaches the baseline number, to obtain multiple first scheduling schemes: determining the vehicle identifiers that match the transportation route and cargo category of the cargo orders in the N cargo information, where N is an integer greater than 1; and obtaining a first scheduling scheme when the loading capacity corresponding to the vehicle identifier is less than or equal to a preset loading capacity threshold; determining multiple second scheduling schemes from the multiple first scheduling schemes based on the quality scores of the multiple first scheduling schemes; and adjusting at least one of the vehicle identifiers and cargo orders in at least two second scheduling schemes to obtain multiple candidate scheduling schemes.

[0007] According to an embodiment of this application, determining a plurality of second scheduling schemes from a plurality of first scheduling schemes based on the quality scores of a plurality of first scheduling schemes includes: selecting a preset number of second scheduling schemes from the plurality of first scheduling schemes based on the quality scores of the plurality of first scheduling schemes, wherein the preset number is determined according to the number of first scheduling schemes; grouping the plurality of first scheduling schemes that are not selected to obtain a plurality of scheme groups; and taking the first scheduling scheme with the highest quality score in each scheme group as the second scheduling scheme.

[0008] According to an embodiment of this application, adjusting at least one of the vehicle identifier and the cargo order in at least two second scheduling schemes to obtain multiple candidate scheduling schemes includes: exchanging vehicle identifiers with the same transportation route and the same cargo category in at least two second scheduling schemes to obtain at least two preferred scheduling schemes; in response to the probability of change of the preferred scheduling scheme relative to the second scheduling scheme being greater than the change threshold, adjusting the vehicle identifiers in the preferred scheduling scheme with the goal of maximizing the quality score of the preferred scheduling scheme to form candidate scheduling schemes.

[0009] According to an embodiment of this application, the scheduling parameters further include a first change threshold and a second change threshold. The change probability is obtained by: obtaining a relative score based on the deviation between the quality score of the optimized scheduling scheme and the maximum quality score among all optimized scheduling schemes; obtaining a change range based on the difference between the first change threshold and the second change threshold, where the first change threshold indicates the upper limit of the change probability and the second change threshold indicates the lower limit of the change probability; and fusing the first change threshold, the relative score, and the change range to obtain the change probability.

[0010] According to an embodiment of this application, the optimization parameters include the baseline number M of adjusting the target scheduling scheme, where M is an integer greater than 1; adjusting the target scheduling scheme based on the optimization parameters with the goal of maximizing the quality score of the target scheduling scheme until an optimized vehicle scheduling scheme is obtained includes: taking the target scheduling scheme as the first scheduling scheme and the first reference scheduling scheme, performing M adjustment operations, and taking the scheme with the higher quality score among the resulting Mth scheduling scheme and the Mth reference scheduling scheme as the optimized scheduling scheme, wherein the mth adjustment operation includes: with the goal of maximizing the quality score of the m scheduling schemes, adjusting the vehicle identifiers of vehicles with the same transportation routes and the same cargo categories in the mth scheduling scheme to form the mth intermediate scheduling scheme, m=1,…,M-1; if the quality score of the mth intermediate scheduling scheme is greater than the quality score of the mth scheduling scheme or the acceptance probability of the mth intermediate scheduling scheme is greater than or equal to a preset probability threshold, the mth intermediate scheduling scheme is taken as the (m+1)th scheduling scheme; if the quality score of the mth intermediate scheduling scheme is greater than the quality score of the mth reference scheduling scheme, the mth intermediate scheduling scheme is taken as the (m+1)th reference scheduling scheme.

[0011] According to embodiments of this application, determining the quality score of each candidate scheduling scheme includes performing the following operations for each candidate scheduling scheme: obtaining a loading score by summing the loading scores represented by the loading rates corresponding to multiple vehicle identifiers; and fusing at least one of the vehicle score, constraint score, and overload score with the loading score to obtain the quality score of the candidate scheduling scheme. The vehicle score is based on the total number of vehicle identifiers; the constraint score is based on at least one of the following: the number of cargo categories corresponding to each vehicle identifier, the degree of deviation between the vehicle type corresponding to each vehicle identifier and the reference vehicle type, the degree of deviation between the loading amount corresponding to each vehicle identifier and the preset loading amount threshold, and the number of vehicle types corresponding to each transport route. The overload score is based on vehicle identifiers with loading amounts greater than the loading amount threshold.

[0012] According to embodiments of this application, scheduling parameters and optimization parameters are obtained in the following manner: Multiple initial scheduling parameters and multiple initial optimization parameters are determined; each initial scheduling parameter and each initial optimization parameter is input into a prediction model to obtain multiple accuracy scores and multiple stability scores; the prediction model is pre-trained using historical scheduling parameters, historical optimization parameters, and corresponding accuracy score labels and stability score labels; based on the multiple accuracy scores and multiple stability scores, multiple candidate scheduling parameters are determined from the multiple initial scheduling parameters, and multiple candidate control parameters are determined from the multiple initial optimization parameters; multiple candidate optimized scheduling schemes corresponding to the multiple candidate scheduling parameters and multiple candidate optimization parameters are determined; based on the quality scores of the multiple candidate optimized scheduling schemes, a target optimized scheduling scheme is determined from the multiple candidate optimized scheduling schemes; the candidate scheduling parameters corresponding to the target optimized scheduling scheme are used as scheduling parameters, and the candidate optimization parameters corresponding to the target optimized scheduling scheme are used as optimization parameters.

[0013] According to a second aspect of this application, an apparatus for determining a vehicle scheduling scheme is provided. The apparatus includes: a scheme generation module, configured to, in response to receiving multiple cargo information, adjust the vehicle identifiers corresponding to each cargo information based on scheduling parameters, with the objectives of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, according to the transportation route and cargo category of each cargo information, until multiple candidate scheduling schemes are obtained, wherein the scheduling parameters are used to control the number of candidate scheduling schemes; a determination module, configured to determine a quality score for each candidate scheduling scheme based on at least one of the loading capacity, transportation route, and cargo category corresponding to the vehicle identifier and the loading rate corresponding to the vehicle identifier in each candidate scheduling scheme; a screening module, configured to determine a target scheduling scheme from the multiple candidate scheduling schemes based on the quality scores of each candidate scheduling scheme; and an optimization module, configured to adjust the target scheduling scheme based on optimization parameters with the objective of maximizing the quality score of the target scheduling scheme, until an optimized vehicle scheduling scheme is obtained, wherein the optimization parameters are used to control the number of optimizations for the target scheduling scheme.

[0014] According to a third aspect of this application, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0015] According to a fourth aspect of this application, a computer-readable storage medium is also provided, on which a computer program or instructions are stored, wherein the computer program or instructions, when executed by a processor, implement the steps of the above-described method.

[0016] According to a fifth aspect of this application, a computer program product is also provided, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0017] The method for determining a vehicle dispatching scheme provided in this application has at least the following advantages compared with related technologies:

[0018] With the goal of maximizing loading capacity and minimizing the total number of vehicle identifiers, the vehicle identifiers corresponding to multiple cargo information are adjusted based on scheduling parameters. Considering transportation routes and cargo categories, preliminary candidate scheduling schemes are generated, providing diverse basic schemes that meet the practical application requirements of transportation routes and cargo categories for subsequent steps. Then, a comprehensive quantitative evaluation of the candidate scheduling schemes is conducted using a quality score that comprehensively considers at least one of the following: loading capacity, transportation route, and cargo category, as well as loading rate, to improve the accuracy of determining the target scheduling scheme. Finally, based on optimization parameters, the target scheduling scheme is adjusted to obtain the optimized vehicle scheduling scheme, making the final determined scheduling scheme more closely match the actual transportation needs of the vehicles and further improving the effectiveness of the optimized scheduling scheme. Attached Figure Description

[0019] The above-mentioned contents, other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1 The illustration schematically depicts an application scenario of the method, apparatus, device, and medium for determining a vehicle scheduling scheme according to embodiments of this application;

[0021] Figure 2 A flowchart illustrating a method for determining a vehicle dispatching scheme according to an embodiment of this application is shown schematically.

[0022] Figure 3 A flowchart illustrating the process of obtaining multiple cargo information according to an embodiment of this application is shown schematically;

[0023] Figure 4 A flowchart illustrating the process of obtaining multiple second scheduling schemes according to embodiments of this application is shown in the illustration.

[0024] Figure 5 A flowchart illustrating an optimized scheduling scheme according to an embodiment of this application is shown schematically.

[0025] Figure 6 A flowchart illustrating the adjustment and optimization scheduling scheme according to an embodiment of this application is shown schematically.

[0026] Figure 7 A flowchart illustrating the calculation of the probability of change according to an embodiment of this application is shown schematically;

[0027] Figure 8 A flowchart illustrating a processing target scheduling scheme according to an embodiment of this application is shown schematically;

[0028] Figure 9 A flowchart illustrating the calculation of accuracy and stability scores according to embodiments of this application is shown in the illustration.

[0029] Figure 10 This schematic diagram illustrates a structural block diagram of an apparatus for determining a vehicle dispatching scheme according to an embodiment of this application;

[0030] Figure 11 A block diagram schematically illustrates an electronic device suitable for implementing a method for determining a vehicle scheduling scheme according to an embodiment of this application. Detailed Implementation

[0031] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0032] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0033] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0034] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0035] In complex business scenarios, to ensure delivery efficiency, it is necessary to find the optimal vehicle scheduling scheme for the goods to be transported. In other words, it is necessary to solve the goods-vehicle allocation combination optimization problem under multiple constraints and objectives.

[0036] In related technologies, a widely used approach is for warehouse personnel to manually assign vehicles to transport goods based on the shipping plan. However, this process lacks automation support and is difficult to efficiently match the demand for goods and vehicles. At the same time, it is difficult to balance compliance with multiple constraints and optimization requirements with multiple objectives, which can easily lead to mismatch, overloading, and other problems, resulting in waste of vehicle resources and high transportation costs.

[0037] With the development of technology, common optimization algorithms are also being applied to generate vehicle scheduling schemes. These algorithms can include descending best-fit algorithms, greedy-backtracking hybrid algorithms, genetic algorithms, and simulated annealing algorithms, but most are practical applications of optimization algorithms without considering the business characteristics of the actual application scenario, thus the effectiveness of the scheduling schemes needs to be improved. Specifically:

[0038] In the descending best-fit algorithm, goods are arranged in descending order of weight or quantity, prioritizing the processing of heavier or more numerous goods. For each goods, a vehicle with the smallest remaining space is selected to accommodate it, filling the space as much as possible. However, when the proportion of lighter goods is high, a large number of vehicles with low loading rates are likely to occur, making it impossible to correct the allocation errors of heavier goods in the early stages; the global optimization capability is weak, and the number of vehicles usually differs from the theoretical optimal solution.

[0039] In the greedy-backtracking hybrid algorithm, an initial plan is first generated using a descending best-fit algorithm. Then, vehicles with low loading rates are screened, and their cargo is backtracked to other vehicles on the same route. Empty vehicle optimization results are deleted. However, it can only locally optimize inefficient vehicles and cannot adjust the core allocation decisions for heavy cargo in the early stages. The backtracking depth is limited, and it is still prone to getting trapped in local optima, resulting in unstable optimization effects.

[0040] Genetic algorithms use operations such as general selection, crossover, and mutation to iteratively optimize and generate compliant scheduling schemes. However, their local optimization capabilities are weak; relying solely on mutation operations makes it difficult to finely adjust vehicles with low loading rates, and they are prone to getting trapped in local optima. Furthermore, they are parameter-sensitive and require manual tuning, resulting in high adaptation and maintenance costs. Crossover operations, using single-point / two-point crossover methods, may lead to the mixing of different types of goods.

[0041] In simulated annealing, an initial solution (i.e., an initial scheduling scheme) is first randomly generated, and then the initial solution is optimized by combining a general neighborhood operation (random swap / insertion) with the Metropolis acceptance criterion. However, its global search energy is poor, the quality of the initial solution directly determines the final result, and it is easy to miss the globally optimal solution when randomly generating the initial solution; using only a single neighborhood operation, parameters such as initial temperature and cooling rate need to be manually adjusted, and the adaptability to different scenarios is poor, resulting in high maintenance costs for algorithm developers and an inability to form a virtuous cycle for the project.

[0042] To address at least one of the aforementioned problems, embodiments of this application provide a method for determining a vehicle scheduling scheme. The method aims to maximize the loading capacity corresponding to each of multiple vehicle identifiers in the desired scheduling scheme and minimize the total number of vehicle identifiers corresponding to the desired scheduling scheme. Based on the transportation routes and cargo categories of each cargo information, the method adjusts the vehicle identifiers corresponding to each cargo information based on scheduling parameters. Considering transportation routes and cargo categories, candidate scheduling schemes are initially generated, providing diverse basic schemes that meet the practical application requirements of transportation routes and cargo categories for subsequent steps. Then, a quality score that comprehensively considers at least one of loading capacity, transportation routes, and cargo categories, as well as the loading rate, is used to comprehensively and quantitatively evaluate the candidate scheduling schemes, improving the accuracy of determining the target scheduling scheme. Finally, with the goal of maximizing the quality score of the target scheduling scheme, the target scheduling scheme is adjusted based on optimization parameters to obtain an optimized vehicle scheduling scheme, further improving the effectiveness of the optimized scheduling scheme.

[0043] Figure 1 The diagram illustrates an application scenario of a method for determining a vehicle dispatching scheme according to an embodiment of this application. Figure 1 As shown, application scenario 100 according to an embodiment of this application may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables. For example, a user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send information, etc.

[0044] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be electronic devices such as smartphones, wearable devices, personal computers, intelligent voice interaction devices, smart home appliances, intelligent vehicles, in-vehicle terminals, aircraft, unmanned vending terminals, and extended reality devices. Extended reality devices can include virtual reality devices, augmented reality devices, and mixed reality devices. A client application for the target application can be installed and run on the terminal devices. This target application can include, but is not limited to, financial transaction applications, payment applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, and social media platform software (these are just examples). Furthermore, this application embodiment does not limit the form of the target application, and it can include, but is not limited to, applications, mini-programs, etc., installed on the terminal devices, and can also be in the form of web pages.

[0045] Server 105 can be a server providing various services, such as a backend management server supporting websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process received user requests and other data, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services such as cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and basic cloud computing services such as big data. The server can be the backend server of the aforementioned target application, used to provide backend services to the clients of the target application.

[0046] It should be noted that the method for determining a vehicle dispatching scheme provided in this application embodiment can generally be executed by server 105 and / or terminal devices 101-103. Accordingly, the vehicle dispatching device provided in this application embodiment can generally be set in server 105 and / or terminal devices 101-103.

[0047] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0048] Figure 2 A flowchart illustrating a method for determining a vehicle scheduling scheme according to an embodiment of this application is shown schematically.

[0049] like Figure 2 As shown, the method 200 for determining a vehicle dispatching scheme according to an embodiment of this application may include steps S210 to S240.

[0050] In step S210, in response to receiving multiple cargo information, with the goal of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, the vehicle identifiers corresponding to each cargo information are adjusted based on the transportation route and cargo category of each cargo information according to the scheduling parameters until multiple candidate scheduling schemes are obtained.

[0051] According to embodiments of this application, cargo information may refer to relevant information about the cargo to be transported, such as weight, volume, production stage, packaging method, etc.; each cargo information has a corresponding transportation route and cargo category. The transportation route may include a railway transportation route, a multimodal transport route, etc., and the cargo category may include completed production, incomplete production, shipped domestically, and shipped internationally, etc.

[0052] Vehicle identifiers represent vehicles and can be vehicle numbers, vehicle codes, etc. Candidate scheduling schemes can include multiple vehicle identifiers, each corresponding to a load capacity, load rate, transport route, and cargo category. Specifically, candidate scheduling schemes can indicate the mapping relationship between each vehicle identifier and its corresponding cargo information. That is, each vehicle identifier corresponds to cargo information associated with that vehicle identifier; the cargo represented by this cargo information is the cargo that the vehicle represented by that vehicle identifier needs to load; and the transport route and cargo category corresponding to this cargo information are the transport route and cargo category corresponding to that candidate vehicle.

[0053] Load capacity can refer to the required capacity of the cargo information associated with a vehicle identifier. Load rate can refer to the ratio of the required capacity of the cargo information associated with a vehicle identifier to the maximum load capacity of the vehicle represented by that vehicle identifier. Scheduling parameters are used to control the number of multiple candidate scheduling schemes; for example, scheduling parameters may include the number of candidate scheduling schemes.

[0054] For example, step S210 may include: sequentially assigning cargo information with the same transportation route to at least one randomly generated vehicle identifier according to cargo category, with the goal of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, to form a candidate scheduling scheme; until the number of candidate scheduling schemes reaches the requirements of the scheduling parameters, multiple candidate scheduling schemes are obtained.

[0055] In step S220, the quality score of each candidate scheduling scheme is determined based on at least one of the following: the loading amount corresponding to the vehicle identifier, the transportation route, and the cargo category, as well as the loading rate corresponding to the vehicle identifier.

[0056] Further, step S220 may include: First, according to preset scoring rules, converting at least one of the following factors in each candidate scheduling scheme: the loading amount, transportation route, cargo category, and loading rate corresponding to the vehicle identifier, into a quality score for each candidate scheduling scheme.

[0057] For example, the scoring rules indicate at least one of the following: load capacity, transport route, cargo category, and the conversion relationship between load rate and quality score. For instance, the scoring rules could include: a higher load rate results in a higher quality score; a lower quality score is awarded when the load capacity exceeds the maximum load capacity; a lower quality score is awarded when the candidate vehicle has more than two cargo categories; and a lower quality score is awarded when the vehicle type does not match the transport route.

[0058] In step S230, the target scheduling scheme is determined from multiple candidate scheduling schemes based on the quality scores of each candidate scheduling scheme.

[0059] For example, the candidate scheduling schemes are sorted in descending order of their average quality, and the candidate scheduling scheme ranked first is taken as the target scheduling scheme.

[0060] In step S240, with the goal of maximizing the quality score of the target scheduling scheme, the target scheduling scheme is adjusted based on the optimization parameters until an optimized scheduling scheme for vehicles is obtained.

[0061] According to an embodiment of this application, the optimization parameters are used to control the number of adjustments made to the target scheduling scheme.

[0062] For example, step S240 may include: adjusting the vehicle identifiers in the target scheduling scheme that are the same in terms of both transportation routes and cargo categories, with the goal of maximizing the quality score of the target scheduling scheme; repeating the above steps until the number of adjustments is reached, and using the updated target scheduling scheme as the optimal scheduling scheme.

[0063] In the embodiments of this application, with the goal of maximizing loading capacity and minimizing the total number of vehicle identifiers, the vehicle identifiers corresponding to multiple cargo information are adjusted based on scheduling parameters. Taking into account transportation routes and cargo categories, preliminary candidate scheduling schemes are generated, providing diverse basic schemes that meet the practical application requirements of transportation routes and cargo categories for subsequent steps. Then, a comprehensive quantitative evaluation of the candidate scheduling schemes is performed using a quality score that comprehensively considers at least one of loading capacity, transportation routes, and cargo categories, as well as loading rate, to improve the accuracy of determining the target scheduling scheme. Finally, based on optimization parameters, the target scheduling scheme is adjusted to obtain the optimized vehicle scheduling scheme, further improving the effectiveness of the optimized scheduling scheme.

[0064] In some embodiments, determining the quality score of each candidate scheduling scheme includes performing the following operations for each candidate scheduling scheme:

[0065] First, the loading score is obtained by summing the loading scores corresponding to the loading rates of multiple vehicle identifiers.

[0066] Furthermore, firstly, based on the preset loading score conversion rules, the loading rates corresponding to multiple vehicle identifiers are converted into multiple loading scores, and the sum of the multiple loading scores is used as the loading score of the candidate scheduling scheme.

[0067] Taking the number of vehicle identifiers as P (P is a positive integer greater than 1) as an example, the loading score conversion rule may include: First, sort the P vehicle identifiers in descending order according to their corresponding loading rates; then, for the first P-1 vehicle identifiers, if the loading amount corresponding to the vehicle identifier is greater than a preset first threshold, the loading score corresponding to the vehicle identifier is = loading rate × 5 + 10, otherwise, the loading score corresponding to the vehicle identifier is = loading rate × 3; for the Pth vehicle identifier, the loading score corresponding to the vehicle identifier is = loading rate × 0.5.

[0068] For example, the preset first threshold can be 98%. Loading score of candidate scheduling schemes. It can be represented as:

[0069] ;

[0070] In the formula, Indicates the transportation route. This indicates the number of vehicle identification marks within transport route L. This indicates the result of sorting vehicle identification numbers within transport route L by loading rate. Vehicle identification Loading rate.

[0071] Then, at least one of the vehicle score, constraint score, and overload score is fused with the loading score to obtain the quality score of the candidate scheduling scheme.

[0072] According to an embodiment of this application, the vehicle score is obtained based on the total number of vehicle identifiers, the constraint score is obtained based on at least one of the following: the number of cargo categories corresponding to each vehicle identifier, the degree of deviation between the vehicle type corresponding to each vehicle identifier and the reference vehicle type, the degree of deviation between the loading amount corresponding to each vehicle identifier and the preset loading amount threshold, and the number of vehicle types corresponding to each transport route. The overload score is obtained based on vehicle identifiers whose loading amount is greater than the loading amount threshold.

[0073] Furthermore, the vehicle score can be obtained by multiplying the total number of vehicle identifiers by a preset first multiple. The constraint score can be obtained by multiplying the number of violations by a preset second multiple. Here, the number of violations can include: the number of times the number of cargo categories corresponding to each vehicle identifier exceeds a preset first value, the number of times the vehicle model is different from the reference vehicle model, the number of times the load corresponding to each vehicle identifier exceeds a preset load threshold, and the number of times vehicle identifiers on the same transport route correspond to more than two vehicle models. The overload score can be obtained by multiplying the overload amount corresponding to the vehicle identifier whose load exceeds the load threshold by a preset third multiple. Here, the preset first multiple can be -4, the preset second multiple can be -20, the preset third multiple can be -100, the load threshold can be the maximum load corresponding to the vehicle identifier, the preset first value can be 2, and the overload amount can be the difference between the load corresponding to the vehicle identifier and the load threshold.

[0074] For example, the vehicle score, constraint score, and overload score are fused with the loading score to obtain a quality score for the candidate scheduling scheme.

[0075] Vehicle Scoring It can be represented as:

[0076] ;

[0077] Constraint Scores It can be represented as:

[0078] ;

[0079] Overload score It can be represented as:

[0080] ;

[0081] The quality score F(S) can be expressed as:

[0082] F(S) = S load +P v +P c +P o ;

[0083] In the formula, 'a' represents the total number of vehicle identification numbers. This indicates the number of times the quantity of a goods category exceeds a preset first value. This indicates the number of times the vehicle model differs from the reference vehicle model. This indicates the number of times the loaded capacity exceeds a preset loading capacity threshold. This indicates the number of times that vehicle identification marks on the same transport route correspond to more than two different vehicle types.

[0084] Based on this, "loading rate" is taken as the positive core, while "number of vehicles, constraint of violations, and overloading" are used as negative penalty items. This approach emphasizes loading efficiency while enforcing compliance, avoiding optimization bias caused by a single indicator. Quality scores are used to reflect the generation quality of corresponding candidate scheduling schemes in dimensions such as loading capacity and total number of vehicle identifiers.

[0085] In the embodiments of this application, a quantitative index system is established by comprehensively considering loading score, vehicle score, constraint score and overload score, and comprehensively evaluating information such as the number of vehicle identifiers, loading rate and compliance of the scheduling scheme, so as to provide an objective standard for judging the merits of the scheduling scheme.

[0086] In the embodiments of this application, the generation of scheduling schemes cannot violate preset constraints. Violation of constraints means that a constraint penalty must be imposed when calculating the quality score. The calculation of the aforementioned constraint score corresponds to the constraints in the embodiments of this application. During the execution of the method in the embodiments of this application, all scheduling schemes must satisfy the following constraints:

[0087] Constraint 1: The cargo orders in the cargo information can only be loaded by the specified vehicle type of the transportation route corresponding to the order. For example, a certain railway transportation route only allows vehicle type 1, and a certain intermodal transportation route only allows vehicle type 2.

[0088] Constraint 2: The same vehicle identifier can only be associated with goods orders of the same goods category.

[0089] Constraint 3: The load capacity corresponding to the vehicle identification cannot exceed the maximum load capacity corresponding to that vehicle identification.

[0090] Constraint 4: A maximum of two vehicle types may be used on the same transport route.

[0091] Figure 3 A flowchart illustrating the process of obtaining multiple cargo information according to an embodiment of this application is shown schematically.

[0092] To ensure that the data used for vehicle dispatching conforms to the processing logic for dispatching scheme generation and optimization, the acquired cargo data needs to be converted into multiple cargo information items before executing step S210. Next, combined with... Figure 3 The process for obtaining information on multiple goods will be further explained.

[0093] In the embodiments of this application, multiple cargo information items are obtained using the following methods:

[0094] First, the acquired cargo data is preprocessed according to preset conversion rules.

[0095] According to embodiments of this application, the goods data may include multiple purchase order information; each purchase order information may include a purchase order number and a goods order number (LOT). id ), transportation line, production stage identifier (kr) flag ), delivery address identifier (PRC9) flag Volumetric information, etc., can include the goods data and corresponding volume data (such as packaging height) and material data for each purchase order.

[0096] For example, the production stage identifier can include a K identifier, an R identifier, a HOLD identifier, and no identifier. A K identifier indicates that the purchase order has completed production on the production line and passed the barcode scan; an R identifier indicates that the purchase order has been generated on the production line and packaged; a HOLD identifier indicates that production of the purchase order is temporarily suspended; and no identifier indicates that the production stage identifier is blank. The delivery address identifier can be a PRC9 identifier. If the purchase order is shipped domestically and its packaging method is full-stack packaging, PRC9=T; otherwise, PRC9=F.

[0097] It should be noted that a single purchase order can only be in one production stage at any given time, and cannot simultaneously have multiple markings such as K, R, HOLD, etc. K or R markings can be mixed but cannot be mixed with other markings.

[0098] In logistics and transportation operations, multiple purchase orders with the same attributes can be linked together as a single goods order, such as the same shipping date, the same route, the same carrier, or the same customer. Therefore, purchase orders within the same goods order have the same goods order number.

[0099] For example, the conversion rules may include: if the packaging height of the goods is greater than 130 cm, the required capacity of the goods is calculated as 2 truck pallets; if the packaging height of the goods is greater than 70 cm but less than 130 cm, the required capacity of the goods is calculated as 1 truck pallet; and if the packaging height of the goods is less than 70 cm, the required capacity of the goods is calculated as 0.5 truck pallets.

[0100] Here, "truck pallet" can refer to a unit used in logistics and transportation to measure truck capacity. The required capacity of goods can also be expressed in terms of pallets. For example, a pallet with a height greater than 130 cm is counted as 2 truck pallets, a pallet with a height greater than 70 cm but less than 130 cm is counted as 1 truck pallet, and a pallet with a height less than 70 cm is counted as 0.5 truck pallets.

[0101] Then, for each goods order, the number of truck pallets, production stage identifier, and delivery address identifier are summarized according to the goods order number to determine the total number of truck pallets, production stage identifier, and delivery address identifier for each goods order.

[0102] For example, for each goods order, the sum of the number of truck pallets corresponding to all purchase orders in the goods order is taken as the total number of truck pallets (qty) corresponding to that goods order. If all purchase orders in the goods order have a production stage identifier of K, the goods order is identified as having a production stage identifier of K; if all purchase orders in the goods order have a production stage identifier of R, the goods order is identified as having a production stage identifier of R; if at least one purchase order in the goods order has a production stage identifier of HOLD, the goods order is identified as having a production stage identifier of HOLD. If all purchase orders in the goods order have a receiving address identifier of "PRC9=T", the goods order is marked as "PRC9=T"; otherwise, the goods order is marked as "PRC9=F".

[0103] Here, the relevant information for a Goods Order (LOT) can be represented as: LOT(line="Line A", LOT) id =="LOT1",qty=12.31,prc9 flag =="T",kr flag =="K"

[0104] Then, the multiple goods orders are grouped to obtain multiple goods information.

[0105] Furthermore, firstly, all freight orders are iterated through. Based on the transportation routes of the freight orders (e.g., route A, route B, route C), freight orders along the same transportation route are grouped into the same route group. For each route group, only freight orders that meet the route-vehicle type constraint are retained, excluding invalid freight orders that do not match a transportation route. Then, each route group is iterated through, and based on the production stage identifier and delivery address identifier of the freight order, the freight category of the freight order is determined according to a preset judgment rule. Then, for each freight category, its corresponding freight orders are sorted in descending order of freight quantity to prioritize the allocation of freight orders with larger quantities in subsequent allocations, thereby improving vehicle utilization. Here, the freight orders grouped by transportation route and freight category constitute the freight information.

[0106] For example, a line-vehicle constraint can refer to a transport route and the types of vehicles that can be used on that route. types The correspondence between them, for example, LineVehicle(line="Line A", vehicle) types =["Model 1"]).

[0107] The judgment rules may include: in kr flag ∈['K','R'] and prc9 flag In the case of "="T", the goods category is Category 1; in kr flag ∈['K','R'] and prc9 flag In the case of ="F", the goods category is Category 2; in kr flag ∉['K','R']and prc9 flag In the case of "="T", the goods category is category 3; in kr flag ∉['K','R']and prc9 flag In the case of "="F, the goods category is Category 4.

[0108] In some embodiments, the scheduling parameters include a baseline number of the first scheduling scheme; with the goal of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, the vehicle identifiers corresponding to each cargo information are adjusted based on the transportation route and cargo category of each cargo information according to the scheduling parameters, until multiple candidate scheduling schemes are obtained, including:

[0109] First, in response to receiving N cargo information, perform the following operations until the number of first scheduling schemes reaches a baseline quantity, resulting in multiple first scheduling schemes: determine the vehicle identifier that matches the transportation route and cargo category of the cargo order in the N cargo information, where N is an integer greater than 1; and, if the loading capacity corresponding to the vehicle identifier is less than or equal to a preset loading capacity threshold, obtain a first scheduling scheme.

[0110] In the embodiments of this application, to avoid cross-category mixing from the source of scheme generation, vehicle identification is determined considering the cargo category; simultaneously, to avoid selecting vehicle types that are not permitted to operate on the transportation route, vehicle identification is allocated in conjunction with the transportation route, preventing the vehicle scheduling scheme from being ineffective in practical applications and defining compliance boundaries for subsequent optimization. Cargo information can be cargo orders grouped according to transportation routes and cargo categories.

[0111] For example, firstly, multiple cargo orders, a dictionary of vehicle types allowed for a route, and data on the maximum load capacity of each vehicle type are obtained. Here, the dictionary of vehicle types allowed for a route includes vehicle types allowed to run on multiple transportation routes, and data on the maximum load capacity of each vehicle type includes the maximum load capacity corresponding to multiple vehicle types. Then, the following operations are performed iteratively on N cargo orders until the number of the first scheduling scheme (also known as an individual) reaches the baseline number: traverse all transportation routes and determine the vehicle types allowed to run on each transportation route; and, for cargo orders in the same route group, perform the following operations on each cargo order with the same cargo category: (1) randomly generate 1 to 10 vehicle identifiers, and randomly select the vehicle type corresponding to the vehicle identifier from the vehicle types allowed to run on the transportation route; (2) sort cargo orders with the same cargo category in descending order of cargo quantity, and attempt to allocate them to existing vehicle identifiers in turn (up to 30 attempts). If the sum of the current load capacity corresponding to the vehicle identifier and the cargo quantity of the order is less than or equal to the maximum load capacity corresponding to the vehicle identifier, the allocation is successful; if the allocation attempts fail 30 times, create a new vehicle identifier associated with the cargo order. Remove empty vehicle identifiers of each cargo category that are not associated with cargo orders.

[0112] Here, the baseline number of the first scheduling scheme can refer to the number of iteration operations performed on N goods orders. The number of iteration operations performed determines the number of first scheduling schemes.

[0113] Then, based on the quality scores of multiple first scheduling schemes, multiple second scheduling schemes are determined from the multiple first scheduling schemes.

[0114] Here, the calculation method for the quality score of the first scheduling scheme is the same as that for the aforementioned candidate scheduling schemes, and will not be repeated here.

[0115] For example, a first scheduling scheme with a quality score greater than a preset score threshold is selected as a second scheduling scheme.

[0116] Then, adjust at least one of the vehicle identifier and cargo order in at least two second scheduling schemes to obtain multiple candidate scheduling schemes.

[0117] For example, with the goal of maximizing the quality score of the second scheduling scheme, the vehicle identifiers or cargo orders in at least two second scheduling schemes are adjusted to obtain multiple candidate scheduling schemes. For example, vehicle identifiers corresponding to the same transportation routes and cargo categories in at least two second scheduling schemes are exchanged.

[0118] In the embodiments of this application, candidate scheduling schemes are generated by considering transportation routes and cargo categories to obtain candidate scheduling schemes that meet constraints such as route-vehicle matching and no overloading. This provides a compliant and diverse basic scheme for subsequent optimization, ensuring the optimization efficiency of subsequent optimization.

[0119] Figure 4 A flowchart illustrating a plurality of second scheduling schemes according to an embodiment of the present application is shown.

[0120] The method of directly selecting a second scheduling scheme from the first scheduling scheme based on quality scores is simplistic and may result in either missed or over-selection, thus having certain limitations. To retain high-quality schemes from multiple first scheduling schemes, maintain scheme diversity, and avoid subsequent operations getting trapped in local optima due to over-selection, thus providing a high-quality foundation for subsequent operations, a second scheduling scheme is selected using quality scores and grouping.

[0121] Next, combined Figure 4 The method for determining multiple second scheduling schemes from multiple first scheduling schemes is explained in detail.

[0122] In some embodiments, determining a plurality of second scheduling schemes 402 from a plurality of first scheduling schemes 401 based on the quality scores of the plurality of first scheduling schemes 401 includes:

[0123] First, based on the quality scores of multiple first scheduling schemes 401, a preset number of second scheduling schemes 402 are selected from the multiple first scheduling schemes 401.

[0124] According to an embodiment of this application, the preset quantity is determined based on the number of first scheduling schemes 401; for example, the preset quantity can be 10% of the number of first scheduling schemes 401, thereby ensuring that high-quality schemes with high quality scores among multiple first scheduling schemes 401 are not lost.

[0125] For example, multiple first scheduling schemes 401 are arranged in descending order of quality score, and a preset number of first scheduling schemes 401 at the top are selected as second scheduling schemes 402 and will not participate in subsequent selections.

[0126] Then, the multiple first scheduling schemes 403 that were not selected are grouped to obtain multiple scheme groups 404.

[0127] For example, the scheduling parameters also include the group size. Multiple unselected first scheduling schemes 403 can be randomly divided into several scheme groups according to the group size. Here, the group size can be: the number of schemes in each scheme group can be 3 to 8.

[0128] Then, the first scheduling scheme with the highest quality score in each scheme group is selected as the second scheduling scheme.

[0129] For example, for each group of schemes, the first scheduling scheme with the highest quality score is selected as the second scheduling scheme.

[0130] Repeat the second and third steps described above in this embodiment until the number of second scheduling schemes is equal to the number of first scheduling schemes, thus obtaining multiple second scheduling schemes.

[0131] Figure 5 A flowchart illustrating an optimized scheduling scheme according to an embodiment of this application is shown. Figure 6 A flowchart illustrating the adjustment and optimization scheduling scheme according to an embodiment of this application is shown.

[0132] In some embodiments, adjusting at least one of the vehicle identifier and cargo order in at least two second scheduling schemes to obtain multiple third scheduling schemes includes:

[0133] First, the vehicle identifiers of vehicles with the same transportation routes and the same cargo categories in at least two second scheduling schemes are exchanged to obtain at least two preferred scheduling schemes.

[0134] Scheduling parameters also include the crossover rate. For example... Figure 5 As shown, further, the following operation is performed on any two of the multiple second scheduling schemes (which can be referred to as parent individuals):

[0135] Step 1: Generate a first random number in the range of (0,1); if the random number is less than or equal to the crossover rate, proceed to Step 2; otherwise, directly use the second scheduling scheme as the preferred scheduling scheme (which can be called the offspring individual), that is, return a copy of the second scheduling scheme as the offspring individual.

[0136] Step 2: Traverse each transportation route and determine whether at least one transportation route corresponding to the two second scheduling schemes is consistent.

[0137] Step 3: For freight orders within the same route group, randomly generate a number "0" or "1" for each corresponding freight category to select the parent source of the optimized scheduling scheme. Specifically, when the number is 0, the vehicle identifier corresponding to that category in the second scheduling scheme 1 is used as the vehicle identifier corresponding to the corresponding freight order in the preferred scheduling scheme 1, and the vehicle identifier corresponding to that category in the second scheduling scheme 2 is used as the vehicle identifier corresponding to the corresponding freight order in the preferred scheduling scheme 2. When the number is 1, the vehicle identifier corresponding to that category in the second scheduling scheme 1 is used as the vehicle identifier corresponding to the corresponding freight order in the preferred scheduling scheme 2, and the vehicle identifier corresponding to that category in the second scheduling scheme 2 is used as the vehicle identifier corresponding to the corresponding freight order in the preferred scheduling scheme 1.

[0138] Step 4: Remove vehicle identifiers (empty vehicle identifiers) from child individuals that are not associated with cargo orders.

[0139] Through the above operations, the source is selected separately for the vehicle identification corresponding to each cargo category, fundamentally avoiding cross-category mixing; at the same time, the exchange frequency is controlled by random numbers and crossover rate to balance the diversity and stability of the scheme update.

[0140] Then, in response to the probability of change of the preferred scheduling scheme relative to the second scheduling scheme being greater than the change threshold, the vehicle identifiers in the preferred scheduling scheme are adjusted to form candidate scheduling schemes with the goal of maximizing the quality score of the preferred scheduling scheme.

[0141] Here, the change threshold can be a second random number in the range of (0,1) that is randomly generated.

[0142] For example, such as Figure 6 As shown, for each preferred scheduling scheme, if its change probability is greater than the change threshold, one transportation route is randomly selected, and one cargo category is randomly selected from the cargo categories corresponding to that transportation route. Cargo orders corresponding to the aforementioned transportation route and cargo category are reassigned through the following operations: First, cargo orders are sorted in descending order of cargo quantity; then, referring to the original number of vehicle identifiers corresponding to that cargo category, [original vehicle identifier count - 1, original vehicle identifier count + 1] vehicle identifiers are randomly generated, and the vehicle type corresponding to these vehicle identifiers is the vehicle type allowed to operate on the aforementioned transportation route; then, each cargo order is successively assigned to the newly generated vehicle identifiers, and if assignment fails, the vehicle identifiers are rebuilt; the original vehicle identifiers corresponding to that category in the preferred scheduling scheme are removed and replaced with the reassigned non-empty vehicle identifiers, completing the adjustment of the preferred scheduling scheme and obtaining the candidate scheduling scheme.

[0143] In the embodiments of this application, the second scheduling scheme is adjusted by considering the cargo category and transportation route to improve the overall quality and diversity of the scheduling scheme, avoid the scheduling scheme from getting stuck in local optima, and provide more potential high-quality schemes for subsequent optimization.

[0144] Figure 7 A flowchart illustrating the calculation of the probability of change according to an embodiment of this application is shown schematically.

[0145] In some embodiments, the scheduling parameters further include a first change threshold 704 and a second change threshold 705. For example... Figure 7 As shown, the change probability 707 is obtained in the following way: based on the degree of deviation between the quality score 701 of the optimized scheduling scheme and the maximum quality score 702 among all optimized scheduling schemes, a relative score 703 is obtained; based on the difference between the first change threshold 704 and the second change threshold 705, the change range is obtained; the first change threshold 704, the relative score 703 and the change range 706 are merged to obtain the change probability 707.

[0146] According to an embodiment of this application, the first change threshold 704 indicates the upper limit of the change probability, and the second change threshold 705 indicates the lower limit of the change probability.

[0147] Furthermore, based on the ratio of the quality score 701 of the optimized scheduling scheme to the maximum quality score 702 among all optimized scheduling schemes, a relative score 703 is obtained; based on the difference between the first change threshold 704 and the second change threshold 705, a change range 706 is obtained; by multiplying the relative score 703 and the change range 706, and based on the difference between the first change threshold 704 and the product, a change probability 707 is obtained.

[0148] For example, the probability of change, mutation rate It can be represented as:

[0149] mutation rate =max mutation-rate -(max mutationrate -min mutation-rate )×(g / g max );

[0150] In the formula, max mutation-rate Min represents the first threshold value for change. mutation-rate This represents the second change threshold, and g represents the quality score of the optimized scheduling scheme. max This represents the highest quality score among all optimized scheduling schemes.

[0151] In the embodiments of this application, in order to avoid the destruction of high-quality solutions due to the adjustment of the optimized scheduling scheme, the quality score of the optimized scheduling scheme is used to calculate the probability of change, and the mutation rate is dynamically adjusted with the individual fitness (the higher the fitness, the lower the mutation rate), which not only prevents the destruction of high-quality solutions, but also provides optimization space for low-fit individuals.

[0152] Figure 8 A flowchart illustrating a processing target scheduling scheme according to an embodiment of this application is shown.

[0153] In some embodiments, the optimization parameters include the baseline number M for adjusting the target scheduling scheme, where M is an integer greater than 1. For example... Figure 8 As shown, with the goal of maximizing the quality score of the target scheduling scheme, the target scheduling scheme is adjusted based on optimization parameters until an optimal vehicle scheduling scheme is obtained, including:

[0154] Using the target scheduling scheme as the first scheduling scheme (initial solution) and the first reference scheduling scheme (optimal solution), perform M adjustment operations. The scheme with the higher quality score among the resulting Mth scheduling scheme and the Mth reference scheduling scheme is selected as the optimized scheduling scheme. The mth adjustment operation includes:

[0155] With the objective of maximizing the quality score of m scheduling schemes (the current solution), the vehicle identifiers for vehicles with the same transportation routes and cargo categories in the m-th scheduling scheme are adjusted to form the m-th intermediate scheduling scheme, where m = 1, ..., M-1. If the quality score of the m-th intermediate scheduling scheme is greater than the quality score of the m-th overall scheduling scheme, or if the acceptance probability of the m-th intermediate scheduling scheme is greater than or equal to a preset probability threshold, the m-th intermediate scheduling scheme is adopted as the (m+1)-th scheduling scheme; if the quality score of the m-th intermediate scheduling scheme is greater than the quality score of the m-th reference scheduling scheme, the m-th intermediate scheduling scheme is adopted as the (m+1)-th reference scheduling scheme.

[0156] Furthermore, if the quality score of the m-th intermediate scheduling scheme is less than or equal to the quality score of the m-th reference scheduling scheme and the acceptance probability of the m-th intermediate scheduling scheme is less than the probability threshold, the m-th scheduling scheme is adopted as the (m+1)-th scheduling scheme. In other words, if the quality score of the adjusted scheduling scheme does not increase and the acceptance probability is less than the probability threshold, the adjustment is not accepted, and the original scheme is used for further adjustment. If the quality score of the m-th intermediate scheduling scheme is less than or equal to the quality score of the m-th reference scheduling scheme, the m-th reference scheduling scheme is adopted as the (m+1)-th reference scheduling scheme. In other words, if the quality score of the adjusted scheduling scheme is less than the optimal solution, the optimal solution is not updated.

[0157] For example, adjusting vehicle identifiers with the same transport route and cargo category in the (m-1)th scheduling scheme can be one of vehicle identifier merging, cargo order reallocation, or vehicle identifier splitting. Vehicle identifier merging can refer to selecting two non-empty vehicle identifiers corresponding to the cargo category, merging them into one if the combined loading capacity is less than or equal to the maximum loading capacity, and then deleting redundant vehicles. Cargo order reallocation can refer to randomly selecting one cargo order from those associated with a non-empty vehicle identifier and reallocating it to another vehicle identifier with the same cargo category, transferring the cargo order if the allocation is successful. Vehicle identifier splitting refers to selecting one cargo order from a vehicle identifier associated with multiple cargo orders and assigning it to a newly added compliant vehicle identifier. Here, M can be 15~45.

[0158] For example, the probability threshold can be a third random number in the range of (0,1) that is randomly generated. The acceptance probability of the m-th intermediate scheduling scheme can be obtained by: based on the quality score of the m-th intermediate scheduling scheme, the quality score of the m-th scheduling scheme, and the m-th current temperature, the acceptance probability of the m-th intermediate scheduling scheme is obtained.

[0159] The optimization parameters also include initial temperature and cooling rate. The initial temperature is the current temperature after the first adjustment operation. After each adjustment operation, temperature decay is required to adjust the acceptance probability of intermediate scheduling schemes. The m-th current temperature = the (m-1)-th current temperature × cooling rate. Here, the initial temperature can be 50~100, and the cooling rate can be 0.92~0.99.

[0160] For example, the acceptance probability P can be expressed as:

[0161] P = exp(Quality score of intermediate scheduling scheme - Quality score of scheduling scheme) / Current temperature).

[0162] In the embodiments of this application, the obtained target scheduling scheme is finely adjusted, and the quality score and acceptance probability are used to determine whether to accept the adjusted scheme. This allows for the acceptance of a small number of non-optimal solutions, avoiding getting trapped in local optima, and further improving the loading rate and reducing the number of vehicles.

[0163] Figure 9 A flowchart illustrating the calculation of accuracy and stability scores according to embodiments of this application is shown.

[0164] In some embodiments, the scheduling parameters and optimization parameters are obtained using the following method:

[0165] First, determine multiple initial scheduling parameters 901 and multiple initial optimization parameters 902.

[0166] For example, multiple initial scheduling parameters and multiple initial optimization parameters are randomly generated based on the value ranges of the initial scheduling parameters and initial optimization parameters, such as three. The initial scheduling parameters may include the baseline number of candidate scheduling schemes (also known as population size), crossover rate, first change threshold, second change threshold, scheme group size, etc. The initial optimization parameters may include the initial temperature, cooling rate, and number of iterations, etc. The population size can range from 50 to 150, and the crossover rate can range from 0.8 to 0.9. For ease of description, the initial scheduling parameters and initial optimization parameters will be collectively referred to as initial control parameters.

[0167] Then, as Figure 9 As shown, each initial scheduling parameter 901 and each initial optimization parameter 902 are input into the prediction model 903 to obtain multiple accuracy scores 904 and multiple stability scores 905.

[0168] According to an embodiment of this application, the prediction model 903 is obtained by pre-training using historical scheduling parameters, historical optimization parameters, and corresponding accuracy and stability score labels.

[0169] In embodiments of this application, the prediction model 903 can be a Bayesian-optimized Gaussian process model. The objective function of the Gaussian process model is... It can be represented as:

[0170] ;

[0171] In the formula, Indicates control parameters The corresponding optimized scheduling scheme, Indicates control parameters The quality score of the corresponding optimized scheduling scheme.

[0172] For example, firstly, three sets of initial control parameters are randomly selected. Using steps S210 to S240 and existing cargo data, the quality score of the corresponding optimized scheduling scheme, i.e., the objective function value, is obtained, and the Gaussian process model is initialized. Then, 10 iterative searches are performed. Each search specifically includes: inputting the initial control parameters into the prediction model for processing to obtain the predicted target value (predicted mean) and predicted variance of the objective function. The predicted target value is used as the accuracy score, and the predicted variance is used as the stability score.

[0173] Then, based on multiple accuracy scores 904 and multiple stability scores 905, multiple candidate scheduling parameters are determined from multiple initial scheduling parameters 901, and multiple candidate optimization parameters are determined from multiple initial optimization parameters 902.

[0174] In the embodiments of this application, initial scheduling parameters 901 and initial optimization parameters 902 with high accuracy scores (904) and stability scores (905) are preferentially selected. A higher accuracy score (904) corresponds to higher accuracy of the parameter. A higher stability score (905) corresponds to higher uncertainty of the parameter. To find the globally optimal parameters with the fewest iterations, sufficient exploration is required to avoid local optima. Selecting parameters with high uncertainty balances utilization and exploration in the Bayesian optimization process.

[0175] For example, the accuracy score 904 and the stability score 905 can be weighted as the comprehensive score of the corresponding initial scheduling parameter 901 and initial optimization parameter 902, and the initial scheduling parameter 901 and initial optimization parameter 902 with a comprehensive score greater than a preset comprehensive score threshold can be used as candidate scheduling parameters and candidate optimization parameters.

[0176] Then, multiple candidate optimized scheduling schemes corresponding to multiple candidate scheduling parameters and multiple candidate optimization parameters are determined. Based on the quality scores of multiple candidate optimized scheduling schemes, the target optimized scheduling scheme is determined from the multiple candidate optimized scheduling schemes. The candidate scheduling parameters corresponding to the target optimized scheduling scheme are used as scheduling parameters, and the candidate optimization parameters corresponding to the target optimized scheduling scheme are used as optimization parameters.

[0177] In the embodiments of this application, multiple candidate optimized scheduling schemes corresponding to multiple candidate scheduling parameters and multiple candidate optimization parameters are determined using the aforementioned steps S210 to S240. The candidate optimized scheduling scheme with the highest quality score among the multiple candidate optimized scheduling schemes is selected as the target optimized scheduling scheme. The candidate scheduling parameters corresponding to the target optimized scheduling scheme are selected as scheduling parameters, and the candidate optimization parameters corresponding to the target optimized scheduling scheme are selected as optimization parameters.

[0178] In the embodiments of this application, the scheduling parameters and optimization parameters are optimized and solved using a Bayesian optimized Gaussian process model, eliminating the need for manual parameter tuning and improving the efficiency of adjusting the scheduling parameters and optimization parameters under different business scenarios.

[0179] Based on the above-described method for determining a vehicle dispatching plan, embodiments of this application also provide an apparatus for determining a vehicle dispatching plan. The following will be combined with... Figure 10 The device is described in detail.

[0180] Figure 10 A schematic block diagram of an apparatus for determining a vehicle scheduling scheme according to an embodiment of this application is shown.

[0181] like Figure 10 As shown, the device 1000 for determining vehicle scheduling schemes in this embodiment includes a scheme generation module 1010, a determination module 1020, a filtering module 1030, and an optimization module 1040.

[0182] The first determining module 1010 is used to respond to receiving multiple cargo information and, with the objective of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, adjusts the vehicle identifiers corresponding to each cargo information based on the transportation route and cargo category of each cargo information according to scheduling parameters until multiple candidate scheduling schemes are obtained. The scheduling parameters are used to control the number of candidate scheduling schemes. In one embodiment, the scheme generation module 1010 can be used to execute step S210 described above, which will not be repeated here.

[0183] The determining module 1020 is used to determine the quality score of each candidate scheduling scheme based on at least one of the following: the loading amount corresponding to the vehicle identifier, the transportation route, and the cargo category, as well as the loading rate corresponding to the vehicle identifier. In one embodiment, the determining module 1020 can be used to perform step S220 described above, which will not be repeated here.

[0184] The filtering module 1030 is used to determine the target scheduling scheme from multiple candidate scheduling schemes based on the quality scores of each candidate scheduling scheme. In one embodiment, the filtering module 1030 can be used to perform step S230 described above, which will not be repeated here.

[0185] The optimization module 1040 is used to adjust the target scheduling scheme based on optimization parameters with the goal of maximizing the quality score of the target scheduling scheme, until an optimized scheduling scheme for vehicles is obtained. The optimization parameters are used to control the number of optimizations for the target scheduling scheme. In one embodiment, the optimization module 1040 can be used to execute step S240 described above, which will not be repeated here.

[0186] According to an embodiment of this application, the scheduling parameters include a baseline number of first scheduling schemes; the scheme generation module 1010 is specifically used to respond to receiving N cargo information and perform the following operations until the number of first scheduling schemes reaches the baseline number, thereby obtaining multiple first scheduling schemes: determining a vehicle identifier that matches the transportation route and cargo category of the cargo order in the N cargo information, where N is an integer greater than 1; and obtaining a first scheduling scheme when the loading capacity corresponding to the vehicle identifier is less than or equal to a preset loading capacity threshold; determining multiple second scheduling schemes from the multiple first scheduling schemes based on the quality scores of the multiple first scheduling schemes; and adjusting at least one of the vehicle identifier and cargo order in at least two second scheduling schemes to obtain multiple candidate scheduling schemes.

[0187] According to an embodiment of this application, determining a plurality of second scheduling schemes from a plurality of first scheduling schemes based on the quality scores of a plurality of first scheduling schemes includes: selecting a preset number of second scheduling schemes from the plurality of first scheduling schemes based on the quality scores of the plurality of first scheduling schemes, wherein the preset number is determined according to the number of first scheduling schemes; grouping the plurality of first scheduling schemes that are not selected to obtain a plurality of scheme groups; and taking the first scheduling scheme with the highest quality score in each scheme group as the second scheduling scheme.

[0188] According to an embodiment of this application, adjusting at least one of the vehicle identifier and the cargo order in at least two second scheduling schemes to obtain multiple candidate scheduling schemes includes: exchanging vehicle identifiers with the same transportation route and the same cargo category in at least two second scheduling schemes to obtain at least two preferred scheduling schemes; in response to the probability of change of the preferred scheduling scheme relative to the second scheduling scheme being greater than the change threshold, adjusting the vehicle identifiers in the preferred scheduling scheme with the goal of maximizing the quality score of the preferred scheduling scheme to form candidate scheduling schemes.

[0189] According to an embodiment of this application, the scheduling parameters further include a first change threshold and a second change threshold. The change probability is obtained by: obtaining a relative score based on the deviation between the quality score of the optimized scheduling scheme and the maximum quality score among all optimized scheduling schemes; obtaining a change range based on the difference between the first change threshold and the second change threshold, where the first change threshold indicates the upper limit of the change probability and the second change threshold indicates the lower limit of the change probability; and fusing the first change threshold, the relative score, and the change range to obtain the change probability.

[0190] According to an embodiment of this application, the optimization module 1040 includes a determination submodule, which is used to take the target scheduling scheme as the first scheduling scheme and the first reference scheduling scheme, perform M adjustment operations, and take the scheme with the higher quality score among the obtained Mth scheduling scheme and the Mth reference scheduling scheme as the optimized scheduling scheme. The mth adjustment operation includes: taking the maximization of the quality score of the m scheduling schemes as the objective, adjusting the vehicle identifiers with the same transportation route and the same cargo category in the mth scheduling scheme to form the mth intermediate scheduling scheme, m=1,...,M-1; if the quality score of the mth intermediate scheduling scheme is greater than the quality score of the mth scheduling scheme or the acceptance probability of the mth intermediate scheduling scheme is greater than or equal to a preset probability threshold, the mth intermediate scheduling scheme is taken as the m+1th scheduling scheme; if the quality score of the mth intermediate scheduling scheme is greater than the quality score of the mth reference scheduling scheme, the mth intermediate scheduling scheme is taken as the m+1th reference scheduling scheme.

[0191] According to an embodiment of this application, the screening module 1030 is specifically used to obtain a loading score by summing the loading scores represented by the loading rates corresponding to multiple vehicle identifiers; and to fuse at least one of the vehicle score, constraint score, and overload score with the loading score to obtain a quality score for the candidate scheduling scheme; wherein, the vehicle score is obtained based on the total number of vehicle identifiers, the constraint score is obtained based on at least one of the following: the number of cargo categories corresponding to each vehicle identifier, the degree of deviation between the vehicle type corresponding to each vehicle identifier and the reference vehicle type, the degree of deviation between the loading amount corresponding to each vehicle identifier and the preset loading amount threshold, and the number of vehicle types corresponding to each transportation route; and the overload score is obtained based on vehicle identifiers whose loading amount is greater than the loading amount threshold.

[0192] According to embodiments of this application, scheduling parameters and optimization parameters are obtained in the following manner: determining multiple initial scheduling parameters and multiple initial optimization parameters; inputting each initial scheduling parameter and each initial optimization parameter into a prediction model to obtain multiple accuracy scores and multiple stability scores, wherein the prediction model is pre-trained using historical scheduling parameters, historical optimization parameters, and corresponding accuracy score labels and stability score labels; determining multiple candidate scheduling parameters from the multiple initial scheduling parameters and multiple candidate optimization parameters based on the multiple accuracy scores and multiple stability scores; determining multiple candidate optimized scheduling schemes corresponding to the multiple candidate scheduling parameters and multiple candidate optimization parameters; determining a target optimized scheduling scheme from the multiple candidate optimized scheduling schemes based on the quality scores of the multiple candidate optimized scheduling schemes; and using the candidate scheduling parameters corresponding to the target optimized scheduling scheme as scheduling parameters and the candidate optimization parameters corresponding to the target optimized scheduling scheme as optimization parameters.

[0193] According to embodiments of this application, any multiple modules among the scheme generation module 1010, determination module 1020, screening module 1030, and optimization module 1040 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this application, at least one of the scheme generation module 1010, determination module 1020, screening module 1030, and optimization module 1040 can be at least partially implemented as hardware circuitry, such as field-programmable gate arrays, programmable logic arrays, systems-on-a-chip, systems-on-a-substrate, systems-on-package, application-specific integrated circuits, or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the scheme generation module 1010, determination module 1020, filtering module 1030 and optimization module 1040 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0194] Figure 11 A block diagram schematically illustrates an electronic device suitable for implementing a method for determining a vehicle scheduling scheme according to an embodiment of this application.

[0195] like Figure 11 As shown, an electronic device 1100 according to an embodiment of this application includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory 1102 or a program loaded from a storage portion 1108 into a random access memory 1103. The processor 1101 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a dedicated microprocessor. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for executing different steps of the method flow according to an embodiment of this application.

[0196] Random access memory 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, read-only memory 1102, and random access memory 1103 are interconnected via bus 1104. Processor 1101 executes various steps of the method flow according to embodiments of this application by executing programs in read-only memory 1102 and / or random access memory 1103. It should be noted that the programs may also be stored in one or more memories other than read-only memory 1102 and random access memory 1103. Processor 1101 may also execute various steps of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0197] According to embodiments of this application, the electronic device 1100 may further include an input / output interface 1105, which is also connected to a bus 1104. The electronic device 1100 may also include one or more of the following components connected to the input / output interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube, liquid crystal display, etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the input / output interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0198] Embodiments of this application also provide a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0199] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include the read-only memory 1102, and / or random access memory 1103, and / or one or more memories other than read-only memory 1102 and random access memory 1103 described above.

[0200] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this application.

[0201] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1109, and / or installed from the removable medium 1111. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0202] In embodiments of this application, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by processor 1101, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0203] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0204] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0205] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

Claims

1. A method for determining a vehicle dispatching scheme, characterized in that, The method includes: In response to receiving multiple cargo information, with the goal of maximizing the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimizing the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, the vehicle identifiers corresponding to each cargo information are adjusted based on the transportation route and cargo category of each cargo information according to the scheduling parameters until multiple candidate scheduling schemes are obtained. The scheduling parameters are used to control the number of candidate scheduling schemes. The quality score of each candidate scheduling scheme is determined based on at least one of the loading amount, transportation route and cargo category corresponding to the vehicle identifier and the loading rate corresponding to the vehicle identifier in each candidate scheduling scheme. Based on the quality scores of each candidate scheduling scheme, a target scheduling scheme is determined from multiple candidate scheduling schemes; With the goal of maximizing the quality score of the target scheduling scheme, the target scheduling scheme is adjusted based on optimization parameters until an optimized vehicle scheduling scheme is obtained. The optimization parameters are used to control the number of adjustments to the target scheduling scheme.

2. The method for determining a vehicle dispatching scheme according to claim 1, characterized in that, The scheduling parameters include the baseline quantity of the first scheduling scheme; the objective is to maximize the loading capacity corresponding to each of the multiple vehicle identifiers in the scheduling scheme to be determined and minimize the total number of vehicle identifiers corresponding to the scheduling scheme to be determined, and to adjust the vehicle identifiers corresponding to each of the cargo information based on the transportation routes and cargo categories of each cargo information, until multiple candidate scheduling schemes are obtained, including: In response to receiving N cargo information, perform the following operations until the number of first scheduling schemes reaches the baseline number, resulting in multiple first scheduling schemes: Determine the vehicle identifier that matches the transportation route and cargo category of a cargo order from N cargo information entries, where N is an integer greater than 1; and If the loading amount corresponding to the vehicle identifier is less than or equal to a preset loading amount threshold, a first scheduling scheme is obtained. Based on the quality scores of multiple first scheduling schemes, multiple second scheduling schemes are determined from the multiple first scheduling schemes; Adjust at least one of the vehicle identifier and cargo order in at least two of the second scheduling schemes to obtain the plurality of candidate scheduling schemes.

3. The method for determining a vehicle dispatching scheme according to claim 2, characterized in that, The step of determining multiple second scheduling schemes from the multiple first scheduling schemes based on quality scores of multiple first scheduling schemes includes: Based on the quality scores of the plurality of first scheduling schemes, a preset number of second scheduling schemes are selected from the plurality of first scheduling schemes, wherein the preset number is determined according to the number of first scheduling schemes; The multiple first scheduling schemes that were not selected are grouped to obtain multiple scheme groups; The first scheduling scheme with the highest quality score in each of the scheme groups is selected as the second scheduling scheme.

4. The method for determining a vehicle dispatching scheme according to claim 2, characterized in that, The adjustment of at least one of the vehicle identifier and cargo order in at least two of the second scheduling schemes yields multiple candidate scheduling schemes, including: By exchanging the vehicle identifiers of at least two vehicles with the same transport routes and the same cargo categories in the second scheduling scheme, at least two preferred scheduling schemes are obtained. In response to the probability of change of the preferred scheduling scheme relative to the second scheduling scheme being greater than the change threshold, the vehicle identifiers in the preferred scheduling scheme are adjusted to form a candidate scheduling scheme with the goal of maximizing the quality score of the preferred scheduling scheme.

5. The method for determining a vehicle dispatching scheme according to claim 4, characterized in that, The scheduling parameters also include a first change threshold and a second change threshold, and the change probability is obtained using the following method: A relative score is obtained based on the degree of deviation between the quality score of the optimized scheduling scheme and the maximum quality score among all optimized scheduling schemes. The range of change is obtained based on the difference between the first change threshold and the second change threshold. The first change threshold indicates the upper limit of the probability of change, and the second change threshold indicates the lower limit of the probability of change. The change probability is obtained by fusing the first change threshold, the relative score, and the change range.

6. The method for determining a vehicle dispatching scheme according to claim 1, characterized in that, The optimization parameters include a baseline number M for adjusting the target scheduling scheme, where M is an integer greater than 1; the step of adjusting the target scheduling scheme based on the optimization parameters, with the goal of maximizing the quality score of the target scheduling scheme, until an optimized vehicle scheduling scheme is obtained, includes: Using the target scheduling scheme as the first scheduling scheme and the first reference scheduling scheme, perform M adjustment operations. The scheme with the higher quality score among the resulting Mth scheduling scheme and the Mth reference scheduling scheme is selected as the optimized scheduling scheme. The mth adjustment operation includes: With the goal of maximizing the quality score of m scheduling schemes, the vehicle identifiers with the same transportation routes and the same cargo categories in the m-th scheduling scheme are adjusted to form the m-th intermediate scheduling scheme, where m=1,…,M-1; If the quality score of the m-th intermediate scheduling scheme is greater than the quality score of the m-th scheduling scheme or the acceptance probability of the m-th intermediate scheduling scheme is greater than or equal to a preset probability threshold, the m-th intermediate scheduling scheme shall be used as the (m+1)-th scheduling scheme. If the quality score of the m-th intermediate scheduling scheme is greater than the quality score of the m-th reference scheduling scheme, the m-th intermediate scheduling scheme shall be used as the (m+1)-th reference scheduling scheme.

7. The method for determining a vehicle dispatching scheme according to claim 1, characterized in that, Determining the quality score for each candidate scheduling scheme includes performing the following operations for each candidate scheduling scheme: The loading score is obtained by summing the loading scores corresponding to the loading rates of multiple vehicle identifiers; The quality score of the candidate scheduling scheme is obtained by fusing at least one of the vehicle score, constraint score, and overload score with the loading score. The vehicle score is obtained based on the total number of vehicle identifiers. The constraint score is obtained based on at least one of the following: the number of cargo categories corresponding to each vehicle identifier, the degree of deviation between the vehicle type corresponding to each vehicle identifier and the reference vehicle type, the degree of deviation between the loading amount corresponding to each vehicle identifier and the preset loading amount threshold, and the number of vehicle types corresponding to each transport route. The overload score is obtained based on vehicle identifiers whose loading amount is greater than the loading amount threshold.

8. The method for determining a vehicle dispatching scheme according to claim 1, characterized in that, The scheduling parameters and the optimization parameters are obtained using the following method: Determine multiple initial scheduling parameters and multiple initial optimization parameters; The initial scheduling parameters and the initial optimization parameters are input into the prediction model to obtain multiple accuracy scores and multiple stability scores. The prediction model is pre-trained using historical scheduling parameters, historical optimization parameters, and corresponding accuracy score labels and stability score labels. Based on the multiple accuracy scores and the multiple stability scores, multiple candidate scheduling parameters are determined from the multiple initial scheduling parameters, and multiple candidate control parameters are determined from the multiple initial optimization parameters; Multiple candidate optimized scheduling schemes corresponding to the multiple candidate scheduling parameters and multiple candidate optimization parameters are determined. Based on the quality scores of the multiple candidate optimized scheduling schemes, a target optimized scheduling scheme is determined from the multiple candidate optimized scheduling schemes. The candidate scheduling parameters corresponding to the target optimized scheduling scheme are used as scheduling parameters, and the candidate optimization parameters corresponding to the target optimized scheduling scheme are used as optimization parameters.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 8.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

Images