Vehicle scheduling optimization method and related equipment

Abstract

The invention provides a vehicle scheduling optimization method and related equipment, and relates to the technical field of scheduling. The method comprises the following steps: screening lines according to historical delivery volume data of the lines to obtain an initial delivery line; if the initial delivery line meets a preset condition, processing the initial delivery line by adopting a first optimization model to obtain a first optimization result; if the initial delivery route does not meet the preset condition, the second optimization model is adopted to process the initial delivery route, and a second optimization result is obtained.According to the method and device, the route operation cost caused by the uncertainty of the cargo volume can be reduced, screening of the initial delivery route does not need to depend on manual experience, and the reliability and optimization efficiency of vehicle dispatching optimization are improved.

Description

Background Art

[0002] Logistics is the entire process of planning, implementing and managing the transportation, storage and distribution of goods from their place of production to their place of consumption in order to meet the needs of customers at the lowest cost.

[0003] In the related art, vehicle dispatching usually uses artificial experience to determine the route vehicle type or operation optimization method to determine the route vehicle type. However, the above vehicle dispatching methods have the problems of low dispatching efficiency and poor applicability.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a vehicle dispatch optimization method and related equipment, which at least to a certain extent overcome the problems of low dispatch efficiency and poor applicability of vehicle dispatch methods in related technologies.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a vehicle scheduling optimization method is provided, comprising: screening routes according to historical shipping volume data of the routes to obtain an initial shipping route; if the initial shipping route meets a preset condition, processing the initial shipping route using a first optimization model to obtain a first optimization result; if the initial shipping route does not meet the preset condition, processing the initial shipping route using a second optimization model to obtain a second optimization result.

[0008] In one embodiment of the present disclosure, the screening of routes according to historical shipping volume data of the routes to obtain initial shipping routes includes: calculating the cargo volume ratio of each route according to the shipping days and statistical days in the historical shipping volume data of the routes; and determining the route whose cargo volume ratio is greater than or equal to a preset ratio threshold as the initial shipping route.

[0009] In one embodiment of the present disclosure, the method further includes: determining the daily mean volume and the standard deviation of the volume of the initial shipping route within the statistical period based on the historical shipping volume data of the route; calculating the coefficient of variation of the initial shipping route based on the daily mean volume and the standard deviation of the volume; and determining the relationship between the initial shipping route and the preset condition based on the coefficient of variation of the initial shipping route.

[0010] In one embodiment of the present disclosure, the relationship between the initial shipping route and the preset condition is determined based on the coefficient of variation of the initial shipping route, including: if the coefficient of variation is less than a preset coefficient threshold, it is determined that the initial shipping route meets the preset condition; if the coefficient of variation is greater than or equal to the preset coefficient threshold, it is determined that the initial shipping route does not meet the preset condition.

[0011] In one embodiment of the present disclosure, the first optimization model or the second optimization model is obtained in the following manner: based on the decision variables, a cost objective function is constructed with the goal of minimizing the full vehicle cost and the less-than-truckload cost; based on the decision variables, constraints of the cost objective function are constructed, wherein the constraints include vehicle type activation standard constraints, and the vehicle type activation standard constraints of the first optimization model and the second optimization model are different.

[0012] In one embodiment of the present disclosure, the vehicle type activation standard constraint conditions in the first optimization model include: the sum of the minimum total cargo volume of the whole vehicle type and the cargo volume of the less-than-truckload type on the initial shipment route is less than or equal to the total cargo volume of the initial shipment route; the sum of the maximum total cargo volume of the whole vehicle type, the cargo volume of the less-than-truckload type, and the tail cargo volume on the initial shipment route is greater than or equal to the total cargo volume of the initial shipment route.

[0013] In one embodiment of the present disclosure, the vehicle type activation standard constraint condition in the second optimization model is obtained in the following manner: for any decision variable, determine the loss cost caused by system uncertainties, and calculate the average value of the risk level caused when the loss cost exceeds a preset threshold; introduce an auxiliary variable to transform the average value of the risk level caused when the loss cost exceeds the preset threshold, and obtain the average value of the transformed risk level; construct the initial vehicle type activation standard constraint condition in the second optimization model according to the average value of the transformed risk level and the cargo volume that the optimized vehicle type cannot load due to cargo fluctuations; introduce another decision variable to process the initial vehicle type activation standard constraint condition to obtain the processed first vehicle type activation standard constraint condition and the constraint of the other decision variable; linearize the nonlinear function in the constraint of the other decision variable to obtain the second vehicle type activation standard condition, and the cargo loading limit constraint in the second optimization model includes the first vehicle type activation standard constraint condition and the second vehicle type activation standard constraint condition.

[0014] In one embodiment of the present disclosure, the initial shipping route is processed using a first optimization model to obtain a first optimization result, including: obtaining the first optimization result according to the value of the decision variable corresponding to the optimal solution result of the first optimization model.

[0015] In one embodiment of the present disclosure, the using of a second optimization model to process the initial shipping route to obtain a second optimization result includes: obtaining the second optimization result according to the value of the decision variable corresponding to the optimal solution result of the second optimization model.

[0016] According to another aspect of the present disclosure, a vehicle scheduling optimization device is also provided, including: a route screening module, used to screen the route according to the historical shipping volume data of the route to obtain an initial shipping route; a first processing module, used to use a first optimization model to process the initial shipping route if the initial shipping route meets the preset conditions to obtain a first optimization result; a second processing module, used to use a second optimization model to process the initial shipping route if the initial shipping route does not meet the preset conditions to obtain a second optimization result.

[0017] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned vehicle scheduling optimization method by executing the executable instructions.

[0018] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned vehicle scheduling optimization method is implemented.

[0019] According to another aspect of the present disclosure, a computer program product is provided, the computer program product comprising a computer program or computer instructions, the computer program or the computer instructions being loaded and executed by a processor so that a computer implements the above-mentioned vehicle scheduling optimization method.

[0020] In the disclosed embodiment, the routes are screened according to the historical cargo volume data of the routes to obtain an initial shipping route; if the initial shipping route meets the preset conditions, the first optimization model is used to process the initial shipping route to obtain a first optimization result; if the initial shipping route does not meet the preset conditions, the second optimization model is used to process the initial shipping route to obtain a second optimization result, thereby reducing the route operation cost caused by the uncertainty of cargo volume, and the screening of the initial shipping route does not need to rely on manual experience, thereby improving the reliability and optimization efficiency of vehicle scheduling optimization.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0023] Figure 1 The following is an architecture diagram of a vehicle dispatching system provided by an embodiment of the present disclosure;

[0024] Figure 2 A flow chart of a vehicle scheduling optimization method provided by an embodiment of the present disclosure is shown;

[0025] Figure 3 A flow chart of a method for determining an initial shipping route provided by an embodiment of the present disclosure is shown;

[0026] Figure 4 A flow chart of a method for determining a relationship between an initial shipping route and preset conditions provided by an embodiment of the present disclosure is shown;

[0027] Figure 5 A flow chart of a method for establishing a first optimization model or a second optimization model provided by an embodiment of the present disclosure is shown;

[0028] Figure 6 An example flow chart of a vehicle scheduling optimization method provided by an embodiment of the present disclosure is shown;

[0029] Figure 7 A schematic diagram showing a first optimization result obtained by using a first optimization model in an embodiment of the present disclosure;

[0030] Figure 8 A schematic diagram showing a second optimization result obtained by using a second optimization model in an embodiment of the present disclosure;

[0031] Fig. 9 A schematic diagram showing the structure of a vehicle dispatch optimization device provided by an embodiment of the present disclosure is shown;

[0032] Fig.10 A structural block diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0033] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0034] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0035] Figure 1 An exemplary system architecture 100 to which the vehicle scheduling optimization method or vehicle scheduling optimization device according to the embodiments of the present disclosure may be applied is shown.

[0036] like Figure 1 As shown, the system architecture 100 may include a terminal device 110 , a network 120 and a server 130 .

[0037] The network 120 is used to provide a medium for a communication link between the terminal device 110 and the server 130, and may be a wired network or a wireless network. The network 120 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0038] The user may use the terminal device 110 to interact with the server 130 through the network 120 to receive or send messages.

[0039] The terminal device 110 may be any electronic device that has a voice acquisition device and supports web browsing, including but not limited to a smart phone, a tablet computer, a display screen, and a desktop computer.

[0040] Various communication client applications can be installed on the terminal device 110, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc., and historical shipment data can be obtained through the communication client applications.

[0041] It should be noted that the client of the application installed on the terminal device 110 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0042] The server 130 may be a server that provides various services, such as a background management server that supports web browsing websites browsed by users using the terminal device 110. The background server may screen the routes according to the historical shipping volume data of the routes to obtain the initial shipping routes; the background management server may also process the initial shipping routes using the first optimization model to obtain the first optimization result if the initial shipping routes meet the preset conditions; if the initial shipping routes do not meet the preset conditions, the background management server may process the initial shipping routes using the second optimization model to obtain the second optimization result, etc., and perform analysis and other processing to obtain the processing result (such as the first optimization result or the second optimization result, etc.) and feed it back to the terminal device 110.

[0043] Optionally, server 130 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0044] Those skilled in the art will know that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration, and any number of terminal devices, networks and servers may be provided according to actual needs. The embodiments of the present disclosure are not limited to this.

[0045] In related technologies, vehicle type optimization usually uses artificial experience to determine the route vehicle type or operations optimization methods to determine the route vehicle type. During optimization, the vehicle type combination of the route is calculated based on the historical shipping records, cargo volume and route vehicle type cost of the route to be optimized, so as to minimize the route transportation cost.

[0046] According to the analysis of historical data, the volume of cargo on the route fluctuates, which may make the recommended model inappropriate. For example, when the actual volume of cargo is greater than the volume corresponding to the recommended model, it is necessary to temporarily add vehicles or replace vehicles, which increases costs; when the actual volume of cargo is less than the volume corresponding to the recommended model, it will lead to a decrease in loading rate and waste of resources. To solve the above problems, routes with stable and large cargo volumes are generally selected as alternative routes, or random optimization methods are used to consider the impact of cargo volume fluctuations.

[0047] However, the above vehicle scheduling optimization method has the following problems:

[0048] 1) In the related art, only routes with stable cargo volume are selected as alternative routes. However, in reality, there are fewer routes with stable and large cargo volume. Therefore, there are fewer routes that can be optimized and the optimization space is small.

[0049] 2) When selecting alternative routes, indicators such as cargo volume mean and variance are usually used as the basis for selecting routes with stable cargo volume. However, the setting of the above indicators relies on manual experience, which leads to overly loose or overly strict selection of alternative routes, reducing the optimization effect;

[0050] 3) The random optimization method relies on the fact that the cargo volume distribution of the route is Gaussian. If the route has few shipping records or no Gaussian characteristics, the random optimization method cannot be used, and the usage scenarios are limited.

[0051] In order to at least partially solve the above technical problems, the present disclosure provides a vehicle scheduling optimization method. The scenario simulation and CVaR method are used to deal with the problem of cargo volume uncertainty, and the line operation cost caused by cargo volume uncertainty is considered. The vehicle model adjustment scheme obtained by this method can obtain the minimum line vehicle cost under the influence of cargo volume fluctuations. At the same time, compared with the existing method, the screening of candidate routes no longer relies on manual experience, the number of candidate routes can be increased, and the problem of a small number of adjustable schemes can be solved.

[0052] Specifically, the routes are screened according to the historical cargo volume data of the routes to obtain the initial shipping routes; if the initial shipping route meets the preset conditions, the first optimization model is used to process the initial shipping route to obtain the first optimization result; if the initial shipping route does not meet the preset conditions, the second optimization model is used to process the initial shipping route to obtain the second optimization result, thereby reducing the route operation cost caused by the uncertainty of cargo volume. The screening of the initial shipping route does not need to rely on manual experience, thereby improving the reliability and optimization efficiency of vehicle scheduling optimization.

[0053] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0054] The present exemplary implementation is described in detail below with reference to the accompanying drawings and embodiments.

[0055] First, a vehicle scheduling optimization method is provided in an embodiment of the present disclosure, and the method can be executed by any system with computing processing capabilities. The vehicle scheduling optimization method provided in an embodiment of the present disclosure can be executed by a server, for example, by a vehicle scheduling optimization device configured on the server.

[0056] Figure 2 A flow chart of a vehicle scheduling optimization method provided in an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the vehicle scheduling optimization method provided in the embodiment of the present disclosure includes the following steps:

[0057] S202: Screen the routes according to the historical shipping volume data of the routes to obtain an initial shipping route.

[0058] In S202, the historical shipment volume data of the route may include but is not limited to the quantity and type of goods shipped daily by the route during the statistical period, so as to determine the status of the route's shipment volume data and provide data support for screening out routes with stable shipments.

[0059] The quantity of shipped goods can be characterized by parameters such as the volume, number of pieces, and weight of the shipped goods. The types of goods can include ordinary goods, special goods, dangerous goods, and bulk goods. Ordinary goods have special requirements for vehicle structure and transported goods during transportation, loading and unloading, and storage; special goods require special handling in terms of nature, volume, weight, and value; the transportation of dangerous goods requires special handling and safety measures, and bulk goods are not packaged during transportation and are transported in bulk.

[0060] In one embodiment, the above-mentioned screening of routes based on historical shipping volume data of the routes can be performed by calculating the shipping days of the routes within the statistical period as a screening basis to screen the initial shipping routes from multiple routes.

[0061] In one embodiment, for a route of a certain type of goods, the average values ​​of the quantity of goods shipped by the route within a statistical period may be sorted, and the top five routes with the largest average values ​​of the quantity of goods shipped may be selected as initial shipping routes.

[0062] It should be noted that before screening the initial shipping routes, you can also eliminate the routes in the historical shipping volume data that have not been shipped within a preset period of time before the current moment. For example, eliminate the routes that have not been shipped within 5 days before the current moment, so as to ensure the continuity and stability of the shipping routes.

[0063] The initial shipping route obtained by screening may include at least one. When the initial shipping route includes multiple routes, an initial shipping route may be randomly selected for route vehicle type optimization; or a corresponding initial shipping route may be selected for route vehicle type optimization according to a certain selection order, which is not specifically limited in the present disclosure.

[0064] S204: If the initial shipping route meets the preset conditions, the first optimization model is used to process the initial shipping route to obtain a first optimization result.

[0065] In one embodiment, the preset conditions are used to characterize the fluctuation of the cargo volume on the route. The preset conditions are pre-configured in the server. The specific form of the preset conditions can be determined according to actual needs, and the present disclosure does not make specific limitations on this.

[0066] When the initial shipping route meets the preset conditions, it indicates that the cargo volume of the route is stable and the impact of cargo volume fluctuations on the transportation cost of Xi'an Road is small. At this time, the first optimization model can be used to solve.

[0067] The first optimization model can also be called a deterministic optimization model. Based on the decision variables, it constructs a cost objective function with the goal of minimizing the full vehicle cost and the less-than-truckload cost, as well as the constraints of the cost objective function.

[0068] In one embodiment, in the above S204, the first optimization result is obtained according to the value of the decision variable corresponding to the optimal solution of the first optimization model.

[0069] By solving the first optimization model of the initial shipping route, the values ​​of the decision variables are obtained, that is, the vehicle types and their corresponding quantities and the LTL types and their corresponding quantities in the initial shipping route. The values ​​of the decision variables are used as the first optimization result, so as to accurately determine the route optimization result and obtain the route with the minimum vehicle cost.

[0070] S206: If the initial shipping route does not meet the preset conditions, the second optimization model is used to process the initial shipping route to obtain a second optimization result.

[0071] When the initial dispatch route does not meet the preset conditions, it means that the cargo volume of the route is unstable. The use of the first optimization model may lead to unreasonable planning of vehicle models. The actual dispatch may call for a temporary vehicle or the loading rate may be too low, which will increase the cost of the route or waste resources. At this time, the second optimization model can be used to deal with the impact of cargo volume fluctuations.

[0072] The second optimization model can also be called the uncertainty optimization model. Based on the decision variables, it constructs a cost objective function with the goal of minimizing the full vehicle cost and the less-than-truckload cost, as well as the constraints of the cost objective function.

[0073] In one embodiment, in the above S204, the second optimization result is obtained according to the value of the decision variable corresponding to the optimal solution of the second optimization model.

[0074] By solving the second optimization model of the initial shipping route, the values ​​of the decision variables are obtained, that is, the vehicle types and their corresponding quantities and the LTL types and their corresponding quantities in the initial shipping route. The values ​​of the decision variables are used as the second optimization results, thereby reducing the impact of cargo volume fluctuations, accurately determining the route optimization results, and obtaining the route with the minimum vehicle cost.

[0075] It should be noted that the cost objective functions of the first optimization model and the second optimization model are constructed in a similar manner, but the constraints of the cost objective functions are different.

[0076] In the disclosed embodiment, the routes are screened according to the historical cargo volume data of the routes to obtain an initial shipping route; if the initial shipping route meets the preset conditions, the first optimization model is used to process the initial shipping route to obtain a first optimization result; if the initial shipping route does not meet the preset conditions, the second optimization model is used to process the initial shipping route to obtain a second optimization result, thereby reducing the route operation cost caused by the uncertainty of cargo volume, and the screening of the initial shipping route does not need to rely on manual experience, thereby improving the reliability and optimization efficiency of vehicle scheduling optimization.

[0077] Figure 3 A flow chart of a method for determining an initial shipping route provided by an embodiment of the present disclosure is shown as follows: Figure 3 As shown, the above S202 screens the routes according to the historical shipping volume data of the routes to obtain the initial shipping routes, including:

[0078] S302, calculating the cargo volume ratio of each route according to the shipping days and statistical days in the historical shipping volume data of the route;

[0079] S304: Determine the route whose cargo volume ratio is greater than or equal to the preset ratio threshold as the initial shipping route.

[0080] In one embodiment, the shipping days of a route refer to the number of days that the route has cargo within a statistical period. The statistical period can be in units of weeks, months, etc., and a statistical period can include multiple days. The statistical days within the statistical period are recorded, and the ratio of the shipping days to the statistical days is calculated to obtain the cargo ratio of each route.

[0081] The value of the above-mentioned preset ratio threshold value can be determined according to the actual situation, for example, 80%. The preset ratio threshold value can be pre-configured in the server, and the present disclosure does not make any specific limitation on this.

[0082] In the disclosed embodiment, when the adjustable vehicle model is determined and confirmed, the route vehicle model optimization can be performed. The statistical period can be half a month to one month. By selecting the routes whose shipping days account for more than 80% of the statistical days as the initial shipping routes, the implementation of the vehicle model optimization can be guaranteed, and more stable shipping routes can be screened out for route vehicle model optimization.

[0083] Figure 4 A flow chart of a method for determining the relationship between an initial shipping route and preset conditions provided by an embodiment of the present disclosure is shown. Figure 4 As shown, in one embodiment, the vehicle scheduling optimization method provided by the embodiment of the present disclosure further includes:

[0084] S402. Determine the daily mean and standard deviation of the volume of cargo for the initial shipping route within the statistical period based on the historical shipping volume data of the route;

[0085] S404. Calculate the coefficient of variation of the initial shipping route based on the daily cargo volume mean and cargo volume standard deviation;

[0086] S406. Determine the relationship between the initial shipping route and the preset conditions according to the coefficient of variation of the initial shipping route.

[0087] In one embodiment, the mean daily cargo volume of the initial shipping route within the statistical period is the average value of the number of goods shipped by the route within the statistical period. The standard deviation of the cargo volume is the arithmetic mean root of the square of the mean deviation, which can reflect the degree of dispersion of the number of daily cargo shipped by the initial shipping route within the statistical period. The standard deviation of the cargo volume can be calculated according to the standard deviation calculation formula.

[0088] The coefficient of variation of the initial shipping route is used to characterize the stability of the route cargo volume. The coefficient of variation c is expressed by the following formula:

[0089]

[0090] in, is the average daily cargo volume of the initial shipping route during the statistical period, σ m It is the standard deviation of the cargo volume of the initial shipping route during the statistical period.

[0091] In one embodiment, the coefficient of variation of the initial shipping route may also assign different weights to the coefficients of variation of different cargo types in the initial shipping route, and calculate the coefficient of variation of the initial shipping route by weighted summation.

[0092] In addition to the above implementation method, a more detailed division method can also be used to perform a more detailed scenario simulation on the overall situation of the shipped goods of the initial shipping route, so as to distinguish routes with obvious or insignificant cargo volume fluctuations, so as to make the probability distribution of the scenario more consistent with the cargo volume distribution of the actual route.

[0093] In one embodiment, the above S406 determines the relationship between the initial shipping route and the preset conditions based on the coefficient of variation of the initial shipping route, including: if the coefficient of variation is less than the preset coefficient threshold, then it is determined that the initial shipping route meets the preset conditions; if the coefficient of variation is greater than or equal to the preset coefficient threshold, then it is determined that the initial shipping route does not meet the preset conditions.

[0094] In one embodiment, a preset coefficient threshold can be used as a preset condition. The preset coefficient threshold can be determined according to actual needs. The present disclosure does not make specific limitations on this. For example, the preset coefficient threshold is 0.5, that is, when the coefficient of variation of the initial shipping route is less than 0.5, it is determined that the cargo volume fluctuation of the initial shipping route is small, and the first optimization model can be used to optimize the vehicle model scheduling; when the coefficient of variation of the initial shipping route is greater than or equal to 0.5, it is determined that the cargo volume fluctuation of the initial shipping route is large, and the second optimization model can be used to optimize the vehicle scheduling.

[0095] It should be noted that when the line variation coefficient is greater than or equal to the preset coefficient threshold, it is also necessary to perform Monte Carlo sampling on the line's historical shipping volume data to determine the volume changes of the initial shipping line, so that the second optimization model processes the sampled data to obtain a second optimization result.

[0096] The present disclosure uses a scenario model sampling method to simulate the fluctuation of route cargo volume, so that the probability distribution of the scenario is close to the actual route cargo volume, thereby solving the problem that the route cargo volume is affected by factors such as user orders, network changes, and sorting capacity, resulting in the fluctuation of route cargo volume not conforming to the random distribution.

[0097] Figure 5 A flow chart of a method for establishing a first optimization model or a second optimization model provided by an embodiment of the present disclosure is shown. Figure 5 As shown, in one embodiment, the first optimization model or the second optimization model is obtained in the following manner:

[0098] According to the decision variables, the cost objective function is constructed with the goal of minimizing the full truckload cost and the less-than-truckload cost;

[0099] According to the decision variables, the constraints of the cost objective function are constructed, wherein the constraints include vehicle type activation standard constraints, and the vehicle type activation standard constraints of the first optimization model and the second optimization model are different.

[0100] In one embodiment, the cost objective functions of the first optimization model and the second optimization model both aim to minimize the full truckload cost and the less-than-truckload cost, and construct constraints for the cost objective functions. The constraints for the constructed cost objective functions are different.

[0101] The decision variables include y v 、x v and g, where y v Used to indicate whether to select the vth model. V is the vehicle type set V = {0, 1, ..., n}, n is an integer, v0 is the LTL vehicle type; x v is the number of the vth type of vehicle, is a set of integers, v∈V′, g≥0; g represents the amount of unfinished goods.

[0102] The cost objective function constructed based on the decision variables is expressed in Formula 2:

[0103] min∑v ∈V c v x v +g×c0(Formula 2)

[0104] Among them, min() is the minimum function, ∑ v∈V c v x v is the vehicle cost, g×c0 is the LTL cost, V is the vehicle set, V={0,1,…,n}, v0 represents the LTL model, V′ is the vehicle model set, V′={1,…,n}, c v is the cost of the v-th vehicle type, c0 is the cost of the LTL vehicle type, v∈V, and g is the amount of remaining cargo.

[0105] The constraints of the cost objective function are used to characterize the number of vehicle types and / or less-than-truckload types that can be used to transport the cargo volume in the initial shipping route.

[0106] The vehicle type activation standard constraint of the cost objective function is used to characterize the number of vehicle types and / or the number of less-than-truckload models required to transport the minimum or maximum cargo volume in the initial shipment route.

[0107] In one embodiment, the vehicle model activation standard constraint conditions in the first optimization model include satisfying the following conditions:

[0108] The sum of the minimum total cargo volume of the full truckload model and the cargo volume of the LTL model on the initial shipping route is less than or equal to the total cargo volume of the initial shipping route;

[0109] The sum of the maximum total cargo volume of complete truckload vehicles, the cargo volume of less-than-truckload vehicles, and the remaining cargo volume on the initial shipping route is greater than or equal to the total cargo volume of the initial shipping route.

[0110] The vehicle model activation standard constraint conditions in the first optimization model can be expressed by Formula 3 and Formula 4:

[0111] ∑ v∈V′ l v x v +x0l0≤m (Formula 3)

[0112] ∑ v∈V′ u v x v +x0u0+g≤m (Formula 4)

[0113] Among them, l vis the lower limit of the cargo volume of the vth type of vehicle, v∈V, l0 is the lower limit of the maximum cargo volume allowed for the cargo volume or LTL vehicle, u v is the upper limit of cargo volume of the vth vehicle type, u0 is the upper limit of cargo volume of the LTL vehicle type, and m is the total cargo volume of the initial shipping route.

[0114] In addition to the vehicle type opening standard constraint, the cost objective function can also include the vehicle type quantity constraint, which is used to constrain the number of vehicle types and the number of LTL models in the initial shipping route. Among them, the vehicle type quantity constraint can be expressed by formula 5 and formula 6:

[0115]

[0116] y0l0≤x0≤y0u0 (Formula 6)

[0117] Among them, m max is the maximum cargo volume in the history of the initial shipping route. When y0 indicates that the LTL model is selected, y0=1.

[0118] The constraints of the cost objective function also include cargo loading limit constraints, which are used to constrain the loading capacity of each vehicle type. The cargo loading limit constraints can be expressed by formula 7:

[0119] g≤(1-g0)l0

[0120] y0≤∑ v∈V′ y v

[0121] y v ∈{0, 1}, v∈V, v∈V′, x0≤0, g≤0 (Formula 7).

[0122] In one embodiment, the vehicle model activation standard constraint condition in the second optimization model is obtained in the following manner:

[0123] For any decision variable, determine the loss cost caused by system uncertainty factors and calculate the average value of the risk level caused when the loss cost exceeds the preset threshold;

[0124] Auxiliary variables are introduced to transform the average value of the risk level caused when the loss cost exceeds the preset threshold, and the average value of the transformed risk level is obtained;

[0125] According to the average value of the converted risk level and the cargo volume that cannot be loaded by the optimized vehicle model due to cargo fluctuation, the initial vehicle model opening standard constraint condition in the second optimization model is constructed;

[0126] Another decision variable is introduced to process the initial vehicle model opening standard constraint condition to obtain the processed first vehicle model opening standard constraint condition and the constraint of another decision variable;

[0127] The nonlinear function in the constraint of another decision variable is linearized to obtain the standard conditions for opening the second vehicle model. The cargo loading limit constraints in the second optimization model include the standard constraints for opening the first vehicle model and the standard constraints for opening the second vehicle model.

[0128] Due to the fluctuation of cargo volume in the initial shipping route, the vehicle model opening standard constraint conditions (Formula 3 and Formula 4) contain cargo volume uncertain variables, which makes it impossible to use the first constraint model for solution. In order to solve the model, the uncertainty constraints of Formula 3 and Formula 4 can be converted into deterministic constraints.

[0129] In this disclosure, the Conditional Value at Risk (CVaR) method is used to realize the transformation of uncertainty constraints into deterministic constraints. CVaR is a method of measuring risk. It can be used to calculate the average loss value of a decision under the condition that the loss of the decision exceeds a given VaR value, and can be optimized using a linear programming algorithm. The following is an example of converting Formula 3 into CVaR, and the specific implementation process is as follows:

[0130] For any decision variable x v , assuming that the loss cost caused by the system uncertainty factor ξ is H(x, ξ), CVaR means that under the confidence level β, H(x, ξ) exceeds the threshold VaR, which is the average value of the risk level caused. VaR and CVaR are expressed using formula 8 and formula 9:

[0131]

[0132] Among them, ξ is the sample value, δ is the upper limit of the loss value, and P(ξ) is the probability of ξ.

[0133] The auxiliary scalar z is introduced to transform CVaR and obtain the average value of the transformed risk level, as shown in Formula 10:

[0134]

[0135] Among them, ξ s is the sth sample of ξ, P s is the probability corresponding to sample s.

[0136] Formula 10 is used to perform CVaR conversion on Formula 3 to obtain the initial vehicle model activation standard constraint conditions in the second optimization model, as shown in Formula 11:

[0137]

[0138] in, is a set value, representing the cargo volume that cannot be loaded by the optimized vehicle model due to cargo volume fluctuation. When , the optimization feasible domain is the tightest, which will lead to no feasible solution for the second optimization model. As ω increases gradually, the optimization feasible domain gradually increases, and the feasible solutions of the second optimization model increase; 1 is an auxiliary variable.

[0139] The other decision variable introduced is denoted as R s , converting Formula 11 into Formula 12, the processed first vehicle model opening standard constraint condition and the constraint of another decision variable are obtained.

[0140]

[0141] R s ≥max{∑ v∈V′ l v x v +x0l0-ξ s -ω 1 ,0} (Formula 12)

[0142] Replace R in Formula 12 s The function contains a nonlinear maximum value function max(), which is linearized by introducing a large constant M. After transformation, formula 13 is obtained, which is the standard condition for opening the second model, as follows:

[0143]

[0144] Similarly, the vehicle model activation standard constraint condition after converting Formula 4 is shown in Formula 14:

[0145]

[0146] in,

[0147] Figure 6 FIG. 2 shows an example flow chart of a vehicle dispatch optimization method provided by an embodiment of the present disclosure. Figure 6 As shown, the vehicle scheduling optimization method provided by the embodiment of the present disclosure includes the following steps:

[0148] Obtain historical shipping data of the route;

[0149] Select the routes with optimized shipping days accounting for more than 0.8 as the initial optimized routes;

[0150] Calculate the coefficient of variation of the initial optimized route;

[0151] Determine whether the coefficient of variation of the initial optimized line is greater than 0.5. If not, use the deterministic optimization model to optimize the line scheduling and output the results. If so, perform Monte Carlo sampling and use the uncertainty optimization model to optimize the line scheduling and output the results.

[0152] In the present disclosure, the second optimization model can focus on routes with unstable cargo volume, optimize vehicle models to have a higher degree of match with actual shipping vehicle models, improve the implementation rate of the plan, and avoid increased costs in operations. Figure 7 and Figure 8 Schematic diagram of the first optimization result and the second optimization result obtained by optimizing the route with fluctuating cargo volume using the first optimization model and the second optimization model respectively. Figure 7 and Figure 8 It can be obtained that, using the first optimization model, the matching degree between the actual vehicle model of the optimized route and the optimized vehicle model in 30 days of actual operation is only 67.7%. Using the second optimization model to optimize the route, the matching degree between the actual vehicle model and the optimized vehicle model is 87.1%, and the matching degree is improved by 19.4%. The operation of this route is more stable, avoiding the increase in costs in actual operation due to fluctuations in cargo volume.

[0153] This paper proposes a vehicle model adjustment optimization method based on scenario simulation and CVaR method, which can solve the vehicle model optimization problem caused by cargo volume fluctuation. This method does not require cargo volume fluctuation to conform to random distribution, and is more widely used in actual scenarios. For vehicle model optimization scenarios, the uncertainty function processed by the CVaR method is used as the constraint of the model, and the right term of the constraint condition is Control the number of optimization solutions.

[0154] Based on the same inventive concept, the embodiments of the present disclosure also provide a vehicle scheduling optimization device and a vehicle scheduling optimization device, such as the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0155] Fig. 9 FIG. 2 shows a schematic diagram of a vehicle dispatch optimization device provided by an embodiment of the present disclosure. Fig. 9 As shown, the vehicle dispatch optimization device of this embodiment includes a route screening module 910, a first processing module 920 and a second processing module 930. Among them:

[0156] A route screening module 910 is used to screen routes according to historical shipping volume data of the routes to obtain an initial shipping route;

[0157] A first processing module 920 is used to process the initial shipping route using a first optimization model to obtain a first optimization result if the initial shipping route meets a preset condition;

[0158] The second processing module 930 is used to process the initial shipping route using a second optimization model to obtain a second optimization result if the initial shipping route does not meet the preset conditions.

[0159] In one embodiment, the route screening module 910 is used to calculate the cargo volume ratio of each route based on the shipping days and statistical days in the historical shipping volume data of the route; and determine the route with the cargo volume ratio greater than or equal to the preset ratio threshold as the initial shipping route.

[0160] In one embodiment, the device also includes a third processing module not shown in the accompanying drawings, and the third processing module is used to determine the daily mean cargo volume and the standard deviation of the cargo volume of the initial shipping route within the statistical period based on the historical shipping volume data of the route; calculate the coefficient of variation of the initial shipping route based on the daily mean cargo volume and the standard deviation of the cargo volume; and determine the relationship between the initial shipping route and the preset conditions based on the coefficient of variation of the initial shipping route.

[0161] In one embodiment, the third processing module is used to determine that the initial shipping route meets the preset conditions if the coefficient of variation is less than the preset coefficient threshold; if the coefficient of variation is greater than or equal to the preset coefficient threshold, determine that the initial shipping route does not meet the preset conditions.

[0162] In one embodiment, the device also includes a model construction module not shown in the accompanying drawings, and the model construction module is used to construct the first optimization model or the second optimization model in the following manner: based on the decision variables, a cost objective function is constructed with the goal of minimizing the full vehicle cost and the less-than-truckload cost; based on the decision variables, constraints of the cost objective function are constructed, wherein the constraints include vehicle type activation standard constraints.

[0163] It should be noted that the vehicle type activation standard constraint conditions in the first optimization model include: the sum of the minimum total cargo volume of complete vehicle types and the cargo volume of less-than-truckload types on the initial dispatch route is less than or equal to the total cargo volume of the initial dispatch route; the sum of the maximum total cargo volume of complete vehicle types, the cargo volume of less-than-truckload types, and the tail cargo volume on the initial dispatch route is greater than or equal to the total cargo volume of the initial dispatch route.

[0164] In one embodiment, the model building module is also used to obtain the cargo loading limit constraint in the second optimization model in the following manner: for any decision variable, determine the loss cost caused by system uncertainties, and calculate the average value of the risk level caused when the loss cost exceeds the preset threshold; introduce auxiliary variables to transform the average value of the risk level caused when the loss cost exceeds the preset threshold, and obtain the average value of the converted risk level; construct the initial vehicle model activation standard constraint in the second optimization model based on the average value of the converted risk level and the cargo volume that the optimized vehicle model cannot load due to cargo fluctuations; introduce another decision variable to process the initial vehicle model activation standard constraint to obtain the processed first vehicle model activation standard constraint and the constraint of another decision variable; linearize the nonlinear function in the constraint of another decision variable to obtain the second vehicle model activation standard condition, and the cargo loading limit constraint in the second optimization model includes the first vehicle model activation standard constraint and the second vehicle model activation standard constraint.

[0165] In one embodiment, the first processing module 920 is used to obtain a first optimization result according to the value of the decision variable corresponding to when the solution result of the first optimization model reaches the optimal value.

[0166] In one embodiment, the second processing module 930 is used to obtain a second optimization result according to the value of the decision variable corresponding to when the solution result of the second optimization model reaches the optimal value.

[0167] In the disclosed embodiment, the routes are screened according to the historical cargo volume data of the routes to obtain an initial shipping route; if the initial shipping route meets the preset conditions, the first optimization model is used to process the initial shipping route to obtain a first optimization result; if the initial shipping route does not meet the preset conditions, the second optimization model is used to process the initial shipping route to obtain a second optimization result, thereby reducing the route operation cost caused by the uncertainty of cargo volume, and the screening of the initial shipping route does not need to rely on manual experience, thereby improving the reliability and optimization efficiency of vehicle scheduling optimization.

[0168] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0169] Refer to the following Fig.10 The electronic device 1000 according to this embodiment of the present invention will be described. Fig.10 The electronic device 1000 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0170] like Fig.10 As shown, the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 may include but are not limited to: the at least one processing unit 1010, the at least one storage unit 1020, and a bus 1030 connecting different system components (including the storage unit 1020 and the processing unit 1010).

[0171] The storage unit stores program codes, which can be executed by the processing unit 1010, so that the processing unit 1010 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 1010 can perform the following steps: Figure 2 As shown in , the routes are screened according to the historical shipping volume data of the routes to obtain an initial shipping route; if the initial shipping route meets the preset conditions, the first optimization model is used to process the initial shipping route to obtain a first optimization result; if the initial shipping route does not meet the preset conditions, the second optimization model is used to process the initial shipping route to obtain a second optimization result.

[0172] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 10201 and / or a cache storage unit 10202 , and may further include a read-only storage unit (ROM) 10203 .

[0173] The storage unit 1020 may also include a program / utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment.

[0174] Bus 1030 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0175] The electronic device 1000 may also communicate with one or more external devices 1040 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the system, and / or any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1050. Furthermore, the system may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1060. Fig.10 As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 via the bus 1030. It should be understood that although Fig.10 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0176] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0177] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. In an exemplary embodiment of the present disclosure, a computer program product is also provided, which includes a computer program or a computer instruction, and the computer program or the computer instruction is loaded and executed by a processor to enable the computer to implement the steps of the method disclosed in the above embodiment.

[0178] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0179] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0180] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0181] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0182] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0183] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0184] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0185] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A vehicle scheduling optimization method, characterized in that: include: The routes are screened according to the historical shipping volume data of the routes to obtain the initial shipping routes; If the initial shipping route meets the preset conditions, the initial shipping route is processed using a first optimization model to obtain a first optimization result; If the initial shipping route does not meet the preset condition, the second optimization model is used to process the initial shipping route to obtain a second optimization result.

2. The vehicle dispatch optimization method according to claim 1, characterized in that: The process of screening the routes according to the historical shipping volume data of the routes to obtain the initial shipping routes includes: Calculate the cargo volume ratio of each route based on the shipping days and statistical days in the historical shipping volume data of the route; The route whose cargo volume ratio is greater than or equal to a preset ratio threshold is determined as the initial shipping route.

3. The vehicle dispatch optimization method according to claim 1, characterized in that: The method further comprises: Determine the daily cargo volume mean and cargo volume standard deviation of the initial shipping route within the statistical period based on the historical shipping volume data of the route; Calculate the coefficient of variation of the initial shipping route based on the daily cargo volume mean and the cargo volume standard deviation; According to the coefficient of variation of the initial shipping route, a relationship between the initial shipping route and the preset condition is determined.

4. The vehicle dispatch optimization method according to claim 3, characterized in that: The determining, according to the coefficient of variation of the initial shipping route, the relationship between the initial shipping route and the preset condition comprises: If the coefficient of variation is less than a preset coefficient threshold, it is determined that the initial shipping route meets the preset condition; If the coefficient of variation is greater than or equal to the preset coefficient threshold, it is determined that the initial shipping route does not meet the preset condition.

5. The vehicle dispatch optimization method according to any one of claims 1 to 4, characterized in that: The first optimization model or the second optimization model is obtained in the following manner: According to the decision variables, the cost objective function is constructed with the goal of minimizing the full truckload cost and the less-than-truckload cost; According to the decision variables, the constraints of the cost objective function are constructed, wherein the constraints include vehicle type activation standard constraints, and the vehicle type activation standard constraints of the first optimization model and the second optimization model are different.

6. The vehicle dispatch optimization method according to claim 5, characterized in that: The vehicle model activation standard constraint conditions in the first optimization model include: The sum of the minimum total cargo volume of the full truckload model and the cargo volume of the LTL model on the initial shipping route is less than or equal to the total cargo volume of the initial shipping route; The sum of the maximum total cargo volume of complete vehicle types, the cargo volume of less-than-truckload types, and the remaining cargo volume on the initial shipping route is greater than or equal to the total cargo volume of the initial shipping route.

7. The vehicle dispatch optimization method according to claim 6, characterized in that: The vehicle model activation standard constraint condition in the second optimization model is obtained by the following method: For any decision variable, determine the loss cost caused by system uncertainty factors and calculate the average value of the risk level caused when the loss cost exceeds the preset threshold; An auxiliary variable is introduced to transform the average value of the risk level caused when the loss cost exceeds a preset threshold value, so as to obtain the average value of the transformed risk level; According to the average value of the converted risk level and the cargo volume that cannot be loaded by the optimized vehicle type due to cargo fluctuation, constructing the initial vehicle type opening standard constraint condition in the second optimization model; Introducing another decision variable, processing the initial vehicle model activation standard constraint condition, and obtaining the processed first vehicle model activation standard constraint condition and the constraint of the another decision variable; The nonlinear function in the constraint of the other decision variable is linearized to obtain the standard conditions for opening the second vehicle model. The cargo loading limit constraints in the second optimization model include the standard constraints for opening the first vehicle model and the standard constraints for opening the second vehicle model.

8. The vehicle dispatch optimization method according to claim 5, characterized in that: The initial shipping route is processed using a first optimization model to obtain a first optimization result, including: The first optimization result is obtained according to the value of the decision variable corresponding to the optimal solution of the first optimization model.

9. The vehicle dispatch optimization method according to claim 5, characterized in that: The adopting the second optimization model to process the initial shipping route to obtain a second optimization result includes: The second optimization result is obtained according to the value of the decision variable corresponding to the optimal solution of the second optimization model.

10. A vehicle dispatch optimization device, characterized in that: include: The route screening module is used to screen the routes according to the historical shipping volume data of the routes to obtain the initial shipping routes; A first processing module, configured to process the initial shipping route using a first optimization model to obtain a first optimization result if the initial shipping route meets a preset condition; The second processing module is used to use a second optimization model to process the initial shipping route if the initial shipping route does not meet the preset condition to obtain a second optimization result.

11. An electronic device, characterized in that: include: processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the vehicle scheduling optimization method as described in any one of claims 1-9 by executing the executable instructions.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle scheduling optimization method as described in any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that The computer program product includes a computer program or computer instructions, and the computer program or the computer instructions are loaded and executed by a processor to enable a computer to implement the vehicle scheduling optimization method as described in any one of claims 1 to 9.

Images