Route determination method, computer device, storage medium, and computer program product

Abstract

The present application relates to the technical field of logistics, and relates to a route determination method, a computer device, a storage medium, and a computer program product. The method comprises: acquiring historical shipment volume information of each outlet and distance information between outlets, the historical shipment volume information indicating the shipment volume sent by the outlets to a target transit hub within each historical unit period (S202); acquiring a route planning model, the route planning model comprising a constraint condition and an objective function that are configured, the constraint condition being used for constraining stable outlet combinations within a unit period, the objective function being used for maximizing the total shipment volume of at least one stable outlet combination within the unit period, the stable outlet combination comprising at least two outlets, and the number of combinations of the at least two outlets within a set time range satisfying a preset number (S204); and on the basis of the historical shipment volume information and the distance information, as well as the constraint condition and the objective function, solving the route planning model to obtain a target outlet chained route that maximizes the total shipment volume within the unit period (S206).

Description

Circuit determination methods, computer equipment, storage media, and computer program products

[0001] Related applications

[0002] This application claims priority to Chinese patent application filed on February 21, 2025, with application number 2025102057962, entitled "Method for determining circuit, computer equipment, storage medium and computer program product", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of logistics technology, and in particular to a route determination method, computer equipment, storage medium, and computer program product. Background Technology

[0004] With the rapid development of the logistics industry, the capacity of vehicle resources for transshipment is facing challenges. In the traditional lifecycle of express delivery, couriers collect packages at the branch office, the branch office consolidates them at a transshipment center, and then they are transported by trunk line vehicles / aircraft / railway to a bulk cargo transshipment center, finally arriving at the delivery point from the bulk cargo transshipment center. This lifecycle involves at least two transshipments, which can easily lead to damage and delivery delays.

[0005] Based on this, a flexible direct shipment model can be adopted, which involves planning the cargo volume of several network points to be linked together and directly shipped to the destination's bulk cargo transshipment center. This can reduce the number of transportation trips and improve the timeliness of express delivery. In related technologies, the direct shipment routes in the direct shipment model are manually configured. However, the real-time performance and efficiency of manually configuring direct shipment routes cannot meet the actual business needs, resulting in insufficient cargo transportation efficiency in the direct shipment model scenario. Summary of the Invention

[0006] According to various embodiments of this application, a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining a circuit are provided.

[0007] Firstly, this application provides a route determination method. The method includes:

[0008] Obtain historical cargo volume information and distance information between each outlet; the historical cargo volume information refers to the cargo volume sent by the outlet to the target transit center within each historical unit period;

[0009] Obtain a route planning model, which includes configured constraints and an objective function; the constraints are used to constrain stable network point combinations within a unit period; the objective function is used to maximize the total cargo volume of at least one of the stable network point combinations within the unit period; the stable network point combination includes at least two network points, and the number of combinations of the at least two network points within a set time range satisfies a preset number of at least two network points; and

[0010] Based on the historical cargo volume information, the distance information, the constraints, and the objective function, the route planning model is solved to obtain the target network connection route with the largest total cargo volume within the unit period.

[0011] In one embodiment, the step of solving the route planning model based on the historical freight volume information, the distance information, the constraints, and the objective function to obtain the target network connection route with the largest total freight volume within the unit period includes:

[0012] Based on the historical cargo volume information and the distance information, initialize the constraints in the route planning model;

[0013] Based on a mixed-integer programming strategy and the aforementioned constraints, the objective function is determined as the solution objective, and the route planning model is solved to obtain a stable network point combination within the unit period; and

[0014] The stable network point combinations are merged to obtain at least one stable network point connection line, and the at least one stable network point connection line is determined as the target network point connection line with the largest total cargo volume in the unit period.

[0015] In one embodiment, the merging of the stable network nodes to obtain at least one stable network node serial connection includes:

[0016] Determine the network points included in each of the aforementioned stable network point combinations; and

[0017] By connecting stable network points that share the same network points in series, at least one stable network point series line can be obtained.

[0018] In one embodiment, the method further includes:

[0019] Determine the thresholds related to the route planning model; the thresholds include at least one of the following: the longest distance between network points, the maximum number of network points allowed to be connected in series, or the minimum weight limit of the route; the minimum weight limit of the route represents the minimum cargo weight required for each vehicle to depart.

[0020] The model variables related to the route planning model are determined; the model variables include decision variables; the decision variables are used to represent whether each network point is stable and whether the path corresponding to the combination of network points is stable; and

[0021] Based on the threshold and the model variables, the constraints corresponding to the route planning model are determined.

[0022] In one embodiment,

[0023] The step of determining the constraints corresponding to the route planning model based on the threshold and the model variables includes:

[0024] Determine the constraint conditions corresponding to the route planning model based on at least one of the first constraint, second constraint, third constraint, fourth constraint, fifth constraint, sixth constraint, seventh constraint, and eighth constraint;

[0025] Wherein, the first constraint is that the number of network points included in the network point connection route is less than or equal to the maximum number of network points;

[0026] The second constraint is that the total cargo volume corresponding to the outlets included in the route of each outlet is greater than or equal to the minimum weight limit of the route;

[0027] The third constraint is that the number of times each network point is connected in series within a unit period does not exceed a preset number;

[0028] The fourth constraint is that the end point in the network connection line is the target transfer station;

[0029] The fifth constraint is that any combination of two network points is connected in series by the same vehicle.

[0030] The sixth constraint is that the number of times the two nodes in each stable node combination are connected in series within a unit period satisfies a preset number.

[0031] The seventh constraint is that each stable node belongs to at least one stable node combination.

[0032] The eighth constraint is that the total cargo volume of the stable network connection route corresponding to each vehicle is greater than or equal to the minimum weight limit of the route; the stable network connection route is determined based on the stable network combination.

[0033] In one embodiment, the model variables further include fixed variables, which include at least one of the following: variables corresponding to network point information, vehicle information, or unit period information required to solve the route planning model.

[0034] In one embodiment, the fixed variables also include variables corresponding to the historical cargo volume information of each outlet and variables corresponding to the distance information between outlets.

[0035] In one embodiment, determining the constraints corresponding to the route planning model based on the threshold and the model variables further includes:

[0036] Determine the ninth constraint; the ninth constraint is the distance between two points contained in each point combination, which is less than or equal to the longest distance between the points.

[0037] In one embodiment, the method further includes:

[0038] Based on the model variables, the objective function corresponding to the route planning model is determined.

[0039] In one embodiment, determining the objective function corresponding to the route planning model based on the model variables includes:

[0040] For multiple time points within a unit period, the sum of the total freight volume of the stable network connection routes corresponding to each vehicle at each time point is calculated and used as the objective function of the route planning model.

[0041] In one embodiment, the decision variable takes the value 0 or 1, where 0 represents no and 1 represents yes.

[0042] Secondly, this application also provides a route determination device. The device includes:

[0043] The information acquisition module is configured to acquire historical cargo volume information and distance information between each outlet; the historical cargo volume information is the cargo volume sent by the outlet to the target transit center within each historical unit period;

[0044] The model acquisition module is configured to acquire a route planning model, which includes configured constraints and an objective function. The constraints are used to constrain stable point combinations within a unit period. The objective function is used to maximize the total cargo volume of at least one stable point combination within the unit period. Each stable point combination includes at least two points, and the number of combinations of these at least two points within a set time range satisfies a preset number.

[0045] The model solving module is configured to solve the route planning model based on the historical cargo volume information, the distance information, the constraints, and the objective function, to obtain the target network connection route with the largest total cargo volume within the unit period.

[0046] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in the first aspect.

[0047] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0048] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect.

[0049] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the disclosed drawings without creative effort.

[0051] Figure 1 shows the application environment of the route determination method in some embodiments;

[0052] Figure 2 is a flowchart illustrating the route determination method in some embodiments;

[0053] Figure 3 is a flowchart illustrating the process of determining the target network connection route in some embodiments;

[0054] Figure 4 is a flowchart illustrating the determination of constraints and objective functions in some embodiments;

[0055] Figure 5 is a schematic diagram of the direct delivery mode in some embodiments;

[0056] Figure 6 is a flowchart illustrating the route determination method in some other embodiments;

[0057] Figure 7 is a structural block diagram of the circuit determination device in some embodiments;

[0058] Figure 8 is an internal structure diagram of a computer device in some embodiments. Detailed Implementation

[0059] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] The route determination method provided in this application embodiment can be applied to the application environment shown in Figure 1. Terminal 102 communicates with server 104 via a network. Terminal 102 can obtain historical cargo volume information and location information of each branch, thereby determining the distance information between branches. Terminal 102 can synchronize the aforementioned historical cargo volume information and distance information between branches to server 104 for processing. A data storage system can store the data that server 104 needs to process; for example, terminal 102 can send historical cargo volume information and distance information to the data storage system for storage. The data storage system can be integrated on server 104 or located in the cloud or on other network servers.

[0062] Server 104 can acquire historical cargo volume information and distance information between each branch. Historical cargo volume information can be the cargo volume sent by each branch to the target transit center within multiple historical unit periods. Cargo volume can be represented by weight. Server 104 can acquire a pre-configured route planning model and determine the configured constraints and objective function within the model. Constraints are used to constrain stable branch combinations formed by each branch within a unit period. A stable branch combination can be defined as at least two branches whose combination frequency within a set time range satisfies a preset number of combinations. The objective function is used to maximize the total cargo volume of at least one stable branch combination within a unit period. Based on this, server 104 can solve the acquired route planning model based on the historical cargo volume information and distance information between branches to obtain the target branch series route with the largest total cargo volume within a unit period.

[0063] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0064] In an exemplary embodiment, as shown in FIG2, a route determination method is provided. Taking the application of this method to server 104 in FIG1 as an example, the method includes the following steps S202 to S206. Wherein:

[0065] Step S202: Obtain historical cargo volume information and distance information between each branch.

[0066] The historical cargo volume information refers to the volume of cargo sent from the distribution point to the target transit center within each historical unit period. A distribution point is where a courier stores packages after collecting them; in this embodiment, a distribution point may include, but is not limited to, a receiving distribution point or a receiving transit center. A transit center is a site where packages participate in transit and sorting; in this embodiment, the target transit center can be a transit center used to locally distribute packages. The unit period can be a period determined by a week, month, year, etc., and can contain multiple time points, one of which can be a day. The application scenario of this embodiment is to connect multiple receiving distribution points in the same area and link them to a target transit center. The target transit center can be the last distribution point connected. Based on this, vehicles can load packages one by one according to the connected route and send them together to the target transit center.

[0067] Specifically, the server can obtain historical cargo volume information and location information between multiple network points that require route planning from various terminals. The server can determine the distance between two network points using their location information. For example, it can determine the straight-line distance between network points using their geographical coordinates, or determine the travel path between network points as distance information. In one example, historical cargo volume information could be the daily cargo volume sent from a network point to the target transit point over the past several weeks or months. For example, for network point 1, the daily cargo volume sent to the target transit point for each of the seven days of a week can be determined, and based on the daily cargo volume sent to the target transit point, the total cargo volume sent by network point 1 to the target transit point within that week can be obtained, thus obtaining the historical cargo volume information for network point 1.

[0068] Step S204: Obtain the route planning model; the route planning model includes configured constraints and objective functions.

[0069] The constraints are used to constrain stable network combinations within a unit period; the objective function is used to maximize the total cargo volume of at least one stable network combination within a unit period; a stable network combination includes at least two network points, and the number of combinations of at least two network points within a set time range satisfies a preset number.

[0070] Specifically, the server retrieves the configured route planning model. This model includes configured constraints and an objective function. Constraints can be applied to the network point combinations from various dimensions during the transportation process to ensure that the network point combinations meet preset stability conditions. A network point combination that meets these conditions is considered a stable network point combination. The preset stability condition can be that within a unit period and a set time range, the number of combinations of each point in the network point combination meets a preset number. For example, the unit period can be one week, the set time range can be Monday to Friday, and the preset number of combinations is 3. If points 1 and 2 can be combined into a network point combination on 5 days of the week (i.e., the number of combinations of points 1 and 2 within a week is 5), then the network point combination formed by points 1 and 2 can be determined as a stable network point combination.

[0071] The objective function can be used to maximize the total freight volume of multiple stable network point combinations within a unit period. In other words, the objective function determines the total freight volume that multiple network point combinations, obtained by connecting various network points, can transport within a unit period. Solving the route planning model involves aiming to maximize the objective function to obtain stable network point combinations.

[0072] Step S206: Based on historical freight volume information, distance information, constraints, and objective function, solve the route planning model to obtain the target network connection route with the largest total freight volume within a unit period.

[0073] Specifically, the server can input historical freight volume and distance information into the parameters corresponding to the route planning model, and substitute these parameters into the constraints and objective function to solve the route planning model using the historical freight volume and distance information. The route planning model can be an integer programming model, such as the model corresponding to Mixed Integer Programming (MIP). After solving the route planning model, at least one stable combination of multiple network points can be obtained. The server can then connect at least one stable combination of network points to obtain the target network point connection route that maximizes the total freight volume within a unit period.

[0074] In the aforementioned route determination method, historical cargo volume information and distance information between each network point are obtained, and a route planning model is acquired. Based on the historical cargo volume and distance information, as well as the constraints and objective function in the route planning model, the route planning model is solved to obtain the target network point connecting route. Historical cargo volume information refers to the cargo volume sent from each network point to the target transit center within each historical unit period. Constraints are used to constrain stable network point combinations within a unit period. The objective function is used to maximize the total cargo volume of at least one stable network point combination within a unit period. A stable network point combination is defined as at least two network points whose combination frequency satisfies a preset number of combinations within a set time range. By solving the aforementioned route planning model based on the historical cargo volume information and distance information between each network point, the network points can be combined to obtain the target network point connecting route. Under the constraints of the objective function and constraints, the network point connecting route meets the actual business needs of the direct cargo delivery model and quickly generates direct delivery routes, thereby improving the cargo transportation efficiency under the direct cargo delivery model.

[0075] In an exemplary embodiment, as shown in Figure 3, the implementation process of the step "solving the route planning model based on historical freight volume information, distance information, constraints, and objective function to obtain the target network point series route with the largest total freight volume within a unit period" includes steps S302 to S306. Wherein:

[0076] Step S302: Based on historical freight volume information and distance information, initialize the constraints in the route planning model.

[0077] Specifically, the server can perform statistical analysis on the historical freight volume information of each branch to determine branch information. In one example, branch information may include the number of branches participating in route planning and the branch set, where the branch set may include all branches participating in route planning. The server can integrate distance information to obtain a distance matrix composed of the distance information between any two branches. The server inputs the above branch information, distance matrix, historical freight volume information, and distance information into the constraints of the route planning model to update the constraints and objective function.

[0078] Step S304: Based on the mixed integer programming strategy and constraints, the objective function is determined as the solution objective, and the route planning model is solved to obtain a stable network point combination within a unit period.

[0079] The mixed-integer programming strategy can be any of the branch-and-bound method or the cutting plane method. The mixed-integer programming strategy can be used to solve the route planning model and obtain the optimal solution.

[0080] Specifically, the server can randomly generate solutions that satisfy the constraints using a mixed-integer programming strategy, i.e., generate stable network node combinations that satisfy the constraints. Based on the generated stable network node combinations, the server determines the objective function value to maximize the objective function value. After one or more iterations, multiple solutions can be obtained, i.e., multiple stable network node combinations that satisfy the constraints. The stable network node combination corresponding to the maximum objective function value is then determined as the optimal solution.

[0081] Step S306: Combine the stable network points to obtain at least one stable network point connection line, and determine the at least one stable network point connection line as the target network point connection line with the largest total cargo volume in a unit period.

[0082] Specifically, the server can merge stable node combinations, such as by merging stable node combinations based on the nodes they include. For example, if different stable node combinations contain the same node, they can be merged to obtain a stable node concatenation line. In some embodiments, the server can concatenate node combinations with the same node identifier based on the node identifiers of the nodes included in the node combination to obtain at least one stable node concatenation line. For example, if node 1 and node 2 are stable node combinations, and node 2 and node 3 are stable node combinations, the stable node concatenation line can be determined as node 1-node 2-node 3. Similarly, if node 4 and node 5 are stable node combinations, and node 5 and node 6 are stable node combinations, the stable node concatenation line can be determined as node 4-node 5-node 6. This means that the two stable network connection routes, namely network point 1-network point 2-network point 3 and network point 4-network point 5-network point 6, can be identified as the target network connection routes with the largest total cargo volume within a unit period.

[0083] Optionally, when connecting stable node connections, the server prioritizes connecting unconnected node combinations to ensure that nodes in each stable connection are not shared by two connections simultaneously. For example, if node 1-node 4 is a stable node combination, node 1 can be connected in series with either node 2 or node 4. Based on this, the server can assign node 1 to the node 1-node 2-node 3 line and node 4 to the node 4-node 5-node 6 line, thus splitting the node combination of node 1 and node 4 into two independent node connections.

[0084] Optionally, when a network combination is shared by multiple network connection lines, the server can determine the total cargo volume transported by each network connection line and the corresponding line length of each network connection line, and select a network connection line based on the total cargo volume and line length.

[0085] In this embodiment, the constraints and objective function are updated using historical cargo volume and distance information. A mixed integer programming strategy and constraints are used to solve the route planning model with the objective function being maximized. Stable network point combinations within a unit period are obtained. Multiple stable network point combinations are then connected in series to obtain at least one target network point series line. This improves the solution efficiency of the route planning model and the transportation efficiency of the target network point series line.

[0086] In one exemplary embodiment, merging stable network point combinations to obtain at least one stable network point serial connection includes: determining the network points included in each stable network point combination; and serializing stable network point combinations that include the same network points to obtain at least one stable network point serial connection.

[0087] Different stable node combinations may include at least some different nodes. The server can concatenate stable node combinations that include the same nodes to obtain at least one stable node concatenation line. For example, nodes 4 and 5 are stable node combination 1, and nodes 5 and 6 are stable node combination 2. That is, both stable node combination 1 and stable node combination 2 include the same node 5. The server can then concatenate stable node combination 1 with stable node combination 2. For instance, it can concatenate nodes 4 and 5 included in stable node combination 1 with nodes 5 and 6 included in stable node combination 2 to obtain a stable node concatenation line. This stable node concatenation line can include node 4-node 5-node 6.

[0088] In this embodiment, the server can merge stable network point combinations with the same network points to construct at least one stable network point connection line, which can improve the solution efficiency of the route planning model and improve the transportation efficiency of the target network point connection line.

[0089] In an exemplary embodiment, as shown in FIG4, the route determination method further includes steps S402 to S406, wherein:

[0090] Step S402: Determine the thresholds related to the route planning model.

[0091] The thresholds include at least one of the following: the longest distance between service points, the maximum number of service points allowed to be connected in series, or the minimum weight limit for a route. The longest distance between service points can represent the maximum distance between individual service points. The minimum weight limit for a route represents the minimum cargo weight required for each vehicle to depart. The maximum number of service points allowed to be connected in series represents the number of service points that each vehicle can pass through during the same day's transportation.

[0092] Specifically, the server can determine relevant thresholds in the route planning model based on the received configuration instructions. In one example, the server can determine the maximum distance d between network points (e.g., 10 kilometers), the maximum number of network points allowed to be connected in series (e.g., 4), and the minimum weight limit Q of the route (e.g., 1.25 tons) through configuration instructions.

[0093] Step S404: Determine the model variables related to the route planning model; the model variables include decision variables.

[0094] In this context, decision variables represent the stability of each network point and the stability of the paths corresponding to network point combinations. Decision variables are variables in a mathematical model whose values ​​can be controlled and selected by the user. They represent the available options or strategies during the decision-making process. By adjusting and determining the values ​​of decision variables, optimization goals can be achieved or certain constraints can be satisfied.

[0095] In some embodiments, decision variables may further include fixed variables, which include at least one of the following: network point information, vehicle information, and unit period information required to solve the route planning model. In some embodiments, fixed variables also include variables corresponding to historical freight volume information for each network point and variables corresponding to distance information between network points. Fixed variables are variables whose values ​​remain unchanged throughout the analysis process in the mathematical model. Fixed variables typically represent known conditions of the problem, environmental factors, or given constraint parameters, etc. Fixed variables are determined by the background and premises of the problem and do not change with the decision-making process or changes in other variables.

[0096] Specifically, the server can configure decision variables, which can be used to constrain the stability of network points and the stability of paths corresponding to network point combinations. Decision variables can include at least one of the following: a first decision variable, a second decision variable, a third decision variable, a fourth decision variable, and a fifth decision variable. Decision variables take values ​​of 0 or 1, where 0 represents no and 1 represents yes.

[0097] The first decision variable can be used to indicate whether a network point is connected to a vehicle at a certain point in time within a unit period. For example, the first decision variable can be whether the i-th network point is in the k-th vehicle on day d.

[0098] The second decision variable can be used to indicate whether a vehicle is used. For example, the second decision variable could be whether vehicle k is used on day d.

[0099] The third decision variable can be used to indicate whether any two network points are connected by vehicles. For example, the third decision variable could be whether the i-th network point and the j-th network point are in the k-th vehicle on day d. <j。

[0100] The fourth decision variable can be used to indicate whether the connection between any two network points is stable after being connected by vehicles. If the number of times the two network points are connected (combined) is greater than a preset number, then the combination of network points connected by the two network points is considered stable. For example, the fourth decision variable can be whether the path constructed by the i-th network point and the j-th network point is stable for the k-th vehicle, and stability is defined as the number of days the connection is connected being greater than or equal to a preset number of days.

[0101] The fifth decision variable is used to indicate whether any network point connected in series with a vehicle is stable. If the number of times a network point is connected in series is greater than a preset number, then the network point is determined to be stable. For example, the fifth decision variable could be whether the i-th network point is stable on the k-th vehicle, and stability is determined by the number of days the network point is connected in series being greater than or equal to a preset number of days.

[0102] The server can be configured with fixed variables, which may include at least one of the following: a first fixed variable, a second fixed variable, a third fixed variable, a fourth fixed variable, a fifth fixed variable, a sixth fixed variable, a seventh fixed variable, and an eighth fixed variable.

[0103] The first fixed variable can be the driving cost between the i-th and j-th outlets; in this embodiment, the driving cost can be the driving distance. The second fixed variable can be the total cargo volume of the i-th outlet on day d. The third fixed variable can be the number of outlets. The fourth fixed variable can be the number of vehicles. The fifth fixed variable can be the number of time points per unit period, i.e., the number of days involved in the calculation. The sixth fixed variable can be the set of outlets. The seventh fixed variable can be the set of vehicles. The eighth fixed variable can be the set of time points per unit period.

[0104] In one example, the decision variables that the server can configure may include at least one of the following:

[0105] Is the i-th outlet in the k-th vehicle on day d?

[0106] y dk Whether vehicle k was used on day d.

[0107] Whether the i-th and j-th outlets are in the k-th vehicle on day d, i is less than j.

[0108] Whether the path constructed by the i-th and j-th network points is stable on the k-th vehicle is determined by the number of days the path is linked to a network point being greater than or equal to a preset number of days.

[0109] Whether the i-th network point is stable on the k-th vehicle is determined by the number of days the network point participates in the network point connection process being greater than or equal to the preset number of days.

[0110] In one example, the fixed variables that the server can configure may include at least one of the following:

[0111] c ij : The driving cost between the i-th and j-th network points.

[0112] The total cargo volume of the i-th outlet on day d.

[0113] n: Number of outlets, where the last outlet is the target transit point.

[0114] m: Number of vehicles.

[0115] ud: Number of days involved in the calculation.

[0116] N: Set of network points.

[0117] M: Vehicle assembly.

[0118] UD: The set of days involved in the serial point calculation.

[0119] Step S406: Based on the threshold and model variables, determine the constraints corresponding to the route planning model.

[0120] Specifically, the server can use the aforementioned thresholds and model variables to restrict the model variables associated with the network point combination through restriction symbols to obtain constraints. For example, the conditions used to restrict the model variables can be determined as constraints.

[0121] In this embodiment, by configuring thresholds and model variables related to the route planning model, and determining constraints and objective functions based on the thresholds and model variables, the route planning model can be accurately constructed through formulas, thereby increasing the accuracy of the solution results.

[0122] In an exemplary embodiment, the implementation process of the step "determining the constraints corresponding to the route planning model based on thresholds and model variables" includes:

[0123] Determine the constraints corresponding to the route planning model based on at least one of the first, second, third, fourth, fifth, sixth, seventh, and eighth constraints.

[0124] The first constraint is that the number of network points included in the network point connection route is less than or equal to the maximum number of network points.

[0125] Specifically, the server can configure the first constraint to allow each vehicle to connect to a maximum of R points, as shown in the following formula:

[0126] Where n represents the number of network points traversed, and the next n is the target transfer site; R represents the threshold for the maximum number of network points to be concatenated; y dk This indicates whether the k-th vehicle was used on day d; the value is 1 if yes and 0 if no. This indicates whether the i-th network point is in the k-th vehicle on day d, with a value of 1 if yes and 0 if no. M is the set of vehicles. UD is the set of days for which network points participated in the network point calculation.

[0127] According to the formula above, for each vehicle used daily, if any service points are connected to that vehicle, then the number of service points connected to that vehicle is less than R. If no vehicle is used, then no service points are connected, and the formula still holds true.

[0128] The second constraint is that the total cargo volume corresponding to the outlets included in the route of each outlet is greater than or equal to the minimum weight limit of the route.

[0129] Specifically, the server can configure the second constraint so that if the k-th vehicle is used, the vehicle must meet a minimum weight limit, that is, the network connection line corresponding to the vehicle must meet the minimum weight limit of the line, as shown in the following formula:

[0130] in, This represents the volume of goods at the i-th outlet on day d. Indicates whether the i-th branch is in the k-th vehicle on day d, Q represents the minimum weight limit of the route, and y dk This indicates whether vehicle k was used on day d.

[0131] According to the formula above, for each vehicle used daily, the total freight volume corresponding to each network point connected by that vehicle is determined, such that the total freight volume is greater than or equal to the minimum weight limit of the route. This formula also applies if the vehicle is not used.

[0132] The third constraint is that the number of times each branch is connected in series within a unit period shall not exceed the preset number.

[0133] Specifically, the server can configure the third constraint to allow each node to be queued at most once per day, and can also allow nodes to be excluded from the queueing process, as shown in the following formula:

[0134] in, Let represent whether the i-th node is in the k-th vehicle on day d. N is the set of nodes. This formula means that among m vehicles, any node can be connected to any one of the vehicles, or not connected to any vehicle.

[0135] The fourth constraint is that the end point in the network connection line is the target transfer station.

[0136] Specifically, the server can configure the fourth constraint so that if a vehicle is used, it ultimately terminates at the destination transit point, as shown in the following formula:

[0137] in, Indicates the target transit point, y dk This indicates whether vehicle k was used on day d. That is, if a vehicle is used, it will definitely connect to the target transfer station. If a vehicle is not used, it will definitely not connect to the target transfer station.

[0138] The fifth constraint is that any combination of two network points is connected in series by the same vehicle.

[0139] Specifically, the server can configure the fifth constraint as a path constraint, as shown in the following formula:

[0140] in, This indicates whether the i-th branch is in the k-th vehicle on day d. This indicates whether the i-th branch is in the k-th vehicle on day d. Let represent whether the i-th and j-th network points are in the k-th vehicle on day d, where i is less than j. This formula can be expressed as follows: If both the i-th and j-th network points are connected in the same vehicle, then both the i-th and j-th network points will be connected in that vehicle. That is, 2 ≤ 1 + 1 ≤ 1 + 1. If only one of the i-th and j-th network points is connected in the same vehicle, then 0 ≤ 1 + 0 ≤ 0 + 1. If neither the i-th nor the j-th network point is connected in the same vehicle, then 0 ≤ 0 + 0 ≤ 0 + 1. Therefore, this formula holds true for all cases.

[0141] The sixth constraint is that the number of times the two nodes in each stable node combination are connected in series within a unit period satisfies a preset number.

[0142] Specifically, the server can be configured to determine whether any two network points are stable. Stability is defined as the number of days that the points can be cross-referenced being ≥3 days, as shown in the following formula:

[0143] in, This indicates whether the path between the i-th and j-th network points is stable on the k-th vehicle. Stability is defined as the number of days the path crosses network points is greater than or equal to a preset number of days. This indicates whether the i-th and j-th network points are in the k-th vehicle on day d, where i is less than j. The formula states that if, within a unit period, the i-th and j-th network points can always be connected in series with a vehicle, and the number of times they are connected is greater than or equal to 3, then the i-th and j-th network points are considered stable. For example, if the i-th and j-th network points are connected in series with the vehicle for only one day, then 0 ≤ 1 ≤ 0 + 2; if the i-th and j-th network points are connected in series with the vehicle for only two days, then 0 ≤ 2 ≤ 0 + 2; if the i-th and j-th network points are connected in series with the vehicle for three days or more, then 3 ≤ 3 ≤ 3 + 2. In this embodiment, the unit period is defined as one week of working days; therefore, the i-th and j-th network points are connected in series with the vehicle for a maximum of 5 days.

[0144] The seventh constraint is that each stable node belongs to at least one stable node combination.

[0145] Specifically, the server can configure the seventh constraint to determine whether a node is stable, meaning that a stable node must have at least one stable combination of nodes obtained by connecting these nodes in series, as shown in the following formula:

[0146] in, This indicates whether the path between the i-th and j-th network points is stable on the k-th vehicle. Stability is defined as the number of days the path crosses the network points being greater than or equal to a preset number of days. This indicates whether the j-th node is stable on the k-th vehicle. Stability is defined as the number of days the node participates in the connection process being greater than or equal to a preset number of days. The formula states that if the j-th node is stable, then there exists at least one i-th node that forms a stable connection with the j-th node; that is, there exists at least one stable path formed by the i-th node and the j-th node. For example, if the j-th node is stable and only one vehicle connects to it, then the formula is 1 ≤ 1 + 0 ≤ 2, or 1 ≤ 1 + 1 ≤ 2.

[0147] The eighth constraint is that the total cargo volume of the stable network connection route corresponding to each vehicle is greater than or equal to the minimum weight limit of the route; the stable network connection route is determined based on the stable network combination.

[0148] Specifically, the server can configure the eighth constraint as the sum of the weights of stable network point series lines, which must satisfy the minimum load constraint, as shown in the following formula:

[0149] in, Indicate whether the i-th network point is stable on the k-th vehicle; This represents the volume of goods at the i-th outlet on day d.

[0150] In this embodiment, the above-mentioned constraints can constrain the route planning model to be solved from the dimensions of stability, weight, and no repetition, which can improve the diversity of constraints and increase the accuracy of the network combination obtained by solving the route planning model.

[0151] In an exemplary embodiment, after the step "determine the constraints corresponding to the route planning model based on the threshold and model variables", the method further includes:

[0152] Determine the ninth constraint; the ninth constraint is the distance between two nodes contained in each node combination, which is less than or equal to the longest distance between nodes.

[0153] Specifically, the server can configure the ninth constraint to ensure that if network points are connected in series, the distance between any two network points does not exceed the longest distance between network points, as shown in the following formula:

[0154] like

[0155] in, Is the i-th branch in the k-th vehicle on day d? To determine whether the j-th outlet is in the k-th vehicle on day d, c ij Let $\frac{i}{j}$ be the travel cost between the $i$-th and $j$-th service points. If the travel cost between the $i$-th and $j$-th service points exceeds the longest distance between them, then we can determine $\frac{i}{j}$. and At least one of them is 0, for example, 0+0≤1, 1+0≤1, or 0+1≤1.

[0156] In one exemplary embodiment, the route determination method further includes: determining the objective function corresponding to the route planning model based on the model variables.

[0157] Specifically, the server can combine the various model variables according to user needs to obtain the objective function corresponding to the route planning model.

[0158] In this embodiment, by configuring thresholds and model variables related to the route planning model, and determining constraints and objective functions based on the thresholds and model variables, the route planning model can be accurately constructed through formulas, thereby increasing the accuracy of the solution results.

[0159] In an exemplary embodiment, the implementation process of the step "determining the objective function corresponding to the route planning model based on model variables" includes:

[0160] For multiple time points within a unit period, the sum of the total freight volume of the stable network connection routes corresponding to each vehicle at each time point is calculated and used as the objective function of the route planning model.

[0161] Specifically, the objective function is mainly used to maximize the total freight volume at stable route points, and the formula for the objective function is as follows:

[0162] in, This represents the total volume of goods at the i-th outlet on day d. This indicates whether the i-th service point is stable on the k-th vehicle. m represents the number of vehicles, ud represents the number of days involved in the calculation, and n-1 represents the number of service points excluding the target transit point.

[0163] In this embodiment, by maximizing the total cargo volume in the stable network connection route corresponding to each vehicle under the number of days of participation in the calculation, the optimal network connection route can be determined, which can improve the prediction accuracy of the route planning model.

[0164] As shown in Figure 5, the execution process of the above route determination method is described in detail below with reference to an embodiment. First, the terms used in this application embodiment are explained. Outlet: The place where the courier collects and stores the packages; Transfer center: The site where packages participate in transfer and sorting; Connecting outlets: Connecting outlets together using the shortest path, with a large vehicle passing through these outlets in sequence to combine the goods and transport them to the destination bulk cargo transfer center; Connecting route: Defining a direct route as connecting multiple outlets in multiple cities and sending them directly to the destination transfer center. For example, if three different outlets (1, 2, 3) in multiple different cities (ABC) send goods directly to the destination transfer center in city D, then the route is defined as: Outlet 1 in city A -> Outlet 2 in city B -> Outlet 3 in city C -> D destination transfer center in city D. Furthermore, considering the stability of the multi-day direct delivery mode, if a route can be connected for direct delivery for at least 3 out of 5 days, then this route is considered a stable route.

[0165] As shown in Figure 6, firstly, the server can preprocess the cargo volume information from the distribution points to the transit hub and the distance information between the distribution points. Data preprocessing can include anomaly data deletion, data filling, and data normalization. Secondly, the server can configure constraints within a unit period. Thirdly, the server can configure the objective function within a unit period. Fourthly, the server can solve the MIP model based on the constraints and objective function to obtain stable paths corresponding to multiple distribution point combinations. Finally, the stable paths are merged to obtain the final target distribution point connection route.

[0166] The mathematical modeling process of the MIP model is as follows:

[0167] (1) Assumptions: 1. Without considering the order of mailing time, it is assumed that the network points can be connected before the latest departure time of the vehicle; 2. Without considering the vehicle loading rate, and multiple vehicles can be dispatched.

[0168] (2) Parameter settings: 1. Maximum driving distance between any two network points: d, for example, the maximum driving distance between any two network points is 10km; 2. Maximum number of network points connected in each route: R. For example, each route can connect a maximum of 4 network points; 3. Minimum weight limit for each route: Q. For example, the minimum weight limit for each route is 1.25T.

[0169] (3) Model variables: 1. Decision variables. The following variables take integer values ​​of 0-1, where 1 represents yes and 0 represents no. Is the i-th branch in the k-th vehicle on day d? dk Whether vehicle k was used on day d. Whether the i-th and j-th outlets are in the k-th vehicle on day d, i is less than j. Whether the path of the ij-th network point is stable on the k-th vehicle is determined by the number of days the path is linked to the network point being greater than or equal to a preset number of days. Whether the i-th network point is stable on the k-th vehicle is determined by the number of days the network point participates in the network point connection process being greater than or equal to the preset number of days.

[0170] 2. Fixed variables, including: c ij : The driving cost between the i-th and j-th network points. The total cargo volume of the i-th branch on day d. n: Number of branches, where the last branch is the target transit point. m: Number of vehicles. ud: Number of days involved in the calculation. N: Set of branches. M: Set of vehicles. UD: Set of days involved in the branch calculation.

[0171] The constraints determined based on the parameters and model variables are as follows:

[0172] 1. If the service points are located in multiple locations, the distance between any two service points must not exceed 10 kilometers.

[0173] like

[0174] 2. Each vehicle can connect to a maximum of R points.

[0175] 3. If the kth vehicle is used, the minimum weight limit must be met.

[0176] 4. Each outlet can be linked to another outlet a maximum of once per day, and outlets are allowed to not participate in such linking.

[0177] 5. If the vehicle is used, its final destination will be the transit point.

[0178] 6. Path constraints.

[0179] 7. To determine whether any two network points are stable: the number of days that the points can be cross-referenced is ≥3 days.

[0180] 8. Determine if the network is stable: There must be at least 3 consecutive days of cross-network connections with the same network.

[0181] 9. The total weight of stable line network points must meet the minimum load constraint.

[0182] The defined objective function is to maximize the total cargo volume at stable route points.

[0183] At this point, the vehicle routing problem is transformed into a network point combination problem, reducing the complexity of the model solution. Ultimately, it is transformed into a MIP integer programming problem. Solving this integer programming problem subsequently yields the optimal network point combination and the optimal network point connection route.

[0184] In one example, suppose there are four distribution points A, B, C, and D, and the cargo volume (Monday to Friday) to the destination transshipment center H is as follows:

[0185] Monday: A: 150, B: 200, C: 450, D: 400;

[0186] Tuesday: A: 130, B: 220, C: 430, D: 410;

[0187] Wednesday: A: 120, B: 230, C: 420, D: 430;

[0188] Thursday: A: 100, B: 200, C: 300, D: 450;

[0189] Friday: A: 180, B: 100, C: 380, D: 300;

[0190] Distance parameters:

[0191] C(AB)=C(BA)=20, C(AC)=C(CA)=10, C(AD)=C(DA)=25, C(BC)=C(CB)=25, C(BD)=C(DB)=10, C(CD)=C(DC)=20, C(AH)=100, C(BH)=120, C(CH)=140, C(DH)=150.

[0192] Starting weight: Must exceed 500 for departure; Stable definition: Must have enough starting weight for at least 4 days from Monday to Friday; Point connection parameter: Point connection is allowed if the distance between two points is within 15km.

[0193] The final solution to the parameters yields the stable path:

[0194] 1. AC: The total volume of goods checked from Monday to Friday is 600, 560, 540, 400, and 560. The route to the destination transfer station is: C->A->H: The total distance is 10+100=110.

[0195] 2. BD: The total volume of goods checked from Monday to Friday is 600, 630, 660, 650, and 400. The route to the destination transit center is: D->B->H: Total distance 10+120=130.

[0196] 3. At this point, the total cargo volume of the model is determined as: cargo volume of AC line + cargo volume of BD line = 600 + 560 + 540 + 400 + 560 + 600 + 630 + 660 + 650 + 400 = 5600, and the average daily cargo volume is 5600 / 5 = 1120.

[0197] In this embodiment, a new flexible direct delivery model for logistics outlets is proposed. Based on the daily shipment volume from historical outlets to transit hubs, a periodic outlet chaining model is constructed, defining periodic stable route types to maximize the total cargo volume of stable routes. At the same time, the shortest path problem is transformed into a chaining MIP model, and the integer programming model is easier to solve for the optimal solution. Furthermore, the new delivery model reduces the number of transit nodes, improves the timeliness of express delivery, and reduces transit transportation costs, thereby maximizing the overall efficiency of express delivery.

[0198] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0199] Based on the same inventive concept, this application also provides a route determination apparatus for implementing the route determination method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more route determination apparatus embodiments provided below can be found in the limitations of the route determination method described above, and will not be repeated here.

[0200] In an exemplary embodiment, as shown in FIG7, a route determination device 700 is provided, including: an information acquisition module 701, a model acquisition module 702, and a model solving module 703, wherein:

[0201] The information acquisition module 701 is configured to acquire historical cargo volume information and distance information between each network point; the historical cargo volume information is the cargo volume sent by the network point to the target transit center within each historical unit period;

[0202] The model acquisition module 702 is configured to acquire a route planning model, which includes configured constraints and an objective function. The constraints are used to constrain stable network point combinations within a unit period. The objective function is used to maximize the total cargo volume of at least one stable network point combination within a unit period. A stable network point combination includes at least two network points, and the number of times the at least two network points are combined within a set time range satisfies a preset number.

[0203] The model solving module 703 is configured to solve the route planning model based on historical cargo volume information, distance information, constraints, and objective function to obtain the target network connection route with the largest total cargo volume within a unit period.

[0204] Furthermore, the model solving module 703 is configured to: initialize the constraints in the route planning model based on historical cargo volume information and distance information; solve the route planning model based on mixed integer programming strategy and constraints, with the objective function as the solution objective, to obtain stable network point combinations within a unit period; and merge each stable network point combination to obtain at least one stable network point connection route, and determine at least one stable network point connection route as the target network point connection route with the largest total cargo volume within a unit period.

[0205] Furthermore, the model solving module 703 is configured to determine the network points included in each stable network point combination; and to connect stable network point combinations that include the same network points in series to obtain at least one stable network point series line.

[0206] Furthermore, the device also includes a condition and function determination module, configured to determine thresholds related to the route planning model; the thresholds include at least one of the longest distance between network points, the maximum number of network points allowed to be connected in series, or the minimum weight limit for the route; the minimum weight limit for the route represents the minimum cargo weight required for each vehicle to depart; determine model variables related to the route planning model; the model variables include decision variables; the decision variables are configured to represent whether each network point is stable and whether the path corresponding to the combination of network points is stable; and determine the constraints corresponding to the route planning model based on the thresholds and model variables.

[0207] Furthermore, the condition and function determination module is also configured to: determine the constraint conditions corresponding to the route planning model based on at least one of the first, second, third, fourth, fifth, sixth, seventh, and eighth constraints; wherein, the first constraint is that the number of network points included in the route connecting all network points is less than or equal to the maximum number of network points; the second constraint is that the total cargo volume corresponding to the network points included in the route connecting all network points is greater than or equal to the minimum weight limit of the route; the third constraint is that the number of times each network point is connected within a unit period does not exceed a preset number; the fourth constraint is that the ending network point in the route connecting all network points is the target transfer station; the fifth constraint is that any combination of network points consisting of two network points is connected by the same vehicle; the sixth constraint is that the number of times the two network points included in each stable network point combination are connected within a unit period meets the preset number; the seventh constraint is that each stable network point belongs to at least one stable network point combination; the eighth constraint is that the total cargo volume of the stable network point connection routes corresponding to each vehicle is greater than or equal to the minimum weight limit of the route; the stable network point connection routes are determined based on stable network point combinations.

[0208] Furthermore, the model variables also include fixed variables, which include at least one of the following: variables corresponding to network point information, vehicle information, or unit period information required to solve the route planning model.

[0209] Furthermore, the model variables also include variables corresponding to the historical cargo volume information of each outlet and variables corresponding to the distance information between outlets.

[0210] Furthermore, the condition and function determination module is also configured to: determine the ninth constraint; the ninth constraint is the distance between two points contained in each point combination, which is less than or equal to the longest distance between points.

[0211] Furthermore, the condition and function determination module is also configured to determine the objective function corresponding to the route planning model based on the model variables.

[0212] Furthermore, the condition and function determination module is also configured to: sum the total freight volume of the stable network connection routes corresponding to each vehicle at each time point within a unit period, and use this sum as the objective function of the route planning model.

[0213] Furthermore, the decision variable can take values ​​of 0 or 1, where 0 represents no and 1 represents yes.

[0214] Each module in the aforementioned circuit determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0215] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram is shown in Figure 8. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores historical cargo volume information and distance information between network points. The I / O interfaces of the computer device are used for information exchange between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a route determination method.

[0216] Those skilled in the art will understand that the structure shown in Figure 8 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0217] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0218] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0219] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0220] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0221] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0222] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0223] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for determining a route, characterized in that, The method includes: Obtain historical cargo volume information and distance information between each outlet; the historical cargo volume information refers to the cargo volume sent by the outlet to the target transit center within each historical unit period; A route planning model is obtained, comprising configured constraints and an objective function; the constraints are used to constrain stable network point combinations within a unit period; the objective function is used to maximize the total cargo volume of at least one stable network point combination within the unit period; the stable network point combination includes at least two network points, and the number of combinations of the at least two network points within a set time range satisfies a preset number; and Based on the historical cargo volume information, the distance information, the constraints, and the objective function, the route planning model is solved to obtain the target network connection route with the largest total cargo volume within the unit period.

2. The method according to claim 1, characterized in that, The step of solving the route planning model based on the historical freight volume information, the distance information, the constraints, and the objective function to obtain the target network point connecting route with the largest total freight volume within the unit period includes: Based on the historical cargo volume information and the distance information, initialize the constraints in the route planning model; Based on a mixed-integer programming strategy and the aforementioned constraints, the objective function is determined as the solution objective, and the route planning model is solved to obtain a stable network point combination within the unit period; and The stable network point combinations are merged to obtain at least one stable network point connection line, and the at least one stable network point connection line is determined as the target network point connection line with the largest total cargo volume in the unit period.

3. The method according to claim 2, characterized in that, The process of combining and merging the stable network points to obtain at least one stable network point serial connection includes: Determine the network points included in each of the aforementioned stable network point combinations; and By connecting stable network points that share the same network points in series, at least one stable network point series line can be obtained.

4. The method according to claim 1, characterized in that, The method further includes: Determine the thresholds related to the route planning model; the thresholds include at least one of the following: the longest distance between network points, the maximum number of network points allowed to be connected in series, or the minimum weight limit of the route; the minimum weight limit of the route represents the minimum cargo weight required for each vehicle to depart. The model variables related to the route planning model are determined; the model variables include decision variables; the decision variables are used to represent whether each network point is stable and whether the path corresponding to the combination of network points is stable; and Based on the threshold and the model variables, the constraints corresponding to the route planning model are determined.

5. The method according to claim 4, characterized in that, The step of determining the constraints corresponding to the route planning model based on the threshold and the model variables includes: Determine the constraint conditions corresponding to the route planning model based on at least one of the first constraint, second constraint, third constraint, fourth constraint, fifth constraint, sixth constraint, seventh constraint, and eighth constraint; Wherein, the first constraint is that the number of network points included in the network point connection route is less than or equal to the maximum number of network points; The second constraint is that the total cargo volume corresponding to the outlets included in the route of each outlet is greater than or equal to the minimum weight limit of the route; The third constraint is that the number of times each network point is connected in series within a unit period does not exceed a preset number; The fourth constraint is that the end point in the network connection line is the target transfer station; The fifth constraint is that any combination of two network points is connected in series by the same vehicle. The sixth constraint is that the number of times the two nodes in each stable node combination are connected in series within a unit period satisfies a preset number. The seventh constraint is that each stable node belongs to at least one stable node combination. The eighth constraint is that the total cargo volume of the stable network connection route corresponding to each vehicle is greater than or equal to the minimum weight limit of the route; the stable network connection route is determined based on the stable network combination.

6. The method according to claim 3, characterized in that, The model variables also include fixed variables, which include at least one of the following: variables corresponding to network point information, vehicle information, or unit period information required to solve the route planning model.

7. The method according to claim 6, characterized in that, The fixed variables also include variables corresponding to the historical cargo volume information of each outlet and variables corresponding to the distance information between outlets.

8. The method according to claim 5, characterized in that, The step of determining the constraints corresponding to the route planning model based on the threshold and the model variables further includes: Determine the ninth constraint; the ninth constraint is the distance between two points contained in each point combination, which is less than or equal to the longest distance between the points.

9. The method according to claim 4, characterized in that, The method further includes: Based on the model variables, the objective function corresponding to the route planning model is determined.

10. The method according to claim 9, characterized in that, The step of determining the objective function corresponding to the route planning model based on the model variables includes: For multiple time points within a unit period, the sum of the total freight volume of the stable network connection routes corresponding to each vehicle at each time point is calculated and used as the objective function of the route planning model.

11. The method according to any one of claims 4 to 10, characterized in that, The decision variable can take the values ​​0 or 1, where 0 represents no and 1 represents yes.

12. A route determination device, characterized in that, The device includes: The information acquisition module is configured to acquire historical cargo volume information and distance information between each outlet; the historical cargo volume information is the cargo volume sent by the outlet to the target transit center within each historical unit period; The model acquisition module is configured to acquire a route planning model, which includes configured constraints and an objective function. The constraints are used to constrain stable point combinations within a unit period. The objective function is used to maximize the total cargo volume of at least one stable point combination within the unit period. Each stable point combination includes at least two points, and the number of combinations of these at least two points within a set time range satisfies a preset number. The model solving module is configured to solve the route planning model based on the historical cargo volume information, the distance information, the constraints, and the objective function, to obtain the target network connection route with the largest total cargo volume within the unit period.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, The processor is configured to implement the steps of the method according to any one of claims 1 to 11 when executing the computer program.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is configured to implement the steps of the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product, comprising a computer program, characterized in that, The computer program is configured to implement the steps of the method according to any one of claims 1 to 11 when executed by a processor.

Images