Method, device, storage medium and electronic device for generating unloading process plan

Abstract

The present application discloses a method, device, storage medium and electronic device for generating a truck unloading process plan, which relates to the field of computer technology, specifically to artificial intelligence technologies such as deep learning and intelligent scheduling. The specific implementation solution is as follows: Obtain train information and process string information, input the train information and process string information into a preset mathematical model for the truck unloading process problem, and solve the mathematical model for the truck unloading process problem based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model for the truck unloading process problem. According to the optimal solution, determine the optimal truck unloading process plan. The present application can improve the solving efficiency of the mathematical model for the truck unloading process problem, thereby improving the efficiency of obtaining the optimal truck unloading process plan and enhancing the unloading capacity of the port.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to artificial intelligence technologies such as deep learning and intelligent scheduling, and particularly to a method, device, storage medium, and electronic device for generating a car unloading process plan. Background Art

[0002] In the related art, coal ports play an important role as transfer stations in coal transportation, unloading the coal transported by rail into the coal yard and then loading it onto ships for transportation to the destination. The car unloading process mainly consists of a connection of a car dumper, a belt conveyor, and a stacker. The car unloading plan includes arranging the car unloading time for each arriving train and the process sequence of the car dumper, belt conveyor, stacker, and storage yard, while ensuring a reasonable match between the train and the process sequence. The rationality of the car unloading plan directly affects the car unloading efficiency and further affects the throughput of the port. Summary of the Invention

[0003] This application provides a method, device, storage medium, and electronic device for generating a car unloading process plan.

[0004] According to one aspect of this application, a method for generating a car unloading process plan is provided, including:

[0005] Obtaining train information and process sequence information;

[0006] Inputting the train information and the process sequence information into a preset mathematical model of the car unloading process problem, and solving the mathematical model of the car unloading process problem based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the car unloading process problem;

[0007] Determining an optimal car unloading process plan according to the optimal solution.

[0008] According to a second aspect of this application, a device for generating a car unloading process plan is provided, including:

[0009] A first obtaining module, configured to obtain train information and process sequence information;

[0010] A second obtaining module, configured to input the train information and the process sequence information into a preset mathematical model of the car unloading process problem, and solve the mathematical model of the car unloading process problem based on a branch and bound device and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the car unloading process problem;

[0011] A determining module, configured to determine an optimal car unloading process plan according to the optimal solution.

[0012] According to a third aspect of this application, an electronic device is provided, including:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the first aspect.

[0016] According to a fourth aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are for causing the computer to execute the method described in the first aspect.

[0017] According to a fifth aspect of the present application, there is provided a computer program product including a computer program, and when the computer program is executed by a processor, the steps of the method for generating a truck unloading process plan as described in the first aspect are implemented.

[0018] According to the technical solution of the present application, the solution efficiency of the mathematical model of the truck unloading process problem can be improved through a feasible solution prediction model and a branch and bound method, thereby improving the efficiency of obtaining an optimal truck unloading process plan and enhancing the unloading capacity of the port.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Description of the Drawings

[0020] The drawings are used to better understand the present solution and do not constitute a limitation to the present application. Among them:

[0021] Figure 1 is a schematic diagram according to the first embodiment of the present application;

[0022] Figure 2 is a schematic diagram according to the second embodiment of the present application;

[0023] Figure 3 is a schematic diagram according to the third embodiment of the present application;

[0024] Figure 4 is a schematic diagram according to the fourth embodiment of the present application;

[0025] Figure 5 is a schematic diagram according to the fifth embodiment of the present application;

[0026] Figure 6 is a schematic diagram according to the sixth embodiment of the present application;

[0027] Figure 7 is a schematic diagram according to the seventh embodiment of the present application;

[0028] Figure 8 is a schematic diagram according to the eighth embodiment of the present application;

[0029] Figure 9 is a schematic diagram according to the ninth embodiment of the present application;

[0030] Figure 10 is a schematic diagram according to the tenth embodiment of the present application;

[0031] Figure 11 is a block diagram of an electronic device that can implement the method for generating a truck unloading process plan according to the embodiments of the present application. Detailed implementation manners

[0032] The following describes exemplary embodiments of the present application with reference to the accompanying drawings. Various details of the embodiments of the present application are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0033] In the related art, coal ports play an important role as transfer stations in coal transportation, unloading the coal transported by rail onto the coal yard and then loading it onto ships for transportation to the destination. The truck unloading process mainly consists of a dumper, a belt conveyor, and a stacker connected together. The truck unloading plan includes arranging the unloading time for each arriving train and the process string of the dumper, belt conveyor, stacker, and storage yard, and at the same time ensuring a reasonable match between the train and the process string. The rationality of the truck unloading plan directly affects the unloading efficiency and further affects the throughput of the port.

[0034] Based on the above problems, the present application proposes a method, device, storage medium, and electronic device for generating a truck unloading process plan, which can improve the solution efficiency of the mathematical model of the truck unloading process problem through a feasible solution prediction model and the branch and bound method, thereby improving the efficiency of obtaining the optimal truck unloading process plan and enhancing the unloading capacity of the port.

[0035] Figure 1 is a schematic diagram according to the first embodiment of the present application. It should be noted that the method for generating a truck unloading process plan in the embodiments of the present application can be used in the device for generating a truck unloading process plan in the embodiments of the present application, and this device can be configured in an electronic device. As Figure 1 shown, the method for generating a truck unloading process plan includes the following steps:

[0036] Step 101, obtain train information and process string information.

[0037] It should be noted that the above train information may be relevant information of a freight train. The above process string may be composed of multiple process steps, and the process steps may be multiple process steps for unloading goods from the train to the port yard in the port. The process string information may be relevant information of the above multiple process steps.

[0038] As a possible example, train information and process string information are obtained in advance.

[0039] Step 102: Input the train information and the process string information into a preset mathematical model of the unloading process problem, and solve the mathematical model of the unloading process problem based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the unloading process problem.

[0040] It can be understood that the above mathematical model of the unloading process problem may be a mathematical model pre-constructed according to the actual requirements of port unloading. The above feasible solution prediction model may be a pre-trained prediction model used to assist the branch and bound method in solving the mathematical model of the unloading process problem.

[0041] As a possible example, the train information and the process string information are input into a preset mathematical model of the unloading process problem. The train information and the process string information input into the preset mathematical model of the unloading process problem are solved by the branch and bound method, and a feasible solution prediction model is used to assist the branch and bound method in solving the mathematical model of the unloading process problem to obtain the optimal solution of the mathematical model of the unloading process problem. Using the feasible solution prediction model to assist the branch and bound method in solving the mathematical model of the unloading process problem can improve the speed of solving the mathematical model of the unloading process problem.

[0042] Step 103: Determine the optimal unloading process plan according to the optimal solution.

[0043] As a possible example, according to the optimal solution of the mathematical model of the unloading process problem, the unloading process plan corresponding to the optimal solution is determined, and this unloading process plan is used as the optimal unloading process plan, which can maximize the unloading volume of the port.

[0044] According to the method for generating an unloading process plan according to the embodiments of the present application, train information and process string information are obtained, the train information and the process string information are input into a preset mathematical model of the unloading process problem, and the mathematical model of the unloading process problem is solved based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the unloading process problem. According to the optimal solution, the optimal unloading process plan is determined, thereby effectively improving the solving efficiency of the mathematical model of the unloading process problem, further improving the efficiency of obtaining the optimal unloading process plan, and enhancing the unloading capacity of the port.

[0045] Optionally, in order to quickly obtain the optimal solution for the mathematical model of the car unloading process problem, the mathematical model of the car unloading process problem is solved based on the feasible solution prediction model and the branch and bound method. Figure 2 FIG. Figure 2 is a schematic diagram according to the second embodiment of the present application. It should be noted that the method for generating the car unloading process plan in the embodiments of the present application can be executed by the car unloading process plan generating device in the embodiments of the present application. In some embodiments of the present application, as Figure 2 shown, the method for generating the car unloading process plan includes:

[0046] Step 201, obtain train information and process string information.

[0047] In the embodiments of the present application, step 201 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations on this, nor will they be elaborated further.

[0048] Step 202, input the train information and the process string information into a preset mathematical model of the car unloading process problem.

[0049] It should be noted that the above train information may be related information of the train transporting goods. For example, the train information may be any one or more of the following items 1)-3): 1) the number of trains; 2) the train number; 3) the time when the train arrives at the port.

[0050] It should be noted that the above process string may be composed of multiple process links for unloading goods from the train to the port yard in the port. For example, the process string may include the link of using a dumper to transfer the goods from the train to the belt after the train arrives at the port, and also includes the link of the belt transporting the goods to the stacker, and also includes the link of the stacker stacking the goods on the yard. The process string information may be related information of the above multiple process links. For example, the process string information may be any one or more of the following items 1)-3): 1) the model and quantity of the transportation equipment involved in the process string; 2) the process link information in the process string; 3) the transportation equipment information corresponding to the process link in the process string.

[0051] As a possible example, the train information and the process string information are input into a preset mathematical model of the car unloading process problem.

[0052] As a possible example, the mathematical model of the car unloading process problem can be constructed through the following steps:

[0053] Step 2021, define the variables in the mathematical model, for example:

[0054] Define X[i] as the start time of operation of train i;

[0055] Define Y[i,j] as whether train i selects process string j;

[0056] Define Z[i1, i2] as whether the operation start time of train i1 is after i2. Z[i1, i2] is an auxiliary variable used to assist in solving for X and Y.

[0057] Step 2022, set the constraint conditions of the mathematical model, such as:

[0058] The operation start time of the train is greater than the arrival time of the train and less than the end-of-day time, Start_time[i] <= X[i] <= T, where Start_time[i] is the arrival time of train i at the port, and T is the end-of-day time of the port;

[0059] When two trains are processed collaboratively, they must use the same dumper, Y[i1, j1] = Y[i2, j2], if (i1, i2) collaborate and (j1, j2) are on the same dumper. Among them, train i1 and train i2 work collaboratively, and process strings j1 and j2 share the same dumper. It is necessary to input in the mathematical model which trains can collaborate and which process strings are on the same dumper. No other trains can be inserted between two trains when they are processed collaboratively;

[0060] The time between two conflicting process strings cannot overlap: X[i1] - X[i2] = Work_time[i2] or X[i2] - X[i1] = Work_time[i1], if (i1, i2) collaborate, where Work_time[i2] is the working time of train i2, and Work_time[i1] is the working time of train i1. If train i1 and train i2 work collaboratively, it is necessary to input the working time of each train in the mathematical model;

[0061] X[i1] - X[i2] >= Work_time[i2], if Y[i1, j1] = 1, Y[i2, j2] = 1 and (j1, j2) conflict. It is necessary to input the conflict information between process strings;

[0062] Match between trains and process strings, Y[i1, j1] = 1 if and only if (i1, j1) match. It is necessary to input the matching relationship between trains and process strings, including whether the dumper in the process can operate the train (such as not exceeding the height, consistent coal type, whether it can handle collaborative train pairs), and whether the yard in the process matches the train (such as yard location requirements, consistent coal type);

[0063] A train can choose at most one process string, sum_{j}Y[i, j] <= 1;

[0064] The order is unique, Z[i1, i2] + Z[i2, i1] = 1;

[0065] The start time of the operation determines the order: X[i1] >= X[i2] if Z[i1, i2] = 1.

[0066] Step 2023: Set the objective function of the mathematical model. For example, max sum_{i,j}Y[i,j]*Coal_weight[i] to maximize the total unloading amount during car unloading.

[0067] Step 2024: Linearize the constraint conditions and the objective function in the above mathematical model, and transform the linearized mathematical model into a standard mixed-integer linear programming problem (MILP) structure:

[0068] (P) min c T x

[0069] s.t. Ax > h

[0070]

[0071] where c T x represents the objective function: -sum_{i,j}Y[i,j]*Coal_weight[i], and Ax >= b represents the constraints. That is, the above multiple constraint conditions, and x represents the defined variables X[i], Y[i,j], Z[i1, i2]. It can be seen from the MILP structure that each MILP is uniquely determined by its (A, b, c), so (A, b, c) is used to briefly represent the above MILP structure. Take the above mixed-integer linear programming problem (MILP) structure as the problem to be branched.

[0072] Step 203: Based on the branch and bound method, train information, and process string information, branch the problem to be branched in the mathematical model of the car unloading process problem to obtain multiple sub-problems of the problem to be branched and the first feasible solution corresponding to each sub-problem.

[0073] It should be noted that before branching the problem to be branched in the mathematical model of the car unloading process problem, it is necessary to perform a linear programming relaxation process on the problem to be branched to obtain the problem to be branched after linear relaxation processing, and then branch the problem to be branched after linear relaxation processing.

[0074] As a possible example, input the train information and process string information into the mathematical model of the car unloading process problem. Through the branch and bound method, branch the problem to be branched in the mathematical model of the car unloading process problem based on the train information and process string information, decompose the problem to be branched into multiple sub-problems, and solve the multiple sub-problems to obtain the first feasible solution corresponding to each sub-problem.

[0075] Step 204: Input the multiple sub-problems into the feasible solution prediction model respectively to obtain the second feasible solutions corresponding to the multiple sub-problems respectively.

[0076] As a possible example, input the multiple sub-problems into the feasible solution prediction model respectively. The feasible solution prediction model predicts the feasible solutions of each sub-problem to obtain the second feasible solutions corresponding to the multiple sub-problems respectively.

[0077] As a possible example, the feasible solution prediction model is a pre-trained prediction model. Optionally, the prediction model can be a conditional generation model. The feasible solution prediction model can be trained by the maximum likelihood estimation method. The specific training method is as follows:

[0078] Suppose the MILP problem is M=(A, b, c), and p(x|M) represents the probability that the lower bound x of the problem M appears. Our current goal is to train a fitting function p_theta(x|M) of p(x|M). Suppose there are N problems (M1,..., MN) in the training set, and the i-th problem M i has N i feasible solutions, and the corresponding set of feasible solutions is Then the likelihood function of the problem Mi is:

[0079]

[0080] Adopting the idea of maximum likelihood estimation, we expect p_theta to make the likelihood function of each M i reach the maximum value. Therefore, the loss function can be expressed as:

[0081]

[0082] where w ij represents the corresponding weight of the corresponding integer solution: the smaller the objective function value corresponding to the integer solution, the greater the weight; p_theta is the network fitting function we constructed. By minimizing L(theta), we obtain the parameter theta and the fitting function p_theta. Once the model is trained, we can randomly generate a series of integer solutions according to the probability distribution function p_theta and select the feasible solutions from the generated integer solutions. Compared with the artificially given variable selection rules of the traditional method, the way the feasible solution prediction model selects variables is obtained by training with historical training data, which can explore the potential structure of the problem and give higher-quality feasible solutions.

[0083] Step 205: According to the first feasible solutions corresponding to the multiple sub-problems and the second feasible solutions corresponding to the multiple sub-problems respectively, perform pruning processing on the multiple sub-problems to obtain the optimal solution of the mathematical model of the truck unloading process problem.

[0084] As a possible example, based on the first feasible solutions corresponding to multiple sub-problems and the second feasible solutions corresponding to multiple sub-problems, determine the sub-problems that need to be pruned, perform pruning processing on the sub-problems that need to be pruned, and finally obtain the optimal solution of the mathematical model of the car unloading process problem.

[0085] Step 206, determine the optimal car unloading process plan according to the optimal solution.

[0086] For example, obtain the optimal solutions of variables X[i] and Y[i,j]. According to the optimal solutions of variables X[i] and Y[i,j], determine the corresponding relationship between train i and process string j, so as to obtain the optimal car unloading process plan.

[0087] According to the method for generating a car unloading process plan according to an embodiment of the present application, input train information and process string information into a preset mathematical model of the car unloading process problem. Based on the branch and bound method, train information and process string information, perform branching processing on the problem to be branched in the mathematical model of the car unloading process problem to obtain multiple sub-problems of the problem to be branched and the first feasible solutions corresponding to the multiple sub-problems. Input the multiple sub-problems into a feasible solution prediction model respectively to obtain the second feasible solutions corresponding to the multiple sub-problems. According to the first feasible solutions corresponding to the multiple sub-problems and the second feasible solutions corresponding to the multiple sub-problems, perform pruning processing on the multiple sub-problems to obtain the optimal solution of the mathematical model of the car unloading process problem, thereby realizing quickly obtaining the optimal solution of the mathematical model of the car unloading process problem based on the feasible solution prediction model, and further improving the speed of obtaining the optimal car unloading process plan.

[0088] To obtain the optimal solution of the mathematical model of the car unloading process problem, optionally, compare the upper bound and the lower bound of the sub-problem to determine whether pruning needs to be performed on the sub-problem. Figure 3 It is a schematic diagram according to the third embodiment of the present application. It should be noted that the method for generating a car unloading process plan according to an embodiment of the present application can be executed by the car unloading process plan generating device in the embodiment of the present application. In some embodiments of the present application, as Figure 3 shown, the method for generating a car unloading process plan includes:

[0089] Step 301, obtain train information and process string information.

[0090] In the embodiment of the present application, step 301 can be implemented in any one of the embodiments of the present application respectively. The embodiments of the present application do not make any limitations on this and will not be elaborated any further.

[0091] Step 302, input the train information and the process string information into a preset mathematical model of the car unloading process problem.

[0092] In an embodiment of the present application, step 302 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0093] Step 303: Based on the branch and bound method, train information, and process string information, perform branching processing on the problem to be branched in the mathematical model of the unloading process problem, and obtain multiple sub-problems of the problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems.

[0094] In an embodiment of the present application, step 303 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0095] Step 304: Input the multiple sub-problems into the feasible solution prediction model respectively, and obtain the second feasible solution corresponding to each of the multiple sub-problems.

[0096] In an embodiment of the present application, step 304 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0097] Step 305: Based on the first feasible solution of the current sub-problem, determine the lower bound of the current sub-problem.

[0098] It can be understood that in the branch and bound method, each sub-problem has a corresponding upper bound and lower bound, and it is necessary to determine the upper bound and lower bound of each sub-problem to implement the bounding process for the problem to be decomposed.

[0099] As a possible example, determine the lower bound value of the current sub-problem according to the first feasible solution of the current sub-problem.

[0100] Step 306: Based on the second feasible solution of the current sub-problem, determine the upper bound of the current sub-problem.

[0101] It should be noted that steps 305 and 306 do not distinguish the execution order.

[0102] As a possible example, determine the upper bound value of the current sub-problem according to the second feasible solution of the current sub-problem.

[0103] Step 307: In response to the upper bound being less than the lower bound, use the current sub-problem as the new problem to be branched, and execute the step of performing branching processing on the problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method to obtain multiple sub-problems of the problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems, that is, return to step 303.

[0104] As a possible example, compare the upper bound and the lower bound. In response to the upper bound being less than the lower bound, it indicates that the current sub-problem can continue to be branched. Therefore, take the current sub-problem as the new sub-problem to be branched, and perform branching on the sub-problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method to obtain multiple sub-problems of the sub-problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems.

[0105] Step 308, in response to the upper bound being greater than the lower bound, prune the current sub-problem.

[0106] As a possible example, compare the upper bound and the lower bound. In response to the upper bound being greater than the lower bound, it indicates that the current sub-problem does not need to be further branched, and prune the current sub-problem. After pruning is completed, continue to determine the lower bound of the sub-problem based on the first feasible solution of the next sub-problem, that is, execute step 305.

[0107] Step 309, in response to the upper bound being equal to the lower bound, determine the first feasible solution as the optimal solution of the mathematical model of the unloading process problem.

[0108] It should be noted that steps 307, 308, and 309 do not distinguish the order of execution.

[0109] As a possible example, compare the upper bound and the lower bound. In response to the upper bound being equal to the lower bound, it indicates that the first feasible solution of the current sub-problem is the optimal solution of the mathematical model of the unloading process problem.

[0110] Step 310, determine the optimal unloading process plan according to the optimal solution.

[0111] In the embodiments of the present application, step 310 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0112] According to the method for generating an unloading process plan in the embodiments of the present application, based on the first feasible solution of the current sub-problem, determine the lower bound of the current sub-problem, based on the second feasible solution of the current sub-problem, determine the upper bound of the current sub-problem. In response to the upper bound being less than the lower bound, take the current sub-problem as the new sub-problem to be branched, and execute the step of performing branching on the sub-problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method to obtain multiple sub-problems of the sub-problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems. In response to the upper bound being greater than the lower bound, prune the current sub-problem. In response to the upper bound being equal to the lower bound, determine the first feasible solution as the optimal solution of the mathematical model of the unloading process problem, thereby realizing rapid pruning of the sub-problem, and further improving the efficiency of obtaining the optimal solution of the mathematical model of the unloading process problem.

[0113] In order to determine whether a current sub - problem needs to be pruned based on a lower bound and an upper bound, optionally, calculate a first objective function value of a first feasible solution. Figure 4 FIG. Figure 4 is a schematic diagram according to the fourth embodiment of the present application. It should be noted that the method for generating a truck - unloading process plan in the embodiments of the present application can be executed by the truck - unloading process plan generation device in the embodiments of the present application. In some embodiments of the present application, as Figure 4 shown, the method for generating a truck - unloading process plan includes:

[0114] Step 401, obtain train information and process string information.

[0115] In the embodiments of the present application, step 401 can be implemented in any one of the ways in the respective embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0116] Step 402, input the train information and the process string information into a preset mathematical model of the truck - unloading process problem.

[0117] In the embodiments of the present application, step 402 can be implemented in any one of the ways in the respective embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0118] Step 403, based on the branch - and - bound method, the train information, and the process string information, perform a branching process on the sub - problems to be branched in the mathematical model of the truck - unloading process problem, and obtain multiple sub - problems of the sub - problems to be branched and first feasible solutions respectively corresponding to the multiple sub - problems.

[0119] In the embodiments of the present application, step 403 can be implemented in any one of the ways in the respective embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0120] Step 404, input the multiple sub - problems into a feasible solution prediction model respectively, and obtain second feasible solutions respectively corresponding to the multiple sub - problems.

[0121] In the embodiments of the present application, step 404 can be implemented in any one of the ways in the respective embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0122] Step 405, in response to the first feasible solution satisfying the preset constraint conditions of the mathematical model of the truck - unloading process problem, calculate a first objective function value of the first feasible solution based on the preset objective function of the mathematical model of the truck - unloading process problem.

[0123] It can be understood that the first feasible solution needs to satisfy all the preset constraint conditions of the mathematical model of the truck - unloading process problem.

[0124] As a possible example, in response to the first feasible solution satisfying the preset constraint conditions of the mathematical model of the truck unloading process problem, based on the preset objective function of the mathematical model of the truck unloading process problem, calculate the first objective function value of the first feasible solution.

[0125] Step 406, determine the lower bound of the current sub-problem as the first objective function value.

[0126] As a possible example, use the first objective function value as the lower bound of the current sub-problem.

[0127] Step 407, based on the second feasible solution of the current sub-problem, determine the upper bound of the current sub-problem.

[0128] In the embodiments of the present application, step 404 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not be elaborated further.

[0129] Step 408, in response to the upper bound being less than the lower bound, take the current sub-problem as the new sub-problem to be branched, and perform the branching process on the sub-problem to be branched in the mathematical model of the truck unloading process problem based on the branch and bound method to obtain multiple sub-problems of the sub-problem to be branched and the first feasible solutions respectively corresponding to the multiple sub-problems.

[0130] In the embodiments of the present application, step 408 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not be elaborated further.

[0131] Step 409, in response to the upper bound being greater than the lower bound, prune the current sub-problem, continue to bound the next sub-problem, and based on the first feasible solution of the next sub-problem, that is, execute step 405.

[0132] In the embodiments of the present application, step 409 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not be elaborated further.

[0133] Step 410, in response to the upper bound being equal to the lower bound, determine the first feasible solution as the optimal solution of the mathematical model of the truck unloading process problem.

[0134] In the embodiments of the present application, step 410 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not be elaborated further.

[0135] Step 411, according to the optimal solution, determine the optimal truck unloading process plan.

[0136] In the embodiments of the present application, step 411 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not limit this and will not be elaborated further.

[0137] According to the method for generating a truck unloading process plan according to an embodiment of the present application, in response to the first feasible solution satisfying the preset constraint conditions of the mathematical model of the truck unloading process problem, based on the preset objective function of the mathematical model of the truck unloading process problem, calculate the first objective function value of the first feasible solution, and determine the first objective function value as the lower bound of the current sub-problem, so that it is possible to determine whether the current sub-problem needs to be pruned according to the lower bound and the upper bound.

[0138] Optionally, calculate the second objective function value of the second feasible solution in order to be able to determine whether the current sub-problem needs to be pruned according to the lower bound and the upper bound. Figure 5 It is a schematic diagram according to the fifth embodiment of the present application. It should be noted that the method for generating a truck unloading process plan according to the embodiment of the present application can be executed by the device for generating a truck unloading process plan in the embodiment of the present application. In some embodiments of the present application, as Figure 5 shown, the method for generating a truck unloading process plan includes:

[0139] Step 501, obtain train information and process string information.

[0140] In the embodiments of the present application, step 501 can be implemented in any one of the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0141] Step 502, input the train information and the process string information into a preset mathematical model of the truck unloading process problem.

[0142] In the embodiments of the present application, step 502 can be implemented in any one of the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0143] Step 503, based on the branch and bound method, the train information and the process string information, perform a branching process on the problem to be branched in the mathematical model of the truck unloading process problem, and obtain a plurality of sub-problems of the problem to be branched and the first feasible solution corresponding to each of the plurality of sub-problems.

[0144] In the embodiments of the present application, step 503 can be implemented in any one of the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0145] Step 504, input the plurality of sub-problems into a feasible solution prediction model respectively, and obtain the second feasible solution corresponding to each of the plurality of sub-problems.

[0146] In the embodiments of the present application, step 504 can be implemented in any one of the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0147] Step 505: Determine the lower bound of the current sub-problem based on the first feasible solution of the current sub-problem.

[0148] In the embodiments of the present application, step 505 can be implemented in any of the ways in the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0149] Step 506: In response to the second feasible solution satisfying the preset constraint conditions of the mathematical model of the truck unloading process problem, calculate the second objective function value of the second feasible solution based on the preset objective function of the mathematical model of the truck unloading process problem.

[0150] It can be understood that the second feasible solution needs to satisfy all the preset constraint conditions of the mathematical model of the truck unloading process problem.

[0151] As a possible example, in response to the second feasible solution satisfying the preset constraint conditions of the mathematical model of the truck unloading process problem, calculate the second objective function value of the second feasible solution based on the preset objective function of the mathematical model of the truck unloading process problem.

[0152] Step 507: Determine the upper bound of the current sub-problem as the second objective function value.

[0153] As a possible example, take the second objective function value as the upper bound of the current sub-problem.

[0154] Step 508: In response to the upper bound being less than the lower bound, take the current sub-problem as the new sub-problem to be branched, and perform the branching process on the sub-problem to be branched in the mathematical model of the truck unloading process problem based on the branch and bound method to obtain multiple sub-problems of the sub-problem to be branched and the first feasible solutions corresponding to the multiple sub-problems respectively.

[0155] In the embodiments of the present application, step 508 can be implemented in any of the ways in the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0156] Step 509: In response to the upper bound being greater than the lower bound, prune the current sub-problem, continue to bound the next sub-problem, and based on the first feasible solution of the next sub-problem, that is, execute step 505.

[0157] In the embodiments of the present application, step 509 can be implemented in any of the ways in the various embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0158] Step 510: In response to the upper bound being equal to the lower bound, determine the first feasible solution as the optimal solution of the mathematical model of the truck unloading process problem.

[0159] In the embodiments of the present application, step 510 can be implemented in any one of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0160] Step 511, determine the optimal unloading process plan according to the optimal solution.

[0161] In the embodiments of the present application, step 511 can be implemented in any one of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0162] According to the method for generating an unloading process plan in the embodiments of the present application, in response to the second feasible solution satisfying the preset constraint conditions of the mathematical model of the unloading process problem, based on the preset objective function of the mathematical model of the unloading process problem, calculate the second objective function value of the second feasible solution, and determine the second objective function value as the upper bound of the current sub-problem, so that it is possible to determine whether the current sub-problem needs to be pruned according to the lower bound and the upper bound.

[0163] Optionally, in order to select a better feasible solution among multiple feasible solutions of the same sub-problem, calculate the objective function values of the multiple feasible solutions respectively, and compare the objective function values of the multiple feasible solutions respectively. Figure 6 It is a schematic diagram according to the second embodiment of the present application. It should be noted that the method for generating an unloading process plan in the embodiments of the present application can be executed by the device for generating an unloading process plan in the embodiments of the present application. In some embodiments of the present application, such as Figure 6 shown, the method for generating an unloading process plan includes:

[0164] Step 601, obtain train information and process string information.

[0165] In the embodiments of the present application, step 601 can be implemented in any one of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0166] Step 602, input the train information and the process string information into a preset mathematical model of the unloading process problem.

[0167] In the embodiments of the present application, step 602 can be implemented in any one of the ways in the embodiments of the present application. The embodiments of the present application do not limit this and will not elaborate further.

[0168] Step 603, based on the branch and bound method, train information and process string information, perform branching processing on the problem to be branched in the mathematical model of the unloading process problem, and obtain multiple sub-problems of the problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems.

[0169] In an embodiment of the present application, step 603 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0170] Step 604: Input multiple sub-problems into the feasible solution prediction model respectively to obtain multiple intermediate feasible solutions corresponding to each of the multiple sub-problems.

[0171] It can be understood that after inputting a sub-problem into the feasible solution prediction model, multiple predicted feasible solutions of the sub-problem can be obtained, that is, the above-mentioned intermediate feasible solutions.

[0172] As a possible example, input multiple sub-problems into the feasible solution prediction model respectively. The feasible solution prediction model predicts feasible solutions for the multiple sub-problems to obtain multiple intermediate feasible solutions corresponding to each of the multiple sub-problems.

[0173] Step 605: Calculate the objective function values of multiple intermediate feasible solutions of the same sub-problem respectively based on the preset objective function of the unloading process problem mathematical model.

[0174] As a possible example, calculate the objective function values corresponding to multiple intermediate feasible solutions of each sub-problem respectively based on the preset objective function of the unloading process problem mathematical model.

[0175] Step 606: Determine the intermediate feasible solution with the smallest objective function value as the second feasible solution corresponding to the sub-problem.

[0176] It can be understood that the smaller the objective function value, the higher the quality of the feasible solution, and thus a better upper bound can be obtained, so as to better bound the sub-problems to be decomposed.

[0177] As a possible example, use the intermediate feasible solution with the smallest objective function value as the second feasible solution corresponding to the sub-problem.

[0178] Step 607: Perform pruning processing on multiple sub-problems according to the first feasible solutions corresponding to each of the multiple sub-problems and the second feasible solutions corresponding to each of the multiple sub-problems to obtain the optimal solution of the unloading process problem mathematical model.

[0179] In an embodiment of the present application, step 607 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0180] Step 608: Determine the optimal unloading process plan according to the optimal solution.

[0181] In an embodiment of the present application, step 608 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0182] According to the method for generating a truck unloading process plan according to an embodiment of the present application, a plurality of sub-problems are respectively input into a feasible solution prediction model to obtain a plurality of intermediate feasible solutions corresponding to each of the plurality of sub-problems. Based on a preset objective function of the mathematical model of the truck unloading process problem, the objective function values of the plurality of intermediate feasible solutions of the same sub-problem are calculated, and the intermediate feasible solution with the smallest objective function value is determined as the second feasible solution corresponding to the sub-problem, so as to select a better feasible solution from the plurality of feasible solutions, thereby further improving the efficiency of obtaining the optimal solution of the mathematical model of the truck unloading process problem.

[0183] Optionally, in order to reduce the amount of data input into the mathematical model of the truck unloading process problem, weight distribution is performed on the unloading equipment, and the available truck unloading process strings are determined according to the weights. Figure 7 It is a schematic diagram according to the second embodiment of the present application. It should be noted that the method for generating a truck unloading process plan according to an embodiment of the present application can be executed by the truck unloading process plan generating device in the embodiment of the present application. In some embodiments of the present application, as Figure 7 shown, the method for generating a truck unloading process plan includes:

[0184] Step 701, obtain train information.

[0185] In the embodiments of the present application, step 701 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations on this and will not be elaborated further.

[0186] Step 702, obtain unloading equipment information.

[0187] It should be noted that the execution order of step 701 and step 702 is not distinguished.

[0188] As a possible example, the unloading equipment information may be any one or more of the following items 1)-3): 1) the number of unloading equipment; 2) the model of the unloading equipment; 3) the historical usage frequency of the unloading equipment; 4) the historical usage frequency of the unloading equipment for each process string.

[0189] Step 703, determine the weight ratio between a plurality of unloading equipment according to the unloading equipment information.

[0190] As a possible example, the historical usage frequency of each of the plurality of unloading equipment can be determined according to the unloading equipment information, the weight value of each of the plurality of unloading equipment can be determined according to the historical usage frequency of each of the plurality of unloading equipment, and the weight ratio between the plurality of unloading equipment can be determined based on the weight values of each of the plurality of unloading equipment.

[0191] Step 704, determine the required quantity of the unloading process string for each of the plurality of unloading equipment according to the weight ratio and the total required quantity of the preset process string.

[0192] As a possible example, based on the weight ratios among multiple unloading devices and the weight ratios among multiple unloading devices, determine the required quantity of unloading process strings for each of the multiple unloading devices.

[0193] Step 705: Based on the process string information and the required quantity of unloading process strings for each of the multiple unloading devices, determine the available unloading process strings for each of the multiple unloading devices.

[0194] As a possible example, based on the process string information, determine the historical usage frequencies of each of the multiple unloading process strings. Based on the historical usage frequencies of each of the multiple unloading process strings and the required quantity of unloading process strings for each of the multiple unloading devices, determine the available unloading process strings for each of the multiple unloading devices.

[0195] For example, obtain from historical data the process strings with high usage frequencies for each stacker. Different stackers can reach different storage yards. Allocate weights to the stackers based on their usage frequencies. For example: Stacker 1 can reach Storage Yards 1 and 2, and Stacker 2 can reach Storage Yards 3 and 4. Stacker 1 was used a total of 1000 times throughout last year, and Stacker 2 was used a total of 2000 times. Then assign Stacker 2 a weight twice that of Stacker 1. Then, based on the weights, select for each stacker the process strings with higher historical usage frequencies as the available unloading process strings. For example: The weight of Stacker 2 is twice that of Stacker 1. Now we plan to select a total of 30 process strings. Then, based on the weights, select the top 10 process strings with the most usage times last year for Stacker 1 and the top 20 process strings with the most usage times last year for Stacker 2 to form a total of 30 available unloading process strings.

[0196] Step 706: Determine the unloading device information and the available unloading process strings for each of the multiple unloading devices as the process string information.

[0197] As a possible example, use the unloading device information and the available unloading process strings for each of the multiple unloading devices as the process string information.

[0198] Step 707: Input the train information and the process string information into a preset mathematical model for the unloading process problem, and solve the mathematical model for the unloading process problem based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model for the unloading process problem.

[0199] In the embodiments of the present application, Step 707 can be implemented in any of the ways in the respective embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0200] Step 708: Based on the optimal solution, determine the optimal unloading process plan.

[0201] In an embodiment of the present application, step 708 can be implemented in any one of the embodiments of the present application. The embodiments of the present application do not make any limitations in this regard and will not be elaborated further.

[0202] A method for generating a truck unloading process plan according to an embodiment of the present application includes obtaining truck unloading equipment information, determining a weight ratio between multiple truck unloading equipment according to the truck unloading equipment information, determining the required quantity of truck unloading process strings for each of the multiple truck unloading equipment according to the weight ratio and the total required quantity of process strings preset, determining the available truck unloading process strings for each of the multiple truck unloading equipment according to the process string information and the required quantity of truck unloading process strings for each of the multiple truck unloading equipment, and determining the truck unloading equipment information and the available truck unloading process strings for each of the multiple truck unloading equipment as the process string information, thereby reducing the amount of data input into the mathematical model of the truck unloading process problem, further reducing the solution range of the mathematical model of the truck unloading process problem, and further improving the efficiency of solving the mathematical model of the truck unloading process problem.

[0203] To implement the above embodiments, the present application proposes a device for generating a truck unloading process plan.

[0204] Figure 8 It is a schematic diagram according to the eighth embodiment of the present application. As Figure 8 shown, the device includes: a first acquisition module 801, a second acquisition module 802, and a determination module 803.

[0205] The first acquisition module 801 is configured to acquire train information and process string information;

[0206] The second acquisition module 802 is configured to input the train information and the process string information into a preset mathematical model of the truck unloading process problem, and solve the mathematical model of the truck unloading process problem based on a branch and bound device and a pre-trained feasible solution prediction model to obtain an optimal solution of the mathematical model of the truck unloading process problem;

[0207] The determination module 803 is configured to determine an optimal truck unloading process plan according to the optimal solution.

[0208] The device for generating a truck unloading process plan according to an embodiment of the present application acquires train information and process string information, inputs the train information and the process string information into a preset mathematical model of the truck unloading process problem, solves the mathematical model of the truck unloading process problem based on a branch and bound method and a pre-trained feasible solution prediction model to obtain an optimal solution of the mathematical model of the truck unloading process problem, and determines an optimal truck unloading process plan according to the optimal solution, thereby effectively improving the solution efficiency of the mathematical model of the truck unloading process problem, further improving the efficiency of obtaining an optimal truck unloading process plan, and enhancing the unloading capacity of the port.

[0209] To implement the above embodiments, the present application proposes a device for generating a truck unloading process plan.

[0210] Figure 9 It is a schematic diagram according to the eighth embodiment of the present application. As Figure 9 shown, the device includes: a first acquisition module 910, a second acquisition module 920, and a determination module 930. Among them, the second acquisition module 920 includes: a first input sub-module 921, a branching sub-module 922, a second input sub-module 923, and a pruning sub-module 924.

[0211] The first acquisition module 910 is configured to acquire train information and process string information;

[0212] The second acquisition module 920 is configured to input the train information and the process string information into a preset mathematical model of the unloading process problem, and solve the mathematical model of the unloading process problem based on a branch and bound device and a pre-trained feasible solution prediction model to obtain an optimal solution of the mathematical model of the unloading process problem;

[0213] Among them, the second acquisition module 920 includes:

[0214] The first input sub-module 921 is configured to input the train information and the process string information into a preset mathematical model of the unloading process problem;

[0215] The branching sub-module 922 is configured to perform a branching process on the problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method, train information, and process string information to obtain multiple sub-problems of the problem to be branched and first feasible solutions respectively corresponding to the multiple sub-problems;

[0216] The second input sub-module 923 is configured to input the multiple sub-problems into the feasible solution prediction model respectively to obtain second feasible solutions respectively corresponding to the multiple sub-problems;

[0217] Among them, the second input sub-module 923 is specifically configured to: input the multiple sub-problems into the feasible solution prediction model respectively to obtain multiple intermediate feasible solutions respectively corresponding to the multiple sub-problems, calculate the objective function values of the multiple intermediate feasible solutions of the same sub-problem based on a preset objective function of the mathematical model of the unloading process problem, and determine the intermediate feasible solution with the smallest objective function value as the second feasible solution corresponding to the sub-problem.

[0218] The pruning sub-module 924 is configured to perform a pruning process on the multiple sub-problems according to the first feasible solutions respectively corresponding to the multiple sub-problems and the second feasible solutions respectively corresponding to the multiple sub-problems to obtain an optimal solution of the mathematical model of the unloading process problem.

[0219] Among them, the pruning sub-module is specifically used for: determining the lower bound of the current sub-problem based on the first feasible solution of the current sub-problem, determining the upper bound of the current sub-problem based on the second feasible solution of the current sub-problem, in response to the upper bound being less than the lower bound, taking the current sub-problem as a new sub-problem to be branched, and performing the step of branching the sub-problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method to obtain multiple sub-problems of the sub-problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems; in response to the upper bound being greater than the lower bound, pruning the current sub-problem; in response to the upper bound being equal to the lower bound, determining the first feasible solution as the optimal solution of the mathematical model of the unloading process problem.

[0220] Optionally, in some embodiments of the present application, the pruning sub-module is further used for: in response to the first feasible solution satisfying the preset constraint conditions of the mathematical model of the unloading process problem, calculating the first objective function value of the first feasible solution based on the preset objective function of the mathematical model of the unloading process problem, and determining the first objective function value as the lower bound of the current sub-problem.

[0221] Optionally, in some embodiments of the present application, the pruning sub-module is further used for: in response to the second feasible solution satisfying the preset constraint conditions of the mathematical model of the unloading process problem, calculating the second objective function value of the second feasible solution based on the preset objective function of the mathematical model of the unloading process problem, and determining the second objective function value as the upper bound of the current sub-problem.

[0222] The determination module 930 is used to determine the optimal unloading process plan according to the optimal solution.

[0223] The unloading process plan generation device according to the embodiment of the present application inputs the train information and the process string information into a preset mathematical model of the unloading process problem, branches the sub-problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method, the train information, and the process string information to obtain multiple sub-problems of the sub-problem to be branched and the first feasible solution corresponding to each of the multiple sub-problems, inputs the multiple sub-problems into the feasible solution prediction model respectively to obtain the second feasible solution corresponding to each of the multiple sub-problems, and performs pruning processing on the multiple sub-problems according to the first feasible solution corresponding to each of the multiple sub-problems and the second feasible solution corresponding to each of the multiple sub-problems to obtain the optimal solution of the mathematical model of the unloading process problem, thereby realizing quickly obtaining the optimal solution of the mathematical model of the unloading process problem based on the feasible solution prediction model, and further improving the speed of obtaining the optimal unloading process plan.

[0224] To implement the above embodiments, the present application proposes an unloading process plan generation device.

[0225] Figure 10 It is a schematic diagram according to the eighth embodiment of the present application. As Figure 10As shown in the figure, the device includes: a first acquisition module 1010, a second acquisition module 1020, and a determination module 1030. Among them, the first acquisition module 1010 includes: an acquisition sub-module 1011, a first determination sub-module 1012, a second determination sub-module 1013, a third determination sub-module 1014, and a fourth determination sub-module 1015.

[0226] The first acquisition module 1010 is used to acquire train information and process string information.

[0227] Among them, the first acquisition module 1010 includes:

[0228] The acquisition sub-module 1011 is used to acquire unloader information.

[0229] The first determination sub-module 1012 is used to determine the weight ratio between multiple unloaders according to the unloader information.

[0230] The second determination sub-module 1013 is used to determine the required quantity of the unloading process string for each of the multiple unloaders according to the weight ratio and the total required quantity of the preset process string.

[0231] The third determination sub-module 1014 is used to determine the available unloading process strings for each of the multiple unloaders according to the process string information and the required quantity of the unloading process string for each of the multiple unloaders.

[0232] The fourth determination sub-module 1015 is used to determine the unloader information and the available unloading process strings for each of the multiple unloaders as the process string information.

[0233] The second acquisition module 1020 is used to input the train information and the process string information into a preset mathematical model of the unloading process problem, and solve the mathematical model of the unloading process problem based on a branch and bound device and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the unloading process problem.

[0234] The determination module 1030 is used to determine the optimal unloading process plan according to the optimal solution.

[0235] The device for generating the truck unloading process plan according to the embodiment of the present application obtains the truck unloading equipment information, determines the weight ratio among multiple truck unloading equipment according to the truck unloading equipment information, determines the required quantity of the truck unloading process string for each of the multiple truck unloading equipment according to the weight ratio and the total required quantity of the preset process string, determines the available truck unloading process string for each of the multiple truck unloading equipment according to the process string information and the required quantity of the truck unloading process string for each of the multiple truck unloading equipment, and determines the truck unloading equipment information and the available truck unloading process string for each of the multiple truck unloading equipment as the process string information, thereby reducing the amount of data input into the mathematical model of the truck unloading process problem, further reducing the solution range of the mathematical model of the truck unloading process problem, and further improving the efficiency of solving the mathematical model of the truck unloading process problem.

[0236] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0237] As Figure 11 shown, it is a block diagram of an electronic device for the method of generating a truck unloading process plan according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described herein and / or required by the present application.

[0238] As Figure 11 shown, the electronic device includes: one or more processors 1101, a memory 1102, and an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component is interconnected using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the electronic device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (such as, as a server array, a group of blade servers, or a multi-processor system). Figure 11 One processor 1101 is taken as an example herein.

[0239] The memory 1102 is a non-transitory computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable at least one processor to execute the method for generating a vehicle unloading process solution provided in the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to execute the method for generating a vehicle unloading process solution provided in the present application.

[0240] The memory 1102 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the method for generating a truck unloading process solution in the embodiment of the present application (for example, the attached Figure 8 The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, that is, the method for generating the unloading process plan in the above method embodiment is implemented.

[0241] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created by the use of the electronic device generated according to the unloading process scheme, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device generated by the unloading process scheme via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0242] The electronic device of the method for generating a truck unloading process plan may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 11 The example of connecting through bus is taken in the following.

[0243] The input device 1103 can receive input digital or character information and generate key signal inputs related to user settings and function controls of the electronic device for generating the unloading process plan, such as input devices like touchscreens, keypads, mice, trackpads, touchpads, pointing sticks, one or more mouse buttons, trackballs, joysticks, etc. The output device 1104 can include display devices, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibration motors), etc. The display device can include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device can be a touchscreen.

[0244] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0245] These computing programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disks, optical disks, memories, programmable logic devices (PLDs)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term “machine-readable signal” refers to any signal for providing machine instructions and / or data to a programmable processor.

[0246] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input received from the user can be in any form (including acoustic input, voice input, or tactile input).

[0247] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), the Internet, and blockchain network.

[0248] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server can also be a server of a distributed system, or a server combined with blockchain.

[0249] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved, and no limitation is imposed herein.

[0250] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A method for generating a truck unloading process plan, comprising: Obtaining train information and process string information; wherein, the process string is composed of multiple process links, and the multiple process links include the process link of the port unloading goods from the train to the port yard, and the process string information includes the relevant information of the multiple process links; Inputting the train information and the process string information into a preset mathematical model of the truck unloading process problem, and solving the mathematical model of the truck unloading process problem based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the truck unloading process problem; the mathematical model of the truck unloading process problem is a mathematical model pre-constructed according to the actual requirements of port unloading, the feasible solution prediction model is a conditional generation model, the feasible solution prediction model is trained based on the maximum likelihood estimation method, and the feasible solution prediction model is used to assist the branch and bound method in solving the mathematical model of the truck unloading process problem; Determining an optimal truck unloading process plan according to the optimal solution; Wherein, the step of solving the mathematical model of the truck unloading process problem based on the branch and bound method and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the truck unloading process problem includes: Based on the branch and bound method, the train information and the process string information, branching the sub-problems to be branched in the mathematical model of the truck unloading process problem to obtain multiple sub-problems of the sub-problems to be branched and the first feasible solutions corresponding to the multiple sub-problems respectively; wherein, in the branch and bound method, each sub-problem has a corresponding upper bound and lower bound, and the bounding process of the sub-problem to be branched is realized based on the upper bounds and lower bounds of the multiple sub-problems respectively; Inputting the multiple sub-problems into the feasible solution prediction model respectively, and the feasible solution prediction model predicts the feasible solutions of each sub-problem to obtain the second feasible solutions corresponding to the multiple sub-problems respectively; wherein, the first feasible solution is used to determine the lower bound of the corresponding sub-problem, and the second feasible solution is used to determine the upper bound of the corresponding sub-problem; According to the first feasible solutions corresponding to the multiple sub-problems and the second feasible solutions corresponding to the multiple sub-problems, pruning the multiple sub-problems to obtain the optimal solution of the mathematical model of the truck unloading process problem.

2. The method according to claim 1, wherein The step of pruning the multiple sub-problems according to the first feasible solutions corresponding to the multiple sub-problems and the second feasible solutions corresponding to the multiple sub-problems to obtain the optimal solution of the mathematical model of the truck unloading process problem includes: Determining the lower bound of the current sub-problem based on the first feasible solution of the current sub-problem; Determining the upper bound of the current sub-problem based on the second feasible solution of the current sub-problem; In response to the upper bound being less than the lower bound, taking the current sub-problem as a new sub-problem to be branched, and executing the step of branching the sub-problems to be branched in the mathematical model of the truck unloading process problem based on the branch and bound method to obtain multiple sub-problems of the sub-problems to be branched and the first feasible solutions corresponding to the multiple sub-problems respectively; In response to the upper bound being greater than the lower bound, pruning the current sub-problem; In response to the upper bound being equal to the lower bound, determining the first feasible solution as the optimal solution of the mathematical model of the car unloading process problem.

3. The method according to claim 2, wherein The determining the lower bound of the current sub-problem based on the first feasible solution of the current sub-problem includes: In response to the first feasible solution satisfying the preset constraint conditions of the mathematical model of the car unloading process problem, calculating a first objective function value of the first feasible solution based on the preset objective function of the mathematical model of the car unloading process problem; Determining the first objective function value as the lower bound of the current sub-problem.

4. The method according to claim 2, wherein The determining the upper bound of the current sub-problem based on the second feasible solution of the current sub-problem includes: In response to the second feasible solution satisfying the preset constraint conditions of the mathematical model of the car unloading process problem, calculating a second objective function value of the second feasible solution based on the preset objective function of the mathematical model of the car unloading process problem; Determining the second objective function value as the upper bound of the current sub-problem.

5. The method according to claim 1, wherein, The inputting the multiple sub-problems into the feasible solution prediction model respectively to obtain the second feasible solution corresponding to each of the multiple sub-problems includes: Inputting the multiple sub-problems into the feasible solution prediction model respectively to obtain multiple intermediate feasible solutions corresponding to each of the multiple sub-problems; Calculating the objective function values of the multiple intermediate feasible solutions of the same sub-problem based on the preset objective function of the mathematical model of the car unloading process problem; Determining the intermediate feasible solution with the smallest objective function value as the second feasible solution corresponding to the sub-problem.

6. The method according to claim 1, wherein The obtaining the process string information includes: Obtaining car unloading equipment information; Determining the weight ratio between the multiple car unloading equipment according to the car unloading equipment information; Determining the car unloading process string requirement quantity of each of the multiple car unloading equipment according to the weight ratio and the total quantity of the preset process string requirements; Determining the available car unloading process strings of each of the multiple car unloading equipment according to the process string information and the car unloading process string requirement quantity of each of the multiple car unloading equipment; Determining the car unloading equipment information and the available car unloading process strings of each of the multiple car unloading equipment as the process string information.

7. A car unloading process plan generation device, comprising: A first acquisition module, configured to acquire train information and process string information; wherein, the process string consists of multiple process links, the multiple process links include the process link of the port unloading goods from the train to the port yard, and the process string information includes the relevant information of the multiple process links; A second acquisition module, configured to input the train information and the process string information into a preset mathematical model of the car unloading process problem, and solve the mathematical model of the car unloading process problem based on a branch and bound device and a pre-trained feasible solution prediction model to obtain the optimal solution of the mathematical model of the car unloading process problem; the mathematical model of the car unloading process problem is a mathematical model pre-constructed according to the actual requirements of port unloading, the feasible solution prediction model is a conditional generation model, the feasible solution prediction model is trained based on the maximum likelihood estimation method, and the feasible solution prediction model is used to assist the branch and bound method in solving the mathematical model of the car unloading process problem; A determination module, configured to determine an optimal car unloading process plan according to the optimal solution; Among them, the second acquisition module includes: A first input sub-module, configured to input the train information and the process string information into a preset mathematical model of the unloading process problem; A branching sub-module, configured to perform a branching process on the problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method, the train information, and the process string information, to obtain multiple sub-problems of the problem to be branched and first feasible solutions corresponding to the multiple sub-problems respectively; wherein, in the branch and bound method, each sub-problem has a corresponding upper bound and a lower bound, and the bounding process of the problem to be branched is implemented based on the upper bounds and lower bounds of the multiple sub-problems respectively; A second input sub-module, configured to input the multiple sub-problems into the feasible solution prediction model respectively, and the feasible solution prediction model predicts the feasible solutions of each sub-problem to obtain second feasible solutions corresponding to the multiple sub-problems respectively; wherein, the first feasible solution is used to determine the lower bound of the corresponding sub-problem, and the second feasible solution is used to determine the upper bound of the corresponding sub-problem; A pruning sub-module, configured to perform a pruning process on the multiple sub-problems according to the first feasible solutions corresponding to the multiple sub-problems and the second feasible solutions corresponding to the multiple sub-problems, to obtain the optimal solution of the mathematical model of the unloading process problem.

8. The device according to claim 7, wherein Specifically, the pruning sub-module is configured to: Determine the lower bound of the current sub-problem based on the first feasible solution of the current sub-problem; Determine the upper bound of the current sub-problem based on the second feasible solution of the current sub-problem; In response to the upper bound being less than the lower bound, use the current sub-problem as a new problem to be branched, and execute the step of performing a branching process on the problem to be branched in the mathematical model of the unloading process problem based on the branch and bound method, to obtain multiple sub-problems of the problem to be branched and first feasible solutions corresponding to the multiple sub-problems respectively; In response to the upper bound being greater than the lower bound, prune the current sub-problem; In response to the upper bound being equal to the lower bound, determine the first feasible solution as the optimal solution of the mathematical model of the unloading process problem.

9. The device according to claim 8, wherein, The pruning sub-module is further configured to: In response to the first feasible solution satisfying the preset constraint conditions of the mathematical model of the unloading process problem, calculate the first objective function value of the first feasible solution based on the preset objective function of the mathematical model of the unloading process problem; Determine the first objective function value as the lower bound of the current sub-problem.

10. The apparatus according to claim 8, wherein, The pruning sub-module is further configured to: In response to the second feasible solution satisfying the preset constraint conditions of the mathematical model of the unloading process problem, calculate the second objective function value of the second feasible solution based on the preset objective function of the mathematical model of the unloading process problem; Determine the second objective function value as the upper bound of the current sub-problem.

11. The device according to claim 7, wherein, Specifically, the second input sub-module is configured to: Input the multiple sub-problems into the feasible solution prediction model respectively, to obtain multiple intermediate feasible solutions corresponding to the multiple sub-problems respectively; Calculate the objective function values of the multiple intermediate feasible solutions of the same sub-problem based on the preset objective function of the mathematical model of the unloading process problem; Determine the intermediate feasible solution with the minimum objective function value as the second feasible solution corresponding to the sub-problem.

12. The device according to claim 7, wherein The first acquisition module includes: An acquisition sub-module, configured to acquire unloader device information; A first determination sub-module, configured to determine the weight ratio between the multiple unloader devices according to the unloader device information; A second determination sub-module, configured to determine the demand quantity of the unloading process string for each of the multiple unloader devices according to the weight ratio and the total demand quantity of the preset process string; A third determination sub-module, configured to determine the available unloading process string for each of the multiple unloader devices according to the process string information and the demand quantity of the unloading process string for each of the multiple unloader devices; A fourth determination sub-module, configured to determine the unloader device information and the available unloading process string for each of the multiple unloader devices as the process string information.

13. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

15. A computer program product, comprising a computer program, where the computer program, when executed by a processor, implements the steps of the unloading process plan generation method according to any one of claims 1 to 6.

Images