Transportation planning method of sylvite product and related equipment

Abstract

The invention relates to the technical field of transportation, and provides a potassium salt product transportation planning method and related equipment, and the method comprises the steps: obtaining a plurality of goods allocation spaces, a plurality of wagon spaces and a plurality of wagons of a potassium salt product shipping region, and a plurality of uncertain shipping demands of the potassium salt product shipping region; clustering all the uncertain shipping demands, and taking the uncertain shipping demand in a cluster obtained by clustering as a target shipping demand; constructing a two-stage objective function and constraint conditions according to all the goods allocation spaces, all the wagon spaces, all the wagons and all the target delivery requirements; performing peer-to-peer conversion on the two-stage objective function and the constraint condition to obtain a peer-to-peer model; and solving the peer-to-peer model by stages to obtain a transportation planning scheme of the sylvite product dispatching area. According to the method, the reliability of transportation planning can be improved.

Description

Technical Field

[0001] The present application relates to the field of transportation technology, and in particular to a transportation planning method and related equipment for potassium salt products. Background Art

[0002] At present, due to the characteristics of high carrying capacity, strong stability, low transportation cost, environmental protection and energy saving, and strong regional connectivity, railway logistics is crucial in the resource scheduling of the enterprise's industrial chain, and can provide efficient, stable and environmentally friendly resource scheduling services. The cargo space layout and loading and unloading of railway platforms are important links in the resource scheduling of the industrial chain. Reasonable planning of cargo space layout can maximize the convenience of loading goods, improve loading efficiency, and reduce operating costs. At the same time, reasonable loading and unloading can ensure the safe and stable transportation of goods and reduce damage to goods. Since cargo space layout is the prerequisite for subsequent loading and unloading operations, the optimization of cargo space layout and loading and unloading are inseparable. Optimizing one aspect alone does not necessarily have a greater advantage from the overall perspective.

[0003] Through scientific cargo space layout and loading and distributing strategies, railway logistics can achieve efficient, safe and timely transportation of goods and improve the overall resource operation efficiency of the industrial chain. However, the constraints involved in cargo space layout and loading and distributing are complex and numerous, and it is difficult to consider both at the same time. In order to solve this problem, a robust optimization configuration and planning method for potassium salt products under uncertain supply and demand conditions was proposed. However, due to the nested structure of the two-level optimization problem, the group-based characteristics of swarm intelligence algorithms such as evolutionary algorithms greatly affect their efficiency and effectiveness, which generally leads to the low efficiency of collaborative optimization methods.

[0004] It can be seen that there is an urgent need for a robust optimization configuration and planning method for potassium salt products under conditions of supply and demand uncertainty with high optimization efficiency and accuracy.

[0005] As an important means of logistics and trade, railway transportation plays an irreplaceable role in promoting global economic development. Railway transportation is efficient, reliable and relatively low-cost, providing a fast and reliable channel for the flow of goods between countries. Therefore, railway transportation is also an important means of transporting potash fertilizer products from chemical plants to all parts of the country. The cargo space layout and loading and unloading of freight platforms are important links in the resource scheduling of the industrial chain. Reasonable cargo space layout can maximize the convenience of loading goods, improve loading efficiency and reduce operating costs. However, due to changes in orders and unforeseen delays and changes in the railway scheduling process, traditional fixed cargo space layout and loading and unloading methods are often difficult to cope with demand fluctuations in actual operations, resulting in problems such as low loading efficiency.

[0006] In the existing technology, freight space allocation and loading planning are usually optimized using deterministic models, but such models ignore the impact of demand uncertainty. In actual operation, customer demand may change at any time, orders may be canceled or urgent orders may be added, and problems such as wagon resource shortages, bad weather and equipment failures may also occur during railway scheduling, all of which make it difficult to accurately execute transportation plans. It can be seen that under the condition of uncertain demand, the existing transportation planning methods have the problem of low reliability of transportation planning. Summary of the invention

[0007] The present application provides a transportation planning method and related equipment for potassium salt products, which can solve the problem of low reliability of transportation planning.

[0008] In a first aspect, an embodiment of the present application provides a transportation planning method for a potassium salt product, the transportation planning method comprising:

[0009] Obtain multiple cargo spaces, multiple car spaces, multiple car bodies, and multiple uncertain shipping demands in the potassium salt product shipping area; cargo spaces are used to store potassium salt products, car body spaces are used to park car bodies, car bodies are used to transport and load potassium salt products, and uncertain shipping demands are used to describe the demand status for shipping potassium salt products;

[0010] Cluster all uncertain shipping demands, and use the uncertain shipping demands in the clusters obtained by clustering as target shipping demands;

[0011] A two-stage objective function and constraints are constructed based on all cargo space, all car space, all car, and all target shipping requirements. The two-stage objective function is used to describe the planning status of the two stages of cargo space layout and loading and handling.

[0012] Perform equivalent transformation on the two-stage objective functions and constraints to obtain an equivalent model;

[0013] The equivalence model is solved in stages to obtain a transportation planning scheme for the potassium salt product shipping area; the transportation planning scheme is used to describe the allocation of cargo space, car space, and car when transporting potassium salt products required for all target shipping needs.

[0014] Optionally, clustering all uncertain shipping demands, and taking the uncertain shipping demands in the clusters obtained by clustering as target shipping demands, including:

[0015] Extract timing information based on all uncertain shipping requirements;

[0016] The time series information is filtered and redistributed to obtain the shipping demand characteristics; the shipping demand characteristics include the characteristics of each uncertain shipping demand;

[0017] The shipping demand features are clustered, and the uncertain shipping demand corresponding to the features in the clusters obtained by clustering is taken as the target shipping demand.

[0018] Optionally, the timing information is filtered and redistributed to obtain shipping demand characteristics, including:

[0019] By formula:

[0020] g r =σ(W gr H r +b gr )

[0021] temp r =tanh(W ar H r +b ar )

[0022] gate r =g r ·temp r

[0023]

[0024] e r =utanh(W r ·gate r +b r )

[0025]

[0026]

[0027] Calculate the shipping demand characteristics S;

[0028] Among them, H r represents the rth information in the time series information, g r represents the rth gate value, temp r Indicates the rth replacement value, gate r Represents the rth gated filtering feature, Gate out Represents the gate output information, e r represents the probability distribution, α r represents the input of the attention operation, u, W gr , W ar , W r Both represent weight matrices, b gr 、b ar 、b r They all represent bias vectors, r=1,2,...,n, and n represents the number of dimensions of time series information.

[0029] Optionally, cluster the shipping demand characteristics, including:

[0030] By formula:

[0031] out=f Cluster (S)

[0032] Get the clustering result out;

[0033] Among them, f Cluster () represents the clustering algorithm.

[0034] Optionally, the two-stage objective function is:

[0035]

[0036] Among them, y jl =[0,1],y jl =1 means that the lth car space is allocated for parking the jth car, y jl = 0 means that the lth car space is not allocated for parking the jth car, h lk represents the specified distance from the kth freight space to the lth car space, z kj =[0,1],z kj =1 means that the kth freight space is allocated to the jth car, Z kj = 0 means that the kth freight space is not allocated to the jth car, U represents the set of all target shipping demands, c represents the freight volume, and f lk represents the transportation distance from the kth freight space to the lth car space, C lk represents the freight volume from the kth freight space to the lth car body space, j=1,2,...,N, N represents the number of cars, l=1,2,...,L, L represents the number of car body spaces, k=1,2,...,W, W represents the number of freight spaces.

[0037] Optionally, the constraints include shipping demand constraints, car loading constraints, and cargo space constraints;

[0038] The shipping demand constraints are:

[0039]

[0040]

[0041] Among them, cap j represents the capacity limit of the j-th car, x ij =[0,1],x ij =1 means that the i-th target shipping demand is assigned to the j-th car, x ij= 0 means that the i-th target shipping demand has not been allocated to the j-th car, v i represents the unit volume of potassium salt products corresponding to the i-th target shipping demand, q i represents the i-th target shipping demand, m ik = [0, 1], when m ik =1 means that the i-th target shipping demand is allocated to the k-th freight space. ik =0 means that the i-th target shipping demand is not allocated to the k-th freight space, cap2 represents the capacity limit of each freight space, i=1,2,...,I, I represents the number of target shipping demands;

[0042] The car loading constraints are:

[0043]

[0044]

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] Among them, y jl =[0,1],y jl =1 means that the lth car space is allocated for parking the jth car, y jl = 0 means that the lth car space is not allocated for parking the jth car, u id =[0,1],u id =1 indicates that the i-th target shipping demand is sent to the destination d, u id = 0 means that the i-th target shipping demand is not sent to the destination d, y j，l-1 =[0,1],y j，l-1 =1 means that the l-1th car space is allocated for parking the jth car, y j，k-1 = 0 means that the l-1th car space is not allocated for parking the jth car, and N represents the number of cars;

[0051] The cargo space constraints are:

[0052]

[0053]

[0054]

[0055]

[0056] Where W is the amount of cargo space, The type of goods that represent the i-th target shipping demand is t1. The product type of the fth target shipping demand is t2, T represents the product type set, m fk = [0, 1], when m fk =1 means that the fth target shipping demand is allocated to the kth freight space. fk =0 means that the f-th target shipping demand has not been allocated to the k-th freight space.

[0057] Optional, peer model is:

[0058]

[0059]

[0060] α≥0

[0061]

[0062]

[0063] α1≥0

[0064]

[0065] Among them, cap1 represents the capacity limit of the car body, x ij =[0,1],x ij =1 means that the i-th target shipping demand is assigned to the j-th car, x ij = 0 means that the i-th target shipping demand has not been allocated to the j-th car. represents the nominal value of the demand for the i-th target shipment demand, v i represents the unit volume of potassium salt products corresponding to the i-th target shipping demand, α, α1, β 1i are auxiliary variables. represents the maximum value of the demand for the i-th target shipping demand deviating from the nominal value, cap2 represents the capacity limit of each freight space, j=1, 2, ..., N, N represents the number of wagons, l=1, 2, ..., L, L represents the number of wagon spaces, i=1, 2, ..., I, I represents the number of target shipping demands.

[0066] Optionally, the peer model is solved in stages to obtain a transportation planning solution for the potassium salt product shipping area, including:

[0067] Design the cargo space allocation sub-problem, the wagon arrival sequence sub-problem, the cargo space assignment sub-problem, and the loading scheduling sub-problem; the cargo space allocation sub-problem is used to describe the placement planning of different types of potassium salt products in all cargo space spaces, the wagon arrival sequence sub-problem is used to describe the order in which all wagons arrive at the potassium salt product shipping area, the cargo space assignment sub-problem is used to describe the multiple cargo space spaces allocated to each wagon, and the loading scheduling sub-problem is used to describe the distribution volume of potassium salt products when the cargo space is distributed to the corresponding wagon;

[0068] According to the cargo space allocation sub-problem, the peer model is solved to obtain the cargo space allocation plan. According to the car arrival sequence sub-problem, the peer model is solved to obtain the car arrival sequence. According to the cargo space assignment sub-problem, the peer model is solved to obtain the cargo space assignment plan. According to the loading scheduling sub-problem, the peer model is solved to obtain the loading scheduling plan.

[0069] The cargo space allocation plan, car arrival sequence, cargo space assignment plan, and loading scheduling plan are integrated to obtain a transportation planning plan.

[0070] In a second aspect, an embodiment of the present application provides a transportation planning device for potassium salt products, comprising:

[0071] An acquisition module is used to acquire multiple cargo spaces, multiple car spaces, multiple car bodies, and multiple uncertain shipping demands in the potassium salt product shipping area; cargo spaces are used to store potassium salt products, car body spaces are used to park car bodies, car bodies are used to transport and load potassium salt products, and uncertain shipping demands are used to describe the demand status for shipping potassium salt products;

[0072] The clustering module clusters all uncertain shipping demands and uses the uncertain shipping demands in the clusters obtained by clustering as target shipping demands;

[0073] The construction module constructs a two-stage objective function and constraints based on all cargo space, all car space, all car, and all target shipping requirements; the two-stage objective function is used to describe the planning status of the two stages of cargo space layout and loading and handling;

[0074] The equivalent conversion module performs equivalent conversion on the two-stage objective functions and constraints to obtain an equivalent model;

[0075] The solution module solves the peer model in stages to obtain a transportation planning scheme for the potassium salt product shipping area; the transportation planning scheme is used to describe the allocation of cargo space, car space, and car when transporting potassium salt products required for all target shipping needs.

[0076] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for transport planning of potassium salt products when executing the above-mentioned computer program.

[0077] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned transportation planning method for potassium salt products.

[0078] The above solution of the present application has the following beneficial effects:

[0079] In an embodiment of the present application, multiple cargo spaces, multiple car body spaces, multiple car bodies, and multiple uncertain shipping demands of a potassium salt product shipping area are obtained, and then all the uncertain shipping demands are clustered, and the uncertain shipping demands in the cluster clusters obtained by clustering are used as target shipping demands, and then a two-stage objective function and constraints are constructed according to all cargo spaces, all car body spaces, all car bodies, and all target shipping demands, and then the two-stage objective function and constraints are converted equivalently to obtain an equivalent model, and finally the equivalent model is solved in stages to obtain a transportation planning scheme for the potassium salt product shipping area. Among them, multiple target shipping demands are determined from all uncertain shipping demands, which reduces the situation where the shipping demand is abnormal data that does not conform to reality, improves the accuracy and practicality of the target shipping demand, and constructs a two-stage objective function and constraints based on cargo space, car space, car, and target shipping demand. The four aspects of information on the transportation of potassium salt products are considered, which improves the comprehensiveness and information richness of the two-stage objective function, can accurately describe the transportation status of potassium salt products, and improves the reliability of the transportation planning scheme obtained according to the two-stage objective function.

[0080] In addition, since cargo space, car space, car body, and uncertain target shipping demand are taken into consideration when constructing the two-stage objective function, the obtained transportation planning scheme has plans for the allocation of cargo space, car body space, and car body. Even in the case of sudden changes in target shipping demand, the allocation of cargo space, car body space, and car body can be adjusted in time according to the changed target shipping demand, further improving the reliability of transportation planning.

[0081] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0083] Figure 1 A flow chart of a method for transport planning of potash products provided in one embodiment of the present application;

[0084] Figure 2 A flowchart for obtaining target shipping requirements provided in an embodiment of the present application;

[0085] Figure 3 A flowchart of solving a peer-to-peer model provided in an embodiment of the present application;

[0086] Figure 4 A schematic diagram of the structure of a transport planning device for potassium salt products provided in one embodiment of the present application;

[0087] Figure 5 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0088] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0089] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0090] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0091] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0092] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0093] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0094] In response to the problem of low reliability of existing transportation planning, an embodiment of the present application provides a transportation planning method for potassium salt products. The transportation planning method obtains multiple cargo spaces, multiple car body spaces, multiple car bodies, and multiple uncertain shipping demands in the potassium salt product shipping area, and then clusters all uncertain shipping demands, and uses the uncertain shipping demands in the clustered clusters obtained by clustering as target shipping demands, and then constructs a two-stage objective function and constraint conditions based on all cargo spaces, all car body spaces, all car bodies, and all target shipping demands, and then performs an equivalent conversion on the two-stage objective function and constraint conditions to obtain an equivalent model, and finally solves the equivalent model in stages to obtain a transportation planning scheme for the potassium salt product shipping area. Among them, multiple target shipping demands are determined from all uncertain shipping demands, which reduces the situation where the shipping demand is abnormal data that does not conform to reality, improves the accuracy and practicality of the target shipping demand, and constructs a two-stage objective function and constraints based on cargo space, car space, car, and target shipping demand. The four aspects of information on the transportation of potassium salt products are considered, which improves the comprehensiveness and information richness of the two-stage objective function, can accurately describe the transportation status of potassium salt products, and improves the reliability of the transportation planning scheme obtained according to the two-stage objective function.

[0095] In addition, since cargo space, car space, car body, and uncertain target shipping demand are taken into consideration when constructing the two-stage objective function, the obtained transportation planning scheme has plans for the allocation of cargo space, car body space, and car body. Even in the case of sudden changes in target shipping demand, the allocation of cargo space, car body space, and car body can be adjusted in time according to the changed target shipping demand, further improving the reliability of transportation planning.

[0096] Next, the transportation planning method for potassium salt products provided in this application is exemplified.

[0097] like Figure 1 As shown, the transportation planning method for potassium salt products provided in this application includes the following steps:

[0098] Step 11, obtaining multiple cargo spaces, multiple car spaces, multiple car bodies, and multiple uncertain shipping demands in the potassium salt product shipping area.

[0099] The above-mentioned potassium salt product shipping area is an area where potassium salt products are stored and loaded and shipped (such as a railway station), the above-mentioned cargo space is used to store potassium salt products (such as a freight warehouse at a railway station), the wagon space is used to park wagons (such as the carriage parking space at a railway station), and the wagons are used to transport and load potassium salt products (such as the carriages of a freight train). The uncertain shipping demand is used to describe the demand status for shipping potassium salt products. Exemplarily, the uncertain shipping demand may include the destination to be shipped, the volume of potassium salt products required, the type of potassium salt products required, etc. Compared with the shipping demand without uncertainty, the uncertain shipping demand, the destination to be shipped, the volume of potassium salt products required, the type of potassium salt products required, etc., may change at any time, and the uncertain shipping demand may be cancelled at any time.

[0100] In some embodiments of the present application, multiple uncertain shipping demands can be obtained by accessing the logistics system of the potassium salt product shipping area, etc.

[0101] Step 12: cluster all uncertain shipping demands, and use the uncertain shipping demands in the clusters obtained through clustering as target shipping demands.

[0102] It should be noted that when clustering all uncertain shipping demands, the uncertain shipping demands are clustered according to the distance between them, and the distance reflects the similarity between the uncertain shipping demands. For example, multiple uncertain shipping demands whose distance from a certain uncertain shipping demand is less than a distance threshold can be grouped as a cluster.

[0103] In some embodiments of the present application, the clustering result obtained by clustering includes only one cluster. The above step of clustering all uncertain shipping demands and taking the uncertain shipping demands in the cluster obtained by clustering as the target shipping demands specifically includes:

[0104] In the first step, timing information is extracted based on all uncertain shipping demands.

[0105] The above time series information includes the characteristic vectors of all uncertain shipping demands in time series.

[0106] Specifically, the stacked autoencoder based on the long short-term memory network (LSTM) can be used to extract the timing information of all uncertain shipping requirements, expressed as:

[0107] H1=f LSTM-EN (W x X+b f )

[0108]

[0109] Among them, X represents all uncertain shipping demands, H1 represents the output of the first encoding layer (that is, the first information in the time series information), and H1 represents the encoded feature vector. represents the output of the first decoding layer, W X Both represent weight matrices, b f Both represent bias vectors, f LSTM-EN () represents the LSTM encoder network, f LSTM-DE () represents the LSTM decoder network.

[0110] After processing as in the above formula, the stacked autoencoder finally outputs time series information H=H1,...,H n , H n Represents the output of the last encoding layer (that is, the last information in the time series information).

[0111] In the second step, the timing information is filtered and redistributed to obtain the shipping demand characteristics.

[0112] The above shipping demand characteristics include the characteristics of each uncertain shipping demand.

[0113] Specifically, through the formula:

[0114] g r =σ(W gr H r +b gr )

[0115] temp r =tanh(W ar H r +b ar )

[0116] gate r =g r ·temp r

[0117]

[0118] e r =utanh(W r ·gate r +b r )

[0119]

[0120]

[0121] Calculate the shipping demand characteristics S;

[0122] Among them, H r represents the rth information in the time series information, g r represents the rth gate value, temp r Indicates the rth replacement value, gate r Represents the rth gated filtering feature, Gate out Represents the gate output information, e r represents the probability distribution, α r represents the input of the attention operation, u, W gr , W ar , W r Both represent weight matrices, b gr 、b ar 、b r They all represent bias vectors, r=1,2,...,n, where n represents the number of dimensions of the timing information.

[0123] The third step is to cluster the shipping demand characteristics, and use the uncertain shipping demand corresponding to the characteristics in the clusters obtained by clustering as the target shipping demand.

[0124] Specifically, through the formula:

[0125] By formula:

[0126] out=f Cluster (S)

[0127] Get the clustering result out.

[0128] Among them, fCluster () represents the clustering algorithm.

[0129] It should be noted that the above clustering results are clusters. The above shipping demand characteristics include the characteristics of each uncertain shipping demand. All the features in the shipping demand characteristics are clustered using a clustering algorithm to obtain a cluster, and the uncertain shipping demand corresponding to each feature in the cluster is used as a target shipping demand. Uncertain shipping demands that do not belong to the cluster are considered to be abnormal data that do not conform to reality and need to be eliminated.

[0130] Exemplarily, the above clustering algorithm may be a K-means clustering algorithm, and this step may also be expressed as:

[0131]

[0132] in, represents the target shipping demand set, W = (W1, ..., W L ), W represents the set of weight matrices, W1, W L All represent weight matrices, q represents uncertain shipping demand, represents the center point of the cluster, R represents the radius, ||·|| represents the norm, and R N Represents a set of uncertain shipping requirements.

[0133] It is worth mentioning that multiple target shipping demands are determined from all uncertain shipping demands, which reduces the situation where the shipping demands are abnormal data that do not conform to reality and improves the accuracy and practicality of the target shipping demands.

[0134] This step is illustrated below with reference to a specific example.

[0135] like Figure 2 As shown in Figure 1, the model for obtaining multiple target shipping requirements includes an LSTM decoder, an LSTM encoder, a gating unit, an attention mechanism, and a clustering mechanism. All uncertain shipping requirements X are input into multiple encoding layers of the LSTM encoder, and outputs h1, h2, and h3 in sequence. The output of each encoding layer is input into the corresponding decoding layer. The output of the first decoding layer is The second decoding layer output The output of the third decoding layer Each coding layer corresponds to the gating layer in the gating unit. Each gating layer is composed of a gating block (Gate), an activation function block (Tanh) and an addition block +. The gating block and the activation function block both input the output data of the corresponding coding layer. The output ends of the gating block and the activation function block are connected to the input end of the addition block. The output end of the addition block is the output end of the gating layer. The outputs of all gating layers are added and input into the attention mechanism. After being processed by the attention mechanism, they are input into the multi-layer perceptron MLP for processing. Finally, the K-means algorithm is used to cluster them to obtain multiple target shipping requirements.

[0136] Step 13, construct a two-stage objective function and constraints based on all cargo spaces, all car spaces, all car spaces, and all target shipping requirements.

[0137] The above two-stage objective function is used to describe the planning status of the two stages of cargo space layout and loading and handling.

[0138] Specifically, the two-stage objective function is:

[0139]

[0140] Among them, y jl =[0,1],y jl =1 means that the lth car space is allocated for parking the jth car, y jl = 0 means that the lth car space is not allocated for parking the jth car, h lk represents the specified distance from the kth freight space to the lth car space, z kj =[0,1],z kj =1 means that the kth freight space is allocated to the jth car, z kj = 0 means that the kth freight space is not allocated to the jth car, U represents the set of all target shipping demands, c represents the freight volume, and f lk represents the transportation distance from the kth freight space to the lth car space, c lk represents the freight volume from the kth freight space to the lth car body space, j=1,2,...,N, N represents the number of cars, l=1,2,...,L, L represents the number of car body spaces, k=1,2,...,W, W represents the number of freight spaces.

[0141] Constraints include shipping demand constraints, car loading constraints, and cargo space constraints;

[0142] The shipping demand constraints are:

[0143]

[0144]

[0145] Among them, cap j represents the capacity limit of the j-th car, x ij =[0,1],x ij =1 means that the i-th target shipping demand is assigned to the j-th car, x ij = 0 means that the i-th target shipping demand has not been allocated to the j-th car, v i represents the unit volume of potassium salt products corresponding to the i-th target shipping demand, q i represents the i-th target shipping demand, m ik = [0, 1], when m ik =1 means that the i-th target shipping demand is allocated to the k-th freight space. ik =0 means that the i-th target shipping demand is not allocated to the k-th freight space, cap2 represents the capacity limit of each freight space, i=1,2,...,I, I represents the number of target shipping demands;

[0146] The car loading constraints are:

[0147]

[0148]

[0149]

[0150]

[0151]

[0152]

[0153]

[0154] Among them, y jl =[0,1],y jl =1 means that the lth car space is allocated for parking the jth car, y jl = 0 means that the lth car space is not allocated for parking the jth car, u id =[0,1],u id =1 indicates that the i-th target shipping demand is sent to the destination d, u id = 0 means that the i-th target shipping demand is not sent to the destination d, y j，l-1 =[0,1],y j，l-1 =1 means that the l-1th car space is allocated for parking the jth car, y j，l-1 = 0 means that the l-1th car space is not allocated for parking the jth car, and N represents the number of cars;

[0155] The cargo space constraints are:

[0156]

[0157]

[0158]

[0159]

[0160] Where W is the amount of cargo space, The type of goods that represent the i-th target shipping demand is t1. The product type of the fth target shipping demand is t2, T represents the product type set, m fk = [0, 1], when m fk =1 means that the fth target shipping demand is allocated to the kth freight space. fk =0 means that the f-th target shipping demand has not been allocated to the k-th freight space.

[0161] Exemplarily, computer software such as matlab and python can be used to construct the two-stage objective function and constraints.

[0162] It is worth mentioning that the two-stage objective function and constraints are constructed based on cargo space, car space, car, and target shipping demand, taking into account four aspects of information on the transportation of potash products, which improves the comprehensiveness and information richness of the two-stage objective function and can accurately describe the transportation status of potash products.

[0163] Step 14, perform equivalent conversion on the two-stage objective functions and constraints to obtain an equivalent model.

[0164] Specifically, according to the strong duality theory, the original problem is feasible and bounded, and the objective function values ​​of the original problem and the dual problem are consistent. The two-stage objective functions and constraints are converted equivalently to obtain an equivalent model, which is:

[0165]

[0166]

[0167] α≥0

[0168]

[0169]

[0170] α1≥0

[0171]

[0172] Among them, cap1 represents the capacity limit of the car body, x ij =[0,1],x ij =1 means that the i-th target shipping demand is assigned to the j-th car, x ij = 0 means that the i-th target shipping demand has not been allocated to the j-th car. represents the nominal value of the demand for the i-th target shipment demand, v i represents the unit volume of potassium salt products corresponding to the i-th target shipping demand, α, α1, β 1i are auxiliary variables. It represents the maximum value of the demand for the i-th target shipment demand deviating from the nominal value, cap2 represents the capacity limit of each freight space, j=1,2,...,N, N represents the number of wagons, l=1,2,...,L, L represents the number of wagon spaces, i=1,2,...,I, I represents the number of target shipment demands.

[0173] Exemplarily, computer software such as matlab and python can be used to perform equivalent conversion on the two-stage objective functions and constraints to obtain an equivalent model.

[0174] Step 15, solving the peer model in stages to obtain a transportation planning solution for the potassium salt product shipping area.

[0175] The above transportation planning scheme is used to describe the allocation of cargo space, car space, and car when transporting potash products required for all target shipping needs.

[0176] In some embodiments of the present application, the above-mentioned step of solving the peer model in stages to obtain a transportation planning scheme for the potassium salt product shipping area specifically includes:

[0177] The first step is to design the cargo space allocation sub-problem, car arrival sequence sub-problem, cargo space assignment sub-problem, and loading scheduling sub-problem.

[0178] The above-mentioned storage space allocation sub-problem is used to describe the placement planning of different types of potassium salt products in all storage spaces, which can be expressed as: which storage spaces are used to place which type of potassium salt products?

[0179] The wagon arrival sequence subproblem is used to describe the order in which all wagons arrive at the potassium salt product shipping area, which can be expressed as: In what order are the wagons arranged at their destinations?

[0180] The cargo space assignment subproblem is used to describe the multiple cargo space allocated to each car body, which can be expressed as: for each car body, which one or more cargo space will perform the delivery task?

[0181] The loading scheduling subproblem is used to describe the delivery quantity of potassium salt products when the cargo space delivers to the corresponding wagon. It can be expressed as: if a cargo space performs a delivery task, how to arrange the delivery quantity of the cargo space to the assigned wagon.

[0182] In the second step, according to the cargo space allocation sub-problem, the peer model is solved to obtain the cargo space allocation plan. According to the car arrival sequence sub-problem, the peer model is solved to obtain the car arrival sequence. According to the cargo space assignment sub-problem, the peer model is solved to obtain the cargo space assignment plan. According to the loading scheduling sub-problem, the peer model is solved to obtain the loading scheduling plan.

[0183] It should be noted that the cargo space allocation plan describes the placement plan of potassium salt products in the cargo space, and gives the type, quantity and volume of potassium salt products stored in each cargo space (using all cargo spaces to store the potassium salt products required for all target shipping needs). The wagon arrival sequence describes the order in which the wagons enter the potassium salt product shipping area. The wagons enter the area in sequence and stop at the wagon spaces in turn, and the wagon space corresponding to each wagon is given. The cargo space assignment plan describes at least one cargo space corresponding to the wagon, and gives the potassium salt products loaded from at least one designated cargo space for each wagon. The loading scheduling plan gives the distribution volume of potassium salt products distributed from the cargo space to the corresponding wagon.

[0184] Exemplarily, the Tabu Search algorithm (TS) is used to solve the cargo space allocation subproblem and the train arrival subproblem. TS encodes the cargo space allocation and train arrival sequence at the same time, and generates initial feasible solutions for the two problems respectively. This combined subproblem is called the cargo space allocation and car body sequence subproblem. By initializing this subproblem, a sequence set containing all cargo space allocations and a sequence set containing car body destinations can be generated. When TS solves the peer model, the final optimized solution is obtained by continuously iteratively updating the initial solution.

[0185] For the cargo space allocation subproblem and loading scheduling subproblem, they are converted into assignment problems and effectively solved by GORUBI solver. This combination of subproblems is called storage space allocation and loading scheduling subproblem. In the previous stage of cargo space allocation and car body sequence planning, the cargo space allocation problem does not need to be predetermined or determined before solving. Instead, it is determined together with the scheduling plan of the current stage. After obtaining the solution of the cargo space allocation and loading scheduling subproblem, the result is used as the fitness evaluation criterion for the population of cargo space allocation and car body sequence subproblem. Iteratively update the optimal solution of TS until the termination condition is met (such as: reaching the set number of iterations). When the GORUBI solver solves the peer model, it finds the optimal solution by establishing a problem model.

[0186] The above-mentioned solution process is illustrated below with reference to a specific example.

[0187] like Figure 3 As shown, the cargo space allocation sequence is initialized, and then the taboo search algorithm is used to evolve the sequence, and the new fitness value Lnew is calculated, Leurr is the current fitness value. If Lnew<Leurr, the cargo space allocation sequence is updated, and the updated cargo space allocation sequence is input into the GORUBI solver, and the step of using the taboo search algorithm to evolve the sequence is returned, and a total of N iterations are made. If Lnew>Leurr, the step of using the taboo search algorithm to evolve the sequence is returned. At the same time, the car arrival sequence is initialized, and then the taboo search algorithm is used to evolve the sequence, and the new fitness value Rnew is calculated, Reurr is the current fitness value. If Rnew<Reurr, the car arrival sequence is updated, and the updated car arrival sequence is input into the GORUBI solver, and the step of using the taboo search algorithm to evolve the sequence is returned, and a total of M iterations are made. If Rnew>Reurr, the step of using the taboo search algorithm to evolve the sequence is returned. The GORUBI solver solves and obtains the loading scheduling plan and cargo space assignment plan.

[0188] The third step is to integrate the cargo space allocation plan, car arrival sequence, cargo space assignment plan, and loading scheduling plan to obtain a transportation planning plan.

[0189] Exemplarily, the transportation planning scheme includes a planning scheme for storing potassium salt products required for all target shipping needs in cargo space, the correspondence between car bodies and car body spaces, the correspondence between car bodies and cargo spaces, and the delivery quantity of potassium salt products from cargo spaces to car bodies.

[0190] It is worth mentioning that multiple target shipping demands are determined from all uncertain shipping demands, which reduces the situation where the shipping demand is abnormal data that does not conform to reality, improves the accuracy and practicality of the target shipping demand, and constructs a two-stage objective function and constraints based on cargo space, car space, car, and target shipping demand. The four aspects of information on the transportation of potassium salt products are considered, which improves the comprehensiveness and information richness of the two-stage objective function, can accurately describe the transportation status of potassium salt products, and improves the reliability of the transportation planning scheme obtained according to the two-stage objective function.

[0191] In addition, since cargo space, car space, car body, and uncertain target shipping demand are taken into consideration when constructing the two-stage objective function, the obtained transportation planning scheme has plans for the allocation of cargo space, car body space, and car body. Even in the case of sudden changes in target shipping demand, the allocation of cargo space, car body space, and car body can be adjusted in time according to the changed target shipping demand, further improving the reliability of transportation planning.

[0192] The following is an illustrative description of the transportation planning method for potassium salt products of the present application in conjunction with a specific example, using the transportation distance and calculation time to evaluate the optimization effect, the transportation distance is the sum of the transportation distances between all freight spaces and the corresponding wagons, and the calculation time is the time taken by the method of the present application to calculate the transportation planning solution. The optimization results are shown in Table 1.

[0193] Strategy Transport distance TD(m) Calculation time (min) Artificial experience method 7038 40-60 Deterministic Optimization Strategy 3678 12.31 K-means clustering strategy 4581 12.92 The method disclosed herein provides an uncertain optimization strategy 3987 14.11

[0194] Table 1

[0195] It can be seen from this that the method of the present application significantly reduces the transportation distance compared to manual experience and K-means clustering strategy, greatly improving the optimization effect of the transportation planning scheme under uncertain conditions; deterministic optimization ignores the influence of uncertain factors, while the method disclosed in the present application, taking into account uncertain factors, is only slightly larger than the transportation distance obtained by the deterministic optimization strategy, and the calculation time is also within a reasonable range, indicating that the method of the present application is effective in resisting uncertain factors, which also verifies the effectiveness of the method disclosed in the present application.

[0196] The following is an exemplary description of the transportation planning device for potassium salt products provided in this application.

[0197] like Figure 4 As shown, the embodiment of the present application provides a transportation planning device for potash products, and the transportation planning device 400 for potash products includes:

[0198] Acquisition module 401, acquiring multiple cargo spaces, multiple car spaces, multiple car bodies, and multiple uncertain shipping demands of the potassium salt product shipping area; the cargo spaces are used to store potassium salt products, the car body spaces are used to park car bodies, the car bodies are used to transport and load potassium salt products, and the uncertain shipping demands are used to describe the demand status for shipping potassium salt products;

[0199] A clustering module 402 clusters all uncertain shipping demands and uses the uncertain shipping demands in the clusters obtained by clustering as target shipping demands;

[0200] Construction module 403, constructing a two-stage objective function and constraint conditions according to all cargo space, all car space, all car, and all target shipping requirements; the two-stage objective function is used to describe the planning status of the two stages of cargo space layout and loading and handling;

[0201] The equivalent conversion module 404 performs equivalent conversion on the two-stage objective functions and constraint conditions to obtain an equivalent model;

[0202] The solution module 405 solves the peer model in stages to obtain a transportation planning scheme for the potassium salt product shipping area; the transportation planning scheme is used to describe the allocation of cargo space, car space, and car when transporting potassium salt products required for all target shipping needs.

[0203] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0204] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0205] like Figure 5 As shown, an embodiment of the present application provides a terminal device. The terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 5 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 implements the steps of any of the above-mentioned method embodiments when executing the computer program D102.

[0206] Specifically, when the processor D100 executes the computer program D102, it obtains multiple cargo spaces, multiple car body spaces, multiple car bodies, and multiple uncertain shipping demands in the potassium salt product shipping area, and then clusters all the uncertain shipping demands, and uses the uncertain shipping demands in the cluster clusters obtained by clustering as target shipping demands, and then constructs a two-stage objective function and constraints based on all cargo spaces, all car body spaces, all car bodies, and all target shipping demands, and then performs an equivalent conversion on the two-stage objective function and constraints to obtain an equivalent model, and finally solves the equivalent model in stages to obtain a transportation planning scheme for the potassium salt product shipping area. Among them, multiple target shipping demands are determined from all uncertain shipping demands, which reduces the situation where the shipping demand is abnormal data that does not conform to reality, improves the accuracy and practicality of the target shipping demand, and constructs a two-stage objective function and constraints based on cargo space, car space, car, and target shipping demand. The four aspects of information on the transportation of potassium salt products are considered, which improves the comprehensiveness and information richness of the two-stage objective function, can accurately describe the transportation status of potassium salt products, and improves the reliability of the transportation planning scheme obtained according to the two-stage objective function.

[0207] In addition, since cargo space, car space, car body, and uncertain target shipping demand are taken into consideration when constructing the two-stage objective function, the obtained transportation planning scheme has plans for the allocation of cargo space, car body space, and car body. Even in the case of sudden changes in target shipping demand, the allocation of cargo space, car body space, and car body can be adjusted in time according to the changed target shipping demand, further improving the reliability of transportation planning.

[0208] The processor D100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0209] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart memory card (SMC, SmartMedia Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), etc. equipped on the terminal device D10. Further, the memory D101 may also include both an internal storage unit of the terminal device D10 and an external storage device. The memory D101 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as the program code of the computer program, etc. The memory D101 may also be used to temporarily store data that has been output or is to be output.

[0210] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0211] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0212] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code to the transportation planning method device / terminal device of potassium salt products. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0213] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0214] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0215] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for transport planning of potash products, characterized in that: include: Acquire multiple cargo spaces, multiple car spaces, multiple car bodies, and multiple uncertain shipping demands of the potassium salt product shipping area; The cargo space is used to store potash products, the wagon space is used to park wagons, the wagons are used to transport and load potash products, and the uncertain shipping demand is used to describe the demand status for shipping potash products; Cluster all uncertain shipping demands, and use the uncertain shipping demands in the clusters obtained by clustering as target shipping demands; A two-stage objective function and constraint conditions are constructed based on all cargo space, all car space, all car, and all target shipping requirements; the two-stage objective function is used to describe the planning status of the two stages of cargo space layout and loading and handling; Performing equivalent conversion on the two-stage objective functions and the constraint conditions to obtain an equivalent model; The peer model is solved in stages to obtain a transportation planning scheme for the potassium salt product shipping area; the transportation planning scheme is used to describe the allocation of cargo space, car space, and car when transporting potassium salt products required for all target shipping needs.

2. The transportation planning method according to claim 1, characterized in that: The step of clustering all uncertain shipping demands and taking the uncertain shipping demands in the clusters obtained by clustering as target shipping demands includes: Extract timing information based on all uncertain shipping requirements; Filtering and redistributing the time series information to obtain shipping demand characteristics; the shipping demand characteristics include characteristics of each of the uncertain shipping demands; The shipping demand features are clustered, and the uncertain shipping demand corresponding to the features in the clusters obtained by clustering is used as the target shipping demand.

3. The transportation planning method according to claim 2, characterized in that: The filtering and reallocation of the time sequence information to obtain the shipping demand characteristics includes: By formula: g r =σ(W gr H r +b gr ) temperature r =tanh(W ar H r +b ar ) gate r =g r ·temp r e r =utanh(W r ·gate r +b r ) Calculate the shipping demand characteristics S; Among them, H r represents the rth information in the time series information, g r represents the rth gate value, temp r Indicates the rth replacement value, gate r Represents the rth gated filtering feature, Gate out Represents the gate output information, e r represents the probability distribution, α r represents the input of the attention operation, u, W gr , W ar , W r Both represent weight matrices, b gr , b ar , b r Both represent bias vectors, r=1, 2, ..., n, and n represents the number of dimensions of the timing information.

4. The transportation planning method according to claim 3, characterized in that: The clustering of the shipping demand characteristics includes: By formula: out=f Cluster (S) Get the clustering result out; Among them, f Cluster () represents the clustering algorithm.

5. The transportation planning method according to claim 1, characterized in that: The two-stage objective function is: Among them, y jl =[0,1],y jl =1 means that the lth car space is allocated for parking the jth car, y jl = 0 means that the lth car space is not allocated for parking the jth car, h lk represents the specified distance from the kth freight space to the lth car space, z kj =[0,1], z kj =1 means that the kth freight space is allocated to the jth car, z kj = 0 means that the kth freight space is not allocated to the jth car, U represents the set of all target shipping demands, c represents the freight volume, and f lk represents the transportation distance from the kth freight space to the lth car space, c lk represents the freight volume from the kth freight space to the lth car body space, j=1,2,...,N, N represents the number of cars, l=1,2,...,L, L represents the number of car body spaces, k=1,2,...,W, W represents the number of freight spaces.

6. The transportation planning method according to claim 5, characterized in that: The constraints include shipping demand constraints, car loading constraints, and cargo space constraints; The shipping demand constraints are: Among them, cap j represents the capacity limit of the j-th car, x ij =[0,1],x ij =1 indicates that the i-th target shipping demand is allocated to the j-th car, x ij = 0, indicating that the i-th target shipping demand has not been allocated to the j-th car body, v i represents the unit volume of potassium salt products corresponding to the i-th target shipping demand, q i represents the i-th target shipping demand, m ik = [0,1], when m ik =1 indicates that the i-th target shipping demand is allocated to the k-th freight space. ik =0 indicates that the i-th target shipping demand is not allocated to the k-th freight space, cap2 indicates the capacity limit of each freight space, i=1,2,...,I, I indicates the number of target shipping demands; The car loading constraints are: Among them, y jl =[0,1],y jl =1 means that the lth car space is allocated for parking the jth car, y jl = 0 means that the lth car space is not allocated for parking the jth car, u id =[0,1],u id =1 indicates that the i-th target shipping demand is sent to the destination d, u id =0 indicates that the i-th target shipping demand is not sent to the destination d, y j,l-1 =[0,1],y j,l-1 =1 means that the l-1th car space is allocated for parking the jth car, y j,l-1 = 0 means that the l-1th car space is not allocated for parking the jth car, and N represents the number of cars; The cargo space constraints are: Where W is the amount of cargo space, The type of goods that represent the i-th target shipping demand is t1. The product type of the fth target shipping demand is t2, T represents the product type set, m fk = [0,1], when m fk =1 indicates that the fth target shipping demand is allocated to the kth freight space. fk =0 indicates that the f-th target shipping demand has not been allocated to the k-th freight space.

7. The transportation planning method according to claim 1, characterized in that: The peer model is: α≥0 α1≥0 Among them, cap1 represents the capacity limit of the car body, x ij =[0,1],x ij =1 indicates that the i-th target shipping demand is allocated to the j-th car, x ij = 0 means that the i-th target shipping demand has not been allocated to the j-th car. represents the nominal value of the demand for the i-th target shipment demand, v i represents the unit volume of the potassium salt product corresponding to the i-th target shipping demand, α, β i , α1, β 1i are auxiliary variables. It represents the maximum value of the demand for the i-th target shipment demand deviating from the nominal value, cap2 represents the capacity limit of each freight space, j=1,2,...,N, N represents the number of wagons, l=1,2,...,L, L represents the number of wagon spaces, i=1,2,...,I, I represents the number of target shipment demands.

8. The transportation planning method according to claim 1, characterized in that: The peer model is solved in stages to obtain a transportation planning scheme for the potassium salt product shipping area, including: Design cargo space allocation sub-problem, car arrival sequence sub-problem, cargo space assignment sub-problem, loading scheduling sub-problem; the cargo space allocation sub-problem is used to describe the placement planning of different categories of potassium salt products in all cargo space spaces, the car arrival sequence sub-problem is used to describe the order in which all cars arrive at the potassium salt product shipping area, the cargo space assignment sub-problem is used to describe the multiple cargo space spaces allocated to each car, and the loading scheduling sub-problem is used to describe the distribution volume of potassium salt products when the cargo space is distributed to the corresponding car; According to the cargo space allocation sub-problem, the peer model is solved to obtain a cargo space allocation plan; according to the car arrival sequence sub-problem, the peer model is solved to obtain a car arrival sequence; according to the cargo space assignment sub-problem, the peer model is solved to obtain a cargo space assignment plan; according to the loading scheduling sub-problem, the peer model is solved to obtain a loading scheduling plan; The cargo space allocation plan, the car arrival sequence, the cargo space assignment plan, and the loading scheduling plan are integrated to obtain the transportation planning plan.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the transportation planning method for potassium salt products according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the transportation planning method for potassium salt products according to any one of claims 1 to 8 is implemented.

Images