Cargo merging and loading method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a cargo merging and loading method, device and equipment and a storage medium. The method comprises the following steps: acquiring a plurality of dispersed cargos and a target container for merging and loading the cargos; carrying out cargo clustering based on a preset cargo category number, the actual cargo size information corresponding to each cargo and the cargo weight identification information, and obtaining a target cargo set corresponding to each cargo category; based on the target cargo set, virtual cargo size information corresponding to each cargo is determined; and carrying out cargo loading optimization on the target container based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container to obtain a target cargo loading strategy, and merging and loading the target cargo into the target container based on the target cargo loading strategy. Through the technical scheme of the embodiment of the invention, the calculation amount can be reduced, and the cargo merging and loading efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to logistics technology, and more particularly to a cargo merging loading method, device, equipment and storage medium. Background Art

[0002] In logistics scenarios, especially those related to manufacturing, there are often many small and scattered goods, such as spare parts. In order to facilitate transportation, the scattered goods need to be combined and loaded into larger containers. This operation is called consolidation.

[0003] At present, in the process of optimizing cargo consolidation loading for a single container, it is necessary to traverse all categories of cargo at each position of the container to obtain the optimal cargo loading strategy. However, in the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] Due to the wide variety of dispersed cargo, the calculation complexity is greatly increased, thereby reducing the efficiency of cargo consolidation loading. Summary of the invention

[0005] The embodiments of the present invention provide a cargo merging loading method, device, equipment and storage medium to reduce the amount of calculation and improve the efficiency of cargo merging loading.

[0006] In a first aspect, an embodiment of the present invention provides a cargo consolidation loading method, comprising:

[0007] Acquire dispersed multiple cargoes and target containers for consolidating and loading cargoes;

[0008] Cargo clustering is performed based on the number of preset cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information, to obtain a target cargo set corresponding to each cargo category;

[0009] Based on the target cargo set, determining virtual cargo size information corresponding to each cargo;

[0010] Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading of the target container is optimized to obtain a target cargo loading strategy, and based on the target cargo loading strategy, the target cargo is combined and loaded into the target container.

[0011] In a second aspect, an embodiment of the present invention further provides a cargo merging loading device, comprising:

[0012] An information acquisition module, used to acquire dispersed multiple goods and a target container for merging and loading the goods;

[0013] A cargo clustering module is used to cluster cargo based on the number of preset cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information, to obtain a target cargo set corresponding to each cargo category;

[0014] A virtual size determination module, used to determine virtual cargo size information corresponding to each cargo based on the target cargo set;

[0015] The combined loading module is used to optimize the cargo loading of the target container based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, obtain the target cargo loading strategy, and combine and load the target cargo into the target container based on the target cargo loading strategy.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0017] one or more processors;

[0018] A memory for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the cargo consolidation loading method provided by any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cargo consolidation loading method provided in any embodiment of the present invention.

[0021] One embodiment of the above invention has the following advantages or beneficial effects:

[0022] By clustering a variety of scattered goods based on the preset number of goods categories, the actual goods size information corresponding to each goods, and the goods weight identification information, a target goods set corresponding to each goods category under the preset number of goods categories is obtained, and the virtual goods size information corresponding to each goods is determined based on the target goods set; based on the virtual goods size information corresponding to each goods and the actual size information of the target container, the cargo loading of the target container is optimized, and based on the target cargo loading strategy, the target goods are merged and loaded into the target container, so that by clustering goods, the number of goods categories that need to be considered in the cargo loading optimization process can be reduced, thereby reducing the computational complexity in the cargo loading optimization process, reducing the amount of calculation, and improving the efficiency of cargo merging and loading. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 is a flow chart of a cargo consolidation loading method provided by one embodiment of the present invention;

[0025] Figure 2 is an example diagram of cargo loading optimization involved in an embodiment of the present invention;

[0026] Figure 3 is a flow chart of another cargo consolidation loading method provided by one embodiment of the present invention;

[0027] Figure 4 It is a structural schematic diagram of a cargo merging loading device provided by one embodiment of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0030] Figure 1 This is a flow chart of a cargo merging method provided by an embodiment of the present invention. This embodiment can be applied to optimize cargo loading of dispersed cargoes and merge the most suitable dispersed cargoes into the same container. The method can be executed by a cargo merging device, which can be implemented by software and / or hardware and integrated into an electronic device. Figure 1 As shown, the method specifically comprises the following steps:

[0031] S110, obtaining a plurality of dispersed goods and a target container for merging and loading the goods.

[0032] Among them, the cargo can be any object that needs to be loaded together. For example, the cargo can be parts loaded in small rectangular boxes. Different categories of cargo can refer to different models of cargo. Different categories of cargo have different sizes. For example, the length, width and height of the nth cargo are l(n), w(n) and h(n) respectively. The quantity of each cargo can be one or more. The target container can be any container used for loading cargo together. For example, the target container can refer to a standard logistics box.

[0033] S120: Cluster the goods based on the number of preset goods categories, actual goods size information corresponding to each kind of goods, and goods weight identification information to obtain a target goods set corresponding to each kind of goods.

[0034] Among them, the preset number of cargo categories may be the number of cargo categories that the cargo is desired to be clustered into, which is pre-set based on business needs and scenarios. The preset number of cargo categories M is less than the original number of cargo categories N. For example, when there are N different categories of cargo, it is necessary to cluster the N types of cargo into M categories, so that the number of cargo categories can be reduced. The actual cargo size information corresponding to each type of cargo may be the actual size information of the cargo, i.e., l(n), w(n), and h(n). The cargo weight identification information may be identification information used to characterize whether the cargo is heavy or light. For example, the cargo weight identification information may be 0 or 1, where 0 represents light cargo and 1 represents heavy cargo. The target cargo set may refer to each cargo set in the final clustering result. The number of target cargo sets is the preset number of cargo categories. Each target cargo set includes multiple cargoes of similar sizes.

[0035] Specifically, by using a preset clustering method, such as a K-means clustering method or a hierarchical clustering method, the goods are clustered based on the preset number of goods categories, the actual goods size information corresponding to each kind of goods, and the goods weight identification information, to obtain a target goods set of the preset number of goods categories after clustering. For example, multiple goods with the closest sizes and meeting the preset weight merging conditions can be merged to obtain a target goods set corresponding to each kind of goods with the smallest merge loss value.

[0036] Exemplarily, S120 may include: clustering the goods based on a beam search method, a preset number of goods categories, actual goods size information corresponding to each kind of goods, and goods weight identification information to obtain a target goods set corresponding to each kind of goods.

[0037] Among them, the beam search method is to select the range of each search result by limiting the beam width, so that the optimal solution search is performed within a certain beam width each time, thereby improving the search efficiency of the optimal solution. Specifically, by using the beam search method to cluster goods, the global optimal clustering result can be quickly obtained, thereby improving the efficiency of goods clustering.

[0038] Exemplarily, clustering cargoes based on a beam search method, a preset number of cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information to obtain a target cargo set corresponding to each cargo category may include: initializing each cargo as a current cargo set corresponding to a cargo category, and obtaining cargo weight identification information corresponding to each current cargo set; based on the cargo weight identification information corresponding to each current cargo set and the actual cargo size information corresponding to each cargo, performing a beam search of successive merging and merging losses on two current cargo sets that meet a preset weight merging condition to obtain a target cargo set corresponding to each cargo category under a preset number of cargo categories.

[0039] Specifically, each of the N kinds of goods is regarded as a current set of goods corresponding to a goods category, and the current set of goods at this time contains only one goods. The goods weight identification information corresponding to each kind of goods can be directly determined as the goods weight identification information of the corresponding current set of goods. During the first clustering and merging, it is equivalent to the existence of N current sets of goods, and there is only one goods in each current set of goods. Based on the goods weight identification information corresponding to each current set of goods and the actual goods size information corresponding to each kind of goods, two current sets of goods that meet the preset weight merging conditions in the N current sets of goods are merged one by one and the beam search of the merging loss is performed. Each merger will reduce the number of current sets of goods until the number of current sets of goods is reduced to the preset number of goods categories, and the merger ends. Based on the cluster search results after the merger, the target set of goods corresponding to each category of goods under the preset number of goods categories can be determined.

[0040] S130: Determine virtual cargo size information corresponding to each cargo based on the target cargo set.

[0041] The virtual cargo size information refers to the size information that is similar to the actual cargo size. Specifically, the sizes of all cargoes in each target cargo set can be unified, and the same virtual cargo size information can be used to approximate the actual cargo size information of each cargo in the set, so that N types of cargo can be integrated into M types of cargo, reducing the number of cargo categories.

[0042] Exemplarily, S130 may include: determining virtual cargo size information corresponding to the target cargo set; and determining the virtual cargo size information corresponding to the target cargo set as virtual cargo size information corresponding to each cargo in the target cargo set.

[0043] Specifically, for each target cargo set, the maximum cargo size information corresponding to the target cargo set can be determined based on the actual cargo size information corresponding to each cargo in the target cargo set, and the maximum cargo size information is determined as the virtual cargo size information corresponding to the target cargo set. For example, the actual length l(n), actual width w(n) and actual height h(n) of each cargo in the target cargo set can be compared to determine the maximum actual length, maximum actual width and maximum actual height in the target cargo set, and the maximum actual length, maximum actual width and maximum actual height are respectively determined as the virtual length L(m), virtual width W(m) and virtual height H(m) corresponding to the target cargo set, thereby obtaining the virtual cargo size information corresponding to the target cargo set. The virtual cargo size information corresponding to each cargo in the target cargo set is determined as the virtual cargo size information corresponding to the target cargo set, so that each cargo in the target cargo set is treated as cargo with sizes of L(m), W(m) and H(m), thereby greatly reducing the number of cargo categories and thus reducing the amount of calculation.

[0044] S140: Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, optimize cargo loading for the target container, obtain a target cargo loading strategy, and merge and load the target cargo into the target container based on the target cargo loading strategy.

[0045] The target cargo loading strategy may refer to an optimal combined loading strategy. For example, the target cargo loading strategy may be a cargo loading strategy when the target container loading rate is maximized. The target cargo loading strategy may include: the target cargo that needs to be combined and loaded in the target container and the loading position and posture of each target cargo, so that the loading rate of the target container is maximized (i.e., the number of loaded cargoes is the largest).

[0046] Specifically, integer programming algorithms, genetic algorithms, or reinforcement learning can be used to optimize the loading rate to maximize the loading rate. Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading optimization of the target container is performed to obtain the target cargo loading strategy when the loading rate is maximized. Since the number of cargo categories can be reduced after cargo clustering, when traversing all categories of cargo at each position of the target container, the number of traversals can be reduced, the amount of calculation can be reduced, and the optimal target cargo loading strategy can be obtained more quickly, which greatly improves the efficiency of cargo merging and loading.

[0047] The technical solution of this embodiment clusters a variety of scattered goods based on the preset number of goods categories, the actual goods size information corresponding to each kind of goods, and the goods weight identification information, to obtain a target goods set corresponding to each kind of goods category under the preset number of goods categories, and determine the virtual goods size information corresponding to each kind of goods based on the target goods set; based on the virtual goods size information corresponding to each kind of goods and the actual size information of the target container, optimize the cargo loading of the target container, and based on the target cargo loading strategy, merge and load the target goods into the target container, so that by clustering goods, the number of goods categories that need to be considered in the cargo loading optimization process can be reduced, thereby reducing the computational complexity in the cargo loading optimization process, reducing the amount of computation, and improving the efficiency of cargo merging and loading.

[0048] On the basis of the above technical solution, "based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, optimizing the cargo loading of the target container to obtain the target cargo loading strategy" in S140 may include: based on the tree search method, the virtual cargo size information corresponding to each cargo and the actual size information of the target container, optimizing the cargo loading of the target container to obtain the target cargo loading strategy when the loading rate is maximum.

[0049] Specifically, the tree search method uses goods to pile up into columns that can verify the horizontal and vertical directions of the container, and then fills the container. Figure 2 As shown in the figure, tree search uses the structure of a binary tree. The left subtree stores the result of filling a horizontal column based on the current node, and the right subtree stores the result of filling a vertical column based on the current node. Among the two results, the one with the largest loading rate will be returned. Using the structure of the binary tree, a comparison can be made from the bottom to the top, and finally the root node is reached, and the output is the cargo loading strategy with the largest loading rate. Each horizontal and vertical column is formed by the accumulation of cargoes one by one, that is, each column is formed by the stacking of a single cargo from the bottom to the top. When generating each column, the solution of the knapsack problem can be used to traverse all types of cargo at each position and select the best way to form the column. By filling the remaining space in the target container with a horizontal column or a vertical column, the one with a higher loading rate is found from the two options, so that the target cargo loading strategy with the largest loading rate can be accurately obtained by using the tree search method under the constraints of the virtual cargo size information of each cargo and the actual size information of the target container.

[0050] It should be noted that the complexity of cargo loading optimization using tree search is O(N M), where N is the number of cargo categories and M is related to the size of the target container. By reducing the number of cargo categories, the complexity of cargo loading optimization can be reduced, thereby reducing the amount of calculation and improving the efficiency of cargo consolidation loading.

[0051] Figure 3 This is a flow chart of another cargo merging loading method provided by an embodiment of the present invention. Based on the above embodiments, this embodiment describes in detail the specific process of the cluster search. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0052] See also Figure 3 Another cargo consolidation loading method provided in this embodiment specifically includes the following steps:

[0053] S310: Acquire a plurality of dispersed goods and a target container for merging and loading the goods.

[0054] S320: Initialize each type of cargo as a current cargo set corresponding to a cargo category, and obtain cargo weight identification information corresponding to each current cargo set.

[0055] Specifically, each of the N types of goods is regarded as a current goods set corresponding to a goods category, and the current goods set at this time contains only one goods. The goods weight identification information corresponding to each kind of goods can be directly determined as the goods weight identification information of the corresponding current goods set. When clustering and merging for the first time, it is equivalent to having N current goods sets, and each current goods set contains only one goods.

[0056] S330. Based on the cargo weight identification information corresponding to each current cargo set, two current cargo sets that meet the preset weight merging condition are traversed and merged to obtain multiple first clustering results after the merger, and the number of current cargo categories after the merger is updated.

[0057] Among them, the preset weight merging condition may be a weight condition that is set in advance based on business needs and scenarios, and that the goods that can be merged into a group need to meet. For example, in an actual business scenario, heavy goods cannot be pressed on top of light goods, so light goods and heavy goods cannot be merged, and light goods and heavy goods need to be separated and placed in different categories. Based on this, the preset weight merging condition may be to merge heavy goods with heavy goods, and light goods with light goods. The first clustering result may refer to the clustering result obtained after merging only two current goods sets among all current goods sets. The two current goods sets merged in different first clustering results are different. Each current goods set corresponds to a goods category. The number of current goods categories may be the number of current goods sets that exist after the current merge.

[0058] Specifically, during the first clustering and merging, based on the cargo weight identification information corresponding to each current cargo set, two current cargo sets that meet the preset weight merging conditions among the N current cargo sets can be traversed and merged to obtain multiple first clustering results after the current merging. Since only two current cargo sets are merged each time, each first clustering result obtained after the first merging includes N-1 current cargo sets. In view of this, the current cargo category number can be updated by reducing the current cargo category number N by 1, that is, after the current merging, the current cargo category number is updated to N-1.

[0059] Exemplarily, "based on the cargo weight identification information corresponding to each current cargo set, traversing and merging two current cargo sets that meet the preset weight merging conditions to obtain multiple first clustering results after the merger" in S330 may include: traversing and merging two current cargo sets with the same cargo weight identification information to obtain multiple first clustering results after the merger; wherein, each first clustering result contains only one merger of two current cargo sets.

[0060] Specifically, based on the cargo weight identification information corresponding to each current cargo set, two current cargo sets that belong to the same light cargo or heavy cargo can be merged in all cases to obtain the first clustering result corresponding to each merged case. For example, if there are 6 types of cargo (i.e., N is equal to 6), namely cargo A, cargo B, cargo C, cargo D, cargo E, and cargo F, then there are 6 current cargo sets during the first clustering and merging, namely {A}, {B}, {C}, {D}, {E}, and {F}, among which {A}, {B}, and {C} are light cargo, and {D}, {E}, and {F} are heavy cargo. By traversing and merging two light cargoes or two heavy cargoes, 6 first clustering results can be obtained. The clustering results are: [{AB}, {C}, {D}, {E}, {F}]; [{A}, {BC}, {D}, {E}, {F}]; [{AC}, {B}, {D}, {E}, {F}]; [{A}, {B}, {C}, {DE}, {F}]; [{A}, {B}, {C}, {D}, {EF}]; and [{A}, {B}, {C}, {E}, {DF}]. It can be seen that the current number of cargo categories after the first merger is updated to 5.

[0061] S340. Determine a combined loss value corresponding to each first clustering result based on actual cargo size information corresponding to each cargo in each first clustering result, and determine a second clustering result with a preset beam width number from the first clustering results based on the combined loss value.

[0062] The merge loss value refers to the precision loss value after approximating the actual size of each cargo to the virtual size of the cargo set. The closer the actual size of each cargo is to the virtual size of the cargo set, the smaller the merge loss value. The preset beam width number B can be a preset result range of each beam search, that is, the number of clustering results that need to be retained after each merge. The second clustering result can refer to the first clustering result with a smaller merge loss value. The number of second clustering results is the preset beam width number.

[0063] Specifically, for each first clustering result after the current merger, the merger loss value after approximating the actual size of each cargo in the first clustering result to the virtual size of the cargo set can be determined based on the actual cargo size information corresponding to each cargo in the first clustering result. The merger loss values ​​corresponding to each first clustering result are arranged in ascending order from small to large to obtain a first clustering result sequence with increasing merger loss values, and the first clustering results with the preset number of beam widths in the first clustering result sequence are determined as the second clustering results to complete the current clustering merger operation. Continuing with the above example, if the preset number of beam widths is 4, the first 4 first clustering results with the smallest merger loss values ​​are selected from the 6 first clustering results as the second clustering results after the current merger.

[0064] Exemplarily, the “determining the combined loss value corresponding to each first clustering result based on the actual cargo size information corresponding to each cargo in each first clustering result” in S340 may include the following steps S341 and S342:

[0065] S341. For each first clustering result, based on actual cargo size information corresponding to each cargo in each current cargo set in the first clustering result, determine virtual cargo size information corresponding to each current cargo set in the first clustering result.

[0066] The virtual cargo size information refers to size information that is similar to the actual cargo size. Specifically, for each first clustering result, the sizes of all cargoes in each current cargo set in the first clustering result can be unified, and the same virtual cargo size information can be used to approximate the actual cargo size information of each cargo in each current cargo set, thereby reducing the number of cargo categories.

[0067] Exemplarily, S341 may include: for each current cargo set in the first clustering result, determining the maximum cargo size information corresponding to the current cargo set based on the actual cargo size information corresponding to each cargo in the current cargo set; and determining the maximum cargo size information as the virtual cargo size information corresponding to the current cargo set.

[0068] Specifically, for each current cargo set in the first clustering result, the maximum cargo size information corresponding to the current cargo set can be determined based on the actual cargo size information corresponding to each cargo in the current cargo set, and the maximum cargo size information can be determined as the virtual cargo size information corresponding to the current cargo set. For example, the actual length l(n), actual width w(n) and actual height h(n) of each cargo in the current cargo set can be compared to determine the maximum actual length, maximum actual width and maximum actual height in the current cargo set, and the maximum actual length, maximum actual width and maximum actual height can be determined as the virtual length L(m), virtual width W(m) and virtual height H(m) corresponding to the current cargo set, respectively, so as to obtain the virtual cargo size information corresponding to the current cargo set. The virtual cargo size information corresponding to each cargo in the current cargo set is determined as the virtual cargo size information corresponding to the current cargo set, so that each cargo in the current cargo set is treated as cargo with sizes of L(m), W(m) and H(m), thereby greatly reducing the number of cargo categories and thus reducing the amount of calculation.

[0069] S342: Determine a combined loss value corresponding to the first clustering result based on the virtual cargo size information corresponding to each current cargo set in the first clustering result and the actual cargo size information corresponding to each cargo.

[0070] Specifically, the virtual cargo size information corresponding to each current cargo set is the virtual cargo size information corresponding to each cargo included in each current cargo set. Based on the virtual cargo size information and the actual cargo size information corresponding to each cargo in each current cargo set in the first clustering result, the combined loss value after approximating the actual size of each cargo to the virtual size of the cargo set in the first clustering result can be determined.

[0071] Exemplarily, S342 may include: determining the volume loss value corresponding to each current cargo set in the first clustering result based on the virtual cargo size information corresponding to each current cargo set in the first clustering result and the actual cargo size information corresponding to each cargo; determining the combined loss value corresponding to the first clustering result based on the volume loss value corresponding to each current cargo set in the first clustering result.

[0072] Specifically, based on the virtual cargo size information corresponding to each current cargo set in the first clustering result, the virtual volume corresponding to each cargo in each current cargo set can be determined. For example, the virtual volume corresponding to the i-th cargo in the m-th set G(m) is V m = L(m)×W(m)×H(m). The actual volume corresponding to each cargo is determined based on the actual cargo size information corresponding to each cargo. For example, the actual volume corresponding to the i-th cargo is Vi = l(i)×w(i)×h(i). The absolute value of the difference between the virtual volume corresponding to each cargo and the corresponding actual volume is determined as the volume loss value corresponding to the corresponding cargo, that is, V(i,m) = |V m -V i |. Add the volume loss values ​​corresponding to each type of cargo contained in each current cargo set in the first clustering result to obtain the volume loss value corresponding to each current cargo set, which is ∑ i∈G(m) V(i,m). Add the volume loss values ​​corresponding to each current cargo set in the first clustering result to obtain the combined loss value corresponding to the first clustering result, which is ∑ m ∑ i∈G(m) V(i,m). The combined loss value corresponding to each first clustering result is determined and obtained in the above manner.

[0073] S350: Perform a cluster search for the next merger and merger loss based on the cargo weight identification information corresponding to each current cargo set in each second clustering result, until the merger ends when the updated current cargo category quantity is the preset cargo category quantity.

[0074] Specifically, according to the first clustering and merging method described in steps S330-S340, based on the cargo weight identification information corresponding to each current cargo set in each second clustering result, two current cargo sets that meet the preset weight merging condition are traversed and merged to obtain multiple first clustering results after the second merging, and the current cargo category quantity after the second merging is updated, that is, the current cargo category quantity is reduced by 1 after each merging. Based on the actual cargo size information corresponding to each cargo in each first clustering result after the second merging, the merging loss value corresponding to each first clustering result is determined, and based on the merging loss value, the second clustering result with the preset beam width quantity after the second merging is determined from the first clustering result, and the second clustering merging operation is completed. Similarly, based on the cargo weight identification information corresponding to each current cargo set in each second clustering result after the second merging, a third merging and a beam search of merging loss are performed until the merging ends when the updated current cargo category quantity is the preset cargo category quantity, that is, when the clustering ends when the specified cargo category quantity is reached, thereby completing the clustering of N types of cargo into M types of categories and reducing the number of cargo categories.

[0075] S360: Based on the second clustering result of the preset beam width quantity after the merging is completed, determine the target cargo set corresponding to each cargo category under the preset cargo category quantity.

[0076] Specifically, the merging loss values ​​corresponding to the second clustering results of the preset beam width number after the merging are completed can be compared, and the second clustering result with the smallest merging loss value can be determined as the final target clustering result. The target clustering result includes a set of cargoes of a preset number of cargo categories. Each cargo set included in the target clustering result is determined as a target cargo set corresponding to each cargo category, thereby obtaining the optimal cargo clustering result, minimizing the accuracy loss caused by size unification, and ensuring the accuracy of cargo merging and loading.

[0077] S370: Determine virtual cargo size information corresponding to each cargo based on the target cargo set.

[0078] S380: Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, optimize the cargo loading of the target container, obtain the target cargo loading strategy, and merge and load the target cargo into the target container based on the target cargo loading strategy.

[0079] The technical solution of this embodiment is to traverse and merge two current cargo sets that meet the preset weight merging conditions based on the cargo weight identification information corresponding to each current cargo set, obtain multiple first clustering results after the current merger, and determine the merging loss value corresponding to each first clustering result based on the actual cargo size information corresponding to each cargo in each first clustering result, and determine the second clustering results with a preset beam width number from the first clustering results based on the merging loss value, thereby completing the first merged beam search, and perform the next merge and merging loss beam search based on the cargo weight identification information corresponding to each current cargo set in each second clustering result, until the merge is completed when the updated current cargo category number is the preset cargo category number, so that the beam search method can be used to accurately cluster cargo and ensure the efficiency and accuracy of cargo merging and loading.

[0080] The following is an embodiment of a cargo merging and loading device provided in an embodiment of the present invention. The device and the cargo merging and loading methods of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the cargo merging and loading device, reference can be made to the embodiment of the above-mentioned cargo merging and loading method.

[0081] Figure 4 This is a schematic diagram of the structure of a cargo merging loading device provided by an embodiment of the present invention. This embodiment is applicable to optimizing the loading of dispersed cargoes and merging the most suitable dispersed cargoes into the same container. Figure 4 As shown, the device specifically includes: an information acquisition module 410, a cargo clustering module 420, a virtual size determination module 430 and a combined loading module 440.

[0082] Among them, the information acquisition module 410 is used to obtain a variety of scattered goods and a target container for merging and loading the goods; the goods clustering module 420 is used to cluster the goods based on the preset number of goods categories, the actual goods size information corresponding to each kind of goods, and the goods weight identification information, and obtain the target goods set corresponding to each kind of goods category; the virtual size determination module 430 is used to determine the virtual goods size information corresponding to each kind of goods based on the target goods set; the merging and loading module 440 is used to optimize the cargo loading of the target container based on the virtual goods size information corresponding to each kind of goods and the actual size information of the target container, obtain the target cargo loading strategy, and merge and load the target goods into the target container based on the target cargo loading strategy.

[0083] The technical solution of this embodiment clusters a plurality of scattered goods based on the preset number of goods categories, the actual goods size information corresponding to each goods, and the goods weight identification information, to obtain a target goods set corresponding to each goods category under the preset number of goods categories, and determines the virtual goods size information corresponding to each goods based on the target goods set; optimizes the cargo loading of the target container based on the virtual goods size information corresponding to each goods and the actual size information of the target container, and merges and loads the target goods into the target container based on the target cargo loading strategy, so that by clustering goods, the number of goods categories that need to be considered in the cargo loading optimization process can be reduced, thereby reducing the computational complexity in the cargo loading optimization process, reducing the amount of computation, and improving the efficiency of cargo merging and loading.

[0084] Optionally, the cargo clustering module 420 includes:

[0085] The cargo initialization submodule is used to initialize each cargo to a current cargo set corresponding to a cargo category, and obtain cargo weight identification information corresponding to each current cargo set;

[0086] The cargo clustering submodule is used to perform a cluster search of successive merging and merging losses on two current cargo sets that meet the preset weight merging conditions based on the cargo weight identification information corresponding to each current cargo set and the actual cargo size information corresponding to each cargo, so as to obtain a target cargo set corresponding to each cargo category under a preset number of cargo categories.

[0087] Optionally, the cargo clustering submodule includes:

[0088] A first clustering result determination unit is used to traverse and merge two current cargo sets that meet a preset weight merging condition based on cargo weight identification information corresponding to each current cargo set, obtain a plurality of first clustering results after the current merging, and update the quantity of current cargo categories after the current merging;

[0089] a second clustering result determining unit, configured to determine a combined loss value corresponding to each first clustering result based on actual cargo size information corresponding to each cargo in each first clustering result, and determine a second clustering result of a preset beam width number from the first clustering results based on the combined loss value;

[0090] A next merging search unit, used for performing a beam search of next merging and merging loss based on the cargo weight identification information corresponding to each current cargo set in each second clustering result, until the merging ends when the updated current cargo category quantity reaches the preset cargo category quantity;

[0091] The target cargo set determination unit is used to determine the target cargo set corresponding to each cargo category under the preset cargo category quantity based on the second clustering result of the preset beam width quantity after the merging is completed.

[0092] Optionally, the first clustering result determining unit is specifically configured to:

[0093] Two current cargo sets with the same cargo weight identification information are traversed and merged to obtain a plurality of first clustering results after the current merging; wherein each first clustering result only contains one merging of the two current cargo sets.

[0094] Optionally, the second clustering result determining unit includes:

[0095] a virtual cargo size determination subunit, for determining, for each first clustering result, virtual cargo size information corresponding to each current cargo set in the first clustering result based on actual cargo size information corresponding to each cargo in each current cargo set in the first clustering result;

[0096] The combined loss value determining subunit is used to determine the combined loss value corresponding to the first clustering result based on the virtual cargo size information corresponding to each current cargo set in the first clustering result and the actual cargo size information corresponding to each cargo.

[0097] Optionally, the virtual cargo size determination subunit is specifically used to:

[0098] For each current cargo set in the first clustering result, based on the actual cargo size information corresponding to each cargo in the current cargo set, the maximum cargo size information corresponding to the current cargo set is determined; and the maximum cargo size information is determined as the virtual cargo size information corresponding to the current cargo set.

[0099] Optionally, the merge loss value determination subunit is specifically used for:

[0100] Based on the virtual cargo size information corresponding to each current cargo set in the first clustering result and the actual cargo size information corresponding to each cargo, determine the volume loss value corresponding to each current cargo set in the first clustering result; based on the volume loss value corresponding to each current cargo set in the first clustering result, determine the combined loss value corresponding to the first clustering result.

[0101] Optionally, the virtual size determination module 430 is specifically configured to:

[0102] Determine virtual cargo size information corresponding to the target cargo set; determine the virtual cargo size information corresponding to the target cargo set as virtual cargo size information corresponding to each cargo in the target cargo set.

[0103] Optionally, the merge loading module 440 is specifically used for:

[0104] Based on the tree search method, the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading of the target container is optimized to obtain the target cargo loading strategy when the loading rate is maximized.

[0105] The cargo merging and loading device provided in the embodiment of the present invention can execute the cargo merging and loading method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the cargo merging and loading method.

[0106] It is worth noting that in the embodiment of the above-mentioned cargo merging loading device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0107] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Figure 5 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0108] like Figure 5 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0109] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0110] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0111] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0112] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0113] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0114] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a cargo consolidation loading method provided in the embodiment of the present invention, the method comprising:

[0115] Acquire dispersed multiple cargoes and target containers for consolidating and loading cargoes;

[0116] Cargo clustering is performed based on the number of preset cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information, to obtain a target cargo set corresponding to each cargo category;

[0117] Based on the target cargo set, determining virtual cargo size information corresponding to each cargo;

[0118] Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading of the target container is optimized to obtain a target cargo loading strategy, and based on the target cargo loading strategy, the target cargo is combined and loaded into the target container.

[0119] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the cargo consolidation loading method provided by any embodiment of the present invention.

[0120] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the cargo consolidation loading method provided in any embodiment of the present invention are implemented. The method includes:

[0121] Acquire dispersed multiple cargoes and target containers for consolidating and loading cargoes;

[0122] Cargo clustering is performed based on the number of preset cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information, to obtain a target cargo set corresponding to each cargo category;

[0123] Based on the target cargo set, determining virtual cargo size information corresponding to each cargo;

[0124] Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading of the target container is optimized to obtain a target cargo loading strategy, and based on the target cargo loading strategy, the target cargo is combined and loaded into the target container.

[0125] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0126] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0127] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0128] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0129] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0130] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A cargo consolidation loading method, characterized in that: include: Obtaining dispersed multiple cargoes and target containers for consolidating and loading cargoes; Cargo clustering is performed based on the number of preset cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information, to obtain a target cargo set corresponding to each cargo category; Based on the target cargo set, determining virtual cargo size information corresponding to each cargo; Based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading of the target container is optimized to obtain a target cargo loading strategy, and based on the target cargo loading strategy, the target cargo is combined and loaded into the target container.

2. The method according to claim 1, characterized in that The clustering of goods based on the preset number of goods categories, the actual goods size information corresponding to each kind of goods, and the goods weight identification information to obtain a target goods set corresponding to each kind of goods category includes: Based on the beam search method, the number of preset cargo categories, the actual cargo size information corresponding to each cargo, and the cargo weight identification information, cargo clustering is performed to obtain the target cargo set corresponding to each cargo category.

3. The method according to claim 2, characterized in that The clustering of goods based on the beam search method, the number of preset goods categories, the actual goods size information and the goods weight identification information corresponding to each goods, and obtaining the target goods set corresponding to each goods category includes: Initialize each cargo to a current cargo set corresponding to a cargo category, and obtain cargo weight identification information corresponding to each current cargo set; Based on the cargo weight identification information corresponding to each current cargo set and the actual cargo size information corresponding to each cargo, a cluster search of successive merging and merging losses is performed on two current cargo sets that meet the preset weight merging conditions to obtain a target cargo set corresponding to each cargo category under the preset cargo category quantity.

4. The method according to claim 3, characterized in that The method of performing a cluster search of successive merging and merging loss on two current cargo sets that meet a preset weight merging condition based on the cargo weight identification information corresponding to each current cargo set and the actual cargo size information corresponding to each cargo, and obtaining a target cargo set corresponding to each cargo category under a preset cargo category quantity, includes: Based on the cargo weight identification information corresponding to each current cargo set, two current cargo sets that meet the preset weight merging condition are traversed and merged to obtain multiple first clustering results after the merger, and the number of current cargo categories after the merger is updated; Determine a combined loss value corresponding to each first clustering result based on actual cargo size information corresponding to each cargo in each first clustering result, and determine a second clustering result with a preset beam width number from the first clustering results based on the combined loss value; Based on the cargo weight identification information corresponding to each current cargo set in each second clustering result, a beam search for the next merger and merger loss is performed until the number of updated current cargo categories reaches the preset number of cargo categories; Based on the second clustering result of the preset beam width quantity after the merging is completed, a target cargo set corresponding to each cargo category under the preset cargo category quantity is determined.

5. The method according to claim 4, characterized in that Based on the cargo weight identification information corresponding to each current cargo set, two current cargo sets that meet the preset weight merging condition are traversed and merged to obtain a plurality of first clustering results after the current merging, including: Two current cargo sets with the same cargo weight identification information are traversed and merged to obtain a plurality of first clustering results after the current merging; wherein each first clustering result only contains one merging of the two current cargo sets.

6. The method according to claim 4, characterized in that The determining, based on the actual cargo size information corresponding to each cargo in each first clustering result, a combined loss value corresponding to each first clustering result includes: For each first clustering result, based on the actual cargo size information corresponding to each cargo in each current cargo set in the first clustering result, determine the virtual cargo size information corresponding to each current cargo set in the first clustering result; Based on the virtual cargo size information corresponding to each current cargo set in the first clustering result and the actual cargo size information corresponding to each cargo, a combined loss value corresponding to the first clustering result is determined.

7. The method according to claim 6, characterized in that The determining, based on the actual cargo size information corresponding to each cargo in each current cargo set in the first clustering result, virtual cargo size information corresponding to each current cargo set in the first clustering result includes: For each current cargo set in the first clustering result, based on actual cargo size information corresponding to each cargo in the current cargo set, determine maximum cargo size information corresponding to the current cargo set; The maximum cargo size information is determined as virtual cargo size information corresponding to the current cargo set.

8. The method according to claim 6, characterized in that The determining, based on the virtual cargo size information corresponding to each current cargo set in the first clustering result and the actual cargo size information corresponding to each cargo, a combined loss value corresponding to the first clustering result includes: Determine a volume loss value corresponding to each current cargo set in the first clustering result based on virtual cargo size information corresponding to each current cargo set in the first clustering result and actual cargo size information corresponding to each cargo; Based on the volume loss value corresponding to each current cargo set in the first clustering result, a combined loss value corresponding to the first clustering result is determined.

9. The method according to claim 1, characterized in that: The determining, based on the target cargo set, virtual cargo size information corresponding to each cargo includes: Determine virtual cargo size information corresponding to the target cargo set; The virtual cargo size information corresponding to the target cargo set is determined as the virtual cargo size information corresponding to each cargo in the target cargo set.

10. The method according to claim 1, characterized in that The step of optimizing cargo loading of the target container based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container to obtain a target cargo loading strategy includes: Based on the tree search method, the virtual cargo size information corresponding to each cargo and the actual size information of the target container, the cargo loading of the target container is optimized to obtain the target cargo loading strategy when the loading rate is maximized.

11. A cargo merging loading device, characterized in that: include: An information acquisition module, used to acquire dispersed multiple goods and a target container for merging and loading the goods; A cargo clustering module is used to cluster cargo based on the number of preset cargo categories, actual cargo size information corresponding to each cargo, and cargo weight identification information, to obtain a target cargo set corresponding to each cargo category; A virtual size determination module, used to determine virtual cargo size information corresponding to each cargo based on the target cargo set; The combined loading module is used to optimize the cargo loading of the target container based on the virtual cargo size information corresponding to each cargo and the actual size information of the target container, obtain the target cargo loading strategy, and combine and load the target cargo into the target container based on the target cargo loading strategy.

12. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the cargo consolidation loading method as described in any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cargo consolidation loading method as described in any one of claims 1 to 10 is implemented.

Images