Warehouse layout methods, media, program products, and electronic devices

Abstract

The present invention relates to the field of logistics management and provides a warehouse layout method that can optimize warehouse layout, improve warehouse work efficiency, and reduce warehouse costs. [Solution] The solution includes the steps of: obtaining an order dataset within a set period; determining a plurality of functional areas within a warehouse based on the order dataset; determining a first area for each functional area based on the order dataset; determining the location of each functional area as a first optimization target, the aspect ratio of each functional area as a second optimization target, performing a dual encoding process on the first and second optimization targets using a genetic algorithm based on the first area of ​​each functional area, and decoding the encoded first and second optimization targets to determine an optimization result that satisfies pre-set conditions, wherein the optimization result includes the target location of each functional area and the target aspect ratio of each functional area.

Description

[Technical Field]

[0001] This invention relates to the field of logistics management technology, and more particularly to warehouse layout methods, media, program products, and electronic devices. [Background technology]

[0002] In today's manufacturing sector, the demand for integrated logistics warehouses for production, sales, and after-sales service is exploding. The diverse range of goods, small lot sizes, high frequency of shipments, and comprehensive operations such as receiving, inspecting, processing, sorting, and packaging have presented higher demands on warehouse management. The constantly changing demand for goods creates a need for non-fixed warehouse space. For example, when shipping demand is low, a smaller warehouse is needed to reduce warehouse costs, while when shipping demand is high, a larger warehouse area is required. Another example is the need to shorten the distance between several functional areas to improve operational efficiency, for example, by reducing the distance goods need to be transported. Therefore, the ability to flexibly adjust warehouse layouts in response to changing warehouse demands has become an urgent issue. [Overview of the project] [Problems that the invention aims to solve]

[0003] The present invention aims to provide a warehouse layout method, medium, program product, and electronic device that can optimize warehouse layout, improve warehouse work efficiency, and reduce warehouse costs. [Means for solving the problem]

[0004] In a first embodiment, an embodiment of the present invention provides a warehouse layout method, which includes the steps of: acquiring an order dataset for a set period; determining a plurality of functional areas within a warehouse based on the order dataset; determining a first area for each functional area based on the order dataset; and determining an optimization result that satisfies preset conditions, wherein the position of each functional area is the first optimization target, the aspect ratio of each functional area is the second optimization target, and a genetic algorithm is used to perform a dual encoding process on the first and second optimization targets based on the first area of ​​each functional area, and the encoded first and second optimization targets are decoded, and the optimization result satisfies preset conditions, the optimization result including the target position of each functional area and the target aspect ratio of each functional area. The preset conditions are for characterizing the degree of optimization of the position and aspect ratio of each functional area, and it should be understood that the degree of optimization of the target position and target aspect ratio of each functional area in the optimization result when the preset conditions are met is relatively high.

[0005] Here, the order dataset within the above-mentioned period can reflect the actual demand of the warehouse, and furthermore, a genetic algorithm can be employed based on the order dataset to simultaneously optimize the location and size of each functional area. In this way, the method can automatically optimize the size and location layout of each functional area of ​​the warehouse based on the set order data, which is advantageous in achieving the objective of reducing the total cost of the warehouse and / or reducing the total occupied area of ​​the warehouse.

[0006] In one possible implementation of the first embodiment described above, the order data in the order dataset includes at least one of the following data: order number, order date, order time in minutes, cargo type, cargo quantity, processing flow, container specifications, and work type, wherein the work type includes at least one of the following: outbound work, inbound work, and inbound work, each work type corresponds to multiple work flows, each work flow corresponds to one functional area, and the processing flow includes at least one work flow corresponding to the work type. For example, the order dataset described above may be historical data of an existing warehouse of a user such as a warehouse user, e.g., a logistics company or a merchant, or forecast data set by the user based on actual warehouse demand.

[0007] In one possible implementation of the first embodiment described above, the step of determining multiple functional areas within a warehouse based on an order dataset includes the step of determining multiple functional areas within a warehouse based on the workflows corresponding to outbound, inbound and inbound operations in the order dataset, wherein the multiple functional areas include at least one of the following: unloading area, receiving area, pallet dismantling area, quality inspection area, packing area, outbound area, pallet stacking / loading area, loading area, storage area, sorting area, equipment storage area, defective / returned goods area, and office area. For example, when determining multiple functional areas within a warehouse, the names and numbers of each functional area may be determined such that different functional areas have different numbers.

[0008] In a possible implementation of the first embodiment described above, the step of determining a first area of ​​each functional area based on an order dataset includes the steps of determining the maximum positive difference of the positive difference in cargo volume between the amount of cargo received and the amount of cargo shipped to the warehouse during a set period, based on the order dataset; determining the maximum area of ​​each functional area according to the maximum positive difference; and determining a corresponding first area based on the maximum area of ​​each functional area, wherein the first area of ​​each functional area is less than or equal to the corresponding maximum area. Naturally, the positive difference in cargo volume during a set period can reflect the peak demand for cargo volume during that period, and therefore, the maximum area of ​​each functional area may be determined based on the maximum positive difference so that the warehouse area corresponding to the determined area of ​​each functional area (e.g., the maximum area or the first area) corresponds to the maximum flow rate of cargo.

[0009] In one possible implementation of the first embodiment described above, the step of determining a corresponding first area based on the maximum area of ​​each functional area includes the step of setting the maximum area of ​​each functional area as the corresponding first area. This ensures that each functional area has sufficient space to realize its corresponding function.

[0010] In one possible implementation of the first embodiment described above, the step of determining a corresponding first area based on the maximum area of ​​each functional area includes the steps of determining a second area of ​​each functional area, wherein the second area is a preset area or an area calculated based on the work processing capacity per unit area of ​​the functional area; if the second area of ​​the functional area is smaller than the corresponding maximum area, the second area is set as the first area of ​​the functional area; and if the second area of ​​the functional area is equal to or greater than the corresponding maximum area, the maximum area is set as the first area of ​​the functional area.

[0011] Thus, the maximum area of ​​the functional area determined based on the maximum positive difference over a predetermined period, the predetermined area of ​​the functional area, and the area calculated based on the work processing capacity per unit area of ​​the functional area may comprehensively consider the maximum area of ​​the functional area and the actual area requested by the user. This is advantageous in determining a first area of ​​the functional area that is small in size but can handle a large volume of cargo.

[0012] In one possible implementation of the first embodiment described above, the step of determining the maximum positive difference of the positive difference between the amount of goods received and the amount of goods shipped to the warehouse within a set period, based on the order dataset, includes the steps of: dividing the order dataset into a plurality of sub-order datasets in a rolling manner according to the delayed processing cycle of warehouse goods (e.g., one week); calculating the positive difference of the amount of goods received and the amount of goods shipped in each sub-order dataset to obtain a plurality of positive differences of goods; and setting the maximum value of the plurality of positive differences of goods as the maximum positive difference within the set period.

[0013] In a possible implementation of the first embodiment described above, the steps of performing a dual encoding process on a first optimization target and a second optimization target using a genetic algorithm include: encoding the first optimization target and determining the encoded first optimization target as a first chromosome, wherein the first chromosome contains the numbers of each functional area and the position of the functional area in the storage corresponds to the insertion order of the functional area numbers in the first chromosome; and encoding the second optimization target and determining the encoded second optimization target as a second chromosome, wherein the second chromosome contains the aspect ratio of each functional area, the aspect ratio is within a predetermined range, and the size of the functional area corresponds to the area of ​​the first functional area and the aspect ratio in the second chromosome, wherein the first and second chromosomes constitute a pair of dual-encoded chromosomes. Here, decoding the encoded first and second optimization targets using a genetic algorithm means performing a solution on the encoded dual-encoded chromosomes. Specifically, a genetic algorithm is employed to iteratively construct a population of dual-coded chromosomes, and a dual-coded chromosome that satisfies pre-set conditions is found for each population of dual-coded chromosomes. Then, the position and aspect ratio of each functional area in the dual-coded chromosome are set as the target position and target aspect ratio, respectively, to obtain an optimized result that satisfies the pre-set conditions, i.e., an optimized warehouse layout is obtained. In this way, the genetic algorithm in the present invention can simultaneously optimize the size and aspect ratio of each functional area, so the warehouse layout corresponding to the optimized aspect ratio and position of each functional area is advantageous in reducing the total warehouse cost and / or the total warehouse footprint.

[0014] In one possible implementation of the first embodiment described above, the step of decoding the encoded first and second optimization targets and determining an optimization result that satisfies pre-set conditions is a step of constructing the kth dual-encoded chromosome population of the kth iteration process, corresponding to the number of iterations being equal to k, and performing a solution on the kth dual-encoded chromosome population to obtain the fitness of the kth iteration process, where k is a positive integer less than or equal to T, the dual-encoded chromosome population includes N pairs of dual-encoded chromosomes, and the fitness relates to the distance between different functional areas and the flow rate of cargo between different functional areas, and if the kth iteration process satisfies pre-set conditions, the optimization result is determined based on the kth dual-encoded chromosome population. The process includes a step of making a decision, and if the kth iteration does not satisfy a predetermined condition, updating the number of iterations from k to k+1 until the kth iteration satisfies the predetermined condition, re-executing the construction of the kth dual-coded chromosome population in the kth iteration, and solving for the kth dual-coded chromosome population to obtain the fitness of the kth iteration, wherein the predetermined condition includes at least one of the following: the current number of iterations is greater than T, the difference between the fitness of the current iteration and the fitness of each iteration in the previous adjacent S iterations is all less than or equal to a predetermined threshold, and the fitness of the current iteration is greater than or equal to the predetermined fitness, where S is a positive integer. In this way, the predetermined condition, limited by the number of iterations and fitness, can be used as a criterion for determining the optimization goal, allowing for the calculation of better optimization results, i.e., the position and aspect ratio of each functional area with good optimization effect, within a reasonable time. Furthermore, the present invention can determine the fit of dual-encoded chromosomes by comprehensively considering the flow rate and distance of goods between different functional areas. This is advantageous in optimizing the position and aspect ratio of each functional area by comprehensively considering the impact of these factors on the warehouse layout, thereby improving the optimization effect of the warehouse layout.

[0015] In one possible implementation of the first embodiment described above, the step of solving for the k-th bicoded chromosome population to obtain the fitness of the k-th iteration process includes the steps of calculating the fitness of each bicoded chromosome in the N pairs of bicoded chromosomes of the k-th bicoded chromosome population to obtain N fitness scores, and taking the maximum of the N fitness scores as the fitness of the k-th iteration process. The fitness score of a bicoded chromosome is used to measure the optimization effect of this bicoded chromosome (i.e., the optimization effect of the position and aspect ratio of each functional area in the bicoded chromosome), and it should be understood that a larger fitness score indicates a better corresponding optimization effect.

[0016] In a possible implementation of the first embodiment described above, the process for calculating the fitness of a dual-coded chromosome includes the steps of: decoding the dual-coded chromosome; solving the decoded dual-coded chromosome using a two-dimensional bin packing algorithm to obtain the insertion coordinates of each functional area in the warehouse and a first total area of ​​a plurality of functional areas, wherein the first total area is the area of ​​the minimum enclosing rectangle of the plurality of functional areas; calculating the distance between different functional areas based on the insertion coordinates of each functional area; and calculating the fitness of the dual-coded chromosome based on the cargo flow rate between different functional areas, the distance between different functional areas, and the first total area. In some embodiments, the fitness may be calculated based on the following equation (6). For example, the fitness of a dual-coded chromosome is related not only to the cargo flow rate and distance between different functional areas, but also to the transport cost per unit distance of cargo and the cost per warehouse area. This allows the fitness calculated using the transport distance cost and warehouse area cost to be used as a criterion for determining the overall optimization goal of the dual-coded chromosome.

[0017] In one possible implementation of the first embodiment described above, the distance between different functional areas is the Manhattan distance, the non-penetrating shortest path distance, the distance between the boundary points of different functional areas, or the distance between the center points of different functional areas.

[0018] In one possible implementation of the first aspect described above, the calculation flow for the insertion coordinates of a functional area includes the step of determining the insertion coordinates of each functional area by inserting a rectangle corresponding to each functional area into the global plane from a set origin along a first direction of a first coordinate axis and a second direction of a second coordinate axis, based on the insertion order and aspect ratio of each functional area in the dual coding chromosome and the corresponding first area, wherein the size of the functional area includes a first directional length in the first direction and a second directional length in the second direction of the rectangle corresponding to the functional area, the insertion coordinates of the functional area include a first directional coordinate value in the first coordinate axis and a second directional coordinate value in the second coordinate axis, the sum of the first directional coordinate value of the functional area and the first directional length of the functional area is less than or equal to a first total length threshold, the first total length threshold is equal to the square root of the area of ​​the global plane, and the area of ​​the global plane is a preset multiple of the sum of the first areas corresponding to each functional area. It should be understood that this invention, when combined with a two-dimensional bin packing algorithm for chromosomal dual coding, can seamlessly puzzle each functional area in the first direction (e.g., horizontal direction) and the gaps between each functional area in the second direction (e.g., vertical direction) can be evolutionarily optimized by a chromosomal genetic algorithm, thereby minimizing the warehouse area.

[0019] In one possible implementation of the first aspect described above, the step of constructing the k-th dual-coded chromosome population of the k-th iteration process includes, corresponding to k being equal to 1, the step of randomly constructing the k-th dual-coded chromosome population of the k-th iteration process, and, corresponding to k > 1, the step of performing a reconstruction operation on the dual-coded chromosomes among the k-1-th dual-coded chromosome population of the k-1-th iteration process to obtain the k-th dual-coded chromosome population of the k-th iteration process, wherein the reconstruction operation includes at least one of a selection operation, a crossover operation, or a mutation operation. For example, the selection operation, crossover operation, or mutation operation may be performed on a pair of dual-coded chromosomes with a set probability. In this way, the evolutionary process of chromosomal dual coding can be used to solve the problem of large vertical gaps in functional areas, optimize and adjust the insertion order and variable length and width of functional areas, and reduce the vertical gaps in functional areas.

[0020] In one possible implementation of the first embodiment described above, the crossover operation on the functional area numbers in different bicoded chromosomes includes the step of exchanging the positions of the first and second functional area numbers on the first chromosome of one pair of bicoded chromosomes with the second and first functional area numbers on the first chromosome of another pair of bicoded chromosomes to obtain two pairs of bicoded chromosomes after the crossover operation, and the crossover operation on the aspect ratios of the functional areas in different bicoded chromosomes includes the step of linearly processing the aspect ratio q1 of the functional area corresponding to the first index on the second chromosome of one pair of bicoded chromosomes and the aspect ratio q2 of the functional area corresponding to the first index on the second chromosome of the other pair of bicoded chromosomes such that the aspect ratio q1 is adjusted to d1 after the crossover operation and the aspect ratio q2 is adjusted to d2 after the crossover operation, where d1 = α·q1 + (1-α)·q2 and d2 = (1-α)·q1 + α·q2, where α is a coefficient less than 1.

[0021] In one possible implementation of the first embodiment described above, a mutation operation on the number of a functional area in different dual-coded chromosomes includes the step of swapping the positions of a third functional area number and a fourth functional area number in one dual-coded chromosome, and a mutation operation on the aspect ratio of a functional area in different dual-coded chromosomes includes the step of replacing the aspect ratio of the functional area corresponding to the second index in one dual-coded chromosome with a value within a predetermined range of ratios.

[0022] In one possible implementation of the first embodiment described above, the method further comprises the steps of: calculating the acceptance probability of a bicoded chromosome after a crossover operation in the k-th bicoded chromosome population; making the bicoded chromosome one of the bicoded chromosomes in the k-th bicoded chromosome population, corresponding to the acceptance probability of the bicoded chromosome being a first value; and making the bicoded chromosome one of the bicoded chromosomes in the k-th bicoded chromosome population, corresponding to the crossover operation of the bicoded chromosome being rolled back, corresponding to the acceptance probability of the bicoded chromosome being one of the bicoded chromosomes in the k-th bicoded chromosome population, wherein the acceptance probability correlates with the maximum fitness of each bicoded chromosome in the first bicoded chromosome population of This invention is based on an annealing algorithm. It should be understood that, in the evolutionary process of the genetic algorithm, at the start of the genetic algorithm, mutated chromosomes are accepted with a high probability, and as the genetic algorithm evolves to later stages and the fitness of the iteration process does not change much, mutated chromosomes are accepted with a low probability, reducing disturbances caused by mutations and avoiding impact on chromosomal properties.

[0023] In a second aspect, an embodiment of the present invention provides a readable medium storing instructions that cause an electronic device to execute the warehouse layout method in the first aspect and any possible embodiments thereof when executed on the electronic device.

[0024] In a third aspect, an embodiment of the present invention provides a computer program product that causes an electronic device to execute the warehouse layout method in the first aspect and any possible embodiments thereof when executed on the electronic device.

[0025] In a fourth aspect, an embodiment of the present invention provides an electronic device comprising a memory storing instructions executed by one or more processors of the electronic device, and a processor being one of the processors of the electronic device that executes the warehouse layout method in the first aspect and any possible embodiments thereof.

[0026] Regarding the effects of the above second to fourth aspects, reference may be made to the description of the first aspect, and the description is omitted here.

Advantages of the Invention

[0027] According to the warehouse layout method, medium, program product and electronic device of the present invention, the warehouse layout can be optimized, the warehouse operation efficiency can be improved, and the warehouse cost can be reduced.

Brief Description of the Drawings

[0028] [Figure 1] A schematic diagram showing the flow of the warehouse layout method according to an embodiment of the present invention. [Figure 2] A schematic diagram showing the flow of determining the first area of each functional area according to an embodiment of the present invention. [Figure 3] A schematic diagram showing the flow of solving double-encoded chromosomes for a plurality of functional areas according to an embodiment of the present invention. [Figure 4] A schematic diagram showing the flow of the reconfiguration operation of the double-encoded chromosome population according to an embodiment of the present invention. [Figure 5A]A schematic diagram illustrating the process of crossover operation of dual-encoded chromosomes according to an embodiment of the present invention. [Figure 5B] A schematic diagram illustrating the process of mutation manipulation of a dual-encoded chromosome according to an embodiment of the present invention. [Figure 6] A schematic diagram showing the flow of executing the kneeling algorithm on a population of dual-encoded chromosomes after reconstruction according to an embodiment of the present invention. [Figure 7] A schematic diagram showing the calculation flow of the degree of fit of a dual-encoded chromosome according to an embodiment of the present invention. [Figure 8A] A schematic diagram of the insertion of a functional area into a global planar area of ​​a warehouse according to an embodiment of the present invention. [Figure 8B] A schematic diagram of the insertion of a functional area into a global planar area of ​​a warehouse according to an embodiment of the present invention. [Figure 8C] A schematic diagram of the insertion of a functional area into a global planar area of ​​a warehouse according to an embodiment of the present invention. [Figure 8D] A schematic diagram of the insertion of a functional area into a global planar area of ​​a warehouse according to an embodiment of the present invention. [Figure 9] A schematic diagram showing the flow of inserting a functional area using a two-dimensional bin packing algorithm according to an embodiment of the present invention. [Figure 10] A schematic diagram of an electronic device according to an embodiment of the present invention. [Modes for carrying out the invention]

[0029] Exemplary embodiments of the present invention include, but are not limited to, warehouse layout methods, media, program products, and electronic devices.

[0030] To flexibly set the warehouse layout according to the actual demand of the warehouse, an embodiment of the present invention provides a warehouse layout method that includes the steps of: acquiring an order dataset for a set period, for example, within one month, such as cargo volume, cargo type, etc.; determining a plurality of functional areas in the warehouse based on the order dataset, for example, determining an unloading area, a shelving area, etc.; determining a first area for each functional area based on the order dataset, for example, determining the maximum set area for each functional area; and using a genetic algorithm to perform a dual encoding process on the first and second optimization targets based on the first area of ​​each functional area, with the position of each functional area as the first optimization target and the aspect ratio of each functional area as the second optimization target, and then decoding the encoded first and second optimization targets to determine an optimization result that satisfies preset conditions, including the target position of each functional area and the target aspect ratio of each functional area.

[0031] Furthermore, the order dataset within the specified period can reflect the actual demand of the warehouse, and a genetic algorithm can be employed based on this order dataset to simultaneously optimize the location and size of each functional area. In this way, the method can automatically optimize the size and location layout of each functional area of ​​the warehouse based on the set order data, which is advantageous in achieving the objective of reducing the total cost of the warehouse and / or reducing the total occupied area of ​​the warehouse.

[0032] Furthermore, optimizing the functional area layout of a warehouse is a crucial foundation for efficient and fully utilized warehouse operations. A dynamic warehouse optimization layout ensures the coordination and efficiency of warehouse workflows and reduces overall warehouse costs. This minimizes cargo stagnation, reduces operating costs, and avoids cargo loss. By shortening the total picking distance, operational efficiency is effectively improved, and operating costs are reduced. Moreover, by improving the utilization rate of effective warehouse space, the total warehouse space occupied is reduced, further lowering storage costs.

[0033] In some embodiments, the entity that executes the warehouse layout method according to the embodiments of this specification may be an electronic device, or a module or unit for executing the warehouse layout method on the electronic device, and is not particularly limited herein. For example, the module or unit may be executed as a software algorithm, and the software algorithm may be implemented by an independent application, software, etc., or by plugging into existing software or applications in the logistics field. In the following embodiments, the warehouse layout method will be described with the entity that executes it being an electronic device.

[0034] Exemplary examples of the electronic devices in the embodiments of the present invention may include tablets, desktops, laptops, handheld computers, and ultra-mobile personal computer (UMPC) devices, and the embodiments of the present invention do not particularly limit the form of the electronic device.

[0035] As shown in Figure 1, this is a schematic diagram illustrating the flow of a warehouse layout method according to an embodiment of the present invention. This flow includes the following steps.

[0036] S101: Retrieves the order dataset for the specified period.

[0037] The setting period may be one month, two months, or any other set period. The length of this period can be set according to the user's actual needs, and the present invention is not specifically limited thereto.

[0038] In some embodiments, the above order dataset may be historical data of an existing warehouse belonging to a warehouse user, such as a logistics company or merchant, or forecast data set by the user based on actual warehouse demand.

[0039] For example, the above order dataset includes multiple order data, each order data including at least one of the following: order number, order date, order time / minutes, cargo type, cargo quantity, processing flow, container specifications, and work type.

[0040] Table 1 shows an example of order data.

[0041] [Table 1]

[0042] Table 1 is merely an example of order data, and in actual applications, the order data may contain more or less content. Please understand that the embodiments of the present invention are not particularly limited thereto. For example, the order data may further include shelf specification data.

[0043] Next, we will explain the work type, processing flow, work co-flow, container specifications, and shelf specifications in order data using the contents shown in Tables 2 to 6 as examples.

[0044] In some embodiments, the work type includes at least one of outbound work, inbound work, and inbound work.

[0045] Table 2 shows an example of work types. Here, each work type corresponds to one type label, and the type label for the outbound work type shown in Table 2 is 0.

[0046] [Table 2]

[0047] In some embodiments, each work type corresponds to multiple work flows.

[0048] Refer to Table 3 for an example of a workflow corresponding to receiving operations. As shown in Table 3, the workflow corresponding to receiving operations includes unloading, counting / quality inspection, temporary storage, pallet dismantling, relabeling, and shelving. Each workflow corresponds to one type of work code, and the receiving work code corresponding to unloading in Table 3 is U.

[0049] [Table 3]

[0050] Refer to Table 4 to see an example of a workflow corresponding to outbound operations. As shown in Table 4, the workflow corresponding to outbound operations includes picking, quality inspection, packaging, labeling, palletizing, temporary storage, counting, and loading. Each workflow corresponds to one type of work code, and the outbound work code corresponding to picking in Table 4 is G.

[0051] [Table 4]

[0052] Refer to Table 5 to see an example of a work flow corresponding to in-warehouse movement operations. As shown in Table 5, the work flow corresponding to in-warehouse movement operations includes picking, counting, temporary storage, pallet dismantling, relabeling, and shelving. Each work flow corresponds to one type of work code, and the in-warehouse movement work code corresponding to temporary storage in Table 5 is S.

[0053] [Table 5]

[0054] As can be seen from Tables 2-5, a single work flow may correspond to one or more work types. For example, unloading may correspond only to the receiving work flow, while shelving may correspond to both receiving and internal movement.

[0055] In some embodiments, the processing flow in order data may include at least one work co-flow corresponding to one work type. For example, in Table 1, the processing flow in order data for order number 1 is UCSBT, and the work type label is 1. In this case, as can be seen from Table 1-3, this processing flow sequentially includes unloading (U), counting (C), temporary storage (S), labeling (B), and shelving (T) during receiving operations.

[0056] Table 6 shows the container specification data. Here, each container specification corresponds to one specification label and one set of length, width, and height data. As shown in Table 6, the length, width, and height of the container specification for specification label S are all 50, and the data unit may be centimeters (cm).

[0057] [Table 6]

[0058] Table 7 shows the shelf specifications. Here, the shelf specifications include multiple parameter types such as shelf length, width, and height, and the unit of these values ​​is meters (m). The parameter types of the shelf specifications also include the number of shelves, and the unit of this value is layers. In the shelf specifications shown in Table 7, the shelf length is 3.5m, the shelf width is 1.2m, the shelf height is 1.4m, and the number of shelves is 3 layers.

[0059] [Table 7]

[0060] The explanations for each data point in Tables 1-7 above are merely examples. In actual applications, these data points may be set to other values ​​and may be configured according to the actual needs of the user's warehouse users.

[0061] S102: Determine multiple functional areas within the warehouse based on the order dataset.

[0062] In some embodiments, the above-mentioned functional areas may include at least one of the following: unloading area, receiving temporary storage area, pallet dismantling work area, quality inspection work area, packaging work area, shipping temporary storage area, pallet stacking / stacking work area, loading area, storage area, sorting area, equipment layout area, defective goods / returns area, and office area. Furthermore, the functional areas within the warehouse include, but are not limited to, the above examples, and may include other functional areas, and embodiments of the present invention are not particularly limited thereto.

[0063] In some embodiments, the electronic device may determine multiple functional areas within the warehouse based on the work flow corresponding to outbound, inbound, and inbound operations in the order dataset. Naturally, one type of work flow may correspond to one functional area. For example, shelving may correspond to a shelving area, and unloading to an unloading area.

[0064] In some embodiments, when determining multiple functional areas within a warehouse, the names and numbers of each functional area may be determined so that different functional areas have different numbers. For example, the unloading area may be numbered 1 and the receiving / temporary storage area may be numbered 2; the actual functional area numbers are not limited to this example.

[0065] S103: Determine the first area of ​​each functional area from the order dataset.

[0066] In some embodiments, the first area of ​​the functional area may be a fixed area set by the user according to actual demand, or it may be an area dynamically determined according to the positive difference in cargo volume corresponding to the order dataset. However, within a certain period, the positive difference in cargo volume is equal to the difference between the amount of cargo received and the amount of cargo sent out.

[0067] S104: The position of each functional area is set as the first optimization target, and the aspect ratio of each functional area is set as the second optimization target. Based on the first area of ​​each functional area, a genetic algorithm is used to perform a dual encoding process on the first and second optimization targets. The encoded first and second optimization targets are then decoded to determine an optimization result that satisfies pre-set conditions.

[0068] Here, the optimization results include the target position and target aspect ratio of each functional area, and these optimization results represent the functional area layout of the warehouse.

[0069] In some embodiments, a first optimization target is encoded, and the encoded first optimization target is designated as the first chromosome. The first chromosome contains the number of each functional area, and the position of the functional area in the warehouse corresponds to the insertion order of the functional area numbers in the first chromosome. A second optimization target is encoded, and the encoded second optimization target is designated as the second chromosome. The second chromosome contains the aspect ratio of each functional area, and the aspect ratio is within a predetermined range. The size of the functional area corresponds to the area of ​​the first functional area and the aspect ratio in the second chromosome. Here, the first and second chromosomes constitute a pair of dual-encoded chromosomes. For example, the predetermined range of the ratio is (0.2, 5), i.e., the aspect ratio is between 1:5 and 5:1.

[0070] Refer to Table 8 for examples of dual-encoded chromosomes.

[0071] [Table 8]

[0072] Taking Table 8 as an example, the first chromosome is a functional area code, meaning that the fragments within the first chromosome are the numbers of each functional area, and the index of each fragment may represent the insertion order of the corresponding functional area. As shown in Table 8, if the warehouse contains 10 functional areas, let's assign the numbers 0 to 9 to these functional areas. In this case, in the first chromosome, the functional area numbered 4 is contained in the fragment with index 0, indicating that the insertion order of functional area number 4 is 1. In other words, this functional area is the first functional area to be inserted into the global plane where the warehouse is located.

[0073] Taking Table 8 as an example, the second chromosome represents the aspect ratio of the functional area, meaning that each fragment within the second chromosome represents the aspect ratio of the respective functional area. When setting up a dual-encoded chromosome, it should be understood that while the first area of ​​the functional area in the second chromosome is fixed, its aspect ratio changes dynamically. As shown in Table 8, in the second chromosome, the aspect ratio of the functional area included in the segment with index 0 is 2.9, meaning the aspect ratio of functional area number 4 is 2.9. In this case, based on the known first area of ​​that functional area, its length and width can be calculated using that first area and its aspect ratio, thereby determining the size of that functional area.

[0074] In some embodiments, decoding the encoded first and second optimization targets using a genetic algorithm means solving for the encoded dual-encoded chromosomes. Specifically, a genetic algorithm can be used to iteratively construct a population of dual-encoded chromosomes, and for each population of dual-encoded chromosomes, a dual-encoded chromosome that satisfies pre-set conditions is found. Then, by setting the position and aspect ratio of each functional area in the dual-encoded chromosome as the target position and target aspect ratio, an optimization result that satisfies pre-set conditions is obtained, i.e., an optimized warehouse layout is obtained.

[0075] It should be noted that the aforementioned pre-set conditions are intended to characterize the degree of optimization of the position and aspect ratio of each functional area, and that when the pre-set conditions are met, the degree of optimization of the target position and target aspect ratio of each functional area in the optimization result is relatively high. The specific contents included in the pre-set conditions will be described later, so the explanation is omitted here. In this case, the warehouse layout corresponding to the above optimization result can guarantee the coordination and efficiency of work flows between different functional areas, as well as improve the effective area utilization rate of the warehouse.

[0076] Thus, the genetic algorithm in the present invention can simultaneously optimize the size and aspect ratio of each functional area, and the warehouse layout corresponding to the optimized aspect ratio and position of each functional area is advantageous in reducing the total warehouse cost and / or the total warehouse footprint.

[0077] Referring to Figure 2, a flowchart for determining the first area of ​​each functional area according to the present invention is shown. As shown in Figure 2, S103 shown in Figure 1 above may include S1031 to S1033.

[0078] S1031: Based on the order dataset, determine the maximum positive difference between the amount of goods received and the amount of goods shipped to the warehouse during the specified period.

[0079] Within a certain period, the positive difference in cargo volume is equal to the difference between the volume of cargo received and the volume of cargo shipped out.

[0080] In some embodiments, the maximum positive difference within the set period is the value obtained by subtracting the total outgoing amount from the total incoming amount within the set period.

[0081] In other embodiments, the maximum value of the difference between the amount of goods shipped out and the amount of goods received within the set period, i.e., the maximum positive difference within the set period, may be calculated in a rolling manner based on the delayed processing cycle of warehouse goods, for example, one week (the cycle can be set).

[0082] For example, in the case of electronic equipment, the order dataset can be divided into multiple sub-order datasets in a rolling manner according to the delayed processing cycle of warehouse cargo (e.g., one week), the positive difference between the amount of incoming cargo and the amount of outgoing cargo in each sub-order dataset can be calculated, multiple positive differences in cargo quantities can be obtained, and the maximum value among these multiple positive differences in cargo quantities can be taken as the maximum positive difference within the set period, that is, within the set period, max(positive difference in cargo quantities) = max(amount of incoming cargo - amount of outgoing cargo).

[0083] S1032: Determine the maximum area of ​​each functional area based on the maximum positive difference.

[0084] Furthermore, since the positive difference in cargo volume during the set period can reflect the peak demand for cargo volume during that period, the maximum area of ​​each functional area may be determined based on the maximum positive difference, and the warehouse area corresponding to the determined area of ​​each functional area (for example, the maximum area or the first area) may be made to correspond to the maximum cargo flow rate.

[0085] S1033: A corresponding first area is determined based on the maximum area of ​​each functional area, where the first area of ​​each functional area is less than or equal to the corresponding maximum area.

[0086] In some embodiments, the maximum area of ​​each functional area may also be the corresponding first area.

[0087] In other embodiments, the flow for determining the first area based on the maximum area of ​​each functional area includes the following steps, as shown in S1033 of Figure 2: Step 1: Determine the second area of ​​each functional area, which is either a preset area of ​​the corresponding functional area (i.e., a set fixed area) or an area calculated based on the work processing capacity per unit area of ​​the corresponding functional area. Step 2: If the second area of ​​a functional area is smaller than the corresponding maximum area, the second area of ​​the functional area is set as the corresponding first area. Step 3: If the second area of ​​a functional area is greater than or equal to the corresponding maximum area, the maximum area of ​​the functional area is set as the corresponding first area. Here, steps 2 and 3 are parallel steps.

[0088] In some embodiments, a number may be set for a fixed-area functional area, that is, a functional area may be set as a fixed-area functional area, and the area value of the fixed area may be entered in advance. For example, the area of ​​the office area may be set as a fixed area according to the number of office workers.

[0089] Thus, the maximum area of ​​the functional area determined based on the maximum positive difference over a predetermined period, the predetermined area of ​​the functional area, and the area calculated based on the work processing capacity per unit area of ​​the functional area may comprehensively consider the maximum area of ​​the functional area and the actual area requested by the user. This allows for the determination of a first functional area that is small in size but capable of handling a large volume of cargo.

[0090] In some embodiments, the present invention may initialize the genetic algorithm before using it. For example, the population size may be N, i.e., the number of groups containing dual-encoded chromosomes, the maximum number of evolutionary generations of the algorithm may be T, i.e., the maximum number of iterations may be T, and the termination condition of the algorithm may be set. The termination condition of this algorithm will be explained in the flowchart shown in Figure 3 below, so the explanation will be omitted here.

[0091] Referring to Figure 3, the flow for solving a dual-encoded chromosome for multiple functional areas may include the following steps, for example, as shown in S105 in Figure 1.

[0092] S1051: Construct a population of individuals with the k-th dual-coded chromosome in the k-th iteration process, and then perform a solution on the k-th dual-coded chromosome population to obtain the fitness of the k-th iteration process.

[0093] Here, k is a positive integer less than or equal to T, and a population of bizygotic chromosomes contains N pairs of bizygotic chromosomes.

[0094] In some embodiments, the degree of fit is related to the distance between different functional areas and the flow rate of cargo between different functional areas.

[0095] In some embodiments, the present invention may calculate the cargo flow between each functional area before S1051 is executed, for example, after S104 is executed and before S1051 is executed. As an example, the cargo flow between each functional area in the cycle may be calculated together using the work flows and cargo volumes of different types of cargo in the order dataset within the set period, where different work flows correspond to the determined functional areas.

[0096] Refer to Table 9 for an example of cargo flow between each functional area. For example, the cargo flow from functional area 3 (number 3) to functional area 4 (number 4) is 25,417.

[0097] [Table 9]

[0098] In some embodiments, the present invention may calculate the fitness of each dual-coded chromosome in a single iteration process and select the fitness of one dual-coded chromosome as the fitness of that iteration process. For example, in the k-th iteration process, the fitness of each dual-coded chromosome in the k-th dual-coded chromosome population is calculated to obtain N fitnesss, and the maximum of the N fitnesss is taken as the maximum fitness of the k-th iteration process.

[0099] S1052: Determine whether the k-th iteration of the process satisfies a predetermined condition.

[0100] If the k-th iteration satisfies the pre-set conditions, proceed to S1053; otherwise, proceed to S1054.

[0101] Here, the pre-set conditions include at least one of the following: the current iteration count is greater than T (i.e., the maximum iteration count), the difference between the fitness of the current iteration process and the fitness of the previous adjacent S iteration processes is all less than or equal to a set threshold, and the fitness of the current iteration process is greater than or equal to a pre-set fitness. Here, S is a positive integer.

[0102] In some embodiments, the preset fitness score may be the maximum fitness score from the M iterations prior to the current iteration. For example, M is a positive integer greater than or equal to 1, i.e., the preset fitness score may be the fitness score obtained by performing the iterative process of the genetic algorithm at least once.

[0103] In some embodiments, the termination condition of the algorithm is one of the following three conditions. (1) The difference in the optimal chromosome fitness of consecutive S generations (e.g., S=3) is set to a threshold (i.e., an intergenerational difference threshold, e.g., 10) -6 It is smaller than ). (2) The current number of iterations is greater than T (i.e., the maximum number of iterations). (3) The current fit of the iterative process is equal to or better than the predetermined fit.

[0104] It should be understood that the optimal chromosome in a single iteration process refers to the bizygotic chromosome with the highest fitness among the bizygotic chromosome population in the iteration process. Furthermore, the fitness level of a bizygotic chromosome is used to evaluate the optimization effect of that bizygotic chromosome (i.e., the optimization effect of the position and aspect ratio of each functional area in the bizygotic chromosome), with a higher fitness level indicating a better corresponding optimization effect.

[0105] S1053: Determine the optimization result based on the population of individuals with the k-th dual-encoded chromosome.

[0106] S1054: Update the iteration count from k to k+1 and re-execute S1051.

[0107] In some embodiments, the dual-coded chromosomes among the k-th dual-coded chromosome population constructed in the k-th iteration process described above may be constructed randomly or based on the dual-coded chromosome population from the previous iteration process.

[0108] For example, corresponding to k being equal to 1, the k-th dual-coded chromosome population in the k-th iteration process is randomly constructed. That is, in the first iteration process, N dual-coded chromosomes are randomly constructed to obtain the first dual-coded chromosome population.

[0109] Corresponding to k being greater than 1, a reconstruction operation is performed on the bicoded chromosome in the bicoded chromosome population of the (k-1)th bicoded chromosome in the (k-1)th bicoded chromosome population of the k-

[0110] In some embodiments, the above reconstruction operation includes at least one of the following: selection, crossover, or mutation. Alternatively, the above selection, crossover, or mutation operation may be performed on a set of dual-encoded chromosomes at predetermined probabilities. The reconstruction operation will be described later and will not be detailed here.

[0111] Please understand that during the execution of the genetic algorithm, the evolution process of S1051 may be cyclically repeated until the algorithm terminates.

[0112] Thus, pre-set conditions limited by the number of iterations and the degree of fit can be used as criteria for determining the optimization goal, and it is possible to calculate better optimization results, i.e., the position and aspect ratio of each functional area with good optimization effect, within a reasonable time.

[0113] Referring to Figure 4, the procedure for reconstruction of a dual-coded chromosome population is shown, using the example of constructing a k-th dual-coded chromosome population based on the k-th dual-coded chromosome population.

[0114] S401: Select a pair of L1 dual-coded chromosomes with a relatively high degree of fit from the k-1 dual-coded chromosome population, and select a pair of L2 dual-coded chromosomes with first probability from the remaining N-L1 pairs of dual-coded chromosomes in the k-1 dual-coded chromosome population. Based on the L1 pair and the L2 pair, construct the k dual-coded chromosome population.

[0115] However, L2 is less than or equal to L1, and both L1 and L2 are less than N. In this case, the (k-1)th iteration process does not satisfy the pre-set conditions.

[0116] In some embodiments, if L1+L2 is less than N, several pairs of dual-coded chromosomes may be randomly generated and these dual-coded chromosomes may be added to the k-th dual-coded chromosome population such that the number of pairs of dual-coded chromosomes in the k-th dual-coded chromosome population is N.

[0117] In other words, the population of the k-1-th dual-coded chromosome retains superior L1 pairs of dual-coded chromosomes at a certain configurable ratio (this ratio is L1 / N, e.g., 0.4), and these superior chromosomes can be carried over to the next generation. For the remaining chromosomes, a chromosome is randomly selected based on a configurable first probability β (e.g., 0.5) to enter the next generation. If the number of dual-coded chromosomes is less than N, dual-coded chromosomes are randomly generated until the population size reaches N.

[0118] S402: A crossover operation is performed on the k-th double-coded chromosome in the population of individuals with the k-th double-coded chromosome, with a probability of 2, to obtain the population of individuals with the k-th double-coded chromosome after the crossover operation.

[0119] The crossover operation is performed between two pairs of dual-encoded chromosomes. Furthermore, the crossover operation includes crossover of the functional area numbers in the two first chromosomes, and / or crossover of the aspect ratio of the functional areas in the two second chromosomes. However, a second probability γ is applied to each pair of dual-encoded chromosomes. cPerform the crossover operation with (for example, 0.4).

[0120] In some embodiments, a two-point crossover operation may be employed for the functional area numbers, i.e., the crossover position may be randomly selected to exchange the functional area numbers between the two first chromosomes. For example, the positions of the first and second functional area numbers of two sets of dual-encoded chromosomes may be swapped. That is, the first and second functional area numbers of the first chromosome of one set of dual-encoded chromosomes are swapped with the second and first functional area numbers of the first chromosome of the other set of dual-encoded chromosomes, respectively, to obtain two sets of dual-encoded chromosomes after the crossover operation.

[0121] Referring to Figure 5A, a process diagram of the crossover operation of dual-coded chromosomes is shown. The crossover operation will be explained using the example of two first chromosomes from two sets of dual-coded chromosomes, namely paternal chromosome p1 and paternal chromosome p2, as shown in Figure 5. As shown in Figure 5A, the positions of functional area 8 (e.g., the first functional area) number 8 and functional area 2 (e.g., the second functional area) number 2 in paternal chromosome p1 are swapped with the positions of functional area 2 number 2 and functional area 8 number 8 in paternal chromosome p2, respectively, to obtain the offspring chromosomes c1 and c2 after the crossover operation.

[0122] In some embodiments, as a crossover operation on the aspect ratio of the functional area, the aspect ratios of the same segments (i.e., the same position) in the two second chromosomes may be randomly selected and the aspect ratios within the segments may be linearly manipulated. For example, the aspect ratio q1 of the functional area corresponding to the first index of the second chromosome in one set of dual-coded chromosomes and the aspect ratio q2 of the functional area corresponding to the first index of the second chromosome in the other set of dual-coded chromosomes may be linearly processed such that aspect ratio q1 is adjusted to d1 after the crossover operation and aspect ratio q2 is adjusted to d2 after the crossover operation. For example, the first index is the index with a value of 3, that is, the aspect ratio of the functional area corresponding to the first index is the aspect ratio of the functional area with insertion order 4.

[0123] For example, the above linear operation may also be calculated using the following equations (1) and (2), where α is a coefficient less than 1, for example, α = 0.4.

[0124] d1 = α·q1 + (1-α)·q2 (1) d2 = (1 - α)·q1 + α·q2 (2) S403: A mutation operation is performed on the k-th dual-coded chromosome in the population of individuals with the k-th dual-coded chromosome after crossover, with a probability of 3, to obtain a population of individuals with the k-th dual-coded chromosome after mutation.

[0125] The mutation operation is performed on one pair of dual-encoded chromosomes. Furthermore, the mutation operation includes mutations on the number of the functional area on the first chromosome and / or mutations on the aspect ratio of the functional area on the second chromosome. However, a third probability γ is applied to each pair of dual-encoded chromosomes. m Perform the crossover operation with (for example, 0.6).

[0126] In some embodiments, the mutation operation on the functional area numbers may involve randomly selecting two points for exchange. For example, the positions of the functional area numbers of one functional area and the other functional area in a pair of dual-coded chromosomes may be swapped. That is, the positions of the functional area numbers of one functional area and the other functional area in the first chromosome of a pair of dual-coded chromosomes are swapped to obtain the mutated dual-coded chromosome.

[0127] Referring to Figure 5B, a process diagram of the mutation operation of a dual-coding chromosome is shown. As shown in Figure 5B, the position of number 8 in functional area 8 and number 2 in functional area 2 of the paternal chromosome are swapped to obtain the mutated offspring chromosome.

[0128] In some embodiments, the mutation operation on the aspect ratio of a functional area may involve randomly selecting a point and randomly regenerating the data for that point within a range of aspect ratio values ​​(0.2, 5.0). For example, the aspect ratio value of one functional area in a pair of bicoded chromosomes may be randomly replaced with another value. For instance, the aspect ratio q3 of the functional area corresponding to the second index of the second chromosome in a pair of bicoded chromosomes is adjusted to d4 (e.g., q3 is equal to 0.9 and q4 is equal to 1.3) to obtain the second chromosome after the mutation operation. For example, the second index is the index with a value of 4, meaning the aspect ratio of the functional area corresponding to the second index is the aspect ratio of the functional area with insertion order 5.

[0129] During the execution of the genetic algorithm, the population evolution process in S401-S403 may be repeated cyclically until the pre-set conditions are met.

[0130] S404: Based on the k-th dual-coded chromosome population after mutation, the k-th dual-coded chromosome population of the k-th iteration process is obtained.

[0131] For example, the population of individuals with the kth double-coded chromosome after mutation may be directly used as the population of individuals with the kth double-coded chromosome in the kth iteration process.

[0132] In this way, by utilizing the evolutionary process of chromosomal double coding, the problem of large vertical gaps in functional areas can be solved, and the insertion order and variable length and width of functional areas can be optimized and adjusted to reduce the vertical gaps in functional areas.

[0133] In other embodiments, the mutation process of the genetic algorithm of the present invention may be improved using an annealing algorithm. Referring to Figure 6, the flow of performing the annealing algorithm on the dual-encoded chromosome population after the reconstruction operation is shown. Specifically, S404 shown in Figure 4 may include S4041 to S4043.

[0134] S4041: For each pair of double-encoded chromosomes in the k-th double-encoded chromosome population after the mutation operation, calculate the acceptance probability of the double-encoded chromosome.

[0135] S4042: When the acceptance probability of the double-encoded chromosome is the first value, set this double-encoded chromosome as one of the double-encoded chromosomes in the k-th iteration process.

[0136] S4043: When the acceptance probability of the double-encoded chromosome is less than the first value, roll back the double-encoded chromosome after the mutation operation and set it as the double-encoded chromosome in the k-th iteration process.

[0137] In this way, based on some double-encoded chromosomes after the mutation operation and the double-encoded chromosomes with the mutation operation rolled back, the k-th double-encoded chromosome population in the k-th iteration process can be obtained.

[0138] In some embodiments, the acceptance probability of the above double-encoded chromosome is calculated by the following formulas (3) to (5).

[0139]

Number

[0140]

Number

[0141]

Number

[0142] However, in formula (3), corresponding to Fmax(c,k) ≧ MaxF, when the acceptance probability takes the value 1, the above first numerical value is 1. Corresponding to ρFmax(c,k) < MaxFρ, the value of the acceptance probability is usually smaller than the first value, for example, smaller than 1.

[0143] Specifically, T0 represents the initial annealing temperature, and the value of T0 is calculated according to equation (4) above. tmax represents the maximum fitness of each bicoded chromosome in the first bicoded chromosome population of the first iteration process, tmin represents the minimum fitness of each bicoded chromosome in the first bicoded chromosome population of the first iteration process, Fmax(c,k) represents the fitness of the c-th set of bicoded chromosomes in the k-th bicoded chromosome population of the k-th iteration process, where c is a positive integer less than or equal to N, and MaxF is the maximum fitness of each iteration process (e.g., the fitness of the k-1th iteration process).

[0144] Then, as the number of iterations increases from k to k+1, T k T is calculated according to equation (5) above. k+1 Then, MaxF is updated to Fmax(c, k).

[0145] It should be understood that the acceptance probability of a bicoded chromosome correlates with tmax, tmin, Fmax(c,k), and MaxF, and that the acceptance probability decreases as the number of repeats increases.

[0146] Thus, the genetic algorithm of the present invention may set a certain acceptance probability for offspring individuals generated after mutation, according to the annealing algorithm. If the acceptance probability of a dual-coded chromosome is relatively high, it is accepted; otherwise, it is not accepted. Therefore, the genetic algorithm of the present invention can dynamically adjust the dual-coded chromosomes in the population, utilize the optimal solution obtained through mutation, and search for a better solution in a global range near that optimal solution. That is, if the offspring individual is better, the acceptance probability of accepting that individual is set to 100% (i.e., 1), and if the offspring individual is not better, the acceptance probability of accepting that offspring individual gradually decreases. This feature combines the search speed of the genetic algorithm with the global searchability of the annealing algorithm, allowing searches to be performed in a way that obtains a better layout plan within a certain time.

[0147] This invention is based on an annealing algorithm. It should be understood that, in the evolutionary process of the genetic algorithm, at the start of the genetic algorithm, mutated chromosomes are accepted with a high probability, and as the genetic algorithm evolves to later stages and the fitness of the iteration process does not change much, mutated chromosomes are accepted with a low probability, reducing disturbances caused by mutations and avoiding impact on chromosomal properties.

[0148] Next, the process for calculating the degree of fit in this invention will be explained.

[0149] Figure 7 shows the process for calculating the goodness of fit of a bicoded chromosome.

[0150] S701: The dual-coded chromosome is decoded, and the decoded dual-coded chromosome is solved using a two-dimensional bin packing algorithm to obtain the insertion coordinates of each functional area in the warehouse and the first total area of ​​multiple functional areas.

[0151] In some embodiments, the first total area is the area of ​​the minimum enclosing rectangle of multiple functional areas.

[0152] It should be understood that decoding a dual-coded chromosome yields the insertion order and aspect ratio of each functional area within that chromosome.

[0153] S702: Calculates the distance between different functional areas based on the insertion coordinates of each functional area.

[0154] In some embodiments, the distance between different functional areas may be the Manhattan distance, the non-penetrating shortest path distance, the distance between the boundary points of different functional areas, or the distance between the center points of different functional areas. It should be understood that based on the insertion point and size of a functional area, positional points such as the center point and boundary points of that functional area can be determined, and based on these positional points, the distance between different functional areas can be calculated.

[0155] S703: Calculate the fitness of the double-encoded chromosome based on the cargo flow rate between different functional areas, the distance between different functional areas, and the first total area.

[0156] In some embodiments, for one double-encoded chromosome, first, the cargo flow rate between different functional areas, the distance between different functional areas, and the first total area of the plurality of functional areas may be calculated. Next, calculate the fitness of the double-encoded chromosome based on the cargo flow rate between different functional areas, the distance between different functional areas, and the first total area of the plurality of functional areas.

[0157] As an example, the fitness of the double-encoded chromosome may be calculated according to the following formula (6).

[0158]

Number

[0159] Here, Fitness is the fitness, r i,j represents the cargo flow rate from the i-th functional area to the j-th functional area, d i,j represents the distance between the i-th functional area and the j-th functional area, S represents the first total area, w1 and w2 are weighting factors, n is the number of the plurality of functional areas, and both i and j are positive integers not exceeding n. For example, r 3,4 is the cargo flow rate from the third functional area (i.e., functional area 3 with number 3) to the fourth functional area (i.e., functional area 4 with number 4). As can be seen from Table 9, r i,j = 25417.

[0160] The present invention uses the objective function of the optimization process of the double-encoded chromosome as

[0161]

Number

[0162] It should be understood that you can set the parameters as follows, calculate the objective function, and then use the reciprocal of that objective function as the degree of fit.

[0163] In some embodiments, w1 and w2 in equation (6) are different weighting coefficients, and w1 + w2 = 1w1w2. For example, the values ​​of w1 and w2 may both be 0.5, but the specific values ​​are not limited to this.

[0164] In other embodiments, w1 in equation (6) is the transport cost per unit distance of cargo (e.g., the economic cost of transporting one box of cargo per meter), and w2 is the cost per unit warehouse area (e.g., the economic cost of rental and management). It should be understood that the fitness of a dual-coded chromosome is related not only to the flow rate and distance of cargo between different functional areas, but also to the transport cost per unit distance of cargo and the cost per warehouse area. Thus, the fitness calculated using transport distance cost and warehouse area cost may be used as a criterion for determining the overall optimization goal of the dual-coded chromosome.

[0165] Thus, the present invention can determine the fit of a dual-encoded chromosome by comprehensively considering the flow rate and distance of goods between different functional areas, as well as the cost of transporting goods per unit distance and the cost per unit warehouse area. This is advantageous in optimizing the location and aspect ratio of each functional area by comprehensively considering the impact of these factors on the warehouse layout, thereby improving the optimization effect of the warehouse layout.

[0166] In some embodiments, the decryption flow for a dual-coded chromosome may include inserting the corresponding rectangle of each functional area into the global plane from a set origin along a first direction of the first coordinate axis and a second direction of the second coordinate axis, based on the insertion order and aspect ratio of each functional area in the dual-coded chromosome, as well as the corresponding first region, and obtaining the insertion coordinates of each functional area. Here, the size of the functional area includes the first directional length in the first direction and the second directional length in the second direction of the corresponding rectangle of the functional area, the insertion coordinates of the functional area include the first directional coordinate value on the first coordinate axis and the second directional coordinate value on the second coordinate axis, the value obtained by adding the first directional length of the functional area to the first directional coordinate value of the functional area is less than or equal to the first total length threshold (denoted as maxL), the first total length threshold is equal to the square root of the area of ​​the global domain plane, and the area of ​​the global domain plane (denoted as S1) is a predetermined multiple (e.g., denoted as 1.25) of the sum of the corresponding first areas of each functional area (denoted as S0). In this case, S1 = S0 * 1.25 and maxL = sprt(S1) = √S1. For example, assuming S0 = 288 square meters, S1 = 360 square meters and maxL = 60 meters.

[0167] It should be understood that this invention, when combined with a two-dimensional bin packing algorithm for chromosomal dual coding, can seamlessly puzzle each functional area in the first direction (e.g., horizontal direction) and the gaps between each functional area in the second direction (e.g., vertical direction) can be evolutionarily optimized by a chromosomal genetic algorithm, thereby minimizing the warehouse area.

[0168] As an example, Figure 8A shows a schematic diagram of the insertion of a functional area into the global planar area of ​​a warehouse. As shown in Figure 8A, the origin is the lower left corner a1(0,0) of the global planar area, the first coordinate axis is a horizontal coordinate axis (e.g., x-axis) like the coordinate axis in the length direction of the global planar area, and the second coordinate axis is a vertical axis (e.g., y-axis) like the coordinate axis in the width direction of the global planar area. Furthermore, the first direction is the positive direction of the first coordinate axis, for example, the direction from left to right along the horizontal direction, and the second direction is the positive direction of the second coordinate axis, for example, the direction from bottom to top along the vertical direction, the first directional coordinate is the horizontal coordinate, and the second direction is the vertical coordinate. Correspondingly, the first directional length of the functional area may be the length in the horizontal direction, and the second directional length may be the height in the vertical direction, for example, the first directional length of functional area 1 in Figure 8A is L1 and the second directional length is h1. Specifically, the rectangles of each functional area, whose size has been determined, and their insertion order are taken as input. The lower left corner of the global domain plane is set as the origin (0,0), and the vertical and horizontal coordinates are increased upwards and to the right, respectively, to insert each functional area into the global domain plane. For example, as shown in Figures 8A to 8D, functional areas 2-4 may be inserted sequentially into the global domain plane, and similarly, the remaining functional areas out of N may be inserted sequentially.

[0169] Furthermore, in other embodiments, the first coordinate axis, the second coordinate axis, and the first and second directions of the present invention are not limited to the examples in Figures 8A to 8D, and may be other embodiments in which the first coordinate axis is a vertical coordinate axis and the second coordinate axis is a horizontal coordinate axis.

[0170] Referring to Figure 9, a schematic diagram of the flow for inserting a functional area using a two-dimensional bin packing algorithm is shown, and the flow includes the following steps.

[0171] S901: Determine the rectangles of N functional areas based on the first area and aspect ratio of each functional area, determine the insertion order of each functional area, set the lower left corner of the global region plane as the origin (0,0), initialize the insertable points as the origin, and initialize the first direction total length threshold maxL and the second direction length maximum value maxH of the rectangle.

[0172] The maximum value of the second direction length of the rectangle, maxH, may also be the maximum value of the length along the longitudinal direction of the rectangle; for example, it should be understood that maxH can be initialized to 0.

[0173] Furthermore, maxL may be set according to the area S1 of the global region plane; for example, maxL may be initialized to 60m.

[0174] S902: Corresponding to a functional area with insertion order 1, the current rectangle is inserted into the insertable point with the lower left corner of the rectangle as the insertion point, the first directional coordinate value of the insertable point is updated to the first directional length of the rectangle, and the maximum value maxH of the second directional length of the rectangle is updated to the second directional length of the current rectangle.

[0175] For example, as shown in Figure 8A, if the current rectangle is the rectangle of functional area 1 in insertion order 1, the current insertable point is point a1(0,0), and the insertion point of the current rectangle is point b1. As shown in Figure 8B, the insertion point b1 of functional area 1 may be inserted into the insertable point a1, and the current rectangle may be inserted. In this case, the insertion coordinates of functional area 1 will be the coordinates (0,0) of insertion point b1. After inserting functional area 1, the first directional coordinate value of the insertable point may be updated to l1, updating the insertable point to point a2(l1,0), and the maximum value maxH of the second directional length of the rectangle may be updated to the second directional length h1 of the current rectangle.

[0176] S903: For functional areas with an insertion order greater than 1, determine whether the sum of the first directional length of the current rectangle and the first directional coordinate value of the insertable point is greater than the first total length threshold maxL.

[0177] If the sum of the current rectangle's first directional length and the insertion point's first directional coordinate value is greater than the first total length threshold, proceed to S904. If the sum of the current rectangle's first directional length and the insertion point's first directional coordinate value is less than or equal to the first total length threshold, proceed directly to S905.

[0178] S904: The first directional coordinate value of the insertable point is set to 0, the second directional coordinate value of the insertable point is added to the second directional maximum value of the rectangle to update the insertable point, and the second directional maximum value of the rectangle is updated to 0.

[0179] S905: Insert the current rectangle into the updated insertable point using the lower left corner of the rectangle as the insertion point. Update the insertable point by adding the first directional coordinate value of the insertable point to the first directional length of the current rectangle. Update the maximum value of the second directional length of the rectangle to the second directional length of the current rectangle.

[0180] As an example, as shown in Figure 8B, if the current rectangle is the rectangle of functional area 2 with insertion order 2, the current insertable point is point a2(l1,0) and the insertion point of the current rectangle is point b2. If the sum of the first directional length l2 of the current rectangle and the first directional coordinate value l1 of the current insertable point is less than or equal to the first total length threshold maxL (e.g., 60m), as shown in Figure 8C, the insertion point b2 of functional area 2 may be inserted into the insertable point a2 in order to insert the current rectangle. In this case, the insertion coordinate of functional area 2 is the coordinate of insertion point b2 (l1,0). After inserting functional area 2, the first directional coordinate value of the insertable point is updated to L1+L2, updating the insertable point to point a3(l1+l2,0), and the maximum value of the second directional length maxH of the rectangle is updated. For example, the maximum value of the second directional lengths h2 and h1 of the current rectangle may be set to the updated maximum value of the second directional length maxH of the rectangle, for example, h2.

[0181] For example, as shown in Figure 8C, if the current rectangle is the rectangle of functional area 3 with insertion order 3, the current insertable point is point a3(l1+l2,0) and the insertion point of the current rectangle is point b3. If the sum of the first directional length l3 of the current rectangle and the first directional coordinate value l1+l2 of the current insertable point > the first total length threshold maxL (e.g., 60m), then as shown in Figure 8D, the insertable point a3 may first be updated to insertable point a3'(0,h2), and the maximum value maxH of the second directional length of the rectangle may be updated to 0. Furthermore, the insertion point b3 of functional area 3 is inserted into the insertable point a3' to insert the current rectangle. At this time, the insertion coordinates of functional area 3 are the coordinates of insertion point b3 (l3,h2). Then, after inserting the functional area 3, the first directional coordinate value of the insertable point may be updated to l3, updating the insertable point to point a4(l3,h2), and the maximum value maxH of the second directional length of the rectangle may be updated to the current second directional length h3 of the rectangle.

[0182] S906: Determines whether all N function area rectangles have been inserted.

[0183] If all n functional area rectangles have been inserted, S907 is executed; otherwise, S903 is continued. This sequentially inserts the functional area rectangles of each insertion order into the global area plane. Similarly, referring to the rectangle insertion process for functional areas 1 to 3 shown in Figures 8A to 8D, the other functional areas among the n functional areas can be inserted into the global area plane in the manner described above to realize the layout of the functional areas in the warehouse.

[0184] S907: The coordinates of the insertion point of each functional area are used as the insertion coordinates, and the area of ​​the minimum surrounding rectangle of all functional areas is calculated and used as the first total area.

[0185] In this way, a seamless puzzle of rectangles for each functional area can be realized in the first direction of the global domain plane, for example, the horizontal direction. It should be understood that the operation of the genetic algorithm utilizes the evolutionary process of chromosomal double coding to solve the problem of large vertical gaps during the insertion of functional areas into the global domain plane, optimizing the insertion order of functional areas and their variable length and width to reduce the vertical gaps between functional areas.

[0186] Next, the hardware configuration of the electronic device according to an embodiment of the present invention will be described.

[0187] Figure 10 shows the hardware configuration of an electronic device.

[0188] Referring now to Figure 10, a block diagram of an electronic device 800 according to one embodiment of the present invention is shown. This electronic device 800 may be applied to devices such as terminal devices and cloud servers. Figure 10 schematically shows exemplary electronic devices 800 according to various embodiments. In one embodiment, the electronic device 800 may include one or more processors 804, an electronic device control logic 808 connected to at least one of the processors 804, an electronic device memory 812 connected to the electronic device control logic 808, a non-volatile memory (NVM) 816 connected to the electronic device control logic 808, and a network interface 820 connected to the electronic device control logic 808.

[0189] In some embodiments, the processor 804 may include one or more single-core or multi-core processors. In some embodiments, the processor 804 may include any combination of general-purpose processors and dedicated processors (e.g., graphics processors, application processors, baseband processors, etc.). In embodiments in which the electronic equipment 800 uses an evolved node B (eNB) 101 or a radio access network (RAN) controller 102, the processor 804 may be configured to perform various adapted embodiments, such as the embodiments shown in Figures 1-4 and Figures 6, 7, and 9.

[0190] In some embodiments, the electronic control logic 808 may include any suitable interface controller to provide any suitable interface to at least one of the processors 804 and / or any suitable device or component communicating with the electronic control logic 808.

[0191] In some embodiments, the electronic control logic 808 may include one or more memory controllers to provide an interface connected to the electronic memory 812. The electronic memory 812 may be used to load and store data and / or instructions. In some embodiments, the memory 812 of the electronic device 800 may include any suitable volatile memory, such as a suitable dynamic random access memory (DRAM).

[0192] The network interface 820 provides a wireless interface to the electronic device 800 and may further include transceivers for communicating with any other suitable devices (e.g., front-end modules, antennas, etc.) via one or more networks. In some embodiments, the network interface 820 may be integrated with other components of the electronic device 800. For example, the network interface 820 may be integrated with at least one of the following in the processor 804: electronic device memory 812, NVM / memory 816, and a firmware device (not shown) having instructions. When at least one in the processor 804 executes the instructions, the electronic device 800 implements the method shown in Figure 3.

[0193] The network interface 820 may further include any suitable hardware and / or firmware to provide a multi-input, multi-output wireless interface. For example, the network interface 820 may be a network adapter, a wireless network adapter, a telephone modem, and / or a wireless modem.

[0194] In one embodiment, at least one of the processors 804 may be packaged together with the logic of one or more controllers of the electronic control logic 808 to form an electronic device package (SiP). In one embodiment, at least one of the processors 804 may be integrated on the same die as the logic of one or more controllers of the electronic control logic 808 to form a system on a chip (SoC).

[0195] The electronic device 800 may further include an input / output (I / O) device 832. The I / O device 832 may include a user interface that enables interaction between the user and the electronic device 800. The design of the peripheral component interface also enables interaction between peripheral components and the electronic device 800. In some embodiments, the electronic device 800 further includes a sensor for determining at least one of environmental conditions and location information related to the electronic device 800.

[0196] In some embodiments, the user interface may include, but is not limited to, a display (e.g., a liquid crystal display, a touchscreen display), a speaker, a microphone, one or more cameras (e.g., a still image camera and / or a video camera), a flashlight (e.g., a light-emitting diode flash), and a keyboard.

[0197] In some embodiments, the peripheral component interface may include, but is not limited to, a non-volatile memory port, an audio jack, and a power interface.

[0198] In one possible embodiment, a readable medium is provided on which instructions are stored that cause the electronic device to execute the above-described warehouse layout method when executed on the electronic device.

[0199] In one possible embodiment, a computer program product is provided that, when executed on an electronic device, causes the above warehouse layout method to be implemented on the electronic device.

[0200] Embodiments of the mechanisms disclosed herein may be implemented in hardware, software, firmware, or a combination thereof. Embodiments of the present invention may be implemented as computer programs or program code that run on a programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0201] The functions described herein may be performed and output information generated by applying program code to the input of instructions. The output information may be applied to one or more output devices in known ways. For the purposes of the present invention, the processing system includes any system having a processor such as a digital signal processor (DSP), a microcontroller, an application-specific integrated circuit (ASIC), or a microprocessor.

[0202] The program code may be implemented in a high-level programming language or an object-oriented programming language to communicate with the processing system. If necessary, the program code may also be implemented in assembly language or machine code. In fact, the mechanisms described herein are not limited to any particular programming language. In any case, the language may be a compiled language or an interpreted language.

[0203] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be delivered over a network or over other computer-readable media. Therefore, machine-readable media can be applied to any mechanism for storing or transmitting electronic instructions or information in a machine (e.g., computer)-readable format, and include, but are not limited to, floppy disks, optical disks, floppies, read-only memory (CD-ROMs), magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic or optical cards, flash memory, or tangible machine-readable memory that transmits information using the internet via electrical, optical, acoustic or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.). Therefore, machine-readable media includes any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a machine (e.g., computer)-readable format.

[0204] In drawings, certain structural or methodological features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not always be necessary. Rather, in some embodiments, these features may be arranged in a different manner and / or order than those shown in the exemplary drawings. Furthermore, the inclusion of structural or methodological features in a particular drawing does not mean that such features are necessary in all embodiments, and in some embodiments, these features may be omitted or combined with other features.

[0205] Furthermore, all units / modules mentioned in the embodiments of the apparatus of the present invention are logical units / modules. Physically, a logical unit / module may be a single physical unit / module, part of a single physical unit / module, or realized by a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not of paramount importance; rather, the combination of functions realized by these logical units / modules is key to solving the technical problems pointed out herein. Moreover, in order to emphasize the innovative aspects of the present invention, each embodiment of the apparatus described herein does not introduce units / modules that are not closely related to solving the technical problems pointed out herein. This does not mean that other units / modules do not exist in the embodiments of the apparatus.

[0206] In the examples and specification of the present invention, relational terms such as "first" and "second" are used solely to distinguish one entity or action from another, and should be noted that they do not necessarily require or suggest that such an actual relationship or order exists between these entities or actions. Furthermore, the terms "composes," "includes," or any other variation thereof are intended to include non-exclusive inclusion, so that a process, method, article, or apparatus containing a set of elements includes not only those elements but also other elements not explicitly listed, or elements specific to such a process, method, article, or apparatus. Unless further limited, an element defined by the term "includes one" does not preclude the presence of other identical elements in a process, method, article, or apparatus containing that element.

[0207] While the present invention has been illustrated and described with reference to several preferred embodiments, those skilled in the art will understand that various modifications can be made formally and in detail without departing from the spirit and scope of the invention. [Explanation of Symbols]

[0208] 800:Electronic equipment 804: Processor 808: Electronic Equipment Control Logic 812: Memory 816: Memory 820: Network Interface 832: I / O Devices

Claims

1. Warehouse layout method, Steps to obtain order datasets within a specified period, The steps include determining multiple functional areas within the warehouse based on the aforementioned order dataset, A step of determining the first area of ​​each functional area based on the order dataset, The position of each of the aforementioned functional areas is the first target for optimization, and the aspect ratio of each of the aforementioned functional areas is the second target for optimization. A warehouse layout method characterized by comprising the steps of: performing a dual encoding process on the first optimization target and the second optimization target using a genetic algorithm based on the first area of ​​each of the functional areas, and decoding the encoded first optimization target and the second optimization target to determine an optimization result that satisfies preset conditions, wherein the optimization result includes the target position of each of the functional areas and the target aspect ratio of each of the functional areas.

2. The order data in the aforementioned order dataset includes at least one of the following data: order number, order date, order time, cargo type, cargo quantity, processing flow, container specifications, and work type. The work type includes at least one of outbound work, inbound work, and inbound work, each work type corresponds to a plurality of work flows, and each work flow corresponds to one of the functional areas. The warehouse layout method according to claim 1, characterized in that the processing flow includes at least one work flow corresponding to one of the work types.

3. The step of determining multiple functional areas within the warehouse based on the aforementioned order dataset is: The step includes determining the plurality of functional areas of the warehouse based on the work flow corresponding to outbound operations, inbound operations and in-warehouse operations in the order dataset, The warehouse layout method according to claim 2, characterized in that the plurality of functional areas include at least one of the following: unloading area, receiving temporary storage area, pallet dismantling work area, quality inspection work area, packaging work area, shipping temporary storage area, pallet stacking / stacking work area, loading area, storage area, sorting area, equipment storage area, defective goods / returns area, and office area.

4. The step of determining the first area of ​​each functional area based on the aforementioned order dataset is: Based on the order dataset, the step of determining the maximum positive difference of the positive difference between the amount of goods received and the amount of goods shipped to the warehouse within the set period, The steps include determining the maximum area of ​​each functional area according to the maximum positive difference, The warehouse layout method according to claim 1, comprising the step of determining a corresponding first area based on the maximum area of ​​each of the functional areas, wherein the first area of ​​each of the functional areas is less than or equal to the corresponding maximum area.

5. The step of determining the corresponding first area based on the maximum area of ​​each of the aforementioned functional areas is: The warehouse layout method according to claim 4, characterized in that it includes the step of setting the maximum area of ​​each of the functional areas to the corresponding first area.

6. The step of determining the corresponding first area based on the maximum area of ​​each of the aforementioned functional areas is: A step of determining the second area of ​​each of the aforementioned functional areas, wherein the second area is a predetermined area or an area calculated based on the work processing capacity per unit area of ​​the aforementioned functional area, If the second area of ​​the functional area is smaller than the corresponding maximum area, the step is to set the second area to the first area of ​​the functional area. The warehouse layout method according to claim 4, further comprising the step of setting the maximum area of ​​the functional area to the first area of ​​the functional area if the second area of ​​the functional area is equal to or greater than the corresponding maximum area.

7. Based on the aforementioned order dataset, the step of determining the maximum positive difference of the positive difference between the amount of goods received and the amount of goods shipped to the warehouse during the specified period is: The steps include dividing the order dataset into multiple sub-order datasets in a rolling manner according to the delay processing cycle of warehouse cargo, The steps include: calculating the positive difference between the amount of goods received and the amount of goods sent out in each sub-order dataset, and obtaining multiple positive differences in the amount of goods received; The warehouse layout method according to claim 4, characterized by including the step of setting the maximum value of the positive difference among the plurality of cargo quantities to the maximum positive difference within the set period.

8. The step of performing dual encoding on the first and second optimization targets using a genetic algorithm is: A step of encoding the first optimization target and determining the encoded first optimization target as a first chromosome, wherein the first chromosome includes the number of each of the functional areas, and the position of the functional area in the warehouse corresponds to the insertion order of the functional area numbers in the first chromosome. The steps include encoding the second optimization target and determining the encoded second optimization target as a second chromosome, wherein the second chromosome includes the aspect ratio of each of the functional areas, the aspect ratio is within a predetermined ratio range, and the size of the functional area corresponds to the first area of ​​the functional area and the aspect ratio in the second chromosome, The warehouse layout method according to claim 1, characterized in that the first chromosome and the second chromosome constitute a pair of double-encoded chromosomes.

9. The step of decoding the encoded first and second optimization targets and determining an optimization result that satisfies the pre-set conditions is: A step of constructing a population of the kth dual-coded chromosome in the k-th iteration process, corresponding to the number of iterations being equal to k, and performing a solution on the kth dual-coded chromosome population to obtain the fitness of the k-th iteration process, wherein k is a positive integer less than or equal to T, the population of dual-coded chromosomes includes N sets of dual-coded chromosomes, and the fitness relates to the distance between different functional areas and the flow rate of cargo between different functional areas. If the k-th iteration process satisfies the predetermined conditions, the optimization result is determined based on the k-th dual-encoded chromosome population. If the k-th iteration process does not satisfy the predetermined conditions, the process includes updating the number of iterations from k to k+1 until the k-th iteration process satisfies the predetermined conditions, re-executing the construction of the k-th dual-coded chromosome population in the k-th iteration process, and solving for the k-th dual-coded chromosome population to obtain the fitness of the k-th iteration process, The warehouse layout method according to claim 8, wherein the aforementioned preset conditions include at least one of the following: the current number of iterations is greater than T; the difference between the fitness of the current iteration process and the fitness of each iteration process in the previous adjacent S iteration processes is all less than or equal to a set threshold; and the fitness of the current iteration process is greater than or equal to a preset fitness, where S is a positive integer.

10. The step of solving for the k-th dual-encoded chromosome population and obtaining the degree of fit of the k-th iteration process is: The steps include calculating the fitness of each dual-encoded chromosome in N sets of dual-encoded chromosomes in the k-th dual-encoded chromosome population and obtaining N fitness values, The warehouse layout method according to claim 9, characterized by comprising the step of setting the maximum value among the N fitness scores as the fitness score of the k-th iteration process.

11. The calculation flow for the goodness of fit of the aforementioned dual-coded chromosome is as follows: A step of decoding the dual-coded chromosome, solving the decoded dual-coded chromosome using a two-dimensional bin packing algorithm to obtain the insertion coordinates of each of the functional areas in the warehouse and the first total area of ​​the plurality of functional areas, wherein the first total area is the area of ​​the minimum enclosing rectangle of the plurality of functional areas, A step of calculating the distance between different functional areas based on the insertion coordinates of each functional area, The warehouse layout method according to claim 10, comprising the step of calculating the fitness of the dual-coded chromosome based on the flow rate of goods between different functional areas, the distance between different functional areas, and the first total area.

12. The warehouse layout method according to claim 11, characterized in that the distance between different functional areas is the Manhattan distance, the shortest non-penetrating path distance, the distance between the boundary points of the different functional areas, or the distance between the center points of the different functional areas.

13. The calculation flow for the insertion coordinates of the aforementioned functional area is as follows: The warehouse layout method according to claim 11, comprising the step of determining the insertion coordinates of each functional area by inserting rectangles corresponding to each functional area into a global plane along a first direction of a first coordinate axis and a second direction of a second coordinate axis, from a set origin, based on the insertion order, aspect ratio, and corresponding first area of ​​each functional area in the dual coding chromosome, wherein the size of the functional area includes the first directional length in the first direction and the second directional length in the second direction of the rectangle corresponding to the functional area, the insertion coordinates of the functional area include the first directional coordinate value in the first coordinate axis and the second directional coordinate value in the second coordinate axis, the value obtained by adding the first directional length of the functional area to the first directional coordinate value of the functional area is less than or equal to a first total length threshold, the first total length threshold is equal to the square root of the area of ​​the global plane, and the area of ​​the global plane is a preset multiple of the sum of the first areas corresponding to each of the functional areas.

14. The step of constructing the k-th dual-encoded chromosome population in the k-th iteration process described above is: Corresponding to the case where k is equal to 1, the k-th iteration process involves randomly constructing the k-th dual-coded chromosome population, The warehouse layout method according to claim 9, characterized in that, in correspondence with k > 1, a reconfiguration operation is performed on the dual-coded chromosomes among the k-1-th dual-coded chromosome population of the k-1-th iteration process to obtain the k-th dual-coded chromosome population of the k-th iteration process, wherein the reconfiguration operation includes at least one of a selection operation, a crossover operation, and a mutation operation.

15. Crossover operations on the numbers of the functional areas in different dual-encoded chromosomes are performed as follows: The process includes the step of exchanging the positions of the first and second functional area numbers on the first chromosome of one set of the dual-coded chromosomes with the second and first functional area numbers on the first chromosome of another set of the dual-coded chromosomes, thereby obtaining two sets of dual-coded chromosomes after the crossover operation. Crossover operations on the aspect ratio of the functional area in different dual-encoded chromosomes are performed The process includes the step of linearly processing the aspect ratio q1 of the functional area corresponding to the first index on the second chromosome of one pair of dual-coding chromosomes and the aspect ratio q2 of the functional area corresponding to the first index on the second chromosome of the other pair of dual-coding chromosomes such that the aspect ratio q1 is adjusted to d1 after crossover and the aspect ratio q2 is adjusted to d2 after crossover, The warehouse layout method according to claim 14, characterized in that, here, d1 = α・q1 + (1-α)・q2, d2 = (1-α)・q1 + α・q2, and α is a coefficient less than 1.

16. Mutation operations on the number of the functional area in different dual-encoded chromosomes are, The process includes the step of swapping the positions of the third functional area number and the fourth functional area number in one dual-coding chromosome, The mutation operation on the aspect ratio of the functional area in different dual-encoded chromosomes is, The warehouse layout method according to claim 14, characterized in that it includes the step of replacing the aspect ratio of a functional area corresponding to a second index in one dual-encoded chromosome with a value within the range of the preset ratio.

17. The steps include calculating the acceptance probability of the double-coded chromosome after the crossover operation in the k-th double-coded chromosome population, In accordance with the fact that the acceptance probability of the dual-coded chromosome is a first value, the step is to make the dual-coded chromosome one of the k-th dual-coded chromosome individuals, The method further includes the step of rolling back the crossover operation of the dual-coded chromosome in response to the acceptance probability of the dual-coded chromosome not being the first value, and then making it one of the k-th dual-coded chromosome individuals, Hereinafter, the acceptance probability correlates with the maximum fitness value of each bicoded chromosome in the first bicoded chromosome population of the first bicoded chromosome population in the first iteration process, the minimum fitness value of each bicoded chromosome in the first bicoded chromosome population of the first iteration process, the fitness value of the bicoded chromosome of the c-th group in the k-th bicoded chromosome population of the k-th iteration process, and the maximum fitness value of each iteration process, and the acceptance probability decreases with increasing number of iterations of the bicoded chromosome, and c is a positive integer less than or equal to N, as described in claim 14.

18. A readable medium characterized in that, when executed on an electronic device, it stores an instruction causing the electronic device to execute the warehouse layout method described in any one of claims 1 to 17.

19. A computer program product characterized by causing the warehouse layout method described in any one of claims 1 to 17 to be executed on an electronic device when the program is run on the electronic device.

20. An electronic device comprising a memory for storing instructions executed by one or more processors of the electronic device, and a processor which is one of the processors of the electronic device for executing the warehouse layout method described in any one of claims 1 to 17.

Images