Picking sorting decision method considering wall capacity, service platform and storage medium

Abstract

The application relates to a picking sorting decision method considering the capacity of a seeding wall, a service platform and a storage medium. The method comprises the following steps: performing random coding and population initialization on SKUs associated with a plurality of picking orders to be sorted according to a preset coding mode, and generating a plurality of first sorting coding bodies; performing sorting correction preprocessing on sub-codes corresponding to the plurality of first sorting coding bodies by using a heap optimization simulated annealing algorithm, generating a plurality of second sorting coding bodies, and repeatedly performing non-dominated solution sorting and genetic evolution operation iteration on the fitness of the NSGA-II algorithm and the corresponding sorting coding bodies based on the plurality of second sorting coding bodies until a plurality of alternative sorting coding bodies are generated; selecting a target sorting coding body from the plurality of alternative sorting coding bodies according to the fitness of the alternative sorting coding body, and taking a plurality of target picking batches obtained by processing the target sorting coding body according to a picking sorting decision rule and a picking path mapped by the target picking batches as a decision result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer intelligent application, in particular to a picking and sorting decision method considering the capacity of a seeding wall, a service platform and a storage medium. BACKGROUND

[0002] In the prior art, due to the large order quantity, high time efficiency requirement and high picking density of an e-commerce warehouse, a multi-person collaborative picking operation mode is usually adopted to improve efficiency. However, in the case that batch picking operations are performed simultaneously and sorting or packaging operation resources are limited, if the batch operation quantity is unbalanced, the order operations may not be coordinated, resulting in waiting time. In related technologies, the research on order sorting links usually assumes that there is no capacity limitation of the sorting area when performing operations, or assumes that the capacity of the sorting area is large enough. However, in actual warehouse operation, the seeding wall and other equipment used for order sorting operations have capacity limitations. If the picking plan does not consider the resource limitations of the sorting operation link, congestion and waiting may occur in the sorting operation.

[0003] At present, there is no effective solution to the problem that the picking plan in related technologies does not consider the resource limitations of the sorting operation link, and congestion and waiting easily occur in the sorting operation. SUMMARY

[0004] Embodiments of the present application provide a picking and sorting decision method considering the capacity of a seeding wall, a service platform and a storage medium, to at least solve the problem that the picking plan in related technologies does not consider the resource limitations of the sorting operation link, and congestion and waiting easily occur in the sorting operation.

[0005] In a first aspect, the embodiments of the present application provide a picking sorting decision method considering the capacity of a seeding wall, comprising: after obtaining a plurality of picking orders to be picked in a picking order pool corresponding to a target warehouse, randomly encoding and population initializing SKUs associated with the plurality of picking orders according to a preset encoding mode, to generate a plurality of first sorting encoding bodies, wherein each picking order is associated with at least one SKU, and each first sorting encoding body includes a plurality of sub-codes representing picking orders in gene bits, and each sub-code corresponds to one SKU; using a heap optimization simulated annealing algorithm to sort and correct the sub-codes corresponding to the plurality of first sorting encoding bodies, to generate a plurality of second sorting encoding bodies, and based on the plurality of second sorting encoding bodies, repeatedly performing non-dominated solution sorting and genetic evolution operation iteration using the NSGA-II algorithm and the fitness of the corresponding sorting encoding body, until a plurality of candidate sorting encoding bodies are generated, wherein the fitness is determined according to the target function value corresponding to the plurality of picking batches corresponding to the corresponding sorting encoding body, the picking batch is generated by sorting and picking the SKUs of the corresponding sorting encoding body according to a picking sorting decision rule considering the capacity of the seeding wall, and the genetic evolution operation adopts adaptive crossover probability and adaptive mutation probability; selecting a target sorting encoding body from the plurality of candidate sorting encoding bodies according to the fitness of the candidate sorting encoding body, and taking the plurality of target picking batches obtained by processing the target sorting encoding body according to the picking sorting decision rule as a decision result.

[0006] In a second aspect, the embodiments of the present application provide a service platform, comprising a memory and a processor, characterized in that the memory stores a computer program, and the processor is configured to run the computer program to execute the steps of the picking sorting decision method considering the capacity of the seeding wall in the first aspect.

[0007] In a third aspect, the embodiments of the present application provide a storage medium having a computer program stored thereon, which is executed by a processor to implement the picking sorting decision method considering the capacity of the seeding wall in the first aspect.

[0008] Compared with the related art, the picking and sorting decision method considering the capacity of the seeding wall, the service platform and the storage medium provided by the embodiments of the present application, after obtaining a plurality of picking orders to be picked in a picking order pool corresponding to a target warehouse, the SKU associated with the plurality of picking orders is randomly encoded and initialized according to a preset encoding mode to generate a plurality of first sorting encoding bodies; the sub-codes corresponding to the plurality of first sorting encoding bodies are sorted and corrected by using a heap optimization simulated annealing algorithm to generate a plurality of second sorting encoding bodies, and based on the plurality of second sorting encoding bodies, the fitness of the NSGA-II algorithm and the corresponding sorting encoding body is repeatedly executed for non-dominated solution sorting and genetic evolution operation iteration until a plurality of alternative sorting encoding bodies are generated, the fitness is determined according to the target function value corresponding to the plurality of picking batches corresponding to the corresponding sorting encoding body, and the picking and sorting batches are generated by sorting and picking the SKUs of the corresponding sorting encoding body according to the picking and sorting decision rule; according to the fitness of the alternative sorting encoding body, a target sorting encoding body is selected from the plurality of alternative sorting encoding bodies, and a plurality of target picking batches obtained by processing the target sorting encoding body according to the picking and sorting decision rule are mapped to a picking path by the sorting of all SKUs in each target picking batch as a decision result. By introducing the capacity constraint of the seeding wall, the multi-objective is used as the fitness, the picking and sorting joint optimization decision considering the order picking path, the seeding wall capacity and the capacity constraint of the picking equipment is performed, the joint optimization of picking and sorting operations is realized under the limited capacity of the seeding wall, the backlog and waiting of orders in the sorting link are avoided, the efficient operation of order operations is ensured, the overall operation efficiency is improved, and the problem that the picking planning in the related art does not consider the resource limitation of the sorting operation link and congestion and waiting easily occur in the sorting operation is solved. BRIEF DESCRIPTION OF DRAWINGS

[0009] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0010] Figure 1 is a hardware structure block diagram of a terminal of the picking and sorting decision method considering the capacity of the seeding wall according to the embodiments of the present application;

[0011] Figure 2 is a flowchart of the picking and sorting decision method considering the capacity of the seeding wall according to the embodiments of the present application;

[0012] Figure 3 is a structure block diagram of the picking and sorting decision device considering the capacity of the seeding wall according to the embodiments of the present application. DETAILED DESCRIPTION

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and explained below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application and should not be used to limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of the present application. In addition, it should be understood that, although the efforts made in this development process can be complex and lengthy, some design, manufacture or production changes made on the basis of the technical content disclosed in the present application by those of ordinary skill in the art related to the content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the present application.

[0014] In the present application, the term "embodiment" means that the specific features, structures or properties described in conjunction with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0015] Unless otherwise defined, the technical terms or scientific terms involved in the present application should be understood as the usual meaning understood by those of ordinary skill in the art to which the present application belongs. The terms "one", "a", "an", "the", and similar words involved in the present application do not represent a quantity limitation, but can represent a singular or plural number. The terms "include", "contain", "have", and any variations thereof involved in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device including a series of steps or modules (units) is not limited to the listed steps or units, but can also include steps or units not listed, or can also include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in the present application refers to more than or equal to two links. "And / or" describes the association between the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent the following three cases: A exists alone, A and B exist together, and B exists alone. The terms "first", "second", "third", and the like involved in the present application only distinguish similar objects, and do not represent a specific order for the objects.

[0016] Before the method of the embodiments of the present application is described and explained, the related technologies involved in the embodiments of the present application are described as follows:

[0017] NAGA-II (Non-dominated Sorting Genetic Algorithm II) algorithm is a multi-objective optimization algorithm based on genetic algorithm, which is an improved version of NAGA (Non-dominated Sorting Genetic Algorithm) and is designed to deal with non-dominated sorting problems. NSGA-II inherits the idea of genetic algorithm (Genetic Algorithm, GA) and retains operations such as selection, crossover and mutation. However, it specially designs mechanisms such as non-dominated sorting and crowdedness comparison for multi-objective optimization problems. Through simulating the process of biological evolution in nature, NSGA-II can find a uniformly distributed and non-dominated Pareto optimal solution set in multi-objective optimization. The principle of NSGA-II algorithm is to simulate the process of biological reproduction, survival of the fittest and natural selection in nature, so as to realize the optimization of multi-objective problems. In NSGA-II algorithm, each individual represents a spatial solution, just like a biological individual in nature, which has its own characteristics (chromosome gene coding). These individuals are distributed in the search space and are constantly optimized through evolution operations. The process of finding a multi-objective Pareto optimal solution set in the iteration process is analogous to the process of survival of the fittest in the population.

[0018] The specific process of NSGA-II algorithm is as follows: 1. Initialize the population, randomly generate an initial population of size M, initialize the maximum number of iterations, crossover rate and mutation rate, etc.; 2. Fast non-dominated sorting, calculate the fitness function of the initial population and sort it; 3. Selection, crossover and mutation, get the first generation of offspring population, enrich the diversity of the population; 4. Merge the parent and offspring populations, the population size changes from M to 2M; 5. Fast non-dominated sorting, perform fast non-dominated sorting on the new population; 6. Calculate the crowdedness; 7. Form a new parent, select appropriate individuals to form a new parent according to the non-dominated relationship and the crowdedness of the individuals; 8. Selection, crossover and mutation, continuously cycle until the iteration criteria are met.

[0019] NSGA-II mainly uses fast non-dominated sorting and crowdedness calculation to select individuals, so as to ensure the quality of Pareto optimal solution and maintain the diversity of the population in the optimization process. Among them,

[0020] Fast non-dominated sorting is one of the core parts of NSGA-II algorithm. According to the Pareto dominance relationship between the population, each individual in the population is assigned to different levels (Front), ensuring that better solutions can be preserved in the multi-objective optimization process and maintaining the diversity of the population.

[0021] Non-dominated sorting, i.e. defining the dominance count of each individual in the population, in multi-objective optimization, to make individual p dominate individual q, must satisfy the following two conditions: p is not worse than q in all objectives; p is better than q in at least one objective, for example: take a minimum three-objective problem as an example, if the individual p corresponds to three objective values [4, 1, 6]; and the individual q corresponds to three objective values [2, 1, 5], at this time, the individual q is less than or equal to the individual p in all objectives, and the first and third objectives of the individual q are less than the individual p corresponding to the objective value, which satisfies the dominance relationship, so the individual q dominates the individual p; by traversing the dominance relationship between population individuals, the entire population is layered according to the dominance relationship, the first layer (Front1): the solution not dominated by any individual, called the optimal solution set; the second layer (Front2): the solution only dominated by the first layer individual; the third layer (Front3): the solution only dominated by the first two layers of individuals, and so on. Finally, the entire population is divided into multiple non-dominated layers, each layer corresponds to a group of solutions with the same dominance level.

[0022] Crowding distance calculation measures the sparseness of each individual in the objective space, so that non-dominated solutions can also be compared in size, so that more dispersed solutions are preferred when selecting the next generation of population individuals, avoiding the convergence of the population to a narrow area. In general, the population with a large crowding distance will be preferred, because the distribution of its solution is more dispersed, which is more conducive to obtaining a complete Pareto front, thereby facilitating the maintenance of population diversity.

[0023] The List-Based Simulated Annealing (LBSA) algorithm is an improved version based on the original Simulated Annealing (SA) algorithm. The main difference between LBSA and SA is the temperature control strategy. LBSA determines a state transition probability P0 at the beginning, and based on the corresponding acceptance probability formula of SA, it back calculates a temperature back calculation formula: An initial temperature list is first generated using the temperature back-calculation formula. In subsequent simulated annealing, the optimal annealing is performed based on the temperature stored in this list. The specific process of LBSA is as follows: Step (1) Initialize the temperature list and the number of iterations; Step (2) Take the maximum value tmax in the list, update the number of iterations in the outer loop, temperature, number of iterations in the inner loop, and the number of different solutions accepted; Step (3) Create a new solution; (4) Judge and compare. If the new solution is better, go to step (6); if the new solution is worse, go to step (5); Step (5) Calculate the acceptance probability, judge whether to accept it. If accepted, update t and c, and go to step (6); if not accepted, go to step (7); Step (6) Replace the original solution; Step (7) Judge whether it is less than the number of iterations in the inner loop. If yes, go to step (3); if not, go to step (8); Step (8) Judge whether the number of different solutions accepted is 0. If not, update the temperature list; Step (9) Judge whether it is less than the number of iterations in the outer loop. If yes, go to step (2); if not, end.

[0024] A Stock Keeping Unit (SKU) is the smallest available unit for maintaining and controlling inventory. It is typically measured in pieces, boxes, pallets, etc., and is used in logistics management for numbering and categorizing goods. Each product has a unique SKU number, which contains detailed attributes such as brand, model, configuration, packaging capacity, unit, production date, shelf life, usage, price, and country of origin. SKUs also play a crucial role in warehouse management. By numbering and managing SKUs, warehouse layout and storage strategies can be optimized, unnecessary movement and path conflicts can be reduced, and warehouse operational efficiency can be improved.

[0025] The following describes specific embodiments of the picking and sorting decision-making method considering the seed wall capacity according to the present application:

[0026] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. Taking running on a terminal as an example, Figure 1 This is a hardware structure block diagram of the terminal for a picking and sorting decision-making method considering the capacity of the seed wall, according to an embodiment of this application. Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are more... Figure 1more or less components than those shown, or configured differently from those shown, as Figure 1

[0027] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as the computer program of the picking sorting decision method considering the capacity of the seeding wall in the embodiments of the present application. The processor 102 can execute various functional applications and data processing, i.e., implement the above method, by running the computer program stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, which can be connected to the terminal 10 through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0028] The transmission device 106 is configured to receive or send data via a network. The specific example of the above network can include a wireless network provided by a communication provider of the terminal 10. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is configured to communicate with the Internet in a wireless manner.

[0029] The embodiments of the present application provide a picking sorting decision method considering the capacity of the seeding wall running on the above terminal, Figure 2 is a flowchart of the picking sorting decision method considering the capacity of the seeding wall according to the embodiments of the present application, as Figure 2 shown, the flowchart includes the following steps:

[0030] In step S201, after obtaining a plurality of picking orders to be picked in a picking order pool corresponding to a target warehouse, a SKU associated with the plurality of picking orders is randomly coded and initialized in a preset coding manner to generate a plurality of first sorting codes, wherein each picking order is associated with at least one SKU, and the first sorting code includes a plurality of sub-codes representing picking orders in gene bits, and each sub-code corresponds to one SKU.

[0031] ​In the present embodiment, the execution subject of the present embodiment includes but is not limited to a warehouse order management system, and after receiving a customer order, the execution subject will convert the received order into a picking order and intercept it in the picking order pool to wait for picking planning; after starting the picking planning, the current multiple picking orders to be planned are extracted from the picking order pool, and all SKUs to be coded are obtained according to the SKUs contained in each picking order, for example: there are picking order a [1, 2, 3, 4] and picking order b [5, 6, 7] and picking order c [8, 9], and the corresponding SKUs to be coded are: 1, 2, 3, 4, 5, 6, 7, 8, 9; At this time, the SKUs to be coded are coded according to the preset coding mode. It can be understood that coding is the process of mapping the feasible solution of a problem from the solution space to the search space that can be processed by the algorithm. Common coding methods include natural number coding and binary coding, etc. In the present embodiment, the batch and picking sequence of the goods (mapped to the corresponding SKU) in the order are determined, and each SKU has a unique natural number. The final solution is a natural number sequence with a certain order. In the present embodiment, natural number coding is used to improve the efficiency of the algorithm and the quality of the solution.

[0032] In the embodiment, the SKUs associated with the multiple picking orders are encoded to generate multiple first sorting encoding bodies, that is, the corresponding initial population, for example: the picking orders to be picked include: picking order 1 (having SKU numbers: 1, 2, 3), picking order 2 (having SKU numbers: 4, 5, 6), picking order 3 (having SKU numbers: 7, 8), picking order 4 (having SKU numbers: 9, 10, 11, 12), picking order 5 (having SKU numbers: 13, 14), picking order 6 (having SKU numbers: 15, 16), picking order 7 (having SKU numbers: 17, 18, 19, 20), picking order 8 (having SKU numbers: 21, 22, 23), picking order 9 (having SKU numbers: 24, 25, 26), picking order 10 (having SKU numbers: 27, 28), after encoding in the natural number coding mode, the first sorting encoding body 1 is generated: [10, 1, 11, 27, 28, 6, 4, 9, 14, 22, 15, 25, 16, 3, 20, 24, 19, 26, 18, 23, 17, 5, 13, 21, 8, 7, 12, 2], and then randomly initialized to generate partial sorting encoding bodies, including: the first sorting encoding body 2 [13, 1, 8, 27, 28, 6, 4, 9, 14, 3, 15, 25, 16, 22, 20, 24, 26, 18, 23, 17, 19, 5, 10, 21, 11, 7, 12, 2], and the first sorting encoding body 3 [27, 28, 6, 10, 1, 11, 4, 9, 14, 22, 15, 24, 19, 26, 18, 23, 25, 16, 3, 20, 17, 5, 13, 21, 8, 7, 12, 2]; It can be understood that in a first sorting encoding body, the position of a SKU represents the order in which it is picked, for example: 10 in the first sorting encoding body is in the first order, which means that the SKU will be picked by the first index, but it does not mean that it is assigned to the corresponding picking batch.

[0033] In step S202, the heap optimization simulated annealing algorithm is used to sort and correct the sub-codes corresponding to the multiple first sorting encoding bodies to generate multiple second sorting encoding bodies, and based on the multiple second sorting encoding bodies, the NSGA-II algorithm and the fitness of the corresponding sorting encoding body are repeatedly executed for non-dominated solution sorting and genetic evolution operation iteration until multiple candidate sorting encoding bodies are generated, wherein the fitness is determined according to the target function values of the multiple picking batches corresponding to the corresponding sorting encoding body, the picking batch is generated by picking and sorting processing the SKUs of the corresponding sorting encoding body according to the picking and sorting decision rule considering the sowing wall capacity, and the genetic evolution operation adopts adaptive crossover probability and adaptive mutation probability.

[0034] In the embodiment, because of the initialization of the first sorting encoding body, the corresponding solution distribution is uneven, the initial population quality is poor, the subsequent sorting and sorting combined optimization effect and convergence efficiency are affected, the solution is easy to fall into local optimum, in the embodiment, the LBSA algorithm (stack optimization simulated annealing algorithm) is used to pretreat and optimize the initial population, which can effectively improve the initial population quality, avoid premature convergence to local optimum, make the NSGA-II algorithm start optimization from better solution in the subsequent evolution process, speed up the expansion of the Pareto front, and enhance the diversity of the solution.

[0035] In the embodiment, the algorithm combining NSGA-II and LBSA is adopted, and the specific process includes the following steps:

[0036] Step 1, initialize parameters, including initializing the size of the population composed of the first sorting encoding body, the maximum number of iterations, the adaptive crossover probability and the adaptive mutation probability, the list length of LBSA, and the number of inner and outer loops.

[0037] Step 2, initialize the population, randomly generate an initial population with a size of M, including a plurality of first sorting encoding bodies.

[0038] Step 3, use the LBSA algorithm to pretreat the initial population to obtain the second sorting encoding body, then perform fast non-dominated sorting, calculate the fitness of the optimized initial population and sort it.

[0039] Step 4, after the selection is completed, cross and mutate with the preset adaptive crossover probability and adaptive mutation probability to obtain the first generation of offspring population.

[0040] Step 5, the parent population (initial population) and the offspring population (first generation of offspring population) are combined, the population number changes from M to 2M, the combined population is fast non-dominated sorted to obtain a new population with a preset population size, and a population composed of corresponding sorting encoding bodies is obtained.

[0041] Step 6, calculate the crowding degree.

[0042] Step 7, form a new parent, select appropriate individuals to form a new parent according to the non-dominated relationship and the crowding degree of the individuals.

[0043] Step 8, repeat the selection, crossover and mutation, and cycle repeatedly until the iteration standard is met.

[0044] It can be understood that the operation steps corresponding to the LBSA and NSGA-Ⅱ algorithms used in the embodiment are known or clear to those skilled in the art, and the related operations of the existing LBSA and NSGA-Ⅱ algorithms can be used to realize the preprocessing optimization of the first sorting encoding body, and the non-dominated solution sorting and crowding calculation based on the second sorting encoding body, and the corresponding selection, crossover and mutation genetic evolution operations, and then the candidate sorting encoding body satisfying the preset standard is obtained.

[0045] In the embodiment, in the process of calculating the fitness, the sorting and sorting decision rule considering the capacity of the seeding wall is first used to sort and sort the related sorting encoding body, to generate the corresponding sorting batch, at the same time, based on the SKU sorting of each sorting batch, the corresponding sorting path is determined, and then according to each sorting batch and the corresponding sorting path and the target value corresponding to the plurality of target functions, the sorting time corresponding to each sorting batch, the sorting completion time of the order and the sorting operation balance are determined, so as to determine the fitness of each corresponding sorting encoding body, and then the non-dominated solution sorting and genetic evolution operation iteration are performed according to the fitness, until the corresponding fitness guides the genetic evolution and the candidate sorting encoding body satisfying the set requirement is determined.

[0046] In step S203, the target sorting encoding body is selected from the plurality of candidate sorting encoding bodies according to the fitness of the candidate sorting encoding body, and the plurality of target sorting batches obtained by processing the target sorting encoding body according to the sorting and sorting decision rule are used as the decision result.

[0047] In the embodiment, the LBSA combined with the NSGA-Ⅱ algorithm is used to perform multiple sorting and sorting joint optimization on the coded first sorting encoding body until the fitness of the corresponding sorting encoding body meets the set requirement or the iteration number reaches the set requirement. At this time, a plurality of candidate sorting encoding bodies are obtained, and then the corresponding candidate sorting encoding body is selected from the plurality of candidate sorting encoding bodies meeting the requirement to obtain the target sorting encoding body. Because the sorting and sorting decision rule considering the capacity of the seeding wall is used to process the SKU of the sorting encoding body before the fitness of the corresponding sorting encoding body is calculated, the corresponding sorting batch is generated, that is, the plurality of target sorting batches and the sorting path mapped by the SKU sorting of each target sorting batch are obtained, and the decision result of the order batch and the sorting path planning is obtained.

[0048] By the above steps S201 to S203, after obtaining a plurality of to-be-picked picking orders trapped in the picking order pool corresponding to the target warehouse, the SKU associated with the plurality of picking orders is randomly coded and initialized by a preset coding method to generate a plurality of first sorting codes; the sub-codes corresponding to the plurality of first sorting codes are sorted and corrected by using a heap optimization simulated annealing algorithm to generate a plurality of second sorting codes, and based on the plurality of second sorting codes, the non-dominated solution sorting and genetic evolution operation iteration are repeatedly performed by using the NSGA-II algorithm and the fitness of the corresponding sorting code, until a plurality of candidate sorting codes are generated, the fitness is determined according to the target function value corresponding to the plurality of picking batches corresponding to the corresponding sorting code, the picking batch is generated by sorting and sorting the SKU of the corresponding sorting code according to the sorting and sorting decision rule considering the capacity of the seeding wall; according to the fitness of the candidate sorting code, the target sorting code is selected from the plurality of candidate sorting codes, and the plurality of target picking batches obtained by processing the target sorting code according to the sorting and sorting decision rule are mapped to the picking path by the sorting of all SKUs in each target picking batch, as a decision result, by introducing the capacity constraint of the seeding wall, the sorting and sorting joint optimization decision considering the order picking path, the capacity of the seeding wall and the capacity of the sorting equipment is performed with the preset multi-objective as the fitness, the joint optimization of sorting and sorting operation is realized under the limited capacity of the seeding wall, the backlog and waiting of orders in the sorting link are avoided, the efficient operation of the order operation is ensured, the overall operation efficiency is improved, and the problem that the sorting planning in the related art does not consider the resource limitation of the sorting operation link and the congestion and waiting in the sorting operation are easily generated is solved.

[0049] In some embodiments, before determining the fitness of the corresponding sorting code, the corresponding sorting code is sorted and sorted according to the sorting and sorting decision rule considering the capacity of the seeding wall by the following steps:

[0050] Step 21, determine the target seeding wall currently associated with the active order and the picking capacity corresponding to each picking batch to be constructed, wherein the active order is used to represent the picking order allowed to be loaded on the target seeding wall, and the picking capacity is used to represent the number of SKUs picked by the sorting device associated with the target seeding wall for one picking batch.

[0051] In the present embodiment, in the process of picking and sorting the corresponding SKU, the capacity of the seeding wall determines the priority of the order to be picked in the case of considering the capacity of the seeding wall. In order to consider the capacity of the seeding wall, the seeding wall activates or associates at least one active order when indexing the corresponding SKU. The currently activated or associated order has priority when indexing the corresponding SKU, that is, when the indexed SKU belongs to the SKU of the picking order corresponding to the active order currently associated with the seeding wall, the SKU is allowed to be batched into the corresponding picking batch, otherwise, the SKU will be skipped. The picking capacity of each picking batch is determined by the capacity of the picking device corresponding to the seeding wall, for example: the capacity of the picking device associated with the seeding wall is 4, so the upper limit of the number of picked SKUs is 4 when picking the current picking batch. When all SKUs of the corresponding active order are picked, if the number of SKUs in the corresponding picking batch is less than 4, no additional SKU of the picking order will be supplemented to maintain the state of less than 4 SKUs to ensure the feasibility of the picked picking batch. It can be understood that when performing picking and sorting of the corresponding sorting code body, the active order associated with the target seeding wall and the picking capacity of the corresponding picking device need to be determined to determine the picking order of the picking order and the batch parameter of the picking batch.

[0052] Step 22, index picking all SKUs of the third sorting code body currently to be picked and sorted, and determine whether the currently picked SKU belongs to the SKU of the currently associated active order.

[0053] Step 23, in the case where it is determined that the currently picked SKU belongs to the SKU of the currently associated active order, the currently picked SKU is added to an unfull picking batch.

[0054] In the present embodiment, when all SKUs of the third sorting code body are traversed, only when the SKU belongs to an order that already exists in the active order list (corresponding to a SKU of the active order), the SKU will be put into a currently unfull picking batch, otherwise, the indexed SKU will be skipped and the next SKU will be read;

[0055] Step 24, repeat the steps of indexing the corresponding SKU, determining whether the picked SKU is the SKU of the active order, and adding the SKU to the corresponding picking batch until the multiple picking batches corresponding to the currently associated active order are determined, and the multiple picking batches determined by multiple times are combined into a total picking batch. The multiple picking batches corresponding to the third sorting code body include the total picking batch, and the number of SKUs added in each picking batch does not exceed the picking capacity.

[0056] In the embodiment, when a SKU is picked, the corresponding SKU capacity is added to the current load of the picking device associated with the seeding wall. When the load of the picking device reaches its maximum capacity, the current picking batch is terminated, the picking object returns to the seeding wall to sort the picked SKU, and then a new picking batch is generated from the position where the previous picking batch terminated in the third sorting code body until the index picking of a third sorting code body is completed.

[0057] Through steps 21 to 24, the active orders associated with the seeding wall are prioritized by considering the capacity constraints of the seeding wall and the picking device, the corresponding sorting code body is sorted and sorted according to the sorting and sorting decision rule considering the capacity of the seeding wall, the feasibility of the picking batch and the picking path planning is ensured, the overall operation efficiency is optimized, and the order operation continuity is improved.

[0058] In some embodiments, in the case where it is determined that the currently picked SKU does not belong to the SKU of the currently associated active order, the following steps are implemented:

[0059] Step 31, according to the number of the currently associated active orders and the order loading capacity corresponding to the target seeding wall, determine whether the target seeding wall allows to add the associated active order.

[0060] In the embodiment, if it is determined that the order to which the currently indexed SKU belongs has not been activated (that is, the SKU does not belong to the active order), at this time, it is first determined whether the seeding wall has remaining order capacity, that is, whether there is order capacity that can be activated or associated with the active order, for example, when the order capacity of the active order associated with the seeding wall is 2, one active order has been associated before, then there is one order capacity that can be associated with the active order.

[0061] Step 32, in the case where it is determined that the target seeding wall allows to add the associated active order, the picking order to which the currently picked SKU belongs is added as the added active order, and the already associated active order and all added active orders are taken as the current active order of the target seeding wall, and the currently picked SKU is added to an unsorted picking batch.

[0062] In the embodiment, when it is determined that there is still order capacity that can be associated with the active order, the picking order to which the currently picked SKU belongs is associated with the target seeding wall as the active order, that is, the picking order to which the currently picked SKU belongs is activated, and the currently picked SKU is added to the corresponding picking batch.

[0063] Step 33, in the case of determining that the target seeding wall does not allow to add the active order associated, the next SKU is indexed and picked.

[0064] In the embodiment, when it is determined that there is no order capacity that can be associated with the active order, the currently picked SKU is skipped, and the next SKU needs to be indexed and picked to determine whether the next SKU belongs to the SKU of the currently activated active order.

[0065] In some embodiments, after determining the multiple picking batches corresponding to the currently associated active order, the following steps are implemented:

[0066] Step 41, index and pick the next SKU, and determine the picking order to which the next SKU belongs.

[0067] Step 42, release all active orders currently associated, and at least associate the picking order to which the next SKU belongs as the corresponding active order, and add the indexed next SKU to the newly constructed picking batch.

[0068] In the embodiment, when all SKUs of the active order associated with the target seeding wall are indexed and picked, at this time, the next SKU is indexed and picked, which does not belong to the picking batch that can be batched, at this time, by releasing the associated active order, that is, releasing the order capacity of the target seeding wall, and by associating the picking order to which the indexed next SKU belongs, that is, activating at least one active order, then, a picking batch is newly constructed, and the next SKU is added to the picking batch. It can be understood that, when continuing to index and pick the candidate SKU, before the SKU not belonging to the SKU of the at least activated active order is indexed, the target seeding wall can not activate or associate the corresponding active order, when the SKU not belonging to the SKU of the at least activated active order is indexed, the picking order to which the indexed SKU belongs is activated as an active order, to ensure the feasibility of the picking and sorting of the picking batch.

[0069] In some embodiments, after adding the currently indexed and picked SKU to the corresponding picking batch and before combining the multiple picking batches determined by multiple decisions into a total picking batch, the following steps are implemented:

[0070] Step 51, determine whether the currently picked SKU is located at the end of the third sorting code body.

[0071] Step 52, in the case of determining that the currently picked SKU is located at the end of the third sorting code body, obtain all SKUs that are not added to the corresponding picking batch, to obtain a candidate SKU group.

[0072] Step 53, based on the alternative SKU group, repeat the operation of index picking SKU, adding the index-picked SKU to the corresponding picking batch, and updating the active order associated with the target seeding wall, until all the SKUs of the third sorting code body are added to the corresponding picking batch.

[0073] In the present embodiment, after all the SKUs picked to the end of the third sorting code body, it is judged whether there are SKUs previously skipped that have not been added to the corresponding picking batch. If so, index picking is performed again from the beginning of the third sorting code body. During the re-index picking process, the SKUs already arranged in the corresponding picking batch are not repeatedly picked, that is, by index picking in the SKU group composed of all the SKUs not added to the corresponding picking batch. It can be understood that in the case where the currently picked SKU is at the end of the third sorting code body, the current picking batch will be terminated, and when a new picking batch is started, the consideration of the picking batch of the picking order, that is, the determination of whether to add the SKU re-started index picking to the corresponding picking batch, gives priority to the picking order to which the last index-picked SKU belongs before re-starting index picking. The target seeding wall will give priority to maintaining the picking order to which the last index-picked SKU belongs as an active order.

[0074] In the present embodiment, the operation of index picking SKU, adding the index-picked SKU to the corresponding picking batch, and updating the active order associated with the target seeding wall is repeated, and the repeated operation is continued until all the SKUs of the corresponding third sorting code body are index-picked and batched to the corresponding picking batch position.

[0075] In some optional embodiments, the picking batch of all the SKUs of the third sorting code body is implemented by the following steps:

[0076] Step 1: Initialize the active order list active_orders=[] and the total picking batch set tours=[].

[0077] In this embodiment, active orders represents the list of active orders on the target seeding wall, used to store the picking orders that have been partially picked but not yet completely picked, which will be updated in the continuous allocation of SKUs; tours represents the total picking batches, which is also the final output result; i represents the index position of the indexed SKU in the third sorting code body; PickCap and PutCap are the initial input values, representing the picking device capacity and seeding wall order capacity, respectively; tour represents one of the picking batches, which will be terminated when certain conditions are met, such as the picking device being overloaded, unable to continue to put in SKUs, or i indexing to the end of the third sorting code body, then the current batch is stored in tours and a new tour is started to store the next batch of SKUs, until all SKUs are allocated to the picking batches.

[0078] Step 2: Execute the main loop to gradually build the picking batches (loop execution until all order SKUs are picked), create a new picking batch tour = [], used to store the current batch of SKUs; initialize the picking batch load load = 0, indicating that no SKU has been added yet; start traversing from the first SKU of the third sorting code body i = 1.

[0079] Step 3: Enter the sub-loop to read SKUs one by one and build the picking batches.

[0080] This loop continues to execute until the end of the third sorting code body is reached or the picking object load reaches the upper limit PickCap, and the active order list is continuously updated in this loop.

[0081] Step 4: Complete the current picking batch and update the total picking batch set; recreate a new tour and continue the loop until all order SKUs are completely picked.

[0082] Step 5: Process the SKUs that have not been batched, if there are still SKUs that have not been included in any picking batch after the first traversal, then perform a second traversal to only process the remaining SKUs until all SKUs are completely included in a picking batch.

[0083] Step 6: Output the final total picking batch scheme and return the final tours.

[0084] In some optional embodiments, two order capacities are set to 2, and the to-be-picked orders are set as: picking order 1 (having SKU numbers 1, 2, and 3), picking order 2 (having SKU numbers 4, 5, and 6), picking order 3 (having SKU numbers 7 and 8), picking order 4 (having SKU numbers 9, 10, 11, and 12), picking order 5 (having SKU numbers 13 and 14), picking order 6 (having SKU numbers 15 and 16), picking order 7 (having SKU numbers 17, 18, 19, and 20), picking order 8 (having SKU numbers 21, 22, and 23), picking order 9 (having SKU numbers 24, 25, and 26), and picking order 10 (having SKU numbers 27 and 28). In a generated sorting code body, the first index-picked SKU is number 10, the SKU of number 10 is assigned to the picking order (corresponding to picking order 4) to which the SKU belongs, and the SKU is assigned to the first picking batch. The next SKU is number 1, and the picking order (corresponding to picking order 1) to which the SKU belongs is activated. The next SKU is number 11, and the picking order to which the SKU belongs is the same as the picking order to which the SKU of number 10 belongs. When the picking device capacity allows (the picking batch has two SKUs, and the picking device capacity is four SKUs), the SKU is assigned to the current picking batch. The next SKU is number 27, and the SKU does not belong to the activated picking order. When there are two activated picking orders (two active orders), the SKU cannot be assigned to the current picking batch. The SKU of number 9 is found, and the picking order to which the SKU belongs is activated.

[0085] In some embodiments, the fitness of the corresponding sorting code body is determined by the following steps.

[0086] In step 61, all picking batches corresponding to the fourth sorting code body are determined, and the SKU corresponding to each picking batch is searched from the preset order bin parameter information, where the fourth sorting code body includes one of the second sorting code body, the alternative sorting code body, and the target sorting code body.

[0087] Step 62, using the preset batch picking time function and the corresponding storage location parameters, the first picking time corresponding to each picking batch is calculated, and the total picking time corresponding to the fourth sorting code body is calculated through the preset minimum total picking time function and the corresponding first picking time.

[0088] In this embodiment, the first picking time corresponding to the picking batch is calculated by the following formula :

[0089] .

[0090] In this embodiment, the picking batch is calculated to obtain the corresponding picking time, that is, the sum of the picking times of all picking batches, the picking time is from the starting point (the seeding wall) to the warehouse according to the picking order of the picking batch, and finally returns to the starting point (the seeding wall). According to the corresponding picking path, a picking distance can be obtained, and then the picking distance is divided by a set picking speed (walking speed of the picking object) to obtain the picking time.

[0091] The corresponding total picking time is calculated by the following formula: ;

[0092] The corresponding order sorting total completion time is calculated by the following formula:

[0093] ;

[0094] The corresponding minimum picking worker work balance parameter is calculated by the following formula:

[0095] ;

[0096] Wherein, j represents the jth picking order, j∈{1,2,…,J},J represents the picking order set, s i represents the s i th SKU, s i ∈{1,2,…,S},S represents the SKU set, b represents the bth picking batch, b∈{1,2,…,B},B represents the picking batch set; D represents the target seeding wall position, c s1,s2 represents the shortest path length between the s1th SKU and the s2th SKU position, which is a known value, c s represents the path length between the s th SKU position and the target seeding wall, V represents the walking speed of the picker, represents the picking time of the bth picking batch, represents the waiting time of the bth picking batch in the sorting link, represents the picking order of the SKU in the bth picking batch; = 1 if the s-th SKU of the j-th picking order is the first picked SKU in the b-th picking batch, otherwise, = 1, otherwise, = 0, = 1 if the s-th SKU of the j-th picking order is the last picked SKU in the b-th picking batch, otherwise, = 1, otherwise, = 0, = 1 if the j-th picking order is partially or completely picked in the b-th picking batch, otherwise, = 1, otherwise, = 0; = 1 if the j-th picking order is partially or completely picked in the b-th picking batch, otherwise, = 1 if the j-th picking order contains the s-th SKU, otherwise, = 1, otherwise, j = 1, otherwise, b = 1, otherwise.

[0097] In this embodiment, before calculating the fitness according to the corresponding formula, the following mathematical model is established: 1. The capacity of the seeding wall is limited and it is not possible to associate all picking orders at once; 2. The grid on the seeding wall is only associated with one picking order, and only when the picking order items (SKU) are all picked can the next picking order be associated; 3. The capacity of each grid in the seeding wall is large enough; 4. The picking order information is known in advance, and each picking order contains at least one SKU; 5. The picking order is allowed to be split; 6. The time of putting the items into the corresponding grid of the seeding wall after the picking batch is completed is not considered; 6. There is no out-of-stock situation for the items on the storage location; 7. The amount of items in the picking batch does not exceed the capacity of the picking device; 8. The storage location of the picking object in the warehouse is known; 8. The walking speed of the picking object remains constant; 9. The picking object starts picking from the seeding wall and returns to the seeding wall after completing the picking.

[0098] In this embodiment, the following constraints are established

[0099] 1. Order association sequence constraint on the seeding wall

[0100] For any two orders j1 and j2, there can only be a unique priority relationship in the grid association order on the seeding wall, and the constraint is: ;

[0101] If order j1 is picked before order j2, and order j2 is picked before order j3, then order j1 is picked before order j3, and the constraint is: ;

[0102] If two orders have the same predecessor or successor, they should also have a precedence relationship between them, in particular, if order j1 and order j2 have the same successor j3, then it must be guaranteed that order j1 and order j2 have a precedence in the ordering; similarly, if order j1 and order j2 have the same predecessor j0, then they also need to establish a precedence relationship between them, with the constraint: ; .

[0103] 2. Picking batch constraints

[0104] ;

[0105] The above constraint represents the minimum number of precedence relationships required between orders based on the capacity of the seeding wall, where mod is the modulo operator.

[0106] The constraint for the picking device capacity constraint is: .

[0107] The picking path integrity constraint is: .

[0108] The constraint that the picking path starts and ends with a seeding wall: .

[0109] The constraint that each picking path starts from the start point at most once: .

[0110] 3. Order batching constraints

[0111] The constraint that all SKUs in each picking order are assigned to a picking batch: , , .

[0112] The constraint that the SKUs of two picking orders subject to a precedence constraint cannot be assigned to the same picking batch: , .

[0113] The constraint that an order is either partially picked or completely picked in a batch, provided that at least one SKU related to the order is picked in the batch. That is, if a SKU of an order is assigned to a batch, then the order must start to be fulfilled in that batch, with the constraint: , ;

[0114] , .

[0115] One picking order is prioritized over another picking order, then the two picking orders cannot be in the same picking batch, the constraint is: , .

[0116] The number of orders picked in each picking batch is limited within the maximum capacity of the seeding wall, .

[0117] Sub-path elimination constraint: .

[0118] Step 63, according to the total picking time, in turn using the preset order sorting completion time function and the picking batch picking completion time standard deviation function, the order sorting total completion time and the minimum picking person work balance parameter corresponding to the fourth sorting code body are calculated respectively.

[0119] Step 64, based on the total picking time, the order sorting total completion time and the minimum picking person work balance parameter, the fitness corresponding to the fourth sorting code body is calculated.

[0120] In some embodiments, before selecting the target sorting code body, the following steps are also implemented:

[0121] Step 71, judge whether the fitness corresponding to the sorting code body corresponding to the current iteration is greater than the preset fitness threshold.

[0122] Step 72, in the case where the fitness corresponding to the corresponding sorting code body is greater than the preset fitness threshold, the corresponding sorting code body is taken as the candidate sorting code body.

[0123] Step 73, select the candidate sorting code body with the largest fitness from the plurality of candidate sorting code bodies to obtain the target sorting code body.

[0124] In some optional embodiments, the non-dominated solution sorting and genetic evolution operation on the fifth sorting code body to be currently subjected to non-dominated solution sorting and genetic evolution operation include:

[0125] Step 1, using a non-dominated sorting algorithm, non-dominated sorting is performed on all fifth sorting code bodies, and the crowding degree of all fifth sorting code bodies subjected to non-dominated sorting is calculated to obtain the code parameters corresponding to each fifth sorting code body, wherein the code parameters include non-dominated sorting parameters and crowding degree.

[0126] Step 2, according to the non-dominated sorting parameters and the crowding degree, the first non-dominated code body is selected from all fifth sorting code bodies.

[0127] Step 3, using the NSGA-II algorithm, genetic evolution operation is performed on all fifth sorting codes to generate a preset number of first sub-codes, and the genetic evolution operation includes one of the following: tournament selection, crossover, mutation, the crossover corresponds to the adaptive crossover probability generated by the logsig function with a preset gradient decrease, and the mutation corresponds to the adaptive mutation probability generated by the logsig function with a preset gradient decrease;

[0128] Step 4, the sixth sorting code after merging all first non-dominated codes and all first sub-codes is sorted and crowdedness is calculated, and according to the non-dominated sorting parameter and the crowdedness, the same number of sorting codes as the fifth sorting code is selected from all sixth sorting codes to obtain the sorting code after completing the non-dominated solution sorting and genetic evolution operation.

[0129] The embodiment also provides a picking sorting decision device considering the capacity of the seeding wall, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the terms "module", "unit", "sub-unit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0130] Figure 3 is a structure block diagram of a picking sorting decision device considering the capacity of the seeding wall according to the embodiment of the application, as shown in Figure 3 The device includes an encoding module 31, a processing module 32 and a generating module 33:

[0131] The encoding module 31 is configured to, after obtaining a plurality of picking orders to be picked trapped in a picking order pool corresponding to a target warehouse, randomly encode and initialize a population for SKUs associated with the plurality of picking orders in a preset encoding manner to generate a plurality of first sorting codes, wherein each picking order is associated with at least one SKU, the first sorting code includes a plurality of sub-codes representing picking order in gene bits, and each sub-code corresponds to one SKU;

[0132] The processing module 32 is coupled to the encoding module 31, and is configured to perform sorting correction preprocessing on the sub-codes corresponding to the plurality of first sorting encodings by using a stack optimization simulated annealing algorithm, to generate a plurality of second sorting encodings, and repeatedly perform, based on the plurality of second sorting encodings, non-dominated solution sorting and genetic evolution operation iterations by using the NSGA-II algorithm and the fitness of the corresponding sorting encodings, until a plurality of candidate sorting encodings are generated, wherein the fitness is determined according to the objective function values corresponding to the plurality of picking batches corresponding to the corresponding sorting encodings, the picking batch is generated by performing picking and sorting processing on the SKUs of the corresponding sorting encodings according to a picking and sorting decision rule considering the capacity of the seeding wall, and the genetic evolution operation adopts adaptive crossover probability and adaptive mutation probability.

[0133] The generating module 33 is coupled to the processing module 32, and is configured to select a target sorting encoding from the plurality of candidate sorting encodings according to the fitness of the candidate sorting encodings, and take, as a decision result, a plurality of target picking batches obtained by processing the target sorting encoding according to the picking and sorting decision rule, as the decision result.

[0134] In some embodiments, the processing module 32 is further configured to, before determining the fitness of the corresponding sorting encoding, determine a picking capacity corresponding to each picking batch to be constructed and a current associated active order of the target seeding wall, wherein the active order is used to represent a picking order allowed to be loaded on the target seeding wall, and the picking capacity is used to represent the number of SKUs picked by a picking device associated with the target seeding wall for one picking batch; index picking all SKUs of a third sorting encoding currently to be picked and sorted, and determine whether the currently picked SKU belongs to the SKUs of the currently associated active order; in a case where it is determined that the currently picked SKU belongs to the SKUs of the currently associated active order, add the currently picked SKU to an un-full picking batch; repeat the steps of index picking the corresponding SKU, determining whether the picked SKU is the SKU corresponding to the active order, and adding the SKU to the corresponding picking batch, until a plurality of picking batches corresponding to the current associated active order are determined, and combine the plurality of picking batches determined by multiple times of decision-making into a total picking batch, wherein the plurality of picking batches corresponding to the third sorting encoding include the total picking batch, and the number of SKUs added in each picking batch does not exceed the picking capacity.

[0135] In some embodiments, the processing module 32 is further configured to, in a case where it is determined that the currently picked SKU does not belong to the SKU of the currently associated active order, determine whether the target seeding wall allows to add an associated active order according to the number of the currently associated active order and the order loading capacity corresponding to the target seeding wall; in a case where it is determined that the target seeding wall allows to add an associated active order, add the picking order to which the currently picked SKU belongs as an added active order, and take the associated active order and all added active orders as the currently associated active order of the target seeding wall, and add the currently picked SKU to an unfull picking batch; in a case where it is determined that the target seeding wall does not allow to add an associated active order, index picking the next SKU.

[0136] In some embodiments, the processing module 32 is further configured to, after determining the multiple picking batches corresponding to the currently associated active order, index picking the next SKU and determining the picking order to which the next SKU belongs; release all the currently associated active orders and at least associate the picking order to which the next SKU belongs as a corresponding active order, and add the index-picked next SKU to a newly constructed picking batch.

[0137] In some embodiments, the processing module 32 is further configured to, before combining the multiple picking batches determined by multiple times of determination into a total picking batch, determine whether the currently picked SKU is located at the end of the third sorting code body; in a case where it is determined that the currently picked SKU is located at the end of the third sorting code body, obtain all SKUs that are not added to the corresponding picking batch to obtain a candidate SKU group; based on the candidate SKU group, repeatedly perform the operations of indexing picking a SKU, adding the index-picked SKU to the corresponding picking batch, and updating the active order associated with the target seeding wall, until all SKUs of the third sorting code body are added to the corresponding picking batch.

[0138] In some embodiments, the processing module 32 is further configured to determine all picking batches corresponding to the fourth sorting code body that has completed the current picking and sorting process, and to find the storage location parameters corresponding to the SKU of each picking batch from the preset order storage location parameter information, wherein the fourth sorting code body includes one of the second sorting code body, the alternative sorting code body, and the target sorting code body; to calculate the first picking time corresponding to each picking batch using the preset batch picking time function and the corresponding storage location parameters, and to calculate the total picking time corresponding to the fourth sorting code body using the preset minimum total picking time function and the corresponding first picking time; based on the total picking time, to calculate the total order picking completion time and the minimum picking manual operation balance parameter corresponding to the fourth sorting code body respectively using the preset order picking completion time function and the picking batch picking completion time standard deviation function; and to calculate the fitness corresponding to the fourth sorting code body based on the total picking time, the total order picking completion time, and the minimum picking manual operation balance parameter.

[0139] In some embodiments, the processing module 32 calculates the first picking time corresponding to the picking batch using the following formula. :

[0140] ;

[0141] The total picking time is calculated using the following formula: ;

[0142] The total order sorting completion time is calculated using the following formula:

[0143] ;

[0144] The corresponding minimum picking manpower balance parameter is calculated using the following formula:

[0145] ;

[0146] Where j represents the j-th picking order, j∈{1,2,…,J}, J represents the picking order set, and s i Indicates the sth i SKU, s i b ∈ {1,2,…,S}, where S represents the SKU set, b represents the b-th picking batch, b ∈ {1,2,…,B}, where B represents the picking batch set; D represents the target seeding wall position, c s1,s2 c represents the shortest path length between the positions of the s1-th SKU and the s2-th SKU, which is a known value. s Let V represent the path length between the location of the s-th SKU and the target seeding wall, and let V represent the walking speed of the picker. This represents the picking time for the b-th picking batch. denotes the possible waiting time of the b-th picking batch at the picking stage, denotes the picking order of the SKU in the b-th picking batch; denotes whether the s-th SKU of the j-th picking order is the first picked SKU in the b-th picking batch, if yes, = 1, otherwise, = 0, denotes whether the s-th SKU of the j-th picking order is the last picked SKU in the b-th picking batch, if yes, = 1, otherwise, = 0, denotes whether the j-th picking order is partially or completely picked in the b-th picking batch, if yes, = 1, otherwise, = 0.

[0147] In some embodiments, the generating module 33 is further configured to, before selecting the target ranking code body, determine whether the fitness corresponding to the ranking code body after completion of the current iteration is greater than a preset fitness threshold; in a case where it is determined that the fitness corresponding to the ranking code body is greater than the preset fitness threshold, the ranking code body is taken as a candidate ranking code body; and from the plurality of candidate ranking code bodies, a candidate ranking code body with the greatest fitness is selected to obtain the target ranking code body.

[0148] The embodiment also provides a service platform, including a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any of the method embodiments.

[0149] Optionally, the service platform can further include a transmission device and an input and output device, wherein the transmission device is connected with the processor, and the input and output device is connected with the processor.

[0150] Optionally, in the embodiment, the processor can be configured to execute the following steps through the computer program:

[0151] S1, after obtaining a plurality of picking orders to be picked trapped in a picking order pool corresponding to a target warehouse, randomly encoding and population initializing SKUs associated with the plurality of picking orders in a preset encoding manner to generate a plurality of first ranking code bodies.

[0152] S2, using the stack optimization simulated annealing algorithm, the first sorting encoding body corresponding to a plurality of sub-code sorting correction preprocessing, generating a plurality of second sorting encoding body, and based on a plurality of second sorting encoding body, repeatedly using NSGA-Ⅱ algorithm and the corresponding sorting encoding body fitness, non dominated solution sorting and genetic evolution operation iteration, until a plurality of alternative sorting encoding body is generated.

[0153] S3, according to the fitness of the alternative sorting encoding body, selecting the target sorting encoding body from the plurality of alternative sorting encoding bodies, and processing the target sorting encoding body according to the sorting decision rule to obtain a plurality of target sorting batches, and the sorting path mapped by the sorting of all SKUs in each target sorting batch is used as the decision result.

[0154] It should be noted that the specific examples in the present embodiment can refer to the examples described in the above embodiments and optional implementation manners, and the present embodiment will not be described here.

[0155] In addition, in combination with the sorting and sorting decision method considering the sowing wall capacity in the above embodiment, the present embodiment can provide a storage medium for implementation. The storage medium has a computer program stored thereon; the computer program is executed by a processor to implement any one of the sorting and sorting decision methods considering the sowing wall capacity in the above embodiments.

[0156] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A pick sorting decision method considering the capacity of a seeding wall, characterized in that, The method comprises the following steps: After obtaining a plurality of to-be-picked picking orders trapped in a picking order pool corresponding to a target warehouse, a plurality of SKUs associated with the plurality of picking orders are randomly coded and population initialized according to a preset coding mode, to generate a plurality of first sorting codes, wherein each picking order is associated with at least one SKU, and the first sorting code comprises a plurality of sub-codes representing picking sequences in gene positions, and each sub-code corresponds to one SKU; The sub-codes corresponding to the plurality of first sorting codes are sorted and pre-processed by using a heap optimization simulated annealing algorithm to generate a plurality of second sorting codes, and based on the plurality of second sorting codes, the NSGA-II algorithm and the fitness of the corresponding sorting code are repeatedly executed for non-dominated solution sorting and genetic evolution operation iteration until a plurality of candidate sorting codes are generated, wherein the fitness is determined according to the target function value corresponding to the plurality of picking batches corresponding to the corresponding sorting code, the picking batches are generated by performing picking and sorting processing on the SKUs of the corresponding sorting code according to a picking and sorting decision rule considering the capacity of the seeding wall, and the genetic evolution operation adopts adaptive crossover probability and adaptive mutation probability; According to the fitness of the candidate sorting code, a target sorting code is selected from the plurality of candidate sorting codes, and a plurality of target picking batches obtained by processing the target sorting code according to the picking and sorting decision rule are used as a decision result.

2. The method of claim 1, wherein, Before determining the fitness of the corresponding sorting code, the method further comprises: determining a target seeding wall currently associated with an active order and a picking capacity corresponding to each picking batch to be constructed, wherein the active order is used to represent the picking order allowed to be loaded on the target seeding wall, and the picking capacity is used for the number of SKUs picked by the picking equipment associated with the target seeding wall for one picking batch; index picking all SKUs of a third sorting code currently to-be-picked and sorted, and determining whether the currently picked SKUs belong to the SKUs of the currently associated active order; in a case where it is determined that the currently picked SKUs belong to the SKUs of the currently associated active order, adding the currently picked SKUs to one not full picking batch; repeating the steps of index picking the corresponding SKUs, determining whether the picked SKUs are the SKUs corresponding to the active order, and adding the SKUs to the corresponding picking batch until a plurality of picking batches corresponding to the currently associated active order are determined, and combining the plurality of picking batches respectively determined by multiple times of decision into a total picking batch, wherein the plurality of picking batches corresponding to the third sorting code include the total picking batch, and the number of SKUs added in each picking batch does not exceed the picking capacity.

3. The method of claim 2, wherein, In a case where it is determined that the SKU currently picked does not belong to the SKU of the active order currently associated, the method further comprises: According to the number of the active order currently associated and the order loading capacity corresponding to the target seeding wall, it is determined whether the target seeding wall allows to add the active order associated; In a case where it is determined that the target seeding wall allows to add the active order associated, the picking order to which the SKU currently picked belongs is taken as the active order added, and the active order associated and all the active order added are taken as the active order currently associated with the target seeding wall, and the SKU currently picked is added to a picking batch that is not full. In a case where it is determined that the target seeding wall does not allow to add the active order associated, the next SKU is index-picked.

4. The method of claim 3, wherein, After the decision of the picking batch corresponding to the active order currently associated, the method further comprises: Index-picking the next SKU and determining the picking order to which the next SKU belongs; Releasing all the active order currently associated, and at least associating the picking order to which the next SKU belongs as the active order corresponding, and adding the next SKU index-picked to a picking batch newly constructed.

5. The method of claim 4, wherein, Before the combination of the picking batch decided by multiple times into a total picking batch, the method further comprises: Determining whether the SKU currently picked is located at the end of the third sorting code body; In a case where it is determined that the SKU currently picked is located at the end of the third sorting code body, all SKUs not added to the corresponding picking batch are obtained to obtain a candidate SKU group; Based on the candidate SKU group, the operations of index-picking the SKU, adding the SKU index-picked to the corresponding picking batch, and updating the active order associated with the target seeding wall are repeatedly executed until all the SKUs of the third sorting code body are added to the corresponding picking batch.

6. The method of claim 1, wherein, Determining the fitness of the corresponding sorting code body comprises: Determining all the picking batch corresponding to the fourth sorting code body of the current picking and sorting processing, and finding the storage location parameter corresponding to the SKU of each picking batch from the preset order storage location parameter information, wherein the fourth sorting code body includes one of the second sorting code body, the candidate sorting code body, and the target sorting code body; Using a preset batch picking time function and the corresponding storage location parameter, a first picking time corresponding to each picking batch is calculated, and a total picking time corresponding to the fourth sorting code body is calculated through a preset minimum total picking time function and the corresponding first picking time. According to the total picking time, an order picking total completion time corresponding to the fourth sorting code body and a minimum picker work balance parameter are respectively calculated by using a preset order picking completion time function and a picking batch picking completion time standard deviation function in sequence; Based on the total picking time, the order picking total completion time and the minimum picker work balance parameter, the fitness corresponding to the fourth sorting code body is calculated.

7. The method of claim 6, wherein, The first sorting time corresponding to the sorting batch is calculated using the following formula : ； The corresponding total picking time is calculated using the following formula: ; The order picking total completion time corresponding to the fourth sorting code body is calculated by using the following formula: ； The minimum picker work balance parameter corresponding to the fourth sorting code body is calculated by using the following formula: ； Where j represents the j-th picking order, j∈{1,2,…,J}, J represents the picking order set, and s i Indicates the sth i SKU, s i b ∈ {1,2,…,S}, where S represents the SKU set, b represents the b-th picking batch, b ∈ {1,2,…,B}, where B represents the picking batch set; D represents the target seeding wall position, c s1,s2 c represents the shortest path length between the positions of the s1-th SKU and the s2-th SKU, which is a known value. s Let V represent the path length between the location of the s-th SKU and the target seeding wall, and let V represent the walking speed of the picker. This represents the picking time for the b-th picking batch. This represents the potential waiting time for the b-th picking batch during the sorting process. This indicates the picking order of SKUs in the b-th picking batch; This indicates whether the s-th SKU in the j-th picking order is the first SKU picked in the b-th picking batch. If it is, =1, otherwise, =0, This indicates whether the s-th SKU in the j-th picking order is the last SKU picked in the b-th picking batch. If it is, =1, otherwise, =0, This indicates whether the j-th picking order was partially or completely picked in the b-th picking batch. If so, =1, otherwise, =0.

8. The method of claim 1, wherein, Before selecting the target sorting code body, the method further comprises: determining whether the fitness corresponding to the sorting code body after the current iteration is greater than a preset fitness threshold; in a case where it is determined that the fitness corresponding to the sorting code body is greater than the preset fitness threshold, the sorting code body is taken as the candidate sorting code body; from the multiple candidate sorting code bodies, the candidate sorting code body with the maximum fitness is selected to obtain the target sorting code body. 9.A service platform, comprising a memory and a processor, characterized in that, The computer program is stored in the memory, and the processor is configured to execute the computer program to perform the steps of the picking sorting decision method considering the capacity of the seeding wall according to any one of claims 1 to 8.

10. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the picking sorting decision method considering the capacity of the seeding wall according to any one of claims 1 to 8.

Images