Picking and replenishment linkage decision-making method and service platform considering ergonomic risks

Abstract

The present application relates to a picking and replenishment linkage decision-making method and service platform that considers ergonomic risks. The method includes: after obtaining aggregated bill of materials information and storage location information from a replenishment picking data stream, encoding is performed according to first to-be-replenished material quantity information, the aggregated bill of materials information, and the storage location information corresponding to the aggregated bill of materials information to generate a first dual-coded population including first dual-coded individuals; according to non-dominated solution parameters and target congestion corresponding to the first dual-coded individuals, a target selection operation corresponding to the NSGA-II algorithm is performed on the first dual-coded population to obtain candidate dual-coded individuals; a target genetic operation corresponding to the NSGA-II algorithm is performed on all candidate dual-coded individuals, and the target selection operation and the target genetic operation are repeatedly performed on all candidate dual-coded individuals generated after the target genetic operation is completed until a target dual-coded population is generated that includes at least target dual-coded individuals whose individual fitness is less than a preset fitness threshold.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing and smart logistics technology, in particular to a picking and replenishment linkage decision-making method and service platform that takes ergonomic risks into consideration. Background Art

[0002] In related technologies, large-scale customized production is adopted to meet the new business model of multi-variety and small-batch production. At the same time, in related technologies, the vendor managed inventory model (VMI) and the kitting model (Kitting) are also adopted to solve the problems in customized production. That is, the material demand information is sent to the VMI warehouse, and the VMI warehouse is responsible for transporting the materials to the production workshop. The workshop workers then replenish the materials to the shelves in the picking area. The picking workers then pick all the parts required to assemble a product into a material box, and complete the delivery of materials in the form of material boxes, thereby reducing the assembly workers' material retrieval time and error rate.

[0003] In the related technologies, technical solutions for picking and replenishment based on the VMI model usually focus on solving a single problem. However, in the mass customized production model, since picking and replenishment problems are handled sequentially or in isolation, the analysis is not extended to include the collaborative optimization of picking and replenishment operations, and their effectiveness is limited. At the same time, in the related technologies, existing technical solutions for picking and replenishment focus on the systematization of operations, which leads to suboptimal resource utilization and increases ergonomic risks for employees, affecting their work efficiency and physical and mental burden.

[0004] Currently, there is no effective solution to the problems of picking-replenishment collaborative decision-making in large-scale customized production workshops, which may lead to insufficient adaptability to dynamic customized orders, complex picking-replenishment operations under customized requirements, and increased ergonomic risks. Summary of the Invention

[0005] The embodiments of the present application provide a method and service platform for coordinated decision-making for picking and replenishment that takes ergonomic risks into consideration, thereby at least resolving the problems of related technologies in relation to coordinated picking and replenishment decision-making in large-scale customized production workshops, such as insufficient adaptability to dynamic customized orders, complex picking and replenishment operations under customized requirements, and increased ergonomic risks.

[0006] In a first aspect, an embodiment of the present application provides a method for decision-making in linkage between picking and replenishment that considers ergonomic risks, comprising: after obtaining aggregate bill of materials information and storage location information corresponding to a target set picking area from an acquired replenishment picking data stream, determining the quantity of first materials to be replenished corresponding to a current wave order according to the aggregate bill of materials information, and performing replenishment picking linkage encoding on the first materials to be replenished, the aggregate bill of materials information, and the storage location information to generate a first dual-coded population, wherein the first dual-coded population includes a plurality of first dual-coded individuals; performing a target selection operation corresponding to a preset NSGA-II algorithm on the first dual-coded population according to non-dominated solution parameters and target congestion corresponding to the first dual-coded individuals to obtain candidate dual-coded individuals, wherein the non-dominated solution parameters are based on the individual fitness corresponding to the first dual-coded individuals, A non-dominated sorting is performed, wherein the individual fitness includes parameters of the following two dimensions: total replenishment picking operation time and picking ergonomic risk score; the target congestion is calculated based on the total replenishment picking operation time and the picking ergonomic risk score corresponding to the first dual-coded individuals in the same non-dominated layer; a target genetic operation corresponding to the NSGA-II algorithm is performed on all the candidate dual-coded individuals, and the target selection operation and the target genetic operation are repeatedly performed on all candidate dual-coded individuals generated after completing the target genetic operation until a target dual-coded population including at least the target dual-coded individual is generated, thereby obtaining a decision result including the target dual-coded individual, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold, and the target genetic operation includes partial mapping crossover and random mutation.

[0007] In a second aspect, an embodiment of the present application provides a service platform including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the picking and replenishment linkage decision-making method considering ergonomic risks as described in the first aspect.

[0008] In a third aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the picking and replenishment linkage decision-making method considering ergonomic risks as described in the first aspect above are implemented.

[0009] Compared to related technologies, the picking and replenishment linkage decision-making method, device, service platform, and storage medium provided in the embodiments of the present application consider ergonomic risks. After obtaining aggregated bill of materials information and storage location information corresponding to a target set picking area from an acquired replenishment picking data stream, the first to-be-replenished material quantity information corresponding to the current wave order is determined based on the aggregated bill of materials information, and the first to-be-replenished material information, the aggregated bill of materials information, and the storage location information are subjected to replenishment picking linkage coding to generate a first dual-coded population, wherein the first dual-coded population includes multiple first dual-coded individuals; based on non-dominated solution parameters and target congestion corresponding to the first dual-coded individuals, a target selection operation corresponding to a preset NSGA-II algorithm is performed on the first dual-coded population to obtain candidate dual-coded individuals, wherein the non-dominated solution parameters are generated by non-dominated sorting based on the individual fitness corresponding to the first dual-coded individuals, and the individual fitness includes parameters in the following two dimensions: total replenishment picking operation time and picking ergonomic risk score. The target congestion is calculated based on the total replenishment picking operation time and the picking ergonomic risk score corresponding to the first dual-coded individuals in the same non-dominated layer; a target genetic operation corresponding to the NSGA-II algorithm is performed on all the candidate dual-coded individuals, and the target selection operation and the target genetic operation are repeatedly performed on all the candidate dual-coded individuals generated after completing the target genetic operation until a target dual-coded population including at least a target dual-coded individual is generated, and a decision result including the target dual-coded individual is obtained, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold, and the target genetic operation includes partial mapping crossover and random mutation. This solves the problems of insufficient adaptability to dynamic customized orders, complex picking-replenishment operations under customized requirements, and increased ergonomic risks in the related art for picking-replenishment linkage decisions in large-scale customized production workshops, thereby achieving high-efficiency, low-ergonomic-risk material delivery, promoting agile operation of production workshops, and improving production efficiency.

[0010] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute 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:

[0012] Figure 1 This is a hardware structure block diagram of a terminal for a method for coordinated decision-making in picking and replenishment considering ergonomic risks according to an embodiment of the present application;

[0013] Figure 2 is a flow chart of a method for coordinated decision-making for picking and replenishment considering ergonomic risks according to an embodiment of the present application;

[0014] Figure 3 This is a structural block diagram of a picking and replenishment linkage decision-making device that takes into account ergonomic risks according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by persons of ordinary skill in the art without making any creative work are within the scope of protection of the present application. In addition, it is also understandable that although the efforts made in this development process may be complex and lengthy, for persons of ordinary skill in the art related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are merely conventional technical means and should not be understood as meaning that the contents disclosed in the present application are insufficient.

[0016] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0017] Unless otherwise defined, technical or scientific terms used in this application shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this application belongs. The use of "a," "an," "an," "the," and similar expressions in this application does not denote a limitation of quantity and may refer to either the singular or the plural. The terms "comprise," "include," "have," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or modules (units) is not limited to the listed steps or units but may also include steps or units not listed, or may include other steps or units inherent to the process, method, product, or device. As used in this application, "multiple steps" means two or more steps. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" may mean: A exists alone, A and B exist simultaneously, or B exists alone. The terms "first," "second," and "third," etc., as used in this application, simply distinguish similar objects and do not imply a specific ordering of the objects.

[0018] Before describing the embodiments of the present application, the relevant terms involved in the embodiments of the present application are explained as follows:

[0019] Manufacturing system: refers to the collection of various workstations and related processes used to assemble products.

[0020] Vendor managed inventory: refers to an inventory management method in which the upstream enterprise in the supply chain actively manages and controls the inventory of downstream enterprises based on the demand plan, sales information and inventory level of the downstream enterprises in accordance with the agreement reached between the two parties.

[0021] Bill of Materials: A list of all subassemblies, intermediate parts, parts, and raw materials that make up a parent assembly, including the quantity of each sub-item required for assembly.

[0022] Inventory Management Unit: refers to the unique identifier of different products or commodities in inventory management.

[0023] Ergonomics: refers to the science that studies the relationship between the three major elements of the "man-machine-environment" system, namely man, machine, and environment, and provides theories and methods for solving the performance and health problems of people in the system.

[0024] Ergonomic risks: refers to factors in the working environment that may cause harm to human health and safety.

[0025] Full set picking: refers to obtaining material requirements based on order information and product BOM table, and picking materials in quantities that just meet product production needs.

[0026] Mass customization: refers to a production method that provides customized products and services based on customers' personalized needs through low cost, high quality and efficiency of large-scale production.

[0027] Production-logistics linkage: refers to the seamless connection and efficient collaboration between production activities and logistics activities.

[0028] The following describes the embodiments of the present application with reference to the accompanying drawings:

[0029] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 This is a hardware structure block diagram of the terminal of the picking and replenishment linkage decision method considering ergonomic risks in the embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. A person skilled in the art will understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0030] Memory 104 can be used to store computer programs, such as application software programs and modules, such as the computer program corresponding to the method for coordinated decision-making regarding picking and replenishment that considers ergonomic risks in the embodiments of the present invention. Processor 102 executes the computer programs stored in memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned method. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located from processor 102, which can be connected to terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] Transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of terminal 10. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] This embodiment provides a method for decision-making on picking and replenishment linkage that takes into account ergonomic risks and runs on the above-mentioned terminal. Figure 2 is a flow chart of a method for decision-making in linkage between picking and replenishment considering ergonomic risks according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0033] Step S201, after obtaining the aggregate material list information and the storage location information corresponding to the target set picking area from the acquired replenishment picking data stream, determine the first material quantity information to be replenished corresponding to the current wave order based on the aggregate material list information, and perform replenishment picking linkage coding on the first material information to be replenished, the aggregate material list information and the storage location information to generate a first double-coded population, wherein the first double-coded population includes multiple first double-coded individuals.

[0034] In this embodiment, the execution entity for executing the coordinated decision of picking and replenishment of the embodiment of the present application is an associated preset Vendor Managed Inventory (VMI) system, and the replenishment picking data stream is obtained from the VMI system; after receiving several customer orders, the VMI system will interpret each customer order to determine the corresponding customer order bill of materials, and then reprocess the customer order bill of materials to generate multiple aggregate bills of materials. At the same time, the VMI system also stores the storage location information corresponding to the target set picking area (that is, the corresponding shelf and the shelf location information set on the shelf); in this embodiment, after obtaining the replenishment picking data stream, the replenishment picking data stream is interpreted to obtain the replenishment material quantity for large-scale customized production corresponding to the current coordinated decision to meet the production demand of the current wave; in this embodiment, a replenishment decision is first made to replenish the goods to the corresponding shelf location of the target set picking area based on the replenishment material quantity, that is, the corresponding replenishment material quantity (all materials required to meet the production of the current wave order) is transported to the target set picking area, and then, based on the replenishment material quantity, the replenishment material quantity is transported to the target set picking area. Based on the replenishment decision information placed in the target complete picking area, a picking decision is made, that is, all materials contained in the target product that meets the production needs of the customer order are picked accordingly, that is, the picking decision information of the picking order in which the picking object starts from the picking platform, walks to the corresponding storage location to pick, and then returns to the picking platform. One piece of picking decision information corresponds to the arrangement of the picking order of materials contained in one target product, and also corresponds to a picking path for picking multiple materials. In this embodiment, the decision result of the picking and replenishment linkage decision includes replenishment decision information and picking decision information, and in the decision iteration process, the replenishment decision information is first generated, and then the picking decision information is decided based on the generated replenishment decision information. By continuously optimizing the linkage decision during the decision iteration process, the replenishment decision information that achieves the preset target (optimal in terms of non-dominated sorting and congestion, and the non-dominated sorting and congestion are both determined by the total operation time of replenishment picking and the ergonomic risk score) is generated.

[0035] In this embodiment, each first double-coded individual includes a replenishment code individual with multiple cargo location allocation codes and a picking code individual with multiple picking sub-codes, wherein a cargo location allocation code is used to represent the replenishment location information allocated to a material, and the position of a cargo location allocation code in the replenishment code individual indicates the material number of the corresponding material, that is, which material it is. For example, the corresponding material numbers of the materials to be replenished are set to: 1, 2, 3, 4. When replenishing, material 1 is allocated to cargo location 10, material 2 is allocated to cargo location 5, material 3 is allocated to cargo location 18, and material 4 is allocated to cargo location 3. Then the corresponding replenishment code individual is

[10] [5]

[18] [3]; a picking sub-code The code body is used to represent the picking decision information for picking multiple materials corresponding to a target product. The position of a picking sub-code body in the picking code individual represents the model or product type of the target product corresponding to the picking sub-code body. For example, the second picking sub-code body in the picking code individual corresponds to the picking sub-code body corresponding to the second target product; a picking sub-code body includes multiple picking codes, and a picking code of the picking sub-code body corresponds to a cargo location allocation code corresponding to a material to be picked. The sorting of the picking codes in the picking sub-code body represents the order in which the corresponding materials are picked. The picking codes are arranged in the order of the cargo locations that the picking object needs to visit when completing the picking of a target product. In this embodiment, the picking station and the cargo location are coded with non-repeating natural numbers. Since the picking object starts from the picking station and returns to the picking station after picking, the picking codes corresponding to the picking station are 0 and J+1, J represents the type of material corresponding to a target product, and the picking codes corresponding to the cargo location are 1 to J. The gene length of a picking code individual is set to be equal to the number of target products required in the order corresponding to the aggregated picking material list information × (the types of different materials required for a target product + 2). For example: the picking order for multiple materials of target product 1 is set to: cargo location 5, cargo location 18, cargo location 7, cargo location 10, then a picking sub-code body is set to [0][5]

[18] [7]

[10] [2 5][0]. In this embodiment, during the encoding process, the picking coding individual is coded for the cargo location numbered 0 between two adjacent picking sub-coding bodies (corresponding to returning to the picking platform), and the cargo location allocation code at the end of the previous picking sub-coding body is omitted. For example, the picking order of multiple materials of target product 2 is set to: cargo location 8, cargo location 7, cargo location 16, cargo location 25, and the picking sub-coding body corresponding to the target product 2 is set to [0][8][7]

[16]

[25] [0]. Then the picking coding individual consisting of target product 1 and target product 2 is [0][5]

[18] [7]

[10]

[25] [0][8][7]

[16]

[25] .

[0036] In step S202, based on the non-dominated solution parameters and target congestion corresponding to the first dual-coded individual, a target selection operation corresponding to the preset NSGA-II algorithm is performed on the first dual-coded population to obtain candidate dual-coded individuals. The non-dominated solution parameters are generated by non-dominated sorting based on the individual fitness corresponding to the first dual-coded individual. The individual fitness includes parameters of the following two dimensions: total replenishment picking operation time and picking ergonomic risk score. The target congestion is calculated based on the total replenishment picking operation time and picking ergonomic risk score corresponding to the first dual-coded individuals in the same non-dominated layer.

[0037] In this embodiment, after the initial population (corresponding to the first dual-coded population) is generated, the individual fitness of each first dual-coded individual in the initial population is calculated in two dimensions. In this embodiment, the individual fitness of the two dimensions corresponding to the first dual-coded individual includes the total replenishment picking operation time and the picking ergonomic risk score. In this embodiment, after determining the individual fitness corresponding to each first dual-coded individual, the first dual-coded population is sorted by non-dominated solutions based on the total replenishment picking time and the picking ergonomic risk score in the individual fitness to obtain the corresponding non-dominated solution parameters. It can be understood that the sorting of non-dominated solutions based on the NSGA-II algorithm performed in this embodiment is known and clear to those skilled in the art and does not constitute an unclear limitation of the present application. At the same time, in this embodiment, after calculating the individual fitness of each individual in the two dimensions, the crowding distance of each individual under the non-dominated solution is calculated, and the difference in the total replenishment picking time and the difference in the picking ergonomic risk score between individuals in the same non-dominated layer are calculated respectively. Then, the differences in the individual fitness of the two dimensions are accumulated to obtain the target crowding degree corresponding to each individual.

[0038] In this embodiment, a preset number of first dual-coded individuals are randomly selected from the first dual-coded population, and then the optimal individual is selected (target selection operation is performed) based on the comparison between the non-dominated solution parameter and the target congestion degree, that is, a preset number of candidate dual-coded individuals are obtained.

[0039] Step S203: Perform a target genetic operation corresponding to the NSGA-II algorithm on all candidate dual-coded individuals, and repeat the target selection operation and the target genetic operation on all candidate dual-coded individuals generated after the target genetic operation is completed, until a target dual-coded population including at least the target dual-coded individual is generated, and a decision result including the target dual-coded individual is obtained, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold, and the target genetic operation includes partial mapping crossover and random mutation.

[0040] In this embodiment, after all candidate dual-coded individuals are obtained, a crossover operation and mutation operation corresponding to the NSGA-II algorithm are performed to complete a genetic operation. After that, a target selection operation based on the non-dominated solution parameters and target congestion of the corresponding individual and a corresponding target genetic operation are performed to generate the corresponding dual-coded individuals. Then, after a preset number of iterations or when the individual fitness corresponding to each dual-coded individual converges, a target dual-coded population including the target dual-coded individual is obtained. After obtaining the target dual-coded population, the dual-coded individual with the best individual fitness is selected from the target dual-coded population to obtain the corresponding target dual-coded individual. Then, the replenishment decision information and picking decision information interpreted from the target dual-coded individual are used to generate the corresponding decision result.

[0041] Through the above steps S201 to S203, after obtaining the aggregate material list information and the storage location information corresponding to the target set picking area from the acquired replenishment picking data stream, the first material quantity information to be replenished corresponding to the current wave order is determined according to the aggregate material list information, and the first material information to be replenished, the aggregate material list information and the storage location information are subjected to replenishment picking linkage coding to generate a first double-coded population, wherein the first double-coded population includes multiple first double-coded individuals; according to the non-dominated solution parameters and target congestion corresponding to the first double-coded individuals, the first double-coded population is subjected to a target selection operation corresponding to the preset NSGA-Ⅱ algorithm to obtain candidate double-coded individuals, wherein the non-dominated solution parameters are generated by non-dominated sorting based on the individual fitness corresponding to the first double-coded individuals, and the individual fitness includes parameters of the following two dimensions: total replenishment picking operation time and picking ergonomic risk score, and the target congestion is determined based on the individual fitness of the individuals in the same non-dominated order. The total replenishment picking operation time and the picking ergonomic risk score corresponding to the first dual-coded individual in the dominant layer are jointly calculated; the target genetic operation corresponding to the NSGA-Ⅱ algorithm is performed on all candidate dual-coded individuals, and the target selection operation and the target genetic operation are repeatedly performed on all candidate dual-coded individuals generated after the target genetic operation is completed, until a target dual-coded population including at least the target dual-coded individual is generated, and a decision result including the target dual-coded individual is obtained, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold. The target genetic operation includes partial mapping crossover and random mutation, which solves the problems of insufficient adaptability of dynamic customized orders, complex picking-replenishment operations under customized needs, and increased ergonomic risks in the related technologies for the picking-replenishment linkage decision-making of large-scale customized production workshops, so as to achieve high-efficiency and low-ergonomic-risk material delivery, promote the agile operation of production workshops and improve production efficiency.

[0042] It should be noted that the embodiments of the present application break through the bottlenecks of low adaptability to dynamic customized orders under the large-scale customized production model, complex picking-replenishment operations under customized needs, and increased ergonomic risks. In a manufacturing environment where the operation process is transparent and traceable, starting from the underlying interactive logic and overall operation mechanism of picking-replenishment, considering the balance between ergonomic risks and operational efficiency, a linkage decision-making method is proposed to achieve high-efficiency, low-ergonomic-risk material delivery, and promote the agile operation and development of production workshops.

[0043] In some embodiments, the first to-be-replenished material information, the aggregated material list information, and the storage location information are coded for replenishment and picking linkage to generate a first double-coded population, which is achieved by the following steps:

[0044] Step 21: Acquire multiple target materials corresponding to the first material to be replenished information, and determine the storage codes of all storage locations based on the storage location information.

[0045] Step 22: Based on the golden storage location allocation strategy, multiple target materials and storage codes are integer-coded to generate a storage location allocation code corresponding to the replenishment storage location information allocated to each target material.

[0046] Step 23: Determine the multiple picking materials corresponding to the target product associated with the aggregate bill of materials. From all shelf allocation codes, select the shelf allocation codes corresponding to the multiple picking materials corresponding to each target product according to the picking order divided by the codes. Perform integer encoding on all selected shelf allocation codes to obtain a picking sub-code corresponding to one target product. The order of the shelf allocation codes in the corresponding picking sub-code represents the order in which the corresponding picking materials are picked. The picking sub-code is also used to represent the picking decision information for picking the multiple picking materials corresponding to one target product.

[0047] Step 24, after encoding all the cargo location allocation codes and generating replenishment code individuals, encode all the picking sub-code entities to generate picking code individuals, encode the replenishment code individuals and the picking code individuals into the first double-coded individuals, and initialize the population of the first double-coded individuals to generate the first double-coded population.

[0048] In this embodiment, each element in the replenishment code individual corresponds to a material code, the value of a shelf allocation code indicates the shelf number to which the material is assigned, a shelf allocation code is used to represent the replenishment location information assigned to a material, and the position of a shelf allocation code in the replenishment code individual indicates the material number of the corresponding material, that is, which material it indicates. For example, the material numbers corresponding to the materials to be replenished are set to: 1, 2, 3, 4. When replenishing, material 1 is assigned to shelf 10, material 2 is assigned to shelf 5, material 3 is assigned to shelf 18, and material 4 is assigned to shelf 3. The corresponding replenishment code individual is

[10] [5]

[18] [3].

[0049] In this embodiment, starting from the entrance of the shelf, assuming there are S shelves, with M rows and N layers, the shelves are numbered in the order of shelf, row, and layer to generate the following shelf number table 1:

[0050] Table 1

[0051]

[0052] In this embodiment, after the shelf locations are numbered, the material numbers and shelf location numbers are mapped one-to-one to generate corresponding shelf location allocation codes and replenishment code individuals; at the same time, when processing shelf location allocation, an adjustment mechanism is set to check and adjust duplicate or out-of-bounds shelf location numbers to ensure that all allocated shelf location numbers are unique and within the valid range, that is, each material is eventually allocated to a valid, unoccupied shelf location.

[0053] In this embodiment, a picking code of the picking sub-code body of the picking code individual represents a cargo location number. The cargo location numbers are arranged in the order of the cargo locations that the picking object needs to visit when completing the picking of all materials of a target product, and a corresponding picking sub-code body is generated. When arranging the order of the picked cargo locations, the picking platform and the cargo locations are coded as non-repeating natural numbers. Because the picking object starts from the picking platform and returns to the picking platform after picking, the picking codes corresponding to the picking platform are 0 and J+1, J represents the type of material corresponding to a target product, and the picking codes corresponding to the cargo locations are 1 to J. The gene length of a picking code individual is set to be equal to the number of target products required in the order corresponding to the aggregated picking material list information × (the types of different materials required for a target product + 2). For example: the picking order for multiple materials of target product 1 is set to: cargo location Position 5, position 18, position 7, position 10, then a picking sub-coding body is set to [0][5]

[18] [7]

[10]

[25] [0]. In this embodiment, during the encoding process, the picking coding individual is assigned a code to the cargo position numbered 0 between two adjacent picking sub-coding bodies (corresponding to returning to the picking platform), and a cargo position assignment code is omitted at the end of the previous picking sub-coding body. For example: the picking order of multiple materials of target product 2 is set to: cargo position 8, cargo position 7, cargo position 16, cargo position 25, and the picking sub-coding body corresponding to the target product 2 is set to [0][8][7]

[16]

[25] [0], then the picking coding individual consisting of target product 1 and target product 2 is [0][5]

[18] [7]

[10]

[25] [0][8][7]

[16]

[25] .

[0054] Through the above steps 21 to 24, the replenishment and picking linkage coding is realized according to the first material information to be replenished, the aggregate material list information and the storage location information, and the initial coding population is generated, providing a data basis for subsequent population iteration. At the same time, through coding and population initialization, the information of the material to be replenished and the storage location information of the complete picking area are associated, providing data for the generation of replenishment decision information and picking decision information.

[0055] It should be noted that, in this embodiment, each first double-coded individual includes a storage location allocation and picking order decision plan. The decision plan is generated based on the golden storage location allocation strategy, which prioritizes placing materials with high demand frequency in easily accessible locations to reduce picking time and improve efficiency.

[0056] In some embodiments, iterating over the population is performed by:

[0057] Step 31, determining the second dual-coded individual of the current decision iteration, wherein the second dual-coded individual includes one of the following: the first dual-coded individual, and the candidate dual-coded individual generated after completing the target genetic operation corresponding to the previous decision iteration.

[0058] In this embodiment, when the second dual-coded individual is the first dual-coded individual, it means that the genetic evolution processing based on the NSGA-Ⅱ algorithm is performed based on the initial dual-coded population; when the second dual-coded individual is the alternative dual-coded individual, it means that the genetic evolution processing based on the NSGA-Ⅱ algorithm is performed based on the non-initial dual-coded population.

[0059] Step 32 : determining the non-dominated layer corresponding to each second dual-coded individual according to the non-dominated solution parameter corresponding to each second dual-coded individual, and determining the target congestion degree corresponding to each second dual-coded individual in the same non-dominated layer.

[0060] In this embodiment, the second dual-coded population is divided into different non-dominated layers according to the fitness values of the individuals (including the total replenishment operation time and the picking ergonomic risk score). The first-layer individuals are removed from the second dual-coded population. If the remaining individuals are not empty, the layer assignment is repeated for the remaining individuals and the individual's level and dominance counter are updated. Then, the first-layer individuals are continued to be removed from the population. The cycle ends until the remaining individuals are empty, and the non-dominated frontier of each layer is output.

[0061] In this embodiment, the crowding distance is calculated for each second dual-coded individual in the non-dominated layer. The difference between the second dual-coded individual and its adjacent individuals is calculated based on either the total replenishment operation time or the picking ergonomic risk score. Then, the differences in the two dimensions of total replenishment operation time and picking ergonomic risk score are accumulated (normalization is used in the accumulation process) to obtain the total crowding degree corresponding to each second dual-coded individual, that is, the target crowding degree. It can be understood that the target crowding degree reflects the distribution uniformity of the solution (a second dual-coded individual). The higher the crowding degree, the sparser the solution is, which is conducive to maintaining the diversity of the population and ensuring the uniform distribution of the Pareto front.

[0062] Step 33: Based on the non-dominated layer and target congestion of the second dual-coded individuals, a tournament selection method is used to select a preset number of second dual-coded individuals from the plurality of second dual-coded individuals to obtain a plurality of third dual-coded individuals. The third dual-coded individuals include one of the following: candidate dual-coded individuals and alternative dual-coded individuals generated after completing the current decision iteration.

[0063] In this embodiment, a tournament selection method is used to randomly select N second dual-coded individuals, and their non-dominated layers and crowding distances are compared to select the best N individuals. In this embodiment, a binary tournament selection method is used to select two corresponding individuals from the second dual-coded population. The non-dominated layers to which the two corresponding individuals belong are preferentially compared, and the one with the higher ranking is selected. When the non-dominated layer rankings are consistent, the target crowding degrees are compared, and the one with the higher target crowding degree is selected. This process is repeated N times to obtain the N best individuals.

[0064] Through the above steps 31 to 33, the selection operation is performed on the population of the current iteration, thereby selecting the best individual.

[0065] In some embodiments, based on the non-dominated layer and target congestion of the second dual-coded individuals, a tournament selection method is used to select a preset number of second dual-coded individuals one by one from a plurality of second dual-coded individuals, which is achieved by the following steps:

[0066] Step 41 : using the tournament selection method, randomly select two second dual-coded individuals from multiple second dual-coded individuals to obtain intended dual-coded individuals, and determine whether the two intended dual-coded individuals are in the same non-dominated layer.

[0067] In step 42, when it is determined that the two intended dual-coded individuals are in the same non-dominated layer, the intended dual-coded individual with the highest target congestion is used as the corresponding third dual-coded individual. When it is determined that the two intended dual-coded individuals are not in the same non-dominated layer, the intended dual-coded individual with a higher non-dominated layer is used as the corresponding third dual-coded individual.

[0068] Step 43 , repeatedly performing the operations of selecting two intended dual-coded individuals using the tournament selection method and selecting a corresponding third dual-coded individual from the two corresponding intended dual-coded individuals, until a preset number of third dual-coded individuals are obtained.

[0069] Through the above steps 41 to 43, the selection of individuals based on the tournament selection method is realized, providing data for performing the target genetic operation corresponding to the NSGA-II algorithm and solving the optimal solution.

[0070] In some embodiments, after obtaining a plurality of third double-coded individuals, the following steps are further performed:

[0071] In step 51, two third double-coded individuals randomly obtained from multiple third double-coded individuals are used as the parent double-coded individuals currently being processed, and the replenishment coded individuals and picking coded individuals corresponding to the two parent double-coded individuals are obtained to obtain two candidate parent replenishment coded individuals and two candidate parent picking coded individuals.

[0072] Step 52: Divide all the cargo location allocation codes corresponding to the candidate parent replenishment code individuals into a first cross cargo location code group and a first mapping cargo location code group, and combine the first mapping cargo location code group of a corresponding candidate parent replenishment code individual with the first cross cargo location code group of another corresponding candidate parent replenishment code individual to generate two candidate child replenishment code individuals, and randomly mutate all the cargo location allocation codes of the candidate child replenishment code individuals to generate new child replenishment code individuals.

[0073] Step 53, after selecting the picking sub-coding bodies corresponding to multiple target products from all the picking sub-coding bodies of the two candidate parent picking coding individuals, divide all the storage location allocation codes of the two picking sub-coding bodies corresponding to each target product into a second cross storage location code group and a second mapping storage location code group, and combine the second mapping storage location code group corresponding to one of the two picking sub-coding bodies with the second cross storage location code group corresponding to the other picking sub-coding body to generate two new picking sub-coding bodies corresponding to the corresponding target products, and combine all the new picking sub-coding bodies corresponding to the candidate parent picking coding individuals with the unselected picking sub-coding bodies to generate a new child picking coding individual corresponding to the corresponding candidate parent picking coding individual.

[0074] In this embodiment, a partially mapped crossover (PMX) operator is used to perform a crossover operation on the candidate parent replenishment coded individuals and the candidate parent picking coded individuals of each parent dual-coded individual. It can be understood that the partial mapping method using the PMX operator is to exchange part of the genes of the two parent individuals into the offspring, construct a mapping relationship of the exchanged genes, and replace the offspring code according to the mapping relationship while maintaining the relative order between the genes.

[0075] In this embodiment, a partial mapping crossover operation is performed on the candidate parent replenishment code individuals of the parent double-coded individuals, and random mutation is used to randomly mutate all the cargo location allocation codes of the candidate child replenishment code individuals, that is, a certain cargo location allocation code of the candidate parent replenishment code individuals is randomly changed with a certain probability for mutation, for example: the replenishment code individuals coded as

[10] [5]

[18] [3] are randomly mutated to generate the replenishment code individuals of

[10]

[25]

[18] [3]; it should be noted that the random mutation operator obeys the boundary constraints. During the mutation process, any new cargo location number is generated by random selection within the valid range, ensuring that the newly allocated cargo location number does not exceed the preset cargo location range. In addition, if the newly generated cargo location number is occupied, it is necessary to find an unoccupied valid cargo location number to replace it, so as to ensure the feasibility of the replenishment decision.

[0076] Step 54: After the new offspring replenishment coded individuals and the corresponding new offspring picking coded individuals are combined into a new offspring dual-coded individual corresponding to the third dual-coded individual, all new offspring dual-coded individuals and all third dual-coded individuals are merged into a candidate dual-coded population, and based on the non-dominated layers and target congestion of all fourth dual-coded individuals corresponding to the candidate dual-coded population, a preset number of fourth dual-coded individuals are selected one by one using the tournament selection method to obtain a new dual-coded population corresponding to the current decision iteration, and the dual-coded individuals of the new dual-coded population are used as the dual-coded individuals generated after completing the current decision iteration.

[0077] In this embodiment, after performing selection, crossover, and mutation operations on the population to generate new offspring individuals, the parent dual-coded individuals and the new offspring are merged to form a corresponding population. Then, from the merged population (the number of individuals is twice the number of the set population), a tournament selection is performed using the non-dominated layer and target crowding degree of each individual to obtain the next generation population that matches the number of individuals in the set population, that is, the new dual-coded population.

[0078] Through the above steps 51 to 54, genetic selection, genetic crossover and genetic mutation operations are implemented on the dual-coding population in each iteration, and the next generation population is generated.

[0079] In some embodiments, before determining the non-dominated layer corresponding to each second dual-coded individual according to the non-dominated solution parameter corresponding to each second dual-coded individual, the following steps are further performed:

[0080] Step 61: Obtain the total replenishment picking operation time and picking ergonomic risk score corresponding to the second double-coded individual.

[0081] In this embodiment, the picking ergonomic risk score is determined by using a preset ergonomic risk assessment method, such as the Rapid Entire Body Assessment (REBA) method, to assess and score the working posture.

[0082] Step 62 , respectively calculating a first difference in the total replenishment picking operation time and a second difference in the picking ergonomic risk score corresponding to any two second dual-coded individuals, and determining whether the first difference and the second difference are less than a preset threshold.

[0083] In step 63 , if it is determined that one of the first difference and the second difference is less than a preset threshold, the two second dual-coded individuals are determined to be in the same non-dominated layer, and the corresponding non-dominated layer is recorded as the non-dominated solution parameters corresponding to the two second dual-coded individuals.

[0084] Through the above steps 61 to 63, the non-dominated solution parameters of the dual-coded individuals of the current iteration are determined, that is, the non-dominated solutions of the individuals in the dual-coded population of the current iteration are sorted, thereby achieving stratification.

[0085] In some embodiments, determining the target congestion degree corresponding to each second dual-coded individual in the same non-dominated layer is achieved by the following steps:

[0086] Step 71 : Select two second dual-coded individuals adjacent to the corresponding second dual-coded individual from all second dual-coded individuals in the same non-dominated layer to obtain a fifth dual-coded individual and a sixth dual-coded individual.

[0087] Step 72: Determine the operation time congestion distance corresponding to the corresponding second dual-coded individual based on the ratio of the third difference in the total supplementary picking operation time corresponding to the fifth dual-coded individual and the sixth dual-coded individual to the first target time difference, and determine the ergonomic risk congestion distance corresponding to the corresponding second dual-coded individual based on the ratio of the fourth difference in the picking ergonomic risk score corresponding to the fifth dual-coded individual and the sixth dual-coded individual to the first target coefficient difference, wherein the first target time difference is the difference between the maximum and minimum values of the total supplementary picking operation time corresponding to all second dual-coded individuals in the same non-dominated layer, and the first target coefficient difference is the difference between the maximum and minimum values of the picking ergonomic risk score corresponding to all second dual-coded individuals in the same non-dominated layer.

[0088] In this embodiment, the third difference or the fourth difference is calculated using the following formula:

[0089]

[0090] represents the crowding distance corresponding to the i-th double-coded individual in the working time crowding distance or the ergonomic risk crowding distance, represents the crowding distance of the mth operation time or the crowding distance of ergonomic risk, It represents the maximum value of the crowding distance or ergonomic risk crowding distance at the mth working time among all double-coded individuals. It represents the minimum value of crowding distance or ergonomic risk crowding distance at the mth working time among all dual-coded individuals.

[0091] Step 73: The sum of the working time crowding distance and the ergonomic risk crowding distance is used as the target crowding degree corresponding to the corresponding second dual-coded individual.

[0092] In some embodiments, after determining the second dual-coded individual for the current decision iteration, the method includes:

[0093] Calculate the corresponding total replenishment picking time PRTT according to the following formula:

[0094]

[0095]

[0096]

[0097] The picking ergonomic risk score PERT is calculated as follows:

[0098]

[0099]

[0100] Calculate the total replenishment picking time (PRTT) and the picking ergonomic risk score (PERT), satisfying the following constraints:

[0101] ; ; ; ; ; ; ; ; ; ; ; ; ; ; ;

[0102] Among them, the target material set is I, I={1,2,…,i,…,|I|}, i represents the i-th target material; the order set corresponding to the aggregate material list is O, O={1,2,…,o,…,|O|}, o represents the o-th aggregate material list; the set of replenishment material arrival waves is W, W={1,2,…,w,…,|W|}, w represents the w-th wave; the replenishment object set is R, R={1,2,…,r,…,|R|}, r represents the r-th replenishment object; the picking object set is B, B={1,2,…,b,…,|B|}, b represents the b-th picking object; the storage location set is J, J={1,2,…,j,…,|J|}, j represents the j-th storage location, and the horizontal coordinate of the storage location is x j , the vertical coordinate of the cargo location is y j , the cargo location coordinates are (x j ,y j , z j ), the target product model set is P, P = {1, 2, …, p, …, |P|}, p represents the model of the p-th target product; h zjIndicates the level where the cargo location is located, h zj ∈{0,1}, if the jth cargo location is on the zth layer of the shelf, h zj =1, otherwise, h zj =0;O op Indicates the quantity of target product p contained in the order corresponding to order O, Indicates whether the target product p requires material i, If the target product p requires material i, ,otherwise ;U pi Indicates the quantity of material i required for the target product p, G ow Indicates whether the wth wave contains the oth order, G ow ∈{0,1}, if the wth wave contains the oth order, G ow =1, otherwise, G ow =0;n oi Indicates the quantity of material i requested in the oth order; C i represents the capacity of a shelf location for item i; M is a large constant; K represents the width of each shelf location; H represents the height of each shelf location; D represents the depth of each shelf location; v1 represents the walking speed of the replenishment object; v2 represents the walking speed of the picking object; x represents the number of shelf rows, y represents the number of shelf columns, and z represents the number of shelf layers; PT z Indicates picking and storing in the The duration of the layer of material, PT z is a preset constant, Indicates picking and storing in the Ergonomic risks of layered materials, is a preset constant; , if the wave is w, material i is assigned to location j, ,otherwise ; Indicates the target product Need to be from the cargo location Picking materials the number of If the target product Need to be from the cargo location Picking materials , ,otherwise ; Indicates whether the target product p needs to be moved from location j1 to location j2. If the target product p needs to be moved from the shelf Move to shelf Selection, ,otherwise ; Indicates the coordinates of the picking platform; T indicates the width of each aisle in the picking configuration area; Indicates storage in the cargo area Picking distance; Indicates that the picking platform arrives at the cargo location Walking time; Represents the coordinates of the replenishment object; Indicates storage in the cargo area Replenishment distance; Indicates the arrival location of the replenishment object Walking time; Indicates the distance between cargo locations or between picking platforms and cargo locations; It represents the walking time between the cargo location and the cargo location or between the picking platform and the cargo location; the picking walking time of the target product p is ;The picking walking time of order o is ;The picking operation time of target product p is ; The ergonomic risk of picking objects at each shelf level is ;The total ergonomic risk of picking the target product p is ; Picking orders The total ergonomic risk is ; Indicates any.

[0103] In this embodiment, if there are materials on the cargo position j in the complete picking area that need to be picked, then the picking distance stored in the cargo position j is is the Euclidean distance from the picking platform to the storage location j, and the walking time from the picking platform to the storage location j Picking distance and the picker's walking speed The corresponding definition formula is: , .

[0104] In this embodiment, since the picking mode is complete set picking, the picking object needs to pick all the materials required for a target product and then return to the picking platform. , in the collection Add the starting point and end point, the distance between the cargo location and the cargo location, and the distance between the picking platform and the cargo location and the walking time between cargo locations and between picking platforms and cargo locations The calculation is similar, and the definition formula is: , .

[0105] In this embodiment, during the replenishment phase, the replenishment distance stored at location j is is the Euclidean distance from the replenisher to the storage location j, and the walking time of the replenisher to the storage location j Picking distance and the picker's walking speed The corresponding definition formula is: , .

[0106] In this embodiment, minimizing the total replenishment picking time PRTT is an optimization goal. The order picking walking time, order picking operation time, and order replenishment walking time in the current wave are important components of the total replenishment picking time PRTT. The corresponding definition formula is:

[0107] Target products Picking travel time: .

[0108] Order Picking travel time: .

[0109] Target products Picking operation time: .

[0110] Order Picking operation time: .

[0111] Minimize the total replenishment picking time PRTT:

[0112] In this embodiment, minimizing the average ergonomic risk PERT is another optimization goal. The ergonomic risk of the picking object and the replenishment object during idle activities (i.e., walking) is not considered. In addition, in comparison, the working posture of the replenishment object is relatively simple and has little variation, while the picking object has a more complex and changeable working posture due to the large amount of picking work. In this embodiment, only the ergonomic risk of the picking object is studied. The total ergonomic risk value of the picking object is determined as the weighted sum of the ergonomic risks of the picking activities, using the duration of its picking operation. As a weight, the average ergonomic risk value is obtained by dividing the total ergonomic risk of the picking order by the total time of the picking operation. The corresponding definition formula is:

[0113] Ergonomic risks of picking objects at each shelf level: .

[0114] Picking products Total ergonomic risk of: .

[0115] Picking orders Total ergonomic risk of: .

[0116] Minimized average ergonomic risks: .

[0117] In this embodiment, material allocation restrictions are defined so that each material can be allocated to a storage location. The corresponding definition formula is: .

[0118] In this embodiment, the storage capacity limit of each storage location is defined. Each storage location can only accommodate one type of material in each wave. The number of materials replenished in each wave does not exceed the storage capacity of each storage location. The storage capacity of each storage location is sufficient to accommodate the picked materials. The corresponding definition formula is: ; ; .

[0119] In this example, we define the quantity requirement limits for product types to ensure that the requirements for each material are met. The corresponding definition formula is: ; .

[0120] In this embodiment, the path selection restrictions for picking objects are defined to ensure that the path of the picking objects is continuous. The picking objects must start from the picking station, arrive at a storage location, pick the items, and then leave to the next storage location for picking. After finishing, they must return to the picking station. The corresponding definition formula is: ; ; ; ; .

[0121] In this embodiment, product picking operation constraints are defined and auxiliary variables are introduced , ensure product Pick the material on location j , the corresponding definition formula is: , .

[0122] In this embodiment, the relationship between the location allocation and the picking order is defined to ensure that only when the product Need to be picked at the location Materials When the corresponding picking order is generated, the corresponding definition formula is: ; .

[0123] In this embodiment, a limit is defined on the number of directed paths between cargo locations to ensure that there can be at most one directed path between two cargo locations. The corresponding definition formula is: .

[0124] This embodiment also provides a picking and replenishment linkage decision-making device that takes ergonomic risks into consideration. The device is used to implement the above-mentioned embodiments and preferred implementation methods, and the details that have been explained will not be repeated here. As used below, the terms "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that implements predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0125] Figure 3 is a structural block diagram of a picking and replenishment linkage decision-making device considering ergonomic risks according to an embodiment of the present application, such as Figure 3 As shown, the device includes an acquisition module 31, a processing module 32 and a decision module 33, wherein:

[0126] The acquisition module 31 is used to obtain the aggregate material list information and the storage location information corresponding to the target set picking area from the acquired replenishment picking data stream, determine the first material quantity information to be replenished corresponding to the current wave order based on the aggregate material list information, and perform replenishment picking linkage coding on the first material information to be replenished, the aggregate material list information and the storage location information to generate a first double-coded population, wherein the first double-coded population includes multiple first double-coded individuals.

[0127] The processing module 32 is coupled to the acquisition module 31 and is configured to perform a target selection operation corresponding to the preset NSGA-II algorithm on the first dual-coded population based on the non-dominated solution parameters and target congestion corresponding to the first dual-coded individual to obtain candidate dual-coded individuals, wherein the non-dominated solution parameters are generated by non-dominated sorting based on the individual fitness corresponding to the first dual-coded individual, and the individual fitness includes parameters of the following two dimensions: total replenishment picking operation time and picking ergonomic risk score. The target congestion is calculated based on the total replenishment picking operation time and picking ergonomic risk score corresponding to the first dual-coded individuals in the same non-dominated layer.

[0128] The decision module 33 is coupled to the processing module 32 and is configured to perform a target genetic operation corresponding to the NSGA-II algorithm on all candidate dual-coded individuals, and repeatedly perform the target selection operation and the target genetic operation on all candidate dual-coded individuals generated after the target genetic operation is completed, until a target dual-coded population including at least the target dual-coded individual is generated, and a decision result including the target dual-coded individual is obtained, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold, and the target genetic operation includes partial mapping crossover and random mutation.

[0129] In some embodiments, the acquisition module 31 further includes:

[0130] The acquisition unit is used to acquire multiple target materials corresponding to the first material to be replenished information, and determine the storage codes of all storage locations according to the storage location information.

[0131] The generating unit is coupled to the acquiring unit and is used to integer encode multiple target materials and storage codes based on the golden storage location allocation strategy, and generate a storage location allocation code corresponding to the replenishment storage location information allocated for each target material.

[0132] The encoding unit is coupled to the generating unit and is used to determine the multiple picking materials corresponding to the target product associated with the aggregate material list, select the storage location allocation codes corresponding to the multiple picking materials corresponding to each target product according to the picking order divided by the codes from all storage location allocation codes, and perform integer encoding on all the selected storage location allocation codes to obtain a picking sub-code body corresponding to a target product, wherein the order of the storage location allocation codes in the corresponding picking sub-code body represents the order in which the corresponding picking materials are picked, and the picking sub-code body is also used to represent the picking decision information for picking the multiple picking materials corresponding to a target product.

[0133] The combination unit is coupled to the encoding unit and is used to encode all the cargo location allocation codes to generate replenishment coding individuals, then encode all the picking sub-coding entities to generate picking coding individuals, encode the replenishment coding individuals and the picking coding individuals into the first double-coding individuals, and initialize the population of the first double-coding individuals to generate the first double-coding population.

[0134] In some embodiments, the linkage decision-making device is further used to determine a second dual-coded individual for the current decision iteration, wherein the second dual-coded individual includes one of the following: a first dual-coded individual, or a candidate dual-coded individual generated after completing the target genetic operation corresponding to the previous decision iteration; determining a non-dominated layer corresponding to the second dual-coded individual based on the non-dominated solution parameter corresponding to each second dual-coded individual, and determining a target crowding degree corresponding to each second dual-coded individual in the same non-dominated layer; based on the non-dominated layer and the target crowding degree of the second dual-coded individual, using a tournament selection method, selecting a preset number of second dual-coded individuals one by one from the plurality of second dual-coded individuals to obtain a plurality of third dual-coded individuals, wherein the third dual-coded individual includes one of the following: a candidate dual-coded individual, or a candidate dual-coded individual generated after completing the current decision iteration.

[0135] In some embodiments, the linkage decision-making device is further used to randomly select two second dual-coded individuals from multiple second dual-coded individuals using a tournament selection method to obtain intended dual-coded individuals, and determine whether the two intended dual-coded individuals are in the same non-dominated layer; when it is determined that the two intended dual-coded individuals are in the same non-dominated layer, the intended dual-coded individual with the largest target congestion is used as the corresponding third dual-coded individual; and when it is determined that the two intended dual-coded individuals are not in the same non-dominated layer, the intended dual-coded individual with a higher non-dominated layer is used as the corresponding third dual-coded individual; repeatedly performing the operations of selecting two intended dual-coded individuals using the tournament selection method and selecting the corresponding third dual-coded individual from the two corresponding intended dual-coded individuals until a preset number of third dual-coded individuals is obtained.

[0136] In some embodiments, after obtaining a plurality of third double-coded individuals, the linkage decision-making device is further configured to randomly obtain two third double-coded individuals from the plurality of third double-coded individuals as the currently processed parent double-coded individuals, and obtain the replenishment code individuals and picking code individuals corresponding to the two parent double-coded individuals to obtain two candidate parent replenishment code individuals and two candidate parent picking code individuals; divide all cargo location allocation codes corresponding to the candidate parent replenishment code individuals into a first cross cargo location code group and a first mapped cargo location code group, and combine the first mapped cargo location code group of a corresponding candidate parent replenishment code individual with the first cross cargo location code group of the corresponding other candidate parent replenishment code individual to generate two candidate child replenishment code individuals; randomly mutate all cargo location allocation codes of the candidate child replenishment code individuals to generate new child replenishment code individuals; after selecting multiple picking sub-codes corresponding to target products from all picking sub-codes of the two candidate parent picking code individuals, all cargo location allocation codes of the two picking sub-codes corresponding to each target product are mutated. The system is divided into a second cross-cargo location code group and a second mapped cargo location code group, and the second mapped cargo location code group corresponding to one of the two picking sub-code bodies is combined with the second cross-cargo location code group corresponding to the other picking sub-code body to generate two new picking sub-code bodies corresponding to the corresponding target products, and all new picking sub-code bodies corresponding to the candidate parent picking code individuals are combined with the unselected picking sub-code bodies to generate new child picking code individuals corresponding to the corresponding candidate parent picking code individuals; after the new child replenishment code individuals and the corresponding new child picking code individuals are combined into new child dual-code individuals corresponding to the third dual-code individuals, all new child dual-code individuals and all third dual-code individuals are merged into a candidate dual-code population, and based on the non-dominated layer and target congestion degree of all fourth dual-code individuals corresponding to the candidate dual-code population, a preset number of fourth dual-code individuals are selected one by one using the tournament selection method to obtain a new dual-code population corresponding to the current decision iteration, and the dual-code individuals of the new dual-code population are used as the dual-code individuals generated after completing the current decision iteration.

[0137] In some embodiments, before determining the non-dominated layer corresponding to the second dual-coded individuals based on the non-dominated solution parameters corresponding to each second dual-coded individual, the linkage decision-making device is further used to obtain the total replenishment picking operation time and the picking ergonomic risk score corresponding to the second dual-coded individuals; respectively calculate a first difference in the total replenishment picking operation time and a second difference corresponding to the picking ergonomic risk score corresponding to any two second dual-coded individuals, and respectively determine whether the first difference and the second difference are less than a preset threshold; if it is determined that one of the first difference and the second difference is less than the preset threshold, determine that the two second dual-coded individuals are in the same non-dominated layer, and record the corresponding non-dominated layer as the non-dominated solution parameters corresponding to the two second dual-coded individuals.

[0138] In some embodiments, the linkage decision-making device is further configured to select two second dual-coded individuals adjacent to the corresponding second dual-coded individual from all second dual-coded individuals in the same non-dominated layer to obtain a fifth dual-coded individual and a sixth dual-coded individual; determine the operation time congestion distance corresponding to the corresponding second dual-coded individual based on the ratio of the third difference in the total replenishment picking operation time corresponding to the fifth dual-coded individual and the sixth dual-coded individual to the first target time difference; and determine the ergonomic risk congestion distance corresponding to the corresponding second dual-coded individual based on the ratio of the fourth difference in the picking ergonomic risk scores corresponding to the fifth dual-coded individual and the sixth dual-coded individual to the first target coefficient difference, wherein the first target time difference is the difference between the maximum and minimum values of the total replenishment picking operation time corresponding to all second dual-coded individuals in the same non-dominated layer, and the first target coefficient difference is the difference between the maximum and minimum values of the picking ergonomic risk scores corresponding to all second dual-coded individuals in the same non-dominated layer; and use the sum of the operation time congestion distance and the ergonomic risk congestion distance as the target congestion degree corresponding to the corresponding second dual-coded individual.

[0139] In some embodiments, after determining the second dual-coded individual of the current decision iteration, the linkage decision device is further configured to calculate the corresponding total replenishment picking time PRTT according to the following formula:

[0140]

[0141]

[0142]

[0143] The picking ergonomic risk score PERT is calculated as follows:

[0144]

[0145]

[0146] Calculate the total replenishment picking time (PRTT) and the picking ergonomic risk score (PERT), satisfying the following constraints:

[0147] ; ; ; ; ; ; ; ; ; ; ; ; ; ; ;

[0148] Among them, the target material set is I, I={1,2,…,i,…,|I|}, i represents the i-th target material; the order set corresponding to the aggregate material list is O, O={1,2,…,o,…,|O|}, o represents the o-th aggregate material list; the set of replenishment material arrival waves is W, W={1,2,…,w,…,|W|}, w represents the w-th wave; the replenishment object set is R, R={1,2,…,r,…,|R|}, r represents the r-th replenishment object; the picking object set is B, B={1,2,…,b,…,|B|}, b represents the b-th picking object; the storage location set is J, J={1,2,…,j,…,|J|}, j represents the j-th storage location, and the horizontal coordinate of the storage location is x j , the vertical coordinate of the cargo location is y j , the cargo location coordinates are (x j ,y j , z j ), the target product model set is P, P = {1, 2, …, p, …, |P|}, p represents the model of the p-th target product; h zj Indicates the level where the cargo location is located, h zj ∈{0,1}, if the jth cargo location is on the zth layer of the shelf, h zj =1, otherwise, h zj =0;O op Indicates the quantity of target product p contained in the order corresponding to order O, Indicates whether the target product p requires material i, If the target product p requires material i, ,otherwise ;U pi Indicates the quantity of material i required for the target product p, G ow Indicates whether the wth wave contains the oth order, G ow∈{0,1}, if the wth wave contains the oth order, G ow =1, otherwise, G ow =0;n oi Indicates the quantity of material i requested in the oth order; C i represents the capacity of a shelf location for item i; M is a large constant; K represents the width of each shelf location; H represents the height of each shelf location; D represents the depth of each shelf location; v1 represents the walking speed of the replenishment object; v2 represents the walking speed of the picking object; x represents the number of shelf rows, y represents the number of shelf columns, and z represents the number of shelf layers; PT z Indicates picking and storing in the The duration of the layer of material, PT z is a preset constant, Indicates picking and storing in the Ergonomic risks of layered materials, is a preset constant; , if the wave is w, material i is assigned to location j, ,otherwise ; Indicates the target product Need to be from the cargo location Picking materials the number of If the target product Need to be from the cargo location Picking materials , ,otherwise ; Indicates whether the target product p needs to be moved from location j1 to location j2. If the target product p needs to be moved from the shelf Move to shelf Selection, ,otherwise ; Indicates the coordinates of the picking platform; T indicates the width of each aisle in the picking configuration area; Indicates storage in the cargo area Picking distance; Indicates that the picking platform arrives at the cargo location Walking time; Represents the coordinates of the replenishment object; Indicates storage in the cargo area Replenishment distance; Indicates the arrival location of the replenishment object Walking time; Indicates the distance between cargo locations or between picking platforms and cargo locations; It represents the walking time between the cargo location and the cargo location or between the picking platform and the cargo location; the picking walking time of the target product p is ;The picking walking time of order o is ;The picking operation time of target product p is ; The ergonomic risk of picking objects at each shelf level is ;The total ergonomic risk of picking the target product p is ; Picking orders The total ergonomic risk is ; Indicates any.

[0149] This embodiment further provides a service platform, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0150] Optionally, the service platform may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0151] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0152] S1. After obtaining the aggregate material list information and the storage location information corresponding to the target set picking area from the acquired replenishment picking data stream, determine the first material quantity information to be replenished corresponding to the current wave order based on the aggregate material list information, and perform replenishment picking linkage coding on the first material information to be replenished, the aggregate material list information and the storage location information to generate a first double-coded population, wherein the first double-coded population includes multiple first double-coded individuals.

[0153] S2. According to the non-dominated solution parameters and target congestion corresponding to the first dual-coded individual, the target selection operation corresponding to the preset NSGA-Ⅱ algorithm is performed on the first dual-coded population to obtain candidate dual-coded individuals. The non-dominated solution parameters are generated by non-dominated sorting based on the individual fitness corresponding to the first dual-coded individual. The individual fitness includes parameters in the following two dimensions: total replenishment picking operation time and picking ergonomic risk score. The target congestion is calculated based on the total replenishment picking operation time and picking ergonomic risk score corresponding to the first dual-coded individual in the same non-dominated layer.

[0154] S3, performing the target genetic operation corresponding to the NSGA-II algorithm on all candidate dual-coded individuals, and repeating the target selection operation and the target genetic operation on all candidate dual-coded individuals generated after completing the target genetic operation, until a target dual-coded population including at least the target dual-coded individual is generated, and a decision result including the target dual-coded individual is obtained, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold, and the target genetic operation includes partial mapping crossover and random mutation.

[0155] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0156] In addition, in conjunction with the above-mentioned methods for coordinated decision-making regarding picking and replenishment that consider ergonomic risks, embodiments of the present application may provide a storage medium for implementation. The storage medium stores a computer program that, when executed by a processor, implements any of the above-mentioned methods for coordinated decision-making regarding picking and replenishment that consider ergonomic risks.

[0157] Those skilled in the art should understand that the various technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A picking and replenishment linkage decision-making method considering ergonomic risks, characterized by: include: After obtaining aggregate material bill information and storage location information corresponding to a target matching picking area from the acquired replenishment picking data stream, determining the quantity of first materials to be replenished corresponding to the current wave order based on the aggregate material bill information, and performing replenishment picking linkage coding on the first materials to be replenished, the aggregate material bill information, and the storage location information to generate a first double-coded population, wherein the first double-coded population includes a plurality of first double-coded individuals; Based on the non-dominated solution parameters and target congestion corresponding to the first dual-coded individuals, a target selection operation corresponding to a preset NSGA-II algorithm is performed on the first dual-coded population to obtain candidate dual-coded individuals, wherein the non-dominated solution parameters are generated by non-dominated sorting based on the individual fitness corresponding to the first dual-coded individuals, and the individual fitness includes parameters in the following two dimensions: total replenishment picking operation time and picking ergonomic risk score. The target congestion is calculated based on the total replenishment picking operation time and the picking ergonomic risk score corresponding to the first dual-coded individuals in the same non-dominated layer. A target genetic operation corresponding to the NSGA-II algorithm is performed on all the candidate dual-coded individuals, and the target selection operation and the target genetic operation are repeatedly performed on all candidate dual-coded individuals generated after completing the target genetic operation, until a target dual-coded population including at least a target dual-coded individual is generated, and a decision result including the target dual-coded individual is obtained, wherein the target dual-coded individual is a dual-coded individual whose individual fitness is less than a preset fitness threshold, and the target genetic operation includes partial mapping crossover and random mutation.

2. The method according to claim 1, characterized in that Performing replenishment and picking linkage coding on the first to-be-replenished material information, the aggregated material list information, and the storage location information to generate a first double-coded population, including: Acquire multiple target materials corresponding to the first material to be replenished information, and determine storage codes of all storage locations based on the storage location information; Based on the golden storage location allocation strategy, the plurality of target materials and the storage codes are integer-coded to generate a storage location allocation code corresponding to the replenishment storage location information allocated to each target material; Determine multiple picking materials corresponding to the target product associated with the aggregate bill of materials, select the shelf allocation codes corresponding to the multiple picking materials corresponding to each target product from all the shelf allocation codes according to the picking order divided by the codes, and integer-code all the selected shelf allocation codes to obtain a picking sub-code body corresponding to one target product, wherein the order of the shelf allocation codes in the corresponding picking sub-code body represents the order in which the corresponding picking materials are picked, and the picking sub-code body is also used to represent picking decision information for picking the multiple picking materials corresponding to one target product; After encoding all the cargo location allocation codes and generating replenishment code individuals, all the picking sub-code entities are encoded to generate picking code individuals, the replenishment code individuals and the picking code individuals are encoded as the first double-coded individuals, and the first double-coded individuals are initialized as a population to generate the first double-coded population.

3. The method according to claim 2, characterized in that The method further comprises: Determine a second dual-coded individual for the current decision iteration, wherein the second dual-coded individual includes one of the following: the first dual-coded individual, the candidate dual-coded individual generated after completing the target genetic operation corresponding to the previous decision iteration; determining a non-dominated layer corresponding to each of the second dual-coded individuals according to the non-dominated solution parameters corresponding to each of the second dual-coded individuals, and determining the target congestion degree corresponding to each of the second dual-coded individuals in the same non-dominated layer; Based on the non-dominated layer of the second dual-coded individuals and the target congestion, a tournament selection method is used to select a preset number of the second dual-coded individuals one by one from the plurality of the second dual-coded individuals to obtain a plurality of third dual-coded individuals, wherein the third dual-coded individuals include one of the following: the candidate dual-coded individuals, and the alternative dual-coded individuals generated after completing the current decision iteration.

4. The method according to claim 3, characterized in that Based on the non-dominated layer of the second dual-coded individuals and the target congestion, a preset number of the second dual-coded individuals are selected one by one from a plurality of the second dual-coded individuals using a tournament selection method, comprising: Randomly selecting two second dual-coded individuals from a plurality of second dual-coded individuals using a tournament selection method to obtain intended dual-coded individuals, and determining whether the two intended dual-coded individuals are in the same non-dominated layer; If it is determined that the two intended dual-coded individuals are in the same non-dominated layer, the intended dual-coded individual with the largest target congestion degree is used as the corresponding third dual-coded individual; and if it is determined that the two intended dual-coded individuals are not in the same non-dominated layer, the intended dual-coded individual with a higher non-dominated layer is used as the corresponding third dual-coded individual. Repeat the operations of selecting two intended dual-coded individuals using the tournament selection method and selecting the corresponding third dual-coded individual from the two corresponding intended dual-coded individuals until a preset number of the third dual-coded individuals are obtained.

5. The method according to claim 3, characterized in that After obtaining a plurality of third double-coded individuals, the method further includes: Two third double-coded individuals randomly obtained from the plurality of third double-coded individuals are used as the parent double-coded individuals currently being processed, and the replenishment coded individuals and the picking coded individuals corresponding to the two parent double-coded individuals are obtained to obtain two candidate parent replenishment coded individuals and two candidate parent picking coded individuals; Dividing all the cargo location allocation codes corresponding to the candidate parent replenishment code individuals into a first cross cargo location code group and a first mapped cargo location code group, combining the first mapped cargo location code group of a corresponding candidate parent replenishment code individual with the first cross cargo location code group of another corresponding candidate parent replenishment code individual to generate two candidate child replenishment code individuals, and randomly mutating all the cargo location allocation codes of the candidate child replenishment code individuals to generate new child replenishment code individuals; After selecting the picking sub-coding bodies corresponding to a plurality of the target products from all the picking sub-coding bodies of the two candidate parent picking coding individuals, all the cargo location allocation codes of the two picking sub-coding bodies corresponding to each target product are divided into a second cross cargo location code group and a second mapping cargo location code group, and the second mapping cargo location code group corresponding to one of the two picking sub-coding bodies is combined with the second cross cargo location code group corresponding to the other picking sub-coding body to generate two new picking sub-coding bodies corresponding to the corresponding target products, and all the new picking sub-coding bodies corresponding to the candidate parent picking coding individuals are combined with the unselected picking sub-coding bodies to generate a new child picking coding individual corresponding to the corresponding candidate parent picking coding individual; After the new offspring replenishment coded individuals and the corresponding new offspring picking coded individuals are combined into a new offspring double-coded individual corresponding to the third double-coded individual, all the new offspring double-coded individuals and all the third double-coded individuals are merged into a candidate double-coded population, and based on the non-dominated layers of all fourth double-coded individuals corresponding to the candidate double-coded population and the target congestion, a preset number of the fourth double-coded individuals are selected one by one using the tournament selection method to obtain a new double-coded population corresponding to the current decision iteration, and the double-coded individuals of the new double-coded population are used as the double-coded individuals generated after completing the current decision iteration.

6. The method according to claim 3, characterized in that Before determining the non-dominated layer corresponding to each of the second dual-coded individuals according to the non-dominated solution parameters corresponding to each of the second dual-coded individuals, the method further includes: Obtaining the total replenishment picking operation time and the picking ergonomic risk score corresponding to the second dual-coded individual; Calculating respectively a first difference in the total replenishment picking operation time and a second difference in the picking ergonomic risk score corresponding to any two of the second dual-coded individuals, and determining respectively whether the first difference and the second difference are less than a preset threshold; When it is determined that one of the first difference and the second difference is less than a preset threshold, it is determined that the two second dual-coded individuals are in the same non-dominated layer, and the corresponding non-dominated layer is recorded as the non-dominated solution parameters corresponding to the two second dual-coded individuals.

7. The method according to claim 6, characterized in that Determining the target congestion degree corresponding to each of the second dual-coded individuals in the same non-dominated layer includes: Selecting two second dual-coded individuals adjacent to the corresponding second dual-coded individual from all the second dual-coded individuals in the same non-dominated layer to obtain a fifth dual-coded individual and a sixth dual-coded individual; Determine the operation time congestion distance corresponding to the corresponding second dual-coded individual based on the ratio of the third difference in the total supplementary picking operation time corresponding to the fifth dual-coded individual and the sixth dual-coded individual to the first target time difference, and determine the ergonomic risk congestion distance corresponding to the corresponding second dual-coded individual based on the ratio of the fourth difference in the picking ergonomic risk score corresponding to the fifth dual-coded individual and the sixth dual-coded individual to the first target coefficient difference, wherein the first target time difference is the difference between the maximum and minimum values of the total supplementary picking operation time corresponding to all the second dual-coded individuals in the same non-dominated layer, and the first target coefficient difference is the difference between the maximum and minimum values of the picking ergonomic risk score corresponding to all the second dual-coded individuals in the same non-dominated layer; The sum of the operation time crowding distance and the ergonomic risk crowding distance is used as the target crowding degree corresponding to the corresponding second dual-coded individual.

8. The method according to claim 3, characterized in that After determining the second dual-coded individual for the current decision iteration, the method includes: The corresponding total replenishment picking time PRTT is calculated according to the following formula: The picking ergonomic risk score PERT is calculated as follows: The total replenishment picking time PRTT and the picking ergonomic risk score PERT are calculated to meet the following constraints: ； ； ； ； ； ； ； ； ； ； ； ； ； ； ； Among them, the target material set is I, I={1,2,…,i,…,|I|}, i represents the i-th target material; the order set corresponding to the aggregate material list is O, O={1,2,…,o,…,|O|}, o represents the o-th aggregate material list; the set of replenishment material arrival waves is W, W={1,2,…,w,…,|W|}, w represents the w-th wave; the replenishment object set is R, R={1,2,…,r,…,|R|}, r represents the r-th replenishment object; the picking object set is B, B={1,2,…,b,…,|B|}, b represents the b-th picking object; the storage location set is J, J={1,2,…,j,…,|J|}, j represents the j-th storage location, and the horizontal coordinate of the storage location is x j , the vertical coordinate of the cargo location is y j , the cargo location coordinates are (x j ,y j , z j ), the target product model set is P, P = {1, 2, …, p, …, |P|}, p represents the model of the p-th target product; h zj Indicates the level where the cargo location is located, h zj ∈{0,1}, if the jth cargo location is on the zth layer of the shelf, h zj =1, otherwise, h zj =0;O op Indicates the quantity of target product p contained in the order corresponding to order O, Indicates whether the target product p requires material i, If the target product p requires material i, ,otherwise ;U pi Indicates the quantity of material i required for the target product p, G ow Indicates whether the wth wave contains the oth order, G ow ∈{0,1}, if the wth wave contains the oth order, G ow =1, otherwise, G ow =0;n oi Indicates the quantity of material i requested in the oth order; C i represents the capacity of a shelf location for item i; M is a large constant; K represents the width of each shelf location; H represents the height of each shelf location; D represents the depth of each shelf location; v1 represents the walking speed of the replenishment object; v2 represents the walking speed of the picking object; x represents the number of shelf rows, y represents the number of shelf columns, and z represents the number of shelf layers; PT z Indicates picking and storing in the The duration of the layer of material, PT z is a preset constant, Indicates picking and storing in the Ergonomic risks of layered materials, is a preset constant; , if the wave is w, material i is assigned to location j, ,otherwise ; Indicates the target product Need to be from the cargo location Picking materials the number of If the target product Need to be from the cargo location Picking materials , ,otherwise ; Indicates whether the target product p needs to be moved from location j1 to location j2. If the target product p needs to be moved from the shelf Move to shelf Selection, ,otherwise ; Indicates the coordinates of the picking platform; T indicates the width of each aisle in the picking configuration area; Indicates storage in the cargo area Picking distance; Indicates that the picking platform arrives at the cargo location Walking time; Represents the coordinates of the replenishment object; Indicates storage in the cargo area Replenishment distance; Indicates the arrival location of the replenishment object Walking time; Indicates the distance between cargo locations or between picking platforms and cargo locations; It represents the walking time between the cargo location and the cargo location or between the picking platform and the cargo location; the picking walking time of the target product p is ;The picking walking time of order o is ;The picking operation time of target product p is ; The ergonomic risk of picking objects at each shelf level is ;The total ergonomic risk of picking the target product p is ; Picking orders The total ergonomic risk is ; Indicates any.

9. A service platform comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the picking and replenishment linkage decision-making method considering ergonomic risks according to any one of claims 1 to 8.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the picking and replenishment linkage decision-making method considering ergonomic risks according to any one of claims 1 to 8 are implemented.

Images