Order affinity-based SKU placement method and system

Abstract

A stock keeping unit (SKU) placement method according to an embodiment disclosed herein is performed by a computing system and comprises the steps of: identifying order affinities among respective SKUs included among a plurality of SKUs to be placed, wherein the order affinities among the respective SKUs are identified on the basis of the number of times the SKUs were ordered together in a single order during a predetermined specific period; identifying one or more preset constraints; and establishing a SKU placement plan so that the constraints are satisfied and the sum of the order affinities between a first SKU and a second SKU placed in the same zone among the plurality of SKUs is maximized, wherein the SKU placement plan places the plurality of SKUs in at least one zone.

Description

Order Intimacy-Based SKU Placement Method and System

[0001] The present disclosure relates to a stock keeping unit (SKU) placement method and system. More specifically, it relates to a method and system for optimizing SKU placement by identifying order affinity for each SKU and placing SKUs with high order affinity into the same zone to improve SKU picking efficiency or reduce outbound time.

[0002] In a logistics center, SKUs (stock keeping units) can play a crucial role in product management, inbound and outbound processes, and shipments. Generally, SKU placement can be done randomly, which can contribute to the efficient utilization of space within the logistics center and increase the productivity of workers in inbound operations. However, the random placement method increases the likelihood that specific SKUs will be distributed across different zones, which can lead to reduced efficiency in picking operations.

[0003] This problem can be even more pronounced when multiple SKUs must be shipped together in a single order. If SKUs must be picked from multiple zones, picking paths may become longer and work times may increase, resulting in a decrease in both the operational efficiency of the logistics center and the speed of delivery services provided to customers.

[0004] Since the existing random placement method does not consider order relationships or shipping patterns between SKUs, the proportion of orders that can be completed within the same zone is low, and there is a high possibility that additional logistics costs may be incurred during the overall shipping process.

[0005] Meanwhile, the placement area of ​​specific SKUs may be restricted due to physical constraints such as temperature conditions, shelf life, or size. If random placement is applied while ignoring these constraints, quality control issues may arise, which could lead to a decline in end-customer trust.

[0006] Therefore, there is a need for a new batching method and system that can establish an efficient batching plan based on order affinity between SKUs and simultaneously satisfy constraints.

[0007] The technical problem to be solved in some embodiments of the present disclosure is to provide a method and system for analyzing order affinity between SKUs and placing SKUs with high order affinity into the same zone.

[0008] The technical problem to be solved in some other embodiments of the present disclosure is to provide a method and system capable of establishing an optimal SKU placement plan while satisfying constraints such as temperature, quantity, and shelf life during SKU placement.

[0009] The technical problem to be solved in some other embodiments of the present disclosure is to provide a method and system that can optimize space utilization by appropriately arranging SKUs, taking into account the physical characteristics of the SKUs and the spatial structure within the logistics center.

[0010] The technical problem to be solved in some other embodiments of the present disclosure is to provide a system that can efficiently control an automatic placement robot according to an SKU placement plan, thereby minimizing human error and improving the overall operational efficiency of a logistics center.

[0011] The technical problems of the present disclosure are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by a person skilled in the art from the description below.

[0012] A method for placing SKUs, performed by a computing system according to an embodiment of the present disclosure for solving the above technical problem, may include the steps of: identifying order affinity between each SKU included in a plurality of stock keeping units (SKUs) to be placed, wherein the order affinity between each SKU is identified based on the number of times they were ordered together in a single order during a predetermined specific period; identifying one or more predetermined constraints; and establishing an SKU placement plan such that the sum of order affinities between a first SKU and a second SKU placed in the same zone among the plurality of SKUs is maximized while satisfying the constraints, wherein the SKU placement plan places the plurality of SKUs in at least one zone.

[0013] According to one embodiment, the SKU placement method may further include the step of controlling an automatic placement robot according to the SKU placement plan to place the plurality of SKUs in a specific area.

[0014] According to one embodiment, the constraint may include the number of SKUs that can be placed in a specific area being less than or equal to a preset threshold.

[0015] According to one embodiment, the constraint may include that a specific SKU cannot be placed in a plurality of zones.

[0016] According to one embodiment, the constraint may include a temperature constraint, a quantity constraint, a shelf life constraint, or a shipment quantity constraint for the SKU to be placed.

[0017] An SKU placement system performed by a computing system according to another embodiment of the present disclosure for solving the above technical problem comprises: one or more processors; and a memory for storing a computer program executed by one or more processors. When the computer program is executed, the one or more processors may perform the following operations: identifying order affinity between each SKU included in a plurality of stock keeping units (SKUs) to be placed, wherein the order affinity between each SKU is identified based on the number of times they were ordered together in a single order during a predetermined specific period; identifying one or more predetermined constraints; and establishing an SKU placement plan such that the sum of order affinities between a first SKU and a second SKU placed in the same zone among the plurality of SKUs is maximized while satisfying the constraints, wherein the SKU placement plan places the plurality of SKUs in at least one zone.

[0018] According to one embodiment, the processor may further perform the operation of placing the plurality of SKUs in a specific area by controlling an automatic placement robot according to the SKU placement plan.

[0019] According to one embodiment, the constraint may include the number of SKUs that can be placed in a specific area being less than or equal to a preset threshold.

[0020] According to one embodiment, the constraint may include that at least one of the plurality of SKUs to be placed cannot be placed in a plurality of zones.

[0021] According to one embodiment, the constraint may include a temperature constraint, a quantity constraint, a shelf life constraint, or a shipment quantity constraint for the SKU to be placed.

[0022] FIG. 1 is a drawing illustrating an SKU placement system according to one embodiment of the present disclosure.

[0023] FIG. 2 is a diagram illustrating the configuration of an optimization model according to one embodiment.

[0024] FIG. 3 is a diagram illustrating the optimal solution of an optimization model according to one embodiment.

[0025] FIG. 4 is a diagram illustrating the objective function of an SKU placement optimization model according to one embodiment of the present disclosure.

[0026] FIG. 5 is a diagram illustrating the constraints of an SKU placement optimization model according to one embodiment of the present disclosure.

[0027] FIG. 6 is a diagram illustrating the provided data of an SKU placement optimization model according to one embodiment of the present disclosure.

[0028] FIG. 7 is a diagram illustrating the optimal solution of an SKU placement optimization model according to one embodiment of the present disclosure.

[0029] FIG. 8 is a flowchart illustrating the overall sequence of an SKU placement method according to another embodiment of the present disclosure.

[0030] FIG. 9 is a block diagram showing the hardware configuration of a computing device for affinity-based SKU placement according to one embodiment of the present disclosure.

[0031] Preferred embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments described below but may be implemented in various different forms. The embodiments are provided merely to make the present disclosure complete and to fully inform those skilled in the art of the scope of the invention, and the present disclosure is defined only by the scope of the claims.

[0032] It should be noted that when assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the present disclosure, if it is determined that a detailed description of related known components or functions could obscure the essence of the present disclosure, such detailed description is omitted.

[0033] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this disclosure pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. The terms used herein are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text.

[0034] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are intended only to distinguish the components from other components and do not limit the nature, order, or sequence of the components. Where it is stated that a component is "connected," "coupled," or "joined" to another component, it should be understood that the component may be directly connected or joined to the other component, but that another component may also be "connected," "coupled," or "joined" between each component.

[0035] As used in the specification, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components, steps, actions, and / or elements to the mentioned components, steps, actions, and / or elements.

[0036] In the present disclosure, an SKU pair refers to two SKUs, and the order affinity between them can be calculated based on the frequency with which the SKU pair is included together in a single order. Meanwhile, in the present disclosure, a single order may refer to a transaction in which a customer pays for at least one product at a time during the product ordering process. In the present disclosure, a zone may refer to a place for storing products in an appropriate location within a fulfillment or warehouse. At least one zone may exist within a single fulfillment, and dozens or more zones may exist on each floor of a fulfillment.

[0037] In the present disclosure, SKU placement may correspond to an SKU stowing process or an SKU allocation process. Additionally, in the present disclosure, SKU selection may correspond to an SKU picking process or an SKU selection process.

[0038] FIG. 1 is a drawing illustrating an SKU placement system according to one embodiment of the present disclosure.

[0039] A user terminal (110) may be a device connected to an SKU placement system (130) that provides input data to a user or allows the user to check a placement plan or placement results. The user terminal (110) may be a concept including, for example, a smartphone, tablet, computer, etc. The user terminal (110) may transmit and receive data to and from the SKU placement system (130) via a network (120). Meanwhile, the users of the user terminal (110) may include an administrator who establishes an SKU placement plan and an administrator who selects items based on the placed SKUs.

[0040] The network (120) is a communication network that enables data communication by connecting a user terminal (110) and an SKU placement system (130), and may include a wired network, a wireless network, or a combination thereof. The network (120) can efficiently transmit SKU placement requests, placement plan results, or other information.

[0041] The SKU placement system (130) may include an SKU placement optimization model (131) and an automatic placement robot (132), and may perform key functions related to SKU placement.

[0042] The SKU placement optimization model (131) can analyze order affinity between SKUs and SKU placement constraints, and generate an optimal placement plan based on this. This model can maximize SKU placement efficiency by using data provided by users or past order data.

[0043] Order affinity is a value calculated based on the number of times specific SKUs are ordered together in a single order, allowing for the quantitative representation of the association between SKUs. For example, if snack A and beverage B are frequently ordered together, the order affinity between A and B can be assessed as high. Based on this order affinity, SKUs that are frequently shipped together can be placed in the same zone to improve the efficiency of picking or product selection operations in the logistics center.

[0044] SKU placement constraints may include conditions that must be met when placing SKUs in specific zones. For example, there may be temperature constraints requiring that SKUs requiring refrigeration be placed in a refrigerated zone. Additionally, the number of SKUs that can be placed in a zone may be limited by physical space, and shelf-life constraints may apply, prohibiting identical SKUs with different expiration dates from being placed in the same location. Furthermore, weight and size constraints may exist, such as requiring heavy or large SKUs to be placed in the pallet zone on the ground floor and restricting placement on upper floors. Constraints may also be included requiring that certain fragile products, such as eggs, be placed in dedicated zones.

[0045] These examples are merely illustrative to aid in understanding the present disclosure and are not limited to these examples. Depending on various environments and conditions, additional order affinity analysis methods or SKU placement constraints may be applied.

[0046] The automatic placement robot (132) is a device that appropriately places SKUs within a physical space according to a placement plan generated from an SKU placement optimization model (131). This robot can reduce human error and increase work efficiency through the automation of placement tasks.

[0047] FIG. 2 is a diagram illustrating the configuration of an optimization model according to one embodiment.

[0048] The above optimization model may consist of an objective (210), constraints (220), additional data (230), and output data (240). Each component of the above optimization model may be an input or output element of the optimization model.

[0049] Objective (210) may refer to a goal to be achieved in an optimization model. As an example, in FIG. 2, the objective of the optimization model is defined as minimizing two function values. Such an optimization objective clearly defines a specific goal that a system or model must achieve and may be considered essential for optimizing the performance of the system. In this disclosure, the objective (210) of the optimization model may be the same concept as the objective function, Objective, or Objective function of the optimization model.

[0050] Constraints (220) may represent limitations that must be satisfied during the optimization process. As an example, FIG. 2 discloses constraints that σ_1 and σ_2 must have values ​​of 200 MPa or less, and that the two regions (A_1, A_2) are greater than 1 mm^2 and less than 20 mm^2. Constraints may be set considering realistic physical limits or system constraints and may play an essential role in the process of finding the optimal solution. In this disclosure, constraints (220) of the optimization model may have the same meaning as subject to (st) or constraints.

[0051] Data (230) may be a concept that includes information or constants provided by default in addition to the basic objectives and constraints of the optimization model. As an example, in FIG. 2, information such as l=100mm, θ=45, and P=2000N is provided as data. Such data can help to define the optimization problem more specifically and to derive a more precise optimal solution. In the present disclosure, data (230) of the optimization model may have the same meaning as where of the optimization model.

[0052] Finally, the output data (240) may represent the result value derived through the optimization model, i.e., the optimal solution. As an example, in FIG. 2, finding two variables x_1 and x_2 may be presented as the optimization result. This output data is the optimal solution derived by considering all of the optimization model's objectives (210), constraints (220), and data (230), and can be used for decision-making in a system or process. In the present disclosure, the output data of the optimization model may be the same concept as the decision variable or decision variable of the optimization model.

[0053] Each component (210, 220, 230, 240) described in FIG. 2 is merely an example to illustrate the process of finding the optimal solution. According to one embodiment of the present disclosure, the SKU placement optimization model may include goals, constraints, data, and output results different from the example above.

[0054] Figure 3 is a diagram illustrating the optimal solution of an optimization model in one embodiment.

[0055] Mixed integer programming is an optimization technique that handles both integer and continuous variables simultaneously and can be used to solve various problems that occur in real life. This method is effective for solving complex optimization problems that include both discrete variables, which must be expressed only as integers, and continuous variables, which can have continuous values ​​within a specific range. Through mixed integer programming, optimized solutions can be obtained in various fields such as complex logistics problems, inventory placement, and inventory management. Figure 3 illustrates an example of using mixed integer programming to find an optimal solution. However, this is merely an example, and the method for finding an optimal solution for SKU placement in this disclosure is not limited to mixed integer programming.

[0056] Figure 3 visually represents various possible solutions based on the X and Y axes. The dots filled in blue represent possible integer solutions, while the empty circles represent possibilities for continuous variables. Various constraints are applied within this solution space, and regions restricted by these conditions are generated. The colored regions in the figure represent the solution space that satisfies the given constraints, and the optimal solution is found within this space. The graph in Figure 3 visually represents the solutions that can be selected during the optimization process, demonstrating how solutions satisfying constraints are determined in reality.

[0057] x_1 and y_1 are coordinates representing the optimal solution obtained through this mixed integer programming. These coordinates represent the value that yields the most optimal result while satisfying both the given objective function and constraints. In other words, the optimal solution x_1 and y_1 shown in Figure 3 is a solution selected from among all possible solutions within the constraints, and can be practically applied in decision-making processes such as logistics or inventory management. This optimal solution is a result for achieving specific goals, such as minimizing costs or maximizing sales volume, and can be important data derived through mixed integer programming.

[0058] FIG. 4 is a diagram illustrating the objective function of an SKU placement optimization model according to one embodiment of the present disclosure.

[0059] The SKU placement optimization model can be defined as a model that optimizes SKU placement within a logistics center based on order affinity between SKUs. The optimization model aims to increase the proportion of orders that can be processed within the same area and improve the efficiency of picking operations by maximizing the affinity between SKUs.

[0060] In the objective function of Fig. 4, represents a set of specific SKU pairs for which order affinity between SKUs is defined, and can be expressed in the form (k_1, k_2). K can be defined based on the frequency with which specific SKUs k_1 and k_2 are ordered together. Meanwhile, in the objective function of Fig. 4, J can represent a set of zones within a logistics center.

[0061] The definition of the objective function according to the present disclosure is to maximize the sum of order affinities in the SKU placement optimization problem. This can maximize SKU placement efficiency and improve the overall operational performance of the logistics center.

[0062] f_k, which constitutes the objective function, is a value representing the order frequency of a specific SKU pair (k_1, k_2) and may quantify the affinity between SKUs. f_k can be calculated based on the number of times multiple SKUs are shipped together in a single order.

[0063] A_k,j constituting the objective function may be a binary variable representing the probability that SKU k is placed in zone j. A_k,j has a value of 1 or 0, and can be set to 1 if SKU k is placed in zone j, and 0 otherwise.

[0064] The objective function disclosed in FIG. 4 induces SKUs with high order affinity to be placed in the same area and can aim to maximize the efficiency of SKU placement. Maximizing SKU placement efficiency can contribute to shortening the picking path of a logistics center and reducing working time.

[0065] Meanwhile, the objective function of FIG. 4 is merely an example for optimal SKU placement, and the present disclosure is not limited to such an example.

[0066] FIG. 5 is a diagram illustrating the constraints of an SKU placement optimization model according to one embodiment of the present disclosure.

[0067] The first constraint (510) may indicate that the total output of SKUs placed in each zone must be within the lower and upper limits of the zone. Through the first constraint (510), the allowable output of SKUs in each zone can be managed so as not to be exceeded.

[0068] The second constraint (520) may limit the number of BIN locations available in a specific area and the SKU placement limit per BIN so that the number of SKUs placed in that area does not exceed the allowed capacity based on the validity period of the SKUs placed in that area. In this disclosure, a BIN is a physical space unit used to store small or medium SKUs, which is mainly located on shelves in a logistics center and may refer to a storage space that is easily accessible to workers. However, this is merely an example of a BIN, and this disclosure is not to be interpreted as being limited thereto.

[0069] The third constraint (530) represents the case of SKU placement using pallet locations, and the placement quantity can be managed so as not to exceed the allowed capacity by considering the pallet locations and SKU limits per pallet. In the present disclosure, a pallet is a unit of space used to store large SKUs or heavy SKUs, and may refer to a structure that can stably store a large quantity of goods by placing it mainly on the floor of a logistics center or in an area accessible by forklift. However, this is merely an example of a pallet, and the present disclosure is not to be interpreted as being limited thereto.

[0070] The fourth constraint (540) may be a condition that sets the SKU pairs to be placed in the same zone when specific SKU pairs with high order affinity are placed in the same zone. This allows SKU pairs with high order affinity to be picked in close proximity.

[0071] The fifth constraint (550) may be a condition that sets SKU pairs with low order affinity to be placed in different zones. This condition allows for efficient management of picking paths within the logistics center.

[0072] The sixth constraint (560) may be a condition that restricts the SKU to be placed in only one zone. This prevents the problem of SKUs being placed in multiple zones.

[0073] The seventh constraint (570) may be a condition that ensures a specific SKU is placed in a dedicated area if it is a product requiring special care, such as an egg. This allows for the safe storage and management of SKUs requiring special care.

[0074] Meanwhile, the constraints of FIG. 5 are merely examples of constraints for optimal SKU placement, and the present disclosure is not to be interpreted as being limited to such examples.

[0075] FIG. 6 is a diagram illustrating the provided data of an SKU placement optimization model according to one embodiment of the present disclosure.

[0076] The provided data can be used to establish an optimal placement plan in an optimization model, and each data point can serve as an input value for the model.

[0077] The first data (602) is a value representing the frequency with which a specific pair of SKUs are ordered together, and can be used to calculate the order affinity between SKUs.

[0078] The second data (604) represents the average daily shipment quantity of a specific SKU and can reflect the demand and shipment pattern of the SKU.

[0079] The third data (608) indicates the minimum value of the allowed shipment volume in a specific area and can define the minimum quantity of SKUs that must be placed in that area.

[0080] The fourth data (610) represents the maximum value of the allowed shipment volume in a specific area and can limit the placement of SKUs so that they are not excessively distributed.

[0081] The fifth data (612) represents the expiration date information of the SKU and can be used as data to efficiently arrange SKUs for which the expiration date is important during management.

[0082] The 6th data (614) is a value indicating whether a specific SKU is placed in a BIN location, and if it is 1, it means it is placed in a BIN location, and if it is 0, it means it is placed in another location.

[0083] The seventh data (616) represents the total number of BIN locations available in a specific area and may reflect the physical storage space limitations.

[0084] The eighth data (618) represents the maximum number of SKUs that can be placed in a single BIN location and can be used as a criterion for optimizing space utilization.

[0085] The ninth data (620) indicates the total number of pallet locations available in a specific area and may reflect the limitations of pallet storage space.

[0086] The 10th data (622) indicates the maximum number of SKUs that can be placed in one pallet location and can be used for efficient placement of large SKUs.

[0087] The 11th data (624) represents the ratio of available locations when SKU placement, and can serve as a standard for managing to prevent work efficiency from decreasing due to excessive location utilization.

[0088] The 12th data (626) represents the entire set of SKUs and may include all SKUs considered in the model.

[0089] The 13th data (628) may mean a set of zones representing all zones that can be placed in a logistics center.

[0090] The 14th data (630) is a set of specific SKU pairs for which order affinity has been calculated, and can be used to define the relationship between SKUs.

[0091] Based on such pre-existing data, the SKU placement optimization model can derive an optimal placement plan, which can contribute to maximizing picking efficiency and space utilization in logistics centers. The pre-existing data in FIG. 6 is merely an example, and the present disclosure is not limited to such examples.

[0092] FIG. 7 is a diagram illustrating the optimal solution of an SKU placement optimization model according to one embodiment of the present disclosure. FIG. 7 discloses a first decision variable (710) and a second decision variable (720) derived as a result of the optimization model, and the first decision variable and the second decision variable can be used to efficiently design SKU placement within a logistics center.

[0093] The first decision variable (710) is a variable indicating how often a specific pair of SKUs is ordered simultaneously. This variable quantifies the order affinity between SKUs, thereby inducing SKUs that are frequently ordered together to be placed in the same area. This allows for the efficient management of SKU pairs with high order affinity.

[0094] The second decision variable (720) is a variable indicating whether a specific pair of SKUs is placed in zone j. This variable has a binary value (0 or 1), and if it is 1, it may mean that the corresponding pair of SKUs is placed together in zone j. This allows pairs of SKUs with high affinity to be placed in the same zone, thereby maximizing picking efficiency.

[0095] These two decision variables are key elements of the SKU placement optimization model, and an optimal placement plan can be derived by clearly defining the relationships between SKUs and the placement status within a zone. This optimal solution can contribute to improving operational efficiency in logistics centers and reducing picking time and logistics costs.

[0096] Meanwhile, the decision variables of FIG. 7 are merely examples, and the decision variables of the present disclosure are not limited to these examples.

[0097] FIG. 8 is a flowchart illustrating the overall sequence of an SKU placement method according to one embodiment of the present disclosure.

[0098] Step S810 is a step for identifying order affinity between each SKU included in the multiple SKUs targeted for placement. In this step, order affinity between each SKU can be analyzed based on the number of times they were ordered together in a single order during a pre-set specific period. This order affinity quantitatively evaluates the association between SKUs and can be utilized as an important criterion when establishing SKU placement plans.

[0099] Step S820 is a step for identifying one or more pre-established constraints. Constraints may include a condition that the number of SKUs that can be placed in a specific zone must be below a pre-established threshold, a condition that a specific SKU cannot be placed in multiple zones, or special constraints such as temperature, quantity, shelf life, or outbound quantity. This enables the fulfillment of the physical, environmental, and business requirements of the logistics center during SKU placement.

[0100] Step S830 is the stage for establishing an SKU placement plan that maximizes the sum of order affinities while satisfying constraints. In this stage, SKU pairs to be placed in the same zone can be determined by reflecting the order affinities between SKUs and the constraints. The SKU placement plan can be designed to efficiently place SKUs in at least one zone. This enables the shortening of picking paths in the logistics center and the maximization of operational efficiency.

[0101] Step S840 is the stage where the automated placement robot is controlled according to the SKU placement plan. In this stage, the automated robot can be controlled to place SKUs into designated areas based on the established placement plan. This minimizes human error and improves the speed and accuracy of the placement operation.

[0102] FIG. 9 is a block diagram showing the hardware configuration of a computing device for affinity-based SKU placement according to one embodiment of the present disclosure.

[0103] Referring to FIG. 9, a computing device (5000) may include one or more processors (5010), a bus (5060), a communication interface (5020), a memory (5040) for loading a computer program executed by the processor (5010), and a storage (5030) for storing a computer program (5050). However, FIG. 9 illustrates components related to an embodiment of the present disclosure.

[0104] Therefore, a person skilled in the art to which this disclosure pertains will understand that other general-purpose components may be included in addition to the components shown in FIG. 9. That is, the computing device (5000) may include various additional components in addition to the components shown in FIG. 9. Furthermore, depending on the case, the computing device (5000) may be configured in a form in which some of the components shown in FIG. 9 are omitted. Hereinafter, each component of the computing device (5000) will be described. Meanwhile, throughout this disclosure, the terms computing device (5000) and computing system may be used interchangeably.

[0105] The processor (5010) can control the overall operation of each component of the computing device (5000). The processor (5010) may be configured to include at least one of a CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), GPU (Graphic Processing Unit), or any form of processor well known in the art of the present disclosure. Additionally, the processor (5010) may perform operations for at least one application or program for executing operations / methods according to embodiments of the present disclosure. The computing device (5000) may have one or more processors.

[0106] Next, the memory (5040) may store various data, commands and / or information. The memory (5040) may load a computer program (5050) from the storage (5030) to execute an operation / method according to the embodiments of the present disclosure. The memory (5040) may be implemented as a volatile memory such as RAM, but the present disclosure is not limited thereto.

[0107] Next, the bus (5060) can provide communication functions between components of the computing device (5000). The bus (5060) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0108] Next, the communication interface (5020) can support wired and wireless internet communication of the computing device (5000). Additionally, the communication interface (5020) may support various communication methods other than internet communication. To this end, the communication interface (5020) may be configured to include a communication module well known in the art of the present disclosure.

[0109] Next, the storage (5030) may store one or more computer programs (5050) non-temporarily. The storage (5030) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which this disclosure belongs.

[0110] Next, the computer program (5050) may include one or more instructions that cause the processor (5010) to perform an operation / method according to various embodiments of the present disclosure when loaded into memory (5040). That is, the processor (5010) may perform an operation / method according to various embodiments of the present disclosure by executing one or more loaded instructions.

[0111] For example, a computer program (5050) may include instructions to perform operations such as identifying order affinity between each SKU included in a plurality of stock keeping units (SKUs) to be placed, wherein the order affinity between each SKU is identified based on the number of times they were ordered together in a single order during a predetermined specific period; identifying one or more predetermined constraints; and establishing an SKU placement plan such that the sum of order affinities between a first SKU and a second SKU placed in the same zone among the plurality of SKUs is maximized while satisfying the constraints, wherein the SKU placement plan places the plurality of SKUs in at least one zone.

[0112] The SKU placement method and system according to the embodiments of the present disclosure can achieve various effects by optimizing SKU placement. The main effects of the present disclosure may be as follows.

[0113] First, according to an embodiment of the present disclosure, picking efficiency of a logistics center can be maximized by establishing a placement plan based on order affinity between SKUs. By placing SKUs with high order affinity in the same area, the picking path is shortened, and the time for outbound operations can be significantly reduced.

[0114] Second, according to an embodiment of the present disclosure, operational stability can be ensured by considering physical, environmental, and business constraints when placing SKUs. For example, SKUs requiring refrigeration or freezing can be placed in areas equipped with appropriate temperature conditions, and quality issues can be prevented by managing SKUs with different expiration dates so that they are not placed in the same location.

[0115] Third, according to an embodiment of the present disclosure, work speed and accuracy can be improved by utilizing an automatic placement robot to place SKUs in designated areas. This minimizes human error and enables the placement operation to be performed efficiently.

[0116] Fourth, according to the embodiments of the present disclosure, it is possible to respond quickly to changes in demand for specific SKUs or new business requirements. The SKU placement optimization model can periodically update placement plans by reflecting not only historical data but also real-time data. Through this, the logistics center can flexibly respond to the changing environment.

[0117] Fifth, according to the embodiments of the present disclosure, the space utilization of a logistics center can be maximized. Since the SKU placement plan is established by considering the capacity limits of each zone and the availability of bin and pallet locations, space can be used efficiently.

[0118] Sixth, according to the embodiments of the present disclosure, logistics operating costs can be reduced. Efficient SKU placement leads to reduced picking time, optimized movement paths, and reduced operational errors, thereby reducing the overall operating costs of the logistics center.

[0119] The SKU placement method and system according to the embodiments of the present disclosure can improve the operational efficiency of a logistics center and provide fast and accurate delivery services to customers through these functions. Various embodiments of the present disclosure and the effects thereof have been described with reference to FIGS. 1 through 9. The effects of the present disclosure are not limited to those mentioned herein, and additional effects will be clearly understood by a person skilled in the art.

[0120] In the foregoing, although all components constituting an embodiment of the present disclosure have been described as being combined or operating together, the present disclosure is not necessarily limited to such embodiments. That is, within the scope of the purpose of the present disclosure, all components may be selectively combined and operated in one or more ways.

[0121] Although operations are depicted in a specific order in the drawings, it should not be understood that the operations must necessarily be executed in the specific order depicted or in a sequential order, or that all depicted operations must be executed to obtain the desired result. In certain situations, multitasking and parallel processing may be advantageous. Furthermore, the separation of various configurations in the embodiments described above should not be understood as necessarily required, and it should be understood that the described program components and systems can generally be integrated together into a single software product or packaged into multiple software products.

[0122] Although embodiments of the present disclosure have been described above with reference to the attached drawings, those skilled in the art will understand that the present disclosure may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of protection of the present disclosure shall be interpreted by the claims below, and all technical concepts within the equivalent scope shall be interpreted as being included within the scope of rights of the present disclosure.

[0123] [Explanation of the symbol]

[0124] 110: User terminal

[0125] 120: Network

[0126] 130: SKU Batch System

[0127] 131: SKU Placement Optimization Model

[0128] 132: Automated Placement Robot

[0129] 210: Purpose of Optimization Models

[0130] 220: Constraints on the Optimization Model

[0131] 230: Data provided by the optimization model mechanism

[0132] 240: Output data of the optimization model

[0133] 510: First constraint

[0134] 520: Second constraint

[0135] 530: Third Constraint

[0136] 540: The 4th Constraint

[0137] 550: The 5th constraint

[0138] 560: The 6th Constraint

[0139] 570: The 7th Constraint

[0140] 602: 1st data

[0141] 604: Second data

[0142] 608: Third data

[0143] 610: 4th data

[0144] 612: 5th data

[0145] 614: 6th data

[0146] 616: 7th Data

[0147] 618: 8th Data

[0148] 620: 9th Data

[0149] 622: 10th Data

[0150] 624: 11th data

[0151] 626: 12th data

[0152] 628: 13th data

[0153] 630: 14th data

[0154] 710: First decision variable

[0155] 720: Second decision variable

[0156] S810, S820, S830, S840: Step

[0157] 5000: Computing device

[0158] 5010: Processor

[0159] 5020: Communication Interface

[0160] 5030: Storage

[0161] 5040: Memory

[0162] 5050: Computer program

[0163] 5060: BUS

Claims

1. In a method performed by a computing system, A step of identifying order affinity between each SKU included in a plurality of stock keeping units (SKUs) to be placed, wherein the order affinity between each SKU is identified based on the number of times they were ordered together in a single order during a predetermined specific period; A step of identifying one or more pre-set constraints; and A step comprising, while satisfying the above constraints, establishing an SKU placement plan such that the sum of the order affinities between a first SKU and a second SKU placed in the same zone among the plurality of SKUs is maximized, wherein the SKU placement plan places the plurality of SKUs in at least one zone. SKU placement method.

2. In Paragraph 1, The method further includes the step of controlling an automatic placement robot according to the above SKU placement plan to place the plurality of SKUs in a specific area. SKU placement method.

3. In Paragraph 1, The above constraint includes the number of SKUs that can be placed in a specific area being less than or equal to a preset threshold. SKU placement method.

4. In Paragraph 1, The above constraint includes that a specific SKU cannot be placed in multiple zones, SKU placement method.

5. In Paragraph 1 The above constraints include temperature constraints, quantity constraints, shelf-life constraints, or outgoing quantity constraints for the SKUs targeted for batching. SKU placement method.

6. One or more processors; and It includes memory that stores computer programs executed by one or more processors, and When the above computer program is executed, the above one or more processors: An operation to identify the order affinity between each SKU included in a plurality of stock keeping units (SKUs) to be placed, wherein the order affinity between each SKU is identified based on the number of times they were ordered together in a single order during a predetermined specific period. An action that identifies one or more pre-set constraints, and Performing an operation in which, while satisfying the above constraints, an SKU placement plan is established such that the sum of the order affinities between a first SKU and a second SKU placed in the same zone among the plurality of SKUs is maximized, wherein the SKU placement plan places the plurality of SKUs in at least one zone. SKU batch system.

7. In Paragraph 6, The above processor is, Further performing the operation of placing the plurality of SKUs in a specific area by controlling an automatic placement robot according to the above SKU placement plan, SKU batch system.

8. In Paragraph 6, The above constraint includes the number of SKUs that can be placed in a specific area being less than or equal to a preset threshold. SKU batch system.

9. In Paragraph 6, The above constraint includes that at least one of the plurality of SKUs to be placed cannot be placed in a plurality of zones. SKU batch system.

10. In Paragraph 6, The above constraints include temperature constraints, quantity constraints, shelf-life constraints, or outgoing quantity constraints for the SKUs targeted for batching. SKU batch system.

Images