Article inventory adjustment method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses an article inventory adjustment method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: determining an optimization target according to inventory distribution data of articles of a preset grade category; on the basis of the optimization target, a data model is constructed by adopting an operation planning optimization method, and the data model is used for representing the condition that the articles are carried into another warehouse from the warehouse where the articles are located; solving the data model to obtain warehouse moving data of the articles; and according to the carrying quantity indicated by the carrying data and the warehouses, carrying the articles with the carrying quantity from the first warehouse to the second warehouse. The implementation mode is related to a supply chain technology, and an actual scene is abstracted into a mathematical model for solving based on a modeling thought of operational research. And finally, the mathematical solution can be converted into a service executable landing scheme, so that the service is guided to adjust the warehouse separation condition of each category. Concentrated storage of articles is achieved, the order splitting rate can be effectively reduced, and the storage resource utilization rate is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of supply chain, and more particularly to methods, devices, electronic devices, and computer-readable media for adjusting item inventory. Background Art

[0002] An enterprise's supply chain usually constructs a regional distribution center (RDC) group in different regions across the country. And a single RDC generally consists of many warehouses. When the warehouse group receives a customer order, it decides which warehouse or warehouses will produce the package for the customer order based on the category inventory in each warehouse.

[0003] However, the inventors found that when different items in a customer order are produced and fulfilled by different warehouses, it usually causes order splitting. That is, splitting an order package into multiple (at least two) packages. This will result in an increase in the number of packages corresponding to each customer order, increasing the split order rate (the ratio of the number of fulfillment packages generated by splitting a customer order to the number of customer orders), and increasing the logistics cost.

[0004] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0005] This summary of the disclosure is provided to introduce concepts in a brief form, which will be described in detail in the following detailed description section. This summary of the disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0006] Some embodiments of the present disclosure propose a method for adjusting item inventory, an apparatus for adjusting item inventory, an electronic device, a computer-readable medium, and a computer program product to solve one or more of the technical problems mentioned in the above background art section.

[0007] In a first aspect, some embodiments of the present disclosure provide a method for adjusting item inventory, including: determining an optimization goal according to the inventory distribution data of preset level-category items; constructing a data model using an operations research optimization method based on the optimization goal, where the data model is used to represent the situation of moving items from the warehouse where they are located to another warehouse; performing a solution process on the data model to obtain the item moving warehouse data; and moving the number of items indicated by the moving warehouse data from the first warehouse to the second warehouse according to the moving warehouse quantity and the warehouse indicated by the moving warehouse data.

[0008] In some embodiments, the optimization goal includes minimizing the number of item distribution warehouses of the same preset level-category and maximizing the correlation degree between each preset level-category within the same warehouse.

[0009] In some embodiments, based on the optimization objective, an operations research optimization method is used to construct a data model, including: for two preset-level categories, determining the correlation degree between the two categories according to historical order information, and determining the product value of the correlation degree and a first variable, where the first variable indicates whether the items of the two categories are in the same warehouse; constructing a category planning model based on the product value and a second variable to obtain the quantity of items of each preset-level category to be moved into or out of a specified warehouse, where the second variable indicates whether the items of each preset-level category are stored in a certain warehouse.

[0010] In some embodiments, the method further includes: determining the constraint conditions of the category planning model according to the inventory distribution data, where the constraint conditions include at least one of the following: the quantity of items of each preset-level category moved out of the warehouse is not greater than the existing inventory quantity of the items of the preset-level category in the warehouse; or the quantity of items of each preset-level category moved into the warehouse is not greater than the total inventory quantity of the items of the preset-level category in other warehouses except this warehouse; or the same warehouse does not simultaneously carry out the moving in and out of items of the same preset-level category; or using the warehouse where items are already stored; or the items stored in the warehouse cannot exceed the upper limit of the warehouse storage resources, where the upper limit of the warehouse storage resources includes at least one of the following: energy storage upper limit, production capacity upper limit, volume upper limit, and width upper limit of the minimum stock keeping unit; or at least one warehouse stores items of at least two preset-level categories simultaneously.

[0011] In some embodiments, the optimization objective further includes minimizing the value attribute consumed by the warehouse transfer.

[0012] In some embodiments, based on the optimization objective, using the operations research optimization method to construct a data model further includes: constructing a warehouse transfer plan model according to the solution result of the category planning model and the value attribute consumed by the transfer of a unit of inventory to obtain the corresponding relationship and the quantity of warehouse transfer of the items of each preset-level category between warehouses.

[0013] In some embodiments, the method further includes: using the solution result of the category planning model as the constraint condition of the warehouse transfer plan model.

[0014] In some embodiments, solving the data model includes: using a solver to solve the data model.

[0015] In a second aspect, some embodiments of the present disclosure provide an item inventory adjustment device, including: an optimization objective determination unit configured to determine an optimization objective according to the inventory distribution data of items of a preset level category; a mathematical model construction unit configured to construct a data model based on the optimization objective by using an operations research optimization method, where the data model is used to represent the situation of moving items from the warehouse where they are located to another warehouse; a model solution unit configured to perform a solution process on the data model to obtain the item warehouse transfer data; and an inventory adjustment unit configured to move the number of items indicated by the warehouse transfer data from a first warehouse to a second warehouse according to the warehouse transfer quantity and the warehouse indicated by the warehouse transfer data.

[0016] In some embodiments, the optimization objective may include minimizing the number of warehouses where items of the same preset level category are stored, and maximizing the correlation degree between each preset level category within the same warehouse.

[0017] In some embodiments, the mathematical model construction unit may further be configured to, for two preset level categories, determine the correlation degree between the two categories according to historical order information, and determine the product value of the correlation degree and a first variable, where the first variable represents whether the items of the two categories are in the same warehouse; and construct a category planning model based on the product value and a second variable to obtain the number of items of each preset level category moved into or out of a specified warehouse, where the second variable represents whether the items of each preset level category are stored in a certain warehouse.

[0018] In some embodiments, the device further includes a constraint condition determination unit configured to determine the constraint conditions of the category planning model according to the inventory distribution data, where the constraint conditions include at least one of the following: the number of items of each preset level category moved out of the warehouse is not greater than the existing inventory quantity of the items of the preset level category in the warehouse; or the number of items of each preset level category moved into the warehouse is not greater than the total inventory quantity of the items of the preset level category in other warehouses except the warehouse; or the same preset level category of items are not moved into and out of the same warehouse at the same time; or use the warehouse where the items are already stored; or the items stored in the warehouse cannot exceed the upper limit of the warehousing resources of the warehouse, where the upper limit of the warehousing resources includes at least one of the following: energy storage upper limit, production capacity upper limit, volume upper limit, and width upper limit of the minimum stock keeping unit; or at least one warehouse stores at least two preset level categories of items at the same time.

[0019] In some embodiments, the optimization objective may further include minimizing the value attribute consumed by the warehouse transfer.

[0020] In some embodiments, the mathematical model construction unit may further be configured to construct a warehouse transfer plan model according to the solution result of the category planning model and the value attribute consumed by the unit inventory warehouse transfer to obtain the corresponding relationship and the warehouse transfer quantity of the items of each preset level category moved between the warehouses.

[0021] In some embodiments, the constraint determination unit may further be configured to use the solution result of the category planning model as a constraint condition for the warehouse transfer plan model.

[0022] In some embodiments, the model solution unit may further be configured to perform a solution process on the data model by using a solver.

[0023] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, and when the one or more programs are executed by the one or more processors, the one or more processors implement the item inventory adjustment method described in any implementation manner of the first aspect above.

[0024] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the item inventory adjustment method described in any implementation manner of the first aspect above.

[0025] In a fifth aspect, some embodiments of the present disclosure provide a computer program product including a computer program, and the computer program, when executed by a processor, implements the item inventory adjustment method described in any implementation manner of the first aspect above.

[0026] The above various embodiments of the present disclosure have the following beneficial effects: The item inventory adjustment method of some embodiments of the present disclosure can effectively reduce the order splitting rate. Specifically, when current enterprises conduct category-based warehouse distribution planning, they generally determine the corresponding placement relationship between categories and warehouses based on the experience of business personnel. Since the number of categories and warehouses is large, the limiting factors to be considered are relatively complex. It is also necessary to accommodate the requirements of many operations. For example, it is necessary to take into account the attribute matching between categories and warehouses, the mutual exclusion relationship between categories, the handling of special warehouses and special categories, and various constraints such as warehouse resource limitations. Planning solely based on business experience not only takes a long time, but also it is difficult to optimize multiple indicators while taking into account numerous limiting factors, that is, to achieve the optimal planning of category-based warehouse distribution.

[0027] Based on this, the item inventory adjustment method of some embodiments of the present disclosure aims at the business scenario with complex category-based warehouse planning, replacing the past planning method that relied entirely on experience. Based on the modeling idea of operations research, the actual scenario is abstracted into a mathematical model, and mature optimization theories are used for solving. Finally, the mathematical solution is converted into an executable implementation plan for the business to guide the adjustment of the placement relationship of product warehouses. Against the background of the gradual maturity of the digital development of the supply chain, this technology further realizes the intelligence of supply chain decision-making. Based on the mature operations research and optimization theory, it helps the business to formulate an executable and optimal category-based warehouse plan. Thus, it can effectively make up for the one-sidedness and short-sightedness of decision-making based on experience, and maximize the achievement effect of the established business goals. By optimizing the category planning in the warehouse, the warehousing management efficiency can be systematically improved, and the order splitting rate can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0029] Figure 1 is a flowchart of some embodiments of the item inventory adjustment method of the present disclosure;

[0030] Figure 2 is a flowchart of some other embodiments of the item inventory adjustment method of the present disclosure;

[0031] Figures 3A - 3C is a schematic diagram of the effect comparison of inventory optimization using the method of the present disclosure;

[0032] Figure 4 is a schematic structural diagram of some embodiments of the item inventory adjustment device of the present disclosure;

[0033] Figure 5 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0035] It should also be noted that for the convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0036] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules or units.

[0037] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless clearly specified otherwise in the context, it should be understood as "one or more".

[0038] Figure 1 Flow 100 of some embodiments of the item inventory adjustment method according to the present disclosure is shown. The method may include the following steps:

[0039] Step 101, determine an optimization goal according to the inventory distribution data of preset category items.

[0040] In some embodiments, the execution subject of the item inventory adjustment method (such as the management system server of a warehouse group) may determine an optimization goal according to the inventory distribution data of preset category items in the warehouse group it manages. Here, the preset category can be set according to the actual situation. Generally, in the warehousing and logistics industry, items are usually divided into three levels, namely, first-level categories, second-level categories, and third-level categories. Among them, a first-level category usually includes multiple second-level categories, and a second-level category usually includes multiple third-level categories. The above preset category can be a third-level category. The optimization goal here can represent the goal expected to be achieved through optimization and improvement, such as the index to be improved, the value of the improved index, etc. As an example, the optimization goal can be to minimize the number of item sub-warehouses of the same preset category.

[0041] Step 102, based on the optimization goal, construct a data model using an operations research optimization method.

[0042] In some embodiments, based on the optimization goal determined in step 101, the execution subject can use an operations research optimization method to construct a mathematical model. Among them, the data model can be used to represent the situation of moving items from the warehouse where they are located to another warehouse.

[0043] It should be noted that the core of this solution is an inventory adjustment optimization method for category sub-warehouse planning. As Figure 2As shown in the figure, first, the actual business scenario of category warehouse division is abstracted into a standard operational optimization problem on the technical side. The operational optimization problem here generally includes three elements: 1) decision-making elements, which are the elements that can be influenced to achieve the goal, and the corresponding business execution plan; 2) optimization goals, which are the indicators expected to be improved; 3) restriction factors, which are the business rules that need to be followed during the optimization process. By mathematically expressing the above three elements with custom mathematical symbols, a mathematical model can be established.

[0044] Here, the business-side problem is described as follows: In the category warehouse planning problem solved by this solution, when the inventory of each category is dispersed among multiple warehouses, the order splitting rate of customer orders will increase, the number of packages generated will increase, and the logistics fulfillment cost will also increase accordingly. At the same time, it will also cause the supplier's supply locations to be dispersed, reducing the supplier's supply experience. By adjusting the inventory layout of the goods and placing highly related goods in the same warehouse as much as possible, the logistics fulfillment costs caused by order splitting can be effectively reduced. Placing goods of the same category in the same warehouse as much as possible can achieve centralized supply from suppliers and improve the supplier's supply experience. At the same time, when adjusting the inventory layout, it is necessary to take into account the resource limitations of the warehouse (energy storage, production capacity, volume, and SKU width) and balance the resource utilization between warehouses.

[0045] At this point, the above description can be abstracted into a technical problem: In the above-mentioned category warehouse division problem, the decision factor is to determine the inventory adjustment plan for the goods. That is, the inventory quantity of a third-level category moved from one warehouse to another, or equivalently, the proportion of the inventory quantity to the total inventory of the entire third-level category (hereinafter referred to as the inventory ratio). The optimization goal is to maximize the category correlation within the same warehouse and minimize the number of third-level category warehouses by adjusting the inventory layout. At the same time, the cost of moving warehouses should be reduced as much as possible. The optimization is limited by the warehouse storage resources.

[0046] Here, through problem abstraction, a single-stage mathematical model with triangle-labeled decision variables can be established. In this mathematical model, the decision variables can be It represents the proportion of inventory of (level 3) category i moved from warehouse j1 to warehouse j2.

[0047] It should be noted that the mathematical model of the triangle mark may lead to a large scale of decision variables and be difficult to solve. For example, within an RDC, the number of third-level categories is 3,000+ and the number of warehouses is 100+. This will result in a scale of decision variables in the tens of millions. Using a mathematical solver to solve such a large-scale problem will be very inefficient, and it is likely that the optimal solution cannot be obtained within a reasonable time, or even a satisfactory feasible solution cannot be obtained.

[0048] By analyzing the characteristics of the category-based warehousing planning problem, the inventor found that the category planning decision (decision on the transfer ratio) and the transfer plan decision (decision on the transfer relationship) do not affect each other and can be decoupled. Moreover, reducing the order splitting rate has a higher priority than optimizing the transfer cost. Therefore, the single-stage triangular label mathematical model can be decomposed into a two-stage double-label mathematical model, which can effectively reduce the scale of solution.

[0049] In some embodiments, as Figure 2 shown, in the two-stage double-label mathematical model, the category planning model in the first stage can decide the transfer ratio x ij . Among them, the transfer-in ratio can be and the transfer-out ratio can be That is, the inventory ratio of category i transferred into or out of warehouse j. That is to say, determine the transfer-in or transfer-out ratio of each third-level category in each warehouse. And the transfer plan model in the second stage can, for each third-level category i, decide and determine the detailed transfer plan That is, the inventory ratio of category i transferred from warehouse j1 to warehouse j2.

[0050] Furthermore, that is to say, in some embodiments, the above optimization objectives can be split into two. The first optimization objective can include minimizing the number of warehouses for items of the same preset-level category and maximizing the correlation between preset-level categories within the same warehouse. That is, a) Minimize the number of warehouses for third-level categories b) Maximize the correlation between third-level categories placed in the same warehouse At this time, the mathematical model in the first stage can be the category planning model. The elements to be decided in this stage are the transfer-in or transfer-out ratio or quantity of items of each preset-level category from each warehouse.

[0051] Among them, I represents the total number of third-level categories in a group of warehouses; J represents the total number of warehouses in a group of warehouses; represents the correlation between category i1 and category i2; is a 0-1 variable, represents that category i1 and category i2 are placed in the same warehouse, otherwise, z ij is a 0-1 variable, z ij =1 represents that category i is placed in warehouse j, otherwise, z ij =0.

[0052] In some embodiments, the category planning model can be obtained through the following construction method: First, for any two preset-level categories, the correlation degree between the two categories can be determined according to historical order information, and the product value of the correlation degree and the first variable can be determined. For example, the number (or proportion) of times the two categories appear simultaneously in the historical customer orders can be used for approximate substitution. Among them, the first variable can indicate whether the items of the two categories are in the same warehouse. Then, based on the product value and the second variable, a category planning model is constructed to obtain the quantity of items of each preset-level category moved into or out of a specified warehouse. Among them, the second variable can indicate whether the items of each preset-level category are stored in a certain warehouse. As an example, the maximization of the difference between the sum value of the product values and the sum value of the second variable can be used as the category planning model.

[0053] It can be understood that since the correlation degree of products under the same third-level category is often relatively high. Therefore, minimizing the number of third-level category warehouses not only improves the supplier's supply experience and realizes centralized supply, but also increases the correlation degree of categories placed in the same warehouse. Therefore, the above category planning model can also determine the weighted difference between the two. And a greater weight can be given to objective a) here, such as the sum of the correlation degrees of each category can be taken.

[0054] In addition, in order to make the solution result feasible, the resource limitations of the warehouse also need to be considered. That is to say, the constraint conditions of the category planning model can also be determined according to the inventory distribution data. Among them, the constraint conditions can include at least one of the following: the quantity of items of each preset-level category moved out of the warehouse is not greater than the existing inventory quantity of the items of this preset-level category in the warehouse; or the quantity of items of each preset-level category moved into the warehouse is not greater than the total inventory quantity of the items of this preset-level category in other warehouses except this warehouse; or the items of the same preset-level category are not moved into and out of the same warehouse at the same time; or use the warehouse where the items are already stored; or the items stored in the warehouse cannot exceed the upper limit of the warehouse storage resources, where the upper limit of the warehouse storage resources includes at least one of the following: energy storage upper limit, production capacity upper limit, volume upper limit, and width upper limit of the smallest stock keeping unit (SKU); or at least one warehouse stores items of at least two preset-level categories at the same time.

[0055] Specifically,

[0056] (1) The proportion of the third-level category i moved out of the warehouse j cannot exceed the existing inventory proportion of the third-level category i in the warehouse j; at the same time, the proportion of the third-level category i moved into the warehouse j cannot exceed the total inventory proportion of the third-level category i in the remaining warehouses except the warehouse j.

[0057] (2) State and behavior relationship: Constraining that the category i in the warehouse j will not be moved in and out at the same time.

[0058] (3) Warehouse usage relationship: If there is inventory in warehouse j, then this warehouse is used (u j = 1). If warehouse j is not used (u j = 0), then there cannot be inventory in this warehouse.

[0059] (4) Warehouse resource constraints: The goods placed in warehouse j cannot exceed the upper limit of the warehouse resources of this warehouse (including the energy storage upper limit Q j , production capacity upper limit P j , volume upper limit V j , SKU width upper limit O j ).

[0060] (5) Category association relationship: If at least one warehouse has both category i1 and category i2 at the same time, it means that these two categories are associated

[0061] By solving the category planning model in the first stage, the specific proportions of category i moving into or out of warehouse j can be obtained under the goals of minimizing the number of category warehouses and maximizing the category association degree (represented by and respectively). Next, by establishing a second-stage warehouse transfer plan model for each category i, the corresponding relationship and proportion of the movement of this category between warehouses are optimized under the goal of minimizing the warehouse transfer cost.

[0062] Optionally here, the second optimization goal can include minimizing the value attribute consumed by the warehouse transfer (such as the warehouse transfer cost). At this time, the execution entity can construct a warehouse transfer plan model based on the solution result of the category planning model and the value attribute consumed by the transfer of unit inventory, so as to obtain the corresponding relationship and the number of warehouse transfers of the items of each preset-level category between warehouses.

[0063] It should be noted that for category u between warehouse j1 and warehouse j2 For category i, the latter two are generally constants. Therefore, the warehouse transfer plan model can be simplified to: minimizing the sum of the products of the warehouse transfer ratio and the warehouse transfer cost per unit inventory .

[0064] Similarly, when solving the warehouse transfer plan model, constraint conditions also need to be considered. As an example, the solution result of the category planning model can be used as the constraint condition of the warehouse transfer plan model. For example, the warehouse transfer ratio can be no greater than the transfer-in ratio or transfer-out ratio obtained from the category planning model. That is, the warehouse transfer constraint can be: the ratio of moving into or out of the warehouse is equal to the optimal ratio of the category planning model in the first stage.

[0065] Step 103: Solve the data model to obtain the warehousing transfer data of the items.

[0066] In some embodiments, the execution subject may solve the data model in Step 102 to obtain the warehousing transfer data of the items. Among them, the warehousing transfer data may be data representing the adjustment of the inventory in different warehouses of the items, such as the above-mentioned transfer-in or transfer-out ratio (or quantity), the storage relationship (corresponding relationship and quantity) between the items and the warehouses, etc. The solution method here is not limited either. For example, it can be solved by using the written program code, or for another example, a solver can be used to solve the data model. Among them, the solver may include but is not limited to at least one of the following: Gurobi, IBM ILOG Cplex, SCIP, MOSEK, etc. Currently, Gurobi is the solver with the highest solving efficiency and the most extensive use. In most cases, the time for other solvers to obtain the optimal solution will be longer than that of Gurobi. Therefore, Gurobi solver can be preferentially adopted here.

[0067] It should be noted that compared with the single-stage triangular label model, the above two-stage inventory adjustment model can greatly reduce the solving scale of the model, and the optimal solution can be obtained within minutes by using the Gurobi solver.

[0068] Step 104: According to the warehousing quantity and the warehouse indicated by the warehousing transfer data, transfer the items with the warehousing quantity from the first warehouse to the second warehouse.

[0069] In some embodiments, the execution subject may generate a control instruction according to the warehousing transfer data, so as to control the relevant equipment to transfer the items with the warehousing quantity from the first warehouse to the second warehouse according to the warehousing quantity and the warehouse indicated by the warehousing transfer data. Among them, the first warehouse is usually the warehouse to be transferred out. And the second warehouse is usually the warehouse to be transferred in.

[0070] Through the above description, the item inventory adjustment method of some embodiments of the present disclosure can abstract this complex optimization problem into a quantifiable mathematical model. And based on the operation research optimization theory, the model is solved to obtain a category warehousing planning scheme that can be implemented by the business, so as to realize the adjustment of the corresponding relationship and inventory quantity between the items and the warehouses. By minimizing the number of warehouses for items of the same preset-level category, the scattered storage situation of items of the same category can be improved, and thus the order splitting rate can be effectively reduced.

[0071] It should be noted that from Figure 2As can be seen, data input is also required to obtain a mathematical solution from a mathematical model. However, the original data (including inventory snapshots, warehouse information, etc.) often cannot be directly used, and there are problems such as missing data, duplicate data, and inaccurate data. Therefore, it is necessary to involve the business for data review and verification, and data cleaning is carried out by means of deleting error and duplicate data, filling in missing data, etc. Then, through data preprocessing means such as inventory normalization, it is organized into a data structure that matches the model. Combining the processed data (i.e., preprocessed data) to solve the model can obtain the optimal mathematical solution. Transforming the mathematical solution can obtain a business-understandable and executable plan. Among them, Figure 2 The solid line in it represents the technical implementation process; the dotted line represents the data flow or information flow.

[0072] Through the method of the embodiments of the present disclosure, the following technical effects can be achieved:

[0073] First of all, the order splitting rate can be reduced, and the order fulfillment cost can be reduced. When the inventory of each category is relatively dispersed among multiple warehouses, it will lead to order splitting when fulfilling customer orders, generating additional packages and increasing the order fulfillment cost. In addition, when optimizing the placement between multiple warehouses of the same RDC, if the correlation between categories in the customer order structure is considered and the categories with high correlation are placed in the same warehouse as much as possible, the number of packages generated by order splitting can be further reduced. Thus, the customer order splitting rate is reduced, and the logistics full-link fulfillment cost is reduced.

[0074] Secondly, the number of category warehouse allocations can be reduced, and the merchant's delivery experience can be improved. When the inventory of each category is relatively dispersed among multiple warehouses, the number of category warehouse allocations is relatively large, which generally leads to the need for merchants to arrange multiple vehicles to deliver to multiple warehouses when delivering goods to the warehouse. This often increases the complexity of delivery, and at the same time, the delivery volume to each warehouse is reduced and economies of scale cannot be formed, resulting in a relatively high delivery cost.

[0075] Finally, the utilization rate of warehousing resources can be optimized and balanced. When there is a phenomenon that best-selling products are concentrated in a certain warehouse in the category planning scheme, and there are large differences in the utilization rates of production capacity and energy storage between different warehouses, and the resource utilization is unbalanced. By adjusting the placement relationship of product warehouses and using the elastic peak-shifting of production capacity and energy storage to meet different demands for warehouse resources within a certain period of time, the maximization of the unit area warehouse flow efficiency and floor efficiency is realized. That is, in the fourth constraint of the category planning model, the storage volume and production volume allocated to the warehouse are restricted not to exceed the upper limits of the energy storage and production capacity of the warehouse to handle this problem. In this way, it can be forced that best-selling products will not be overly concentrated.

[0076] In some application scenarios, taking a certain RDC as an example, by using the item inventory adjustment method of the embodiments of the present disclosure, the following can be obtained Figures 3A to 3C the optimization effect as shown. From Figure 3AIt can be seen that after the optimization of the model, the order splitting rate and the annual number of packages have decreased by approximately 2.65%. The package fulfillment costs saved by this RDC in one year are approximately in the tens of millions. From Figure 3B It can be seen that although the optimization target is the number of sub-warehouses for the third-level categories, it also indirectly leads to a decrease in the number of sub-warehouses for the first-level and second-level categories. Compared with before the optimization, the number of sub-warehouses for the first-level, second-level, and third-level categories has decreased by 19.55%, 30.36%, and 25.55% respectively. The decrease in the number of category sub-warehouses can, on the one hand, promote the reduction of the order splitting rate, and on the other hand, it can also improve the supply experience of suppliers, achieve centralized supply, and reduce the complexity and cost of delivery. In addition, from Figure 3C It can be seen that through the optimization of the model, the utilization rate of warehousing resources has also been effectively improved. The placement of goods is more concentrated, which can free up spare warehouses and further save warehouse rental costs.

[0077] In summary, the two-stage inventory adjustment optimization method proposed in this patent can, compared with the traditional experience-based product warehouse planning method, efficiently output the category sub-warehouse planning scheme, effectively reduce the number of category sub-warehouses, reduce the package fulfillment costs caused by order splitting, and improve the utilization rate of warehousing resources.

[0078] The technological innovation points of this solution are mainly divided into two parts. The first is for the complex business scenario of category sub-warehouse planning. Instead of the past planning method that completely relies on experience, based on the modeling idea of operations research, the actual scenario is abstracted into a mathematical model, and the mature optimization theory is used for solution. Finally, the mathematical solution is converted into an executable implementation plan for the business to guide the business to adjust the relationship of product warehouse placement to achieve the global optimal effect. The second is that the conventional modeling idea for operations optimization is a single-stage triangular label model, which will lead to a huge solution scale and very low solution efficiency. The present invention disassembles it into a two-stage mathematical model through analyzing the problem characteristics, including the category planning model in the first stage and the warehouse relocation plan model in the second stage. Thus, the model solution efficiency can be greatly improved.

[0079] Further referring to Figure 4 , as an implementation of the above Figure 1 , 2 shown methods, the present disclosure provides some embodiments of an item inventory adjustment device. These device embodiments correspond to Figure 1 , 2 shown method embodiments. This device can be specifically applied to various electronic devices.

[0080] Such as Figure 4As shown, the item inventory adjustment device 400 of some embodiments may include: an optimization goal determination unit 401, configured to determine an optimization goal according to the inventory distribution data of preset level category items; a mathematical model construction unit 402, configured to construct a data model using an operations research optimization method based on the optimization goal, where the data model is used to characterize the situation of moving items from the warehouse where they are located to another warehouse; a model solution unit 403, configured to perform a solution process on the data model to obtain the item warehouse transfer data; and an inventory adjustment unit 404, configured to move the items in the quantity indicated by the warehouse transfer data from the first warehouse to the second warehouse according to the warehouse transfer quantity and the warehouse indicated by the warehouse transfer data.

[0081] In some embodiments, the optimization goal may include minimizing the number of item warehouse partitions of the same preset level category and maximizing the correlation degree between each preset level category in the same warehouse.

[0082] In some embodiments, the mathematical model construction unit 402 may be further configured to, for two preset level categories, determine the correlation degree between the two categories according to historical order information, determine the product value of the correlation degree and a first variable, where the first variable indicates whether the items of the two categories are in the same warehouse; and construct a category planning model based on the product value and a second variable to obtain the quantity of items of each preset level category moved into or out of a specified warehouse, where the second variable indicates whether the items of each preset level category are stored in a certain warehouse.

[0083] In some embodiments, the device 400 may further include a constraint condition determination unit (not shown in the figure), configured to determine the constraint conditions of the category planning model according to the inventory distribution data, where the constraint conditions include at least one of the following: the quantity of items of each preset level category moved out of the warehouse is not greater than the existing inventory quantity of the items of the preset level category in the warehouse; or the quantity of items of each preset level category moved into the warehouse is not greater than the total inventory quantity of the items of the preset level category in other warehouses except this warehouse; or the same preset level category items are not moved into and out of the same warehouse at the same time; or use the warehouse where the items are already stored; or the items stored in the warehouse cannot exceed the upper limit of the warehouse storage resources, where the upper limit of the warehouse storage resources includes at least one of the following: energy storage upper limit, production capacity upper limit, volume upper limit, and width upper limit of the minimum stock keeping unit; or at least one warehouse stores at least two preset level categories of items at the same time.

[0084] In some embodiments, the optimization goal may further include minimizing the value attribute consumed by the warehouse transfer.

[0085] In some embodiments, the mathematical model construction unit 402 may further be configured to construct a warehouse transfer plan model based on the solution result of the category planning model and the value attribute of the unit inventory warehouse transfer consumption, so as to obtain the corresponding relationship and the warehouse transfer quantity of the items of each preset-level category moving between warehouses.

[0086] In some embodiments, the constraint condition determination unit may further be configured to use the solution result of the category planning model as the constraint condition of the warehouse transfer plan model.

[0087] In some embodiments, the model solution unit 403 may further be configured to perform a solution process on the data model by using a solver.

[0088] It can be understood that the units described in the item inventory adjustment device 400 correspond to the respective steps in the method described with reference Figure 1 、 2 Therefore, the operations, features, and beneficial effects described above for the method also apply to the item inventory adjustment device 400 and the units included therein, and will not be elaborated herein.

[0089] Next, with reference to Figure 5 , there is shown a schematic structural diagram of an electronic device 500 suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0090] As Figure 5 shown, the electronic device 500 may include a processing device 501 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0091] Generally, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a speaker, a vibrator, etc.; a storage device 508 including, for example, a memory card, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 5An electronic device 500 with various devices is shown, but it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had. Figure 5 Each block shown in Figure 5 may represent a device or, as needed, multiple devices.

[0092] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program code for performing the methods shown in the flowcharts. In such some embodiments, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, the above functions defined in the methods of some embodiments of the present disclosure are performed.

[0093] It should be noted that the computer-readable medium described in some embodiments of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in some embodiments of the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0094] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0095] The above computer-readable medium can be included in the above electronic device; or can exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to: determine an optimization goal according to the inventory distribution data of preset category items; based on the optimization goal, construct a data model using an operations research optimization method, where the data model is used to characterize the situation of moving items from the warehouse where they are located to another warehouse; perform a solution process on the data model to obtain the item transfer data; and move the quantity of items indicated by the transfer data from the first warehouse to the second warehouse according to the transfer quantity and the warehouse indicated by the transfer data.

[0096] In addition, computer program code for performing the operations of some embodiments of the present disclosure can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0098] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes an optimization objective determination unit, a mathematical model construction unit, a model solution unit, and an inventory adjustment unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the optimization objective determination unit can also be described as "a unit for determining an optimization objective based on the inventory distribution data of preset category items".

[0099] The functions described above herein can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0100] Some embodiments of the present disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any one of the above-described item inventory adjustment methods.

[0101] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure.

Claims

1. An article inventory adjustment method, comprising: Determining an optimization objective according to the inventory distribution data of preset category items; Based on the optimization objective, constructing a data model by using an operations research optimization method, wherein the data model is used to represent the situation of moving articles from the warehouse where they are located to another warehouse; Performing a solution process on the data model to obtain the warehouse transfer data of the articles; According to the warehouse transfer quantity and the warehouse indicated by the warehouse transfer data, moving the articles of the warehouse transfer quantity from the first warehouse to the second warehouse.

2. The method for adjusting the inventory of items according to claim 1, wherein, The optimization objective includes minimizing the number of warehouses where articles of the same preset category are stored, and maximizing the correlation degree among preset categories in the same warehouse.

3. The article inventory adjustment method according to claim 2, wherein, The constructing a data model by using an operations research optimization method based on the optimization objective includes: For two preset category items, determining the correlation degree between the two categories according to historical order information, and determining the product value of the correlation degree and a first variable, wherein the first variable indicates whether the articles of the two categories are in the same warehouse; Based on the product value and a second variable, constructing a category planning model to obtain the quantity of articles of each preset category moving into or out of a specified warehouse, wherein the second variable indicates whether the articles of each preset category are stored in a certain warehouse.

4. The method for adjusting the inventory of items according to claim 3, wherein, The method further includes: determining the constraint conditions of the category planning model according to the inventory distribution data, wherein the constraint conditions include at least one of the following: The quantity of articles of each preset category moving out of the warehouse is not greater than the existing inventory quantity of the articles of the preset category in the warehouse; or The quantity of articles of each preset category moving into the warehouse is not greater than the total inventory quantity of the articles of the preset category in other warehouses except this warehouse; or In the same warehouse, the moving in and out of articles of the same preset category are not carried out simultaneously; or Using the warehouses where articles are already stored; or The articles stored in the warehouse cannot exceed the upper limit of the warehousing resources of the warehouse, wherein the upper limit of the warehousing resources includes at least one of the following: energy storage upper limit, production capacity upper limit, volume upper limit, and width upper limit of the minimum stock keeping unit; or At least one warehouse stores at least two preset category items simultaneously.

5. The article inventory adjustment method according to claim 3, wherein, The optimization objective further includes minimizing the value attribute consumed by warehouse transfer.

6. The method for adjusting the inventory of items according to claim 5, wherein, The constructing a data model by using an operations research optimization method based on the optimization objective further includes: According to the solution result of the category planning model and the value attribute consumed by the transfer of a unit inventory, constructing a warehouse transfer plan model to obtain the corresponding relationship and the warehouse transfer quantity of the articles of each preset category moving between warehouses.

7. The article inventory adjustment method according to claim 6, wherein, The method further includes: using the solution result of the category planning model as the constraint condition of the warehouse transfer plan model.

8. The inventory adjustment method according to any one of claims 1-7, wherein, The performing a solution process on the data model includes: Using a solver to perform a solution process on the data model.

9. An article inventory adjustment device, comprising: An optimization objective determination unit configured to determine an optimization objective according to the inventory distribution data of preset category items; A mathematical model construction unit, configured to construct a data model using an operations research optimization method based on the optimization objective, wherein the data model is used to characterize the situation of moving items from the warehouse where they are located to another warehouse; A model solving unit, configured to perform a solving process on the data model to obtain the item warehouse transfer data; An inventory adjustment unit, configured to move the quantity of the items from the first warehouse to the second warehouse according to the warehouse transfer quantity and the warehouse indicated by the warehouse transfer data.

10. An electronic device, comprising: One or more processors; A storage device having stored thereon one or more programs, When the one or more programs are executed by the one or more processors, enabling the one or more processors to implement the item inventory adjustment method according to any one of claims 1-8.

11. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the item inventory adjustment method according to any one of claims 1-8.

12. A computer program product, comprising a computer program which, when executed by a processor, implements the item inventory adjustment method according to any one of claims 1-8.

Images