CN112330235A

CN112330235A - Data processing method and device for inventory management, electronic equipment and medium

Info

Publication number: CN112330235A
Application number: CN202010145263.7A
Authority: CN
Inventors: 蒋宁宁; 许晔
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2020-03-04
Filing date: 2020-03-04
Publication date: 2021-02-05

Abstract

The present disclosure provides a data processing method for inventory management. The method comprises the following steps: acquiring goods to be stored and classification attributes of the goods to be stored; determining the number of classification attributes of the goods to be stored in an attribute set I, wherein the attribute set I is set as a set consisting of classification attributes of goods in all orders performed from a plurality of storehouses in a preset historical time period; and based on the warehouse inventory layout variable X_ijDetermining a storehouse for storing the goods to be stored, wherein X is_ijIs used for indicating whether goods with classification attribute with number i should be stored in the storeroom with number J, wherein J belongs to J, J is a candidate storehouse set which is set to be a set obtained based on the information of the storerooms; whereinSaid warehouse inventory layout variable X_ijSolving the layout optimization model constructed by the operational research optimization method. The present disclosure also provides a data processing apparatus, an electronic device, and a medium for inventory management.

Description

Data processing method and device for inventory management, electronic equipment and medium

Technical Field

The present disclosure relates to the field of warehouse logistics, and more particularly, to a data processing method, a data processing apparatus, an electronic device, and a medium for inventory management.

Background

The logistics industry has developed very rapidly in recent years. After the consumer purchases goods on line, the merchant can pick the goods from the storehouse according to the purchase order of the consumer, generate a package and then deliver the package. If a consumer has purchased goods stored in different storehouses, the goods are delivered from different storehouses, namely, the contract is performed from different storehouses.

It is common in the prior art to adjust empirically which storeroom different goods should be placed in. However, if the storage layout of the goods between different storehouses is not reasonable enough, it may result in that a purchase by the customer requires the delivery of goods from more storehouses, increasing the cost of performing. In addition, because the hot selling degrees of different goods are different, when the goods with different hot selling degrees are not stored in all storeroom rooms in a balanced manner, some storerooms may be discharged quickly and need to be replenished continuously, and the stock backlog of some storerooms is large. Such imbalance may cause imbalance in the workload of personnel among different warehouses, etc., which is not conducive to management. These increasingly prominent problems are essentially impossible to control and solve completely by human experience. Therefore, there is a need for a more scientific and reasonable way to guide the selection of the storage of goods in the warehouse to optimize the inventory and performance of the warehouse.

Disclosure of Invention

In view of the above, the present disclosure provides a data processing method, apparatus, system, and medium for inventory management more scientifically and reasonably.

One aspect of the present disclosure provides a data processing method for inventory management. The method comprises the following steps: acquiring goods to be stored and classification attributes of the goods to be stored; determining a number of classification attributes of the goods to be deposited in an attribute set I, wherein the attribute set I is set as a score possessed by goods in all orders performed from a plurality of stores within a predetermined historical period of timeA collection of class attributes; and based on the warehouse inventory layout variable X_iiDetermining a storehouse for storing the goods to be stored, wherein X is_ijIs used to indicate whether goods with classification attribute of number i should be stored in the warehouse of number J, wherein J is belonged to J, J is a candidate warehouse set which is set to a set obtained based on the information of the plurality of warehouses. Wherein the warehouse inventory layout variable X_ijAnd solving a layout optimization model which is constructed by an operational research optimization method based on the inventory information and performance information of the plurality of storehouses in the preset historical time period and is used for optimizing the storage layout of the goods in the plurality of storehouses.

According to the embodiment of the present disclosure, the method further includes constructing the layout optimization model, specifically including: obtaining information of the storehouses to obtain the candidate storehouse set J, wherein J belongs to J, and J is the serial number of the storehouses; acquiring an order set K formed by all orders performing in the plurality of storehouses in the preset historical time period, wherein the K belongs to the K, and the K is the serial number of the order; acquiring a set of classification attributes of all goods related to the order set K to obtain an attribute set I, wherein I belongs to I, and I represents the serial number of the classification attributes; constructing the warehouse inventory layout variable X_ij，

X_ijThe system is used for indicating whether goods with classification attributes of the number i should be stored in a storeroom of the number j; construction warehouse performance variable Y_kj，

Wherein, Y_kjFor indicating whether the order numbered k should perform from the store numbered j: constructing the warehouse inventory layout variable X based on the relationship between the inventory and the performance of the plurality of warehouses_ijAnd said warehouse performance variable Y_kjA constraint condition between; using said warehouse inventory layout variable X_ijSaid warehouse performance variable Y_kjThe constraint condition is used for constructing the layout optimization model by applying an operation and research optimization method; and obtaining X in the solution of the layout optimization model_ijAnd obtaining storage layout information used for guiding the goods in different storehouses.

According to an embodiment of the disclosure, the method for applying operational research optimization to construct the layout optimization model includes constructing a first objective function based on a minimum policy of splitting:

wherein the minimum order splitting strategy represents that the sum of times of performing from each warehouse of all orders in the order set K is minimized, wherein each order performs to one warehouse once.

According to an embodiment of the disclosure, the method for applying operational research optimization to construct the layout optimization model includes constructing a second objective function based on a balanced inventory strategy:

Min(U₀-L₀)

wherein U is₀And L₀The upper limit and the lower limit of the inventory amount per unit capacity of all the warehouses in the candidate warehouse set J are respectively set, and the balanced inventory policy represents that the difference between the upper limit and the lower limit of the inventory amount per unit capacity of all the warehouses in the candidate warehouse set J is minimized.

According to an embodiment of the disclosure, the method for applying operational research optimization to construct the layout optimization model includes constructing a third objective function based on a balanced production order strategy:

Min(U₁-L₁)

wherein, U₁And L₁Wherein the balanced production order policy indicates that a difference between an upper limit and a lower limit of the production order per unit capacity of all the warehouses in the candidate warehouse J is minimized.

According to an embodiment of the disclosure, the method for applying operational research optimization to construct the layout optimization model includes constructing a fourth objective function based on a combination of a minimum inventory splitting strategy, a balanced inventory strategy and a balanced production order strategy:

min θ₀∑_k∈K∑_j∈JY_kj+θ₁(U₀-L₀)+θ₂(U₁-L₁)

wherein the content of the first and second substances,

∑_k∈K∑_j∈JY_kjthe objective function expression is used for representing a minimum order splitting strategy and representing the sum of times of performing the contract from each warehouse of all orders in the order set K;

U₀-L₀expression for an objective function representing a balanced inventory based policy, where U₀And L₀Respectively representing the upper limit and the lower limit of the inventory amount of each warehouse in the candidate warehouse set J;

U₁-L₁for expressing an objective function expression based on a balanced production order strategy, where U₁And L₁The upper limit and the lower limit of the production unit quantity of each warehouse in the candidate warehouse set J;

θ₁、θ₂、θ₃is a weight coefficient, wherein₁+θ₂+θ₃＝1。

According to an embodiment of the present disclosure, the method for applying operational research optimization to construct the layout optimization model further includes: selecting at least one optimization strategy from a minimum order splitting strategy, a balanced inventory strategy and a balanced production order strategy; and setting θ based on the at least one optimization strategy₁、θ₂And theta₃The value of (c).

According to an embodiment of the present disclosure, the constructing the warehouse inventory layout variable X_ijFurther comprising: set up X_ij∈{0，1}，

Wherein, X _ij1 indicates that there is a shipment with a classification attribute of number iStoring in a storeroom numbered j, otherwise X_ij0. Constructing the warehouse performance variable Y_kjFurther comprising: set up Y_kj∈{0，1}，

Wherein, Y _kj1 represents an order numbered k fulfilling from the store numbered j, otherwise Y_kj0. Constructing a warehouse inventory layout variable X based on the relationship between the plurality of warehouses' inventory and performance_ijAnd a warehouse performance variable Y_kjThe constraint conditions in between include: the constraint condition Y is set based on the restriction that goods performing from the store numbered j necessarily belong to the stock numbered j_kj≤∑_i∈IX_ij，

And X_ij≤Y_kj，

According to an embodiment of the present disclosure, building a warehouse inventory layout variable X based on the relationship between the inventory and the performance of the plurality of warehouses_ijAnd a warehouse performance variable Y_kjThe constraint between further comprising: the goods with the same classification parameter number in each order are arranged to perform from one storehouse with constraint condition sigma_j∈JX_ij＝1，

According to an embodiment of the present disclosure, building a warehouse inventory layout variable X based on the relationship between the inventory and the performance of the plurality of warehouses_ijAnd a warehouse performance variable Y_kjThe constraint between further comprising: setting the actual capacity constraint condition of each warehouse based on the actual capacity upper and lower limits of each warehouse:

and

wherein the content of the first and second substances,

a_irepresenting a total number of inventories of the goods having the classification attribute of number i;

c_jthe upper capacity limit of storehouse j; and

d_jlower capacity limit of warehouse j.

According to an embodiment of the present disclosure, the method further comprises at least a part X in the solution based on the layout optimization model_ijAnd at least a part of Y_kjAnd obtaining the warehouse layout optimization index.

According to an embodiment of the present disclosure, the classification attribute includes an attribute of at least one dimension of a brand, an item class, or a SKU.

In another aspect of the present disclosure, a data processing apparatus for inventory management is provided. The device comprises an acquisition module, a first determination module and a second determination module. The acquisition module is used for acquiring the goods to be stored and the classification attributes of the goods to be stored. The first determination module is used for determining the number of the classification attribute of the goods to be stored in an attribute set I, wherein the attribute set I is set as a set consisting of classification attributes of the goods in all orders of multiple storeroom fulfillment in a preset historical time period. The second determination module is to base the inventory layout variable X on the warehouse_ijDetermining a storehouse for storing the goods to be stored, wherein X is_ijIs used to indicate whether goods with classification attribute of number i should be stored in the warehouse of number J, wherein J is belonged to J, J is a candidate warehouse set which is set to a set obtained based on the information of the plurality of warehouses. Wherein the warehouse inventory layout variable X_ijSolving a layout optimization model constructed by an operation research optimization method based on the inventory information and performance information of the plurality of storehouses in the preset historical time periodAnd changing the storage layout of the goods in the plurality of storerooms.

According to an embodiment of the present disclosure, the apparatus further comprises a model building module. The model building module includes an optimization object filter, a policy issuer, and an inventory layout optimizer. The optimized object filter is to: obtaining the information of the storehouses to obtain the candidate storehouse set J, wherein J belongs to J, and J is the serial number of the storehouses; acquiring an order set K formed by all orders performing in the plurality of storehouses in the preset historical time period, wherein the K belongs to the K, and the K is the serial number of the order; and acquiring a set of classification attributes of all goods related to the order set K to obtain an attribute set I, wherein I belongs to I, and I represents the serial number of the classification attributes. The policy issuing device is used for: constructing the warehouse inventory layout variable X_ij，

X_ijThe system is used for indicating whether goods with classification attributes of the number i should be stored in a storeroom of the number j; constructing the warehouse performance variable Y_kj，

Wherein, Y_kjFor identifying whether the order numbered k should perform from the store numbered j; constructing the warehouse inventory layout variable X based on the relationship between the inventory and the performance of the plurality of warehouses_ijAnd said warehouse performance variable Y_kjA constraint condition between; and utilizing said warehouse inventory layout variable X_ijSaid warehouse performance variable Y_kiAnd the constraint condition is used for constructing the layout optimization model by applying an operation and research optimization method. The inventory layout optimizer is used for acquiring warehouse inventory layout variables X in the solution of the layout optimization model_ijAnd obtaining storage layout information used for guiding the goods in different storehouses.

According to an embodiment of the present disclosure, the policy issuer is further configured to: constructing a fourth objective function based on the combination of the minimum inventory splitting strategy, the balance inventory strategy and the balance production inventory strategy:

min θ₀∑_k∈K∑_j∈JY_kj+θ₁(U₀-L₀)+θ₂(U₁-L₁)

wherein the content of the first and second substances,

θ₁、θ₂、θ₃is a weight coefficient, wherein₁+θ₂+θ₃＝1。

According to an embodiment of the present disclosure, the policy issuer is further configured to: selecting at least one optimization strategy from a minimum order splitting strategy, a balanced inventory strategy and a balanced production order strategy; and setting θ based on the at least one optimization strategy₁、θ₂And theta₃The value of (c).

According to an embodiment of the present disclosure, the apparatus further comprises an inventory layout optimization effect calculator. The inventory layout optimization effect calculator to calculate at least a portion X of the solution based on the layout optimization model_ijAnd at least a part of Y_kiAnd obtaining the warehouse layout optimization index.

In another aspect of the present disclosure, an electronic device is provided. The electronic device includes one or more memories, and one or more processors. The memory stores executable instructions. The processor executes the executable instructions to implement the method as described above.

In another aspect of the present disclosure, a computer-readable storage medium is provided, having executable instructions stored thereon, which when executed by a processor, cause the processor to perform the method as described above.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.

Another aspect of the disclosure provides a computer program comprising computer executable instructions for implementing the method as described above when executed.

According to the embodiment of the disclosure, the storehouses where the goods to be stored should be stored are determined more scientifically based on the layout optimization model, and in this way, the storage of the goods in different storehouses is optimally guided through the historical order fulfillment data, so that the overall operation cost of each storehouse can be at least partially reduced, and therefore, the technical effect of improving the inventory management efficiency can be achieved.

Drawings

For a more complete understanding of the present disclosure and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario of a data processing method, apparatus, system and medium for inventory management according to an embodiment of the present disclosure;

FIG. 2A schematically illustrates a flow diagram of a data processing method for inventory management according to an embodiment of the present disclosure;

FIG. 2B schematically illustrates a flow diagram for building a layout optimization model in a data processing method for inventory management according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a warehouse inventory layout variable X in accordance with an embodiment of the disclosure_ijSchematic of the matrix formed;

FIG. 4 schematically illustrates a repository performance variable Y according to an embodiment of the disclosure_kiSchematic of the matrix formed;

FIG. 5A schematically illustrates a block diagram of a data processing apparatus for inventory management according to an embodiment of the present disclosure;

FIG. 5B schematically shows a block diagram of a model building module according to an embodiment of the disclosure;

FIG. 6 schematically illustrates an application example flowchart of the data processing method and apparatus for inventory management according to an embodiment of the present disclosure;

FIG. 7 schematically illustrates another application example flowchart of the data processing method and apparatus for inventory management according to an embodiment of the present disclosure;

FIG. 8 schematically illustrates yet another application example flowchart of the data processing method and apparatus for inventory management according to an embodiment of the present disclosure;

FIG. 9 schematically illustrates a flow diagram of yet another example application of a data processing method and apparatus for inventory management, in accordance with an embodiment of the present disclosure;

FIG. 10 schematically illustrates a flow diagram of yet another example application of a data processing method and apparatus for inventory management, in accordance with an embodiment of the present disclosure; and

fig. 11 schematically shows a block diagram of an electronic device adapted to implement a data processing method for inventory management according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

Some block diagrams and/or flow diagrams are shown in the figures. It will be understood that some blocks of the block diagrams and/or flowchart illustrations, or combinations thereof, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the instructions, which execute via the processor, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks. The techniques of this disclosure may be implemented in hardware and/or software (including firmware, microcode, etc.). In addition, the techniques of this disclosure may take the form of a computer program product on a computer-readable storage medium having instructions stored thereon for use by or in connection with an instruction execution system.

Practice of the disclosureThe embodiment provides a data processing method and device for inventory management, an electronic device and a medium. The method comprises the steps of obtaining information of a plurality of storehouses needing to be optimized to obtain a candidate storehouse set J; acquiring an order set K formed by all orders performing in a preset historical time period from a plurality of storehouses; acquiring a set of classification attributes of all goods related to the order set K to obtain an attribute set I; variable X for stock layout of construction warehouse_ij，

Construction warehouse performance variable Y_kj，

Building X based on relationships between inventory and fulfillment of multiple stores_ijAnd Y_kjA constraint condition between; by using X_ij、Y_kjThe constraint condition is used for constructing a layout optimization model by applying an operation and research optimization method; and obtaining all xs in the solution of the layout optimization model_ijThe value of (a) is obtained to be used for guiding the storage layout information of the goods in different storehouses.

According to the embodiment of the disclosure, the storeroom where the goods to be stored should be stored is determined more scientifically based on the layout optimization model, in this way, the storage of the goods in different storerooms can be optimally guided through the historical order fulfillment data, the overall operation cost of each storeroom can be at least partially reduced, and therefore the technical effect of improving the inventory management efficiency can be achieved.

Fig. 1 schematically illustrates an application scenario 100 of a data processing method, apparatus, system and medium for inventory management according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a scenario in which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the application scenario 100 may include

terminal devices

101, 102, 103, a mall server 104, and

warehouse servers

105A, 105B, 105C. The

warehouse servers

105A, 105B, and 105C are respectively the inventory management servers corresponding to the warehouse A, B, C.

The

terminal devices

101, 102, 103 and the mall server 104 may be connected to each other via a wired or wireless network. The consumer may use the

terminal devices

101, 102, 103 to interact with the mall server 104 over a network to receive or send messages or the like. The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as shopping applications.

The mall server 104 may be a server that provides various services, such as a background management server (for example only) that provides support for a consumer's website that utilizes shopping-like applications browsed by the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

The consumer can browse for goods or purchase goods by operating in the user interface of the shopping application in the

terminal device

101, 102, 103. The mall server 104 may obtain the purchase order formed by the consumer in one purchase operation according to each payment operation of the consumer.

The mall server 104 and the

warehouse servers

105A, 105B, and 105C may be connected to each other via a wired or wireless network. The mall server 104 may divide each purchase order into at least one order according to the storage condition of the goods involved in each purchase order in the storage A, B, C, wherein the goods of each order are stored in one storage, so that one order can perform from one storage. The mall server 104 may then distribute the orders resulting from splitting the purchase order to the corresponding

warehouse servers

105A, 105B, 105C.

When each of the

storeroom servers

105A, 105B, and 105C receives an order fulfilled by the local storeroom, package production is performed according to the order, and the packages subjected to production and processing are loaded into a transport vehicle for shipment. In addition, each store needs to carry forward shipments before performing its contract. The

warehouse servers

105A, 105B, 105C may also update the current inventory condition of each warehouse (the current inventory quantity of each type of goods, whether the goods are out of stock, whether replenishment is needed, etc.) according to the goods in and out condition of the warehouse A, B, C, and may feed the current inventory condition back to the mall server 104, so that the mall server 104 comprehensively plans splitting of purchase orders and distribution of orders, and feeds back the available supply state of the goods to the

terminal devices

101, 102, 103.

It can be seen that inventory, parcel production, and shipment are involved in inventory management. In the process of stocking and storing, labor and material resources are consumed to perform the tasks of stocking/replenishing, unloading, stacking and the like. In the wrapping production link, manpower and material resources are consumed for wrapping production. And manpower and material resources are consumed to carry out package loading, vehicle transportation and the like in the cargo sending link. Therefore, if the storage layout of the goods among the different storehouses is not reasonable enough, it may result in splitting a purchase order into a large number of orders, so that a purchase order for a customer needs to be performed from more storehouses. If the goods stored in different storehouses have large difference of hot sales degree, some storehouses have busy work and some storehouses have overstocked work. This imbalance can cause uneven personnel workload between different warehouses, which is not conducive to management.

In view of this, the present disclosure provides a data processing method, apparatus, system and medium for inventory management, which apply an operation optimization method to construct a layout optimization model to optimize storage layouts of goods in different warehouses by using order fulfillment data and the like of each warehouse within a predetermined historical time period. Therefore, goods to be stored can be determined according to the solving result of the layout optimization model, the goods to be stored can be stored in which storeroom, so that goods can be scientifically and reasonably distributed and stored in the storerooms, the goods storage situation or the goods storage situation between different storerooms is more balanced, the parcel production operation situation or the goods transportation situation between different storerooms is more balanced, the overall operation cost of each storeroom is reduced to at least a certain extent, and the inventory management efficiency is improved.

It should be noted that the data processing method for inventory management provided by the embodiment of the present disclosure may be generally performed by the mall server 104. Accordingly, the data processing apparatus for inventory management provided by the embodiments of the present disclosure may be generally disposed in the mall server 104. The data processing method for inventory management provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the mall server 104 and is capable of communicating with the

warehouse servers

105A, 105B, 105C and/or the mall server 104. Accordingly, the data processing apparatus for inventory management provided by the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the mall server 104 and capable of communicating with the

warehouse servers

105A, 105B, 105C and/or the mall server 104.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

FIG. 2A schematically illustrates a flow diagram of a data processing method for inventory management according to an embodiment of the disclosure.

As shown in fig. 2A, the data processing method for inventory management according to an embodiment of the present disclosure may include operations S110 to S130. According to other embodiments of the present disclosure, the data processing method for inventory management may further include operation S100 before operation S110.

Specifically, in operation S100, a layout optimization model is constructed. The layout optimization model is a data processing model which is constructed by an operation and research optimization method based on the inventory information and performance information of the storehouses in the preset historical time period. Reference may be made in particular to the relevant description below.

In operation S110, goods to be stored and a classification attribute of the goods to be stored are acquired.

In operation S120, a number of classification attributes of the goods to be stored in an attribute set I is determined, wherein the attribute set I is set to a set consisting of classification attributes of goods in all orders performed from a plurality of stores within a predetermined historical period of time.

In operation S130, a variable X is laid out based on the warehouse inventory_ijDetermining a storehouse for storing the goods to be stored, wherein X is_ijIs used to indicate whether goods with classification attribute of number i should be stored in the warehouse of number J, wherein J is belonged to J, J is a candidate warehouse set which is set to a set obtained based on the information of the plurality of warehouses. The warehouse inventory layout variable X_ijAnd solving the layout optimization model.

X corresponding to the classification attribute of the goods to be stored_ijTo determine the warehouse in which the goods to be stored are stored.

For example, if X is set_ij∈{0，1}，

Wherein, X _ij1 goods representing the classification attribute of number i are stored in the store of number j, otherwise X_ij0. If the attribute set I is a set of product categories, for example, attribute set I ═ shampoo, facial cleanser, body wash, bed sheet, quilt cover, … }, where each classification attribute in the attribute set I is numbered according to its order in the attribute set I. If the goods to be stored is the bed sheet, the number of the classification attribute of the goods to be stored is 4 in operation S120. Then X, which is 1, is taken in operation S130_4jJ in (2) is the serial number of the storehouse for storing the sheet, namely, the goods to be stored can be stored in the storehouse with the serial number j.

In this way, the storeroom in which the goods to be stored should be stored can be determined more scientifically based on the layout optimization model, so that the goods storage can be distributed among the plurality of storerooms in a more scientific manner.

Fig. 2B schematically shows a flowchart of operation S100 of building a layout optimization model in the data processing method for inventory management according to an embodiment of the present disclosure.

As shown in fig. 2B, operation S100 may include operations S201 to S208 according to an embodiment of the present disclosure.

In operation S201, information of a plurality of storehouses that need to be optimized is obtained, and a candidate bin set J is obtained, where J belongs to J, and J is a serial number of the storehouses.

In operation S202, an order set K formed from all orders performed from a plurality of warehouses within a predetermined historical time period is obtained, where K ∈ K, K being the number of the order. The predetermined historical time period may be, for example, within a half year, or within a quarter. As described above, the order here is obtained by splitting a purchase order generated by a single purchase action of the consumer. The goods in an order are stored in a warehouse from which fulfillment can be performed.

In operation S203, a set of classification attributes of all the goods related to the order set K is obtained, and an attribute set I is obtained, where I belongs to I, and I represents a number of the classification attribute. The classification attribute is the granularity with which the statistics and classification of the good are performed.

According to an embodiment of the present disclosure, the classification attributes include attributes of at least one dimension of a brand, a class, or a SKU (Stock Keeping Unit). The categories may be, for example, categories of goods in the sales segment. For example, a facial cleanser, a body wash, and a shampoo may be provided in different categories. For example, if the attribute set I is a set of goods, in one embodiment, the attribute set I ═ shampoo, facial cleanser, body wash, bed sheet, quilt cover. Of course, the attribute set I may be a set composed of attribute parameters of multiple dimensions such as categories and brands of goods.

In operation S204, a warehouse inventory layout variable X is constructed_ij，

X_ijIndicating whether the goods having the classification attribute of number i are stored in the storage of number j. In particular, warehouse inventory layout variablesX_ijReference may be made to the schematic of fig. 3.

FIG. 3 schematically illustrates a warehouse inventory layout variable X in accordance with an embodiment of the disclosure_ijSchematic of the matrix formed.

As shown in FIG. 3, the warehouse inventory layout variable X_ijThe horizontal axis of the formed matrix graph represents each attribute I of the attribute set I, and the vertical axis represents each warehouse J of the candidate warehouse set J. Each position X in the matrix_ijThe value of (d) represents whether the goods having the classification attribute of number i are stored in the warehouse of number j. Therefore, the whole matrix reflects the condition whether goods with various classification attributes are stored in various storehouses or not on the whole.

X_ijBelonging to a boolean parameter with two selectable values. According to an embodiment of the present disclosure, for convenience of calculation, X may be set in operation S204_ij∈{0，1}，

Wherein, X _ij1 indicates that goods with classification attribute of number i are stored in the store of number j, otherwise X_ij0. For example, if the classification attribute is a product, the product corresponding to i ═ 1 is assumed to be shampoo, and the number of warehouse a is 1. Then X is used when shampoo goods are stored in the storehouse A ₁₁1 is ═ 1; when the storehouse A does not store shampoo, X₁₁＝0。

Thus, when all X's are obtained_ijAfter the values are taken, the storage conditions of the goods with various classification attributes in different storehouses can be determined clearly from the matrix shown in fig. 3.

In operation S205, a warehouse performance variable Y is constructed_kj，

Wherein, Y_kjIndicating whether the order numbered k performs from the store numbered j. More specifically, the warehouse performance variable Y_kjReference may be made to the schematic of fig. 4.

FIG. 4 is a schematic view ofIllustratively shows a library performance variable Y according to an embodiment of the disclosure_kjSchematic of the matrix formed.

As shown in FIG. 4, the warehouse performance variable Y_kjThe horizontal axis of the formed matrix diagram represents each order K of the order set K, and the vertical axis represents each warehouse J of the candidate warehouse set J. Each position Y in the matrix_kiThe value of (b) represents whether the order numbered k performs from the store numbered j. Thus, the overall matrix reflects the performance of each order in each warehouse as a whole.

Y_kjBelonging to a boolean parameter with two selectable values. According to an embodiment of the present disclosure, Y may be set in operation S205 for convenience of calculation_kj∈{0，1}，

Wherein, Y _kj1 represents an order numbered k fulfilling from the store numbered j, otherwise Y_kj＝0。

Thus, when all Y's are obtained_kjAfter the value of (a) is obtained, the performance of each order in different storehouses can be clearly determined from the matrix shown in fig. 4.

In operation S206, a warehouse inventory layout variable X is constructed based on the relationship between the inventory of the plurality of warehouses and the performance_ijAnd a warehouse performance variable Y_kiA constraint in between. Hereinafter with X_ij∈{0，1}、Y_kjE {0, 1} to illustratively introduce X_ijAnd Y_kjThe constraint of (2).

As an alternative example, the constraint condition may be set in operation S206 based on a limit that goods performing from the store numbered j necessarily belong to the inventory in the store numbered j, as follows:

the following description will be made of the formulae (c) and (d) with reference to fig. 3 and 4. For equation (c), all of the goods for any kth order that performs from store j must come from all of the goods stored in store j. For equation (d), any k-th order fulfilling from store j may come from one or more categories stored in that store j.

Or as another alternative, in operation S206, the goods with the same classification parameter number in each order may also be set to perform from a warehouse, and the constraint condition is as follows:

in conjunction with fig. 3, formula (b) limits that goods with a certain classification attribute in an order can only perform from one store, but not from two or more stores. Such restrictions may reduce order fulfillment costs, reducing the cost increase for a consumer's purchase of a certain type of goods, one part performing from one store and another part performing from another store.

As still another alternative, in operation S206, an actual capacity constraint condition of each warehouse may also be set based on the upper and lower limits of the actual capacity of each warehouse, which are as follows:

wherein the content of the first and second substances,

c_jthe upper capacity limit of storehouse j; and

d_jlower capacity limit of warehouse j.

The capacity of the warehouse is the size of the space for accommodating goods determined according to the physical form of the warehouse. According to embodiments of the present disclosure, the capacity of the warehouse may be measured in pieces of inventory for simplicity of calculation. The goods with different forms can be combined or converted, and the like, so that the goods with different classifications measured by taking the piece as a basic unit occupy basically similar or equivalent volumes.

In operation S207, a warehouse inventory layout variable X is utilized_ijWarehouse performance variable Y_kjAnd the constraint condition is used for constructing a layout optimization model by applying an operation and research optimization method.

In operation S208, all xs in the solution of the layout optimization model are obtained_ijThe value of (a) is obtained to be used for guiding the storage layout information of the goods in different storehouses.

When there is a valid solution for the layout optimization model, all xs_ijThe values of (a) form a matrix as shown in fig. 3, and the storage conditions of the goods of various attributes in different storehouses can be clearly shown at a glance. The existence of an effective solution to the layout optimization model means, for example, all xs_ijIs not all zero. When all X_ijIf the values of (1) are all 0, no effective solution exists in the layout optimization model, which indicates that no optimization space exists in the existing inventory management according to the layout optimization model of the embodiment of the present disclosure.

According to the embodiment of the disclosure, the inventory layout problem is solved by converting the artificial experience planning into the linear model which can be solved by the general operational optimization tool, and the inventory layout optimization system can be constructed by flexibly configuring the granularity (namely, classification attribute) of the optimized commodity inventory layout, so that the design of the inventory layout is more scientific and reasonable. Furthermore, for goods to be stored, the solution result X of the layout optimization model can be used_ijTo determine which warehouse the goods to be stored should be stored in (as shown in figure 3). In this way, the goods storage can be scientifically and reasonably distributed in a plurality of storehouses, so that the goods entering and exiting situations or the goods storage situations among different storehouses are more balanced, and/or different storehousesThe parcel production operation condition between the rooms, the goods transportation condition and the like are more balanced, so that the overall operation cost of each warehouse is reduced to at least a certain extent, and the inventory management efficiency is improved.

According to an embodiment of the present disclosure, constructing the layout optimization model in operation S207 may be constructing a first objective function based on a minimum splitting policy, as follows (a.1):

Min ∑_k∈K∑_j∈JY_kj (a.1)

wherein the minimum order splitting strategy represents that the sum of times of performing the orders from each storeroom in the order set K is minimized, wherein each order performs to one storeroom once. With reference to fig. 4, equation (a.1) represents the smallest sum of the values at all positions in the matrix, i.e. the lowest cost of performing for all orders, so as to achieve the lowest cost of shipping and transporting for all warehouses.

According to another embodiment of the present disclosure, constructing the layout optimization model in operation S207 may be constructing a second objective function based on the balanced inventory policy, as shown in the following formula (a.2):

Min(U₀-L₀) (a.2)

wherein U is₀And L₀Respectively, the upper limit and the lower limit of the inventory amount per unit capacity of all the warehouses in the candidate warehouse set J. The balanced inventory policy represents the minimization of the difference between the upper and lower limits of inventory per unit capacity for all stores in the candidate set of bins J. The amount of inventory per unit capacity of each store may be the amount of inventory in that store divided by the capacity of that store, in such a way that the amount of inventory in each store is normalized to make the inventory of the different stores comparable. The upper limit and the lower limit of the stock quantity under the unit capacity of all the storehouses are limited to be minimum by the formula (a.2), so that the stock level under the unit capacity of all the storehouses can be limited in a relatively balanced range, the phenomenon of unbalanced storage of goods with different hot selling degrees in each storehouse is reduced, and the cost of goods storage management of each storehouse is balanced.

According to another embodiment of the present disclosure, constructing the layout optimization model in operation S207 may be constructing a third objective function based on the balanced production order strategy, as shown in the following formula (a.3):

Min(U₁-L₁) (a.3)

wherein, U₁And L₁Upper and lower limits of production units per unit capacity for all warehouses in the intermediate candidate warehouse set J. The balanced production order strategy represents that the difference between the upper limit and the lower limit of the production order quantity in unit capacity of all the storehouses in the candidate warehouse set J is minimized. The unit volume of production per unit capacity of each store may be the number of executions of the store divided by the capacity of the store, in such a way that the number of executions of each store is normalized to make the performance of the different stores comparable. The upper limit and the lower limit of the production unit quantity of all storehouses under the unit capacity are limited to be minimum through the formula (a.3), and the production unit quantity level of all storehouses under the unit capacity can be limited in a relatively balanced range, so that the cost of package production links of all storehouses is balanced.

According to an embodiment of the present disclosure, constructing the layout optimization model in operation S207 may be constructing a fourth objective function based on a combination of the minimum splitting policy, the balance inventory policy, and the balance production order policy, as shown in the following formula (a.4):

min θ₀∑_k∈K∑_j∈JY_kj+θ₁(U₀-L₀)+θ₂(U₁-L₁) (a.4)

wherein the content of the first and second substances,

∑_k∈K∑_j∈JY_kjthe system is used for expressing an objective function expression based on a minimum order splitting strategy and representing the sum of times of performing the contract from each warehouse of all orders in the order set K;

U₀-L₀expression for an objective function representing a balanced inventory based policy, where U₀And L₀Respectively the upper limit and the lower limit of the inventory amount of each warehouse in the candidate warehouse set J under the unit capacity;

U₁-L₁for expressing an objective function expression based on a balanced production order strategy, where U₁And L₁Well candidate binThe upper limit and the lower limit of the production unit quantity of each warehouse in the set J under the unit capacity;

θ₁、θ₂、θ₃is a weight coefficient, wherein₁+θ₂+θ₃＝1。

Further, according to an embodiment of the present disclosure, when the fourth objective function (equation (a.4)) is constructed when the layout optimization model is constructed in operation S207, at least one optimization strategy may be selected from the minimum order splitting strategy, the balance inventory strategy, and the balance production order strategy based on a user operation or a preset, and θ may be set based on the at least one optimization strategy₁、θ₂And theta₃The value of (c).

According to the method of the embodiment of the present disclosure, after operation S208, at least a part X of the solution based on the layout optimization model may be further performed_ijAnd at least a part of Y_kjAnd obtaining the warehouse layout optimization index. E.g. according to sigma obtained by solving after optimization_k∈K∑_j∈JY_kjThe comparison of the value of (a) and the number of performing times of all orders before optimization can obtain the number of performing times saving after optimization, and can also calculate the change of indexes such as the number of storehouses used for performing the orders before and after optimization of the storehouse layout optimization model, the utilization rate of the storehouse capacity, the production order quantity of the storehouse unit capacity and the like.

Fig. 5A schematically shows a block diagram of a data processing device 500 for inventory management according to an embodiment of the present disclosure.

As shown in fig. 5A, the data processing apparatus 500 may include an acquisition module 510, a first determination module 520, a second determination module 530, and a model building module 540. The apparatus 500 may be used to perform the method described with reference to fig. 2A and 2B.

The obtaining module 510 may perform operation S110, for example, to obtain the goods to be stored and the classification attribute of the goods to be stored.

The first determining module 520 may perform operation S120, for example, for determining the number of classification attributes of the goods to be deposited in an attribute set I, wherein the attribute set I is set as a set consisting of classification attributes of the goods in all orders performed from a plurality of stores within a predetermined historical period of time.

The second determination module 530 may perform operation S130, for example, for placement of variables X based on warehouse inventory_ijDetermining a storehouse for storing goods to be stored, wherein X_ijIs used to indicate whether goods with classification attribute of number i should be stored in the warehouse of number J, where J is J, J is a candidate warehouse set as a set derived based on information of a plurality of warehouses. Wherein, the stock layout variable X_ijThe method is used for solving a layout optimization model which is constructed by an operation research optimization method and is based on inventory information and performance information of a plurality of storehouses in a preset historical time period, and the layout optimization model is used for optimizing the storage layout of goods in the plurality of storehouses.

The model building module 540 may, for example, perform operation S100 for building a layout optimization model.

FIG. 5B schematically shows a block diagram of a model building module 540 according to an embodiment of the disclosure.

As shown in FIG. 5B, the model building module 540 may include an optimization object filter 541, a policy issuer 542, an inventory layout optimizer 543, and an inventory layout optimization effect calculator 544. The model building module 540 may be used to implement the method described with reference to fig. 2B.

The optimized object filter 541 may, for example, perform operations S201 to S203, and is configured to obtain information of a plurality of warehouses that need to be optimized, to obtain a candidate warehouse set J, where J belongs to J, and J is a serial number of the warehouse; acquiring an order set K formed by all orders performing in a preset historical time period, wherein the K belongs to the K, and the K is the serial number of the order; and acquiring a set of classification attributes of all goods related to the order set K to obtain an attribute set I, wherein I belongs to I, and I represents the serial number of the classification attributes.

The policy issuer 542, for example, may perform operations S204-S207 for constructing the warehouse inventory layout variable X_ij，

X_ijThe system is used for indicating whether goods with classification attributes of the number i are stored in a storeroom of the number j or not; construction warehouse performance variable Y_kj，

Wherein, Y_kjThe order form is used for identifying whether the order form with the number k performs from the storeroom with the number j or not; building a warehouse inventory layout variable X based on the relationship between inventory and performance of multiple warehouses_ijAnd a warehouse performance variable Y_kjA constraint condition between; and using the warehouse inventory layout variable X_ijWarehouse performance variable Y_kjAnd the constraint condition is used for constructing a layout optimization model by applying an operation and research optimization method.

The inventory layout optimizer 543 can perform operation S208, for example, for obtaining the warehouse inventory layout variables X in the solution of the layout optimization model_ijThe value of (a) is obtained to be used for guiding the storage layout information of the goods in different storehouses.

The inventory layout optimization effect calculator 544 can be used for at least a portion X in the solution based on the layout optimization model_ijAnd at least a part of Y_kjAnd obtaining the warehouse layout optimization index.

According to an embodiment of the present disclosure, the policy issuer 542 may also be configured to construct a first objective function based on a minimum splitting policy, as in equation (a.1). Alternatively, according to the embodiment of the present disclosure, the policy issuer 542 may be further configured to construct a second objective function based on the balanced inventory policy, as shown in equation (a.2). Still alternatively, according to the embodiment of the present disclosure, the policy issuing unit 542 may be further configured to construct a third objective function based on the balanced production single policy, as shown in equation (a.3).

Still alternatively, according to an embodiment of the present disclosure, the policy issuer 542 is further configured to construct a fourth objective function, as shown in equation (a.4), based on a combination of the minimum splitting policy, the balanced inventory policy, and the balanced production order policy. Further, according to an embodiment of the present disclosure, the policy issuer 542 is further configured to balance inventory policies, balance production, and a minimum policy for stripping ordersSelecting at least one optimization strategy from the single strategies, and setting theta in the formula (a.4) based on the at least one optimization strategy₁、θ₂And theta₃The value of (c).

The following describes an implementation of building a layout optimization model in the data processing method and apparatus for inventory management according to the embodiments of the present disclosure with reference to several specific application examples of fig. 6 to fig. 10. It is to be understood that these examples are merely illustrative of the principles and spirit of the disclosed embodiments and that no limitation on the disclosed embodiments is intended thereby.

FIG. 6 is a flow chart that schematically illustrates an example application of the data processing method and apparatus for inventory management, in accordance with an embodiment of the present disclosure.

Referring to fig. 6, in conjunction with fig. 5B, in the data processing apparatus 500, the model building module 540 may include an optimization object filter 541, a policy issuing unit 542, an inventory layout optimizer 543, and an inventory layout optimization effect calculator 544.

Optimization object filter 541 may receive information selected by a user for a plurality of stores that need to be optimized, all orders to perform from the plurality of stores within a predetermined historical period of time, and all shipments involved in the orders have a classification attribute or granularity (SKU, class, brand, etc.).

The policy issuer 542 may apply an operation optimization method to construct a layout optimization model. Wherein, the objective function of the layout optimization model in the application instance may be a fourth objective function, i.e. equation (a.4). Meanwhile, the policy issuing unit 542 may further select a specific policy for optimizing the inventory layout, for example, at least one optimization policy selected from a minimum order splitting policy, a balance inventory amount policy, and a balance production order policy.

The inventory layout optimizer 543 calculates values of the variables that build the layout optimization model, thereby obtaining a solution for the inventory layout.

The inventory layout optimization effect calculator 544 may calculate an inventory index optimization case, such as a case where the order number is decreased, a change before and after the optimization of the generation of the individual amount by each warehouse, a change before and after the optimization of the inventory amount by each warehouse, and the like, based on the inventory layout solution output by the calculation inventory layout optimizer 543.

With continued reference to FIG. 6, the application instance may include operations S601-S607.

First, in operation s601, a user may receive information of a plurality of stores selected by the user to be optimized, all orders to perform from the plurality of stores within a predetermined historical period of time, and classification attributes or granularities (SKUs, categories, or brands) of all goods involved in the orders, through the optimization object filter 541. For example, when the selected warehouse is A, B, C three warehouses and the granularity of the goods optimizing the inventory layout is a class, the goods in A, B, C three warehouses are redistributed in A, B, C three warehouses according to the dimension of the class.

Then, in operation S602, the policy issuer 542 may apply the operation research optimization method to construct a layout optimization model (e.g., construct a fourth objective function — equation (a.4)), and the user selects at least one optimization policy through the policy issuer 542. For example, one or more optimization strategies are selected from a minimum inventory strategy, a balanced inventory strategy, and a balanced production order strategy. If there is no check optimization policy, operation S603 is performed, and if there is a check optimization policy, operation S604 is performed.

Specifically, the process of constructing the layout optimization model by applying the operational research optimization method is as follows:

TABLE 1 data set of layout optimization model

i∈I	I is the item number, and I is the set of all the items.
		j∈J	J is the storehouse number and J is the set of all candidate bins.
k∈K	K is the order number and K is the set of all orders.

Table 2, input parameters of the layout optimization model:

a_i	total number of inventory pieces for brand I, I ∈ I.
		c_j	The upper limit of the capacity of the storehouse J, J belongs to J.
d_j	The lower limit of the capacity of the storehouse J, J belongs to J.
		e_j	The total capacity of the warehouse J, J ∈ J.
θ_l	The weight coefficient set by the user is more than or equal to 0 and more than or equal to theta_l≤1，0≤l≤2。

Table 3, the decision variables were constructed:

then, based on the parameters in tables 1 to 3, a layout optimization model is constructed:

an objective function:

min θ₀w₀∑_k∈K∑_j∈JY_kj+θ₁w₁(U₀-L₀)+θ₂w₂(U₁-L₁) (a.4)

constraint conditions are as follows:

wherein, the formula (a.4) is a fourth objective function constructed based on the combination of the minimum inventory splitting strategy, the balance inventory strategy and the balance production order strategy;

formula (b) limits that a certain class of goods in an order can only perform from one store, but not from two or more stores;

equation (c) limits all of the goods of any kth order that was covered from store j to necessarily come from all of the goods stored in store j;

equation (d), any k-th order fulfilling from storeroom j may come from one or more categories stored in storeroom j;

limiting the inventory of the warehouse by formulas (g) and (h);

limiting the warehouse order throughput;

the formulae (k) and (l) limit X_ijAnd Y_kjThe value of (a).

In operation S603, when only one optimization strategy is selected, the coefficient in the equation (a.4) corresponding to the optimization strategy is set to 1, and the others are set to 0.

In operation S604, when a plurality of optimization strategies are selected, weight coefficients of the strategies may be set according to user input, where the weight values are θ_l，0≤θ_l≤1，0≤l≤2。

In operation S605, the inventory layout optimizer 543 solves the layout optimization model, resulting in an inventory layout optimization result.

In operation S606, the result output by the layout optimization modelIn (C) X_ijThe status of the inventory layout may be indicated. If X is_ijIf all the data are 0, the layout optimization model has no effective solution, and no stock layout optimization result exists, and the process is finished; if X is_ijIf not all are 0' S, then the inventory layout optimization results are present and operation S607 continues.

In operation S607, the result solved by the inventory layout optimizer 543 is passed to the inventory layout optimization effect calculator 544. The inventory layout optimization effect calculator 544 calculates changes in the indexes such as the number of warehouses used for performance before and after optimization of the layout optimization model, the utilization rate of the warehouse capacity, and the unit volume production of the warehouses.

FIG. 7 is a flow chart that schematically illustrates another example application of the data processing method and apparatus for inventory management, in accordance with an embodiment of the present disclosure.

As shown in fig. 7, the application example may include operations S701 to S705.

In operation S701, the user selects A, B, C storehouses requiring stock layout and c upper limit of capacity of each storehouse through the optimized object filter₀、c₁、c₂The lower limit of the capacity is d₀、d₁、d₂The granularity of optimizing the inventory layout of the goods is brand, and the policy selected by the policy issuer 542 is a minimize policy for splitting orders.

In operation S702, it is determined that there is no check for the optimization policy, and thus θ is set₀＝1，θ₁＝0，θ₂＝0。

In operation S703, the inventory layout optimizer 543 acquires the layout optimization model, outputs a result X by calculating an optimal solution_ij。

In operation S704, X is determined_ijWhether all are 0. If so, it is ended, and if not, operation S705 is performed.

In operation S705, a change in the total number of executions (corresponding to the number of orders split into purchase orders) before and after the optimization of the inventory layout is calculated in the inventory layout optimization effect calculator 544 according to the result of the optimization of the inventory layout.

In the present application example, when θ₀＞0，θ₁＝0，θ₂An inventory optimization layout method based purely on a policy of minimizing ticket splitting is provided when being equal to 0.

FIG. 8 schematically illustrates a flowchart of yet another example application of the data processing method and apparatus for inventory management, in accordance with an embodiment of the present disclosure.

As shown in fig. 8, the application example may include operations S801 to S805.

In operation S801, the user selects A, B, C storehouses requiring stock layout and c upper limit of capacity of each storehouse by the optimized object filter₀、c₁、c₂The lower limit of the capacity is d₀、d₁、d₂The granularity of the optimized commodity inventory layout is the category, and the strategy selected by the strategy issuing device is a balanced inventory strategy.

In operation S802, it is determined that there is no check for the optimization strategy, and thus θ is set₀＝0，θ₁＝1，θ₂＝0。

In operation S803, the inventory layout optimizer 543 acquires the layout optimization model, outputs the result X by calculating an optimal solution_ij。

In operation S804, X is determined_ijWhether all are 0. If so, it is ended, and if not, operation S805 is performed.

In operation S805, the change of the total number of executions (corresponding to the number of orders split into purchase orders) before and after the optimization of the inventory layout is calculated in the inventory layout optimization effect calculator 544 according to the result of the optimization of the inventory layout.

In the present application example, θ₀＝0，θ₁＞0，θ₂0, an inventory layout optimization method based purely on a balanced inventory strategy is provided. The limiting conditions (e) and (f) control the inventory capacity through upper and lower limits, so that the layout optimization model can be solved as a linear problem.

FIG. 9 schematically illustrates a flow chart of yet another example of an application of the data processing method and apparatus for inventory management according to an embodiment of the present disclosure.

As shown in fig. 9, the application instance may include operations S901 to S905.

In operation S901, the warehouse where the inventory layout is required is selected A, B, C and the upper limit of the capacity of each warehouse is c by the optimized object filter 541₀、c₁、c₂The lower limit of the capacity is d₀、d₁、d₂The granularity of the optimized commodity inventory layout is a category, and the strategies selected by the strategy down-maker 542 are a minimum order splitting strategy and a balanced production order strategy.

In operation S902, it is determined that the optimization strategy is checked, and then θ may be set₀＝0.6，θ₁＝0，θ₂＝0.4。

In operation S903, the inventory layout optimizer 543 acquires the layout optimization model, outputs a result X by calculating an optimal solution_ij。

In operation S904, X is determined_ijWhether all are 0. If so, it is ended, and if not, operation S905 is performed.

In operation S905, a change in the total number of executions (corresponding to the number of orders split into purchase orders) before and after the optimization of the inventory layout is calculated in the inventory layout optimization effect calculator 544 according to the result of the optimization of the inventory layout.

In the present application example, θ₀＞0，θ₁＝0，θ₂And the inventory optimization layout method based on the minimum order splitting strategy and the balanced production order strategy is provided and is more than 0. The limiting conditions (g) and (h) control the production unit quantity of the storehouse through upper and lower limits, so that the layout optimization model can be used as a linear problem to be solved.

FIG. 10 schematically illustrates a flow chart of yet another example of an application of the data processing method and apparatus for inventory management according to an embodiment of the present disclosure.

As shown in fig. 10, the application instance may include operations S1001 to S1005.

In operation S1001, the warehouse where the inventory layout is required is selected as A, B, C and the upper limit of the capacity of each warehouse is c through the optimized object filter 541₀、c₁、c₂The lower limit of the capacity is d₀、d₁、d₂Optimizing merchandise store clothThe granularity of the bureau is sku, and the strategies selected by the strategy issuing device are a minimum order splitting strategy, a balanced inventory strategy and a balanced production order strategy.

In operation S1002, it is determined that an optimization policy exists a check, and θ may be set₀＝0.3，θ₁＝0.3，θ₂＝0.4。

In operation S1003, the inventory layout optimizer 543 acquires the layout optimization model, outputs a result X by calculating an optimal solution_ij。

In operation S1004, X is determined_ijWhether all are 0. If so, it is ended, and if not, operation S1005 is performed.

In operation S1005, a change in the total number of executions (corresponding to the number of orders split into purchase orders) before and after the optimization of the inventory layout is calculated in the inventory layout optimization effect calculator 544 according to the result of the optimization of the inventory layout.

In the present application example, θ₀＞0，θ₁＞0，θ₂And the constraint conditions (e), (f), (g) and (h) control the capacity of the storeroom and the production unit quantity of the storeroom through upper and lower limits so that a layout optimization model formula can be solved as a linear problem.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any of the acquisition module 510, the first determination module 520, the second determination module 530, the model construction module 540, the optimized object filter 541, the policy issuer 542, the inventory layout optimizer 543, and the inventory layout optimization effect calculator 544 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the obtaining module 510, the first determining module 520, the second determining module 530, the model constructing module 540, the optimized object filter 541, the policy issuer 542, the inventory layout optimizer 543, and the inventory layout optimization effect calculator 544 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, or as any one of three implementations of software, hardware, and firmware, or as a suitable combination of any of them. Alternatively, at least one of the acquisition module 510, the first determination module 520, the second determination module 530, the model construction module 540, the optimized object filter 541, the policy issuer 542, the inventory layout optimizer 543, and the inventory layout optimization effect calculator 544 can be implemented at least in part as a computer program module that can perform corresponding functions when executed.

Fig. 11 schematically shows a block diagram of an electronic device 1100 adapted to implement a data processing method for inventory management according to an embodiment of the present disclosure. The electronic device 1100 shown in fig. 11 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present disclosure.

As shown in fig. 11, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1102 or a program loaded from a storage section 1108 into a Random Access Memory (RAM) 1103. The processor 1101 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 1101 may also include on-board memory for caching purposes. The processor 1101 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to the embodiments of the present disclosure.

In the RAM 1103, various programs and data necessary for the operation of the electronic device 1100 are stored. The processor 1101, the ROM 1102, and the RAM 1103 are connected to each other by a bus 1104. The processor 1101 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 1102 and/or the RAM 1103. It is noted that the programs may also be stored in one or more memories other than the ROM 1102 and RAM 1103. The processor 1101 may also perform various operations of the method flows according to the embodiments of the present disclosure by executing programs stored in the one or more memories.

System 1100 may also include an input/output (I/O) interface 1105, which input/output (I/O) interface 1105 is also connected to bus 1104, according to an embodiment of the present disclosure. Electronic device 1100 may also include one or more of the following components connected to I/O interface 1105: an input portion 1106 including a keyboard, mouse, and the like; an output portion 1107 including a signal output unit such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 1108 including a hard disk and the like; and a communication section 1109 including a network interface card such as a LAN card, a modem, or the like. The communication section 1109 performs communication processing via a network such as the internet. A driver 1110 is also connected to the I/O interface 1105 as necessary. A removable medium 1111 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1110 as necessary, so that a computer program read out therefrom is mounted into the storage section 1108 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 1109 and/or installed from the removable medium 1111. The computer program, when executed by the processor 1101, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 1102 and/or the RAM 1103 and/or one or more memories other than the ROM 1102 and the RAM 1103 described above.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations 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 diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A data processing method for inventory management, comprising:

acquiring goods to be stored and classification attributes of the goods to be stored;

determining the number of classification attributes of the goods to be stored in an attribute set I, wherein the attribute set I is set as a set consisting of classification attributes of goods in all orders performed from a plurality of storehouses in a preset historical time period;

variable X based on warehouse inventory layout_ijDetermining a storehouse for storing the goods to be stored, wherein X is_ijIs used for indicating whether goods with classification attribute with number i should be stored in the storeroom with number J, wherein J belongs to J, J is a candidate storehouse set which is set to be a set obtained based on the information of the storerooms; and

wherein the warehouse inventory layout variable X_ijAnd solving a layout optimization model which is constructed by an operational research optimization method based on the inventory information and the performance information of the plurality of storehouses in the preset historical time period and is used for optimizing the storage layout of the goods in the plurality of storehouses.

2. The method of claim 1, further comprising constructing the layout optimization model, comprising:

obtaining information of the storehouses to obtain the candidate storehouse set J, wherein J belongs to J, and J is the serial number of the storehouses;

acquiring an order set K formed by all orders performing in the plurality of storehouses in the preset historical time period, wherein the K belongs to the K, and the K is the serial number of the order;

acquiring a set of classification attributes of all goods related to the order set K to obtain an attribute set I, wherein I belongs to I, and I represents the serial number of the classification attributes;

constructing the warehouse inventory layout changeQuantity X_ij，

j∈J；X_ijThe system is used for indicating whether goods with classification attributes of the number i should be stored in a storeroom of the number j;

construction warehouse performance variable Y_kj，

K belongs to K; wherein, Y_kjFor indicating whether the order numbered k should perform from the store numbered j:

constructing the warehouse inventory layout variable X based on the relationship between the inventory and the performance of the plurality of warehouses_ijAnd said warehouse performance variable Y_kjA constraint condition between;

using said warehouse inventory layout variable X_ijSaid warehouse performance variable Y_kjThe constraint condition is used for constructing the layout optimization model by applying an operation and research optimization method; and

obtaining X in the solution of the layout optimization model_ijAnd obtaining storage layout information used for guiding the goods in different storehouses.

3. The method of claim 2, wherein the method of applying operational research optimization to construct the layout optimization model comprises:

constructing a first objective function based on a minimum policy of splitting:

4. The method of claim 2, wherein the method of applying operational research optimization to construct the layout optimization model comprises:

constructing a second objective function based on the balanced inventory strategy:

Min(U₀-L₀)

5. The method of claim 2, wherein the method of applying operational research optimization to construct the layout optimization model comprises:

constructing a third objective function based on a balanced production single strategy:

Min(U₁-L₁)

6. The method of claim 2, wherein the method of applying operational research optimization to construct the layout optimization model comprises:

constructing a fourth objective function based on the combination of the minimum inventory splitting strategy, the balance inventory strategy and the balance production inventory strategy:

min θ₀∑_k∈K∑_j∈JY_kj+θ₁(U₀-L₀)+θ₂(U₁-L₁)

wherein the content of the first and second substances,

θ₁、θ₂、θ₃is a weight coefficient, wherein₁+θ₂+θ₃＝1。

7. The method of claim 6, further comprising:

selecting at least one optimization strategy from a minimum order splitting strategy, a balanced inventory strategy and a balanced production order strategy; and

setting θ based on the at least one optimization strategy₁、θ₂And theta₃The value of (c).

8. The method of claim 2,

constructing the warehouse inventory layout variable X_ijFurther comprising: set up X_ij∈{0，1}，

J is an element of J; wherein, X_ij1 indicates that goods with classification attribute of number i are stored in the store of number j, otherwise X_ij＝0；

Constructing the warehouse performance variable Y_kjFurther comprising: set up Y_kj∈{0，1}，

K belongs to K; wherein, Y_kj1 represents an order numbered k fulfilling from the store numbered j, otherwise Y_kj0; and

the building of the warehouse inventory layout variable X based on the relationship between the plurality of warehouses' inventory and performance_ijAnd said warehouse performance variable Y_kjThe constraint conditions in between include:

the constraint condition Y is set based on the restriction that goods performing from the store numbered j necessarily belong to the stock numbered j_kj≤∑_i∈IX_ij，

J ∈ J and X_ij≤Y_kj，

i∈I，j∈J。

9. The method of claim 8, wherein the building of the warehouse inventory layout variable X is based on a relationship between inventory and performance of the plurality of warehouses_ijAnd said warehouse performance variable Y_kjThe constraint between further comprising:

the goods with the same classification parameter number in each order are arranged to perform from one storehouse with constraint condition sigma_j∈JX_ij＝1，

10. The method of claim 9, wherein the building of the warehouse inventory layout variable X is based on a relationship between inventory and performance of the plurality of warehouses_ijAnd said warehouse performance variable Y_kjThe constraint between further comprising:

setting the actual capacity of each warehouse based on the actual upper and lower limits of the capacity of each warehouseCapacity constraint conditions: sigma_i∈Ia_iX_ij≤c_j，

Sum Σ_i∈Ia_iX_ij≥d_j，

Wherein the content of the first and second substances,

c_jthe upper capacity limit of storehouse j; and

d_jlower capacity limit of warehouse j.

11. The method of claim 2, further comprising:

at least a portion X in a solution based on the layout optimization model_ijAnd at least a part of Y_kjAnd obtaining the warehouse layout optimization index.

12. The method of claim 1, wherein the classification attributes comprise attributes for at least one dimension of a brand, an item class, or a SKU.

13. A data processing apparatus for inventory management, comprising:

the system comprises an acquisition module, a storage module and a classification module, wherein the acquisition module is used for acquiring goods to be stored and classification attributes of the goods to be stored;

the first determination module is used for determining the number of the classification attribute of the goods to be stored in an attribute set I, wherein the attribute set I is set as a set consisting of the classification attributes of the goods in all orders performed from a plurality of storehouses in a preset historical time period; and

a second determination module for determining a variable X based on the stock layout_ijDetermining to store the goods to be storedThe storehouse of (1), wherein, X_ijIs used for indicating whether goods with classification attribute with number i should be stored in the storeroom with number J, wherein J belongs to J, J is a candidate storehouse set which is set to be a set obtained based on the information of the storerooms;

wherein the warehouse inventory layout variable X_ijAnd solving a layout optimization model which is constructed by an operational research optimization method based on the inventory information and performance information of the plurality of storehouses in the preset historical time period and is used for optimizing the storage layout of the goods in the plurality of storehouses.

14. The apparatus of claim 13, further comprising a model building module, the model building module comprising:

the optimized object filter is used for acquiring the information of the storehouses to obtain the candidate storehouse set J, wherein J belongs to J, and J is the serial number of the storehouses; acquiring an order set K formed by all orders performing in the plurality of storehouses in the preset historical time period, wherein the K belongs to the K, and the K is the serial number of the order; acquiring a set of classification attributes of all goods related to the order set K to obtain an attribute set I, wherein I belongs to I, and I represents the serial number of the classification attributes;

a policy issuer for constructing said warehouse inventory layout variable X_ij，

j∈J，X_ijThe system is used for indicating whether goods with classification attributes of the number i should be stored in a storeroom of the number j; constructing the warehouse performance variable Y_kj，

K belongs to K; wherein, Y_kjFor identifying whether the order numbered k should perform from the store numbered j; constructing the warehouse inventory layout change based on the relationship between the inventory and the performance of the plurality of warehousesQuantity X_ijAnd said warehouse performance variable Y_kjA constraint condition between; and utilizing said warehouse inventory layout variable X_ijSaid warehouse performance variable Y_kjThe constraint condition is used for constructing the layout optimization model by applying an operation and research optimization method; and

an inventory layout optimizer to obtain the warehouse inventory layout variable X in the solution of the layout optimization model_ijAnd obtaining storage layout information used for guiding the goods in different storehouses.

15. An electronic device, comprising:

one or more memories storing executable instructions; and

one or more processors executing the executable instructions to implement the method of any one of claims 1-12.

16. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 12.