Goods distribution method and device, storage medium and program product
By calculating the first and second constraint values of goods allocation in the retail supply chain, the target allocation method is selected, which solves the problem of low goods allocation efficiency and achieves more efficient goods allocation uniformity and faster calculation speed.
Patent Information
- Application Number
- CN202410534274.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-29
- Publication Date
- 2025-10-31
AI Technical Summary
In the retail supply chain, existing goods allocation methods cannot meet the allocation needs of various goods types, resulting in a decline in goods turnover efficiency. In particular, when there are many stores, the global comparison process takes a long time and the allocation efficiency is low.
By determining the quantity of goods to be allocated to each store, the first and second constraint values of the candidate allocation methods under the target dimension are calculated. The target allocation method that makes the sum of the constraint values of each store less than the threshold is selected, including constraint calculations for SKU, color, and configuration dimensions. The allocation results are optimized using optimization algorithms such as Gurobi or SCIP solvers.
It improves the uniformity and efficiency of cargo allocation, increasing the distribution uniformity by 20% and the variance uniformity by 10%, and improving the solution efficiency by 4.5 times.
Smart Images

Figure CN120875283A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of information processing technology, and in particular to methods, apparatus, storage media and program products for cargo distribution. Background Technology
[0002] In retail supply chain scenarios, it may be necessary to allocate limited goods in a warehouse to stores. Generally, a better allocation method can improve the turnover efficiency of goods and reduce unsold inventory. However, as the types of goods become increasingly diverse, the existing allocation methods may fail to meet the allocation needs, potentially leading to a decline in the turnover efficiency of goods. Summary of the Invention
[0003] To overcome the problems existing in the related technologies, this disclosure provides a cargo distribution method, apparatus, storage medium, and program product.
[0004] According to a first aspect of the present disclosure, a cargo distribution method is provided, comprising:
[0005] Determine the quantity of goods to be allocated to each store;
[0006] Based on the quantity of goods in each store, determine the candidate allocation method for the goods in each store;
[0007] Calculate a first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method, and a second constraint value representing the uniformity of goods allocation under the target dimension for the candidate allocation method;
[0008] The target allocation method for goods is determined from the candidate allocation methods. The target allocation method ensures that the absolute value of the sum of the constraint values of each store is less than a threshold. The constraint values of each store include the first constraint value and the second constraint value of the store.
[0009] Optionally, the target dimension includes a standardized product unit (SKU) dimension. The calculation of a first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method, and a second constraint value representing the uniformity of goods allocation under the target dimension for the candidate allocation method, includes:
[0010] Calculate the first constraint value representing the number of SKUs in the SKU dimension for the candidate allocation method;
[0011] Calculate the second constraint value representing the uniformity of SKU allocation in the SKU dimension of the candidate allocation method.
[0012] Optionally, it includes:
[0013] Obtain the sales data of the goods in the store;
[0014] Obtain the allocation quantity of each SKU in the store under the candidate allocation method;
[0015] Based on the sales data and the allocation of each SKU, the constraint value of the store's goods flow rate is calculated, and the constraint value of the store includes the constraint value of the goods flow rate.
[0016] Optionally, the target dimension includes a cargo color dimension and / or a cargo configuration dimension. The calculation of a first constraint value representing the quantity of cargo allocated under the target dimension, and a second constraint value representing the uniformity of cargo allocation under the target dimension, includes:
[0017] Calculate a first constraint value representing the quantity of goods of each color under the dimension of goods color for the candidate allocation method; and a second constraint value representing the distribution uniformity of goods colors under the dimension of goods color for the candidate allocation method; and / or,
[0018] Calculate a first constraint value representing the quantity of goods in each configuration under the dimension of goods configuration for the candidate allocation method; and a second constraint value representing the allocation uniformity of goods configuration under the dimension of goods configuration for the candidate allocation method.
[0019] Optionally, calculating the first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method includes:
[0020] Obtain the quantity of goods under the target dimension for the candidate allocation method;
[0021] When the quantity of goods is 0, the first constraint value is determined to be 0;
[0022] If the quantity of goods is not zero, the first constraint value is determined to be a preset gain value corresponding to the target dimension.
[0023] Optionally, calculating a second constraint value representing the uniformity of cargo allocation in the target dimension for the candidate allocation method includes:
[0024] Determine the total quantity of the goods under the target dimension;
[0025] Based on the total quantity of goods, calculate the second constraint value representing the uniformity of goods allocation in the target dimension for the candidate allocation method.
[0026] Optionally, calculating the second constraint value representing the uniformity of cargo allocation in the target dimension based on the total quantity of the cargo includes:
[0027] The second constraint value shall be calculated using at least one of the following methods:
[0028] Calculate the square of the total quantity to obtain the second constraint value;
[0029] Calculate the common logarithm of the total quantity to obtain the second constraint value;
[0030] Under the candidate allocation method, obtain the average quantity of goods in each store under the target dimension; calculate the difference between the total quantity and the average value; calculate the square of the difference to obtain the second constraint value.
[0031] According to a second aspect of the present disclosure, a cargo dispensing apparatus is provided, comprising:
[0032] The first module is configured to determine the quantity of goods to be allocated to each store;
[0033] The second module is configured to determine the candidate allocation method for goods in each store based on the quantity of goods in each store.
[0034] The third module is configured to calculate a first constraint value representing the quantity of goods allocated under the target dimension, and a second constraint value representing the uniformity of goods allocation under the target dimension;
[0035] The fourth module is configured to determine a target allocation method for goods from the candidate allocation methods, wherein the target allocation method makes the absolute value of the sum of the constraint values of each store less than a threshold, and the constraint values of each store include a first constraint value and a second constraint value of the store.
[0036] Optionally, the target dimension includes a standardized product unit (SKU) dimension, and the third module is configured as follows:
[0037] Calculate the first constraint value representing the number of SKUs in the SKU dimension for the candidate allocation method;
[0038] Calculate the second constraint value representing the uniformity of SKU allocation in the SKU dimension of the candidate allocation method.
[0039] Optionally, the device includes:
[0040] The fifth module is configured to acquire the sales data of the goods in the store;
[0041] The sixth module is configured to obtain the allocation quantity of each SKU of the store under the candidate allocation method;
[0042] The seventh module is configured to calculate the constraint value of the store's goods flow rate based on the goods sales data and the allocation of each SKU, wherein the constraint value of the store includes the constraint value of the goods flow rate.
[0043] Optionally, the target dimension includes a cargo color dimension and / or a cargo configuration dimension, and the third module is configured as follows:
[0044] Calculate a first constraint value representing the quantity of goods of each color under the dimension of goods color for the candidate allocation method; and a second constraint value representing the distribution uniformity of goods colors under the dimension of goods color for the candidate allocation method; and / or,
[0045] Calculate a first constraint value representing the quantity of goods in each configuration under the dimension of goods configuration for the candidate allocation method; and a second constraint value representing the allocation uniformity of goods configuration under the dimension of goods configuration for the candidate allocation method.
[0046] Optionally, the third module is configured as follows:
[0047] Obtain the quantity of goods under the target dimension for the candidate allocation method;
[0048] When the quantity of goods is 0, the first constraint value is determined to be 0;
[0049] If the quantity of goods is not zero, the first constraint value is determined to be a preset gain value corresponding to the target dimension.
[0050] Optionally, the third module is configured as follows:
[0051] Determine the total quantity of the goods under the target dimension;
[0052] Based on the total quantity of goods, calculate the second constraint value representing the uniformity of goods allocation in the target dimension for the candidate allocation method.
[0053] Optionally, the third module is configured to calculate the second constraint value in at least one of the following ways:
[0054] Calculate the square of the total quantity to obtain the second constraint value;
[0055] Calculate the common logarithm of the total quantity to obtain the second constraint value;
[0056] Under the candidate allocation method, obtain the average quantity of goods in each store under the target dimension; calculate the difference between the total quantity and the average value; calculate the square of the difference to obtain the second constraint value.
[0057] According to a third aspect of the present disclosure, a cargo dispensing apparatus is provided, comprising:
[0058] processor;
[0059] Memory used to store processor-executable instructions;
[0060] The processor is configured to perform the method described in any one of the first aspects.
[0061] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method described in any one of the first aspects.
[0062] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in any one of the first aspects.
[0063] In the above scheme, the quantity of goods to be allocated to each store can be determined, and based on the quantity of goods in each store, candidate allocation methods for the goods in each store can be determined. Furthermore, a first constraint value representing the quantity of goods allocated under the target dimension, and a second constraint value representing the uniformity of goods allocation under the target dimension, can be calculated for each candidate allocation method. Thus, a target allocation method can be determined from the candidate allocation methods, whereby the absolute value of the sum of the constraint values for each store is less than a threshold. The constraint values for each store include both the first and second constraint values.
[0064] Using the above scheme, candidate allocation methods for goods can be determined based on the quantity of goods to be allocated to each store. Furthermore, by setting a target dimension and first and second constraints under that target dimension, the first and second constraint values of the candidate allocation methods under the target dimension can be calculated. Thus, target allocation methods that satisfy the constraints can be filtered using the first and second constraint values of each store, thereby optimizing the goods allocation results.
[0065] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0066] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0067] Figure 1 This is a flowchart illustrating a cargo allocation method according to an exemplary embodiment.
[0068] Figure 2 This is a flowchart illustrating a cargo allocation process according to an exemplary embodiment.
[0069] Figure 3 This is a flowchart illustrating an implementation of step S13 according to an exemplary embodiment.
[0070] Figure 4 This is a flowchart illustrating the calculation of a second constraint value according to an exemplary embodiment.
[0071] Figure 5 This is a block diagram illustrating a cargo distribution device according to an exemplary embodiment.
[0072] Figure 6 This is a block diagram illustrating an apparatus for distributing goods according to an exemplary embodiment. Detailed Implementation
[0073] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0074] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0075] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.
[0076] Before introducing the cargo distribution method, apparatus, storage medium and program product of this disclosure, the relevant scenarios of the embodiments of this disclosure will be introduced first.
[0077] In retail supply chain scenarios, it may be necessary to allocate limited goods in a warehouse to stores. Generally, a better allocation method can improve the turnover efficiency of goods and reduce unsold inventory. For example, for products already on the market, future sales can be estimated based on the store's historical sales data over a period of time, and then an allocation strategy can be used to distribute goods to stores to meet future sales targets. For some new products that have not yet been launched, reference goods can be set according to the product series of the new product. In this way, goods can be allocated to stores based on a certain strategy and the historical sales performance of reference goods.
[0078] However, this allocation method determines the quantity of goods allocated to each store across the entire inventory. In some scenarios, a single item may include multiple characteristics, such as configuration and color. Therefore, simply determining the quantity of goods to be allocated may still not meet the allocation needs. In other words, it may be necessary to allocate based on the quantity of goods to achieve a balanced distribution.
[0079] In some scenarios, stores can be prioritized and then allocated quotas to various configurations or colors through a loop. Alternatively, a global comparison strategy can be used to compare stores and achieve a balanced allocation by swapping configurations or colors. This allocation method involves two independent stages, making it difficult to obtain a globally optimal allocation. Furthermore, when there are many stores, the global comparison process is time-consuming, resulting in low allocation efficiency.
[0080] Therefore, embodiments of this disclosure provide a method for distributing goods. The method can be performed by various stationary or mobile devices, such as laptops, servers, tablets, mobile phones, or combinations thereof. Figure 1 This is a flowchart illustrating a cargo allocation method according to an exemplary embodiment of this disclosure, with reference to... Figure 1 The method includes:
[0081] In step S11, the quantity of goods to be allocated to each store is determined.
[0082] In one implementation, the goods may be unlisted goods. (See reference...) Figure 2 The flowchart shown illustrates a cargo allocation process, which can identify reference cargo. Reference cargo can be, for example, cargo from the same series as the current cargo. For instance, if the current cargo is "XM14" and the previous cargo in the same series is "XM13", then when allocating "XM14", the previous cargo "XM13" can be used as the reference cargo.
[0083] Furthermore, a reference period can be set, such as three months, six months, etc. This allows obtaining sales data for reference goods within the historical reference period from the database. In a possible implementation, the sales data may be sparse, therefore the sales data can also be formatted, i.e., processed into data sequences of equal length.
[0084] Reference Figure 2 When allocating current goods, the sales data of reference goods can be loaded, and the sales data of reference goods can be mapped to the current goods.
[0085] For example, for multiple stores, the quantity of goods can be allocated based on historical sales data. For instance, stores can be sorted from highest to lowest historical sales volume, and the required quantity of goods allocated to each store can be determined by decreasing the allocation amount. This ensures that stores with higher sales volumes receive a larger quantity of goods.
[0086] As an example, the current new product SPU (Standard Product Unit) is 10001, and the stores include...<shop1,shop2,shop3,shop4> Among them, the reference goods for each store, sorted from highest to lowest sales volume over the historical reference period, are as follows:<shop2,shop4,shop1,shop3> In this way, the quantity of goods is allocated according to the store order. For example, the allocation result is <(shop2,10001,10 items),(shop4,10001,9 items),(shop1,10001,7 items),(shop4,10001,5 items)>. In this way, the quantity of goods to be allocated to each store can be determined.
[0087] Reference Figure 1 In step S12, based on the quantity of goods in each store, a candidate allocation method for the goods in each store is determined.
[0088] It should be noted that goods may include characteristic attributes such as color and configuration. Therefore, based on the determined quantity of goods to be allocated to each store, goods can be allocated based on attributes such as color and configuration, resulting in different candidate allocation methods. Taking shop2 as an example, its 10 goods could include 9 white goods and 1 black goods; or it could include 7 white goods and 3 black goods. Similarly, goods in other stores can also be allocated in a fine-grained manner (based on attributes such as color and configuration) given a fixed quantity, thus forming multiple allocation methods.
[0089] In some scenarios, the candidate allocation method for goods in each store can be determined through model solving and optimization.
[0090] In step S13, a first constraint value representing the quantity of goods allocated under the target dimension and a second constraint value representing the uniformity of goods allocation under the target dimension are calculated for the candidate allocation method.
[0091] For example, in one implementation, the target dimension includes the SKU (Stock Keeping Unit) dimension. See [reference needed]. Figure 3The flowchart shown illustrates an implementation of step S13, which includes calculating a first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method, and a second constraint value representing the uniformity of goods allocation under the target dimension for the candidate allocation method, comprising:
[0092] In step S131, the first constraint value representing the number of SKUs in the SKU dimension of the candidate allocation method is calculated.
[0093] For example, the quantity of goods in the SKU dimension of the candidate allocation method can be obtained. If the quantity of goods is 0, the first constraint value can be determined to be 0. If the quantity of goods is not 0, the first constraint value can be determined to be a preset gain value corresponding to the SKU dimension.
[0094] Furthermore, to facilitate the solution, a mathematical representation for calculating the first constraint value can also be generated:
[0095]
[0096]
[0097]
[0098]
[0099] Where, x k,o Let represent the allocation quantity of the k-th SKU in store o, ∈ be a preset value, and M be preset auxiliary solution parameters. Let the first constraint value be the k-th SKU of store o. It is a binary variable, taking the value 0 or 1, gain SKU This is the preset gain value for the SKU dimension.
[0100] Equations 1 to 4 are as follows: When the quantity of the k-th SKU in store o is 0, the first constraint value of the k-th SKU in store o can be determined to be 0. When the quantity of the k-th SKU in store o is not 0, the first constraint value can be determined to be gain. SKU .
[0101] In step S132, the second constraint value representing the uniformity of SKU allocation in the SKU dimension of the candidate allocation method is calculated.
[0102] Figure 4 This is a flowchart illustrating the calculation of a second constraint value according to an exemplary embodiment of this disclosure, with reference to... Figure 2 The second constraint value, representing the uniformity of cargo allocation, is calculated for candidate allocation methods in the target dimension, including:
[0103] In step S41, the total quantity of goods under the target dimension is determined;
[0104] In step S42, based on the total quantity of goods, a second constraint value representing the uniformity of goods allocation under the target dimension is calculated for the candidate allocation method.
[0105] Combination Figure 4 Step S132 is explained as follows: When calculating the second constraint value representing the distribution uniformity of SKUs in the SKU dimension for candidate allocation methods, the total quantity of goods in the SKU dimension can be determined. For example, the total quantity of goods in store o under the k-th SKU... It can be:
[0106]
[0107] Where, x k,o The allocation quantity for the k-th SKU of store o. Let represent the inventory of the k-th SKU in store o.
[0108] Continuing with step S42, the second constraint value representing the uniformity of cargo allocation in the SKU dimension can be calculated based on the total quantity of cargo.
[0109] For example, in one possible implementation, the square of the total quantity can be calculated to obtain the second constraint value. Following Equation 5 above, the second constraint value for store o under the k-th SKU... for:
[0110]
[0111] In one possible implementation, the common logarithm of the total number can be calculated; the negative of the common logarithm is used as the second constraint value. Following Equation 5 above, the second constraint value for store o under the k-th SKU... for:
[0112]
[0113] In this approach, the calculation of the second constraint value does not involve squaring, resulting in faster computational efficiency.
[0114] In one possible implementation, the average quantity of goods in each store under the SKU dimension can be obtained under the candidate allocation method; the difference between the total quantity and the average value can be calculated; the square of the difference can be calculated to obtain the second constraint value. Following Equation 5 above, the second constraint value for store o under the k-th SKU... for:
[0115]
[0116] Here, the sum of the quota and inventory of store o for the k-th SKU is the quantity of goods in store o under the SKU dimension. The SKU quota is the quantity of the k-th SKU allocated to store o under the candidate allocation method.
[0117] It should be noted that the target dimension can be set based on requirements. For example, in one possible implementation, the target dimension includes the cargo color dimension. The calculation of a first constraint value representing the quantity of cargo allocated under the target dimension, and a second constraint value representing the uniformity of cargo allocation under the target dimension, includes:
[0118] Calculate a first constraint value representing the quantity of goods of each color in the dimension of goods color for the candidate allocation method; and a second constraint value representing the distribution uniformity of goods color in the dimension of goods color for the candidate allocation method.
[0119] For example, the quantity of goods under each goods color can be obtained for the candidate allocation method. If the quantity of goods is 0, the first constraint value under that goods color can be determined to be 0. If the quantity of goods is not 0, the first constraint value can be determined to be a preset gain value corresponding to the goods color dimension.
[0120] Furthermore, to facilitate the solution, a mathematical representation for calculating the first constraint value can also be generated:
[0121]
[0122]
[0123]
[0124]
[0125] Among them, Y c,o Let be the allocation quantity of the c-th item color in store o, ∈ be a preset value, and M be preset auxiliary solution parameters. Let c be the first constraint value for the color of the c-th item in store o. It is a binary variable, taking the value 0 or 1, gain COLOR This is the preset gain value for the color dimension of the goods.
[0126] Equations 9 to 12 are as follows: When the quantity of goods of the c-th color in store o is 0, the first constraint value for the c-th color of goods in store o can be determined to be 0. When the quantity of goods of the c-th color in store o is not 0, the first constraint value can be determined to be gain. COLOR.
[0127] In addition, a second constraint value representing the uniformity of cargo color distribution can be calculated for the candidate allocation method in the cargo color dimension.
[0128] Combination Figure 4 To explain, when calculating the second constraint value representing the uniformity of goods color distribution in the goods color dimension for candidate allocation methods, the total quantity of goods in the goods color dimension can be determined. For example, the total quantity of goods in store o under the c-th goods color... It can be:
[0129]
[0130] Among them, y c,o For store o, the allocation quantity for the c-th product color. Let O be the inventory of the c-th item color in store O.
[0131] Continuing with step S42, the second constraint value representing the uniformity of cargo color allocation in the cargo color dimension can be calculated based on the total quantity of cargo.
[0132] For example, in one possible implementation, the square of the total quantity can be calculated to obtain the second constraint value. Following Equation 13 above, the second constraint value for store o under the c-th product color... for:
[0133]
[0134] in, Let c be the total number of goods in store o under the c-th color.
[0135] In one possible implementation, the common logarithm of the total quantity can be calculated; the negative of the common logarithm is used as the second constraint value. Following Equation 13 above, the second constraint value for store o under the c-th product color... for:
[0136]
[0137] In this approach, the calculation of the second constraint value does not involve squaring, resulting in faster computational efficiency.
[0138] In one possible implementation, the average quantity of goods in each store under the goods color dimension can be obtained under the candidate allocation method; the difference between the total quantity and the average value can be calculated; the square of the difference can be calculated to obtain the second constraint value. Following Equation 13 above, the second constraint value for store o under the c-th goods color... for:
[0139]
[0140] Wherein, the sum of the quota and inventory of store o under the c-th product color is the quantity of products of store o under that product color dimension. The quota for product color is the quantity of products under the c-th product color allocated to store o under the candidate allocation method.
[0141] In one possible implementation, the target dimension includes a cargo allocation dimension. The calculation of a first constraint value representing the quantity of cargo allocated under the target dimension, and a second constraint value representing the uniformity of cargo allocation under the target dimension, includes:
[0142] Calculate a first constraint value representing the quantity of goods in each configuration under the dimension of goods configuration for the candidate allocation method; and a second constraint value representing the allocation uniformity of goods configuration under the dimension of goods configuration for the candidate allocation method.
[0143] For example, the quantity of goods under each goods configuration can be obtained for the candidate allocation method. If the quantity of goods is 0, the first constraint value under that goods configuration can be determined to be 0. If the quantity of goods is not 0, the first constraint value can be determined to be a preset gain value corresponding to the goods configuration dimension.
[0144] Furthermore, to facilitate the solution, a mathematical representation for calculating the first constraint value can also be generated:
[0145]
[0146]
[0147]
[0148]
[0149] Among them, Z d,o The allocation quantity for the d-th item in store o, where ∈ is a preset value and M is a preset auxiliary solution parameter. The first constraint value configured for the d-th item in store o. It is a binary variable, taking the value 0 or 1, gain DDR Configure preset gain values for cargo dimensions.
[0150] Equations 17 to 20 are as follows: When the quantity of goods in the d-th configuration of store o is 0, the first constraint value under the d-th goods configuration of store o can be determined to be 0. When the quantity of goods in the d-th configuration of store o is not 0, the first constraint value can be determined to be gain. DDR .
[0151] In addition, a second constraint value representing the uniformity of cargo allocation under the cargo allocation dimension can be calculated for the candidate allocation method.
[0152] Combination Figure 4 To clarify, when calculating the second constraint value, which characterizes the uniformity of goods allocation in the goods allocation dimension, for candidate allocation methods, the total quantity of goods in the goods allocation dimension can be determined. For example, the total quantity of goods in store o under the d-th goods allocation... It can be:
[0153]
[0154] in, For store o, the allocation quantity under the d-th goods configuration. Let O be the inventory level of store o under the d-th product configuration.
[0155] Continuing with step S42, the second constraint value representing the uniformity of cargo allocation under the cargo allocation dimension can be calculated based on the total quantity of cargo.
[0156] For example, in one possible implementation, the square of the total quantity can be calculated to obtain the second constraint value. Following formula 21 above, the second constraint value for store o under the d-th goods configuration is... for:
[0157]
[0158] in, Let O be the total number of goods in the d-th goods configuration for store O.
[0159] In one possible implementation, the common logarithm of the total quantity can be calculated; the negative of the common logarithm is used as the second constraint value. Following Equation 21 above, the second constraint value for store o under the d-th goods configuration is... for:
[0160]
[0161] In this approach, the calculation of the second constraint value does not involve squaring, resulting in faster computational efficiency.
[0162] In one possible implementation, the average quantity of goods in each store under the goods configuration dimension can be obtained under the candidate allocation method; the difference between the total quantity and the average value can be calculated; the square of the difference can be calculated to obtain the second constraint value. Following the above formula 21, the second constraint value of store o under the d-th goods configuration is... for:
[0163]
[0164] Wherein, the sum of the quota and inventory of store o under the d-th goods configuration is the quantity of goods of store o under the goods configuration dimension. The quota of goods configuration is the quantity of goods allocated to store o under the d-th goods configuration under the candidate allocation method.
[0165] Of course, in possible implementations, the target dimension may include both the cargo color dimension and the cargo configuration dimension, and this disclosure does not limit this.
[0166] Reference Figure 1 In step S14, the target allocation method for goods is determined from the candidate allocation methods. The target allocation method makes the absolute value of the sum of the constraint values of each store less than a threshold. The constraint values of a store include the first constraint value and the second constraint value of the store.
[0167] For example, in one possible implementation, the target dimension includes the SKU dimension.
[0168] In this way, for each candidate allocation method, the sum of the constraint values for each store under that candidate allocation method can be calculated. In this way, the candidate allocation method whose absolute value of the sum of constraint values is less than the threshold can be determined as the target allocation method.
[0169] In a possible implementation, the minimum sum of constraint values can also be determined. And the corresponding candidate allocation method is taken as the target allocation method.
[0170] In a possible implementation, weights can also be assigned to the first and second constraint values to facilitate adjusting the tendency of cargo allocation. For example, the minimum value of the sum of the constraint values can be calculated as follows:
[0171]
[0172] Where, λ SKU α is the weight of the first constraint value. SKU The weight of the second constraint value.
[0173] In one possible implementation, the target dimensions include the SKU dimension and the cargo color dimension.
[0174] In this way, for each candidate allocation method, the sum of the constraint values for each store under that candidate allocation method can be calculated. In this way, the candidate allocation method whose absolute value of the sum of constraint values is less than the threshold can be determined as the target allocation method.
[0175] In a possible implementation, the minimum sum of constraint values can also be determined. And the corresponding candidate allocation method is taken as the target allocation method.
[0176] In a possible implementation, weights can also be assigned to the first and second constraint values to facilitate adjusting the tendency of cargo allocation. For example, the minimum value of the sum of the constraint values can be calculated as follows:
[0177]
[0178] Where, λ SKU α represents the weight of the first constraint value under the SKU dimension. SKU λ represents the weight of the second constraint value under the SKU dimension. COLOR α represents the weight of the first constraint value under the cargo color dimension. COLOR The weight of the second constraint value under the cargo color dimension.
[0179] In one possible implementation, the target dimensions include SKU dimension, cargo color dimension, and cargo configuration dimension.
[0180] In this way, for each candidate allocation method, the sum of the constraint values for each store under that candidate allocation method can be calculated. In this way, the candidate allocation method whose absolute value of the sum of constraint values is less than the threshold can be determined as the target allocation method.
[0181] In a possible implementation, the minimum sum of constraint values can also be determined. And the corresponding candidate allocation method is taken as the target allocation method.
[0182] In a possible implementation, weights can also be assigned to the first and second constraint values to facilitate adjusting the tendency of cargo allocation. For example, the minimum value of the sum of the constraint values can be calculated as follows:
[0183]
[0184] Where, λ SKUα represents the weight of the first constraint value under the SKU dimension. SKU λ represents the weight of the second constraint value under the SKU dimension. COLOR α represents the weight of the first constraint value under the cargo color dimension. COLOR λ represents the weight of the second constraint value under the cargo color dimension. DDR The weight of the first constraint value under the cargo configuration dimension, α DDR The weight of the second constraint value under the cargo configuration dimension.
[0185] Furthermore, other constraints can be set based on requirements. For example, in one possible implementation, the store's sales data can be obtained; and the allocation quantity of each SKU in the store under the candidate allocation method can be obtained. In this way, the constraint value of the store's goods flow rate can be calculated based on the sales data and the allocation quantity of each SKU, and the constraint value of the store includes the constraint value of the goods flow rate.
[0186] As an example, the constraint value of the cargo flow rate can be calculated using the following formula.
[0187]
[0188] in, V represents the flow rate of goods for the k-th SKU in the o-th store. k,o The sales volume of the k-th SKU in the o-th store is represented by the average daily sales volume.
[0189] As an example, the constraint value of the cargo flow rate can be calculated using the following formula.
[0190]
[0191] in, Please refer to formula 5 for the calculation method.
[0192] Thus, considering the constraint value of goods flow rate, for each candidate allocation method, the sum of constraint values H of each store under that candidate allocation method can be calculated:
[0193]
[0194] In this way, candidate allocation methods where the absolute value of the sum of constraint values is less than a threshold can be identified as the target allocation method. For example, refer to... Figure 2The objective function can be minimized using H, and the target allocation method can be determined using a Gurobi solver, SCIP solver, or similar methods. In some implementations, the allocation effect of the target allocation method can be tested to check whether it meets SKU distribution indices, uniformity indices, etc.
[0195] Using the above scheme, candidate allocation methods for goods can be determined based on the quantity of goods to be allocated to each store. Furthermore, by setting a target dimension and first and second constraints under that target dimension, the first and second constraint values of the candidate allocation methods under the target dimension can be calculated. Thus, target allocation methods that satisfy the constraints can be filtered using the first and second constraint values of each store, thereby optimizing the goods allocation results.
[0196] After testing and verification, compared with related cargo allocation methods, the target allocation method obtained by the above scheme can improve the distribution uniformity index by 20%, the variance uniformity index by 10%, and the solution efficiency by 4.5 times.
[0197] Based on the same inventive concept, this disclosure provides a cargo distribution device. Figure 5 This is a block diagram of a cargo distribution device shown in an exemplary embodiment of the present disclosure, with reference to... Figure 5 The device includes:
[0198] The first module 501 is configured to determine the quantity of goods to be allocated to each store;
[0199] The second module 502 is configured to determine the candidate allocation method of goods for each store based on the quantity of goods in each store.
[0200] The third module 503 is configured to calculate a first constraint value representing the quantity of goods allocated under the target dimension, and a second constraint value representing the uniformity of goods allocation under the target dimension.
[0201] The fourth module 504 is configured to determine a target allocation method for goods from the candidate allocation methods, the target allocation method being such that the absolute value of the sum of the constraint values of each store is less than a threshold, the constraint values of the stores including the first constraint value and the second constraint value of the stores.
[0202] Using the above scheme, candidate allocation methods for goods can be determined based on the quantity of goods to be allocated to each store. Furthermore, by setting a target dimension and first and second constraints under that target dimension, the first and second constraint values of the candidate allocation methods under the target dimension can be calculated. Thus, target allocation methods that satisfy the constraints can be filtered using the first and second constraint values of each store, thereby optimizing the goods allocation results.
[0203] Optionally, the target dimension includes the standardized product unit (SKU) dimension, and the third module 503 is configured as follows:
[0204] Calculate the first constraint value representing the number of SKUs in the SKU dimension for the candidate allocation method;
[0205] Calculate the second constraint value representing the uniformity of SKU allocation in the SKU dimension of the candidate allocation method.
[0206] Optionally, the device includes:
[0207] The fifth module is configured to acquire the sales data of the goods in the store;
[0208] The sixth module is configured to obtain the allocation quantity of each SKU of the store under the candidate allocation method;
[0209] The seventh module is configured to calculate the constraint value of the store's goods flow rate based on the goods sales data and the allocation of each SKU, wherein the constraint value of the store includes the constraint value of the goods flow rate.
[0210] Optionally, the target dimension includes the cargo color dimension and / or the cargo configuration dimension, and the third module 503 is configured as follows:
[0211] Calculate a first constraint value representing the quantity of goods of each color under the dimension of goods color for the candidate allocation method; and a second constraint value representing the distribution uniformity of goods colors under the dimension of goods color for the candidate allocation method; and / or,
[0212] Calculate a first constraint value representing the quantity of goods in each configuration under the dimension of goods configuration for the candidate allocation method; and a second constraint value representing the allocation uniformity of goods configuration under the dimension of goods configuration for the candidate allocation method.
[0213] Optionally, the third module 503 is configured as follows:
[0214] Obtain the quantity of goods under the target dimension for the candidate allocation method;
[0215] When the quantity of goods is 0, the first constraint value is determined to be 0;
[0216] If the quantity of goods is not zero, the first constraint value is determined to be a preset gain value corresponding to the target dimension.
[0217] Optionally, the third module 503 is configured as follows:
[0218] Determine the total quantity of the goods under the target dimension;
[0219] Based on the total quantity of goods, calculate the second constraint value representing the uniformity of goods allocation in the target dimension for the candidate allocation method.
[0220] Optionally, the third module 503 is configured to calculate the second constraint value in at least one of the following ways:
[0221] Calculate the square of the total quantity to obtain the second constraint value;
[0222] Calculate the common logarithm of the total quantity; use the negative of the common logarithm as the second constraint value;
[0223] Under the candidate allocation method, obtain the average quantity of goods in each store under the target dimension; calculate the difference between the total quantity and the average value; calculate the square of the difference to obtain the second constraint value.
[0224] This disclosure provides a cargo distribution device, including:
[0225] processor;
[0226] Memory used to store processor-executable instructions;
[0227] The processor is configured to execute any of the cargo allocation methods provided in the embodiments of this disclosure.
[0228] This disclosure provides a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement any of the cargo allocation methods provided in this disclosure.
[0229] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements any of the cargo distribution methods provided in this disclosure.
[0230] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0231] Figure 6This is a block diagram illustrating an apparatus 1900 for goods distribution according to an exemplary embodiment. For example, apparatus 1900 may be provided as a server, computer, etc. (Refer to...) Figure 6 The apparatus 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the aforementioned cargo dispensing method.
[0232] Device 1900 may also include a power supply component 1926 configured to perform power management of device 1900, a wired or wireless network interface 1950 configured to connect device 1900 to a network, and an input / output interface 1958. Device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM FreeBSD TM Or similar.
[0233] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.
[0234] Although terms such as “first,” “second,” and “third” may be used herein to describe various modules, these modules are not limited to these terms. Rather, these terms are used only to distinguish one module from another. Thus, without departing from the teachings of the examples described herein, the first module mentioned in the examples may also be referred to as the second module. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “multiple” means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0235] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”
[0236] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. Furthermore, with regard to the use of terms such as “comprising,” “owning,” “having,” “having,” or variations thereof in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”
[0237] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.
[0238] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for distributing goods, characterized in that, include: Determine the quantity of goods to be allocated to each store; Based on the quantity of goods in each store, determine the candidate allocation method for the goods in each store; Calculate a first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method, and a second constraint value representing the uniformity of goods allocation under the target dimension for the candidate allocation method; The target allocation method for goods is determined from the candidate allocation methods. The target allocation method ensures that the absolute value of the sum of the constraint values of each store is less than a threshold. The constraint values of each store include the first constraint value and the second constraint value of the store.
2. The method according to claim 1, characterized in that, The target dimension includes a standardized product unit (SKU) dimension. The calculation of a first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method, and a second constraint value representing the uniformity of goods allocation under the target dimension for the candidate allocation method, includes: Calculate the first constraint value representing the number of SKUs in the SKU dimension for the candidate allocation method; Calculate the second constraint value representing the uniformity of SKU allocation in the SKU dimension of the candidate allocation method.
3. The method according to claim 2, characterized in that, include: Obtain the sales data of the goods in the store; Obtain the allocation quantity of each SKU in the store under the candidate allocation method; Based on the sales data and the allocation of each SKU, the constraint value of the store's goods flow rate is calculated, and the constraint value of the store includes the constraint value of the goods flow rate.
4. The method according to claim 1, characterized in that, The target dimension includes a cargo color dimension and / or a cargo configuration dimension. The calculation of a first constraint value representing the quantity of cargo allocated under the target dimension for the candidate allocation method, and a second constraint value representing the uniformity of cargo allocation under the target dimension for the candidate allocation method, includes: Calculate a first constraint value representing the quantity of goods of each color under the dimension of goods color for the candidate allocation method; and a second constraint value representing the distribution uniformity of goods colors under the dimension of goods color for the candidate allocation method; and / or, Calculate a first constraint value representing the quantity of goods in each configuration under the dimension of goods configuration for the candidate allocation method; and a second constraint value representing the allocation uniformity of goods configuration under the dimension of goods configuration for the candidate allocation method.
5. The method according to any one of claims 1 to 4, characterized in that, The calculation of the first constraint value representing the quantity of goods allocated under the target dimension for the candidate allocation method includes: Obtain the quantity of goods under the target dimension for the candidate allocation method; When the quantity of goods is 0, the first constraint value is determined to be 0; If the quantity of goods is not zero, the first constraint value is determined to be a preset gain value corresponding to the target dimension.
6. The method according to any one of claims 1 to 4, characterized in that, Calculating the second constraint value representing the uniformity of cargo allocation in the target dimension for the candidate allocation method includes: Determine the total quantity of the goods under the target dimension; Based on the total quantity of goods, calculate the second constraint value representing the uniformity of goods allocation in the target dimension for the candidate allocation method.
7. The method according to claim 6, characterized in that, The step of calculating the second constraint value representing the uniformity of cargo allocation under the target dimension based on the total quantity of the cargo includes: The second constraint value shall be calculated using at least one of the following methods: Calculate the square of the total quantity to obtain the second constraint value; Calculate the common logarithm of the total quantity to obtain the second constraint value; Under the candidate allocation method, obtain the average quantity of goods in each store under the target dimension; calculate the difference between the total quantity and the average value; calculate the square of the difference to obtain the second constraint value.
8. A cargo dispensing device, characterized in that, include: The first module is configured to determine the quantity of goods to be allocated to each store; The second module is configured to determine the candidate allocation method for goods in each store based on the quantity of goods in each store. The third module is configured to calculate a first constraint value representing the quantity of goods allocated under the target dimension, and a second constraint value representing the uniformity of goods allocation under the target dimension; The fourth module is configured to determine a target allocation method for goods from the candidate allocation methods, wherein the target allocation method makes the absolute value of the sum of the constraint values of each store less than a threshold, and the constraint values of each store include a first constraint value and a second constraint value of the store.
9. A cargo dispensing device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to perform the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, they implement the method of any one of claims 1 to 7.
11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.