Replenishment Method, Device and Electronic Equipment

Abstract

The present application provides a replenishment method, apparatus and electronic device, relating to the field of data processing. The method includes: obtaining product information and replenishment cycles of candidate products under a target product category; for the candidate products, obtaining a sales volume prediction sequence of the candidate products in each sales area within the replenishment cycle according to historical data in the product information; obtaining a demand volume set of the candidate products in each sales area according to the sales volume prediction sequence of the candidate products; and performing global warehouse distribution replenishment according to the product information, the demand volume set and the mapping relationship between the sales area and the warehouse to obtain a replenishment strategy for the candidate products. In the embodiments of the present application, on the premise of uncertain demand, based on the sales volume prediction sequence, the order quantity of the candidate products is obtained through global warehouse distribution replenishment. This method can improve the accuracy of replenishment, avoid inventory backlog or out-of-stock situations, and thus avoid waste of storage resources and human resources.

Description

Technical Field

[0001] This application relates to the field of data processing, and particularly to a replenishment method, apparatus, and electronic device. Background Art

[0002] When replenishing goods, due to the influence of random factors, there may be a large deviation between the theoretical prediction of the replenishment quantity of goods and the actual demand, thus affecting the replenishment accuracy and resulting in inventory backlog or out-of-stock situations. Therefore, how to improve the accuracy of replenishment has become one of the key research directions. Summary of the Invention

[0003] This application aims to at least partly solve one of the technical problems in the related art. For this reason, one objective of this application is to propose a replenishment method.

[0004] The second objective of this application is to propose a replenishment apparatus.

[0005] The third objective of this application is to propose an electronic device.

[0006] The fourth objective of this application is to propose a non-transitory computer-readable storage medium.

[0007] The fifth objective of this application is to propose a computer program product.

[0008] To achieve the above objectives, an embodiment of the first aspect of this application proposes a replenishment method, including:

[0009] Obtain the product information and replenishment cycle of candidate products under the target product category;

[0010] For the candidate products, according to the historical data in the product information, obtain the sales volume prediction sequences of the candidate products in each sales area during the replenishment cycle;

[0011] According to the sales volume prediction sequences of the candidate products, obtain the demand quantity sets of the candidate products in each sales area;

[0012] Perform global warehouse distribution replenishment according to the product information, demand quantity sets, and the mapping relationship between the sales area and the warehouse, and obtain the replenishment strategy of the candidate products.

[0013] To achieve the above objectives, an embodiment of the second aspect of this application proposes a replenishment apparatus, including:

[0014] A first acquisition module, configured to obtain the product information and replenishment cycle of candidate products under the target product category;

[0015] A second acquisition module, configured to obtain a sales volume prediction sequence of a candidate product in each sales region within a replenishment cycle according to historical data in the product information for the candidate product;

[0016] A third acquisition module, configured to obtain a demand set of the candidate product in each sales region according to the sales volume prediction sequence of the candidate product;

[0017] A replenishment strategy generation module, configured to perform global warehouse-distributed replenishment according to the product information, the demand set, and the mapping relationship between the sales region and the warehouse, so as to obtain a replenishment strategy for the candidate product.

[0018] To achieve the above object, an embodiment of the third aspect of the present application provides an electronic device, including:

[0019] At least one processor; and

[0020] A memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the replenishment method provided in the embodiment of the first aspect of the present application.

[0022] To achieve the above object, an embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which computer instructions are stored, wherein the computer instructions are used to cause a computer to execute the replenishment method provided in the embodiment of the first aspect of the present application.

[0023] To achieve the above object, an embodiment of the fifth aspect of the present application provides a computer program product, including a computer program, and the computer program implements the replenishment method provided in the embodiment of the first aspect of the present application when executed by a processor.

[0024] Under the premise of uncertain demand, the embodiment of the present application obtains the order quantity of the candidate product through global warehouse-distributed replenishment based on the sales volume prediction sequence. This method can improve the accuracy of replenishment, avoid inventory backlog or out-of-stock situations, and thus avoid waste of storage resources and human resources. Description of the Drawings

[0025] Figure 1 is a flowchart of a replenishment method according to an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of the mapping relationship between a sales region and a warehouse according to an embodiment of the present application;

[0027] Figure 3 is a flowchart of a replenishment method according to an embodiment of the present application;

[0028] Figure 4It is a flowchart of a replenishment method according to an embodiment of the present application;

[0029] Figure 5 It is a flowchart of a replenishment method according to an embodiment of the present application;

[0030] Figure 6 It is a flowchart of a replenishment method according to an embodiment of the present application;

[0031] Figure 7 It is a structural block diagram of a replenishment device according to an embodiment of the present application;

[0032] Figure 8 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0033] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

[0034] The replenishment method, device and electronic device according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0035] Figure 1 It is a flowchart of a replenishment method according to an embodiment of the present application, as Figure 1 shown. The method includes the following steps:

[0036] S101, Obtain the product information and replenishment cycle of the candidate products under the target product category.

[0037] Currently, the competition in terminal sales is becoming increasingly fierce. If the replenishment volume of products is too large, it will cause stockpiling of goods, thus wasting warehouse resources. If the replenishment volume is too small, it will lead to waste of labor, affect the order delivery speed, and reduce the customer experience. Therefore, how to determine the replenishment volume of products to save costs and reasonably allocate resources has become an important research direction.

[0038] In some implementations, time can be used as a condition. Whenever the preset time threshold is reached, it is determined that the product needs to be replenished. For example, the preset time threshold can be 15 days. When the time interval from the last replenishment time reaches 15 days, it is determined that the product needs to be replenished. In some implementations, the inventory level of the candidate products can be used as a condition. That is, when the inventory level in the warehouse is less than the preset inventory threshold, it is determined that the product needs to be replenished. In some implementations, whenever the preset time threshold is reached, or when the inventory level in the warehouse is less than the preset inventory threshold, it is determined that replenishment is required.

[0039] In some implementations, one product category is selected as the target product category, and in some implementations, multiple product categories are selected as the target product categories. Furthermore, product information and replenishment cycles of candidate products under the target product categories are obtained, where the candidate products are Stock Keeping Units (SKUs).

[0040] In an implementation, transportation time and shelving time need to be reserved after replenishment. Therefore, the replenishment cycle also includes the number of days for early replenishment. Optionally, in the embodiments of the present application, the replenishment cycle can be the sum of the inventory counting cycle and the number of days for early replenishment.

[0041] S102. For the candidate products, according to the historical data in the product information, obtain the sales volume prediction sequences of the candidate products in each sales region within the replenishment cycle.

[0042] In the embodiments of the present application, the product information of the candidate products includes the historical data of the candidate products. Optionally, the historical data of the candidate products can be historical sales volume information, that is, the daily sales volume and sales date of the candidate products within a period of time.

[0043] In some implementations, the historical data of the candidate products and the replenishment cycle are input into the quantile prediction model. The quantile prediction model predicts the sales volume of the candidate products in each sales region within the replenishment cycle, and obtains a sales volume prediction sequence of the candidate products in each sales region within the replenishment cycle.

[0044] In some implementations, to improve the accuracy of sales volume prediction, the embodiments of the present application select two prediction quantiles and predict the sales prediction sequence of the candidate products based on the two prediction quantiles. That is, the historical data of the candidate products and the replenishment cycle are input into the quantile prediction model. The quantile prediction model predicts the sales volume of the candidate products in each sales region within the replenishment cycle, and obtains two sales volume prediction sequences of the candidate products in each sales region within the replenishment cycle, namely the first sales volume prediction sequence and the second sales volume prediction sequence, where the prediction quantile of the candidate products in the first sales prediction sequence is greater than the prediction quantile of the candidate products in the second sales prediction sequence.

[0045] Optionally, the quantile prediction model can be a decision tree model, such as a Gradient Boosting Decision Tree (GBDT) model, an eXtreme Gradient Boosting (XGboost) model, a Light Gradient Boosting Machine (light GBM) model, etc.

[0046] Optionally, the sales volume prediction sequence of the candidate product in each sales area within the replenishment cycle is the predicted sales volume value of the candidate product in each sales area every day within the replenishment cycle. For example, when the replenishment cycle is 5 days, the sales volume prediction sequence can be {[39, 60, 56, 45, 52, 57], [65, 46, 36, 59, 58, 62],...}, where [39, 60, 56, 45, 52, 56] is the predicted sales volume value of the first sales area. Among them, 39 is the predicted sales volume value on the first day of the replenishment cycle, 60 is the predicted sales volume value on the second day of the replenishment cycle, and so on. 57 is the predicted sales volume value on the fifth day of the replenishment cycle; similarly, [65, 46, 36, 59, 58, 62] is the predicted sales volume value of the second sales area. Among them, 65 is the predicted sales volume value on the first day of the replenishment cycle, 46 is the predicted sales volume value on the second day of the replenishment cycle, and so on. 62 is the predicted sales volume value on the fifth day of the replenishment cycle.

[0047] S103. According to the sales volume prediction sequence of the candidate product, obtain the demand quantity sets of the candidate product in each sales area.

[0048] In response to obtaining a sales volume prediction sequence of the candidate product in each sales area within the replenishment cycle, sum up the predicted sales volume values in the sales volume prediction sequence to obtain one or more demand quantity sets of the candidate product in each sales area. The demand quantity set includes one or more demand quantities of the candidate product in each sales area.

[0049] In response to obtaining the first sales volume prediction sequence and the second sales volume prediction sequence of the candidate product in each sales area within the replenishment cycle, obtain the difference between the predicted quantiles of the first sales volume prediction sequence and the second sales volume prediction sequence in the same sales period, and then obtain one or more demand quantity sets of the candidate product in each sales area according to the difference.

[0050] S104. Perform global warehouse replenishment according to the product information, the demand quantity sets, and the mapping relationship between the sales area and the warehouse, and obtain the replenishment strategy of the candidate product.

[0051] Figure 2 It is a schematic diagram of the mapping relationship between the sales area and the warehouse in an embodiment of the present application. As Figure 2 shown, optionally, the mapping relationship between the sales area and the warehouse can be obtained according to the supply relationship between the sales area and the warehouse. For example, warehouse S 1 can supply goods to sales areas C 1 , C 2 , C 3 . Warehouse S 2 can supply goods to sales areas C 2 , C 3 . Warehouse S 3 can supply goods to sales area C1 , C 2 supplies, then warehouse S 1 and sales area C 1 , C 2 , C 3 have a mapping relationship. Warehouse S 2 and sales area C 2 , C 3 have a mapping relationship. Warehouse S 3 and sales area C 1 , C 2 have a mapping relationship.

[0052] Optionally, according to the commodity information, the demand volume set, and the mapping relationship between the sales area and the warehouse, global warehouse-based replenishment is performed to obtain the replenishment strategy for the candidate commodities, that is, the replenishment quantity of the candidate commodities in each warehouse.

[0053] Optionally, in implementation, there is also the inventory balance of the candidate commodities in the warehouse. To improve the replenishment accuracy, when performing global warehouse-based replenishment, the current inventory balance also needs to be considered. Global warehouse-based replenishment is performed according to the current inventory balance, the commodity information, the demand volume set, and the mapping relationship between the sales area and the warehouse to obtain the replenishment strategy for the candidate commodities, that is, the order quantity of the candidate commodities in each warehouse and the target replenishment cost.

[0054] In the embodiments of the present application, the commodity information and the replenishment cycle of the candidate commodities under the target commodity category are obtained; for the candidate commodities, according to the historical data in the commodity information, the sales volume prediction sequence of the candidate commodities in each sales area within the replenishment cycle is obtained; according to the sales volume prediction sequence of the candidate commodities, the demand volume set of the candidate commodities in each sales area is obtained; global warehouse-based replenishment is performed according to the commodity information, the demand volume set, and the mapping relationship between the sales area and the warehouse to obtain the replenishment strategy for the candidate commodities. In the embodiments of the present application, under the premise of uncertain demand, based on the sales volume prediction sequence, the order quantity of the candidate commodities is obtained through global warehouse-based replenishment. This method can achieve automated replenishment, improve the accuracy of replenishment, avoid inventory backlog or out-of-stock situations, and thus avoid waste of storage resources and human resources.

[0055] Figure 3 is the flowchart of the replenishment method of an embodiment of the present application. As Figure 3 shown, on the basis of the above embodiments, according to the sales volume prediction sequence of the candidate commodities, obtaining the demand volume set of the candidate commodities in each sales area includes the following steps:

[0056] S301, obtain the difference between the predicted quantiles of the first sales prediction sequence and the second sales prediction sequence in the same sales period, and according to the differences of the predicted quantiles of all sales periods, obtain the safety demand volume of the candidate commodities.

[0057] In the embodiment of the present application, the safety demand quantity of the i-th candidate product in the k-th sales area is:

[0058]

[0059] where C r is the prediction quantile of the first sales prediction sequence, M is the replenishment cycle, and the replenishment cycle can measure the sales period in "hours", or in "days", "weeks", "months" or "quarters". f is the f-th sales period. In the embodiment of the present application, an example is given with "days" as the unit. That is to say, the replenishment cycle is M days in total, and f is the f-th day in M days, where f ≤ M. is the sales prediction value of the i-th candidate product in the k-th sales area on the f-th day in the first sales prediction sequence, and C m is the prediction quantile of the second sales prediction sequence. is the sales prediction value of the i-th candidate product in the k-th sales area on the f-th day in the second sales prediction sequence, and C r > C m . In the embodiment of the present application, C r can take 80, and C m can take 50.

[0060] S302. Obtain the target demand quantity of the candidate product based on the sum value of the first sales prediction sequence and the safety demand quantity.

[0061] In the embodiment of the present application, the target demand quantity of the i-th candidate product in the k-th sales area is:

[0062]

[0063] S303. Modify the target demand quantity to obtain the maximum demand quantity of the candidate product.

[0064] Optionally, in the embodiment of the present application, the target demand quantity can be modified based on the slow-moving factor. The maximum demand quantity of the i-th candidate product in the k-th sales area is:

[0065] sp i,k = xs × oul i,k

[0066] where xs is the slow-moving factor, and the slow-moving factor reflects the slow-moving risk of the candidate product. When the market is in short supply, the value of xs can be increased, and when the market supply exceeds the demand, the value of xs can be decreased. In the embodiment of the present application, xs > 1.

[0067] Under the premise of uncertain demand, this embodiment of the present application obtains the demand quantity of candidate products based on the sales volume prediction sequence, and then obtains the order quantity of candidate products through global warehouse replenishment. This method can achieve automated replenishment, improve the accuracy of replenishment, avoid inventory backlogs or out-of-stock situations, and thus avoid waste of storage resources and human resources.

[0068] Figure 4 is a flowchart of the replenishment method of an embodiment of the present application. As Figure 4 shown, global warehouse replenishment is performed according to product information, demand quantity sets, and the mapping relationship between sales regions and warehouses to obtain the replenishment strategy for candidate products, including the following steps:

[0069] S401, based on product information, demand quantity sets, and the mapping relationship between sales regions and warehouses, obtain the inventory quantity sets of candidate products in their respective warehouses under preset constraint conditions.

[0070] In this embodiment of the present application, the lowest cost is used as the preset constraint condition for illustration.

[0071] Shipping costs will be incurred during the process of transporting candidate products in the warehouse to the sales regions, inventory costs will be incurred during the storage process of candidate products in the warehouse, and shortage losses will be incurred during the reordering process due to out-of-stock impacts after the products in the warehouse are sold out. To obtain the optimal replenishment strategy, in this embodiment of the present application, one or several of shipping costs, inventory costs, and shortage losses can be used as constraint conditions, and based on product information, demand quantity sets, and the mapping relationship between sales regions and warehouses, obtain the inventory quantity sets of candidate products in their respective warehouses.

[0072] Obtain the initial inventory quantity sets of candidate products mapped from each warehouse to each sales region. In some implementations, the maximum capacity of each warehouse can be used as a limiting condition, and a heuristic algorithm can be used to obtain the initial inventory quantity sets. Optionally, the heuristic algorithm can be a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm, etc.

[0073] Starting from the initial inventory quantity sets of candidate products, obtain the replenishment costs of candidate products according to product information, demand quantity sets, the inventory quantity sets updated in the current iteration, and the mapping relationship between sales regions and warehouses.

[0074] For any warehouse, obtain the sum of the inventory quantities in the sales regions of candidate products. If the sum of the inventory quantities is greater than the maximum capacity of the warehouse, that is:

[0075]

[0076] It is determined that the iteration end condition is met. Where n is the number of candidate products, i is the i-th candidate product, c is the number of sales regions, k is the k-th sales region, m is the number of warehouses, j is the j-th warehouse, and P i,j,k is the inventory of the i-th candidate product that the j-th warehouse can ship to the k-th sales region.

[0077] In response to meeting the iteration end condition, select the minimum replenishment cost from the total replenishment costs obtained after each iteration.

[0078] Use the inventory set corresponding to the minimum total replenishment cost as the final inventory set of the candidate products.

[0079] S402. Based on the inventory set, perform global warehouse replenishment for the candidate products to obtain the replenishment strategy for the candidate products.

[0080] Optionally, the economic order quantity (EOQ) model can be used to perform global warehouse replenishment for the candidate products, obtain the optimal order quantity of the candidate products, and generate the replenishment strategy.

[0081] Based on the product information, the demand set, and the mapping relationship between the sales regions and the warehouses, the embodiments of the present application obtain the inventory set of the candidate products in the affiliated warehouses under the preset constraint conditions, and then obtain the order quantity of the candidate products through global warehouse replenishment. This method can achieve automated replenishment, improve the accuracy of replenishment, and coordinate the quantity of inventory products, avoiding inventory backlog or out-of-stock situations, and thus avoiding waste of storage resources and human resources.

[0082] Figure 5 is the flowchart of the replenishment method of an embodiment of the present application. As Figure 5 shown, based on the above embodiments, the method further includes the following steps:

[0083] S501. Based on the initial inventory set and demand of the candidate products mapped from each warehouse to each sales region, obtain the out-of-stock quantity of the candidate products.

[0084] In some implementations, in response to the demand of the candidate product being not greater than the inventory, the out-of-stock quantity of the candidate product is constrained to 0; in response to the demand of the candidate product being greater than the inventory, the out-of-stock quantity of the candidate product is obtained based on the demand and the inventory set. That is

[0085]

[0086] Where R i is the out-of-stock quantity of the i-th product, and sc i,k is the demand of the i-th candidate product in the k-th sales region.

[0087] S502. Obtain the unit out-of-stock cost of the candidate product according to the product information, and obtain the out-of-stock loss of the candidate product according to the unit out-of-stock cost and the out-of-stock quantity of the candidate product.

[0088]

[0089] Among them, cost1 is the inventory cost, and q i is the out-of-stock cost of the i-th candidate product.

[0090] S503. Obtain the unit inventory cost of the candidate product and the inventory quantity of the candidate product mapped from each warehouse to each sales area according to the mapping relationship between the sales area and the warehouse, and obtain the inventory cost of the candidate product according to the unit inventory cost and the inventory quantity of the candidate product.

[0091]

[0092] Among them, cost2 is the out-of-stock loss, and t i,j is the unit inventory cost of the i-th candidate product in the j-th warehouse.

[0093] S504. Obtain the regional shipping cost from the warehouse where the candidate product is located to each sales area, and obtain the shipping cost of the candidate product from the warehouse to the sales area according to the regional shipping cost and the inventory quantity set.

[0094]

[0095] Among them, cost3 is the shipping cost, and d i,j,k is the unit cost of shipping the demand for the i-th product in the k-th sales area from the j-th warehouse.

[0096] S505. Obtain the replenishment cost based on the out-of-stock loss, inventory cost, and shipping cost.

[0097] In the embodiments of the present application, the replenishment cost is the sum of the out-of-stock loss, inventory cost, and shipping cost. That is, cost = cost1 + cost2 + cost3.

[0098] S506. Based on the product information, demand quantity set, and the mapping relationship between the sales area and the warehouse, obtain the inventory quantity set of the candidate product in its affiliated warehouse under preset constraint conditions.

[0099] S507. Perform global warehouse replenishment according to the inventory quantity set to obtain the replenishment strategy of the candidate product.

[0100] For the relevant content of step S506 and step S507, reference can be made to the relevant descriptions in the above embodiments, and details are not described herein again.

[0101] In the embodiments of the present application, the replenishment cost is obtained based on the out-of-stock loss, inventory cost, and shipping cost, and then the inventory quantity set of the candidate products in the affiliated warehouse is obtained under preset constraint conditions. The order quantity of the candidate products is obtained through global warehouse replenishment. This method can achieve automated replenishment, improve the accuracy of replenishment, and coordinate the quantity of inventory items, avoiding inventory backlogs or out-of-stock situations, and thus avoiding waste of storage resources and human resources.

[0102] In some implementations, the safety inventory quantity with the lowest cost is obtained based on the safety demand quantity; the target inventory quantity with the lowest cost is obtained based on the target demand quantity; the maximum inventory quantity with the lowest cost is obtained based on the maximum demand quantity. That is, the safety demand quantity of the i-th candidate product in the k-th sales area is used as sc i,k The out-of-stock quantity of the candidate product is obtained, and then the safety inventory quantity with the lowest cost is obtained; the target demand quantity of the i-th candidate product in the k-th sales area is used as sc i,k The out-of-stock quantity of the candidate product is obtained, and then the target inventory quantity with the lowest cost is obtained; the maximum demand quantity of the i-th candidate product in the k-th sales area is used as sc i,k The out-of-stock quantity of the candidate product is obtained, and then the maximum inventory quantity with the lowest cost is obtained.

[0103] Figure 6 is a flowchart of the replenishment method according to an embodiment of the present application. As Figure 6 shown, based on the above embodiments, the method further includes the following steps:

[0104] S601, obtain the current inventory balance.

[0105] Obtain the current inventory balance of the candidate products in each warehouse.

[0106] S602, in response to the current inventory balance of the candidate products being less than the sum of the inventory quantities in the target inventory quantity set, obtain the estimated demand quantity of the candidate products in each warehouse based on the sum of the inventory quantities in the target inventory quantity set and the current inventory balance of the candidate products.

[0107] If the current inventory balance of the candidate products is less than the sum of the inventory quantities in the target inventory quantity set, then use the difference between the sum of the inventory quantities in each sales area of the target inventory quantity set and the current inventory balance of the candidate products as the estimated demand quantity of the candidate products in each warehouse.

[0108] S603, input the estimated demand quantity and the safety demand quantity into the economic order quantity model to obtain the order quantity and the target replenishment cost of the candidate products in each warehouse.

[0109] The order quantity of the candidate products is:

[0110]

[0111] Among them, Q i,j is the order quantity of the i-th candidate product in the j-th warehouse, and D i,j is the estimated demand of the i-th candidate product in the j-th warehouse, and S i is the single-ordering cost of the i-th candidate product.

[0112] The target replenishment cost of the candidate product is:

[0113] TC i,j = D i,j × C i + D i,j / Q i,j × S i + Q i,j × t i,j / 2

[0114] Among them, TC i,j is the target replenishment cost of the i-th candidate product in the j-th warehouse, and Ci is the purchase unit price of the i-th product.

[0115] Optionally, in some implementations, in order to reduce the loss of out-of-stock, when the inventory level in the warehouse is less than the inventory threshold, the candidate product needs to be replenished, and the inventory threshold is:

[0116] R i,j = L i,j × E i,j + ss i,j

[0117] Among them, R i,j is the inventory threshold of the i-th candidate product in the j-th warehouse, L i,j is the days of advance replenishment of the i-th candidate product in the j-th warehouse, L i,j is the average daily demand of the i-th candidate product in the j-th warehouse, L i,j is the safety demand of the i-th candidate product in the j-th warehouse.

[0118] In some implementations, in response to the current inventory balance of the candidate product being greater than the sum of the inventory levels in the sales areas with the largest inventory levels, an inventory slow-moving warning is issued.

[0119] In some implementations, in response to the current inventory balance of the candidate product being less than the sum of the inventory levels in the sales areas with the safety inventory levels, an inventory out-of-stock warning is issued.

[0120] Based on the economic order quantity model, the embodiments of the present application obtain the order quantity of candidate products in each warehouse and the target replenishment cost. This method can achieve automated replenishment, improve the accuracy of replenishment, and coordinate the quantity of inventory products to avoid inventory backlog or out-of-stock situations, thereby avoiding waste of storage resources and human resources.

[0121] As Figure 7 shown, based on the same inventive concept, the embodiments of the present application further provide a replenishment device 700, including:

[0122] A first acquisition module 710, configured to acquire product information and replenishment cycles of candidate products under a target product category;

[0123] A second acquisition module 720, configured to, for candidate products, acquire a predicted sales volume sequence of candidate products in each sales region during the replenishment cycle according to historical data in the product information;

[0124] A third acquisition module 730, configured to acquire a demand set of candidate products in each sales region according to the predicted sales volume sequence of candidate products;

[0125] A replenishment strategy generation module 740, configured to perform global warehouse-based replenishment according to product information, the demand set, and the mapping relationship between the sales region and the warehouse, and acquire a replenishment strategy for candidate products.

[0126] Further, in a possible implementation manner of the embodiments of the present application, the second acquisition module 720 is further configured to:

[0127] Input the historical data of candidate products and the replenishment cycle into a quantile prediction model, and the quantile prediction model predicts the sales volume of candidate products in each sales region during the replenishment cycle to obtain a first predicted sales volume sequence and a second predicted sales volume sequence, where the predicted quantile of candidate products in the first predicted sales volume sequence is greater than the predicted quantile of candidate products in the second predicted sales volume sequence.

[0128] Further, in a possible implementation manner of the embodiments of the present application, the third acquisition module 730 is further configured to:

[0129] Acquire the difference between the predicted quantiles of the first predicted sales volume sequence and the second predicted sales volume sequence in the same sales period, and acquire the safety demand of candidate products according to the differences of the predicted quantiles in all sales periods;

[0130] Acquire the target demand of candidate products based on the sum value of the first predicted sales volume sequence and the safety demand;

[0131] Correct the target demand to obtain the maximum demand of candidate products.

[0132] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0133] Based on the commodity information, the demand quantity set, and the mapping relationship between the sales area and the warehouse, obtain the inventory quantity set of the candidate commodities in the affiliated warehouse under preset constraint conditions;

[0134] Perform global warehouse replenishment according to the inventory quantity set to obtain the replenishment strategy of the candidate commodities.

[0135] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0136] Obtain the initial inventory quantity set of the candidate commodities mapped from each warehouse to each sales area;

[0137] Starting from the initial inventory quantity set of the candidate commodities, according to the commodity information, the demand quantity set, the currently iteratively updated inventory quantity set, and the mapping relationship between the sales area and the warehouse, obtain the replenishment cost of the candidate commodities;

[0138] In response to meeting the iteration end condition, select the minimum replenishment cost from the total replenishment costs obtained after each iteration;

[0139] Use the inventory quantity set corresponding to the minimum total replenishment cost as the final inventory quantity set of the candidate commodities.

[0140] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0141] Based on the currently iteratively updated inventory quantity set and the demand quantity in the sales area corresponding to each warehouse of the candidate commodities, obtain the out-of-stock quantity;

[0142] According to the commodity information, obtain the unit out-of-stock cost of the candidate commodities, and based on the unit out-of-stock cost and the out-of-stock quantity of the candidate commodities, obtain the out-of-stock loss of the candidate commodities;

[0143] According to the mapping relationship between the sales area and the warehouse, obtain the unit inventory cost of the candidate commodities and the inventory quantity of the candidate commodities mapped from each warehouse to each sales area, and based on the unit inventory cost and the inventory quantity of the candidate commodities, obtain the inventory cost of the candidate commodities;

[0144] Obtain the regional shipping cost of the candidate commodities shipped from the warehouse where they are located to each sales area, and based on the regional shipping cost and the inventory quantity set, obtain the shipping cost of the candidate commodities from the warehouse to the sales area;

[0145] Based on the out-of-stock loss, the inventory cost, and the shipping cost, obtain the replenishment cost.

[0146] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0147] For any warehouse, obtain the sum of the inventory quantities in the sales areas of the candidate products. If the sum of the inventory quantities is greater than the maximum capacity of the warehouse, it is determined that the iteration end condition is satisfied.

[0148] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0149] In response to the demand quantity of the candidate product being not greater than the inventory quantity, constrain the out-of-stock quantity of the candidate product to 0;

[0150] In response to the demand quantity of the candidate product being greater than the inventory quantity, obtain the out-of-stock quantity of the candidate product based on the demand quantity and the inventory quantity set.

[0151] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0152] Based on the product information, the safety demand quantity, and the mapping relationship between the sales area and the warehouse, obtain the safety inventory quantity with the lowest cost;

[0153] Based on the product information, the target demand quantity, and the mapping relationship between the sales area and the warehouse, obtain the target inventory quantity with the lowest cost;

[0154] Based on the product information, the maximum demand quantity, and the mapping relationship between the sales area and the warehouse, obtain the maximum inventory quantity with the lowest cost.

[0155] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0156] Obtain the current inventory balance;

[0157] In response to the current inventory balance of the candidate product being less than the sum of the inventory quantities in the target inventory quantity set, obtain the estimated demand quantity of the candidate product in each warehouse based on the sum of the inventory quantities in the target inventory quantity set and the current inventory balance of the candidate product;

[0158] Input the estimated demand quantity and the safety demand quantity into the economic order quantity model to obtain the order quantity of the candidate product in each warehouse and the target replenishment cost.

[0159] Further, in a possible implementation manner of the embodiment of the present application, the replenishment strategy generation module 740 is further configured to:

[0160] If the current inventory balance of the candidate product is greater than the sum of the inventory quantities in the maximum inventory, an inventory slow-moving warning is issued; or if the current inventory balance of the candidate product is less than the sum of the inventory quantities in the safety inventory, an inventory shortage warning is issued.

[0161] In the embodiments of the present application, under the premise of uncertain demand, based on the sales volume prediction sequence, the order quantity of the candidate product is obtained through global warehouse replenishment. This method can achieve automated replenishment, improve the accuracy of replenishment, and coordinate the quantity of inventory products, avoiding inventory backlog or shortage, and thus avoiding waste of storage resources and human resources.

[0162] Based on the same inventive concept, the embodiments of the present application also provide an electronic device.

[0163] Figure 8 It is a schematic structural diagram of the electronic device provided by the embodiments of the present application. As Figure 8 shown, the electronic device 800 includes a storage medium 810, a processor 820, and a computer program product stored on the storage medium 810 and executable on the processor 820. When the processor executes the computer program, the foregoing replenishment method is implemented.

[0164] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0165] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0166] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0167] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0168] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which computer instructions are stored. Among them, the computer instructions are used to cause a computer to execute the replenishment method in the above embodiment.

[0169] Based on the same application concept, an embodiment of the present application further provides a computer program product, including a computer program that, when executed by a processor, performs the replenishment method in the above embodiment.

[0170] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The present application can be implemented by means of hardware including several different components and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0171] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality of" means two or more, unless otherwise specifically defined.

[0172] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0173] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A replenishment method, characterized in that, it includes: Obtain the product information and replenishment cycle of candidate products under the target product category; For the candidate products, according to the historical data in the product information, obtain the sales volume prediction sequences of the candidate products in each sales area during the replenishment cycle; According to the sales volume prediction sequences of the candidate products, obtain the demand quantity sets of the candidate products in each sales area; Perform global warehouse-distributed replenishment according to the product information, the demand quantity sets, and the mapping relationship between the sales areas and the warehouses, and obtain the replenishment strategy of the candidate products; Among them, the performing global warehouse-distributed replenishment according to the product information, the demand quantity sets, and the mapping relationship between the sales areas and the warehouses, and obtaining the replenishment strategy of the candidate products includes: Obtain the initial inventory quantity sets of the candidate products mapped from each warehouse to each sales area; Starting from the initial inventory quantity sets of the candidate products, according to the product information, the demand quantity sets, the inventory quantity sets updated iteratively currently, and the mapping relationship between the sales areas and the warehouses, obtain the replenishment cost of the candidate products; In response to meeting the iteration end condition, select the minimum replenishment cost from the total replenishment costs obtained after each iteration; Use the inventory quantity set corresponding to the minimum replenishment cost as the final inventory quantity set of the candidate products; Perform global warehouse-distributed replenishment according to the inventory quantity set, and obtain the replenishment strategy of the candidate products.

2. The method according to claim 1, characterized in that, the for the candidate products, according to the historical data, obtaining the sales volume prediction sequences of the candidate products in each sales area during the replenishment cycle includes: Input the historical data and replenishment cycle of the candidate products into a quantile prediction model, and the quantile prediction model predicts the sales volume of the candidate products in each sales area during the replenishment cycle, and obtain a first sales volume prediction sequence and a second sales volume prediction sequence, wherein, the prediction quantile of the candidate products in the first sales volume prediction sequence is greater than the prediction quantile of the candidate products in the second sales volume prediction sequence.

3. The method according to claim 2, characterized in that, the according to the sales volume prediction sequences of the candidate products, obtaining the demand quantity sets of the candidate products in each sales area includes: Obtain the difference between the prediction quantiles of the first sales volume prediction sequence and the second sales volume prediction sequence in the same sales period, and according to the differences of the prediction quantiles in all sales periods, obtain the safety demand quantity of the candidate products; Based on the sum value of the first sales volume prediction sequence and the safety demand quantity, obtain the target demand quantity of the candidate products; Correct the target demand quantity to obtain the maximum demand quantity of the candidate products.

4. The method according to claim 1, characterized in that, the according to the product information, the demand quantity sets, the inventory quantity sets updated iteratively currently, and the mapping relationship between the sales areas and the warehouses, obtaining the replenishment cost of the candidate products includes: Obtain the out-of-stock quantity based on the inventory quantity set and the demand quantity currently iteratively updated for the corresponding sales regions of the candidate product in each warehouse; According to the product information, obtain the unit out-of-stock cost of the candidate product, and based on the unit out-of-stock cost and the out-of-stock quantity of the candidate product, obtain the out-of-stock loss of the candidate product; According to the mapping relationship between the sales region and the warehouse, obtain the unit inventory cost of the candidate product and the inventory quantity of the candidate product mapped from each warehouse to each sales region, and based on the unit inventory cost and the inventory quantity of the candidate product, obtain the inventory cost of the candidate product; Obtain the regional shipping cost for the candidate product shipped from the warehouse where it is located to each sales region, and based on the regional shipping cost and the inventory quantity set, obtain the shipping cost for the candidate product from the warehouse to the sales region; Obtain the replenishment cost based on the out-of-stock loss, the inventory cost, and the shipping cost.

5. The method according to claim 4, wherein, the satisfaction of the iteration end condition includes: For any warehouse, obtain the sum of the inventory quantities of the candidate product in the sales regions, and if the sum of the inventory quantities is greater than the maximum capacity of the warehouse, it is determined that the iteration end condition is satisfied.

6. The method according to claim 4, wherein, the obtaining of the out-of-stock quantity based on the inventory quantity set and the demand quantity currently iteratively updated for the corresponding sales regions of the candidate product in each warehouse includes: In response to the demand quantity of the candidate product not being greater than the inventory quantity, constrain the out-of-stock quantity of the candidate product to 0; In response to the demand quantity of the candidate product being greater than the inventory quantity, obtain the out-of-stock quantity of the candidate product based on the demand quantity and the inventory quantity set.

7. The method according to any one of claims 1-4, wherein, obtaining the inventory quantity set of the candidate product in the warehouse to which it belongs under preset constraint conditions includes: Based on the product information, the safety demand quantity, and the mapping relationship between the sales region and the warehouse, obtain the safety inventory quantity with the lowest cost; Based on the product information, the target demand quantity, and the mapping relationship between the sales region and the warehouse, obtain the target inventory quantity with the lowest cost; Based on the product information, the maximum demand quantity, and the mapping relationship between the sales region and the warehouse, obtain the maximum inventory quantity with the lowest cost.

8. The method according to claim 7, wherein, the obtaining of the replenishment strategy of the candidate product by performing global warehouse replenishment according to the inventory quantity set further includes: Obtain the current inventory balance; In response to the current inventory balance of the candidate product being less than the sum of the inventory quantities in the target inventory quantity set, obtain the estimated demand quantity of the candidate product in each warehouse based on the sum of the inventory quantities in the target inventory quantity set and the current inventory balance of the candidate product; Input the estimated demand quantity and the safety demand quantity into the economic order quantity model to obtain the order quantity and the target replenishment cost of the candidate product in each warehouse.

9. The method according to claim 7, wherein, further includes: In response to the current inventory surplus of the candidate product being greater than the sum of the inventory quantities in the maximum inventory quantities, inventory slow-moving warnings are issued; or In response to the current inventory surplus of the candidate product being less than the sum of the inventory quantities in the safety inventory quantities, inventory out-of-stock warnings are issued.

10. A replenishment device, characterized in that, it includes: A first acquisition module for acquiring the product information and replenishment cycle of candidate products under a target product category; A second acquisition module for, for the candidate products, according to the historical data in the product information, acquiring the sales volume prediction sequences of the candidate products in each sales area during the replenishment cycle; A third acquisition module for, according to the sales volume prediction sequences of the candidate products, acquiring the demand quantity sets of the candidate products in each sales area; A replenishment strategy generation module for performing global warehouse-based replenishment according to the product information, the demand quantity sets, and the mapping relationship between the sales areas and the warehouses, and acquiring the replenishment strategy of the candidate products; The replenishment strategy generation module is further configured to: Acquire the initial inventory quantity sets of the candidate products mapped from each warehouse to each sales area; Starting from the initial inventory quantity sets of the candidate products, according to the product information, the demand quantity sets, the currently iteratively updated inventory quantity sets, and the mapping relationship between the sales areas and the warehouses, acquire the replenishment costs of the candidate products; In response to meeting the iteration end condition, select the minimum replenishment cost from the replenishment total costs obtained after each iteration; Use the inventory quantity set corresponding to the minimum replenishment cost as the final inventory quantity set of the candidate products; Perform global warehouse-based replenishment according to the inventory quantity set, and acquire the replenishment strategy of the candidate products.

11. The device according to claim 10, characterized in that, the second acquisition module is further configured to: Input the historical data of the candidate products and the replenishment cycle into a quantile prediction model, and the quantile prediction model predicts the sales volume of the candidate products in each sales area during the replenishment cycle, and acquires a first sales volume prediction sequence and a second sales volume prediction sequence, wherein the predicted quantile of the candidate products in the first sales prediction sequence is greater than the predicted quantile of the candidate products in the second sales prediction sequence.

12. The device according to claim 11, characterized in that, the third acquisition module is further configured to: Acquire the difference between the predicted quantiles of the first sales volume prediction sequence and the second sales volume prediction sequence in the same sales period, and acquire the safety demand quantity of the candidate products according to the differences in the predicted quantiles of all sales periods; Obtain the target demand quantity of the candidate products based on the sum value of the first sales volume prediction sequence and the safety demand quantity; Correct the target demand quantity to obtain the maximum demand quantity of the candidate products.

13. The device according to claim 10, characterized in that, the replenishment strategy generation module is further configured to: Based on the currently iteratively updated inventory quantity sets and demand quantities of the candidate products corresponding to each warehouse in the sales area, acquire the out-of-stock quantity; Obtain the unit out-of-stock cost of the candidate product according to the product information, and obtain the out-of-stock loss of the candidate product according to the unit out-of-stock cost and the out-of-stock quantity of the candidate product; Obtain the unit inventory cost of the candidate product and the inventory quantity of the candidate product mapped from each warehouse to each sales area according to the mapping relationship between the sales area and the warehouse, and obtain the inventory cost of the candidate product according to the unit inventory cost and the inventory quantity of the candidate product; Obtain the regional shipping cost from the warehouse where the candidate product is located to each sales area, and obtain the shipping cost of the candidate product from the warehouse to the sales area according to the regional shipping cost and the inventory quantity set; Obtain the replenishment cost based on the out-of-stock loss, the inventory cost, and the shipping cost.

14. The apparatus according to claim 10 or 13, wherein, the replenishment strategy generation module is further configured to: For any warehouse, obtain the sum of the inventory quantities of the candidate product in the sales area. If the sum of the inventory quantities is greater than the maximum capacity of the warehouse, it is determined that the iteration end condition is satisfied.

15. The apparatus according to claim 14, wherein, the replenishment strategy generation module is further configured to: In response to the demand quantity of the candidate product being not greater than the inventory quantity, constrain the out-of-stock quantity of the candidate product to 0; In response to the demand quantity of the candidate product being greater than the inventory quantity, obtain the out-of-stock quantity of the candidate product based on the demand quantity and the inventory quantity set.

16. The apparatus according to any one of claims 10-13, wherein, the replenishment strategy generation module is further configured to obtain the inventory quantity set of the candidate product in the affiliated warehouse under preset constraint conditions: obtain the safety inventory quantity with the lowest cost based on the product information, the safety demand quantity, and the mapping relationship between the sales area and the warehouse; Obtain the target inventory quantity with the lowest cost based on the product information, the target demand quantity, and the mapping relationship between the sales area and the warehouse; Obtain the maximum inventory quantity with the lowest cost based on the product information, the maximum demand quantity, and the mapping relationship between the sales area and the warehouse.

17. The apparatus according to claim 16, wherein, the replenishment strategy generation module is further configured to: Obtain the current inventory balance; In response to the current inventory balance of the candidate product being less than the sum of the inventory quantities in the target inventory quantity set, obtain the estimated demand quantity of the candidate product in each warehouse based on the sum of the inventory quantities in the target inventory quantity set and the current inventory balance of the candidate product; Input the estimated demand quantity and the safety demand quantity into the economic order quantity model to obtain the order quantity and the target replenishment cost of the candidate product in each warehouse.

18. The apparatus according to claim 16, wherein, the replenishment strategy generation module is further configured to: In response to the current inventory balance of the candidate product being greater than the sum of the inventory quantities in the maximum inventory quantity set, issue an inventory slow-moving warning; or In response to the current inventory balance of the candidate product being less than the sum of the inventory levels in the safety inventory concentration, an inventory out-of-stock warning is issued.

19. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1-9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein, the computer instructions are for causing the computer to execute the method according to any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.

Images