Cloud warehouse selection method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a cloud warehouse product selection method, device, electronic equipment and storage medium. The method comprises: screening initial SKUs according to the predicted sales of the SKUs, and constructing an initial product selection pool; obtaining the days of inventory turnover of the in-stock SKUs in the current cloud warehouse, screening low inventory turnover SKUs, and constructing a low inventory turnover pool; determining the threshold of allowed new SKU categories according to the SKU categories of the current cloud warehouse, the soft upper limit of target SKU categories, the hard upper limit of target SKU categories, and the low inventory turnover SKU categories in the low inventory turnover pool; and obtaining target SKUs from the initial product selection pool according to the threshold of allowed new SKU categories and the predicted sales of the initial SKUs, and adding the target SKUs to a final product selection pool. The method makes the cloud warehouse product selection more efficient and controllable, significantly reduces the labor cost related to product selection, ensures the normal operation of the cloud warehouse, and reduces the cloud warehouse fulfillment cost.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and more specifically, the embodiments of the present invention relate to cloud warehouse product selection methods, apparatus, electronic devices and storage media. Background Technology

[0002] This section is intended to provide background or context for embodiments of the invention as set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] With the booming development of the e-commerce industry, more and more e-commerce sellers are using cloud warehousing to solve their warehousing and delivery problems. Compared with the traditional self-built warehousing model of e-commerce, cloud warehousing can bring lower fulfillment costs.

[0004] However, cloud warehouses have certain business constraints and are not suitable for all SKUs, and there are also limitations on the number of SKU types that can be stored in a cloud warehouse. Therefore, product selection becomes a crucial aspect of the normal operation of a cloud warehouse.

[0005] In similar business scenarios today, product selection is mostly done manually by business personnel based on their experience. When the data volume is large, manual processing becomes extremely difficult and inefficient. Furthermore, the product selection process is largely based on subjective judgment, making the results uncontrollable and leading to business losses. Summary of the Invention

[0006] However, due to human selection processes, existing technologies are inefficient in selecting products.

[0007] Therefore, in the current technology, the product selection process is inefficient, which is a very frustrating process.

[0008] Therefore, there is a great need for an improved product selection method for cloud warehouses to make product selection more efficient.

[0009] In this context, embodiments of the present disclosure are intended to provide a cloud warehouse product selection method, apparatus, electronic device, and storage medium.

[0010] In a first aspect of this disclosure, a cloud warehouse product selection method is provided, comprising: filtering a preset number of initial SKUs based on the predicted sales volume of SKUs to construct an initial product selection pool; obtaining the inventory turnover days of SKUs currently in stock in the cloud warehouse and filtering low-inventory-turnover SKUs to construct a low-inventory-turnover pool; determining a threshold for allowing the addition of new SKU types based on the current cloud warehouse SKU types, the soft upper limit of the target SKU types, the hard upper limit of the target SKU types, and the low-inventory-turnover SKU types in the low-inventory-turnover pool; and obtaining target SKUs from the initial product selection pool and adding them to the final product selection pool based on the threshold for allowing the addition of new SKU types and the predicted sales volume of the initial SKUs.

[0011] In one embodiment of this disclosure, the step of filtering initial SKUs based on the predicted sales of SKUs and constructing an initial product selection pool includes: obtaining SKUs that meet preset cloud warehouse product selection rules; obtaining a preset number of initial SKUs based on the predicted sales of the SKUs, wherein the preset number is a soft upper limit for the target SKU category; and sorting the initial SKUs in descending order of predicted sales to construct the initial product selection pool.

[0012] In another embodiment of this disclosure, obtaining the inventory turnover days of SKUs currently in stock in the cloud warehouse and filtering low-turnover SKUs to construct a low-turnover pool includes: obtaining the current SKU inventory in the cloud warehouse; obtaining the inventory turnover days of each SKU in stock based on the current SKU inventory in the cloud warehouse; marking SKUs in stock with inventory turnover days less than the inventory turnover days threshold as low-turnover SKUs based on the inventory turnover days of each SKU in stock; and arranging the low-turnover SKUs in descending order of predicted sales to construct the low-turnover pool.

[0013] In another embodiment of this disclosure, determining the threshold for allowing new SKU types based on the current cloud warehouse SKU types, the target SKU type soft upper limit, the target SKU type hard upper limit, and the low-stock transfer SKU types in the low-stock transfer pool includes: determining the hard upper limit for allowing new SKU types based on the target SKU type hard upper limit and the current number of SKU types in the cloud warehouse; determining the soft upper limit for allowing new SKU types based on the target SKU type soft upper limit, the cloud warehouse SKU types, and the low-stock transfer SKU types; and determining the threshold for allowing new SKU types by taking the minimum value between the hard upper limit for allowing new SKU types and the soft upper limit for allowing new SKU types.

[0014] In another embodiment of this disclosure, the step of obtaining a target SKU from the initial selection pool and adding it to the final selection pool based on the allowed threshold for new SKU types and the predicted sales of the initial SKU includes: determining a list of new SKUs in the initial selection pool relative to the SKUs in the cloud warehouse; sequentially traversing the initial SKUs in the initial selection pool to determine whether the current initial SKU exists in the list of new SKUs or the low-inventory transfer pool; if the current initial SKU does not exist in the list of new SKUs or the low-inventory transfer pool, then adding the current initial SKU to the final selection pool; if the current initial SKU exists in the list of new SKUs or the low-inventory transfer pool, then determining whether the current new SKU type exceeds the allowed threshold for new SKU types, wherein the current new SKU type is the target SKU to be added to the final selection pool. KU types; if the number of newly added SKU types is greater than the threshold for allowed new SKU types, then the current initial SKU is not added to the final selection pool; if the number of newly added SKU types is less than or equal to the threshold for allowed new SKU types, then it is determined whether the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of low-inventory SKUs in the low-inventory transfer pool is greater than the sales increase threshold; if the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of low-inventory SKUs in the low-inventory transfer pool is greater than the sales increase threshold, then the current initial SKU is added to the final selection pool as a target SKU; if the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of low-inventory SKUs in the low-inventory transfer pool is less than or equal to the sales increase threshold, then the current initial SKU is not added to the final selection pool.

[0015] In another embodiment of this disclosure, the process of determining whether the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low-inventory transfer SKUs in the low-inventory transfer pool is greater than the sales increase threshold includes: labeling each low-inventory transfer SKU in descending order to obtain the label of each low-inventory transfer SKU; determining the calculation starting point of the current initial SKU, wherein the calculation starting point is the low-inventory transfer SKU with the next label corresponding to the low-inventory transfer SKU at the end of the previous initial SKU judgment process; starting from the calculation starting point, continuously calculating the ratio of the predicted sales of the current initial SKU to the predicted sales of each low-inventory transfer SKU to obtain the increase ratio; comparing the increase ratio with the sales increase threshold, and ending the judgment process when the target SKU is obtained or all low-inventory transfer SKUs have been traversed.

[0016] In yet another embodiment of this disclosure, the SKUs in the final selection pool are arranged from largest to smallest according to predicted sales volume.

[0017] In a second aspect of this disclosure, a cloud warehouse product selection device is provided, comprising: a product selection pool construction module, configured to filter initial SKUs based on the predicted sales volume of SKUs and construct an initial product selection pool; a low-inventory transfer pool construction module, configured to obtain the inventory turnover days of SKUs currently in the cloud warehouse and filter low-inventory transfer SKUs to construct a low-inventory transfer pool; a new addition threshold determination module, configured to determine a threshold for allowing new SKU types based on the current cloud warehouse SKU types, a soft upper limit for target SKU types, a hard upper limit for target SKU types, and the low-inventory transfer SKU types in the low-inventory transfer pool; and a product selection module, configured to obtain target SKUs from the initial product selection pool and add them to the final product selection pool based on the allowed new SKU type threshold and the predicted sales volume of the initial SKUs.

[0018] In a third aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the cloud warehouse product selection method described in any of the preceding embodiments via executing the executable instructions.

[0019] In a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the cloud warehouse product selection method described in any of the preceding embodiments.

[0020] According to the cloud warehouse product selection method of this disclosure, initial SKUs are selected based on the predicted sales volume of SKUs to construct an initial product selection pool. Then, the inventory turnover days of SKUs currently in stock in the cloud warehouse are obtained, and low-inventory-turnover SKUs are selected to construct a low-inventory-turnover pool. Based on the current cloud warehouse SKU types, the soft upper limit and hard upper limit of target SKU types, and the low-inventory-turnover SKU types in the low-inventory-turnover pool, a threshold for allowing the addition of new SKU types is determined. Based on the threshold for allowing the addition of new SKU types and the predicted sales volume of the initial SKUs, target SKUs are obtained from the initial product selection pool and added to the final product selection pool. This method can ensure the accuracy of product selection results under controllable conditions without manual intervention, thereby significantly reducing the labor costs associated with product selection and avoiding product accumulation in the cloud warehouse due to selection errors, making cloud warehouse product selection more efficient. Attached Figure Description

[0021] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0022] Figure 1 A schematic diagram illustrating an application scenario according to an embodiment of the present disclosure is provided.

[0023] Figure 2A schematic flowchart of a cloud warehouse product selection method according to an embodiment of the present disclosure is shown.

[0024] Figure 3 A schematic flowchart of a cloud warehouse product selection method according to another embodiment of the present disclosure is shown.

[0025] Figure 4 A schematic flowchart of a cloud warehouse product selection method according to yet another embodiment of the present disclosure is shown.

[0026] Figure 5 A schematic flowchart of a cloud warehouse product selection method according to another embodiment of the present disclosure is shown.

[0027] Figure 6 A schematic diagram illustrating the judgment process of a cloud warehouse product selection method according to an embodiment of the present disclosure is shown.

[0028] Figure 7 A schematic flowchart of a cloud warehouse product selection method according to another embodiment of the present disclosure is shown.

[0029] Figure 8 A schematic diagram of the structure of a storage medium according to an embodiment of the present disclosure is shown.

[0030] Figure 9 A schematic diagram of the structure of a cloud warehouse product selection device according to an embodiment of the present disclosure is shown.

[0031] Figure 10 A schematic diagram of the structure of a computer device according to an embodiment of the present disclosure is shown.

[0032] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0033] The principles and spirit of this disclosure will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0034] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0035] According to embodiments of this disclosure, a method, apparatus, electronic device, and storage medium for cloud warehouse product selection are proposed.

[0036] In this article, it is important to understand that the terms used have the following meanings:

[0037] Cloud warehousing: A new warehousing model emerging in the current e-commerce environment. Cloud warehousing is a third-party warehousing service that can solve all aspects of warehousing, sorting, packaging, and shipping in one stop. Compared to traditional e-commerce warehouses, cloud warehouses have lower fulfillment costs, but they have certain requirements on the number of SKUs in the warehouse and need to maintain the simplest possible product structure.

[0038] SKU: The smallest inventory unit, which can be understood as a product with a specific specification.

[0039] Sales Quantity vs. Sales Order Quantity: Sales quantity refers to the number of units sold for each SKU, while sales order quantity includes the number of outbound orders for each SKU. Relationship between Sales Quantity and Sales Order Quantity: For example, suppose User 1 buys 5 units of SKUa, User 2 buys 1 unit of SKUa and 3 units of SKUb. Then the sales quantity of SKUa is 6 units, and the sales quantity of SKUb is 3 units. The merchant packages the two users' orders into two parcels and ships them to User 1 (SKUa × 5) and User 2 (SKUa × 1 + SKUb × 3) respectively. In this case, the sales order quantity of SKUa is 2, and the sales order quantity of SKUb is 1.

[0040] Inventory turnover days: The number of days that the current inventory of a product can support its sales. For example, if an average of 10 units of a product are sold per day and the current inventory is 500 units, then the inventory turnover days are 50 days.

[0041] Soft and Hard Limits for Target SKU Varieties: The soft limit for target SKU varieties refers to the maximum number of target SKU varieties that must not be exceeded during product selection to maintain the normal operation of the cloud warehouse. The hard limit for target SKU varieties refers to a soft limit on the number of target SKU varieties that must not be exceeded during product selection to maintain the normal operation of the cloud warehouse. The soft limit serves as an expected value for the number of selected SKU varieties. Controllable changes in product selection are allowed; the number of SKU varieties in the cloud warehouse can exceed the soft limit, but cannot exceed the hard limit, fluctuating around the soft limit.

[0042] Furthermore, the number of any elements in the accompanying drawings is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0043] The principles and spirit of this disclosure will be explained in detail below with reference to several representative embodiments.

[0044] Public Overview

[0045] This disclosure reveals that with the booming development of the e-commerce industry and the current popularity of live-streaming sales, most orders placed by users in live-streaming rooms are single-item orders (i.e., orders containing only one type of product). These orders, characterized by a single product category and large quantity, often result in significant cost savings under the cloud warehousing model. However, because cloud warehousing is a third-party warehousing service, its capacity resources are relatively limited compared to the traditional self-built warehousing model, and its support for more complex business operations is limited.

[0046] Self-built warehousing boasts the highest capacity, capable of meeting any complex business model and fulfilling the warehousing and distribution needs of various types of goods. However, it is more expensive. Cloud warehousing offers lower warehousing and distribution costs, but it requires certain business constraints to operate normally and is not suitable for all products. Therefore, for large e-commerce websites, combining both warehousing models is the most cost-effective approach.

[0047] The cloud warehouse scenario has the following business characteristics: the number of SKUs that a cloud warehouse can store cannot be too large, and needs to be controlled within several hundred; otherwise, the cost of the cloud warehouse will increase significantly or even make it impossible to operate normally. When the number of SKUs in the cloud warehouse exceeds the standard, the excess SKUs will be cleared out of the cloud warehouse through means such as transfer, but this will bring additional costs. When the cloud warehouse is operating normally, the fulfillment cost per order is much lower than the fulfillment cost of other warehouses. Newly selected SKUs must first be transferred from other warehouses to the cloud warehouse. SKUs taken over by the cloud warehouse will be continuously replenished to ensure their inventory in the cloud warehouse, and will be shipped from the cloud warehouse as much as possible. SKUs that are no longer selected for the cloud warehouse will not be replenished with inventory, but there will inevitably be surplus inventory in the cloud warehouse. Small quantities can be consumed by daily sales shipments, while large quantities can only be cleared out of the cloud warehouse through transfer. Therefore, selecting which target SKUs from tens of thousands of SKUs to be handled by the cloud warehouse becomes a highly practical issue. The goal is to ensure the normal operation of the cloud warehouse, control the number of SKU types, reduce transfers, and simultaneously ship as many packages as possible from the waybill to lower overall fulfillment costs. At the same time, the product selection list must be dynamically updated to ensure the accuracy and usability of the results.

[0048] To address the above issues, the present invention proposes an automated cloud warehouse product selection method that, while considering business constraints, maximizes cloud warehouse shipments and reduces fulfillment costs. Furthermore, the algorithm's parameters are adjustable, enabling automated product selection under controllable conditions and significantly saving related manpower.

[0049] After introducing the basic principles of this disclosure, various non-limiting embodiments of this disclosure will be described in detail below.

[0050] Application Scenarios Overview

[0051] First refer to Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario provided for an embodiment of this disclosure.

[0052] like Figure 1 As shown, an initial product selection pool 110 is constructed. Low-stock SKUs are obtained from the current cloud warehouse 120 and a low-stock transfer pool 130 is constructed. Based on the SKUs in the current cloud warehouse 120 and the low-stock transfer pool 130, products are selected from the initial product selection pool 110, resulting in a final product selection pool 140. The SKUs in the final product selection pool 140 are the final selection results for entering the cloud warehouse.

[0053] Exemplary methods

[0054] The following is combined Figure 1 Application scenarios, refer to Figure 2 This document describes a method for product selection in a cloud warehouse according to exemplary embodiments of the present disclosure. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in any way. Rather, the embodiments of the present disclosure can be applied to any applicable scenario.

[0055] Step S201: Filter initial SKUs based on the predicted sales volume of SKUs to build an initial product selection pool.

[0056] Specifically, the predicted sales volume for each SKU includes: predicted sales quantity and predicted sales order quantity. Based on a prediction model for sales quantity or sales order quantity, the system can predict the future sales quantity and sales order quantity for each SKU, providing the sales quantity or sales order quantity for the next L days for all SKUs that meet the cloud warehouse product selection rules. From this, a preset number of SKUs with larger predicted sales quantities or sales order quantities are selected. This ensures that while controlling the number of selected products, the cloud warehouse product selection maximizes the SKU shipment volume, thereby minimizing fulfillment costs.

[0057] The initial SKU quantity can be preset based on the actual storage conditions of the cloud warehouse. For example, if the initial SKU quantity is set to N... target Then, after the above filtering, select N with the largest predicted sales volume. target One SKU is used as the initial SKU, and the initial SKU constitutes the initial product pool. N target An optional soft upper limit for the target SKU types is available. The initial product pool includes initial SKUs and the projected sales volume for each initial SKU.

[0058] Step S202: Obtain the inventory turnover days of the SKUs currently in the cloud warehouse, and filter the SKUs with low inventory turnover to build a low inventory turnover pool.

[0059] Specifically, if a certain SKU already has a high inventory in the cloud warehouse, it's difficult for such an SKU to be naturally depleted through sales and shipments; additional costs must be incurred for relocation. Conversely, SKUs with low inventory turnover can be quickly and naturally depleted without incurring additional relocation costs, resulting in minimal impact on the cloud warehouse. Therefore, low-inventory-turnover products do not occupy the soft limit quota for new SKU types, freeing up replacement space for new SKUs. High-inventory-turnover products, on the other hand, occupy the soft limit quota for new SKU types, thus constraining the number of SKUs available regardless of whether they are selected in the next round of product selection.

[0060] The inventory turnover days for SKUs currently in stock in the cloud warehouse are calculated based on the current inventory levels of these SKUs. This is done by forecasting future inventory levels and converting the inventory levels into corresponding inventory turnover days. All SKUs in stock are iterated through, and those meeting the inventory turnover day criteria are selected as low-turnover SKUs. These low-turnover SKUs form the low-turnover pool. The low-turnover pool includes the low-turnover SKUs and their projected sales volumes.

[0061] Step S203: Determine the threshold for allowing new SKU types based on the current cloud warehouse SKU types, the soft upper limit of the target SKU types, the hard upper limit of the target SKU types, and the low-stock transfer SKU types in the low-stock transfer pool.

[0062] In step S201 above, an initial product selection pool is obtained by predicting sales volume. However, since prediction models inevitably have errors, the prediction results will change at different times. If the prediction results are relied upon directly, the product selection pool will be different with each update. Relying entirely on the prediction results will lead to an unstable product selection structure and easily cause product accumulation. Therefore, this embodiment introduces some parameters to ensure the stability of product selection while predicting sales volume.

[0063] Regardless of how many new SKUs are added, the number cannot exceed the target SKU limit in the cloud warehouse. Therefore, it is necessary to consider the current SKU inventory in the cloud warehouse. Based on the current SKU types in the cloud warehouse and the target SKU limit, the new SKU limit can be determined. The hard limit is the absolute maximum value that must not be exceeded to maintain the normal operation of the cloud warehouse.

[0064] Secondly, since low-stock SKUs can be depleted relatively quickly, they can be considered as SKUs to be replaced. Simultaneously, the number of replaced SKUs should approach the soft upper limit of the target SKU category. Therefore, based on the current SKU categories in the cloud warehouse, the types of low-stock SKUs in the low-stock pool, and the soft upper limit of the target SKU category, the soft upper limit for new SKUs can be obtained. The soft upper limit is set as a desired quantity, allowing for controllable changes in the selection pool, ensuring that the number of SKUs in the cloud warehouse can exceed the soft upper limit but not excessively, maintaining a fluctuating upper limit value near the soft upper limit.

[0065] Since the hard limit for new SKUs obtained above cannot be exceeded, the final threshold for allowed new SKU types is based on the minimum of the hard and soft limits for new SKUs. This ensures that the number of new products added that do not overlap with the current inventory in the cloud warehouse is controllable and will not exceed the allowed threshold for new SKU types. These parameters are adjustable, making the product selection results in the cloud warehouse controllable and preventing product accumulation within the cloud warehouse.

[0066] Step S204: Based on the threshold for allowing new SKU types and the predicted sales of the initial SKU, obtain the target SKU from the initial selection pool and add it to the final selection pool.

[0067] If the newly added SKU does not significantly increase the sales volume or quantity forecast compared to the SKUs currently in the cloud warehouse, the benefits of adding such SKUs to the final product selection pool are uncertain, considering the fluctuations caused by the forecast's inherent error.

[0068] Therefore, for valuable new SKU slots, only SKUs that can generate higher order volume revenue should occupy these slots. Using a threshold for the allowed number of new SKU types as an upper limit, the initial selection pool is iterated through sequentially for product selection. It's crucial to ensure that the number of target SKUs added to the final selection pool does not exceed the allowed threshold for new SKU types, guaranteeing the normal and efficient operation of the cloud warehouse. Simultaneously, it's necessary to determine whether the predicted sales of the initial SKU reach the increase threshold. If the predicted sales increase for the selected initial SKU is not significant, considering the fluctuations caused by the error in the prediction model itself, adding the initial SKU to the final selection pool would result in uncertain revenue, potentially increasing the fulfillment costs of the cloud warehouse.

[0069] Optionally, in this embodiment, the low-inventory-transfer products in the low-inventory-transfer pool are traversed to find a low-inventory-transfer SKU with the highest possible predicted value as a benchmark. The predicted sales of the selected initial SKU are calculated relative to the low-inventory-transfer SKUs in the low-inventory-transfer pool, and the initial SKU with an improvement value greater than the improvement threshold is added to the final selection pool as the target SKU.

[0070] The final selection pool of SKUs represents the final result of the cloud warehouse product selection process. When generating the final selection pool, the selected SKUs all come from the initial selection pool, i.e., the top N SKUs in predicted sales. Theoretically, all SKUs in this pool should be eligible for cloud warehouse selection; therefore, no SKU with unrealistic predicted sales will be included. Furthermore, the predicted sales limit for low-inventory-converted SKUs restricts the number of new SKUs, ensuring that the number of new SKUs is not excessive. Simultaneously, low-inventory-converted SKUs occupy the new SKU count during selection, thus guaranteeing that high-inventory-converted SKUs in the cloud warehouse will not be squeezed out by new SKUs. However, not being squeezed out does not guarantee selection; their predicted sales must also be considered. This method, which does not rely on manual intervention, makes cloud warehouse product selection more efficient and transforms the subjective judgment process into more standardized algorithm parameter control, avoiding uncontrollable selection results. When business problems arise, specific pain points can be directly identified, effectively solving business problems in cloud warehouse operation, maximizing the shipment volume of SKUs in the final selection pool, and optimizing fulfillment costs.

[0071] The cloud warehouse product selection method provided in this embodiment filters a preset number of initial SKUs based on the predicted sales volume of each SKU, constructing an initial product selection pool. Then, it obtains the inventory turnover days of the SKUs currently in stock in the cloud warehouse and filters low-inventory-turnover SKUs to construct a low-inventory-turnover pool. Based on the current cloud warehouse SKU types, the soft upper limit and hard upper limit of the target SKU types, and the low-inventory-turnover SKU types in the low-inventory-turnover pool, a threshold for allowing the addition of new SKU types is determined. Based on the threshold for allowing the addition of new SKU types and the predicted sales volume of the initial SKUs, target SKUs are obtained from the initial product selection pool and added to the final product selection pool. This method can ensure the accuracy of product selection results under controllable conditions without manual intervention, thus significantly reducing the labor costs associated with product selection and avoiding product accumulation in the cloud warehouse due to selection errors. This makes cloud warehouse product selection more efficient and greatly reduces the fulfillment costs of the cloud warehouse.

[0072] Please see Figure 3 In one example, step S201, which involves filtering a preset number of initial SKUs based on their predicted sales volume to construct an initial product selection pool, includes:

[0073] Step S301: Obtain SKUs that meet the preset cloud warehouse product selection rules;

[0074] Specifically, preset cloud warehouse product selection rules refer to the limitations imposed by the cloud warehouse's own storage conditions. Due to numerous business constraints inherent in cloud warehouses, such as size restrictions on SKUs and limitations on SKUs requiring low-temperature storage, SKUs that do not meet the preset cloud warehouse product selection rules are excluded. These preset cloud warehouse product selection rules can be set based on the cloud warehouse's specific storage conditions in real-world application scenarios.

[0075] Step S302: Based on the predicted sales volume of the SKU, obtain a preset number of initial SKUs, wherein the preset number is the soft upper limit of the target SKU category;

[0076] The predicted sales volume of the SKUs obtained in step S301 is considered. Based on the predicted sales volume of each SKU, the initial SKU with the larger predicted sales volume is selected. The number of the initial SKUs obtained is a preset quantity, which can be pre-set. In this embodiment, the preset quantity is set to the target SKU soft upper limit, and the target SKU soft upper limit is set to N. target Then select the top N with the highest predicted sales. target Each initial SKU and the initial selection pool should be eligible to be included in the cloud warehouse.

[0077] Step S303: Sort the initial SKUs from largest to smallest according to the predicted sales volume to construct the initial product selection pool.

[0078] In the initial product selection pool, initial SKUs are sorted according to their predicted sales volume. This ensures that initial SKUs with higher predicted sales volume are added to the final product selection pool in order of priority. Selecting products with higher predicted sales volume ensures that product selection in the cloud warehouse maximizes shipment volume and minimizes fulfillment costs.

[0079] Please see Figure 4 In one example, step S202, obtaining the inventory turnover days of SKUs currently in the cloud warehouse and filtering low-inventory-turnover SKUs to construct a low-inventory-turnover pool, includes:

[0080] Step S401: Obtain the current SKU inventory in the cloud warehouse;

[0081] Specifically, based on the current inventory cross-section data of the cloud warehouse excluding packaging materials, the current SKU inventory quantity of the cloud warehouse refers to the product inventory quantity of each SKU in the current cloud warehouse and the number of SKU types of products in the warehouse.

[0082] Step S402: Based on the current SKU inventory in the cloud warehouse, obtain the inventory turnover days for each SKU in stock;

[0083] This involves forecasting future inventory levels for each SKU in stock and converting the inventory into corresponding inventory turnover days (TD).

[0084] Step S403: Based on the inventory turnover days of each SKU in stock, mark the SKUs in stock with inventory turnover days less than the inventory turnover days threshold as low inventory turnover SKUs;

[0085] The inventory turnover days threshold can be set according to actual application. For example, if the inventory turnover days threshold is set to TD... limitIterate through all SKUs in the database. If the SKU is in the database... i Corresponding inventory turnover days TD i Less than TD limit Then it will be in the SKU inventory. i Marked as a low-stock SKU.

[0086] Step S404: Arrange the low-inventory-transfer SKUs in descending order of predicted sales volume to construct the low-inventory-transfer pool.

[0087] Specifically, the number of SKUs transferred from low-inventory inventory (LI) is counted, and these SKUs are sorted according to predicted sales volume to construct a low-inventory transfer pool (C). tail .

[0088] Please see Figure 5 In one example, step S203, which involves determining the threshold for allowing new SKU types based on the current cloud warehouse SKU types, the target SKU type soft upper limit, the target SKU type hard upper limit, and the low-stock transfer SKU types in the low-stock transfer pool, includes:

[0089] Step S501: Determine the hard limit for allowing new SKU types based on the target SKU type hard limit and the current number of SKU types in the cloud warehouse.

[0090] The number of new SKUs allowed in the cloud warehouse cannot exceed the hard limit for the target SKU category, which is set to N. max The current number of SKUs in the cloud warehouse is IS, with a hard limit of S allowed for adding new SKUs. max The expression is:

[0091] Formula 1

[0092] The above formula 1 takes N max -IS is the largest value between the difference and 0.

[0093] Step S502: Determine the soft upper limit for allowing new SKU types based on the target SKU type soft upper limit, the cloud warehouse SKU types in stock, and the low-stock SKU types transferred.

[0094] Specifically, since low-stock SKUs can be consumed relatively quickly and no longer occupy cloud warehouse storage slots, they are considered as SKUs to be replaced. At the same time, the number of new SKUs is kept close to the target SKU category soft cap, which is set to N. target Low-stock SKUs are converted to LI, with a soft limit of S allowed for the addition of new SKU types. target The expression is:

[0095] Formula 2

[0096] The above formula 2 takes N target - (IS-LI) is the maximum value between 0 and 0.

[0097] Step S503: Take the minimum value between the hard upper limit for allowing new SKU types and the soft upper limit for allowing new SKU types to be added, and determine the threshold for allowing new SKU types to be added.

[0098] Specifically, the hard limit S allowed for adding new SKU types max With the soft limit S allowed for adding new SKU types target The expression that takes the minimum value between these two values ​​equals the threshold S for allowing the addition of new SKU types is:

[0099] Formula 3

[0100] The threshold for allowing new SKU types in Formula 3 above cannot be exceeded, thereby limiting the number of SKU types added to the final selection pool.

[0101] Please see Figure 6 In one example, step S204, which involves obtaining target SKUs from the initial selection pool and adding them to the final selection pool based on the threshold for allowing new SKU types and the initial SKU predicted sales, includes:

[0102] Step S601: Determine the list of new SKUs in the initial selection pool relative to the SKUs in the cloud warehouse;

[0103] Specifically, first, determine the types of SKUs in the initial selection pool relative to the current SKUs in the cloud warehouse, and then identify the types of new SKUs to be added, forming a new SKU list. For example, if the current cloud warehouse contains SKUs A, B, C, and D, and the initial selection pool contains SKUs A, C, E, F, and H, then the new SKU list will include E, F, and H.

[0104] Step S602: Iterate through the initial SKUs in the initial selection pool and determine whether the current initial SKU exists in the new SKU list or the low inventory transfer pool.

[0105] Specifically, in the product selection process, the initial SKUs in the initial selection pool are sorted from highest to lowest predicted sales volume. Therefore, starting with the initial SKU with the highest predicted sales volume, each SKU is evaluated one by one to determine whether it should be included in the final selection pool. If the current initial SKU is denoted as SKU... i Determine SKU i It belongs to the newly added SKU list, the SKU low inventory transfer pool, or neither the newly added SKU list nor the SKU low inventory transfer pool.

[0106] Furthermore, when product selection begins, n=0 is defined to record the number of new SKU types added during the selection process. The maximum value of n is the threshold for allowing the addition of new SKU types.

[0107] Step S603: If the current initial SKU does not exist in the new SKU list or the low inventory transfer pool, then add the current initial SKU to the final selection pool.

[0108] Among them, if SKU i SKUs that are not on the list of new SKUs and are not in the low-inventory transfer pool, for example, this SKU. i The product category belongs to the high-volume transfer SKUs in the cloud warehouse. Therefore, this SKU... i It will not occupy the quota for new SKUs, so it will be directly added to the final selection pool, and n will not change.

[0109] Step S604: If the current initial SKU exists in the new SKU list or the low-stock transfer pool, then determine whether the current new SKU type exceeds the threshold of allowed new SKU types, wherein the current new SKU type is the target SKU type to be added to the final selection pool;

[0110] Specifically, if SKU i If it belongs to the newly added SKU list or the SKU low-stock transfer pool, since the above calculation of the allowed new SKU types S includes the number of low-stock transfer SKU types, therefore even if SKU i Even if a product is transferred from a low-stock pool, it will still occupy a new quota and may increase the current number of new SKUs, meaning the value of n may increase. In this case, it's necessary to determine whether the current number of new SKU types, n, exceeds the threshold for allowed new SKU types.

[0111] Step S605: If the number of newly added SKU types is greater than the threshold for allowed new SKU types, then the current initial SKU will not be added to the final selection pool.

[0112] If n > S, then it means that the number of new SKUs has exceeded the threshold for the allowed number of new SKU types. i Not selected.

[0113] Step S606: If the number of newly added SKU types is less than or equal to the threshold for allowing new SKU types, then determine whether the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low-inventory SKUs in the low-inventory transfer pool is greater than the sales increase threshold.

[0114] If n ≦ S, it means that the number of newly added SKUs has not exceeded the threshold for the number of new SKU types allowed. In this case, it is still necessary to determine the SKU. iTo determine whether the predicted sales increase rate reaches the sales increase threshold, it is necessary to iterate through and find a low-inventory SKU with the highest possible predicted value as a benchmark.

[0115] Step S607: If the increase ratio of the predicted sales of the current initial SKU to the predicted sales of the low-inventory SKUs in the low-inventory transfer pool is greater than the sales increase threshold, then the current initial SKU is added to the final selection pool as a target SKU.

[0116] Specifically, the sales increase threshold is set at SG. limit Starting from index k, iterate through the low-level SKUs in the low-level SKU transfer pool and set the current initial SKU. i The projected sales volume is F i Forecast sales volume F of low-inventory SKUs k If F i >F k ×SG limit SKU i The predicted sales volume should be the highest among the SKUs with the lowest predicted sales volume among the low-inventory-turnover SKUs. k The increase rate is greater than the sales increase threshold. Then, n = n + 1, and the SKU... i Added to the final selection pool.

[0117] Step S608: If the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low-inventory SKUs in the low-inventory transfer pool is less than or equal to the sales increase threshold, then the current initial SKU will not be added to the final selection pool.

[0118] Where, if F i ≦ F k ×SG limit Then iterate through the loop to the next SKU. k+1 And so on, if SKU i The percentage increase in predicted sales relative to the predicted sales of low-inventory-to-SKUs in the low-inventory-to-stock pool is less than or equal to the sales increase threshold SG. limit Then it is impossible to use this SKU i The products included in the final selection pool did not meet the projected sales targets.

[0119] See Figure 7 In one example, step S606, the process of determining whether the increase ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low-inventory-to-SKUs in the low-inventory-to-stock pool is greater than the sales increase threshold, includes:

[0120] Step S701: Label each low-level SKU in descending order to obtain the label of each low-level SKU.

[0121] Specifically, k=0 is defined to record the label of the low-stock-to-SKU in the low-stock-to-SKU pool. The label starts from 0 and is assigned to the low-stock-to-SKU in the low-stock-to-SKU pool in descending order of number as 0, 1, 2, ...

[0122] Step S702: Determine the calculation starting point of the current initial SKU, wherein the calculation starting point is the low-stock SKU with the next label corresponding to the low-stock SKU at the end of the previous initial SKU judgment process;

[0123] Specifically, if the previous initial SKU and the low-inventory-transfer product SKU K-1 If the benchmarking shows that the predicted sales increase rate is greater than the sales increase threshold, then the low-stock SKU labeled k needs to be converted to a new SKU. k This serves as the starting point for benchmarking calculations.

[0124] Step S703: Starting from the calculation start point, continue to calculate the ratio of the predicted sales of the current initial SKU to the predicted sales of each low-inventory SKU to obtain the improvement ratio;

[0125] In this process, the initial products are sorted in the initial product pool according to their predicted sales volume from highest to lowest, with the initial products having the highest predicted sales volume being evaluated first. For example, if the initial product pool contains SKU1, SKU2, SKU3, and so on, and SKU1 is transferred from the lower inventory level... k=0 Start by comparing sequentially. If F1 for SKU1 is less than or equal to SKU1... k=0 ×SG limit Then continue iterating to the next low-level SKU, and combine SKU1 with SKU2. k=1 Compare, if F1≦SKU k=1 ×SG limit Then continue with SKU1 and SKU k=2 Compare, if F1 > SKU k=2 ×SG limit If the condition is met, the evaluation of SKU1 ends, and SKU1 is added to the final selection pool as the target SKU. When evaluating the next SKU2, the selection process will then proceed from SKU... k=3 Begin the comparison.

[0126] Step S704: Compare the increase ratio with the sales increase threshold, and end the judgment process when the target SKU is obtained or all low-inventory SKUs have been traversed.

[0127] Specifically, if SKU i After comparing with all low-inventory SKUs, if the increase rate does not exceed the sales increase threshold, then this SKU... i This SKU cannot be selected as a target SKU in the final selection pool. iOther initial SKUs do not require further evaluation and will not be included in the final selection pool. If SKU i If, after comparison with all low-inventory SKUs, the increase rate exceeds the sales increase threshold, then the product is added to the final selection pool. i The next item will be judged starting from step S602 until the judgment is completed.

[0128] In one example, the SKUs in the final selection pool are arranged from largest to smallest according to predicted sales volume.

[0129] In the product selection process described above, which involves obtaining SKUs for the final selection pool, the SKUs in the initial selection pool and the low-inventory transfer pool are arranged from largest to smallest based on predicted sales volume. During the screening process, they are traversed and compared sequentially. Therefore, the SKUs in the final selection pool are also arranged from largest to smallest based on predicted sales volume, which further ensures the normal operation of the cloud warehouse and that the product selection results are controllable and stable, maximizing the cloud warehouse's shipment volume and optimizing fulfillment costs.

[0130] Exemplary media

[0131] After introducing the methods of exemplary embodiments of this disclosure, the following references are made. Figure 7 The storage medium of the exemplary embodiments of this disclosure will be described.

[0132] refer to Figure 8 As shown, in some possible implementations, various aspects of this disclosure can also be implemented as a storage medium 80 storing program code that, when executed by the processor of a device, implements the steps of the cloud warehouse product selection method according to various exemplary embodiments of this application as described in the "Exemplary Methods" section above.

[0133] Specifically, when the processor of the device executes the program code, it performs the following steps: Step S201, filtering initial SKUs based on the predicted sales of SKUs to construct an initial selection pool; Step S202, obtaining the inventory turnover days of SKUs currently in the cloud warehouse, filtering low-inventory-turnover SKUs to construct a low-inventory-turnover pool; Step S203, determining the threshold for allowing new SKU types based on the current cloud warehouse SKU types, the soft upper limit of the target SKU types, the hard upper limit of the target SKU types, and the low-inventory-turnover SKU types in the low-inventory-turnover pool; Step S204, obtaining target SKUs from the initial selection pool and adding them to the final selection pool based on the threshold for allowing new SKU types and the predicted sales of the initial SKUs.

[0134] It should be noted that the aforementioned medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0135] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0136] The program code contained on the readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, RF, or any suitable combination thereof. The program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0137] Exemplary device

[0138] Having introduced the medium of exemplary embodiments of this disclosure, the following references are made to... Figure 9 The cloud warehouse product selection device according to the exemplary embodiments of this disclosure is described to implement the method in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0139] The product selection pool construction module 901 is used to filter initial SKUs based on the predicted sales volume of SKUs and construct the initial product selection pool;

[0140] The low-inventory transfer pool construction module 902 is used to obtain the number of days of inventory transfer for SKUs currently in the cloud warehouse, filter low-inventory transfer SKUs, and construct a low-inventory transfer pool.

[0141] A new threshold determination module 903 has been added to determine the threshold for allowing the addition of new SKU types based on the current cloud warehouse SKU types, the soft upper limit of the target SKU types, the hard upper limit of the target SKU types, and the low-stock transfer SKU types in the low-stock transfer pool.

[0142] The product selection module 904 is used to obtain target SKUs from the initial product selection pool and add them to the final product selection pool based on the threshold for allowing new SKU types and the predicted sales of the initial SKUs.

[0143] In one example, the cloud warehouse product selection device 900 of this embodiment includes a product selection pool construction module 801, which is used to filter initial SKUs based on the predicted sales volume of SKUs and construct an initial product selection pool. It obtains some SKUs that meet the cloud warehouse product selection rules, and selects a certain number of SKUs with higher predicted sales volume as initial SKUs to construct the initial product selection pool for cloud warehouse product selection.

[0144] In one example, the low-inventory transfer pool construction module 802 is used to obtain the inventory turnover days of the SKUs currently in stock in the cloud warehouse, and filter the SKUs for low-inventory transfer to build the low-inventory transfer pool. It calculates the inventory turnover days required for the goods currently in stock in the cloud warehouse, filters out the low-inventory transfer SKUs that meet the conditions, and forms a low-inventory transfer pool. Because the goods in the low-inventory transfer pool are consumed quickly, they will not occupy the quota for subsequent new SKUs.

[0145] In one example, a new threshold determination module 803 is added to determine the threshold for allowing new SKU types based on the current cloud warehouse SKU types, the soft upper limit of the target SKU type, the hard upper limit of the target SKU type, and the low-inventory transfer SKU types in the low-inventory transfer pool. Since products in the low-inventory transfer pool are consumed quickly, they will not occupy the quota for subsequent allowable SKU type additions. The threshold for allowing new SKU types is determined based on the current cloud warehouse SKU types, the soft upper limit of the target SKU type, the hard upper limit of the target SKU type, and the low-inventory transfer SKU types in the low-inventory transfer pool to ensure that the added target SKUs do not exceed this limit.

[0146] In one example, the product selection module 804 is used to obtain target SKUs from the initial product selection pool and add them to the final product selection pool based on the threshold for allowing new SKU types and the predicted sales of the initial SKUs. Within the threshold for allowing new SKU types, the predicted sales of the SKUs in the initial product selection pool need to be considered to ensure that the selected target SKUs bring the minimum fulfillment cost to the cloud warehouse.

[0147] The cloud warehouse product selection device provided in this embodiment can ensure the accuracy of product selection results under controllable conditions without manual intervention, thereby significantly reducing the labor costs related to product selection and avoiding product accumulation in the cloud warehouse due to selection errors, making cloud warehouse product selection more efficient.

[0148] Exemplary computer device

[0149] Having introduced the methods, media, and apparatus of exemplary embodiments of the present disclosure, the electronic devices of exemplary embodiments of the present disclosure will now be described with reference to the figures.

[0150] Figure 10 The electronic device 100 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0151] like Figure 10 As shown, the electronic device 100 is manifested in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: at least one processing unit 1010, at least one storage unit 1020, and a bus 1030 connecting different system components (including storage unit 1020 and processing unit 1010).

[0152] The storage unit stores program code that can be executed by the processing unit 1010, causing the processing unit 1010 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0153] Storage unit 1020 may include readable media in the form of volatile storage units, such as random access memory (RAM) 10201 and / or cache memory 10202, and may further include read-only memory (ROM) 10203.

[0154] Storage unit 1020 may also include a program / utility 10204 having a set (at least one) program module 10205, such program module 10205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0155] Bus 1030 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the multiple bus structures.

[0156] Electronic device 100 can also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 100, and / or with any device that enables the electronic device 100 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 100 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1060. Figure 9 As shown, network adapter 1060 communicates with other modules of electronic device 100 via bus 1030. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with electronic device 100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0157] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0158] It should be noted that although several units / modules or sub-units / modules of the cloud warehouse product selection device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0159] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0160] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A cloud warehouse selection method, characterized in that, The application comprises the following steps: Screening initial SKUs according to predicted sales of SKUs to build an initial product selection pool; Obtaining the days of SKU turnover in the current cloud warehouse, screening low SKU turnover to build a low SKU turnover pool, wherein the low SKU turnover is the SKU in the current cloud warehouse with the days of SKU turnover less than a threshold of days of SKU turnover; Determining a threshold of allowed new SKU categories according to the categories of SKUs in the current cloud warehouse, a soft upper limit of target SKU categories, a hard upper limit of target SKU categories and the categories of low SKU turnover in the low SKU turnover pool; Obtaining target SKUs from the initial product selection pool according to the threshold of allowed new SKU categories and predicted sales of initial SKUs to add the target SKUs to a final product selection pool; The step of obtaining target SKUs from the initial product selection pool according to the threshold of allowed new SKU categories and predicted sales of initial SKUs to add the target SKUs to a final product selection pool comprises the following steps: Determining a list of new SKUs in the initial product selection pool relative to the SKUs in the current cloud warehouse; Traversing the initial SKUs in the initial product selection pool in sequence to determine whether a current initial SKU exists in the list of new SKUs or the low SKU turnover pool; If the current initial SKU does not exist in the list of new SKUs or the low SKU turnover pool, adding the current initial SKU to the final product selection pool; If the current initial SKU exists in the list of new SKUs or the low SKU turnover pool, determining whether a current number of new SKU categories exceeds the threshold of allowed new SKU categories, wherein the current number of new SKU categories is the number of target SKUs added to the final product selection pool; If the current number of new SKU categories is greater than the threshold of allowed new SKU categories, the current initial SKU is not added to the final product selection pool; If the current number of new SKU categories is less than or equal to the threshold of allowed new SKU categories, determining whether a promotion ratio of predicted sales of the current initial SKU relative to predicted sales of low SKU turnover in the low SKU turnover pool is greater than a threshold of sales promotion; If the promotion ratio of predicted sales of the current initial SKU relative to predicted sales of low SKU turnover in the low SKU turnover pool is greater than the threshold of sales promotion, adding the current initial SKU as a target SKU to the final product selection pool; If the promotion ratio of predicted sales of the current initial SKU relative to predicted sales of low SKU turnover in the low SKU turnover pool is less than or equal to the threshold of sales promotion, the current initial SKU is not added to the final product selection pool.

2. The cloud warehouse assortment selection method of claim 1, wherein, The step of screening initial SKUs according to predicted sales of SKUs to build an initial product selection pool comprises the following steps: Obtaining SKUs satisfying preset cloud warehouse product selection rules; Obtaining a preset number of initial SKUs according to predicted sales of the SKUs, wherein the preset number is equal to a soft upper limit of target SKU categories; Sorting the initial SKUs according to predicted sales from large to small to build the initial product selection pool.

3. The cloud warehouse assortment selection method of claim 1, wherein, The step of obtaining the days of SKU turnover in the current cloud warehouse, screening low SKU turnover to build a low SKU turnover pool comprises the following steps: Obtaining SKU inventory of the current cloud warehouse; Obtaining the days of SKU turnover of each SKU in the current cloud warehouse according to the SKU inventory of the current cloud warehouse; According to the days of warehouse turnover of each in-warehouse SKU, mark the in-warehouse SKU with the days of warehouse turnover less than the threshold of days of warehouse turnover as a low-warehouse-turnover SKU; Arrange the low-warehouse-turnover SKU according to the predicted sales from large to small to construct the low-warehouse-turnover pool.

4. The cloud warehouse assortment selection method of claim 1, wherein, The determining of the threshold of allowed new SKU types according to the current SKU types in the cloud warehouse, the soft upper limit of target SKU types, the hard upper limit of target SKU types, and the low-warehouse-turnover SKU types in the low-warehouse-turnover pool comprises: Determining the hard upper limit of allowed new SKU types according to the hard upper limit of target SKU types and the number of in-warehouse SKU types in the current cloud warehouse; Determining the soft upper limit of allowed new SKU types according to the soft upper limit of target SKU types, the in-warehouse SKU types in the cloud warehouse, and the low-warehouse-turnover SKU types; Taking the minimum value between the hard upper limit of allowed new SKU types and the soft upper limit of allowed new SKU types to determine the threshold of allowed new SKU types.

5. The cloud warehouse assortment selection method of claim 1, wherein, The process of judging whether the promotion ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low-warehouse-turnover SKU in the low-warehouse-turnover pool is greater than the threshold of sales promotion comprises: Labeling each low-warehouse-turnover SKU in order from large to small to obtain the label of each low-warehouse-turnover SKU; Determining the calculation starting point of the current initial SKU, wherein the calculation starting point is the low-warehouse-turnover SKU corresponding to the next label of the low-warehouse-turnover SKU at the end of the last initial SKU judgment process; Starting from the calculation starting point, successively calculating the ratio of the predicted sales of the current initial SKU to the predicted sales of each low-warehouse-turnover SKU to obtain the promotion ratio; Comparing the promotion ratio with the threshold of sales promotion, and ending the judgment process when the target SKU is obtained or all low-warehouse-turnover SKUs are traversed.

6. The cloud warehouse assortment selection method of claim 1, wherein, The SKUs in the final product selection pool are arranged according to the predicted sales from large to small.

7. A cloud warehouse product selection device, characterized in that, Comprise: A product selection pool construction module for screening initial SKUs according to the predicted sales of the SKUs to construct an initial product selection pool; A low-warehouse-turnover pool construction module for obtaining the days of warehouse turnover of in-warehouse SKUs in the current cloud warehouse, screening low-warehouse-turnover SKUs to construct a low-warehouse-turnover pool, wherein the low-warehouse-turnover SKU is an in-warehouse SKU with the days of warehouse turnover less than the threshold of days of warehouse turnover; A new threshold determination module for determining the threshold of allowed new SKU types according to the current SKU types in the cloud warehouse, the soft upper limit of target SKU types, the hard upper limit of target SKU types, and the low-warehouse-turnover SKU types in the low-warehouse-turnover pool; A product selection module for obtaining target SKUs from the initial product selection pool to add to the final product selection pool according to the threshold of allowed new SKU types and the predicted sales of initial SKUs; The product selection module is also used to determine the list of new SKUs of the initial product selection pool relative to the in-warehouse SKUs in the cloud warehouse; Sequentially traversing the initial SKUs in the initial product selection pool to judge whether the current initial SKU exists in the list of new SKUs or the low-warehouse-turnover pool; If the current initial SKU does not exist in the list of new SKUs or the low-warehouse-turnover pool, the current initial SKU is added to the final product selection pool. If the current initial SKU exists in the new SKU list or the low warehouse transfer pool, it is determined whether the current new SKU category exceeds the allowed new SKU category threshold, wherein the current new SKU category is a target SKU category added to the final product selection pool; If the current new SKU category is greater than the allowed new SKU category threshold, the current initial SKU is not added to the final product selection pool; If the current new SKU category is less than or equal to the allowed new SKU category threshold, it is determined whether the improvement ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low warehouse transfer SKU in the low warehouse transfer pool is greater than a sales improvement threshold; If the improvement ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low warehouse transfer SKU in the low warehouse transfer pool is greater than the sales improvement threshold, the current initial SKU is added to the final product selection pool as a target SKU; If the improvement ratio of the predicted sales of the current initial SKU relative to the predicted sales of the low warehouse transfer SKU in the low warehouse transfer pool is less than or equal to the sales improvement threshold, the current initial SKU is not added to the final product selection pool.

8. An electronic device, comprising: Comprise: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the cloud warehouse product selection method of any one of claims 1-6 by executing the executable instructions.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the cloud warehouse product selection method of any one of claims 1-6.

Images