VMI dynamic inventory optimization method, device and system and storage medium

Abstract

The invention provides a VMI dynamic inventory optimization method, device and system and a storage medium. The method comprises the steps of obtaining historical behavior data of a plurality of retailers; determining the customer acceptance of each retailer according to the historical behavior data, wherein the customer acceptance is used for indicating the tolerance degree of each retailer to delayed delivery; determining an elastic service time of each retailer based on the customer acceptance of each retailer; and determining an inventory distribution strategy of each retailer based on the customer acceptance and the elastic service time of each retailer by taking the maximization of the inventory turnover rate and the minimization of the customer stockout loss as targets. According to the method, the customer acceptance is calculated through the historical behavior data of the retailers to quantify the quality difference of different retailers, so that when the inventory is allocated to different retailers, the relatively high delivery demand of the retailers' CAS can be guaranteed preferentially, the inventory turnover rate is improved, and the absolute service satisfaction rate of high-quality customers is guaranteed.

Description

Technical Field

[0001] This application relates to the field of inventory management technology, and more specifically, to a VMI (Dynamic Inventory Management) method, apparatus, system, and storage medium for dynamic inventory optimization. Background Technology

[0002] Vendor Managed Inventory (VMI) is a supply chain collaboration strategy where suppliers manage and replenish inventory on behalf of customers (such as retailers). Customers share inventory visibility with suppliers through methods such as sharing point-of-sale (POS) data. Theoretically, this model aims to reduce the "bullwhip effect," lower overall supply chain inventory levels, and improve responsiveness to market demand.

[0003] However, the traditional VMI model has inherent flaws in practical applications. For example, replenishment decisions rely on historical data, and the forecasting methods are static and rigid, failing to effectively capture and quantify the differences in behavioral patterns among different customers. Secondly, suppliers bear all inventory capital costs, the risk of goods depreciation, and losses from unsold inventory, but lack control over the rate of inventory depletion and final sales. The customer's risks are entirely borne by the supplier, eroding their profit margins and hindering the implementation of the VMI model. Therefore, the existing VMI model limits its effectiveness, sacrificing supplier profitability and overall supply chain efficiency while providing high customer satisfaction. Summary of the Invention

[0004] In view of the fact that existing supplier-managed inventory methods, while providing high customer satisfaction, sacrifice supplier profitability and overall supply chain efficiency, this application aims to provide a VMI dynamic inventory optimization method, apparatus, system, and storage medium that can significantly improve inventory turnover while ensuring customer satisfaction.

[0005] Firstly, this application provides a VMI dynamic inventory optimization method, including:

[0006] Acquire historical behavioral data from multiple retailers, including at least each retailer's order data, return data, review data, repurchase data, and delivery time data;

[0007] The customer acceptance level for each retailer is determined based on the historical behavioral data, and the customer acceptance level is used to indicate each retailer's tolerance for delayed delivery;

[0008] The flexible service time for each retailer is determined based on the customer acceptance level of each retailer;

[0009] With the goal of maximizing inventory turnover and minimizing customer stockout losses, an inventory allocation strategy is determined for each retailer based on their customer acceptance and flexible service hours.

[0010] In one possible embodiment, determining customer acceptance for each retailer based on the historical behavioral data includes:

[0011] The return rate, fulfillment satisfaction rate, negative review rate, and repurchase rate of each retailer are determined based on their return data, review data, and repurchase data.

[0012] Determine the corresponding retailer's delivery delay tolerance based on each retailer's delivery time data;

[0013] The customer acceptance level of each retailer is determined based on its return rate, positive fulfillment rate, negative review rate, repurchase rate, and tolerance for delivery delays.

[0014] In one possible embodiment, determining the corresponding retailer's delivery delay tolerance based on each retailer's delivery time data includes:

[0015] The promised delivery time and delivery delay time for each retailer are determined based on the delivery time data for each retailer.

[0016] The corresponding retailer's delivery delay tolerance is determined based on the ratio of the delivery delay time to the promised delivery time.

[0017] In one possible embodiment, determining the flexible service time for each retailer based on the customer acceptance of each retailer includes:

[0018] Obtain an allocation correlation table between the customer acceptance rate and the flexible service time, wherein the flexible service time and the customer acceptance rate are positively correlated in the allocation correlation table;

[0019] The flexible service hours for each retailer are determined based on their customer acceptance and the allocation of the association table.

[0020] In one possible embodiment, the allocation association table requires at least:

[0021] When the retailer's customer acceptance rate is less than or equal to 0.3, the retailer's flexible service time is 0.

[0022] When the retailer's customer acceptance rate is greater than 0.3 and less than or equal to 0.7, the retailer's flexible service time is 2.

[0023] When the retailer's customer acceptance rate is greater than 0.7 and less than 0.9, the retailer's flexible service time is 5.

[0024] When the retailer’s customer acceptance rate is greater than or equal to 0.9, the retailer’s flexible service time is 7.

[0025] In one possible embodiment, the allocation association table also includes the inventory cost allocation ratio corresponding to different customer acceptance levels for retailers, and the inventory cost allocation ratio is negatively correlated with the customer acceptance level.

[0026] In one possible embodiment, the order data includes purchase quantity and inventory shortage losses;

[0027] The goal is to maximize inventory turnover and minimize customer stockout losses. Based on each retailer's customer acceptance and flexible service hours, an inventory allocation strategy is determined for each retailer, including:

[0028] Build an inventory turnover function based on each retailer's purchase volume, customer acceptance, and flexible service hours;

[0029] Construct a stockout loss function based on each retailer's stockout loss and customer acceptance.

[0030] Given the service satisfaction rate as a constraint, find the inventory allocation strategy for each retailer that maximizes inventory turnover and minimizes customer stockout losses.

[0031] Secondly, this application also provides a supplier dynamic inventory optimization device, comprising:

[0032] The historical behavior data acquisition module is used to acquire historical behavior data from multiple retailers. The historical behavior data includes at least each retailer's order data, return data, review data, repurchase data, and delivery time data.

[0033] A customer acceptance calculation module is used to determine the customer acceptance level of each retailer based on the historical behavior data, wherein the customer acceptance level is used to indicate the degree of tolerance of each retailer for delayed delivery;

[0034] The flexible service time calculation module is used to determine the flexible service time for each retailer based on the customer acceptance of each retailer.

[0035] The inventory allocation strategy solving module is used to determine the inventory allocation strategy for each retailer based on the customer acceptance and flexible service time of each retailer, with the goal of maximizing inventory turnover and minimizing customer stockout losses.

[0036] Thirdly, embodiments of this application also provide an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory to implement the method in any possible implementation of the first aspect described above.

[0039] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method in any possible implementation of the first aspect described above.

[0040] Fifthly, embodiments of this application also provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the method in any possible implementation of the first aspect described above.

[0041] This application provides a VMI (Vehicle Managed Inventory) dynamic inventory optimization method, apparatus, system, and storage medium. First, it acquires historical behavioral data from multiple retailers. Based on this historical behavioral data, it determines the customer acceptance level for each retailer, whereby the customer acceptance level indicates each retailer's tolerance for delayed delivery. Based on each retailer's customer acceptance level, it determines the flexible service time for each retailer. With the goal of maximizing inventory turnover and minimizing customer stockout losses, it determines an inventory allocation strategy for each retailer based on their customer acceptance level and flexible service time. This application calculates the customer acceptance level of different retailers by collecting their historical behavioral data, thereby differentiating retailers with different customer acceptance levels. In this way, when allocating inventory to different retailers, it can prioritize the delivery needs of retailers with higher customer acceptance scores, sacrificing the timeliness of inventory allocation for retailers with lower customer acceptance scores, thereby improving inventory turnover and ensuring the absolute service satisfaction rate of high-quality customers. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 This is a schematic diagram illustrating an application scenario of the VMI dynamic inventory optimization system provided in an embodiment of this application;

[0044] Figure 2 A flowchart illustrating a VMI dynamic inventory optimization method provided in an embodiment of this application;

[0045] Figure 3 A flowchart illustrating a VMI dynamic inventory optimization method provided in another embodiment of this application;

[0046] Figure 4 A flowchart illustrating a VMI dynamic inventory optimization method provided in another embodiment of this application;

[0047] Figure 5 This is a schematic diagram of the structure of a VMI dynamic inventory optimization device provided in an embodiment of this application;

[0048] Figure 6 This is a hardware structure diagram of an electronic device provided in an embodiment of this application.

[0049] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0050] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0051] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0052] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more.

[0053] It should be noted that "at the time of..." in the embodiments of this application can be either at the instant when a certain situation occurs, or for a period of time after the occurrence of a certain situation. The embodiments of this application do not specifically limit this.

[0054] To facilitate a clear description of the technical solutions in the embodiments of this application, the technologies involved in the embodiments of this application are briefly introduced below:

[0055] Vendor Managed Inventory (VMI) is a collaborative strategy aimed at minimizing costs for both the user (retailer) and the supplier. Under a shared agreement, the supplier manages inventory, continuously monitors its implementation, and modifies its content to achieve continuous improvement in inventory management. Its core lies in the supplier managing and replenishing inventory on behalf of the customer, while the customer shares inventory visibility with the supplier through methods such as sharing point-of-sale (POS) data. Theoretically, this model aims to reduce the "bullwhip effect," lower overall supply chain inventory levels, and improve responsiveness to market demands.

[0056] However, in years of practical application, the traditional VMI model has the following inherent defects:

[0057] 1. The static and rigid nature of demand forecasting

[0058] Traditional VMI (Vendor Managed Inventory) models rely heavily on time-series forecasting models (such as moving averages and ARIMA) based on historical sales data for replenishment decisions. This forecasting approach is inherently static and rigid, failing to effectively capture and quantify the differences in behavioral patterns among various customers. The system equates low-quality customers with high return rates and frequent negative reviews with high-quality customers who fulfill orders smoothly and maintain good relationships. Consequently, the resulting inventory allocation strategies inevitably deviate significantly from the actual needs of customers.

[0059] 2. A "one-size-fits-all" approach to service level agreements.

[0060] To ensure customer satisfaction, traditional VMI models typically set a uniform, rigid high service level target (such as a 98% order fulfillment rate). This "one-size-fits-all" service strategy lacks flexibility and granularity. To meet all customers' immediate delivery commitments, suppliers are forced to accumulate large amounts of safety stock at various distribution points, leading not only to significant financial pressure but also drastically reduced inventory turnover. Resources cannot be prioritized based on the actual value of each customer.

[0061] 3. Lack of a mechanism that integrates behavioral feedback and incentives.

[0062] Traditional VMI is an open-loop system. Customers' cooperative behavior (such as providing accurate forecasts and reducing returns) receives no reward; conversely, their non-cooperative behavior (such as frequent order cancellations and high damage rates) goes unpunished. This lack of feedback and regulation easily leads to moral hazard, undermines the foundation of trust among supply chain partners, and makes it difficult for the VMI model to be maintained sustainably in the long term.

[0063] 4. Optimize the singularity and isolation of objectives.

[0064] Most existing VMI optimization systems are solely driven by the goal of "avoiding stockouts," pursuing the maximization of service levels in isolation. The result is often that while high service satisfaction rates are achieved, it comes at the expense of supplier profitability and overall supply chain efficiency.

[0065] To address the aforementioned technical problems, this application provides a VMI (Dynamic Inventory Management) optimization method, apparatus, system, and storage medium. The method employs the following technical concept: by acquiring historical behavioral data of different retailers to calculate their respective customer acceptance levels, retailers with different customer acceptance levels can be differentiated. Thus, when allocating inventory to different retailers, priority can be given to ensuring the delivery needs of retailers with higher customer acceptance scores, while sacrificing the timeliness of inventory allocation for retailers with lower customer acceptance scores, thereby improving inventory turnover and ensuring the absolute service satisfaction rate of high-quality customers.

[0066] Figure 1 This is a schematic diagram illustrating an application scenario of a VMI (Dynamic Inventory Management) system provided in an embodiment of this application. The application scenario includes a first terminal 101 and a second terminal 102. The first terminal 101 is equipped with a supplier client for dynamic inventory optimization, which is convenient for suppliers to use. The second terminal 102 is equipped with a retailer client corresponding to the dynamic inventory optimization client, which is convenient for retailers to use. The supplier and retailer clients can be software (e.g., apps, browsers, etc.), or web pages, mini-programs, etc. Each retailer client periodically sends historical behavior data to the supplier client. After receiving the corresponding historical behavior data, the supplier client processes the data to obtain a corresponding inventory allocation strategy. This strategy at least includes a plan on how the supplier should supply goods to different retailers.

[0067] The first terminal 101 and the second terminal 102 are electronic devices used by the target object. These electronic devices can be personal computers, mobile phones, tablets, laptops, e-book readers, in-vehicle terminals, etc. Retailers can share relevant historical behavior data with the first terminal 101 through the client on the second terminal 102. Suppliers can develop corresponding inventory allocation plans for each retailer after receiving the historical behavior data of each retailer through the client on the first terminal 101.

[0068] In other application scenarios, a server 103 can be added to store historical behavioral data sent by each retailer. This allows server 103 to forward the stored historical location data to the first terminal 101. It should be noted that server 103 can be a standalone physical server, an edge device in the cloud computing field, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, cloud functions, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0069] This application embodiment does not impose any limitation on the number of the first terminal 101, the second terminal 102, and the server 103. However, in order to simplify the description of the technical solution of this application, only one first terminal 101 and multiple second terminals 102 are considered. The first terminal 101 is equipped with a processing module to process historical behavior data.

[0070] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments in this specification are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0071] The VMI dynamic inventory optimization method provided by the exemplary embodiments of this application is described below with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way.

[0072] Figure 2 This is a flowchart illustrating a VMI dynamic inventory optimization method provided in an embodiment of this application, applied to... Figure 1 The processing module of the first terminal 101 shown is used in this embodiment to introduce the VMI dynamic inventory optimization method, therefore, the first terminal 101 is used as the execution subject. Figure 2 As shown, a VMI dynamic inventory optimization method includes the following steps:

[0073] S210: Obtain historical behavioral data from multiple retailers, including at least each retailer's order data, return data, review data, repurchase data, and delivery time data.

[0074] In this embodiment, in order to reasonably evaluate the customer quality of different retailers, each retailer first needs to share its own historical behavioral data with the supplier.

[0075] Specifically, the aforementioned historical behavior data may include order data, return data, review data, repurchase data, and delivery time data saved by each retailer on the corresponding client.

[0076] Order data mainly refers to the total number of orders sold by each retailer in the previous period, as well as the amount of purchases made by the retailer from suppliers and inventory shortage losses.

[0077] Return data mainly refers to the number of return orders placed by buyers with a retailer in the previous period. The specific reasons for these returns are not considered; they can be returns without reason or returns due to product issues.

[0078] The review data mainly refers to the number of positive and negative reviews in the retailer's sales orders in the previous period. Orders purchased by customers but without corresponding reviews are considered positive reviews by default. In other words, apart from the number of negative reviews and returned orders, all other order data are the number of fulfilled positive reviews.

[0079] Buyback data mainly refers to the number of buyers who purchased from the retailer more than once in the previous period, as well as the total number of buyers who purchased goods from the retailer.

[0080] Delivery time data mainly refers to the relevant time data of the supplier's delivery to the retailer in the previous period, such as the promised delivery time, the actual delivery time, and the delivery delay time. The time here can be calculated in days. For example, the promised delivery time means how many days the goods are promised to be delivered, and the delivery delay time means how many days the goods are actually delayed.

[0081] The aforementioned period can be one month, six months, or one year. Suppliers can periodically obtain historical behavioral data from retailers according to their actual needs.

[0082] S220: Determine each retailer's customer acceptance level based on historical behavioral data. Customer acceptance level is used to indicate each retailer's tolerance for delayed delivery.

[0083] In this embodiment, the quantity of order data, return data, review data (positive and negative), repurchase data, and delivery time data can all reflect the quality of each retailer. For example, a low negative review rate indicates high customer acceptance, as can a high total number of orders and a low return rate. Therefore, differences in historical behavioral data can reflect individual differences among retailers to a certain extent, and these differences can be quantified using Customer Acceptance Score (CAS).

[0084] For retailers with high customer acceptance of CAS (Customer Acceptance Rate), suppliers should prioritize meeting their inventory needs. This requires sacrificing the timeliness of delivery to retailers with low customer acceptance of CAS in order to ensure the fulfillment rate of orders with high customer acceptance, thereby optimizing the overall supply experience.

[0085] S230: Determine the flexible service hours for each retailer based on each retailer's customer acceptance.

[0086] In this embodiment, based on the analysis in step S220, suppliers will prioritize ensuring the supply needs of retailers with high customer acceptance. Therefore, a higher Flexible Service Days (FSD) can be allocated to retailers with high customer acceptance. The FSD is used to control the flexibility of the retailer's delivery time. In this way, rigid service standards can be made more flexible, thereby enhancing the resilience of the VMI dynamic inventory optimization system to fluctuations.

[0087] S240: With the goal of maximizing inventory turnover and minimizing customer stockout losses, determine each retailer's inventory allocation strategy based on each retailer's customer acceptance and flexible service hours.

[0088] In this embodiment, the objective function can be constructed using the Customer Acceptance (CAS) and Flexible Service Time (FSD) obtained above in the following manner.

[0089] In one possible implementation, the order data includes the amount of goods purchased by the retailer from the supplier in the previous period and the current inventory shortage loss, which is set to 0 by default if there is no shortage.

[0090] The objective function includes the inventory turnover function and the stockout loss function.

[0091] The inventory turnover function can be determined based on each retailer's purchase volume, customer acceptance, and flexible service time in the previous period, as follows:

[0092] Suppose that the purchase quantity of the i-th retailer among n retailers is P. i Customer acceptance is CAS i Elastic service time is FSD i Then the inventory turnover function A is:

[0093]

[0094] The stockout loss function can be determined based on each retailer's inventory stockout loss and customer acceptance, as follows:

[0095] Suppose that the stockout loss of the i-th retailer out of n retailers is Qi, then the stockout loss function B is:

[0096]

[0097] In operations science, constraints refer to the restrictive conditions that must be met during resource planning. They usually appear in the form of inequalities or equations in mathematical models and are used to limit the range of values ​​for decision variables, such as inventory balance and delay days.

[0098] In this embodiment, the constraints can be to meet a preset service fulfillment rate, such as all retailers must meet at least 98% of the supply demand; the constraints can also be that the inventory turnover function must be greater than a preset turnover threshold, and the stockout loss function must be less than a preset loss threshold.

[0099] Taking the constraint of satisfying a preset service satisfaction rate as an example, under this constraint, the solver can be used to maximize the inventory turnover function and minimize the stockout loss function, thereby obtaining the inventory allocation strategy for each retailer.

[0100] It should be noted that the tools used for solving the problem can be commercially available linear programming solvers, such as the GNU Linear Programming Toolkit, LINGO, etc. This embodiment uses the COPT solver developed by the applicant of this application. This solver supports solving multivariate problems such as linear programming (simplex method, interior point method and first-order algorithm), mixed integer programming, semidefinite programming, (mixed integer) second-order cone programming and (mixed integer) convex quadratic constraint programming for large-scale optimization problems.

[0101] Figure 3 This is a flowchart illustrating a VMI dynamic inventory optimization method provided in another embodiment of this application, which is also applicable to... Figure 1 On the processing module of the first terminal 101 shown, the method is executed by a computer device. For example... Figure 3 As shown, a VMI dynamic inventory optimization method includes the following steps:

[0102] S310: Obtain historical behavioral data from multiple retailers, including at least each retailer's order data, return data, review data, repurchase data, and delivery time data.

[0103] In this embodiment, step S310 can be specifically referred to in the description of step S210, and will not be repeated here.

[0104] The following example of steps S320 to S340 illustrates how customer acceptance is calculated. This application does not specifically limit other methods that use historical behavioral data to quantify the quality of retailers.

[0105] S320: Determine the return rate, fulfillment satisfaction rate, negative review rate, and repurchase rate for each retailer based on their return data, review data, and repurchase data.

[0106] In this embodiment, in order to obtain the customer acceptance of each retailer, it is necessary to evaluate it using the historical behavioral data returned by each retailer. Taking one retailer as an example, this can be illustrated.

[0107] Return rate:

[0108] Since return data includes the number of returned orders placed by buyers at that retailer in the previous period, the return rate = number of returned orders / total number of orders.

[0109] Positive and negative feedback rates for fulfillment:

[0110] Since the review data, apart from the number of negative reviews and returned orders, all other order data are the number of fulfilled positive reviews, the fulfillment positive review rate = fulfilled positive review rate / total fulfilled orders, where the total fulfilled orders = total orders - returned orders.

[0111] The number of negative reviews is determined based on the actual negative reviews from the total number of orders. Therefore, the negative review rate = number of negative review orders / total number of orders. In some cases, the numerator may also consider the number of returned orders due to issues such as product quality or discrepancies in description, while the denominator will exclude the number of returned orders due to logistics problems and the number of orders returned without a reason.

[0112] Repurchase rate:

[0113] Since repurchase data includes the number of buyers who made more than one purchase from the retailer in the previous period, as well as the total number of buyers who purchased goods from the retailer, the repurchase rate = number of repeat buyers / total number of buyers.

[0114] S330: Determine the corresponding retailer's delivery delay tolerance based on each retailer's delivery time data.

[0115] In this embodiment, the delivery time data for each retailer includes the promised delivery time, actual delivery time, and delivery delay time of the supplier in the previous period.

[0116] It is clear that the longer the delivery delay, the higher the retailer's tolerance for delivery delays.

[0117] In one specific embodiment, determining the delivery delay tolerance of a corresponding retailer based on the delivery time data of each retailer may include the following steps:

[0118] S331: Determine the promised delivery time and delivery delay time for each retailer based on their delivery time data.

[0119] In this embodiment, the delivery delay time can also be obtained directly from the promised delivery time and the actual delivery time, that is, delivery delay time = actual delivery time - promised delivery time.

[0120] S332: Determine the corresponding retailer's tolerance for delivery delays based on the ratio of the delivery delay time to the promised delivery time.

[0121] In this step, the retailer's delivery delay tolerance can be defined based on the delivery delay time and the promised delivery time, i.e., delivery delay tolerance = delivery delay time / promised delivery time.

[0122] For example, if the promised delivery time is 20 days, but the actual delivery time is the 25th day, then the delivery delay is 5 days, and the retailer's delivery delay tolerance is 0.25.

[0123] It should be noted that steps S320 and S330 can be executed in any order; they can be executed simultaneously or sequentially.

[0124] S340: Determine the customer acceptance level of each retailer based on their return rate, fulfillment satisfaction rate, negative feedback rate, repurchase rate, and delivery delay tolerance.

[0125] After obtaining the return rate, fulfillment satisfaction rate, negative review rate, repurchase rate, and delivery delay tolerance for each retailer through the aforementioned steps, the customer acceptance rate for the corresponding retailer can be calculated using these parameters. The specific calculation formula is as follows:

[0126]

[0127] Among them, CAS i R represents the customer acceptance of the i-th retailer. i Let o represent the number of returned orders from the i-th retailer. i_total Let F represent the total number of orders from the i-th retailer.i F represents the number of positive fulfillment reviews for the i-th retailer. i_total Let C represent the total number of fulfilled orders for the i-th retailer. i RE represents the number of negative reviews for the i-th retailer. i RE represents the number of buyers who made more than one purchase from the i-th retailer. i_total D represents the total number of buyers for the i-th retailer. i D represents the delivery delay time of the i-th retailer. i0 Let represent the promised delivery time of the i-th retailer, where α, β, γ, δ, and η are weighting factors that can be obtained through experience or machine learning training.

[0128] In the above formula, the quantity statistics only apply to the retailer's previous period.

[0129] It can be seen that the formulas for calculating customer acceptance all use positive evaluations to quantify customer acceptance.

[0130] for example The return rate reflects negative feedback from retailers. This will determine whether the non-return rate reflects the retailer's positive evaluation.

[0131] For example, the longer the delivery delay, the greater the retailer's tolerance for delivery delays, and the lower the retailer's customer acceptance.

[0132] It should be noted that the above formula for calculating customer acceptance only needs to consider at least two of the following parameters: return rate, positive fulfillment rate, negative review rate, repurchase rate, and tolerance for delivery delays. The more parameters considered, the more accurately the calculated customer acceptance will quantify the retailer's tolerance for delayed delivery.

[0133] S350: Determine the flexible service time for each retailer based on each retailer's customer acceptance.

[0134] In this embodiment, as can be seen from the calculation formula of customer acceptance in step S340, for the supplier, the higher the customer acceptance value of the retailer, the better the quality of the retailer. Therefore, a larger flexible service time can be allocated to retailers with higher customer acceptance. The flexible service time reflects the flexibility of the retailer's needs in fulfilling them. The larger the flexible service time, the greater the flexibility the supplier has in fulfilling the retailer's needs.

[0135] In theory, the flexible service hours allocated to each retailer are positively correlated with their customer acceptance. This positive correlation can be a step function relationship or a continuously changing function relationship.

[0136] In one specific embodiment, determining the flexible service time for each retailer based on each retailer's customer acceptance may include the following steps:

[0137] S351: Obtain the distribution relationship table between customer acceptance and flexible service time. In the relationship table, there is a positive correlation between flexible service time and customer acceptance.

[0138] In this embodiment, a step function is used to represent the positive correlation between flexible service time and customer acceptance. Specifically, the step function relationship can also be represented by a pre-set allocation association table, which provides the flexible service time corresponding to different ranges of customer acceptance.

[0139] S352: Determine the flexible service hours for each retailer based on each retailer's customer acceptance and the allocation association table.

[0140] Once the customer acceptance level for each retailer is determined, the corresponding flexible service time can be found directly from the allocation association table.

[0141] The following is a preliminary requirement for allocating related tables:

[0142] For example, when the customer acceptance rate (CAS) of the i-th retailer... i When ≤0.3, the retailer's flexible service hours (FSD) are 0; when 0.3 < CAS i When the value is ≤0.7, the retailer's FSD is 2 days; when it is 0.7... <CAS i When <0.9, the retailer's FSD is 5 days; when CAS i When the value is ≥0.9, the retailer's FSD is 7 days.

[0143] The allocation of related tables based on the table representation can be as follows:

[0144] Customer Acceptance (CAS) Flexible Service Hours (FSD) CAS≤0.3 0 0.3 < CAS ≤ 0.7 2 0.7 < CAS < 0.9 5 CAS ≥ 0.9 7

[0145] Of course, depending on actual needs, the above allocation table can also be used to allocate more granular flexible service times for different ranges of customer acceptance.

[0146] S360: With the goal of maximizing inventory turnover and minimizing customer stockout losses, it determines each retailer's inventory allocation strategy based on each retailer's customer acceptance and flexible service hours.

[0147] This step can be referred to in step S240, where the objective function is constructed to solve the inventory allocation strategy, which will not be repeated here.

[0148] In the above embodiments, retailers with higher customer acceptance receive more flexible service time, allowing for differentiated treatment of retailers of varying quality and thus providing differentiated inventory allocation strategies. When allocating inventory, priority can be given to ensuring the inventory needs of retailers with higher customer acceptance (CAS), by sacrificing the timeliness of inventory allocation for retailers with lower CAS, thereby ensuring absolute satisfaction of high-quality customers.

[0149] Furthermore, by setting corresponding flexible allocation times for retailers of different CAS (Customer Acquisition Services), suppliers no longer need to prepare readily available inventory for all orders. This allows suppliers to gain valuable inventory scheduling buffer time, enabling them to allocate limited inventory in a concentrated and efficient manner. Consequently, they can support similar or even better service experiences with lower overall inventory levels, directly reducing the risk of unsold inventory and capital tied up.

[0150] Secondly, since customer acceptance and flexible service time are dynamically calculated based on real-time historical behavior data from the previous period, it can ensure that inventory allocation strategies for each period can be fed back in real time, enabling inventory management to change from "post-event remediation" to "pre-event intelligent decision-making" and from "passive response" to "proactive guidance".

[0151] Finally, since the objective function is to maximize inventory turnover and minimize customer stockout losses, the final calculated inventory allocation strategy can prioritize meeting the needs of high-value customers while pursuing high efficiency, thus finding the optimal balance between improving inventory turnover and ensuring the service level of high CAS retailers.

[0152] Figure 4 The flowchart of the VMI dynamic inventory optimization method provided in another embodiment of this application is also applicable to... Figure 1 On the processing module of the first terminal 101 shown, the method is executed by a computer device. For example... Figure 4 As shown, a VMI dynamic inventory optimization method includes the following steps:

[0153] S410: Obtain historical behavioral data from multiple retailers, including at least each retailer's order data, return data, review data, repurchase data, and delivery time data.

[0154] S420: Determine the return rate, fulfillment satisfaction rate, negative review rate, and repurchase rate for each retailer based on their return data, review data, and repurchase data.

[0155] S430: Determine the corresponding retailer's delivery delay tolerance based on each retailer's delivery time data.

[0156] S440: Determine the customer acceptance level of each retailer based on their return rate, fulfillment satisfaction rate, negative feedback rate, repurchase rate, and delivery delay tolerance.

[0157] S450: Obtain the allocation relationship table between customer acceptance and flexible service time and inventory cost allocation ratio. In the allocation relationship table, there is a positive correlation between flexible service time and customer acceptance, and a negative correlation between inventory cost allocation ratio and customer acceptance.

[0158] The traditional VMI (Vendor Managed Inventory) model inherently contains a mismatch of responsibilities: suppliers bear 100% of the costs associated with tying up inventory, the risk of goods depreciation, and losses from unsold inventory, but lack control over the rate of inventory depletion and final sales. Retailers may experience inventory buildup due to changes in their sales strategies, inaccurate market forecasts, or even malicious actions (such as over-ordering or unjustified large-scale returns), while all risks are borne unilaterally by the supplier. This unequal distribution of "risk-reward" significantly erodes suppliers' profit margins, dampening the enthusiasm for implementing the VMI model.

[0159] In this embodiment, an inventory cost allocation ratio is considered for each retailer based on different levels of customer acceptance. Theoretically, retailers with higher customer acceptance are of higher quality, and therefore should receive a lower or even zero inventory cost allocation ratio. In other words, for high-quality retailers, the supplier is willing to bear a higher proportion of inventory costs, while for low-quality retailers, the supplier requires the retailer to bear a certain proportion of inventory costs. Therefore, there is a positive correlation between the supplier's inventory cost ratio and customer acceptance.

[0160] S460: Determine the flexible service time and inventory cost allocation ratio for each retailer based on each retailer's customer acceptance and the allocation association table.

[0161] In this embodiment, after obtaining the customer acceptance rate for each retailer, the elastic service time and inventory cost allocation ratio corresponding to that customer acceptance rate can be found directly from the allocation association table.

[0162] The following is an allocation relationship table that introduces inventory cost allocation ratios. This allocation relationship table is illustrated in the table below:

[0163] Customer Acceptance (CAS) Flexible Service Hours (FSD) Inventory cost allocation ratio (retailers) CAS≤0.3 0 30％ 0.3 < CAS ≤ 0.7 2 20％ 0.7 < CAS < 0.9 5 10％ CAS ≥ 0.9 7 0％

[0164] It can be seen that the relationship between the retailer's inventory cost allocation ratio and customer acceptance also uses a step function to reflect the negative correlation between the two. For retailers with a customer acceptance rate greater than 0.9, they do not bear any of the supplier's inventory costs, while for retailers with a customer acceptance rate less than 0.3, they need to bear 30% of the supplier's inventory costs.

[0165] S470: With the goal of maximizing inventory turnover and minimizing customer stockout losses, determine each retailer's inventory allocation strategy based on each retailer's customer acceptance and flexible service hours.

[0166] For any points not mentioned in steps S410 to S470 above, please refer to the description of steps S310 to S360, which will not be repeated here.

[0167] In the above embodiments, since retailers with low customer acceptance need to bear part of the supplier's inventory costs, while retailers with high customer acceptance need to bear a small portion or no portion of the supplier's inventory costs, this can reduce the supplier's unsold inventory losses and financial risks to a certain extent. This directly links the downstream sales behavior with its own economic interests, greatly suppresses the non-cooperative behavior of retailers (such as malicious ordering and high return rates), reduces the generation of unsold inventory from the source, and reduces the supplier's capital occupation and risk exposure.

[0168] Furthermore, the negative correlation between a retailer's inventory cost sharing ratio and customer acceptance provides a clear behavioral feedback loop for retailers. Retailers can improve their customer acceptance scores by changing their behavior (such as reducing return rates and negative reviews), thereby securing more favorable business terms (such as lower inventory cost sharing ratios and faster delivery times).

[0169] Figure 5 This is a schematic diagram of a VMI (Dynamic Inventory Management) device according to an embodiment of this application. The device can be in software and / or hardware form. (See also...) Figure 5 A VMI dynamic inventory optimization device includes: a historical behavior data acquisition module 510, a customer acceptance calculation module 520, a flexible service time calculation module 530, and an inventory allocation strategy solution module 540.

[0170] The historical behavior data acquisition module 510 is used to acquire historical behavior data from multiple retailers. The historical behavior data includes at least each retailer's order data, return data, review data, repurchase data, and delivery time data.

[0171] The customer acceptance calculation module 520 is used to determine the customer acceptance of each retailer based on historical behavioral data. The customer acceptance is used to indicate the degree of tolerance of each retailer for delayed delivery.

[0172] The flexible service time calculation module 530 is used to determine the flexible service time for each retailer based on each retailer's customer acceptance.

[0173] The inventory allocation strategy solving module 540 is used to determine the inventory allocation strategy for each retailer based on each retailer's customer acceptance and flexible service time, with the goal of maximizing inventory turnover and minimizing customer stockout losses.

[0174] In some embodiments, the customer acceptance calculation module 520 specifically includes:

[0175] The return rate, fulfillment positive review rate, negative review rate, and repurchase rate of each retailer are determined based on their return data, review data, and repurchase data.

[0176] Determine the corresponding retailer's delivery delay tolerance based on each retailer's delivery time data;

[0177] The customer acceptance level of each retailer is determined based on its return rate, positive fulfillment rate, negative review rate, repurchase rate, and tolerance for delivery delays.

[0178] In some embodiments, delivery delay tolerance can be calculated as follows:

[0179] The promised delivery time and delivery delay time for each retailer are determined based on their order data.

[0180] Retailers’ tolerance for delivery delays is based on the ratio of delivery delay time to promised delivery time.

[0181] In some embodiments, the elastic service time calculation module 530 specifically includes:

[0182] Obtain a correlation table between customer acceptance and flexible service hours, which indicates the positive correlation between customer acceptance and flexible service hours;

[0183] The flexible service hours for each retailer are determined based on their customer acceptance and the allocation of the association table.

[0184] In some embodiments, assigning a related table requires at least the following:

[0185] When a retailer’s customer acceptance rate is less than or equal to 0.3, the retailer’s flexible service time is 0.

[0186] When a retailer's customer acceptance rate is greater than 0.3 and less than or equal to 0.7, the retailer's flexible service time is 2.

[0187] When a retailer's customer acceptance rate is greater than 0.7 and less than 0.9, the retailer's flexible service time is 5.

[0188] When a retailer’s customer acceptance rate is greater than or equal to 0.9, the retailer’s flexible service time is 7.

[0189] In some embodiments, the allocation relationship table also includes the inventory cost allocation ratio corresponding to different customer acceptance levels for the retailer, and the inventory cost allocation ratio is negatively correlated with customer acceptance.

[0190] In some embodiments, order data includes sales volume and inventory shortage losses, in which case the inventory allocation strategy solving module 540 specifically includes:

[0191] Build an inventory turnover function based on each retailer's order data, customer acceptance, and flexible service hours;

[0192] Construct a stockout loss function based on each retailer's stockout loss and customer acceptance.

[0193] Using service satisfaction rate as a constraint, the inventory allocation strategy for each retailer is obtained by solving the problem.

[0194] The VMI dynamic inventory optimization device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned VMI dynamic inventory optimization method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned VMI dynamic inventory optimization method embodiment.

[0195] Figure 6 This is a hardware structure diagram of an electronic device provided in an embodiment of this application. The embodiment provides an electronic device including: at least one processor 601, and a memory 602 communicatively connected to the at least one processor 601; the memory 602 stores computer-executable instructions; the processor 601 executes the computer-executable instructions stored in the memory 602 to implement the VMI dynamic inventory optimization method described in any of the preceding embodiments.

[0196] Figure 6 The illustrated electronic device also includes a communication interface 603 and a communication bus 604. The processor 601, memory 602, and communication interface 603 are interconnected via the communication bus 604. The communication bus 604 can be divided into an address bus, a data bus, a control bus, etc., for ease of representation. Figure 6 The communication bus 604 is represented by only one thick line, but this does not mean that there is only one communication bus 604 or only one type of communication bus 604. The processor 601 can also be called a controller, and there is no restriction on the name.

[0197] In this embodiment, memory 602 stores instructions executable by at least one processor 601. By executing the instructions stored in memory 602, at least one processor 601 can execute the VMI dynamic inventory optimization method discussed above. Processor 601 can implement... Figure 5 The functions of each module in the device shown.

[0198] The processor 601 is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory 602 and calling data stored in memory 602, the processor can perform various functions and process data, thereby monitoring the device as a whole.

[0199] In one possible design, processor 601 may include one or more processing units. Processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 601. In some embodiments, processor 601 and memory 602 may be implemented on the same chip or on separate chips.

[0200] Processor 601 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the VMI dynamic inventory optimization method disclosed in the embodiments of this application can be directly manifested as execution by a hardware processor, or as execution by a combination of hardware and software modules within the processor.

[0201] Memory 602, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 602 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. Memory 602 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 602 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0202] By designing and programming the processor 601, the code corresponding to the VMI dynamic inventory optimization method described in the foregoing embodiments can be embedded into the chip, enabling the chip to execute it during operation. Figure 2 The steps of the VMI dynamic inventory optimization method in the illustrated embodiment are as follows. How to design and program the processor 601 is a technique well-known to those skilled in the art and will not be described further here.

[0203] This application also provides a computer-readable storage medium storing computer-executable instructions. When executed by a processor, these instructions are used to implement the VMI dynamic inventory optimization method described in any of the preceding embodiments; therefore, they will not be repeated here. Furthermore, the beneficial effects of using the same method will also not be repeated. For technical details not disclosed in the computer storage medium embodiments of this invention, please refer to the description of the method embodiments of this invention.

[0204] In some possible implementations, various aspects of the VMI dynamic inventory optimization method provided in this application can also be implemented in the form of a program product, which includes program code that, when the program product is run on a device, causes the control device to perform the steps in the VMI dynamic inventory optimization method according to the various exemplary embodiments of this application described above.

[0205] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0206] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0207] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0208] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0209] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A VMI (Vehicle Managed Inventory) dynamic inventory optimization method, characterized in that, The method includes: Acquire historical behavioral data from multiple retailers, including at least order data, return data, review data, repurchase data, and delivery time data for each retailer; The customer acceptance level for each retailer is determined based on the historical behavioral data, and the customer acceptance level is used to indicate each retailer's tolerance for delayed delivery; The flexible service time for each retailer is determined based on the customer acceptance level of each retailer; With the goal of maximizing inventory turnover and minimizing customer stockout losses, an inventory allocation strategy is determined for each retailer based on their customer acceptance and flexible service hours.

2. The method according to claim 1, characterized in that, The process of determining customer acceptance for each retailer based on the historical behavioral data includes: The return rate, fulfillment satisfaction rate, negative review rate, and repurchase rate of each retailer are determined based on their return data, review data, and repurchase data. Determine the corresponding retailer's delivery delay tolerance based on each retailer's delivery time data; The customer acceptance level of each retailer is determined based on its return rate, positive fulfillment rate, negative review rate, repurchase rate, and tolerance for delivery delays.

3. The method according to claim 2, characterized in that, The process of determining the delivery delay tolerance of each retailer based on their delivery time data includes: The promised delivery time and delivery delay time for each retailer are determined based on the delivery time data for each retailer. The corresponding retailer's delivery delay tolerance is determined based on the ratio of the delivery delay time to the promised delivery time.

4. The method according to claim 1, characterized in that, The determination of each retailer's flexible service time based on each retailer's customer acceptance includes: Obtain an allocation correlation table between the customer acceptance rate and the flexible service time, wherein the flexible service time and the customer acceptance rate are positively correlated in the allocation correlation table; The flexible service hours for each retailer are determined based on their customer acceptance and the allocation of the association table.

5. The method according to claim 4, characterized in that, The allocation association table must at least require: When the retailer's customer acceptance rate is less than or equal to 0.3, the retailer's flexible service time is 0. When the retailer's customer acceptance rate is greater than 0.3 and less than or equal to 0.7, the retailer's flexible service time is 2. When the retailer's customer acceptance rate is greater than 0.7 and less than 0.9, the retailer's flexible service time is 5. When the retailer’s customer acceptance rate is greater than or equal to 0.9, the retailer’s flexible service time is 7.

6. The method according to claim 4, characterized in that, The allocation association table also includes the inventory cost allocation ratio corresponding to different customer acceptance levels for retailers, and the inventory cost allocation ratio is negatively correlated with the customer acceptance level.

7. The method according to claim 1, characterized in that, The order data includes purchase volume and inventory shortage losses; The goal is to maximize inventory turnover and minimize customer stockout losses. Based on each retailer's customer acceptance and flexible service hours, an inventory allocation strategy is determined for each retailer, including: Build an inventory turnover function based on each retailer's purchase volume, customer acceptance, and flexible service hours; Construct a stockout loss function based on each retailer's stockout loss and customer acceptance. Given the service satisfaction rate as a constraint, find the inventory allocation strategy for each retailer that maximizes inventory turnover and minimizes customer stockout losses.

8. A supplier dynamic inventory optimization device, characterized in that, include: The historical behavior data acquisition module is used to acquire historical behavior data from multiple retailers. The historical behavior data includes at least each retailer's order data, return data, review data, repurchase data, and delivery time data. A customer acceptance calculation module is used to determine the customer acceptance level of each retailer based on the historical behavior data, wherein the customer acceptance level is used to indicate the degree of tolerance of each retailer for delayed delivery; The flexible service time calculation module is used to determine the flexible service time for each retailer based on the customer acceptance of each retailer. The inventory allocation strategy solving module is used to determine the inventory allocation strategy for each retailer based on the customer acceptance and flexible service time of each retailer, with the goal of maximizing inventory turnover and minimizing customer stockout losses.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

Images