Inventory information processing method and device

Abstract

The application provides a kind of inventory information processing method and device, wherein the method comprises: determining the demand range of the goods to be replenished corresponding to target period;According to the demand range and the preset quantile point, a plurality of first replenishment schemes located in the demand range are determined, and the demand range is expanded based on the preset quantile point to obtain a plurality of second replenishment schemes located outside the demand range;Determine the inventory change sequence of the first replenishment scheme and the second replenishment scheme in the target period, and determine the expected income corresponding to each first replenishment scheme and second replenishment scheme based on the inventory change sequence to determine the target replenishment scheme of the goods to be replenished in the target period. The implementation can limit the decision space in the conventional demand range and the extended candidate points outside the demand range, ensure the rationality of the replenishment scheme, and at the same time, through the extended candidate points, the special replenishment situation that may occur is covered, and the applicability of the replenishment scheme is improved.

Description

Technical Field

[0001] This invention relates to the field of warehouse management technology, and more specifically, to an inventory information processing method and apparatus. Background Technology

[0002] Inventory management is the cornerstone of supply chain and e-commerce retail. Effective inventory management can reduce holding costs and improve in-stock efficiency. Currently, deep learning or reinforcement learning techniques are increasingly being used to build end-to-end replenishment decision models, directly outputting the target replenishment quantity through a unified neural network. However, end-to-end models typically use a continuous action space to directly output the replenishment quantity, which is prone to extreme outliers during the exploration phase, leading to risks of unsold inventory or stockouts. Consequently, the resulting replenishment solution lacks rationality and applicability. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide at least one inventory information processing method, apparatus, electronic device, and storage medium, which can limit the decision space to the range of conventional demand and extended candidate points beyond the range of demand, ensuring the rationality of the replenishment plan. At the same time, by expanding candidate points, it covers possible special replenishment situations and improves the applicability of the replenishment plan.

[0004] In a first aspect, embodiments of the present invention provide an inventory information processing method, including: Determine the range of demand for the goods to be replenished corresponding to the target time period; Based on the demand range and preset percentiles, multiple first replenishment plans within the demand range are determined, and the demand range is expanded based on the preset percentiles to obtain multiple second replenishment plans outside the demand range. Determine the inventory change sequence of the first and second replenishment plans within the target period, and determine the expected revenue corresponding to each first and second replenishment plan based on the inventory change sequence, so as to determine the target replenishment plan for the goods to be replenished within the target period.

[0005] Optionally, the range of demand for the goods to be replenished corresponding to the target time period is determined, including: The time period characteristics of the target time period are input into the pre-trained demand prediction model so that the demand prediction model can determine the demand range of the goods to be replenished during the target time period. The demand forecasting model was trained based on the following steps: Based on the historical sales and historical inventory status of the items to be replenished within a preset time window, determine the number of visits corresponding to the items that are in stock and the number of visits that are out of stock for the items to be replenished. The conversion rate of the items to be replenished is determined based on the number of visits to in-stock items and the historical sales volume of the items to be replenished within the statistical period of the in-stock visits. Based on the conversion rate and the number of out-of-stock visits, determine the lost sales corresponding to the out-of-stock visit period for the items to be replenished, and determine the actual sales of the items to be replenished within the out-of-stock visit period. Based on the lost sales and actual sales of the items to be replenished during the statistical period of out-of-stock visits, determine the estimated sales of the items to be replenished during the statistical period of out-of-stock visits. The activity features corresponding to the preset time window are extracted, and the demand prediction model is trained based on the historical sales, estimated sales and activity features of the goods to be replenished within the statistical period of the number of visits to the stock.

[0006] Optionally, based on the demand range and preset quantiles, multiple first replenishment plans within the demand range are determined, and the demand range is expanded based on the preset quantiles to obtain multiple second replenishment plans outside the demand range, including: Get the demand corresponding to multiple different preset quantiles within the demand range, use each demand as the corresponding replenishment quantity, and generate multiple first replenishment plans. Based on the demand difference corresponding to different quantiles within the demand range, the expansion is carried out in the upper and lower limits of the demand range according to the preset expansion strategy, and multiple first expansion schemes located outside the demand range are determined. Based on the promotional information corresponding to the target period and the determination of the supply replenishment quantity within the target period, a second extended plan is generated based on the supply replenishment quantity; The first and second expansion plans are used as multiple second replenishment plans.

[0007] Optionally, determine the inventory change sequence of the first replenishment plan and the second replenishment plan within the target period, and determine the expected revenue corresponding to each of the first replenishment plan and the second replenishment plan based on the inventory change sequence, including: Based on the replenishment quantity and inventory information corresponding to each first replenishment plan and each second replenishment plan, the expected sales volume, expected inventory volume and expected stockout volume corresponding to each first replenishment plan and each second replenishment plan are simulated, and the inventory change sequence of each first replenishment plan and each second replenishment plan within the target period is generated. Based on the time relationship between the expected arrival time of each first replenishment plan and each second replenishment plan and the promotion time corresponding to the target period, determine the inventory cost adjustment coefficient corresponding to each first replenishment plan and each second replenishment plan; Based on the inventory change sequence and the inventory cost adjusted by the inventory cost adjustment coefficient, determine the expected revenue corresponding to each first replenishment plan and each second replenishment plan.

[0008] Optionally, before determining the target replenishment plan for the items to be replenished during the target time period, the following steps are also included: Based on the expected revenue corresponding to each first replenishment plan and each second replenishment plan, candidate replenishment plans are determined and pushed to the reviewer. Receive adjustment information from the reviewer that corresponds to the candidate replenishment plan, and determine the adjustment range and reason for the adjustment of the replenishment quantity value in the adjustment information; The adjusted candidate replenishment plan is used as the target replenishment plan, and the demand forecasting model is optimized and trained based on the adjustment information.

[0009] Optionally, the method further includes: If there are at least two items to be replenished, obtain the replenishment quantity constraints corresponding to at least two items to be replenished; Determine the total replenishment quantity based on the target replenishment plan corresponding to each item to be replenished; In response to the total replenishment quantity exceeding the target replenishment quantity corresponding to the replenishment quantity constraint, calculate the revenue increment per unit replenishment quantity of the target replenishment plan for each item to be replenished, and sort each item to be replenished according to the revenue increment per unit replenishment quantity. Based on the sorting results, the replenishment quantity of the target replenishment plan corresponding to at least one item to be replenished is adjusted so that the adjusted total replenishment quantity meets the replenishment quantity constraint.

[0010] Secondly, embodiments of the present invention provide an inventory information processing apparatus, comprising: The range determination module is used to determine the range of demand for goods to be replenished corresponding to the target time period; The solution generation module is used to determine multiple first replenishment solutions within the demand range based on the demand range and preset quantiles, and to expand the demand range based on the preset quantiles to obtain multiple second replenishment solutions outside the demand range. The scheme determination module is used to determine the inventory change sequence of the first replenishment scheme and the second replenishment scheme within the target period, and to determine the expected revenue corresponding to each first replenishment scheme and the second replenishment scheme based on the inventory change sequence, so as to determine the target replenishment scheme for the goods to be replenished within the target period.

[0011] Thirdly, embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the first aspect or any optional implementation of the first aspect are performed.

[0012] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the first aspect or any optional implementation thereof.

[0013] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0014] In any of the above aspects or any implementation methods, the demand range can first be determined based on the goods to be replenished corresponding to the target time period, reflecting the range of demand changes for the goods to be replenished under normal circumstances within the target time period. Then, multiple first replenishment plans can be generated using the demand corresponding to multiple preset quantiles within the demand range as replenishment quantities, covering different replenishment levels such as conservative replenishment, balanced replenishment, and aggressive replenishment. This limits replenishment decisions to a reasonable range corresponding to the demand forecast results, avoiding excessive deviation of replenishment quantities from actual demand that could lead to inventory backlog or stockout risks. Simultaneously, considering that demand forecast results are usually derived from historical data, actual demand may exceed the normal demand range in special scenarios such as promotional activities, sudden market changes, and traffic surges. Therefore, the demand range can be further expanded upwards and downwards based on preset quantiles to generate multiple second replenishment plans outside the demand range. The system's downward expansion covers scenarios with low or even zero replenishment when demand is below the normal range, reducing the risk of inventory buildup during sudden demand drops. Conversely, upward expansion covers scenarios with high replenishment when demand is above the normal range, improving supply capacity during promotional events, peak sales, or periods of surging demand. This allows the system to simultaneously consider both regular and special business scenarios. It simulates inventory changes within a target time period for each replenishment plan, obtaining corresponding inventory change sequences. These sequences are then used to calculate the expected returns for each replenishment plan, selecting the optimal plan rather than relying solely on a single forecast result to generate replenishment decisions. This approach limits the replenishment decision space to the demand range and its reasonable expansion, ensuring that replenishment plans have clear business basis and physical meaning, avoiding abnormal replenishment plans that significantly deviate from actual demand, and improving the rationality of replenishment decisions. Furthermore, by introducing extended candidate points beyond the demand range, replenishment plans can cover special scenarios such as abnormal demand fluctuations and promotional surges, enhancing the adaptability of replenishment decisions to complex business environments and improving the applicability and robustness of the replenishment plans.

[0015] The beneficial effects of the aforementioned inventory information processing device, electronic equipment, and storage medium are described in the description of the aforementioned inventory information processing method, and will not be repeated here. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to the present invention and, together with the specification, serve to explain the technical solutions of the present invention. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 A flowchart of an inventory information processing method provided by an embodiment of the present invention is shown; Figure 2 A flowchart illustrating an inventory information processing method provided by an embodiment of the present invention is shown; Figure 3 A schematic diagram of an inventory information processing device provided in an embodiment of the present invention is shown; Figure 4 An exemplary system architecture in which embodiments of the present invention can be applied is shown; Figure 5 A schematic diagram of the structure of a computer system used to implement embodiments of the present invention is shown. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations, and require notification to users and obtaining their consent or authorization. When applicable, user personal information is subjected to de-identification and / or anonymization and / or encryption technical processing.

[0020] The above problems and solutions are the result of the inventor's practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be considered as the inventor's contribution to the invention.

[0021] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0022] To facilitate understanding of this embodiment, a detailed description of the inventory information processing method disclosed in this invention will be provided first. The execution entity of the inventory information processing method provided in this invention is generally a computer device with a certain computing capability. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, this inventory information processing method can be implemented by a processor calling computer-readable instructions stored in memory.

[0023] See Figure 1 The diagram shows a flowchart of an inventory information processing method provided in an embodiment of the present invention. The method includes steps S101 to S103, wherein: S101: Determine the range of demand for goods to be replenished corresponding to the target time period.

[0024] In this embodiment of the invention, the target time period can refer to a future time period in which a replenishment decision needs to be made. It can be set according to actual business needs, such as the next three days, a future replenishment cycle, or a procurement cycle. Alternatively, the target time period can correspond to a promotional activity cycle, such as the inventory preparation cycle before and after promotional activities like "Double Eleven" or "618". The length of the target time period can be determined based on factors such as the sales characteristics of the goods to be replenished, the procurement cycle, and the transportation cycle; this embodiment of the invention does not impose specific limitations on this.

[0025] In this embodiment of the invention, determining the demand range of the goods to be replenished corresponding to the target time period includes: inputting the time period characteristics of the target time period into a pre-trained demand prediction model, so that the demand prediction model determines the demand range of the goods to be replenished during the target time period; wherein, the demand prediction model is trained based on the following steps: determining the available-for-stock visits and out-of-stock visits corresponding to the goods to be replenished based on the historical sales and historical inventory status of the goods to be replenished within a preset time window; determining the available-for-stock visits and the historical sales of the goods to be replenished within the statistical period of available-for-stock visits based on the available-for-stock visits. Determine the conversion rate of the product to be replenished; based on the conversion rate and the number of out-of-stock visits, determine the lost sales corresponding to the statistical period of out-of-stock visits for the product to be replenished, and determine the actual sales of the product to be replenished within the statistical period of out-of-stock visits; based on the lost sales and actual sales of the product to be replenished within the statistical period of out-of-stock visits, determine the estimated sales of the product to be replenished within the statistical period of out-of-stock visits; extract the activity features corresponding to the preset time window, and train the demand prediction model based on the historical sales, estimated sales, and activity features of the product to be replenished within the statistical period of in-stock visits.

[0026] In practice, time-period features corresponding to the target time period can be extracted. These features can include basic time information such as date, day of the week, month, quarter, Gregorian holidays, lunar dates, and promotional activity calendars, as well as information such as the activity level, phase, and duration of the corresponding promotional activity. The extracted information can then be combined to form the time-period features corresponding to the target time period. After obtaining these features, they can be input into a demand forecasting model. The model, combined with historical sales patterns of the goods to be replenished, will output the demand range corresponding to the target time period.

[0027] In practical implementation, a demand prediction model can be pre-trained. Specifically, historical business data for the items to be replenished within a preset time window can be collected first. This data can include historical sales, inventory status, and pageviews. Pageviews can be categorized into in-stock and out-of-stock visits based on inventory status. In-stock visits refer to user visits when there is available inventory for the items to be replenished, while out-of-stock visits refer to user visits when the items to be replenished are out of stock. Since sales generated when items are in stock accurately reflect user purchasing behavior, the conversion rate of the items to be replenished can be calculated using in-stock visits and historical sales within the corresponding statistical period to characterize the ability of user visits to convert into actual purchases. Furthermore, since actual sales when items are out of stock are limited by inventory and cannot accurately reflect market demand, the conversion rate can be combined with out-of-stock visits to estimate the sales lost due to stockouts. These lost sales are then overlaid with the actual sales within the corresponding statistical period to obtain the estimated sales of the items to be replenished within that statistical period. This restores the true market demand caused by historical stockouts and avoids underestimation of historical sales due to insufficient inventory.

[0028] In one possible implementation, before calculating the conversion rate, preset high percentile values, such as the 95th percentile, can be calculated for the tempting visits and out-of-stock visits within a preset time window. The 95th percentile indicates that 95% of the visits within the statistical period do not exceed this value, with only a small number exceeding it. Therefore, it can serve as a threshold to distinguish between normal and abnormal visits. For in-stock visits, those exceeding the 95th percentile can be considered abnormal and excluded from conversion rate calculations to avoid interference from promotional activities, abnormal traffic, or fraudulent order practices. For out-of-stock visits, the 95th percentile can be used as an upper limit. When out-of-stock visits exceed this limit, it can be used to calculate lost sales instead of actual visits, thus avoiding overestimation of lost sales due to abnormal visits and improving the accuracy of actual sales calculations.

[0029] Meanwhile, to further reflect the impact of external factors such as holidays and promotional activities on future demand, historical activity information corresponding to each date within a preset time window can be extracted to form activity characteristics. These characteristics can include information reflecting the degree of activity impact, such as activity level, activity stage, and duration. Then, the demand prediction model can be trained using historical sales figures for the items to be replenished within the in-stock visit statistics period, estimated sales figures based on lost sales, and activity characteristics. This allows the model to learn the correlation between historical sales, actual demand, and activity factors. After training, during actual replenishment, only the time-period characteristics corresponding to the target time period need to be input into the demand prediction model to output the demand range for the items to be replenished during the target time period.

[0030] Furthermore, when training the demand prediction model, the characteristics of the training sample items can be extracted, such as the item type, purpose, and whether it is a consumable, to learn the demand patterns corresponding to different item characteristics. Therefore, when subsequently using the demand prediction model to output the demand range for a certain item, the item characteristics can be referenced to output the corresponding demand range. It should be noted that the above-described training method for the demand prediction model is only an illustrative example of a feasible implementation in this invention and does not constitute an undue limitation of the invention. In practical applications, appropriate model architecture and training methods can be selected according to actual needs and circumstances to achieve the desired functionality.

[0031] Another feasible implementation method may not require using a demand forecasting model to determine the demand range. For example, the demand range can be determined based on statistical analysis methods. Specifically, historical sales data of the goods to be replenished within a preset time window can be obtained. After filtering and smoothing outliers from the historical sales, the demand statistical interval corresponding to the target time period can be calculated by combining the activity characteristics, seasonal characteristics, holiday characteristics, and historical sales of the same period in the target time period. This demand statistical interval can then be used as the demand range of the goods to be replenished during the target time period. This embodiment of the invention does not specifically limit the method for determining the demand range of the goods to be replenished; in practical applications, it can be selected according to the actual situation and needs.

[0032] S102: Based on the demand range and preset percentiles, determine multiple first replenishment plans within the demand range, and expand the demand range based on the preset percentiles to obtain multiple second replenishment plans outside the demand range.

[0033] In this embodiment of the invention, multiple first replenishment plans within the demand range are determined based on the demand range and preset percentiles. The demand range is then expanded based on the preset percentiles to obtain multiple second replenishment plans outside the demand range. This includes: obtaining the demand corresponding to multiple different preset percentiles within the demand range, using each demand as a corresponding replenishment quantity to generate multiple first replenishment plans; expanding the demand range towards the upper and lower limits according to a preset expansion strategy based on the demand difference between different percentiles within the demand range to determine multiple first expansion plans outside the demand range; generating second expansion plans based on promotional information corresponding to the target time period and the guaranteed replenishment quantity within the target time period; and using the first expansion plans and the second expansion plans as multiple second replenishment plans.

[0034] In practical implementation, after determining the demand range of the goods to be replenished within the target time period, to avoid overly simplistic decision-making due to relying solely on a single demand forecast, multiple pre-defined quantiles can be used to extract the demand corresponding to each quantile within the demand range. Each demand is then used as a different replenishment quantity to generate multiple first replenishment plans. Different quantiles correspond to different demand levels; for example, lower quantiles correspond to more conservative replenishment plans, middle quantiles to conventional replenishment plans, and higher quantiles to relatively aggressive replenishment plans. This allows multiple first replenishment plans to cover business scenarios corresponding to different replenishment levels within the demand range. Furthermore, as... Figure 2As shown, considering the potential for promotional activities, unforeseen events, and abnormal fluctuations in market demand in actual business operations, simply using replenishment plans within the demand range may not cover all actual needs. Therefore, the demand difference between different preset percentiles within the demand range can be used as an expansion basis. Following preset rules, the range can be extended towards both the upper and lower limits, generating multiple first-level expansion plans outside the demand range. Downward expansion generates replenishment plans below the normal demand level to adapt to scenarios such as declining demand and slowing sales; upward expansion generates replenishment plans above the normal demand level to adapt to scenarios such as rapid demand growth or sales surges. For example, when the demand at multiple percentiles within the demand range is 80, 100, 120, 140, and 160 units respectively, the demand difference between adjacent percentiles can be used to further expand upwards to obtain replenishment plans of 180 and 200 units, while simultaneously expanding downwards to obtain replenishment plans of 60 and 40 units, allowing the replenishment plans to exceed the normal demand range. In addition, the replenishment quantity can be determined by combining the promotional information corresponding to the target period, and a second expansion plan can be generated based on the replenishment quantity. The replenishment quantity can be determined by comprehensively considering factors such as the promotional activity level, expected activity traffic, average daily demand, inventory preparation cycle, and historical peak demand during the target period, to ensure that supply can still meet demand during large-scale promotional activities or concentrated demand surges. For example, when the target period corresponds to a large-scale promotional activity such as "Double Eleven," the replenishment quantity can be appropriately increased based on the expected demand growth during the activity period, allowing the second expansion plan to further cover extreme high-demand scenarios beyond the expected demand range. Ultimately, the first and second expansion plans can be combined as multiple second replenishment plans, forming a candidate replenishment plan set together with multiple first replenishment plans. This ensures that replenishment decisions can cover both regular business scenarios and special scenarios such as abnormal demand fluctuations or promotional surges, improving the applicability and robustness of the replenishment plan.

[0035] Specifically, when determining multiple second replenishment plans, the expansion step size can be determined based on the demand corresponding to different preset quantiles within the demand range. Assuming the preset quantiles include P10, P50, and P90, the difference between the demand corresponding to the middle quantile P50 and the demand corresponding to the lowest quantile P10 can be used as the downward expansion step size. The calculation formula is as follows:

[0036] in, This can be used to ensure that the expansion compensation is not less than 0. After obtaining the downward expansion step size, it can be expanded step-by-step based on the demand of P10 to obtain the first and second low-level expansion replenishment schemes. The calculation method is as follows:

[0037] in, A preset downward expansion coefficient can be used to control the expansion range; it can then be reused. The function applies a non-negativity constraint to the expanded result. When the expanded replenishment quantity is less than zero, it is corrected to zero, thereby generating a replenishment plan suitable for scenarios where demand decreases or no replenishment is required.

[0038] Similarly, the difference between the demand corresponding to the high quantile P90 and the demand corresponding to the middle quantile P50 is used as the upward expansion step size, and its calculation formula can be:

[0039] Based on the demand corresponding to the highest quantile, the replenishment plan is generated by progressively expanding upwards according to the expansion step size, resulting in the first and second highest-level replenishment plans. The calculation method is as follows:

[0040] in, A preset upward expansion coefficient can be used to control the extent of upward expansion. To further ensure the supply capacity of goods to be replenished during promotional activities, demand surges, or other special scenarios, when generating multiple second replenishment plans, the replenishment quantity can be determined based on the promotional information corresponding to the target time period, and a replenishment plan can be generated based on the replenishment quantity. Specifically, the replenishment quantity can be calculated first based on the demand quantity P90 corresponding to the highest preset quantile within the demand range, the average daily predicted sales volume of the goods to be replenished, the maximum surge coefficient, and the preparation cycle. The maximum surge coefficient characterizes the maximum possible increase multiple of demand relative to normal demand during promotional activities, holidays, or other special scenarios, and can be preset based on historical sales growth during promotional activities or business experience. The formula for calculating the replenishment quantity can be as follows:

[0041] The first item, P90×1.5, represents reserving a certain percentage of safety stock on top of the usual high demand level to cover the impact of forecast errors or small increases in demand; the second item... This represents the theoretical supply demand calculated based on the expected average daily sales volume within the target period, the maximum demand growth multiple, and the duration of the entire preparation cycle. It is used to cover inventory needs during large-scale promotional events or periods of sustained demand surges. The larger of the two calculated values ​​can be used as the supply replenishment quantity, and a supply replenishment plan can be generated based on this quantity. Because the supply replenishment plan comprehensively considers multiple factors such as demand forecast results, demand surge potential, and preparation cycle, it avoids the problem of insufficient supply capacity caused by relying solely on historical demand forecasts. This allows the replenishment plan to further cover extreme high-demand scenarios, improving the reliability and applicability of replenishment decisions while ensuring supply capacity.

[0042] S103: Determine the inventory change sequence of the first replenishment plan and the second replenishment plan within the target period, and determine the expected revenue corresponding to each first replenishment plan and the second replenishment plan based on the inventory change sequence, so as to determine the target replenishment plan for the goods to be replenished within the target period.

[0043] In this embodiment of the invention, determining the inventory change sequence of the first replenishment plan and the second replenishment plan within a target period, and determining the expected revenue corresponding to each first replenishment plan and the second replenishment plan based on the inventory change sequence, includes: simulating the expected sales volume, expected inventory volume, and expected stockout volume corresponding to each first replenishment plan and the second replenishment plan based on the replenishment quantity and inventory information corresponding to each first replenishment plan and the second replenishment plan, and generating the inventory change sequence of each first replenishment plan and the second replenishment plan within the target period; determining the inventory cost adjustment coefficient corresponding to each first replenishment plan and the second replenishment plan based on the time relationship between the expected arrival time corresponding to each first replenishment plan and the second replenishment plan and the promotion time corresponding to the target period; and determining the expected revenue corresponding to each first replenishment plan and the second replenishment plan based on the inventory change sequence and the inventory cost adjusted based on the inventory cost adjustment coefficient.

[0044] In practical implementation, after generating multiple first replenishment plans and multiple second replenishment plans, inventory change simulations can be further performed on each replenishment plan. Specifically, the replenishment quantity corresponding to each replenishment plan is used as the initial replenishment quantity. Combined with inventory information such as the current inventory, in-transit inventory, projected demand, and lead time of the goods to be replenished, the inventory consumption process is simulated according to the demand changes at each time point within the target period. This yields the projected sales volume, projected inventory volume, and projected stockout volume for each replenishment plan, and generates the corresponding inventory change sequence in chronological order. Here, projected sales volume represents the quantity of goods that can actually be sold within the target period, projected inventory volume represents the remaining inventory quantity at each time point, and projected stockout volume represents the quantity of market demand that cannot be met due to insufficient inventory.

[0045] Furthermore, inventory costs can be dynamically adjusted based on the time relationship between the expected arrival time of each candidate replenishment plan and the promotional period corresponding to the target time. Specifically, the relative time relationship between the expected arrival time and the start time of the promotion can be determined first. When the expected arrival time is earlier than or during the promotional period, it indicates that the replenished goods can participate in the promotional sales. In this case, the inventory cost adjustment coefficient can be reduced to decrease the impact of inventory holding costs on revenue calculation and encourage an appropriate increase in inventory levels before the promotion. When the expected arrival time is later than the end time of the promotion, it indicates that the replenished goods cannot participate in the promotional sales, which may easily lead to post-promotion inventory backlog. In this case, the inventory cost adjustment coefficient can be increased, for example, by adjusting the inventory cost to ten times the normal inventory cost, to significantly increase the proportion of inventory costs in expected revenue, thereby imposing a greater cost penalty on replenishment plans that arrive after the promotion ends. Finally, based on the expected sales volume, expected inventory volume, and expected stockout volume corresponding to each time node in the inventory change sequence, and combined with the inventory cost adjusted by the inventory cost adjustment coefficient, the expected revenue corresponding to each replenishment plan can be calculated, and the expected revenue can be used as an important basis for determining the target replenishment plan.

[0046] For example, for a specific item requiring replenishment, assume three replenishment plans are generated within a target period (e.g., 7 days): Plan A replenishes 100 units, Plan B replenishes 150 units, and Plan C replenishes 200 units, with an initial inventory of 90 units. The system, based on historical demand forecasts, calculates the daily demand for these 7 days as [20, 30, 40, 35, 25, 30, 20]. Taking Plan A as an example, during the simulated inventory change process, demand is gradually reduced daily. When inventory reaches zero, subsequent demand is recorded as a shortage. For instance, if inventory is exhausted on day 7, then 10 units will be out of stock on the last day. Thus, the projected sales volume for Plan A is 100 units, and the shortage is 10 units. Furthermore, considering the projected arrival time is day 3 and the promotional activity occurs from day 4 to day 6, Plan A can partially cover the promotional period; therefore, the inventory cost adjustment coefficient is set to 0.2. Similarly, the simulation of Option B is performed. Since it fully covers the promotion period, the inventory cost coefficient is 0.2. Option C has a large amount of remaining inventory and the goods arrive later than the end of the promotion. Therefore, the inventory cost coefficient is increased to a 10-fold penalty to reflect the risk of unsold goods after the promotion. Finally, the expected revenue is calculated for each option to confirm the target replenishment plan.

[0047] In this embodiment of the invention, before determining the target replenishment plan for the goods to be replenished in the target time period, the method further includes: determining candidate replenishment plans based on the expected revenue corresponding to each first replenishment plan and each second replenishment plan, and pushing the candidate replenishment plans to the reviewer; receiving adjustment information returned by the reviewer corresponding to the candidate replenishment plans, determining the adjustment range and reason for the replenishment quantity value in the adjustment information; using the adjusted candidate replenishment plan as the target replenishment plan, and optimizing and training the demand prediction model based on the adjustment information.

[0048] In practical implementation, since the entity executing the present invention cannot refer to certain real-world situations when generating replenishment plans, such as competitor stockouts, platform traffic support, and signing e-commerce live streaming agreements, a replenishment plan based on expected revenue can be sent to the reviewer for review before determining the target replenishment plan for the items to be replenished, in order to take into account the aforementioned situations that may cause changes in sales. Specifically, all candidate replenishment plans can be uniformly evaluated and ranked based on the expected revenue corresponding to each first replenishment plan and each second replenishment plan, thereby obtaining a set of candidate replenishment plans. Then, the candidate replenishment plans, along with their corresponding replenishment quantities, inventory change sequences, and expected revenue information, can be pushed to the reviewer, who can be a purchasing or sales personnel or strategy management personnel, for manual review and adjustment of the generated replenishment plans. During the review process, the reviewing party can adjust the replenishment quantities in candidate replenishment plans based on business experience, market judgment, or temporary promotional information, and return adjustment information corresponding to each candidate replenishment plan. This adjustment information should at least include the magnitude of the adjustment and the reason for the adjustment, such as an increase in replenishment quantity due to a sudden promotional activity or a decrease in replenishment quantity due to inventory pressure. After receiving the adjustment information, the system can redetermine the target replenishment plan based on the adjusted replenishment quantities.

[0049] Meanwhile, in order to achieve continuous optimization of the model, adjustment information can be introduced into the training process of the demand prediction model as feedback samples. The adjustment range of replenishment quantity can be used as a supervision signal to correct the model's estimation bias of the demand range, while the reason for adjustment can be used as auxiliary semantic information to enhance the model's ability to identify different business scenarios such as promotions, slow-moving goods, or sudden demand, thereby improving the accuracy and stability of future replenishment decisions.

[0050] In this embodiment of the invention, the method further includes: when there are at least two items to be replenished, obtaining replenishment quantity constraints corresponding to at least two items to be replenished; determining the total replenishment quantity according to the target replenishment plan corresponding to each item to be replenished; in response to the total replenishment quantity being greater than the target replenishment quantity corresponding to the replenishment quantity constraint, calculating the revenue increment corresponding to the unit replenishment quantity of the target replenishment plan corresponding to each item to be replenished, and sorting each item to be replenished according to the revenue increment corresponding to the unit replenishment quantity; adjusting the replenishment quantity of the target replenishment plan corresponding to at least one item to be replenished according to the sorting result, so that the adjusted total replenishment quantity satisfies the replenishment quantity constraint.

[0051] In practice, when there are at least two items awaiting replenishment, the replenishment quantity constraints for each item can be obtained first. These constraints can be global resource limitations such as the total budgeted replenishment quantity, warehouse capacity limit, or logistics transportation capacity limit set by procurement and sales, used to constrain the overall replenishment scale. Then, based on the target replenishment plan for each item, the replenishment quantities of all items can be aggregated to obtain the total replenishment quantity under the current plan combination, and compared with the replenishment quantity constraints. If the total replenishment quantity exceeds the target replenishment quantity corresponding to the replenishment quantity constraint, it indicates that the current replenishment plan combination has a resource over-allocation problem and requires global adjustment. At this point, the revenue increment per unit replenishment quantity for each item can be calculated for the target replenishment plan, used to measure the marginal contribution capability of different replenishment priorities. Then, the items awaiting replenishment can be sorted based on the revenue increment per unit replenishment quantity, so that items with higher marginal revenue receive higher replenishment priority. After sorting, the replenishment quantity of the target replenishment plan corresponding to at least one item to be replenished can be adjusted according to the sorting results. That is, the replenishment quantity of high-profit incremental items is retained first, and the replenishment quantity of low-profit incremental items is gradually reduced.

[0052] In addition to the aforementioned situation where the total replenishment volume exceeds the replenishment volume constraint, there can also be situations where the total replenishment volume is less than the replenishment volume constraint. In practice, when the total replenishment volume of multiple replenishment plans for different items is less than the target replenishment volume corresponding to the replenishment volume constraint, it indicates that the current replenishment plan combination is not fully utilizing available replenishment resources. In this case, the minimum safe replenishment volume for each item can be used as the basic replenishment plan, such as the replenishment volume at a lower percentile within the demand range, to ensure that each item meets the basic spot rate requirement. Based on this, the ratio between the expected revenue increment from increasing the current replenishment volume by one percentile for each item can be calculated to represent the marginal revenue capability of each unit of replenishment resource investment. Then, the items can be sorted according to their marginal revenue capability, and the replenishment volume of the target replenishment plan corresponding to the items with higher marginal revenue should be increased first, gradually expanding from lower percentiles to higher percentiles, thereby gradually increasing the overall replenishment volume. If, after completing the step-by-step expansion based on quantiles, the total replenishment volume still fails to reach the target replenishment volume corresponding to the replenishment volume constraint, then further screening of replenishment items based on best-selling attributes can be conducted. Items with the highest sales ranking can be prioritized for replenishment, and the remaining replenishment quota can be allocated according to their demand share, with their replenishment volume adjusted proportionally to bring the overall replenishment volume as close as possible to the upper limit of the replenishment volume constraint. This ensures the rationality of the replenishment structure while fully utilizing replenishment resources, making the replenishment plan as close as possible to the actual demand distribution while meeting the constraints, thereby improving overall inventory utilization efficiency and sales coverage.

[0053] According to a second aspect of the embodiments of the present invention, such as Figure 3 As shown, an inventory information processing device 300 is provided, comprising: The range determination module 301 is used to determine the range of demand for goods to be replenished corresponding to the target time period. The scheme generation module 302 is used to determine multiple first replenishment schemes within the demand range based on the demand range and preset quantiles, and to expand the demand range based on the preset quantiles to obtain multiple second replenishment schemes outside the demand range. The scheme determination module 303 is used to determine the inventory change sequence of the first replenishment scheme and the second replenishment scheme within the target period, and to determine the expected revenue corresponding to each first replenishment scheme and the second replenishment scheme based on the inventory change sequence, so as to determine the target replenishment scheme for the goods to be replenished within the target period.

[0054] Optionally, the range determination module 301 is specifically used for: The time period characteristics of the target time period are input into the pre-trained demand prediction model so that the demand prediction model can determine the demand range of the goods to be replenished during the target time period. The demand forecasting model was trained based on the following steps: Based on the historical sales and historical inventory status of the items to be replenished within a preset time window, determine the number of visits corresponding to the items that are in stock and the number of visits that are out of stock for the items to be replenished. The conversion rate of the items to be replenished is determined based on the number of visits to in-stock items and the historical sales volume of the items to be replenished within the statistical period of the in-stock visits. Based on the conversion rate and the number of out-of-stock visits, determine the lost sales corresponding to the out-of-stock visit period for the items to be replenished, and determine the actual sales of the items to be replenished within the out-of-stock visit period. Based on the lost sales and actual sales of the items to be replenished during the statistical period of out-of-stock visits, determine the estimated sales of the items to be replenished during the statistical period of out-of-stock visits. The activity features corresponding to the preset time window are extracted, and the demand prediction model is trained based on the historical sales, estimated sales and activity features of the goods to be replenished within the statistical period of the number of visits to the stock.

[0055] Optionally, the solution generation module 302 is specifically used for: Get the demand corresponding to multiple different preset quantiles within the demand range, use each demand as the corresponding replenishment quantity, and generate multiple first replenishment plans. Based on the demand difference corresponding to different quantiles within the demand range, the expansion is carried out in the upper and lower limits of the demand range according to the preset expansion strategy, and multiple first expansion schemes located outside the demand range are determined. Based on the promotional information corresponding to the target period and the determination of the supply replenishment quantity within the target period, a second extended plan is generated based on the supply replenishment quantity; The first and second expansion plans are used as multiple second replenishment plans.

[0056] Optionally, the scheme determination module 303 is specifically used for: Based on the replenishment quantity and inventory information corresponding to each first replenishment plan and each second replenishment plan, the expected sales volume, expected inventory volume and expected stockout volume corresponding to each first replenishment plan and each second replenishment plan are simulated, and the inventory change sequence of each first replenishment plan and each second replenishment plan within the target period is generated. Based on the time relationship between the expected arrival time of each first replenishment plan and each second replenishment plan and the promotion time corresponding to the target period, determine the inventory cost adjustment coefficient corresponding to each first replenishment plan and each second replenishment plan; Based on the inventory change sequence and the inventory cost adjusted by the inventory cost adjustment coefficient, determine the expected revenue corresponding to each first replenishment plan and each second replenishment plan.

[0057] Optionally, the scheme determination module 303 is also used for: Based on the expected revenue corresponding to each first replenishment plan and each second replenishment plan, candidate replenishment plans are determined and pushed to the reviewer. Receive adjustment information from the reviewer that corresponds to the candidate replenishment plan, and determine the adjustment range and reason for the adjustment of the replenishment quantity value in the adjustment information; The adjusted candidate replenishment plan is used as the target replenishment plan, and the demand forecasting model is optimized and trained based on the adjustment information.

[0058] Optionally, the scheme determination module 303 is also used for: If there are at least two items to be replenished, obtain the replenishment quantity constraints corresponding to at least two items to be replenished; Determine the total replenishment quantity based on the target replenishment plan corresponding to each item to be replenished; In response to the total replenishment quantity exceeding the target replenishment quantity corresponding to the replenishment quantity constraint, calculate the revenue increment per unit replenishment quantity of the target replenishment plan for each item to be replenished, and sort each item to be replenished according to the revenue increment per unit replenishment quantity. Based on the sorting results, the replenishment quantity of the target replenishment plan corresponding to at least one item to be replenished is adjusted so that the adjusted total replenishment quantity meets the replenishment quantity constraint.

[0059] According to a third aspect of the present invention, an electronic device for processing inventory information is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the present invention.

[0060] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0061] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0062] Figure 4 An exemplary system architecture 400 is shown that can be applied to the inventory information processing method or inventory information processing apparatus implemented by the present invention.

[0063] like Figure 4As shown, system architecture 400 may include terminal devices 401, 402, and 403, a network 404, and a server 405. Network 404 serves as the medium for providing communication links between terminal devices 401, 402, and 403 and server 405. Network 404 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0064] Users can use terminal devices 401, 402, and 403 to interact with server 405 via network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, and 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0065] Terminal devices 401, 402, and 403 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0066] Server 405 can be a server that provides various services, such as a back-end management server that supports shopping websites browsed by users using terminal devices 401, 402, and 403 (for example only). The back-end management server can process received inventory information processing requests and return the processing results (for example only) to the terminal devices.

[0067] It should be noted that the inventory information processing method provided in this embodiment of the invention is generally executed by server 405, and correspondingly, the inventory information processing device is generally located in server 405. The inventory information processing method provided in this embodiment of the invention can also be executed by terminal devices 401, 402, and 403, and correspondingly, the inventory information processing device can be located in terminal devices 401, 402, and 403.

[0068] It should be understood that Figure 4 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0069] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing a terminal device of the present invention. Figure 5 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0070] like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0071] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0072] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0073] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-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 a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0075] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor. For example, a processor may include a range determination module, a scheme generation module, and a scheme determination module. The names of these modules do not necessarily limit the module itself; for example, the range determination module may also be described as "a module for determining the demand range of goods to be replenished corresponding to a target time period."

[0076] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, implement the following method: determining the demand range of the goods to be replenished corresponding to a target time period; determining multiple first replenishment schemes within the demand range based on the demand range and a preset quantile, and expanding the demand range based on the preset quantile to obtain multiple second replenishment schemes outside the demand range; determining the inventory change sequence of the first and second replenishment schemes within the target time period, and determining the expected revenue corresponding to each first and second replenishment scheme based on the inventory change sequence, thereby determining the target replenishment scheme for the goods to be replenished during the target time period.

[0077] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for processing inventory information, characterized in that, include: Determine the range of demand for the goods to be replenished corresponding to the target time period; Based on the demand range and the preset percentile, multiple first replenishment plans within the demand range are determined, and the demand range is expanded based on the preset percentile to obtain multiple second replenishment plans outside the demand range. Determine the inventory change sequence of the first replenishment plan and the second replenishment plan within the target period, and determine the expected revenue corresponding to each first replenishment plan and the second replenishment plan based on the inventory change sequence, so as to determine the target replenishment plan for the goods to be replenished within the target period.

2. The method according to claim 1, characterized in that, Determine the range of demand for the goods to be replenished corresponding to the target time period, including: The time period characteristics of the target time period are input into a pre-trained demand prediction model so that the demand prediction model can determine the demand range of the goods to be replenished during the target time period. The demand prediction model is trained based on the following steps: Based on the historical sales and historical inventory status of the items to be replenished within a preset time window, determine the number of visits with and without stock corresponding to the items to be replenished. The conversion rate of the item to be replenished is determined based on the number of in-stock visits and the historical sales volume of the item to be replenished within the statistical period of the in-stock visits. Based on the conversion rate and the number of out-of-stock visits, determine the lost sales of the items to be replenished during the statistical period of out-of-stock visits, and determine the actual sales of the items to be replenished during the statistical period of out-of-stock visits. Based on the lost sales and actual sales of the items to be replenished during the statistical period of out-of-stock visits, the estimated sales of the items to be replenished during the statistical period of out-of-stock visits are determined. The activity features corresponding to the preset time window are extracted, and the demand prediction model is trained based on the historical sales of the items to be replenished within the statistical period of available visits, the estimated sales, and the activity features.

3. The method according to claim 1, characterized in that, Based on the demand range and preset percentiles, multiple first replenishment plans within the demand range are determined, and the demand range is expanded based on the preset percentiles to obtain multiple second replenishment plans outside the demand range, including: Obtain the demand corresponding to multiple different preset quantiles within the demand range, and use each demand as the corresponding replenishment quantity to generate multiple first replenishment plans. Based on the demand difference corresponding to different quantiles within the demand range, the expansion is carried out in the upper and lower limits of the demand range according to a preset expansion strategy to determine multiple first expansion schemes located outside the demand range. Based on the promotional information corresponding to the target time period, and the determination of the supply replenishment quantity within the target time period, a second extended solution is generated based on the supply replenishment quantity; The first expansion scheme and the second expansion scheme are used as the plurality of second replenishment schemes.

4. The method according to any one of claims 1-3, characterized in that, Determine the inventory change sequence of the first replenishment plan and the second replenishment plan within the target period, and determine the expected revenue corresponding to each of the first replenishment plan and the second replenishment plan based on the inventory change sequence, including: Based on the replenishment quantity and inventory information corresponding to each first replenishment plan and each second replenishment plan, the expected sales volume, expected inventory volume and expected stockout volume corresponding to each first replenishment plan and each second replenishment plan are simulated, and the inventory change sequence of each first replenishment plan and each second replenishment plan within the target period is generated. Based on the time relationship between the expected arrival time of each first replenishment plan and each second replenishment plan and the promotion time corresponding to the target period, determine the inventory cost adjustment coefficient corresponding to each first replenishment plan and each second replenishment plan; Based on the inventory change sequence and the inventory cost adjusted based on the inventory cost adjustment coefficient, the expected revenue corresponding to each first replenishment plan and each second replenishment plan is determined.

5. The method according to claim 2, characterized in that, Before determining the target replenishment plan for the goods to be replenished during the target time period, the following steps are also included: Based on the expected revenue corresponding to each of the first replenishment plans and each of the second replenishment plans, candidate replenishment plans are determined and pushed to the reviewer. Receive adjustment information returned by the reviewer that corresponds to the candidate replenishment plan, and determine the adjustment range and reason for the replenishment quantity value in the adjustment information; The adjusted candidate replenishment plan is used as the target replenishment plan, and the demand prediction model is optimized and trained based on the adjustment information.

6. The method according to claim 4 or 5, characterized in that, The method further includes: If there are at least two items to be replenished, obtain the replenishment quantity constraints corresponding to the at least two items to be replenished; Determine the total replenishment quantity based on the target replenishment plan corresponding to each item to be replenished; In response to the total replenishment quantity being greater than the target replenishment quantity corresponding to the replenishment quantity constraint, the revenue increment corresponding to the unit replenishment quantity of the target replenishment plan for each item to be replenished is calculated, and each item to be replenished is sorted according to the revenue increment corresponding to the unit replenishment quantity. Based on the sorting results, the replenishment quantity of the target replenishment plan corresponding to at least one item to be replenished is adjusted so that the adjusted total replenishment quantity meets the replenishment quantity constraint.

7. An inventory information processing device, characterized in that, include: The range determination module is used to determine the range of demand for goods to be replenished corresponding to the target time period; The solution generation module is used to determine multiple first replenishment solutions within the demand range based on the demand range and preset percentiles, and to expand the demand range based on the preset percentiles to obtain multiple second replenishment solutions outside the demand range. The scheme determination module is used to determine the inventory change sequence of the first replenishment scheme and the second replenishment scheme within the target period, and to determine the expected revenue corresponding to each first replenishment scheme and the second replenishment scheme based on the inventory change sequence, so as to determine the target replenishment scheme for the goods to be replenished within the target period.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images