Inventory management method and system based on iterative approximation
By dynamically adjusting the IT operations and maintenance spare parts inventory target through iterative approximation model, the problem of low prediction accuracy of static threshold method is solved, realizing more efficient and accurate inventory management, adapting to the uncertainty and volatility of spare parts consumption, and reducing operation and maintenance costs.
Patent Information
- Application Number
- CN202511228446.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-29
- Publication Date
- 2025-12-12
AI Technical Summary
Existing IT operations and maintenance spare parts inventory management methods rely on static threshold methods, resulting in low prediction accuracy and an inability to effectively cope with the uncertainty and volatility of spare parts consumption, thus affecting the accuracy and efficiency of inventory management.
An iterative approximation-based inventory management method is adopted. By acquiring historical consumption data, the long-term average consumption is calculated. Combined with the iterative approximation model, the inventory target is dynamically adjusted to generate suggested purchase quantities and inventory reminder information, thereby achieving self-optimization of the inventory target.
It improves the accuracy and efficiency of inventory management, dynamically adjusts inventory targets to adapt to the uncertainty of spare parts consumption, reduces operation and maintenance costs, and improves emergency response efficiency.
Smart Images
Figure CN121119908A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of inventory management technology, and specifically to an inventory management method and system based on iterative approximation. Background Technology
[0002] To ensure high availability of IT systems, reduce operational costs, and improve emergency response efficiency, scientific and reasonable inventory management of IT maintenance spare parts is necessary. Currently, inventory management of IT maintenance spare parts mainly relies on the static threshold method to formulate replenishment strategies. This involves setting a fixed minimum and maximum inventory threshold for each spare part. Procurement is triggered when the inventory falls below the minimum threshold. This method is simple to implement, but the thresholds are usually based on historical experience or rough estimates and rarely change after being set.
[0003] Statistical forecasting methods can use time series analysis models, such as moving averages, exponential smoothing, or ARIMA models, to predict future spare parts demand. However, due to the low frequency and high randomness of IT spare parts inventory management needs, IT spare parts consumption is usually a sudden and discrete event, which does not meet the stationarity assumption required by traditional time series models, resulting in extremely low forecast accuracy.
[0004] Therefore, there is an urgent need for an inventory management method to improve the accuracy and efficiency of IT operations and maintenance spare parts inventory management. Summary of the Invention
[0005] To address the shortcomings of existing technologies, this invention provides an inventory management method and system based on iterative approximation, which aims to generate inventory targets for spare parts, thereby adapting to the uncertainty and volatility of spare parts consumption and improving the accuracy and efficiency of inventory management.
[0006] This invention discloses an inventory management method based on iterative approximation, comprising:
[0007] Step S1: Obtain historical consumption data of the spare parts to be managed, and calculate the long-term average consumption of the spare parts to be managed based on the historical consumption data.
[0008] Step S2: Based on the long-term average consumption, calculate the first inventory target for the spare parts to be managed. The first inventory target is used to characterize the inventory target of the spare parts to be managed in the first management cycle.
[0009] Step S3: Obtain the first actual consumption quantity of the spare parts to be managed within the first management cycle;
[0010] Step S4: Based on the first actual consumption quantity and the long-term average consumption quantity, calculate the first consumption deviation of the spare parts to be managed in the first management cycle;
[0011] Step S5: Input the first consumption deviation and the first inventory target into the iterative approximation model to generate the second inventory target. The second inventory target is used to characterize the inventory target of the spare parts to be managed in the second management cycle. The second management cycle is the next iteration cycle of the first management cycle. The iterative approximation model generates the second inventory target iteratively based on the periodic deviation and the learning rate.
[0012] Step S6: Generate inventory management information for spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity.
[0013] Preferably, the inventory management method based on iterative approximation further includes:
[0014] Step S7: Use the second inventory target as the first inventory target to update the first inventory target;
[0015] Step S8: Obtain the second actual consumption quantity of the spare parts to be managed in the second management cycle, and use the second actual consumption quantity as the first actual consumption quantity to update the first actual consumption quantity;
[0016] Step S9: Repeat steps S4 to S6 to generate inventory management information for spare parts to be managed in the next iteration cycle based on the updated first inventory target and the updated first actual consumption quantity.
[0017] Preferably, the historical consumption data of the spare parts to be managed is obtained, and the long-term average consumption of the spare parts to be managed is calculated based on the historical consumption data, including:
[0018] Query the historical consumption data of spare parts to be managed in the asset management database within the first preset period;
[0019] The average consumption of spare parts to be managed is calculated based on historical consumption data within the management cycle to obtain the long-term average consumption. The management cycle is shorter than the first preset cycle.
[0020] Preferably, based on long-term average consumption, the first inventory target for spare parts to be managed is calculated, including:
[0021] Obtain management parameters, including procurement lead time, service level coefficient, and demand volatility coefficient;
[0022] Based on management parameters and long-term average consumption, the first inventory target for the spare parts to be managed is calculated using the inventory target calculation formula, which is shown below:
[0023]
[0024] Where S1 represents the first inventory target, D avgLT represents the long-term average consumption, Z represents the lead time for procurement, and σ represents the service level coefficient. D This represents the demand volatility coefficient.
[0025] Preferably, based on the first actual consumption quantity and the long-term average consumption quantity, the first consumption deviation of the spare parts to be managed in the first management cycle is calculated, including:
[0026] The difference between the first actual consumption quantity and the long-term average consumption quantity is calculated to obtain the first consumption deviation.
[0027] Preferably, the iterative approximation model generates the second inventory target using an iterative formula, as shown below:
[0028] S2 = S1 + α·E1,
[0029] Where S2 represents the second inventory target, α represents the preset learning rate, and E1 represents the first consumption deviation.
[0030] Preferably, the iterative approximation model adjusts the second inventory target based on the first actual consumption quantity and the long-term average consumption quantity, including:
[0031] If the first actual consumption quantity is greater than the long-term average consumption quantity, the second inventory target will be increased according to the preset adjustment parameters.
[0032] If the first actual consumption quantity is less than the long-term average consumption quantity, the second inventory target will be lowered according to the preset adjustment parameters.
[0033] If the first actual consumption quantity equals the long-term average consumption quantity, then the second inventory target remains unchanged.
[0034] Preferably, the inventory management information includes the suggested purchase quantity;
[0035] Based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity, generate inventory management information for spare parts to be managed, including:
[0036] The recommended purchase quantity is calculated using the purchase quantity calculation formula, which is shown below:
[0037] P1 = S2 - (R1 - C1),
[0038] Where P1 represents the recommended purchase quantity, C1 represents the actual consumption quantity in the first period, and R1 represents the actual inventory quantity.
[0039] Preferably, the inventory management method based on iterative approximation further includes:
[0040] Generate a purchase order based on the suggested purchase quantity;
[0041] Inventory reminders are generated based on purchase orders.
[0042] This invention discloses an inventory management system based on iterative approximation, used to execute an inventory management method based on iterative approximation. The inventory management system based on iterative approximation includes:
[0043] The data acquisition module is configured to: acquire historical consumption data of spare parts to be managed, and calculate the long-term average consumption of spare parts to be managed based on the historical consumption data;
[0044] The initial configuration module is configured to: calculate the first inventory target of the spare parts to be managed based on the long-term average consumption. The first inventory target is used to characterize the inventory target of the spare parts to be managed in the first management cycle.
[0045] The deviation calculation module is configured to: obtain the first actual consumption quantity of the spare parts to be managed in the first management cycle; and calculate the first consumption deviation of the spare parts to be managed in the first management cycle based on the first actual consumption quantity and the long-term average consumption quantity.
[0046] The target generation module is configured to input the first consumption deviation and the first inventory target into the iterative approximation model to generate a second inventory target. The second inventory target is used to characterize the inventory target of the spare parts to be managed in the second management cycle. The second management cycle is the next iteration cycle of the first management cycle. The iterative approximation model iteratively generates the second inventory target based on the periodic deviation and the learning rate.
[0047] The inventory management module is configured to generate inventory management information for spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity.
[0048] The iterative update module is configured to: use the second inventory target as the first inventory target to update the first inventory target; obtain the second actual consumption quantity of the spare parts to be managed in the second management cycle, and use the second actual consumption quantity as the first actual consumption quantity to update the first actual consumption quantity; and generate inventory management information for the spare parts to be managed in the next iteration cycle based on the updated first inventory target and the updated first actual consumption quantity.
[0049] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0050] By employing an iterative approximation model, inventory targets are dynamically adjusted based on actual spare parts consumption, avoiding the inflexibility of static threshold methods and overcoming the insufficient prediction accuracy of traditional time series forecasting models under conditions of low-frequency and high-randomness spare parts demand. Furthermore, by generating suggested purchase quantities and inventory alerts, the automation and responsiveness of inventory management are improved, thereby helping enterprises achieve more efficient and accurate spare parts inventory management. Attached Figure Description
[0051] Figure 1 A flowchart illustrating the iterative approximation-based inventory management method provided by this invention;
[0052] Figure 2 This is a schematic diagram of the structure of the inventory management system based on iterative approximation provided by the present invention. Detailed Implementation
[0053] 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, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0054] The present invention will now be described in further detail with reference to the accompanying drawings.
[0055] like Figure 1 As shown, this embodiment of the invention provides an inventory management method based on iterative approximation, which is applied to an inventory management system based on iterative approximation. The inventory management method includes the following steps.
[0056] S1. Obtain historical consumption data of the spare parts to be managed, and calculate the long-term average consumption of the spare parts to be managed based on the historical consumption data.
[0057] In this embodiment of the invention, the inventory management system obtains historical consumption data of spare parts to be managed from the asset management database. For example, the spare parts to be managed may be specific models of SSD hard drives or memory modules, and the historical consumption data may include information such as the quantity and time of consumption of the spare parts to be managed within a first preset period.
[0058] Next, the average consumption of the spare parts to be managed during the management cycle is calculated based on historical consumption data to obtain the long-term average consumption. The management cycle is shorter than the first preset cycle.
[0059] It should be noted that the long-term average consumption is used to characterize the average spare parts consumption calculated for each iteration period over a relatively long time span. For example, the first preset period is 52 weeks, and the management period is 13 weeks. The average spare parts consumption of the spare parts to be managed is calculated for each management period (13 weeks) within the 52 weeks, thus obtaining the long-term average consumption.
[0060] For example, if the first preset period is 52 weeks, the management period is 13 weeks, and the SSD consumption in the first preset period is 20 units, then the long-term average consumption of the SSD in each management period is 5 units.
[0061] In some embodiments, the long-term average consumption can also be represented by a weighted moving average. This application does not specifically limit the calculation method of the long-term average consumption, as long as it is an indicator that can measure the central trend of demand.
[0062] Step S2: Calculate the first inventory target for spare parts to be managed based on the long-term average consumption.
[0063] In this embodiment of the invention, the first inventory target is used to characterize the inventory target of the spare parts to be managed within the first management cycle. Specifically, in calculating the first inventory target, management parameters are first obtained, including procurement lead time, service level coefficient, and demand fluctuation coefficient.
[0064] Among these parameters, procurement lead time characterizes the average time required from order placement to spare parts delivery. The service level coefficient characterizes the probability that inventory will meet demand, reflecting the inventory system's responsiveness to changes in demand. The demand volatility coefficient quantifies the uncertainty of spare parts demand, characterizing its fluctuations. These management parameters play a crucial role in calculating the primary inventory target, collectively influencing the formulation and implementation of inventory strategies.
[0065] Furthermore, based on the aforementioned management parameters and long-term average consumption, the first inventory target for the spare parts to be managed is calculated using the inventory target calculation formula, which is shown below:
[0066]
[0067] Where S1 represents the first inventory target, D avg LT represents the long-term average consumption, Z represents the lead time for procurement, and σ represents the service level coefficient. D This represents the demand volatility coefficient.
[0068] The operations and maintenance team deploys inventory based on the primary inventory target, ensuring that spare parts inventory levels meet business needs without wasting resources due to excessive inventory. By introducing service level coefficients and demand volatility coefficients, this invention can flexibly address the uncertainty of spare parts demand, improving the flexibility and adaptability of inventory management.
[0069] Step S3: Obtain the first actual consumption quantity of the spare parts to be managed within the first management cycle.
[0070] In this embodiment, it is necessary to record the actual consumption quantity of the spare parts to be managed during the first management cycle, thereby understanding the difference between the actual consumption quantity and the initial inventory target. This provides practical data support for subsequent iterative approximation.
[0071] Step S4: Calculate the first consumption deviation of the spare parts to be managed within the first management cycle based on the first actual consumption quantity and the long-term average consumption quantity.
[0072] In this embodiment of the invention, the difference between the first actual consumption quantity and the long-term average consumption quantity is calculated to obtain the first consumption deviation. The first consumption deviation characterizes the consumption fluctuation of the spare parts under management during the first management cycle. If the first consumption deviation is large, it indicates that there is a significant difference between the actual consumption of the spare parts and the long-term average consumption quantity, and the inventory target is then iteratively updated based on the first consumption deviation.
[0073] Step S5: Input the first consumption deviation and the first inventory target into the iterative approximation model to generate the second inventory target.
[0074] In this embodiment of the invention, the second inventory target is used to characterize the inventory target of the spare parts to be managed in the second management cycle. The second management cycle is the next iteration cycle of the first management cycle. The iterative approximation model generates the second inventory target iteratively based on the periodic deviation and the learning rate.
[0075] Specifically, the iterative approximation model uses an iterative formula to generate the second inventory target, as shown below:
[0076] S2 = S1 + α·E1,
[0077] Where S2 represents the second inventory target, α represents the preset learning rate, and E1 represents the first consumption deviation.
[0078] In this way, based on the preset learning rate, the first consumption deviation, and the first inventory target, the inventory target can be dynamically adjusted through iterative updates to better reflect actual needs. The preset learning rate controls the speed and stability of model convergence; a larger preset learning rate results in larger parameter updates with each iteration, while a smaller preset learning rate results in more subtle updates.
[0079] In some embodiments, a nonlinear function or a second-order term may be used to generate the second inventory target. This application does not specifically limit the specific implementation of the iterative approximation model for generating the second inventory target, as long as it satisfies the requirement of iteratively generating the second inventory target based on periodic deviation and learning rate.
[0080] Furthermore, the iterative approximation model can adjust the second inventory target based on the first actual consumption quantity and the long-term average consumption quantity. If the first actual consumption quantity is greater than the long-term average consumption quantity, the second inventory target is increased according to preset adjustment parameters. If the first actual consumption quantity is less than the long-term average consumption quantity, the second inventory target is decreased according to preset adjustment parameters. If the first actual consumption quantity is equal to the long-term average consumption quantity, the second inventory target remains unchanged. This balances inventory adequacy and avoids overstocking.
[0081] When the first actual consumption quantity exceeds the long-term average consumption quantity, it may indicate an increase in current demand or a future upward trend in demand. Therefore, it's necessary to increase the second inventory target to ensure the continuity of spare parts supply and avoid production interruptions or service delays due to stockouts. Conversely, when the first actual consumption quantity is less than the long-term average consumption quantity, it may indicate a decrease in current demand or inventory backlog. In this case, lowering the second inventory target can reduce unnecessary inventory holding costs and improve capital utilization efficiency. When the first actual consumption quantity equals the long-term average consumption quantity, it means that the current inventory status is consistent with the long-term trend, and no adjustment to the inventory target is necessary to maintain the stability and predictability of inventory management.
[0082] Step S6: Generate inventory management information for spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity.
[0083] In this embodiment of the invention, the actual inventory quantity of spare parts to be managed can be obtained through the asset management database, and inventory management information of the spare parts to be managed can be generated based on the second inventory target, the first actual consumption quantity and the actual inventory quantity. The inventory management information includes the suggested purchase quantity.
[0084] The recommended purchase quantity is calculated using the purchase quantity calculation formula, which is shown below:
[0085] P1 = S2 - (R1 - C1),
[0086] Where P1 represents the suggested purchase quantity, C1 represents the first actual consumption quantity, and R1 represents the actual inventory quantity.
[0087] In this embodiment of the invention, the inventory management system can generate purchase orders based on the suggested purchase quantity and generate inventory alerts based on the purchase orders. The inventory alerts may include information such as the name of the spare parts to be managed, the suggested purchase quantity, the current inventory status, and the expected inventory shortage time, so that relevant personnel can promptly understand the inventory situation and take appropriate procurement measures. Furthermore, the inventory management system can also send purchase orders and inventory alerts to the mobile terminals of relevant personnel to monitor inventory dynamics and respond accordingly.
[0088] In this embodiment of the invention, iterative inventory management of spare parts can be performed. When the system enters the next iteration cycle, inventory management information is generated cyclically by updating some data. Specifically, the following steps are included.
[0089] Step S7: Use the second inventory target as the first inventory target to update the first inventory target.
[0090] Step S8: Obtain the second actual consumption quantity of the spare parts to be managed in the second management cycle, and use the second actual consumption quantity as the first actual consumption quantity to update the first actual consumption quantity.
[0091] Step S9: Repeat steps S4 to S6 to generate inventory management information for spare parts to be managed in the next iteration cycle based on the updated first inventory target and the updated first actual consumption quantity.
[0092] Through the steps described above, the inventory target is no longer a static value, but a dynamic variable that responds to actual demand and continuously optimizes itself. By iteratively feeding the deviation between actual consumption and historical average consumption into the inventory target for the next management cycle, adaptive adjustment of inventory levels is achieved.
[0093] like Figure 2 As shown, this embodiment of the invention also provides an iterative approximation-based inventory management system for executing an iterative approximation-based inventory management method. The iterative approximation-based inventory management system includes: a data acquisition module 201, an initial configuration module 202, a deviation calculation module 203, a target generation module 204, an inventory management module 205, and an iterative update module 206.
[0094] The data acquisition module 201 is configured to acquire historical consumption data of the spare parts to be managed, and calculate the long-term average consumption of the spare parts to be managed based on the historical consumption data.
[0095] The initial configuration module 202 is configured to: calculate the first inventory target of the spare parts to be managed based on the long-term average consumption, the first inventory target being used to characterize the inventory target of the spare parts to be managed in the first management cycle.
[0096] The deviation calculation module 203 is configured to: obtain the first actual consumption quantity of the spare parts to be managed in the first management cycle; and calculate the first consumption deviation of the spare parts to be managed in the first management cycle based on the first actual consumption quantity and the long-term average consumption.
[0097] The target generation module 204 is configured to input the first consumption deviation and the first inventory target into the iterative approximation model to generate a second inventory target. The second inventory target is used to characterize the inventory target of the spare parts to be managed in the second management cycle. The second management cycle is the next iteration cycle of the first management cycle. The iterative approximation model iteratively generates the second inventory target based on the periodic deviation and the learning rate.
[0098] The inventory management module 205 is configured to generate inventory management information for spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity.
[0099] The iterative update module 206 is configured to: use the second inventory target as the first inventory target to update the first inventory target; obtain the second actual consumption quantity of the spare parts to be managed in the second management cycle, and use the second actual consumption quantity as the first actual consumption quantity to update the first actual consumption quantity; and generate inventory management information for the spare parts to be managed in the next iteration cycle based on the updated first inventory target and the updated first actual consumption quantity.
[0100] As can be seen from the above technical solution, this invention provides an inventory management method and system based on iterative approximation, which enables inventory targets to be dynamically adjusted according to the actual consumption of spare parts, thereby improving the accuracy and flexibility of inventory management. Each iteration is based on a comparison between the actual consumption data of the previous iteration cycle and the long-term average consumption. By calculating the consumption deviation and inputting it into the iterative approximation model, a new inventory target is generated. This method not only considers the historical trend of spare parts consumption but also incorporates changes in actual demand, making the inventory strategy more aligned with actual business scenarios, thereby improving the accuracy and efficiency of inventory management.
[0101] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. An inventory management method based on iterative approximation, characterized in that, include: Step S1: Obtain historical consumption data of the spare parts to be managed, and calculate the long-term average consumption of the spare parts to be managed based on the historical consumption data; Step S2: Based on the long-term average consumption, calculate the first inventory target of the spare parts to be managed. The first inventory target is used to characterize the inventory target of the spare parts to be managed in the first management cycle. Step S3: Obtain the first actual consumption quantity of the spare parts to be managed within the first management cycle; Step S4: Calculate the first consumption deviation of the spare parts to be managed in the first management cycle based on the first actual consumption quantity and the long-term average consumption quantity; Step S5: Input the first consumption deviation and the first inventory target into the iterative approximation model to generate a second inventory target. The second inventory target is used to characterize the inventory target of the spare parts to be managed in the second management cycle. The second management cycle is the next iteration cycle of the first management cycle. The iterative approximation model iteratively generates the second inventory target based on the periodic deviation and the learning rate. Step S6: Generate inventory management information for the spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity.
2. The inventory management method according to claim 1, characterized in that, Also includes: Step S7: Use the second inventory target as the first inventory target to update the first inventory target; Step S8: Obtain the second actual consumption quantity of the spare parts to be managed in the second management cycle, and use the second actual consumption quantity as the first actual consumption quantity to update the first actual consumption quantity; Step S9: Repeat steps S4 to S6 to generate inventory management information for the spare parts to be managed in the next iteration cycle based on the updated first inventory target and the updated first actual consumption quantity.
3. The inventory management method according to claim 1, characterized in that, The step of acquiring historical consumption data of the spare parts to be managed and calculating the long-term average consumption of the spare parts to be managed based on the historical consumption data includes: Query the historical consumption data of the spare parts to be managed in the asset management database within the first preset period; The average consumption of the spare parts to be managed during the management period is calculated based on the historical consumption data to obtain the long-term average consumption, wherein the management period is shorter than the first preset period.
4. The inventory management method according to claim 1, characterized in that, The calculation of the first inventory target for the spare parts to be managed based on the long-term average consumption includes: Obtain management parameters, including procurement lead time, service level coefficient, and demand volatility coefficient; Based on the management parameters and the long-term average consumption, the first inventory target for the spare parts to be managed is calculated using the inventory target calculation formula, which is shown below: Where S1 represents the first inventory target, D avg LT represents the long-term average consumption, Z represents the procurement lead time, and σ represents the service level coefficient. D This represents the demand volatility coefficient.
5. The inventory management method according to claim 1, characterized in that, The step of calculating the first consumption deviation of the spare parts to be managed within the first management cycle based on the first actual consumption quantity and the long-term average consumption quantity includes: The difference between the first actual consumption quantity and the long-term average consumption quantity is calculated to obtain the first consumption deviation.
6. The inventory management method according to claim 4, characterized in that, The iterative approximation model generates a second inventory target using an iterative formula, which is shown below: S2 = S1 + α·E1, Wherein, S2 represents the second inventory target, α represents the preset learning rate, and E1 represents the first consumption deviation.
7. The inventory management method according to claim 6, characterized in that, The iterative approximation model adjusts the second inventory target based on the first actual consumption quantity and the long-term average consumption quantity, including: If the first actual consumption quantity is greater than the long-term average consumption quantity, then the second inventory target is increased according to the preset adjustment parameters; If the first actual consumption quantity is less than the long-term average consumption quantity, then the second inventory target is lowered according to the preset adjustment parameters; If the first actual consumption quantity is equal to the long-term average consumption quantity, then the second inventory target remains unchanged.
8. The inventory management method according to claim 7, characterized in that, The inventory management information includes suggested purchase quantities; The step of generating inventory management information for the spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity includes: The suggested purchase quantity is calculated using the purchase quantity calculation formula, which is shown below: P1 = S2 - (R1 - C1), Wherein, P1 represents the suggested purchase quantity, C1 represents the first actual consumption quantity, and R1 represents the actual inventory quantity.
9. The inventory management method according to claim 8, characterized in that, Also includes: A purchase order is generated based on the suggested purchase quantity. Inventory reminder information is generated based on the purchase order.
10. An inventory management system based on iterative approximation, characterized in that, An inventory management method based on iterative approximation as described in any one of claims 1 to 9, characterized in that it comprises: The data acquisition module is configured to: acquire historical consumption data of the spare parts to be managed, and calculate the long-term average consumption of the spare parts to be managed based on the historical consumption data; The initial configuration module is configured to: calculate the first inventory target of the spare parts to be managed based on the long-term average consumption, wherein the first inventory target is used to characterize the inventory target of the spare parts to be managed in the first management cycle; The deviation calculation module is configured to: obtain the first actual consumption quantity of the spare parts to be managed in the first management cycle; and calculate the first consumption deviation of the spare parts to be managed in the first management cycle based on the first actual consumption quantity and the long-term average consumption quantity. The target generation module is configured to input the first consumption deviation and the first inventory target into an iterative approximation model to generate a second inventory target. The second inventory target is used to characterize the inventory target of the spare parts to be managed in the second management cycle. The second management cycle is the next iteration cycle of the first management cycle. The iterative approximation model iteratively generates the second inventory target based on the periodic deviation and the learning rate. The inventory management module is configured to generate inventory management information for the spare parts to be managed based on the second inventory target, the first actual consumption quantity, and the actual inventory quantity. The iterative update module is configured to: use the second inventory target as the first inventory target to update the first inventory target; obtain the second actual consumption quantity of the spare parts to be managed in the second management cycle, and use the second actual consumption quantity as the first actual consumption quantity to update the first actual consumption quantity; and generate inventory management information of the spare parts to be managed in the next iteration cycle based on the updated first inventory target and the updated first actual consumption quantity.