General material inventory control method and system based on robust stochastic optimization

Abstract

The application discloses a kind of general material inventory control method and system based on robust random optimization, belong to inventory management technical field. Including: obtaining material demand and delivery lead time in historical time period and carrying out statistical analysis, verify whether the data characteristics of material demand and delivery lead time meet normal distribution;According to the verification result, the material demand and delivery lead time in historical time period are processed by random optimization or safety stock robust optimization model to obtain the safety stock of future decision cycle. According to the data characteristics of material demand and lead time, different safety stock control methods are selected, which can improve the prediction accuracy of material demand and lead time, reduce the inventory cost of enterprise, reduce the material loss caused by uncertainty, improve production efficiency, and solve the problem that existing safety stock setting cannot meet the actual dynamic change of customer demand.

Description

Technical Field

[0001] This invention relates to the field of inventory management technology, and in particular to a general material inventory control method and system based on robust stochastic optimization. Background Technology

[0002] The statements in this section merely refer to the background art related to this invention and do not necessarily constitute prior art.

[0003] To mitigate the impact of uncertainties such as demand fluctuations and supplier lead time delays, and to ensure the smooth execution of production plans, companies need to maintain an appropriate level of safety stock for general-purpose materials beyond the planned demand during the procurement cycle. In the event of significant demand fluctuations or supplier delays or disruptions, safety stock can sustain normal production activities for a certain period. Higher safety stock provides greater assurance of production and delivery, but also ties up inventory capital, and the company incurs storage costs. Conversely, lower safety stock reduces inventory capital, but increases the risks to production stability and on-time delivery. Therefore, setting an appropriate safety stock level is a challenging decision for any company using safety stock.

[0004] Currently, safety stock standards for common materials in enterprises are mostly based on rough estimates by staff according to historical material usage experience. Production scheduling relies on timely replenishment after consumption, and production is based on experience-driven stockpiling. This lack of scientific and effective mathematical models prevents adjustments based on predicted changes in customer demand, often resulting in shortages of needed materials while unnecessary materials accumulate in inventory. When customer demand changes, there is a lack of effective early warning mechanisms, leaving businesses struggling to address immediate problems. The dual risks of stagnant materials and finished products, and inability to meet customer delivery deadlines, exist simultaneously. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a general material inventory control method, system, electronic device, computer-readable storage medium, and computer program product based on robust stochastic optimization. It combines stochastic optimization and robust optimization to predict safety stock levels based on data characteristics of material demand and lead time, thereby improving prediction accuracy.

[0006] In a first aspect, the present invention provides a general material inventory control method based on robust stochastic optimization;

[0007] A general material inventory control method based on robust stochastic optimization includes:

[0008] Obtain material demand and lead time within a historical time period and perform statistical analysis to verify whether the data characteristics of material demand and lead time conform to a normal distribution.

[0009] Based on the verification results, the material demand and lead time in historical time periods are processed by random optimization or safety stock robust optimization models to obtain the safety stock for future decision-making cycles.

[0010] In some implementations, if the data characteristics of material demand and lead time conform to a normal distribution, the material demand and lead time within a historical time period are processed through random optimization, specifically as follows:

[0011] Based on the average and standard deviation of material demand and lead time over historical periods, and combined with the service level coefficient, the safety stock level for future decision-making cycles is determined.

[0012] In some implementations, the safety stock for future decision-making cycles is expressed as:

[0013]

[0014] In the formula, SS represents the safety stock for the future decision-making cycle, z represents the service level coefficient, and μ L σ represents the average lead time over a historical period. D μ represents the standard deviation of supply and demand over a historical period. D σ represents the average supply and demand over a historical period. L This represents the standard deviation of lead time for delivery over a historical period.

[0015] In some implementations, if the data characteristics of material demand and lead time do not conform to a normal distribution, a robust safety stock optimization model is used to process the material demand and lead time over historical periods. Specifically, this includes:

[0016] Based on the material demand and lead time in historical time periods, obtain the material demand forecast and lead time forecast for future decision-making cycles.

[0017] With the goal of minimizing the ordering cost, inventory holding cost, deferred cost, and shortage cost of safety stock, an uncertainty set is introduced. Under the constraints of emergency ordering, delivery delay, and maximum material inventory level, the safety stock level for the future decision-making period is determined through iterative calculation using the predicted material demand and lead time for the future decision-making period as inputs.

[0018] In some implementations, obtaining the predicted material demand and lead time for the future decision-making period based on the material demand and lead time in the historical time period specifically involves processing the material demand and lead time in the historical time period using a trained LSTM network or exponential smoothing method to obtain the predicted material demand and lead time for the future decision-making period.

[0019] In some implementations, the uncertainty set is the range of fluctuations in material demand and lead time within a future decision-making period, determined based on the difference between material demand and lead time over a historical period and the corresponding predicted material demand and lead time at the same time.

[0020] Secondly, the present invention provides a general material inventory control system based on robust stochastic optimization;

[0021] A general material inventory control system based on robust stochastic optimization includes:

[0022] The normal distribution verification module is configured to: acquire material demand and lead time within a historical time period and perform statistical analysis to verify whether the data characteristics of material demand and lead time conform to a normal distribution;

[0023] The general material inventory control module is configured to: based on the verification results, process the material demand and lead time within a historical period through random optimization or a safety stock robust optimization model to obtain the safety stock level for the future decision-making cycle.

[0024] Thirdly, the present invention provides an electronic device;

[0025] An electronic device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the general material inventory control method based on robust stochastic optimization described above.

[0026] Fourthly, the present invention provides a computer-readable storage medium;

[0027] A computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the steps of the general material inventory control method based on robust stochastic optimization as described above.

[0028] Fifthly, the present invention provides a computer program product;

[0029] A computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of the aforementioned general material inventory control method based on robust stochastic optimization.

[0030] Compared with the prior art, the beneficial effects of the present invention are:

[0031] 1. The technical solution provided by this invention selects the corresponding safety stock prediction method based on the data characteristics of material demand and lead time. On the one hand, it improves the accuracy of safety stock prediction by making predictions based on data development characteristics, reduces enterprise inventory costs, reduces material shortage losses caused by uncertainty, and improves production efficiency. On the other hand, it eliminates the need to predict the material demand and lead time for all general materials in the future decision-making cycle, and can directly calculate the safety stock through data distribution characteristics, thereby improving the efficiency of safety stock prediction.

[0032] 2. The technical solution provided by this invention, for material data whose material demand and lead time conform to a normal distribution within a certain historical period, uses random optimization to process the material demand and lead time within the historical period, and extracts its data distribution characteristics to realize safety stock decision-making. The data processing flow is simple and has strong real-time performance.

[0033] 3. The technical solution provided by this invention, for material data whose material demand and lead time do not conform to a normal distribution within a certain historical period, adopts a robust optimization modeling method to combine demand and lead time forecasting with inventory decisions. By considering the worst case, it reduces the negative impact of uncertainty, thereby reducing risk. It can cope with various uncertainties and changes, making the decision effective when facing the unknown future. It improves the reliability and flexibility of the system, and is usually easy to understand and implement. It does not require complex mathematical models or calculations, and is more in line with the actual situation of enterprises, reflecting the true state of enterprise inventory development. Attached Figure Description

[0034] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0035] Figure 1 This is a flowchart provided for an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of LSTM model parameters provided in an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram illustrating the fitting effect of the LSTM model training data provided in an embodiment of the present invention. Detailed Implementation

[0038] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0039] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments of the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. Furthermore, it should be understood that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0040] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0041] Example 1

[0042] Existing methods for predicting safety stock levels for general-purpose materials cannot be applied to uncertainties such as dynamically changing customer demand and customer forecast quantities, resulting in low prediction accuracy. Therefore, this invention provides a general-purpose material inventory control method based on robust stochastic optimization, which organically combines historical data analysis, long and short memory network prediction, exponential smoothing prediction, stochastic optimization, and robust optimization to achieve safety stock control.

[0043] Next, combined Figures 1-3 This embodiment provides a detailed description of a general material inventory control method based on robust stochastic optimization. This general material inventory control method based on robust stochastic optimization includes the following steps:

[0044] S1. Obtain the material demand and lead time for the historical time period and perform statistical analysis to verify whether the data characteristics of material demand and lead time conform to a normal distribution; if yes, proceed to S2; if no, proceed to S3.

[0045] In this embodiment, the material demand and lead time within a historical period are obtained by analyzing and processing the company's actual historical inventory data.

[0046] Historical inventory data includes daily input and output quantities, return quantities, purchase receipt quantities, purchase receipt times, purchase order placement times, net purchase order value, purchase quantities, fixed costs of warehouse management, order amounts corresponding to materials, late payment penalty ratios, and maximum inventory levels for each material. The specific calculation method is as follows:

[0047] Material requirement = Input quantity - Return quantity;

[0048] Delivery lead time = Procurement receipt time - Purchase order placement time;

[0049] Unit ordering cost = Net value of purchase order / Quantity purchased;

[0050] Unit inventory holding cost = unit material warehouse management fixed cost + unit ordering cost;

[0051] Unit emergency order cost = 2 × unit order cost;

[0052] Unit late payment penalty cost = order amount × late payment penalty percentage.

[0053] For example, run an existing normality test algorithm in Python to perform a normality test and output the normality test coefficient p. If p ≤ 0.05, then the material demand or lead time of the material conforms to a normal distribution, and calculate the standard deviation σ of the material demand D. D The average value μ of material requirement D D Average delivery lead time L, μ L The standard deviation σ of the lead time L L If p > 0.05, then the material requirement or lead time of the material does not conform to a normal distribution, and proceed to S3.

[0054] S2. By randomly optimizing the material demand and lead time within historical time periods, the safety stock level for future decision-making cycles is obtained.

[0055] If the data characteristics of material demand and lead time conform to a normal distribution, then the safety stock level can be accurately predicted based on its data distribution characteristics.

[0056] As one implementation method, the safety stock level for the future decision-making cycle is obtained based on the average and standard deviation of material demand and the average and standard deviation of lead time over a historical period, combined with the service level coefficient, as shown below:

[0057]

[0058] In the formula, SS represents the safety stock for the future decision-making cycle, z represents the service level coefficient, and μ L σ represents the average lead time over a historical period. D μ represents the standard deviation of supply and demand over a historical period. D σ represents the average supply and demand over a historical period. L This represents the standard deviation of lead time for delivery over a historical period.

[0059] In this embodiment, the service level corresponds to the stockout rate, expressing the extent to which fluctuations in demand and lead time can be met, which is determined by the decision-maker. If the service level is set to 95%, it means that the set safety stock has a 95% probability of meeting fluctuations in demand and lead time. The service level coefficient z can be obtained by referring to the "Correspondence Table of Service Level and Safety Coefficient Z Value of Normal Distribution". If the service level is 95%, the corresponding z value is 1.645.

[0060] S3. A robust safety stock optimization model is used to process material demand and lead times over historical periods to determine the safety stock level for future decision-making cycles. Specifically, this includes:

[0061] S301. Based on the material demand and lead time in historical time periods, obtain the predicted material demand and lead time for future decision-making cycles.

[0062] In some implementations, a time threshold is set, and material data within that historical time period is used as training data to construct a training set and a test set. The LSTM network is trained using the training set, and the test set is input into the trained LSTM network and processed using first, second, and third exponential smoothing methods to obtain the corresponding predicted values. These predicted values ​​are then compared with the actual values ​​within that historical time period to obtain the error between the actual and predicted values. The method with the smallest error is selected to predict the material demand and lead time for the next decision cycle.

[0063] If the error of the LSTM network is less than that of the exponential smoothing method, the trained LSTM network is used to process the material demand and lead time in the historical time period, and output the demand forecast value at a certain point in time in the future decision-making cycle, so as to obtain the material demand forecast value and lead time forecast value in the future decision-making cycle.

[0064] Training the LSTM network specifically includes:

[0065] First, a time threshold is set, and material data within that time period is used as training data. The data is preprocessed, including data cleaning (handling missing or outliers), data normalization (normalization or standardization), and possible feature engineering (such as calculating moving averages or seasonal characteristics of demand). Second, the time series data is divided into a series of fixed-length segments to create a dataset for training and prediction. Third, an LSTM model is constructed; the model architecture defined in this embodiment is detailed in [link to documentation]. Figure 2The model is trained, evaluated, and tuned. The model performance is evaluated based on the loss function, and the model parameters and architecture are adjusted. Future time series data are input into the model in batches and the predicted data is output. The predicted data is denormalized and the model is deployed to the production environment.

[0066] Meanwhile, the error between the predicted and actual values ​​obtained when training the LSTM network is removed by removing outliers, and the fluctuation range of the error is set as the fluctuation range of the uncertainty of demand and lead time in the next decision cycle, that is, the upper and lower limits of the uncertainty set.

[0067] By setting an uncertain set, companies can have some flexibility in their inventory decisions, preventing them from incurring significant losses due to fluctuations in demand.

[0068] If the error of the LSTM network is greater than that of the exponential smoothing method, then the material demand and lead time in the historical period are processed by the exponential smoothing method to obtain the predicted material demand and lead time for the future decision-making period.

[0069] The test set was input into Python code for first-order exponential smoothing, second-order exponential smoothing, and third-order exponential smoothing to obtain the corresponding prediction results MSE.

[0070] First, the predicted MSE and seasonal trend charts obtained by the first, second, and third exponential smoothing methods are compared and judged. It is observed that both demand and lead time have seasonal trends, so the exponential smoothing method with the smallest MSE is selected as the prediction method. Second, the predicted MSE under different α values ​​are compared and the α value with the smallest MSE is selected as the model parameter.

[0071] In this embodiment, the triple exponential smoothing method is selected.

[0072] S302. Taking the predicted material demand and lead time of the future decision-making period as input, and aiming to minimize the ordering cost, inventory holding cost, deferred cost and shortage cost of safety stock, an uncertainty set is introduced. Under the constraints of emergency ordering, delivery delay and maximum material inventory level, the safety stock quantity of the future decision-making period is determined by iterative calculation through the safety stock robust optimization model.

[0073] For example, let This indicates that during the t-th decision period, when the demand is... Supplier lead time is Safety stock level set The total cost function at time, using robust optimization to set the safety stock level for the next decision period, is modeled as follows:

[0074]

[0075] In the formula, total cost includes the ordering cost of safety stock, inventory holding cost, emergency ordering cost resulting from actual demand exceeding forecast demand and depleting safety stock, and late delivery penalty cost resulting from supplier delays.

[0076] Based on the above definition, the model can be transformed into:

[0077]

[0078] In the formula: Let be the average unit ordering cost of material i in the t-th period; Let be the average unit inventory holding cost of material i during the t-th period; Let be the average unit emergency order cost of material i after it becomes out of stock in the t-th period; Let be the average unit penalty cost of material i after being delayed in the t-th period; Forecast the demand for material i in the t-th period; The average daily consumption of material i during the t-th period; Predict the lead time of material i in the t-th period; The maximum inventory level of material i; and All are intermediate variables.

[0079] The second and third formulas indicate that emergency ordering (i.e., emergency ordering constraint) will only be triggered if actual demand exceeds forecast demand and safety stock is depleted. The fourth and fifth formulas indicate the impact of supplier delivery delays. A delay penalty (i.e., delivery delay constraint) is triggered when the total consumption within a day exceeds the safety stock. According to the material requirements planning, the sixth formula indicates that the safety stock cannot exceed the maximum inventory level of the material and cannot be less than 0 (i.e., the maximum inventory level constraint of the material).

[0080] Assume that the distributions of actual demand and actual lead time belong to the interval uncertainty set defined below:

[0081] Definition 1. Actual demand is an uncertainty coefficient. The range of values ​​is:

[0082]

[0083] In the formula, The actual demand for material i is represented by a random variable with an unknown distribution. This represents the corresponding predicted value; Indicates the corresponding fluctuation range; and Indicates the upper and lower limits of the corresponding fluctuation range; η j Its function is to adjust the conservatism of robust optimization solutions and 0≤η j ≤1, j=1,2,…,m.

[0084] Definition 2. Actual lead time is an uncertainty factor. The range of values ​​is:

[0085]

[0086] In the formula, The actual lead time of material i is represented by a random variable with an unknown distribution. This represents the corresponding predicted value; Indicates the corresponding fluctuation range; and Indicates the upper and lower limits of the corresponding fluctuation range; ξ j Its function is to adjust the conservatism of robust optimization solutions and 0≤ξ j ≤1, j=1,2,…,m. In actual calculations, for ease of calculation, η is reduced to 1 based on the need for conservatism. j and ξ j Let η and ξ be constants.

[0087] Based on the above basic model construction and the definition of the interval uncertainty set, introducing the interval uncertainty set into the objective function of the total cost of safety stock yields the following:

[0088]

[0089]

[0090] The upper and lower limits of the demand and lead time fluctuations given in the forecast interval are substituted into the model. The conservatism of the robust optimization is adjusted by setting the adjustment coefficient of the robust optimization. Finally, the solution is obtained by calling the gurobi solver using Python.

[0091] Next, to verify the advancement of the method described in this embodiment, this embodiment uses historical inventory data containing 300 common materials of the enterprise for experimentation. The data is as follows:

[0092] The data used includes historical inventory data for 300 common materials of the enterprise, including the daily input quantity, return quantity, purchase acceptance quantity, purchase receipt time, purchase order placement time, net purchase order value, and purchase quantity for each material. In addition, the fixed costs of warehouse management, the order amount corresponding to the materials and the late payment penalty ratio, the maximum inventory level and other data were determined with the enterprise. The required data such as demand, lead time and cost from January 1, 2022 to December 31, 2022 were calculated.

[0093] The data from January 1, 2022 to October 31, 2022 was selected as the training set. For details on the training and fitting results in the LSTM model, please refer to the appendix. Figure 3 Meanwhile, it was observed that the MSE of the triple exponential smoothing forecast was the smallest, and the MSE was the smallest when α1 = 0.1, and the demand forecast result was closest to the actual value. The MSE was the smallest when α2 = 0.4, and the lead time forecast result was closest to the actual value. Therefore, the triple exponential smoothing method was selected for forecasting, and the parameters of the forecasting model were set to 0.1 and 0.4 respectively.

[0094] To obtain demand forecasts for November and December 2022, a prediction time step of 60 was set in the trained LSTM and triple exponential smoothing models. The prediction results were then output and analyzed. Furthermore, the fluctuation ranges of demand and lead time were calculated based on the prediction results.

[0095] After solving the safety stock calculation model based on a combination of stochastic optimization and robust optimization, the total inventory of 300 materials in this example was reduced by 59.83% compared to before the improvement, and the total inventory holding cost was reduced by 1.26 million yuan.

[0096] Example 2

[0097] This embodiment discloses a general material inventory control system based on robust stochastic optimization, including:

[0098] The normal distribution verification module is configured to: acquire material demand and lead time within a historical time period and perform statistical analysis to verify whether the data characteristics of material demand and lead time conform to a normal distribution;

[0099] The general material inventory control module is configured to: based on the verification results, process the material demand and lead time within a historical period through random optimization or a safety stock robust optimization model to obtain the safety stock level for the future decision-making cycle.

[0100] It should be noted that the aforementioned normal distribution verification module and general material inventory control module correspond to the steps in Embodiment 1. The examples and application scenarios implemented by these modules and their corresponding steps are the same, but they are not limited to the content disclosed in Embodiment 1. It should also be noted that these modules, as part of the system, can be executed in a computer system, such as a set of computer-executable instructions.

[0101] Example 3

[0102] Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, they complete the steps of the general material inventory control method based on robust stochastic optimization described above.

[0103] Example 4

[0104] Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps of the aforementioned general material inventory control method based on robust stochastic optimization.

[0105] Example 5

[0106] Embodiment 5 of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-described general material inventory control method based on robust stochastic optimization.

[0107] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0110] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0111] The above description is merely a preferred embodiment of the present invention and is not intended to limit the 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. A general material inventory control method based on robust stochastic optimization, characterized in that, include: Obtain material demand and lead time within a historical time period and perform statistical analysis to verify whether the data characteristics of material demand and lead time conform to a normal distribution. Based on the verification results, the material demand and lead time in the historical period are processed by random optimization or safety stock robust optimization model to obtain the safety stock for the future decision-making cycle. If the data characteristics of material demand and lead time do not conform to a normal distribution, a robust safety stock optimization model is used to process the material demand and lead time over historical periods, specifically including: Based on the material demand and lead time in historical time periods, obtain the material demand forecast and lead time forecast for future decision-making cycles. With the goal of minimizing the ordering cost, inventory holding cost, deferred cost and shortage cost of safety stock, an uncertainty set is introduced. Under the constraints of emergency ordering, delivery delay and maximum material inventory level, the safety stock level for the future decision period is determined by iterative calculation using the predicted material demand and lead time of the future decision period as input. The specific steps for obtaining the predicted material demand and lead time for the future decision-making period based on the material demand and lead time in the historical time period are as follows: the material demand and lead time in the historical time period are processed by a trained LSTM network or exponential smoothing method to obtain the predicted material demand and lead time for the future decision-making period.

2. The general material inventory control method based on robust stochastic optimization as described in claim 1, characterized in that, If the data characteristics of material demand and lead time conform to a normal distribution, random optimization can be used to process the material demand and lead time within historical time periods, specifically as follows: Based on the average and standard deviation of material demand and lead time over historical periods, and combined with the service level coefficient, the safety stock level for future decision-making cycles is determined.

3. The general material inventory control method based on robust stochastic optimization as described in claim 2, characterized in that, The safety stock level for future decision-making cycles is expressed as: ； In the formula, SS represents the safety stock for the future decision-making cycle, and z represents the service level coefficient. This represents the average lead time for delivery over a historical period. The standard deviation of supply and demand over a historical period. This represents the average supply and demand over a historical period. This represents the standard deviation of lead time for delivery over a historical period.

4. The general material inventory control method based on robust stochastic optimization as described in claim 1, characterized in that, The uncertainty set is the range of fluctuations in material demand and lead time within the future decision-making period, determined by the difference between the material demand and lead time in the historical period and the corresponding predicted values ​​of material demand and lead time at the same moment.

5. A general-purpose material inventory control system based on robust stochastic optimization, characterized in that, The general material inventory control method based on robust stochastic optimization as described in any one of claims 1-4 includes: The normal distribution verification module is configured to: acquire material demand and lead time within a historical time period and perform statistical analysis to verify whether the data characteristics of material demand and lead time conform to a normal distribution; The general material inventory control module is configured to: based on the verification results, process the material demand and lead time within a historical period through random optimization or a safety stock robust optimization model to obtain the safety stock level for the future decision-making cycle.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the general material inventory control method based on robust stochastic optimization as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the general material inventory control method based on robust stochastic optimization as described in any one of claims 1-4.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the general material inventory control method based on robust stochastic optimization as described in any one of claims 1-4.

Images