Power material management and control method and device, computer device and storage medium

Abstract

The application relates to a power material management and control method and device, computer equipment and a storage medium. The method comprises the following steps: determining target power materials from a plurality of power materials based on value-related data and demand-related data of the power materials, so that the most important power materials can be preferentially selected to develop an inventory management strategy. Historical demand data of the target power materials is input into a demand prediction model for prediction, so that predicted demand data of the target power materials in a future period of time can be accurately obtained. Thus, a reorder point and a maximum inventory quantity can be accurately calculated according to a possible demand quantity of the target power materials in the future. When the inventory quantity of the target power materials is lower than the reorder point, a replenishment quantity can be calculated according to the maximum inventory quantity, and the target power materials can be timely replenished. Without real-time monitoring and settlement by humans, important power materials can be effectively managed and controlled, the management and control cost of the power materials can be effectively reduced, and the management and control efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for controlling power materials. Background Art

[0002] The supply chain is one of the three pillars of a business, significantly impacting its operating profit margin and capital turnover. Many supply chain performance issues, such as cost reduction, delivery delays, and slow inventory turnover, appear to be due to inadequate execution, but in reality, they stem more from inherent planning deficiencies. Improving planning to improve execution is an effective approach to improving supply chain performance. The linkage between planning and execution can be summarized into three key links: demand forecasting, inventory planning, and supply chain execution—also known as the three lines of defense in the supply chain. Therefore, forecasting material demand and improving inventory management are crucial.

[0003] However, the current power supply system adopts a quantitative purchasing strategy for each type of power material, which requires real-time human monitoring and continuous settlement of the inventory of each type of power material, which consumes too much manpower and material resources and has low management and control efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a power material management and control method, device, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of power material management and control in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for controlling power materials. The method comprises:

[0006] Determine a target power material from multiple power materials based on value-related data and demand-related data of the power materials;

[0007] Obtain historical demand data for target power materials, input the historical demand data into a demand forecasting model, and obtain forecast demand data for the target power materials;

[0008] Determine the reorder point and maximum inventory level for the target power materials based on the forecast demand data; the reorder point is used to indicate the quantity of the target power materials that need to be replenished;

[0009] Target power supplies are managed and controlled according to the inventory management strategy determined by the reorder point and maximum inventory level.

[0010] In one embodiment, determining a target power material from a plurality of power materials based on value-related data and demand-related data of the power materials includes:

[0011] Determine the comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the multiple power materials;

[0012] Obtain the electric power materials whose corresponding comprehensive weights meet the preset conditions as the target electric power materials.

[0013] In one embodiment, determining a comprehensive weight corresponding to each of the plurality of electric power materials based on value-related data and demand-related data respectively corresponding to the plurality of electric power materials includes:

[0014] sorting the plurality of electric power materials based on the value-related data corresponding to each of the plurality of electric power materials to obtain a first sorting result, and assigning a first weight to each electric power material according to the first sorting result;

[0015] sorting the plurality of power materials based on the demand-related data corresponding to each of the plurality of power materials to obtain a second sorting result, and assigning a second weight to each power material according to the first sorting result;

[0016] A weighted calculation is performed on the first weight and the second weight corresponding to each electric power material to obtain a comprehensive weight corresponding to each electric power material.

[0017] In one embodiment, the method for obtaining the demand forecast model includes:

[0018] Obtain the demand benchmark values ​​and equipment characteristics corresponding to the target power materials;

[0019] Build a neural network model based on demand benchmark values ​​and equipment characteristics;

[0020] Building a training set based on historical demand data samples of target power materials, the training set includes training samples and training labels;

[0021] The training samples are processed through the neural network model to obtain the predicted output;

[0022] Construct a cost function based on the difference between the predicted output and the training label, and determine the objective function based on the cost function and the regularization term;

[0023] The neural network model is trained based on the objective function until the training stops when the condition is reached, and the trained neural network model is used as the demand forecasting model.

[0024] In one embodiment, determining a reorder point and a maximum inventory level corresponding to a target power material based on the forecast demand data includes:

[0025] Determine the order lead time and demand fluctuation safety factor corresponding to the target power materials. The order lead time is the time period from when the replenishment order is placed to when the replenishment materials are put into storage.

[0026] Calculate the standard deviation of demand corresponding to the target power materials based on the predicted demand data;

[0027] Calculate the safety stock volume corresponding to the target power materials based on the order lead time, demand change safety factor and demand standard deviation;

[0028] Determine the lead time consumption corresponding to the order lead time based on the forecast demand data, and calculate the reorder point corresponding to the target power materials based on the lead time consumption and safety stock;

[0029] The average demand is determined based on the forecast demand data, and the maximum inventory corresponding to the target power materials is calculated based on the average demand, order lead time and safety stock.

[0030] In one embodiment, the target power material is managed and controlled according to an inventory management strategy determined by a reorder point and a maximum inventory level, including:

[0031] When the inventory of the target power material is not greater than the reorder point, the actual inventory of the target power material is obtained;

[0032] The replenishment quantity corresponding to the target power materials is calculated based on the maximum inventory and the actual inventory, and the target power materials are replenished according to the replenishment quantity.

[0033] In a second aspect, the present application also provides a power material management and control device. The device includes:

[0034] a determination module, configured to determine a target power material from a plurality of power materials based on value-related data and demand-related data of the power materials;

[0035] The forecasting module is used to obtain historical demand data of the target power material, input the historical demand data into the demand forecasting model, and obtain the forecast demand data of the target power material;

[0036] The parameter determination module is used to determine the reorder point and maximum inventory quantity corresponding to the target power material based on the predicted demand data; the reorder point is used to represent the quantity of the target power material when it needs to be replenished;

[0037] The material control module is used to control the target power materials according to the inventory management strategy determined by the reorder point and the maximum inventory quantity.

[0038] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0039] Determine a target power material from multiple power materials based on value-related data and demand-related data of the power materials;

[0040] Obtain historical demand data for target power materials, input the historical demand data into a demand forecasting model, and obtain forecast demand data for the target power materials;

[0041] Determine the reorder point and maximum inventory level for the target power materials based on the forecast demand data; the reorder point is used to indicate the quantity of the target power materials that need to be replenished;

[0042] Target power supplies are managed and controlled according to the inventory management strategy determined by the reorder point and maximum inventory level.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0044] Determine a target power material from multiple power materials based on value-related data and demand-related data of the power materials;

[0045] Obtain historical demand data for target power materials, input the historical demand data into a demand forecasting model, and obtain forecast demand data for the target power materials;

[0046] Determine the reorder point and maximum inventory level for the target power materials based on the forecast demand data; the reorder point is used to indicate the quantity of the target power materials that need to be replenished;

[0047] Target power supplies are managed and controlled according to the inventory management strategy determined by the reorder point and maximum inventory level.

[0048] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0049] Determine a target power material from multiple power materials based on value-related data and demand-related data of the power materials;

[0050] Obtain historical demand data for target power materials, input the historical demand data into a demand forecasting model, and obtain forecast demand data for the target power materials;

[0051] Determine the reorder point and maximum inventory level for the target power materials based on the forecast demand data; the reorder point is used to indicate the quantity of the target power materials that need to be replenished;

[0052] Target power supplies are managed and controlled according to the inventory management strategy determined by the reorder point and maximum inventory level.

[0053] The aforementioned power material management and control method, apparatus, computer device, storage medium, and computer program product identify target power materials from multiple power materials based on value-related and demand-related data. This allows for prioritizing the most important power materials and formulating inventory management strategies. Historical demand data for the target power materials is input into a demand forecasting model for prediction, accurately generating forecasted demand data for the target power materials over a period of time. This allows for accurate calculation of the reorder point and maximum inventory level required for replenishment based on the expected future demand for the target power materials. The target power materials are then managed and controlled according to the inventory management strategy determined by the reorder point and maximum inventory level. When the inventory level of the target power material falls below the reorder point, the replenishment quantity is calculated based on the maximum inventory level, allowing for timely replenishment of the target power material. This eliminates the need for manual real-time monitoring and settlement, effectively managing and controlling important power materials, reducing the cost of power material management and control and improving management and control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 Schematic diagram of a flow chart of a method for controlling power materials in one embodiment;

[0055] Figure 2 Schematic diagram of modeling of ABC&PRS classification method in one embodiment;

[0056] Figure 3 is a logic flow chart of a method for controlling power materials in one embodiment;

[0057] Figure 4 This is a structural block diagram of an electric power material control device in one embodiment;

[0058] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0060] In one embodiment, Figure 1As shown, a method for controlling power materials is provided. This embodiment uses the method applied to a computer device as an example. It can be understood that the computer device can specifically be a terminal or a server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices, portable wearable devices, and Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart medical devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented as an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0061] Step 102 : determining a target electric power material from a plurality of electric power materials based on the value-related data and demand-related data of the electric power materials.

[0062] Power supplies can include wire switches, air switches, concrete poles, towers, various cables, conductors, ground wires, and various hardware, and are not limited in this embodiment. Value-related data refers to the value percentage of each power supply relative to the total power supply, as determined by the ABC classification method. Demand-related data refers to the demand percentage of each power supply relative to the total power supply, as determined by the PRS classification method.

[0063] Optionally, the computer equipment combines the ABC classification method and the PRS classification method to comprehensively calculate the value and demand level of each power material, obtain the comprehensive weight corresponding to each power material, and use the power material whose comprehensive weight meets the preset conditions as the target power material.

[0064] The ABC classification system divides supplies into three categories. Generally speaking, Category A items are the most important and have the highest value, requiring special care; Category B items are of lower value and can be stored generally; and Category C items are the lowest value and are generally purchased in bulk by businesses. The PRS classification system categorizes supplies based on demand quantity and frequency into Category P (popular), indicating high demand; Category R (regular), indicating average demand; and Category S (stranger), indicating low demand.

[0065] In one feasible implementation, the ABC classification method divides materials into multiple categories (more than three), for example, into six categories: A, B, C, D, E, and F. The value of each category decreases from A to F. Similarly, the PRS classification method divides materials into multiple categories (more than three), with the demand for each category decreasing.

[0066] Step 104 : Obtain historical demand data of the target electric power material, input the historical demand data into a demand forecasting model, and obtain forecast demand data of the target electric power material.

[0067] Among them, demand data represents the demand for materials within a period of time.

[0068] Optionally, the computer device obtains historical demand data of the target power material over a period of time in the past, inputs the historical demand data into a pre-trained demand forecasting model, and obtains forecast demand data of the target power material.

[0069] Step 106: Determine the reorder point and maximum inventory quantity corresponding to the target power material based on the forecast demand data; the reorder point is used to represent the quantity of the target power material when it needs to be replenished.

[0070] Specifically, the computer equipment calculates the safety inventory and average demand of the target power materials based on the predicted demand data, and then calculates the corresponding reorder point and maximum inventory of the target power materials based on the order lead time of the target power materials.

[0071] Step 108: Control the target power material according to the inventory management strategy determined by the reorder point and the maximum inventory quantity.

[0072] Optionally, when the inventory of the target power material drops below the reorder point, the computer device obtains the actual inventory of the current target power material, calculates the replenishment quantity based on the maximum inventory and the actual inventory, and replenishes the target power material based on the replenishment quantity.

[0073] In the above-described power material management and control method, target power materials are identified from multiple power materials based on their value and demand data, thereby prioritizing the most important power materials for inventory control strategies. Historical demand data for the target power materials is input into a demand forecasting model for prediction, accurately generating forecasted demand data for the target power materials over a period of time. This allows accurate calculation of the reorder point and maximum inventory level required for replenishment based on the expected future demand for the target power materials. The target power materials are then managed and controlled according to the inventory management strategy determined by the reorder point and maximum inventory level. When the inventory level of the target power material falls below the reorder point, the replenishment quantity is calculated based on the maximum inventory level, allowing timely replenishment of the target power material. This eliminates the need for manual real-time monitoring and settlement, enabling effective management and control of critical power materials, significantly reducing management and control costs and improving management and control efficiency.

[0074] In one embodiment, a target power material is determined from a plurality of power materials based on value-related data and demand-related data of the power materials, including: determining a comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the plurality of power materials; and obtaining a power material whose corresponding comprehensive weight satisfies a preset condition as the target power material.

[0075] Furthermore, based on the value-related data and demand-related data respectively corresponding to the plurality of electric power materials, a comprehensive weight corresponding to each electric power material is determined, including: sorting the plurality of electric power materials based on the value-related data respectively corresponding to the plurality of electric power materials to obtain a first sorting result, and allocating a first weight to each electric power material according to the first sorting result; sorting the plurality of electric power materials based on the demand-related data respectively corresponding to the plurality of electric power materials to obtain a second sorting result, and allocating a second weight to each electric power material according to the first sorting result; and performing weighted calculation on the first weight and the second weight corresponding to each electric power material to obtain a comprehensive weight corresponding to each electric power material.

[0076] In one embodiment, the ABC&PRS classification method is used to determine the comprehensive weight corresponding to each power material. The ABC&PRS classification method is a combination of the ABC classification method and the PRS classification method. Figure 2 As shown, the comprehensive weight of each power resource is determined based on its value and demand. The specific calculation process is as follows: First, different weights are assigned to the ABS and PRS classification methods, for example, a weight of 0.7 for the ABS method and 0.3 for the PRS method. Second, corresponding weights are assigned to the specific categories in each method, for example, 0.5 for Class A, 0.3 for Class B, 0.2 for Class C, 0.5 for Class P, 0.3 for Class R, and 0.2 for Class S. This calculates the weight of each category, for example, A = 0.7 * 0.5 = 0.35. Finally, the combined categories are summed to obtain the comprehensive weight, for example, BP = 0.7 * 0.3 + 0.3 * 0.5 = 0.36. This yields the comprehensive weight of each power resource. All power resources are then ranked in descending order of comprehensive weight, and the top N ranked items are selected as target power resources, where N is a positive integer greater than or equal to 1.

[0077] In a feasible implementation, a comprehensive weight of each electric power material is obtained, and an electric power material having a comprehensive weight greater than a weight threshold is selected as a target electric power material.

[0078] In this embodiment, by determining the comprehensive weight corresponding to each power material based on the value-related data and demand-related data respectively corresponding to multiple power materials, and obtaining the power materials whose comprehensive weight size meets the preset conditions as the target power materials. Considering the material value and demand degree comprehensively, selecting one or several of the most important power materials as the target power materials for priority control can reduce the control cost of power materials and improve the control efficiency.

[0079] In one embodiment, the acquisition method of the demand prediction model includes: obtaining the demand reference value and equipment characteristics corresponding to the target power material; constructing a neural network model based on the demand reference value and equipment characteristics; constructing a training set based on the historical demand data samples of the target power material, where the training set includes training samples and training labels; processing the training samples through the neural network model to obtain a prediction output; constructing a cost function according to the difference between the prediction output and the training label, and determining an objective function according to the cost function and the regularization term; training the neural network model based on the objective function until the training stop condition is reached and then stopping, and taking the trained neural network model as the demand prediction model.

[0080] Optionally, in order to more accurately predict the demand for power materials, the improved BP neural network method based on multi-dimensional fusion of influencing factors is used. Since the uses of power materials include emergency repair projects and business expansion projects, both of which are important, the power material reserve should consider both emergency repair projects and business expansion projects to ensure sufficient power material reserve. The specific influencing factors include:

[0081] (1) Demand reference value

[0082] Considering the plan-driven characteristics of the demand for power materials, the demand quantity estimated by the investment plan can be used as the demand estimate value. However, because this value is relatively rough, it is defined as the demand reference value under the influence of seasonal fluctuations. The formula is as follows: Where Q is the quarterly demand for materials; q is the monthly demand for materials; n is the year.

[0083] (2) Demand scenario division

[0084] The demand reference value of power materials is hierarchically divided according to discrete demand scenarios. Here, the demand is divided into five demand scenarios: very low demand, relatively low demand, general demand, relatively high demand, and very high demand, corresponding to the demand quantity intervals of (a k , b k , (where k = 1, 2, 3, 4, 5, and a1 < b1 = a2 < b2 = a3 < b3 = a4 < b4 = a5 < b5). Among them, a i and b i are respectively the lower and upper limit values of the demand quantity corresponding to the i-th demand type.

[0085] (3) Equipment characteristics

[0086] Equipment is a significant factor influencing the demand for power supplies. High-quality equipment manufacturing and technology enhance its resilience to earthquakes and disasters, resulting in a correspondingly smaller incident scale when subjected to a meteorological disaster of the same magnitude. The quantitative objectives of equipment assessments primarily focus on measuring operational status, stress and disaster resistance, and safety and stability. Historical statistics from power grid disasters indicate that evaluating equipment performance requires a comprehensive analysis of its safety factor and technical status. The equipment safety factor refers to its ability to withstand external interference and damage, including its structure, selection, and materials. Technical status is indicated by the equipment's remaining service life.

[0087] The three factors of the target power material are input into the BP neural network as parameters. The baseline demand value for the target power material serves as the approximate demand value for the target power material. The importance of different materials can be categorized based on demand scenarios, and different weight parameters are assigned to each power material according to the different demand scenarios. The corresponding parameters of the BP neural network are then configured based on the weight parameters of the target power material. Equipment characteristics refer to the condition of the equipment corresponding to the target power material. The better the equipment condition, the less likely it is to have problems, the lower the demand for the target power material, and the lower the corresponding parameter value.

[0088] (4) Demand trends

[0089] Because neural networks are good at capturing nonlinear mapping relationships in data, we use the past n periods of demand as input features and use neural networks to extract trend features. At the same time, to prevent the BP neural network from overfitting, we use the L2 regularization method, adding a regularization term after the cost function. The formula is: Where C0 is the original cost function; λ is the regularization coefficient, ω is used to weigh the regularization term against the original cost function; and n is the size of the training set. The original cost function of a BP neural network is generally the same as that of linear and logistic regression models. When using a neural network for classification, the negative log-likelihood is used as the cost function, while for regression, the mean squared error is used.

[0090] In this embodiment, the demand baseline value and equipment characteristics corresponding to the target power material are obtained; a neural network model is constructed based on the demand baseline value and equipment characteristics; a training set is constructed based on historical demand data samples of the target power material, and the training set includes training samples and training labels; the training samples are processed by the neural network model to obtain a predicted output; a cost function is constructed based on the difference between the predicted output and the training label, and an objective function is determined based on the cost function and a regularization term; the neural network model is trained based on the objective function until a training stopping condition is met, and the trained neural network model is used as the demand forecasting model. Using the demand forecasting model, relatively accurate predicted demand data can be obtained based on the historical demand data of the target power material.

[0091] In one embodiment, a reorder point and a maximum inventory quantity corresponding to a target power material are determined based on forecasted demand data, including: determining an order lead time and a demand variation safety factor corresponding to the target power material, where the order lead time is the time period from when a replenishment order is placed to when the replenishment material is put into storage; calculating a demand standard deviation corresponding to the target power material based on the forecasted demand data; calculating a safety inventory quantity corresponding to the target power material based on the order lead time, the demand variation safety factor, and the demand standard deviation; determining a lead time consumption corresponding to the order lead time based on the forecasted demand data, and calculating a reorder point corresponding to the target power material based on the lead time consumption and the safety inventory quantity; determining an average demand quantity based on the forecasted demand data, and calculating a maximum inventory quantity corresponding to the target power material based on the average demand quantity, the order lead time, and the safety inventory quantity.

[0092] Alternatively, a continuous control strategy (R, S) can be used to replenish power supplies. This strategy improves and enhances the (Q, R) strategy by adjusting the order quantity each time. Specifically, a maximum inventory level S is set. When the inventory level reaches or falls below the R point value, replenishment is performed, ensuring that the inventory level after replenishment is S. Due to the uncertainty of demand, R is adjusted in real time based on demand forecasts, thereby improving inventory control accuracy and reducing inventory costs and out-of-stock rates.

[0093] First, you need to calculate the safety stock corresponding to the target power materials: Where: SS represents the safety stock; σ d represents the standard deviation of demand, which can be obtained from the demand forecasting model; L is the order lead time; and z is the safety factor for demand fluctuations at a certain customer service level. Its corresponding relationship with the service level is shown in Table 1. Given a service level of X of 100% and a value of z of 3.08, the safety stock is calculated using the following process:

[0094] X(％) 80 82 84 86 88 90 92 94 96 98 99.9 z 0.84 0.92 0.99 1.08 1.17 1.28 1.41 1.55 1.75 2.05 3.08

[0095] Table 1

[0096] Step 1: According to the forecast demand model, get the standard deviation σ of demand d ;

[0097] Step 2: Determine the order lead time L. The order lead time is the total time from the purchase order placement to the procurement and warehousing of materials. The power supply bureau needs to provide further data.

[0098] Step 3: By formula Calculate safety stock ss.

[0099] Then we can calculate the reorder point: R = d L +ss. Where R represents the reorder point; d L represents the order lead time consumption; ss represents the safety stock, so the reorder point can be calculated by the following process:

[0100] Step 1: Calculate the safety stock ss;

[0101] Step 2: Determine the order lead time consumption d L , that is, the total consumption of materials during the order lead time L according to the demand forecast model;

[0102] Step 3: Calculate the reorder point R.

[0103] Finally calculate the maximum inventory: Among them, S is the maximum inventory; is the average demand; L is the order lead time; ss is the safety stock. Therefore, the maximum inventory is calculated through the following process:

[0104] Step 1: Calculate the safety stock quantity ss according to the safety stock calculation steps;

[0105] Step 2: Determine the order lead time L. The order lead time is the total time from the purchase order placement to the procurement and warehousing of materials. The power supply bureau needs to provide further data.

[0106] Step 3: Determine the average demand for a period of time based on the forecast demand model

[0107] Step 4: Calculate the maximum inventory quantity S.

[0108] In this embodiment, by determining the order lead time and demand variation safety factor corresponding to the target power materials, the order lead time is the time period from the placement of the replenishment order to the receipt of the replenished materials into the warehouse; calculating the demand standard deviation corresponding to the target power materials based on the predicted demand data; calculating the safety stock quantity corresponding to the target power materials based on the order lead time, demand variation safety factor, and demand standard deviation; determining the lead time consumption corresponding to the order lead time based on the predicted demand data, and calculating the reorder point corresponding to the target power materials based on the lead time consumption and safety stock quantity; determining the average demand based on the predicted demand data, and calculating the maximum stock quantity corresponding to the target power materials based on the average demand, order lead time, and safety stock quantity. Automatically controlling the inventory of the target power materials based on the reorder point and maximum stock quantity can reduce the control cost of power materials and improve the control efficiency.

[0109] In one embodiment, controlling the target power materials according to the inventory management strategy determined by the reorder point and the maximum stock quantity includes: when the inventory quantity of the target power materials is not greater than the reorder point, obtaining the actual inventory quantity of the target power materials; calculating the replenishment quantity corresponding to the target power materials based on the maximum stock quantity and the actual inventory quantity, and replenishing the target power materials according to the replenishment quantity.

[0110] Optionally, when the inventory quantity of the target power materials is not greater than the reorder point, calculate the replenishment quantity: ΔQ = S - Q 实 ; where ΔQ is the replenishment quantity; S is the maximum stock quantity; Q 实 is the actual inventory quantity of the current target power materials. Before replenishment, Q 实 < R, so calculate the replenishment quantity through the following process:

[0111] Step1: Calculate the maximum stock quantity S according to the maximum stock quantity calculation step;

[0112] Step2: Determine the actual inventory quantity Q 实 of the materials. The value of Q 实 is different at different inspection time points and can be directly substituted during actual inspection and calculation;

[0113] Step3: Calculate and determine the replenishment quantity ΔQ.

[0114] In this embodiment, when the inventory quantity of the target power materials is not greater than the reorder point, obtain the actual inventory quantity of the target power materials; calculate the replenishment quantity corresponding to the target power materials based on the maximum stock quantity and the actual inventory quantity, and replenish the target power materials according to the replenishment quantity. It can automatically control the inventory of the target power materials based on the reorder point and the maximum stock quantity, reduce the control cost of power materials, and improve the control efficiency.

[0115] In one embodiment, the inventory of target power materials is managed and controlled based on an inventory management strategy. Management data is recorded over a period of time. This management data is compared with relevant data from a demand forecasting model to verify the accuracy of the demand forecasting model. Based on the data comparison differences, the relevant parameters of the demand forecasting model are modified to optimize the demand forecasting model. Once the demand forecasting model is modified, the output forecasted demand data will also change simultaneously. The safety stock and reorder point calculated based on the forecasted demand data will also be updated, further improving the rationality of the inventory management strategy.

[0116] In one embodiment, Figure 3 As shown, a method for controlling power materials includes:

[0117] The multiple power materials are ranked based on their respective value-related data to obtain a first ranking result, and a first weight is assigned to each power material based on the first ranking result. The multiple power materials are ranked based on their respective demand-related data to obtain a second ranking result, and a second weight is assigned to each power material based on the first ranking result. The first and second weights corresponding to each power material are weighted together to obtain a comprehensive weight corresponding to each power material. The power material whose comprehensive weight meets the preset conditions is selected as the target power material. This is equivalent to using the improved ABC classification method to determine the research object (target power material).

[0118] Obtain the demand benchmark value and equipment characteristics corresponding to the target power material; construct a neural network model based on the demand benchmark value and equipment characteristics; construct a training set based on the historical demand data samples of the target power material, the training set including training samples and training labels; process the training samples through the neural network model to obtain a predicted output; construct a cost function based on the difference between the predicted output and the training label, and determine the objective function based on the cost function and the regularization term; train the neural network model based on the objective function until the training stops when the condition is met, and use the trained neural network model as the demand forecasting model.

[0119] The historical demand data of the target power material is obtained, and the historical demand data is input into the demand forecasting model to obtain the forecast demand data of the target power material.

[0120] Determine the order lead time and demand fluctuation safety factor for the target power material. The order lead time is the time period from when a replenishment order is placed to when the replenishment material arrives in the warehouse. Calculate the standard deviation of demand for the target power material based on the forecasted demand data. Calculate the safety stock level for the target power material based on the order lead time, demand fluctuation safety factor, and demand standard deviation. Determine the lead time consumption corresponding to the order lead time based on the forecasted demand data, and calculate the reorder point for the target power material based on the lead time consumption and safety stock level. The reorder point represents the quantity of the target power material required for replenishment. Determine the average demand based on the forecasted demand data, and calculate the maximum inventory level for the target power material based on the average demand, order lead time, and safety stock level.

[0121] When the inventory of the target power material is not greater than the reorder point, the actual inventory of the target power material is obtained; the replenishment quantity corresponding to the target power material is calculated based on the maximum inventory and the actual inventory, and the target power material is replenished according to the replenishment quantity.

[0122] Based on the inventory management strategy, the inventory of target power materials is controlled, and the control data for a period of time is recorded. By comparing the control data with the relevant data of the demand forecast model, the accuracy of the demand forecast model is verified. According to the data comparison differences, the relevant parameters of the demand forecast model are corrected to optimize the demand forecast model.

[0123] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0124] Based on the same inventive concept, the present application also provides an electric material control device for implementing the above-mentioned electric material control method. The solution provided by the device is similar to the solution described in the above-mentioned method. Therefore, the specific limitations in one or more embodiments of the electric material control device provided below can be found in the above-mentioned limitations on the electric material control method, and will not be repeated here.

[0125] In one embodiment, Figure 4As shown, a power material management and control device 400 is provided, including: a determination module 401, a prediction module 402, a parameter determination module 403 and a material management and control module 404, wherein:

[0126] A determination module 401 is configured to determine a target power material from a plurality of power materials based on value-related data and demand-related data of the power materials;

[0127] The forecasting module 402 is used to obtain historical demand data of the target power material, input the historical demand data into the demand forecasting model, and obtain the forecast demand data of the target power material;

[0128] Parameter determination module 403 is used to determine the reorder point and maximum inventory quantity corresponding to the target power material based on the predicted demand data; the reorder point is used to represent the material quantity when the target power material needs to be replenished;

[0129] The material management and control module 404 is configured to manage and control target power materials according to an inventory management strategy determined by a reorder point and a maximum inventory level.

[0130] In one embodiment, the determination module 401 is further configured to determine a comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the plurality of power materials; and obtain the power material whose corresponding comprehensive weight satisfies a preset condition as the target power material.

[0131] In one embodiment, the determination module 401 is further configured to sort the plurality of electric power materials based on the value-related data corresponding to each of the plurality of electric power materials to obtain a first sorting result, and assign a first weight to each electric power material according to the first sorting result; sort the plurality of electric power materials based on the demand-related data corresponding to each of the plurality of electric power materials to obtain a second sorting result, and assign a second weight to each electric power material according to the first sorting result; and perform weighted calculation on the first weight and the second weight corresponding to each electric power material to obtain a comprehensive weight corresponding to each electric power material.

[0132] In one embodiment, the prediction module 402 is also used to obtain the demand baseline value and equipment characteristics corresponding to the target power material; construct a neural network model based on the demand baseline value and equipment characteristics; construct a training set based on the historical demand data samples of the target power material, the training set including training samples and training labels; process the training samples through the neural network model to obtain a predicted output; construct a cost function based on the difference between the predicted output and the training label, and determine the objective function based on the cost function and the regularization term; train the neural network model based on the objective function until the training stops when the condition is met, and use the trained neural network model as the demand prediction model.

[0133] In one embodiment, the parameter determination module 403 is further used to determine the order lead time and demand change safety factor corresponding to the target power material, where the order lead time is the time period from the placement of a replenishment order to the receipt of the replenishment material; calculate the demand standard deviation corresponding to the target power material based on the predicted demand data; calculate the safety stock corresponding to the target power material based on the order lead time, the demand change safety factor, and the demand standard deviation; determine the lead time consumption corresponding to the order lead time based on the predicted demand data, and calculate the reorder point corresponding to the target power material based on the lead time consumption and the safety stock; determine the average demand based on the predicted demand data, and calculate the maximum inventory corresponding to the target power material based on the average demand, the order lead time, and the safety stock.

[0134] In one embodiment, the material management and control module 404 is further used to obtain the actual inventory of the target power material when the inventory of the target power material is not greater than the reorder point; calculate the replenishment quantity corresponding to the target power material based on the maximum inventory and the actual inventory, and replenish the target power material according to the replenishment quantity.

[0135] Each module in the above-mentioned power material control device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0136] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for controlling power materials is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0137] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0138] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: determining a target power material from a plurality of power materials based on value-related data and demand-related data of the power materials; obtaining historical demand data of the target power material, inputting the historical demand data into a demand forecasting model to obtain forecasted demand data of the target power material; determining a reorder point and a maximum inventory quantity corresponding to the target power material based on the forecasted demand data; the reorder point is used to represent the quantity of the target power material when replenishment is required; and managing the target power material based on an inventory management strategy determined by the reorder point and the maximum inventory quantity.

[0139] In one embodiment, when the processor executes the computer program, it further implements the following steps: determining the comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the multiple power materials; and obtaining the power material whose corresponding comprehensive weight meets the preset conditions as the target power material.

[0140] In one embodiment, when the processor executes the computer program, the following steps are further implemented: sorting the multiple power materials based on the value-related data corresponding to each of the multiple power materials to obtain a first sorting result, and assigning a first weight to each power material according to the first sorting result; sorting the multiple power materials based on the demand-related data corresponding to each of the multiple power materials to obtain a second sorting result, and assigning a second weight to each power material according to the first sorting result; and performing weighted calculation on the first weight and the second weight corresponding to each power material to obtain a comprehensive weight corresponding to each power material.

[0141] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining the demand baseline value and equipment characteristics corresponding to the target power material; constructing a neural network model based on the demand baseline value and equipment characteristics; constructing a training set based on the historical demand data samples of the target power material, the training set including training samples and training labels; processing the training samples through the neural network model to obtain a predicted output; constructing a cost function based on the difference between the predicted output and the training label, and determining the objective function based on the cost function and the regularization term; training the neural network model based on the objective function until the training stops when the condition is met, and using the trained neural network model as the demand prediction model.

[0142] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determining an order lead time and a demand variation safety factor corresponding to the target power material, where the order lead time is the time period from when a replenishment order is placed to when the replenishment material is put into storage; calculating a demand standard deviation corresponding to the target power material based on the forecasted demand data; calculating a safety stock amount corresponding to the target power material based on the order lead time, the demand variation safety factor, and the demand standard deviation; determining a lead time consumption corresponding to the order lead time based on the forecasted demand data, and calculating a reorder point corresponding to the target power material based on the lead time consumption and the safety stock amount; determining an average demand amount based on the forecasted demand data, and calculating a maximum stock amount corresponding to the target power material based on the average demand amount, the order lead time, and the safety stock amount.

[0143] In one embodiment, when the processor executes the computer program, the following steps are further implemented: when the inventory of the target power material is not greater than the reorder point, the actual inventory of the target power material is obtained; based on the maximum inventory and the actual inventory, the corresponding replenishment quantity of the target power material is calculated, and the target power material is replenished according to the replenishment quantity.

[0144] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: based on value-related data and demand-related data of the electric power materials, a target electric power material is determined from a plurality of electric power materials; historical demand data of the target electric power material is obtained, and the historical demand data is input into a demand forecasting model to obtain forecasted demand data of the target electric power material; based on the forecasted demand data, a reorder point and a maximum inventory quantity corresponding to the target electric power material are determined; the reorder point is used to represent the quantity of the target electric power material when replenishment is required; and the target electric power material is managed and controlled according to an inventory management strategy determined by the reorder point and the maximum inventory quantity.

[0145] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining the comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the multiple power materials; and obtaining the power material whose corresponding comprehensive weight meets the preset conditions as the target power material.

[0146] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: sorting the multiple power materials based on the value-related data corresponding to each of the multiple power materials to obtain a first sorting result, and assigning a first weight to each power material according to the first sorting result; sorting the multiple power materials based on the demand-related data corresponding to each of the multiple power materials to obtain a second sorting result, and assigning a second weight to each power material according to the first sorting result; and performing weighted calculation on the first weight and the second weight corresponding to each power material to obtain a comprehensive weight corresponding to each power material.

[0147] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the demand baseline value and equipment characteristics corresponding to the target power material; constructing a neural network model based on the demand baseline value and equipment characteristics; constructing a training set based on the historical demand data samples of the target power material, the training set including training samples and training labels; processing the training samples through the neural network model to obtain a predicted output; constructing a cost function based on the difference between the predicted output and the training label, and determining the objective function based on the cost function and the regularization term; training the neural network model based on the objective function until the training stops when the condition is met, and using the trained neural network model as the demand prediction model.

[0148] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining the order lead time and demand variation safety factor corresponding to the target power material, the order lead time being the time period from when the replenishment order is placed to when the replenishment material is put into storage; calculating the demand standard deviation corresponding to the target power material based on the forecast demand data; calculating the safety stock corresponding to the target power material based on the order lead time, the demand variation safety factor, and the demand standard deviation; determining the lead time consumption corresponding to the order lead time based on the forecast demand data, and calculating the reorder point corresponding to the target power material based on the lead time consumption and the safety stock; determining the average demand based on the forecast demand data, and calculating the maximum inventory corresponding to the target power material based on the average demand, the order lead time, and the safety stock.

[0149] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: when the inventory of the target power material is not greater than the reorder point, the actual inventory of the target power material is obtained; based on the maximum inventory and the actual inventory, the corresponding replenishment quantity of the target power material is calculated, and the target power material is replenished according to the replenishment quantity.

[0150] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the following steps: determining a target electric power material from a plurality of electric power materials based on value-related data and demand-related data of the electric power materials; obtaining historical demand data of the target electric power material, inputting the historical demand data into a demand forecasting model to obtain forecasted demand data of the target electric power material; determining a reorder point and a maximum inventory quantity corresponding to the target electric power material based on the forecasted demand data; the reorder point is used to represent the quantity of the target electric power material when replenishment is required; and managing the target electric power material based on an inventory management strategy determined by the reorder point and the maximum inventory quantity.

[0151] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining the comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the multiple power materials; and obtaining the power material whose corresponding comprehensive weight meets the preset conditions as the target power material.

[0152] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: sorting the multiple power materials based on the value-related data corresponding to each of the multiple power materials to obtain a first sorting result, and assigning a first weight to each power material according to the first sorting result; sorting the multiple power materials based on the demand-related data corresponding to each of the multiple power materials to obtain a second sorting result, and assigning a second weight to each power material according to the first sorting result; and performing weighted calculation on the first weight and the second weight corresponding to each power material to obtain a comprehensive weight corresponding to each power material.

[0153] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the demand baseline value and equipment characteristics corresponding to the target power material; constructing a neural network model based on the demand baseline value and equipment characteristics; constructing a training set based on the historical demand data samples of the target power material, the training set including training samples and training labels; processing the training samples through the neural network model to obtain a predicted output; constructing a cost function based on the difference between the predicted output and the training label, and determining the objective function based on the cost function and the regularization term; training the neural network model based on the objective function until the training stops when the condition is met, and using the trained neural network model as the demand prediction model.

[0154] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining the order lead time and demand variation safety factor corresponding to the target power material, the order lead time being the time period from when the replenishment order is placed to when the replenishment material is put into storage; calculating the demand standard deviation corresponding to the target power material based on the forecast demand data; calculating the safety stock corresponding to the target power material based on the order lead time, the demand variation safety factor, and the demand standard deviation; determining the lead time consumption corresponding to the order lead time based on the forecast demand data, and calculating the reorder point corresponding to the target power material based on the lead time consumption and the safety stock; determining the average demand based on the forecast demand data, and calculating the maximum inventory corresponding to the target power material based on the average demand, the order lead time, and the safety stock.

[0155] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: when the inventory of the target power material is not greater than the reorder point, the actual inventory of the target power material is obtained; based on the maximum inventory and the actual inventory, the corresponding replenishment quantity of the target power material is calculated, and the target power material is replenished according to the replenishment quantity.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0157] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0158] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for controlling power materials, characterized in that: The method comprises: Determine a target power material from a plurality of power materials based on value-related data and demand-related data of the power materials, wherein the value-related data is the value ratio of each of the power materials to the total power materials obtained by the ABC classification method, and the demand-related data is the demand ratio of each of the power materials to the total power materials obtained by the PRS classification method; Obtaining historical demand data for the target electric power material, inputting the historical demand data into a demand forecasting model to obtain forecast demand data for the target electric power material; Determining a reorder point and a maximum inventory level corresponding to the target power material based on the forecast demand data; the reorder point is used to represent the quantity of the target power material when replenishment is required; Managing and controlling the target power material according to an inventory management strategy determined by the reorder point and the maximum inventory level; The step of determining a target power material from a plurality of power materials based on the value-related data and the demand-related data of the power materials includes: Determine the comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the multiple power materials; Obtaining electric power materials whose corresponding comprehensive weights meet preset conditions as target electric power materials; The method for obtaining the demand forecast model includes: Obtaining the demand benchmark value and equipment characteristics corresponding to the target power material; Building a neural network model based on the demand benchmark value and the device characteristics; Building a training set based on historical demand data samples of the target electric power material, wherein the training set includes training samples and training labels; Processing the training samples through the neural network model to obtain a prediction output; Constructing a cost function based on the difference between the predicted output and the training label, and determining an objective function based on the cost function and a regularization term; Training the neural network model based on the objective function until a training stop condition is reached, and using the trained neural network model as the demand forecasting model; Determining the reorder point and maximum inventory quantity corresponding to the target power material according to the predicted demand data includes: Determine the order lead time and demand change safety factor corresponding to the target power material, where the order lead time is the time period from when the replenishment order is placed to when the replenishment material is put into storage; Calculate the demand standard deviation corresponding to the target power material according to the predicted demand data; Calculate the safety inventory corresponding to the target power material according to the order lead time, the demand change safety factor and the demand standard deviation; Determining a lead time consumption corresponding to the order lead time according to the forecast demand data, and calculating a reorder point corresponding to the target power material according to the lead time consumption and the safety stock; Determining an average demand based on the forecast demand data, and calculating a maximum inventory corresponding to the target power material based on the average demand, the order lead time, and the safety stock; The controlling of the target electric power material according to the inventory management strategy determined by the reorder point and the maximum inventory quantity includes: When the inventory of the target electric power material is not greater than the reorder point, obtaining the actual inventory of the target electric power material; The replenishment quantity corresponding to the target power material is calculated according to the maximum inventory quantity and the actual inventory quantity, and the target power material is replenished according to the replenishment quantity.

2. The method according to claim 1, characterized in that The determining of the comprehensive weight corresponding to each power material based on the value-related data and demand-related data respectively corresponding to the plurality of power materials includes: sorting the plurality of electric power materials based on value-related data corresponding to each of the plurality of electric power materials to obtain a first sorting result, and assigning a first weight to each electric power material according to the first sorting result; sorting the plurality of electric power materials based on demand-related data corresponding to each of the plurality of electric power materials to obtain a second sorting result, and assigning a second weight to each electric power material according to the second sorting result; A weighted calculation is performed on the first weight and the second weight corresponding to each electric power material to obtain a comprehensive weight corresponding to each electric power material.

3. The method according to claim 2, characterized in that The method further comprises: The electric power material having the comprehensive weight greater than the weight threshold is used as the target electric power material.

4. The method according to claim 1, wherein The method further comprises: Controlling the inventory of the target power material based on the inventory management strategy, and recording control data for a period of time; By comparing the control data with the relevant data of the demand forecast model, the relevant parameters of the demand forecast model are corrected according to the data comparison differences, and the demand forecast model is optimized.

5. An electric power material control device, characterized in that: The device comprises: a determination module configured to determine a target power material from a plurality of power materials based on value-related data and demand-related data of the power materials, wherein the value-related data is a value ratio of each of the power materials to the total power materials obtained by the ABC classification method, and the demand-related data is a demand ratio of each of the power materials to the total power materials obtained by the PRS classification method; A forecasting module, configured to obtain historical demand data of the target power material, input the historical demand data into a demand forecasting model, and obtain forecast demand data of the target power material; a parameter determination module, configured to determine a reorder point and a maximum inventory quantity corresponding to the target power material based on the predicted demand data; the reorder point is used to represent the quantity of the target power material when replenishment is required; a material management and control module, configured to manage and control the target power material according to an inventory management strategy determined by the reorder point and the maximum inventory level; The determining module is further configured to: Determine the comprehensive weight corresponding to each power material based on the value-related data and demand-related data corresponding to each of the multiple power materials; Obtaining electric power materials whose corresponding comprehensive weights meet preset conditions as target electric power materials; The prediction module is further configured to: Obtaining the demand benchmark value and equipment characteristics corresponding to the target power material; Building a neural network model based on the demand benchmark value and the device characteristics; Building a training set based on historical demand data samples of the target electric power material, wherein the training set includes training samples and training labels; Processing the training samples through the neural network model to obtain a prediction output; Constructing a cost function based on the difference between the predicted output and the training label, and determining an objective function based on the cost function and a regularization term; Training the neural network model based on the objective function until a training stop condition is reached, and using the trained neural network model as the demand forecasting model; The parameter determination module is further used to: Determine the order lead time and demand change safety factor corresponding to the target power material, where the order lead time is the time period from when the replenishment order is placed to when the replenishment material is put into storage; Calculate the demand standard deviation corresponding to the target power material according to the predicted demand data; Calculate the safety inventory corresponding to the target power material according to the order lead time, the demand change safety factor and the demand standard deviation; Determining a lead time consumption corresponding to the order lead time according to the forecast demand data, and calculating a reorder point corresponding to the target power material according to the lead time consumption and the safety stock; Determining an average demand based on the forecast demand data, and calculating a maximum inventory corresponding to the target power material based on the average demand, the order lead time, and the safety stock; The material control module is also used to: When the inventory of the target electric power material is not greater than the reorder point, obtaining the actual inventory of the target electric power material; The replenishment quantity corresponding to the target power material is calculated according to the maximum inventory quantity and the actual inventory quantity, and the target power material is replenished according to the replenishment quantity.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images