An intelligent agricultural wholesale goods sales management system

Abstract

This invention relates to the field of agricultural wholesale market management technology, specifically disclosing an intelligent agricultural wholesale goods sales management system. The system includes a goods sensing and data collection module, an intelligent warehouse management module, a multi-mode transaction matching module, a data processing module, a data analysis and decision support module, and a system management module. The goods sensing and data collection module automatically collects agricultural product attributes and inventory information. After the data processing module performs anomaly removal, missing data imputation, smoothing and noise reduction, seasonal correction, and Z-score standardization preprocessing, the data analysis and decision support module calculates a comprehensive health score based on the unsold inventory coefficient and the stockout risk coefficient, achieving a five-level classification assessment of inventory status. Furthermore, it monitors the supply-demand imbalance in real time through the supply-demand ratio and intelligently generates replenishment suggestions. This invention solves the problems of coexisting goods backlog and shortages and the lack of scientific basis for replenishment decisions in traditional agricultural wholesale market warehouse management, achieving dynamic balance management of stored goods.

Description

Technical Field

[0001] This invention relates to the field of agricultural wholesale market management technology, specifically to an intelligent agricultural wholesale goods sales management system. Background Technology

[0002] Agricultural wholesale markets are the core hubs in the agricultural product distribution system. In the daily operation of agricultural wholesale markets, warehousing management and sales are the most critical links, directly affecting the freshness of goods, spoilage rate, and overall operational efficiency of the market.

[0003] However, traditional agricultural wholesale markets face the following technical problems in the sale and storage management of goods:

[0004] (a) The structural imbalance of coexisting stockpiles and shortages of goods

[0005] Agricultural products are perishable and have short shelf lives, coupled with significant fluctuations in market demand. Under traditional management methods, wholesalers rely primarily on personal experience to determine the types and quantities of goods to purchase, lacking systematic data analysis of sales speed, inventory levels, and market demand trends. This leads to large stockpiles and spoilage of some goods, while others experience shortages due to untimely replenishment. This structural imbalance is a core pain point that agricultural wholesale markets have long faced.

[0006] (ii) The problem of lack of scientific basis for warehouse replenishment decisions

[0007] In existing agricultural wholesale markets, replenishment decisions mainly rely on manual experience and judgment, lacking comprehensive quantitative analysis of multi-dimensional information such as historical sales data, current inventory levels, and sales speed. Wholesalers often do not know "when to replenish, how much to replenish, and which items to prioritize," making replenishment decisions highly subjective and unpredictable. Furthermore, the raw data contains outliers, missing values, random noise, and seasonal fluctuations, and the lack of effective data preprocessing mechanisms results in insufficient accuracy and reliability of decision analysis.

[0008] Therefore, there is an urgent need for an intelligent agricultural wholesale goods sales management system that can replenish warehouses in a timely manner based on the sales situation, avoid inventory backlog or supply shortages, in order to solve the above-mentioned technical problems. Summary of the Invention

[0009] The purpose of this invention is to provide a remote data security storage method to solve the following technical problems:

[0010] How to adaptively improve the accuracy of network security judgments for requesting users.

[0011] The objective of this invention can be achieved through the following technical solutions:

[0012] An intelligent agricultural wholesale goods sales management system, the system comprising:

[0013] The cargo sensing and data collection module is configured at various cargo entrances, storage areas and trading areas of the agricultural wholesale market. It is used to automatically collect and identify information such as the type, weight, origin, storage time and shelf life of agricultural products, and record the quantity of various goods entering and leaving the warehouse and the current inventory in real time.

[0014] The intelligent warehouse management module is connected to the cargo sensing and acquisition module and is used to dynamically allocate storage locations based on cargo attribute information and monitor the inventory quantity, storage time and cargo status of various types of cargo in real time.

[0015] The multi-mode transaction matching module is used to record the sales status of various goods in real time, including the sales speed, sales volume, sales frequency and buyer demand information of each category of goods.

[0016] The data processing module is used to preprocess the massive amounts of data generated during system operation;

[0017] The data analysis and decision support module analyzes the pre-processed data, including inventory health diagnosis, supply and demand balance early warning, and intelligent replenishment suggestions, and provides decision-making basis to the warehouse replenishment decision module based on the analysis results;

[0018] The system management module is used for user permission management, system configuration, log auditing, and anomaly monitoring.

[0019] As a further description of the technical solution of the present invention, the data analysis and decision support module includes:

[0020] The inventory health diagnostic unit is used to calculate the slow-moving coefficient and stockout risk coefficient of various types of goods, and to score and classify the inventory status of each type of goods.

[0021] The supply and demand balance early warning unit is used to monitor the supply and demand ratio of various goods in real time. When the degree of supply exceeding demand or demand falling short of demand exceeds the set threshold, an early warning signal is automatically issued.

[0022] The intelligent replenishment suggestion unit is used to generate suggested replenishment quantities for various types of goods.

[0023] The visual decision dashboard unit is used to graphically display the inventory status, supply and demand balance, and decision-making suggestions for various goods.

[0024] As a further description of the technical solution of the present invention, in the inventory health diagnosis unit, the formula for calculating the slow-moving coefficient is: S=Savg−ScurSavg, where S is the slow-moving coefficient, Savg is the historical average sales speed of similar goods, and Scur is the current sales speed; when the slow-moving coefficient is greater than the first threshold, it is determined to be a stockpiled risk product, and when the slow-moving coefficient is less than the second threshold, it is determined to be a fast-moving product.

[0025] The formula for calculating the stockout risk coefficient is: R = Davg * TreQcur, where R is the stockout risk coefficient, Davg is the average daily sales volume, Tre is the replenishment lead time, and Qcur is the current inventory level. When the stockout risk coefficient is greater than the third threshold, the goods are judged to be at risk of shortage.

[0026] As a further description of the technical solution of the present invention, the process of scoring and classifying the health status of each type of goods includes:

[0027] The overall health score for each type of goods is calculated using the following weighted formula:

[0028] H=100*1−ω1*min1,SSmax−ω2*min1,R−1Rmax−1;

[0029] In the formula, H is the overall health score, ranging from 0 to 100; Smax is the maximum reference value for the slow-moving coefficient; Rmax is the maximum reference value for the stockout risk coefficient; ω1 and ω2 are system-set weighting coefficients. Based on the numerical range of the overall health score H, the inventory status is divided into the following five levels:

[0030] When H≥80, the inventory status is healthy; when 60≤H<80, the inventory status is good with slight fluctuations; when 40≤H<60, the inventory status is average with a tendency to be unbalanced; when 20≤H<40, the inventory status is poor with a risk of overstocking or shortage; when H<20, the inventory status is critical with severe overstocking or shortage.

[0031] As a further description of the technical solution of the present invention, in the supply and demand balance early warning unit, the formula for calculating the supply and demand ratio is: F=QcurXavg∗Tf, where F is the supply and demand ratio, Xavg is the predicted daily average demand, and Tf is the prediction period. When F is greater than the corresponding upper limit threshold, it is determined to be a state of supply exceeding demand, and when F is less than the corresponding lower limit threshold, it is determined to be a state of supply falling short of demand.

[0032] As a further description of the technical solution of the present invention, the working principle of the intelligent replenishment suggestion unit in generating suggested replenishment quantities for various types of goods is as follows:

[0033] First, determine the replenishment trigger conditions:

[0034] When the health level is poor or critical and the inventory status type is shortage risk-dominant or dual risk, a replenishment recommendation is triggered unconditionally.

[0035] When the supply-demand ratio F is less than the corresponding lower threshold, an emergency replenishment recommendation is triggered.

[0036] When the slow-moving inventory coefficient exceeds the first threshold, and the inventory status is dominated by overstock risk, replenishment suggestions will not be triggered; instead, the overstock disposal process will be initiated.

[0037] As a further description of the technical solution of this invention, it is suggested that the replenishment quantity be calculated using the following piecewise function:

[0038] Qa = maxQmin, α∗Davg∗Tre−Qcur (Shortage risk-dominated type) maxQmin, β∗Davg∗Tre−Qcur+Qs (Dual risk type) 0 (Overstock risk-dominated type or supply-demand balance type and Qcur>Qt);

[0039] In the formula, Qa is the suggested replenishment quantity; Qmin is the minimum replenishment batch size, preset according to the product category; α is the shortage risk replenishment coefficient set by the system, dynamically adjusted according to the health score: the lower H is, the larger α is; β is the dual risk replenishment coefficient set by the system; Qs is the safety stock quantity; and Qt is the target stock quantity.

[0040] As a further description of the technical solution of the present invention, the safety stock is calculated by the following formula: Qs=k∗σday∗Tre, where k is the system-set safety factor and σday is the standard deviation of daily sales.

[0041] The target inventory level is calculated using the following formula: Qt = Davg * Tre + Qs.

[0042] The beneficial effects of this invention are as follows: 1. This invention calculates the slow-moving coefficient and stockout risk coefficient through an inventory health diagnostic unit, and assigns a comprehensive health score to each type of goods, classifying them into five levels, thereby achieving quantitative assessment and accurate identification of inventory status. When a risk of overstocking is identified, the overstocking process is automatically triggered; when a risk of shortage is identified, replenishment suggestions are automatically triggered. This effectively solves the structural imbalance problem of coexisting overstocking and shortages under traditional management methods, reduces the loss rate of agricultural products, and improves market operation efficiency.

[0043] 2. This invention uses a data processing module to perform anomaly removal, missing data imputation, smoothing and noise reduction, seasonal correction, and Z-score standardization preprocessing on the raw data to ensure the accuracy and reliability of decision-making data. The intelligent replenishment suggestion unit uses a piecewise function to quantitatively calculate the suggested replenishment quantity based on the health level, supply-demand ratio, and inventory status type. It combines the safety stock and target inventory as decision boundaries to provide wholesalers with scientific basis for replenishment quantity, timing, and priority, overcoming the subjectivity and blindness of human experience-based decision-making. Attached Figure Description

[0044] The invention will now be further described with reference to the accompanying drawings.

[0045] Figure 1 This is a schematic diagram of the outline of the intelligent agricultural wholesale goods sales management system of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Please see Figure 1 As shown, an intelligent agricultural wholesale goods sales management system is provided, the system comprising:

[0048] The cargo sensing and data collection module is configured at various cargo entrances, storage areas and trading areas of the agricultural wholesale market. It is used to automatically collect and identify information such as the type, weight, origin, storage time and shelf life of agricultural products, and record the quantity of various goods entering and leaving the warehouse and the current inventory in real time.

[0049] The intelligent warehouse management module is connected to the cargo sensing and acquisition module and is used to dynamically allocate storage locations based on cargo attribute information and monitor the inventory quantity, storage time and cargo status of various types of cargo in real time.

[0050] The multi-mode transaction matching module is used to record the sales status of various goods in real time, including the sales speed, sales volume, sales frequency and buyer demand information of each category of goods.

[0051] The data processing module is used to preprocess the massive amounts of data generated during system operation: it uses the interquartile range method to detect and remove abnormal sales data, and performs hierarchical filling of missing data through linear interpolation, similar mean interpolation, or SARIMA model; it uses the exponential weighted moving average method to smooth and reduce noise in the sales speed sequence, eliminating the impact of random fluctuations on the calculation of the sluggish sales coefficient; it extracts seasonal factors to decompose and correct the daily average sales volume using an additive model, eliminating periodic interference from weeks, months, and holidays; finally, it performs Z-score standardization on all input features to eliminate the differences in magnitude between different categories of goods, making the standardized data mean 0 and the standard deviation 1, thereby ensuring that the replenishment decision model is not affected by the dimension, improving the accuracy of replenishment suggestions and the model's generalization ability;

[0052] The data analysis and decision support module analyzes the pre-processed data, including inventory health diagnosis, supply and demand balance early warning, and intelligent replenishment suggestions, and provides decision-making basis to the warehouse replenishment decision module based on the analysis results;

[0053] The system management module is used for user permission management, system configuration, log auditing, and anomaly monitoring.

[0054] Through the above technical solution, this invention first automatically collects information such as the type, weight, origin, warehousing time, and shelf life of agricultural products through the cargo sensing and collection module, and records the quantity of goods entering and leaving the warehouse and the inventory in real time; at the same time, the multi-mode transaction matching module records the sales speed, sales volume, sales frequency, and buyer demand information of each category of goods in real time. The collected raw data enters the data processing module for preprocessing: abnormal sales data is removed using the interquartile range method; missing data is filled in hierarchically through linear interpolation, mean interpolation of the same type, or SARIMA model; the sales speed sequence is smoothed and denoised using the exponential weighted moving average method to eliminate the influence of random fluctuations; seasonal factors are extracted and the daily average sales volume is decomposed using an additive model to eliminate periodic interference; finally, all input features are Z-score standardized to eliminate dimensional differences. The preprocessed data is fed into the data analysis and decision support module. The module's inventory health diagnosis unit calculates a comprehensive health score H based on the slow-moving inventory coefficient and the stockout risk coefficient, classifying inventory status into five levels from excellent to critical. The supply-demand balance early warning unit monitors the supply-demand ratio in real time to detect oversupply or undersupply and issues early warnings. The intelligent replenishment suggestion unit determines whether to trigger replenishment based on the health level, supply-demand ratio F, and inventory status type (shortage risk-dominated, dual risk, or overstock risk-dominated), and calculates the suggested replenishment quantity using a piecewise function, while introducing safety stock and target inventory levels as reference boundaries for replenishment decisions. Finally, the warehouse replenishment decision module generates replenishment quantity, timing, and priority strategies based on the analysis results, achieving dynamic balance management of warehouse goods. The system management module is responsible for access control, log auditing, and anomaly monitoring, thus forming a complete intelligent closed-loop management system for agricultural wholesale goods sales.

[0055] As a further description of the technical solution of the present invention, the data analysis and decision support module includes:

[0056] The inventory health diagnostic unit is used to calculate the slow-moving coefficient and stockout risk coefficient of various types of goods, and to score and classify the inventory status of each type of goods.

[0057] The supply and demand balance early warning unit is used to monitor the supply and demand ratio of various goods in real time. When the degree of supply exceeding demand or demand falling short of demand exceeds the set threshold, an early warning signal is automatically issued.

[0058] The intelligent replenishment suggestion unit is used to generate suggested replenishment quantities for various types of goods.

[0059] The visual decision dashboard unit is used to graphically display the inventory status, supply and demand balance, and decision-making suggestions for various goods.

[0060] As a further description of the technical solution of the present invention, in the inventory health diagnosis unit, the formula for calculating the slow-moving coefficient is: S=Savg−ScurSavg, where S is the slow-moving coefficient, Savg is the historical average sales speed of similar goods, and Scur is the current sales speed; when the slow-moving coefficient is greater than the first threshold, it is determined to be a stockpiled risk product, and when the slow-moving coefficient is less than the second threshold, it is determined to be a fast-moving product.

[0061] The formula for calculating the stockout risk coefficient is: R = Davg * TreQcur, where R is the stockout risk coefficient, Davg is the average daily sales volume, Tre is the replenishment lead time, and Qcur is the current inventory level. When the stockout risk coefficient is greater than the third threshold, the goods are judged to be at risk of shortage.

[0062] As a further description of the technical solution of the present invention, the process of scoring and classifying the health status of each type of goods includes:

[0063] The overall health score for each type of goods is calculated using the following weighted formula:

[0064] H=100*1−ω1*min1,SSmax−ω2*min1,R−1Rmax−1;

[0065] In the formula, H is the overall health score, ranging from 0 to 100; Smax is the maximum reference value for the slow-moving coefficient; Rmax is the maximum reference value for the stockout risk coefficient; ω1 and ω2 are system-set weighting coefficients. Based on the numerical range of the overall health score H, the inventory status is divided into the following five levels:

[0066] When H≥80, the inventory status is healthy; when 60≤H<80, the inventory status is good with slight fluctuations; when 40≤H<60, the inventory status is average with a tendency to be unbalanced; when 20≤H<40, the inventory status is poor with a risk of overstocking or shortage; when H<20, the inventory status is critical with severe overstocking or shortage.

[0067] Using the above technical solution, firstly, the inventory health diagnosis unit determines whether goods are at risk of overstocking (when S is greater than the first threshold) or in a fast-moving state (when S is less than the second threshold) by calculating the slow-moving coefficient S = Savg − ScurSavg. Simultaneously, it determines whether there is a shortage risk (when R is greater than the third threshold) by using the stockout risk coefficient R = Davg∗TreQcur. Based on these two coefficients, a weighted formula H = 100∗1−ω1∗min1,SSmax−ω2∗min1,R−1Rmax−1 is used to calculate the comprehensive health score H. Finally, the inventory status is divided into five levels based on the H value.

[0068] As a further description of the technical solution of the present invention, in the supply and demand balance early warning unit, the formula for calculating the supply and demand ratio is: F=QcurXavg∗Tf, where F is the supply and demand ratio, Xavg is the predicted daily average demand, and Tf is the prediction period. When F is greater than the corresponding upper limit threshold, it is determined to be a state of supply exceeding demand, and when F is less than the corresponding lower limit threshold, it is determined to be a state of supply falling short of demand.

[0069] As a further description of the technical solution of the present invention, the working principle of the intelligent replenishment suggestion unit in generating suggested replenishment quantities for various types of goods is as follows:

[0070] First, determine the replenishment trigger conditions:

[0071] When the health level is poor or critical and the inventory status type is shortage risk-dominant or dual risk, a replenishment recommendation is triggered unconditionally.

[0072] When the supply-demand ratio F is less than the corresponding lower threshold, an emergency replenishment recommendation is triggered.

[0073] When the slow-moving inventory coefficient exceeds the first threshold, and the inventory status is dominated by overstock risk, replenishment suggestions will not be triggered; instead, the overstock disposal process will be initiated.

[0074] As a further description of the technical solution of this invention, it is suggested that the replenishment quantity be calculated using the following piecewise function:

[0075] Qa = maxQmin, α∗Davg∗Tre−Qcur (Shortage risk-dominated type) maxQmin, β∗Davg∗Tre−Qcur+Qs (Dual risk type) 0 (Overstock risk-dominated type or supply-demand balance type and Qcur>Qt);

[0076] In the formula, Qa is the suggested replenishment quantity; Qmin is the minimum replenishment batch size, preset according to the product category; α is the shortage risk replenishment coefficient set by the system, dynamically adjusted according to the health score: the lower H is, the larger α is; β is the dual risk replenishment coefficient set by the system; Qs is the safety stock quantity; and Qt is the target stock quantity.

[0077] As a further description of the technical solution of the present invention, the safety stock is calculated by the following formula: Qs=k∗σday∗Tre, where k is the system-set safety factor and σday is the standard deviation of daily sales.

[0078] The target inventory level is calculated using the following formula: Qt = Davg * Tre + Qs.

[0079] Through the above technical solution, firstly, the intelligent replenishment suggestion unit unconditionally triggers replenishment suggestions based on the inventory health level (poor or critical) and inventory status type (shortage risk-dominated or dual risk type). When the supply-demand ratio F is lower than the lower threshold, an emergency replenishment suggestion is triggered. However, when the unsold inventory coefficient is greater than the first threshold (overstock risk-dominated), replenishment is not triggered, and instead, an overstocking process is initiated. After replenishment is triggered, a piecewise function is used to calculate the suggested replenishment quantity: under the shortage risk-dominated type, Qa = maxQmin, α∗Davg∗Tre−Qcur; under the dual risk type, Qa = maxQmin, β∗Davg∗Tre−Qcur+Qs; under the overstock risk-dominated type or the supply-demand balance type, and when the current inventory exceeds the target inventory, the replenishment quantity is 0. The safety stock quantity is calculated using Qs = k∗σday∗Tre, and the target inventory quantity is calculated using Qt =Davg∗Tre+Qs, thus providing a scientific quantity boundary for replenishment decisions.

[0080] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. An intelligent agricultural wholesale goods sales management system, characterized in that, The system includes: The cargo sensing and data collection module is configured at various cargo entrances, storage areas and trading areas of the agricultural wholesale market. It is used to automatically collect and identify information such as the type, weight, origin, storage time and shelf life of agricultural products, and record the quantity of various goods entering and leaving the warehouse and the current inventory in real time. The intelligent warehouse management module is connected to the cargo sensing and acquisition module and is used to dynamically allocate storage locations based on cargo attribute information and monitor the inventory quantity, storage time and cargo status of various types of cargo in real time. The multi-mode transaction matching module is used to record the sales status of various goods in real time, including the sales speed, sales volume, sales frequency and buyer demand information of each category of goods. The data processing module is used to preprocess the massive amounts of data generated during system operation; The data analysis and decision support module analyzes the pre-processed data, including inventory health diagnosis, supply and demand balance early warning, and intelligent replenishment suggestions, and provides decision-making basis to the warehouse replenishment decision module based on the analysis results; The system management module is used for user permission management, system configuration, log auditing, and anomaly monitoring.

2. The intelligent agricultural wholesale goods sales management system according to claim 1, characterized in that, The data analysis and decision support module includes: The inventory health diagnostic unit is used to calculate the slow-moving coefficient and stockout risk coefficient of various types of goods, and to score and classify the inventory status of each type of goods. The supply and demand balance early warning unit is used to monitor the supply and demand ratio of various goods in real time. When the degree of supply exceeding demand or demand falling short of demand exceeds the set threshold, an early warning signal is automatically issued. The intelligent replenishment suggestion unit is used to generate suggested replenishment quantities for various types of goods. The visual decision dashboard unit is used to graphically display the inventory status, supply and demand balance, and decision-making suggestions for various goods.

3. The intelligent agricultural wholesale goods sales management system according to claim 2, characterized in that, In the inventory health diagnostic unit, the formula for calculating the slow-moving inventory coefficient is as follows: In the formula, This is the slow-moving coefficient. This is the historical average sales speed for similar goods. The current sales speed is used as the indicator. When the slow-moving coefficient is greater than the first threshold, the goods are judged as having a risk of overstocking. When the slow-moving coefficient is less than the second threshold, the goods are judged as fast-moving goods. The formula for calculating the stockout risk coefficient is as follows: In the formula, To account for the risk of stockouts, This represents the average daily sales volume. To allow for lead time for replenishment, This represents the current inventory level; goods are considered to be at risk of shortage when the stockout risk coefficient exceeds the third threshold.

4. The intelligent agricultural wholesale goods sales management system according to claim 3, characterized in that, The process of scoring and classifying the inventory status of each type of goods includes: The overall health score for each type of goods is calculated using the following weighted formula: ； In the formula, The overall health score ranges from 0 to 100. This is the maximum reference value for the slow-moving inventory coefficient. This is the maximum reference value for the out-of-stock risk factor. and Set weighting coefficients for the system based on the overall health score. Based on the numerical range, the inventory status of goods is divided into the following five levels: when When ≥80, the inventory status is healthy; when 60≤ When the inventory level is <80, the inventory status is good, with slight fluctuations; when 40 ≤ When the inventory level is <60, the inventory status is generally normal, with a tendency towards imbalance; when 20 ≤ When the inventory level is less than 40, the inventory status is poor, and there is a risk of overstocking or shortage; when When the inventory level is below 20, the inventory situation is critical, with severe overstocking or severe shortage.

5. The intelligent agricultural wholesale goods sales management system according to claim 3, characterized in that, In the supply and demand balance early warning unit, the formula for calculating the supply-demand ratio is: In the formula, The supply-demand ratio, To predict average daily demand, To predict the cycle, when When F is greater than the corresponding upper limit threshold, it is determined to be a state of supply exceeding demand; when F is less than the corresponding lower limit threshold, it is determined to be a state of supply falling short of demand.

6. A remote data security storage method according to claim 3, characterized in that, The working principle of the intelligent replenishment suggestion unit in generating suggested replenishment quantities for various types of goods is as follows: First, determine the replenishment trigger conditions: When the health level is poor or critical and the inventory status type is shortage risk-dominant or dual risk, a replenishment recommendation is triggered unconditionally. When the supply-demand ratio When the stock level falls below the corresponding lower threshold, an emergency replenishment recommendation is triggered. When the slow-moving coefficient is greater than the first threshold, and the inventory status is dominated by backlog risk, replenishment suggestions will not be triggered, but instead the backlog handling process will be triggered.

7. A remote data security storage method according to claim 6, characterized in that, The recommended replenishment quantity is calculated using the following piecewise function: ； In the formula, This is the suggested replenishment quantity; Minimum replenishment quantity is preset based on product category; The shortage risk replenishment coefficient set for the system is dynamically adjusted based on the health score: The lower, The larger; The dual-risk replenishment coefficient set for the system, To maintain a safety stock level, The target inventory level.

8. A remote data security storage method according to claim 7, characterized in that, Safety stock is calculated using the following formula: In the formula, k is the system-defined safety factor. The standard deviation of daily sales volume; The target inventory level is calculated using the following formula: .

Images