Supply chain intelligent replenishment method and system based on data analysis

Abstract

The invention discloses a supply chain intelligent replenishment method and system based on data analysis, and relates to the technical field of intelligent replenishment, during the operation of the system, supply chain related data is collected, sales data, inventory data and supplier data are obtained as a supply chain data set, and the supply chain data set is transmitted to a data preprocessing module; the collected supply chain data set is preprocessed to form a first data set, a second data set and a third data set, a supply chain performance index Gyjx is obtained after calculation, historical sales data and market trend analysis are utilized to predict product demands in a period of time in the future, and a supply chain performance index Gyjx is obtained. The supply chain performance index Gyjx is compared with a preset standard threshold value M and a preset standard threshold value N, a replenishment strategy is obtained, an inventory strategy and replenishment parameters are dynamically adjusted according to demand prediction and inventory conditions, operation conditions and inventory changes of all links of the supply chain are monitored in real time, abnormal conditions are found, and early warning is carried out in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent replenishment, and specifically to a method and system for intelligent replenishment of a supply chain based on data analysis. Background Art

[0002] With the booming development of the e-commerce industry, enterprises are facing increasingly complex supply chain management challenges. With the diversification of consumer demands and the intensification of market competition, enterprises need to ensure that they can meet customer demands in a timely manner while minimizing inventory costs and reducing inventory risks. As one of the crucial links in supply chain management, supply chain replenishment is directly related to the operational efficiency of enterprises and customer satisfaction.

[0003] However, traditional supply chain management methods often face problems such as difficulties in data acquisition, information asymmetry, and slow response speed, resulting in the lag and inaccuracy of decision-making. At the same time, the lack of scientific data analysis and prediction capabilities makes it difficult for enterprises to cope with the rapid changes and uncertainties in the market. In addition, traditional supply chain replenishment methods are usually based on fixed replenishment cycles and fixed replenishment quantities, lacking pertinence and flexibility, and it is difficult to meet the demand characteristics of different products and the requirements of market changes. Enterprises often face problems such as untimely replenishment, excessive or insufficient replenishment quantities, etc., which affect the stable operation of the supply chain and customer satisfaction. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method and system for intelligent replenishment of a supply chain based on data analysis, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent replenishment system for a supply chain based on data analysis, including a data collection module, a data preprocessing module, an intelligent prediction module, an order placement module, an inventory optimization and dynamic adjustment module, and a real-time monitoring module;

[0006] The data collection module is used to collect supply chain-related data, and the data sources include a sales system, an inventory system, and a supplier system, to obtain: sales data, inventory data, and supplier data, as a supply chain data set, and transmit it to the data preprocessing module;

[0007] The data preprocessing module is used to clean, transform, and organize the collected supply chain data set, remove duplicate, missing, or abnormal data, and form a first data group, a second data group, and a third data group;

[0008] The intelligent prediction module is used to use a prediction algorithm to predict future demands from the data preprocessing module, and after calculation, obtain: a supply chain performance index Gyjx;

[0009] The order module is used to predict the product demand in a future period by using historical sales data and market trend analysis, and obtain a replenishment strategy by comparing the supply chain performance index Gyjx with the preset standard thresholds M and N.

[0010] The inventory optimization dynamic adjustment module dynamically adjusts the inventory strategy and replenishment parameters according to the demand forecast and inventory situation to achieve the optimization and maximum utilization of inventory.

[0011] The real-time monitoring module is used to monitor the operation status of each link of the supply chain and inventory changes in real time, discover abnormal situations and give early warnings.

[0012] Preferably, the data collection module includes a sales data collection unit, an inventory data collection unit, and a supplier data collection unit.

[0013] The sales data collection unit is used to obtain sales-related data from the sales system, including sales order information, sales amount, sales quantity, sales channels, and sales regions.

[0014] The inventory data collection unit is used to obtain inventory-related data from the inventory system, including the current inventory quantity of each SKU, inventory turnover, inventory cost, and inventory satisfaction.

[0015] The supplier data collection unit is used to obtain supplier-related data from the supplier system, including supplier information, supplier delivery capacity, supplier price, and supplier quality evaluation.

[0016] Preferably, the data preprocessing module includes a data preprocessing unit and a data group analysis unit.

[0017] The data preprocessing unit is used to clean the supply chain data set, remove duplicate, missing, or abnormal data therein, and normalize the cleaned supply chain data.

[0018] The data group analysis unit is used to obtain relevant data from the preprocessed sales data, inventory data, and supplier data, and obtain a first data group, a second data group, and a third data group.

[0019] The first data group includes the order fulfillment rate Ddly, the product out-of-stock rate Spqh, the order processing duration Ddcl, the order on-time delivery rate Zsjf, and the product return rate Thl.

[0020] The second data group includes the average inventory turnover rate Pjkc, the inventory cost ratio Kzcb, the inventory satisfaction rate Kcmz, the category inventory coverage rate Kcfg, and the proportion of overdue inventory products Yqcp.

[0021] The third data set includes the real-time order processing speed Ssdd, the real-time inventory allocation speed Ssdp, the real-time supply chain collaborative response speed Gyxy, the real-time market trend analysis accuracy rate Qszq, and the real-time commodity sales forecast accuracy rate Xszq.

[0022] Preferably, the intelligent prediction module includes a prediction algorithm unit;

[0023] The prediction algorithm unit is used to calculate and obtain, by using the predicted demand data and other indicators related to the supply chain performance: the supply chain performance index Gyjx, the order management coefficient Ddgl, the inventory management coefficient Kcgl, and the supply chain response ability coefficient Gyxy;

[0024] The supply chain performance index Gyjx is calculated and obtained through the following formula:

[0025] ;

[0026] In the formula, Ddgl represents the order management coefficient, Kcgl represents the inventory management coefficient, Gyxy represents the supply chain response ability coefficient, and q, w, and e respectively represent the proportionality coefficients of the order management coefficient Ddgl, the inventory management coefficient Kcgl, and the supply chain response ability coefficient Gyxy;

[0027] Among them, , , , and , R represents the first correction constant;

[0028] The order management coefficient Ddgl is calculated and obtained through the following formula:

[0029] ;

[0030] In the formula, Ddly represents the order fulfillment rate, Spqh represents the commodity out-of-stock rate, Ddcl represents the order processing duration, Zsjf represents the order on-time delivery rate, Thl represents the commodity return rate, and t, y, u, i, and o respectively represent the proportionality coefficients of the order fulfillment rate Ddly, the commodity out-of-stock rate Spqh, the order processing duration Ddcl, the order on-time delivery rate Zsjf, and the commodity return rate Thl;

[0031] Among them, , , , , , and , P represents the second correction constant.

[0032] Preferably, the inventory management coefficient Kcgl is calculated and obtained through the following formula:

[0033] ;

[0034] In the formula, Pjkc represents the average inventory turnover rate, Kzcb represents the proportion of inventory cost, Kcmz represents the inventory satisfaction rate, Kcfg represents the category inventory coverage rate, Yqcp represents the proportion of overdue inventory products, and a, s, d, f, and g respectively represent the proportionality coefficients of the average inventory turnover rate Pjkc, the proportion of inventory cost Kzcb, the inventory satisfaction rate Kcmz, the category inventory coverage rate Kcfg, and the proportion of overdue inventory products Yqcp;

[0035] Among them, , , , , , and , where H represents the third correction constant.

[0036] Preferably, the supply chain response ability coefficient Gyxy is obtained by calculating through the following formula:

[0037] ;

[0038] In the formula, Ssdd represents the real-time order processing speed, Ssdp represents the real-time inventory allocation speed, Gyxy represents the real-time supply chain collaborative response speed, Qszq represents the accuracy rate of real-time market trend analysis, Xszq represents the accuracy rate of real-time commodity sales forecast, and h, j, k, z, and x respectively represent the proportionality coefficients of the real-time order processing speed Ssdd, the real-time inventory allocation speed Ssdp, the real-time supply chain collaborative response speed Gyxy, the accuracy rate of real-time market trend analysis Qszq, and the accuracy rate of real-time commodity sales forecast Xszq;

[0039] Among them, , , , , , and , where L represents the fourth correction constant.

[0040] Preferably, the order module includes a trend analysis unit and a replenishment strategy formulation unit;

[0041] The trend analysis unit is used to identify factors such as sales trends, periodic changes, and seasonal impacts by analyzing historical sales data, and combine market research to predict future product demand;

[0042] The replenishment strategy formulation unit is used to compare and analyze the predicted product demand by the ordering module and the supply chain performance indicators, including inventory turnover, stockouts, and order fulfillment, with the preset standard threshold M and the preset standard threshold N, and formulate a replenishment level strategy, including the replenishment quantity, replenishment timing, and replenishment priority;

[0043] When Gyjx < M, obtain the first replenishment level, indicating that the supply chain performance does not meet the standard and emergency replenishment is required;

[0044] When M ≤ Gyjx < N, obtain the second replenishment level, indicating that the supply chain performance is 20% lower than the standard progress, and gradually increase the replenishment quantity to replenish twice a week;

[0045] When Gyjx ≥ N, obtain the third replenishment level, indicating that the supply chain performance meets the standard, keep the existing replenishment plan unchanged, and adopt small-batch replenishment or flexibly adjust the replenishment plan according to demand.

[0046] Preferably, the inventory optimization dynamic adjustment module includes an inventory strategy adjustment unit and a replenishment parameter adjustment unit;

[0047] The inventory strategy adjustment unit dynamically adjusts the inventory strategy, including the safety inventory level, reorder point, and order point, according to the prediction results of the demand forecasting module and the current inventory situation, and flexibly adjusts the inventory strategy according to the changes in market demand and the supply chain performance index;

[0048] The replenishment parameter adjustment unit dynamically adjusts the replenishment parameters, including the replenishment quantity, replenishment timing, and replenishment frequency, according to the prediction results of the demand forecasting module and the current inventory situation, and flexibly adjusts the replenishment parameters according to the changes in the supply chain performance index and market demand to achieve inventory optimization and rapid response to demand.

[0049] Preferably, the real-time monitoring module includes a supply chain operation monitoring unit, an inventory change monitoring unit, and an alarm unit;

[0050] The supply chain operation monitoring unit is used to track the operation of each link of the supply chain in real time by monitoring the data of the sales system, inventory system, and logistics system, including the order processing speed, inventory change, and logistics distribution status, and timely detect abnormal situations in the supply chain operation by setting monitoring indicators and thresholds;

[0051] The inventory change monitoring unit is used to monitor the inventory data in the inventory system, track the changes in the inventory levels of each SKU in real time, timely detect abnormal situations of low or high inventory levels by setting appropriate inventory warning indicators and thresholds, and at the same time monitor the indicators of inventory turnover rate and inventory cost to evaluate the effectiveness of inventory management and cost control;

[0052] The alarm unit is used to send alarm information to relevant personnel in real time. When an abnormal situation is detected, corresponding alarm information is generated, including the type of abnormality, severity, and scope of influence. The alarm information is transmitted to relevant personnel or departments in a timely manner, including supply chain managers, inventory managers, and logistics teams. The handling situation of the alarm is monitored, the resolution progress of the alarm is tracked, the alarm information is recorded and analyzed, and the frequency, type, and cause of the alarm are evaluated.

[0053] An intelligent replenishment method for the supply chain based on data analysis, comprising the following steps:

[0054] Step 1: Collect supply chain-related data. The data sources include the sales system, inventory system, and supplier system. Obtain sales data, inventory data, and supplier data as the supply chain data set and transmit it to the data preprocessing module.

[0055] Step 2: Clean, transform, and organize the collected supply chain data set to remove duplicate, missing, or abnormal data, forming a first data group, a second data group, and a third data group.

[0056] Step 3: Use a prediction algorithm in the data preprocessing module to predict future demand, and obtain the supply chain performance index Gyjx after calculation.

[0057] Step 4: Use historical sales data and market trend analysis to predict the product demand within a certain period in the future. By comparing the supply chain performance index Gyjx with a preset standard threshold M and a preset standard threshold N, obtain a replenishment strategy.

[0058] Step 5: Dynamically adjust the inventory strategy and replenishment parameters according to demand prediction and inventory situation to achieve the optimization and maximum utilization of inventory.

[0059] Step 6: Monitor the operation status of each link in the supply chain and inventory changes in real time, detect abnormal situations and give early warnings.

[0060] The present invention provides an intelligent replenishment method and system for the supply chain based on data analysis, having the following beneficial effects:

[0061] (1)When the system is running, it collects relevant supply chain data and obtains: sales data, inventory data, and supplier data, which are used as the supply chain data set. The data set is then transmitted to the data preprocessing module for preprocessing, forming the first data group, the second data group, and the third data group. After calculation, the supply chain performance index Gyjx is obtained. Using historical sales data and market trend analysis, the product demand for a period of time in the future is predicted. By comparing the supply chain performance index Gyjx with the preset standard threshold M and the preset standard threshold N, a replenishment strategy is obtained. Based on the demand prediction and inventory situation, the inventory strategy and replenishment parameters are dynamically adjusted, and the operation status of each link in the supply chain and inventory changes are monitored in real time to detect abnormal situations and give early warnings.

[0062] (2)Through accurate demand prediction and dynamic inventory management, the system can reduce the risks of excessive inventory and out-of-stock situations, thereby reducing inventory costs and capital occupancy. The real-time monitoring module can promptly detect and resolve abnormal situations in the supply chain, further improving the operation efficiency and stability of the supply chain. Using historical sales data and market trend analysis, the system can formulate a more reasonable replenishment strategy to ensure the balance between product supply and demand, avoiding losses caused by out-of-stock or overstock situations. By ensuring the timely supply of products and reducing out-of-stock situations, customer satisfaction can be enhanced, and customer trust and loyalty to the brand can be strengthened.

[0063] (3)Through the sales data collection unit, inventory data collection unit, and supplier data collection unit, the system can accurately collect the required data from each link, providing a reliable data basis for subsequent analysis and decision-making. The data preprocessing unit can clean, transform, and organize the collected data, removing duplicate, missing, or abnormal data, thereby improving the quality and accuracy of the data. The data group analysis unit groups and analyzes the data according to different dimensions, forming the first data group, the second data group, and the third data group, providing multi-angle and comprehensive data support for subsequent decision-making.

[0064] (4)The intelligent prediction module uses prediction algorithms to predict future demand and formulates a replenishment strategy in combination with historical sales data and market trend analysis. It can more accurately predict future demand and formulate corresponding replenishment strategies, thereby reducing inventory risks and improving supply chain efficiency. The inventory optimization and dynamic adjustment module can dynamically adjust the inventory strategy and replenishment parameters according to the demand prediction and inventory situation, realizing the optimization and maximization utilization of inventory, and further enhancing supply chain efficiency and reducing costs. The real-time monitoring module can monitor the operation status of each link in the supply chain and inventory changes in real time, detect abnormal situations and give early warnings, which helps to adjust and handle in a timely manner to ensure the stable operation of the supply chain. Description of the Drawings

[0065] Figure 1Schematic diagram of the block diagram process of an intelligent supply chain replenishment system based on data analysis according to the present invention;

[0066] Figure 2 Schematic diagram of the steps of an intelligent supply chain replenishment method based on data analysis according to the present invention. Specific embodiments

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. With the booming development of the e-commerce industry, enterprises are facing increasingly complex supply chain management challenges. With the diversification of consumer demands and the intensification of market competition, enterprises need to ensure that they can meet customer demands in a timely manner while minimizing inventory costs and reducing inventory risks. Supply chain replenishment, as one of the crucial links in supply chain management, is directly related to the operational efficiency and customer satisfaction of enterprises.

[0068] However, traditional supply chain management methods often face problems such as difficult data acquisition, information asymmetry, slow response speed, etc., resulting in the lag and inaccuracy of decision-making. At the same time, the lack of scientific data analysis and prediction capabilities makes it difficult for enterprises to cope with the rapid changes and uncertainties in the market. In addition, traditional supply chain replenishment methods are usually based on fixed replenishment cycles and fixed replenishment quantities, lacking pertinence and flexibility, and are difficult to meet the demand characteristics of different products and the requirements of market changes. Enterprises often face problems such as untimely replenishment, excessive or insufficient replenishment quantities, etc., affecting the stable operation of the supply chain and customer satisfaction.

[0069] Embodiment 1

[0070] The present invention provides an intelligent supply chain replenishment system based on data analysis. Please refer to Figure 1 , which includes a data acquisition module, a data preprocessing module, an intelligent prediction module, an ordering module, an inventory optimization dynamic adjustment module, and a real-time monitoring module;

[0071] The data acquisition module is used to collect supply chain-related data. The data sources include the sales system, the inventory system, and the supplier system, and obtain: sales data, inventory data, and supplier data, as the supply chain data set, and transmit it to the data preprocessing module;

[0072] The data preprocessing module is used to clean, transform, and organize the collected supply chain data set, remove duplicate, missing, or abnormal data, and form a first data group, a second data group, and a third data group;

[0073] The intelligent prediction module is used to predict future demands from the data preprocessing module using prediction algorithms, and after calculation, obtain: the supply chain performance index Gyjx;

[0074] The order placement module is used to predict product demands within a future period using historical sales data and market trend analysis, and by comparing the supply chain performance index Gyjx with a preset standard threshold M and a preset standard threshold N, obtain a replenishment strategy;

[0075] The inventory optimization and dynamic adjustment module dynamically adjusts inventory strategies and replenishment parameters according to demand forecasts and inventory situations, to achieve optimization and maximum utilization of inventory;

[0076] The real-time monitoring module is used to monitor the operation status of each link in the supply chain and inventory changes in real time, detect abnormal situations and give early warnings.

[0077] In this embodiment, relevant data of the supply chain is collected. The data sources include the sales system, the inventory system, and the supplier system, and obtain: sales data, inventory data, and supplier data, which are used as the supply chain dataset, and transmitted to the data preprocessing module. The collected supply chain dataset is cleaned, transformed, and sorted to remove duplicate, missing, or abnormal data, forming the first data group, the second data group, and the third data group. Predict future demands from the data preprocessing module using prediction algorithms, and after calculation, obtain: the supply chain performance index Gyjx, use historical sales data and market trend analysis to predict product demands within a future period, compare the supply chain performance index Gyjx with a preset standard threshold M and a preset standard threshold N to obtain a replenishment strategy, dynamically adjust inventory strategies and replenishment parameters according to demand forecasts and inventory situations to achieve optimization and maximum utilization of inventory, and monitor the operation status of each link in the supply chain and inventory changes in real time, detect abnormal situations and give early warnings.

[0078] Embodiment 2

[0079] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: The data collection module includes a sales data collection unit, an inventory data collection unit, and a supplier data collection unit;

[0080] The sales data collection unit is used to obtain sales-related data from the sales system, including sales order information, sales amount, sales quantity, sales channels, and sales regions;

[0081] The inventory data collection unit is used to obtain inventory-related data from the inventory system, including the current inventory quantity of each SKU, inventory turnover, inventory cost, and inventory satisfaction;

[0082] The said supplier data collection unit is used to obtain supplier-related data from the supplier system, including supplier information, supplier delivery capacity, supplier price, and supplier quality evaluation.

[0083] The said data preprocessing module includes a data preprocessing unit and a data group analysis unit;

[0084] The said data preprocessing unit is used to clean the supply chain data set, remove duplicate, missing, or abnormal data therein, and normalize the cleaned supply chain data;

[0085] The said data group analysis unit is used to obtain relevant data from the preprocessed sales data, inventory data, and supplier data, and obtain a first data group, a second data group, and a third data group;

[0086] The said first data group includes order fulfillment rate Ddly, product out-of-stock rate Spqh, order processing duration Ddcl, order on-time delivery rate Zsjf, and product return rate Thl;

[0087] The said second data group includes average inventory turnover rate Pjkc, proportion of inventory cost Kzcb, inventory satisfaction rate Kcmz, category inventory coverage rate Kcfg, and proportion of overdue inventory products Yqcp;

[0088] The said third data group includes real-time order processing speed Ssdd, real-time inventory allocation speed Ssdp, real-time supply chain collaborative response speed Gyxy, real-time market trend analysis accuracy rate Qszq, and real-time product sales forecast accuracy rate Xszq.

[0089] In this embodiment, through the sales data collection unit, inventory data collection unit, and supplier data collection unit, the system can accurately collect the required data from all aspects, providing a reliable data basis for subsequent analysis and decision-making. The data preprocessing unit can clean, transform, and organize the collected data, removing duplicate, missing, or abnormal data, thereby improving the quality and accuracy of the data. The data group analysis unit groups and analyzes the data according to different dimensions, forming the first data group, the second data group, and the third data group, providing multi-angle and comprehensive data support for subsequent decision-making. The intelligent prediction module uses prediction algorithms to predict future demand and formulates replenishment strategies in combination with historical sales data and market trend analysis, enabling more accurate prediction of future demand and formulating corresponding replenishment strategies, thereby reducing inventory risks and improving supply chain efficiency. The inventory optimization dynamic adjustment module can dynamically adjust inventory strategies and replenishment parameters according to demand forecasts and inventory situations, realizing inventory optimization and maximizing utilization, further enhancing supply chain efficiency and reducing costs. The real-time monitoring module can monitor the operation status of each link of the supply chain and inventory changes in real time, detect abnormal situations and give early warnings, which helps to adjust and process in a timely manner and ensure the stable operation of the supply chain.

[0090] Embodiment 3

[0091] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: The intelligent prediction module includes a prediction algorithm unit;

[0092] The prediction algorithm unit is used to calculate and obtain, using the predicted demand data and other indicators related to supply chain performance: supply chain performance index Gyjx, order management coefficient Ddgl, inventory management coefficient Kcgl, and supply chain response ability coefficient Gyxy;

[0093] The supply chain performance index Gyjx is calculated and obtained through the following formula:

[0094] ;

[0095] In the formula, Ddgl represents the order management coefficient, Kcgl represents the inventory management coefficient, Gyxy represents the supply chain response ability coefficient, and q, w, and e respectively represent the proportional coefficients of the order management coefficient Ddgl, the inventory management coefficient Kcgl, and the supply chain response ability coefficient Gyxy;

[0096] Among them, , , , and , R represents the first correction constant;

[0097] The order management coefficient Ddgl is calculated and obtained through the following formula:

[0098] ;

[0099] In the formula, Ddly represents the order fulfillment rate, Spqh represents the out-of-stock rate of goods, Ddcl represents the order processing duration, Zsjf represents the on-time delivery rate of orders, Thl represents the return rate of goods, and t, y, u, i, and o respectively represent the proportionality coefficients of the order fulfillment rate Ddly, the out-of-stock rate of goods Spqh, the order processing duration Ddcl, the on-time delivery rate of orders Zsjf, and the return rate of goods Thl;

[0100] Among them, , , , , , and , P represents the second correction constant.

[0101] The inventory management coefficient Kcgl is obtained by calculating through the following formula:

[0102] ;

[0103] In the formula, Pjkc represents the average inventory turnover rate, Kzcb represents the proportion of inventory cost, Kcmz represents the inventory satisfaction rate, Kcfg represents the category inventory coverage rate, Yqcp represents the proportion of overdue inventory products, and a, s, d, f, and g respectively represent the proportionality coefficients of the average inventory turnover rate Pjkc, the proportion of inventory cost Kzcb, the inventory satisfaction rate Kcmz, the category inventory coverage rate Kcfg, and the proportion of overdue inventory products Yqcp;

[0104] Among them, , , , , , and , H represents the third correction constant.

[0105] The supply chain response ability coefficient Gyxy is obtained by calculating through the following formula:

[0106] ;

[0107] Wherein, Ssdd represents the real-time order processing speed, Ssdp represents the real-time inventory allocation speed, Gyxy represents the real-time supply chain collaborative response speed, Qszq represents the accuracy rate of real-time market trend analysis, Xszq represents the accuracy rate of real-time commodity sales prediction, and h, j, k, z, and x respectively represent the proportionality coefficients of the real-time order processing speed Ssdd, the real-time inventory allocation speed Ssdp, the real-time supply chain collaborative response speed Gyxy, the accuracy rate of real-time market trend analysis Qszq, and the accuracy rate of real-time commodity sales prediction Xszq;

[0108] Among them, , , , , , and , L represents the fourth correction constant.

[0109] In this embodiment, by calculating the supply chain performance index Gyjx, the order management coefficient Ddgl, the inventory management coefficient Kcgl, and the supply chain response ability coefficient Gyxy, the system can objectively evaluate the overall operation status of the supply chain, thereby helping enterprises understand their advantages and improvement spaces in aspects such as order management, inventory management, and response ability. The calculation of the performance index covers multiple indicators in aspects such as order management, inventory management, and supply chain response ability, refining the assessment of the supply chain operation performance, helping to more comprehensively understand the advantages and disadvantages of the supply chain. By introducing proportionality coefficients and correction constants, the prediction algorithm unit can weight and correct various indicators according to the actual situation, ensuring that the calculation of the performance index is more accurate and precise, improving the credibility and reliability of the assessment. The calculation result of the supply chain performance index provides an important decision-making reference for enterprise managers, enabling them to timely discover and solve problems existing in supply chain management, formulate corresponding improvement strategies, improve the overall efficiency and competitiveness of the supply chain. The calculation of the performance index is not fixed, but dynamically adjusted and optimized with the change of the supply chain operation situation, can timely reflect the actual situation of the supply chain, and helps enterprises make timely adjustments and improvements.

[0110] Embodiment 4

[0111] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: The order placement module includes a trend analysis unit and a replenishment strategy formulation unit;

[0112] The trend analysis unit is used to predict the future product demand by analyzing historical sales data, identifying factors such as sales trends, periodic changes, and seasonal impacts, and combining market research;

[0113] The replenishment strategy formulation unit is used to compare and analyze the product demand predicted by the order module and the supply chain performance indicators, including inventory turnover, out-of-stock, and order fulfillment, with the preset standard threshold M and the preset standard threshold N, and formulate a replenishment level strategy, including the replenishment quantity, replenishment timing, and replenishment priority;

[0114] When Gyjx < M, obtain the first replenishment level, indicating that the supply chain performance does not meet the standard and emergency replenishment is required;

[0115] When M ≤ Gyjx < N, obtain the second replenishment level, indicating that the supply chain performance is 20% lower than the standard progress, and gradually increase the replenishment quantity to twice a week;

[0116] When Gyjx ≥ N, obtain the third replenishment level, indicating that the supply chain performance meets the standard, keep the existing replenishment plan unchanged, and adopt small-batch replenishment or flexibly adjust the replenishment plan according to demand.

[0117] The inventory optimization dynamic adjustment module includes an inventory strategy adjustment unit and a replenishment parameter adjustment unit;

[0118] The inventory strategy adjustment unit dynamically adjusts the inventory strategy, including the safety inventory level, reorder point, and order point, according to the prediction result of the demand prediction module and the current inventory situation, and flexibly adjusts the inventory strategy according to the changes in market demand and the supply chain performance index;

[0119] The replenishment parameter adjustment unit dynamically adjusts the replenishment parameters, including the replenishment quantity, replenishment timing, and replenishment frequency, according to the prediction result of the demand prediction module and the current inventory situation, and flexibly adjusts the replenishment parameters according to the changes in the supply chain performance index and market demand to achieve inventory optimization and rapid response to demand.

[0120] The real-time monitoring module includes a supply chain operation monitoring unit, an inventory change monitoring unit, and an alarm unit;

[0121] The supply chain operation monitoring unit is used to track the operation status of each link of the supply chain in real time by monitoring the data of the sales system, inventory system, and logistics system, including the order processing speed, inventory change situation, and logistics distribution status, and timely detect abnormal situations in the supply chain operation by setting monitoring indicators and thresholds;

[0122] The inventory change monitoring unit is used to monitor the inventory data in the inventory system, track the inventory level changes of each SKU in real time, timely detect abnormal situations of low or high inventory levels by setting appropriate inventory warning indicators and thresholds, and at the same time monitor the indicators of inventory turnover rate and inventory cost to evaluate the effectiveness of inventory management and cost control;

[0123] The alarm unit is used to send alarm information to relevant personnel in real time. When an abnormal situation is detected, corresponding alarm information is generated, including the type of abnormality, severity, and scope of influence. The alarm information is promptly transmitted to relevant personnel or departments, including supply chain managers, inventory managers, and logistics teams. The handling situation of the alarm is monitored, the resolution progress of the alarm is tracked, the alarm information is recorded and analyzed, and the frequency, type, and cause of the alarm are evaluated.

[0124] In this embodiment, through the trend analysis unit, by combining historical sales data and market research, sales trends and periodic changes can be accurately identified, future product demands can be predicted, which helps enterprises make more accurate replenishment decisions and avoid overstocking or out-of-stock situations. The replenishment strategy formulation unit formulates replenishment strategies at different levels according to supply chain performance indicators and predicted demands, enabling enterprises to flexibly adjust the replenishment plan according to the actual situation and ensuring that the supply chain performance reaches the expected level. The inventory strategy adjustment unit and the replenishment parameter adjustment unit dynamically adjust the inventory strategy and replenishment parameters according to the results of the demand forecasting module and the current inventory situation, realizing the optimization of inventory and rapid response to demands, which helps reduce inventory costs and improve the utilization rate of funds. The real-time monitoring module monitors the operation conditions of each link and inventory changes, promptly discovers abnormal situations and inventory deviations in the supply chain operation, and sends alarm information to relevant personnel through the alarm system, which helps quickly handle abnormal situations and ensure the stable and efficient operation of the supply chain. Through the analysis and processing of a large amount of data by each module, comprehensive data support and decision-making references are provided for enterprises, enabling managers to formulate optimization strategies and decisions more scientifically and improving the efficiency and level of supply chain management.

[0125] Embodiment 5

[0126] An intelligent replenishment method for supply chain based on data analysis, please refer to Figure 2 , specifically: including the following steps:

[0127] Step 1: Collect supply chain-related data. The data sources include the sales system, inventory system, and supplier system, and obtain: sales data, inventory data, and supplier data as the supply chain data set, and transmit it to the data preprocessing module;

[0128] Step 2: Clean, transform, and organize the collected supply chain data set, remove duplicate, missing, or abnormal data, and form the first data group, the second data group, and the third data group;

[0129] Step 3: Use a prediction algorithm in the data preprocessing module to predict future demands, and calculate to obtain: the supply chain performance index Gyjx;

[0130] Step 4: Use historical sales data and market trend analysis to predict the product demand for a certain period in the future, and compare the supply chain performance index Gyjx with the preset standard thresholds M and N to obtain the replenishment strategy;

[0131] Step 5: Dynamically adjust the inventory strategy and replenishment parameters according to the demand forecast and inventory situation to achieve the optimization and maximization utilization of inventory;

[0132] Step 6: Monitor the operation status of each link in the supply chain and inventory changes in real time, detect abnormal situations and give early warnings.

[0133] In this embodiment, by collecting sales data, inventory data and supplier data, and cleaning, transforming and sorting them, a complete supply chain data set can be established, providing a reliable data basis for subsequent analysis and prediction. Using prediction algorithms to predict future demand and calculate the supply chain performance index can help enterprises understand the current performance status of the supply chain and predict future demand trends, providing a basis for subsequent replenishment strategies. Combining historical sales data and market trend analysis to predict the product demand for a certain period in the future, and comparing the supply chain performance index with the preset standard thresholds to formulate corresponding replenishment strategies to ensure that the supply chain can meet market demand in a timely manner. Dynamically adjusting the inventory strategy and replenishment parameters according to the demand forecast and current inventory situation to achieve the optimization and maximization utilization of inventory, improve inventory turnover rate and reduce inventory costs. Monitoring the operation status of each link in the supply chain and inventory changes in real time, detecting abnormal situations and giving early warnings in time, which helps to quickly handle problems, ensure the stable operation of the supply chain, and avoid delays or losses caused by abnormal situations.

[0134] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A supply chain intelligent replenishment system based on data analysis, characterized by: It includes data collection module, data preprocessing module, intelligent prediction module, ordering module, inventory optimization dynamic adjustment module and real-time monitoring module; The data acquisition module is used to collect supply chain related data, the data sources include sales system, inventory system and supplier system, obtain: sales data, inventory data and supplier data as supply chain data set, and transmit to the data preprocessing module; The data preprocessing module is used to clean, convert and organize the collected supply chain data set, remove duplicate, missing or abnormal data, and form a first data group, a second data group and a third data group; The intelligent prediction module is used to predict future demand using the prediction algorithm from the data preprocessing module, and obtains after calculation: supply chain performance index Gyjx; The ordering module is used to use historical sales data and market trend analysis to predict product demand in the future, and to obtain a replenishment strategy by comparing the supply chain performance index Gyjx with a preset standard threshold M and a preset standard threshold N; The inventory optimization dynamic adjustment module dynamically adjusts inventory strategies and replenishment parameters according to demand forecasts and inventory conditions to achieve optimization and maximum utilization of inventory; The real-time monitoring module is used to monitor the operation status and inventory changes of each link in the supply chain in real time, detect abnormal situations and issue early warnings.

2. The supply chain intelligent replenishment system based on data analysis according to claim 1, characterized in that: The data collection module includes a sales data collection unit, an inventory data collection unit and a supplier data collection unit; The sales data acquisition unit is used to obtain sales-related data from the sales system, including sales order information, sales volume, sales quantity, sales channels and sales regions; The inventory data acquisition unit is used to obtain inventory-related data from the inventory system, including the current inventory quantity, inventory turnover, inventory cost and inventory satisfaction of each SKU; The supplier data acquisition unit is used to obtain supplier-related data from the supplier system, including supplier information, supplier delivery capability, supplier price and supplier quality evaluation.

3. The supply chain intelligent replenishment system based on data analysis according to claim 1, characterized in that: The data preprocessing module includes a data preprocessing unit and a data group analysis unit; The data preprocessing unit is used to clean the supply chain data set, remove duplicate, missing or abnormal data therein, and normalize the cleaned supply chain data; The data group analysis unit is used to obtain relevant data from the pre-processed sales data, inventory data and supplier data to obtain a first data group, a second data group and a third data group; The first data group includes order fulfillment rate Ddly, commodity out-of-stock rate Spqh, order processing time Ddcl, order on-time delivery rate Zsjf and commodity return rate Thl; The second data group includes average inventory turnover rate Pjkc, inventory cost ratio Kzcb, inventory satisfaction rate Kcmz, category inventory coverage rate Kcfg and inventory overdue product ratio Yqcp; The third data group includes real-time order processing speed Ssdd, real-time inventory allocation speed Ssdp, real-time supply chain collaborative response speed Gyxy, real-time market trend analysis accuracy Qszq and real-time commodity sales forecast accuracy Xszq.

4. The supply chain intelligent replenishment system based on data analysis according to claim 1, characterized in that: The intelligent prediction module includes a prediction algorithm unit; The prediction algorithm unit is used to calculate and obtain the following: supply chain performance index Gyjx, order management coefficient Ddgl, inventory management coefficient Kcgl and supply chain responsiveness coefficient Gyxy by using the predicted demand data and other indicators related to supply chain performance; The supply chain performance index Gyjx is calculated by the following formula: ； Where Ddgl represents the order management coefficient, Kcgl represents the inventory management coefficient, Gyxy represents the supply chain responsiveness coefficient, q, w and e represent the proportional coefficients of the order management coefficient Ddgl, the inventory management coefficient Kcgl and the supply chain responsiveness coefficient Gyxy respectively; in, , , ,and , R represents the first correction constant; The order management coefficient Ddgl is calculated by the following formula: ； In the formula, Ddly represents the order fulfillment rate, Spqh represents the product out-of-stock rate, Ddcl represents the order processing time, Zsjf represents the order on-time delivery rate, Thl represents the product return rate, t, y, u, i and o represent the proportional coefficients of the order fulfillment rate Ddly, the product out-of-stock rate Spqh, the order processing time Ddcl, the order on-time delivery rate Zsjf and the product return rate Thl respectively; in, , , , , ,and , P represents the second correction constant.

5. The supply chain intelligent replenishment system based on data analysis according to claim 4 is characterized by: The inventory management coefficient Kcgl is calculated by the following formula: ； In the formula, Pjkc represents the average inventory turnover rate, Kzcb represents the inventory cost ratio, Kcmz represents the inventory satisfaction rate, Kcfg represents the category inventory coverage rate, Yqcp represents the proportion of overdue inventory products, a, s, d, f and g represent the proportional coefficients of the average inventory turnover rate Pjkc, the inventory cost ratio Kzcb, the inventory satisfaction rate Kcmz, the category inventory coverage rate Kcfg and the proportion of overdue inventory products Yqcp respectively; in, , , , , ,and , H represents the third correction constant.

6. The supply chain intelligent replenishment system based on data analysis according to claim 4 is characterized by: The supply chain responsiveness coefficient Gyxy is calculated by the following formula: ； In the formula, Ssdd represents the real-time order processing speed, Ssdp represents the real-time inventory allocation speed, Gyxy represents the real-time supply chain collaborative response speed, Qszq represents the real-time market trend analysis accuracy, Xszq represents the real-time commodity sales forecast accuracy, h, j, k, z and x represent the proportional coefficients of the real-time order processing speed Ssdd, the real-time inventory allocation speed Ssdp, the real-time supply chain collaborative response speed Gyxy, the real-time market trend analysis accuracy Qszq and the real-time commodity sales forecast accuracy Xszq respectively; in, , , , , ,and , L represents the fourth correction constant.

7. The supply chain intelligent replenishment system based on data analysis according to claim 1, characterized in that: The ordering module includes a trend analysis unit and a replenishment strategy formulation unit; The trend analysis unit is used to analyze historical sales data, identify sales trends, cyclical changes and seasonal factors, and predict future product demand in combination with market research; The replenishment strategy formulation unit is used to formulate a replenishment level strategy, including replenishment quantity, replenishment timing and replenishment priority, by comparing and analyzing the product demand predicted by the ordering module and the supply chain performance indicators, including inventory turnover, out-of-stock and order fulfillment, with the preset standard threshold M and the preset standard threshold N; When Gyjx<M, the first replenishment level is obtained, indicating that the supply chain performance is not up to standard and urgent replenishment is needed; When M≤Gyjx<N, the second replenishment level is obtained, indicating that the supply chain performance is 20% lower than the standard progress, and the replenishment quantity is gradually increased to two replenishments per week; When Gyjx≥N, the third replenishment level is obtained, indicating that the supply chain performance meets the standard. The existing replenishment plan remains unchanged, and small-batch replenishment is adopted or the replenishment plan is flexibly adjusted according to demand.

8. The supply chain intelligent replenishment system based on data analysis according to claim 1, characterized in that: The inventory optimization dynamic adjustment module includes an inventory strategy adjustment unit and a replenishment parameter adjustment unit; The inventory strategy adjustment unit dynamically adjusts the inventory strategy, including the safety stock level, order point and reorder point, according to the forecast results of the demand forecast module and the current inventory situation, and flexibly adjusts the inventory strategy according to changes in market demand and changes in the supply chain performance index; The replenishment parameter adjustment unit dynamically adjusts the replenishment parameters, including the replenishment quantity, replenishment timing and replenishment frequency, according to the forecast results of the demand forecasting module and the current inventory situation, and flexibly adjusts the replenishment parameters according to the changes in the supply chain performance index and the changes in market demand to achieve inventory optimization and rapid response to demand.

9. The supply chain intelligent replenishment system based on data analysis according to claim 1, characterized in that: The real-time monitoring module includes a supply chain operation monitoring unit, an inventory change monitoring unit and an alarm unit; The supply chain operation monitoring unit is used to track the operation of each link of the supply chain in real time by monitoring the data of the sales system, inventory system and logistics system, including order processing speed, inventory changes and logistics distribution status, and to promptly discover abnormal situations in the supply chain operation by setting monitoring indicators and thresholds; The inventory change monitoring unit is used to monitor the inventory data in the inventory system, track the inventory level changes of each SKU in real time, and promptly discover abnormal situations of low or high inventory levels by setting appropriate inventory warning indicators and thresholds. At the same time, it monitors the indicators of inventory turnover rate and inventory cost to evaluate the effectiveness of inventory management and cost control; The alarm unit is used to send alarm information to relevant personnel in real time. When an abnormal situation is found, corresponding alarm information is generated, including the type, severity and scope of impact of the abnormality. The alarm information is promptly transmitted to relevant personnel or departments, including supply chain managers, inventory management personnel and logistics teams, to monitor the handling of alarms, track the progress of alarm resolution, record and analyze alarm information, and evaluate the frequency, type and cause of alarms.

10. A supply chain intelligent replenishment method based on data analysis, comprising a supply chain intelligent replenishment system based on data analysis as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Collect supply chain related data. The data sources include sales system, inventory system and supplier system. Obtain sales data, inventory data and supplier data as supply chain data sets and transmit them to the data preprocessing module. Step 2: Clean, convert and organize the collected supply chain data sets, remove duplicate, missing or abnormal data, and form the first data group, the second data group and the third data group; Step 3: Use the prediction algorithm in the data preprocessing module to predict future demand and obtain the supply chain performance index Gyjx after calculation; Step 4: Use historical sales data and market trend analysis to predict product demand in the future, and compare the supply chain performance index Gyjx with the preset standard threshold M and the preset standard threshold N to obtain a replenishment strategy; Step 5: Dynamically adjust inventory strategies and replenishment parameters based on demand forecasts and inventory conditions to optimize and maximize inventory utilization; Step 6: Monitor the operation status and inventory changes of each link in the supply chain in real time, detect abnormal situations and issue early warnings.

Images