Inventory management system and management method based on order data

Abstract

The invention relates to the technical field of inventory management, and discloses an inventory management system and method based on order data, and the system comprises a data collection unit, an order analysis unit, an inventory prediction unit, and an inventory management unit. According to the invention, commodities are accurately classified according to order data, a detailed basis is provided for inventory management, extensive management is avoided, and the accuracy is improved; inventory demands are predicted according to different commodity characteristics, multiple factors are combined with historical data, actual sales is close, overstock or stockout is reduced, and the turnover rate and the fund utilization rate are increased; the automatic process reduces manpower, monitors the inventory in real time and gives an early warning, replenishes goods in time, enables managers to concentrate on decision making, improves management efficiency, maintains the reasonable level of the inventory, and reduces cost; the inventory supplement signal contains key information and is quickly transmitted to suppliers, so that the suppliers can supply goods in time, collaboration and communication are enhanced, a stable and efficient supply chain is constructed, risks are reduced, and competitiveness is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of inventory management, and in particular to an inventory management system and management method based on order data. Background Art

[0002] In today's highly competitive business environment, the level of inventory management of an enterprise is directly related to its operating costs, customer satisfaction and market competitiveness. Traditional inventory management methods often rely on experience or simple historical sales data statistics, which have many disadvantages.

[0003] On the one hand, companies lack in-depth mining and accurate analysis of order data. Order data contains rich information, such as the order time reflects the time pattern of customer purchase behavior, the product name determines the product category, and the product quantity reflects the scale of each customer's purchase. However, in the past, many companies failed to make full use of these detailed information and only roughly counted the total sales volume, unable to accurately grasp the differences in the characteristics of different products at the order level.

[0004] On the other hand, due to the lack of scientific order data analysis to predict inventory demand, companies often face the dilemma of inventory backlog or stockout. Inventory backlog leads to capital occupation, increased storage costs, and the risk of commodity expiration and depreciation; stockouts will reduce customer satisfaction, miss sales opportunities, damage the company's reputation, and may even lead to customer loss in the long run. Moreover, when determining whether replenishment is needed and the replenishment quantity, traditional methods lack accurate basis, either blindly replenishing, or replenishing untimely and insufficiently, making it difficult to find a balance between meeting market demand and optimizing inventory costs.

[0005] Furthermore, as the market changes faster, customer demands become more diversified, and the complexity of the supply chain increases, companies are in urgent need of an intelligent and sophisticated inventory management system and method that can track order dynamics in real time, accurately predict inventory demand, and reasonably manage inventory levels in order to adapt to the rapidly changing market environment and enhance their overall competitiveness. Summary of the invention

[0006] The purpose of the present invention is to provide an inventory management system and management method based on order data, which solves the technical problems raised in the background technology.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An inventory management system and management method based on order data, comprising:

[0009] The data collection unit is used to obtain order data; the order data includes order time, product name, and product quantity;

[0010] An order analysis unit is used to perform order analysis and processing based on order data, and to obtain the order frequency of each type of goods and the average quantity in each order based on the order analysis and processing results, and then to classify the goods into high-frequency goods and low-frequency goods based on the order frequency, and to classify the goods into large-quantity order goods and small-quantity order goods based on the average quantity of each type of goods in each order;

[0011] The inventory forecasting unit is used to perform inventory demand forecasting analysis in combination with the order analysis and processing results, and determine the inventory demand forecast value of each type of product at the forecast time through the inventory demand forecasting analysis;

[0012] The inventory management unit is used to perform commodity inventory management analysis based on the inventory demand forecast value of each type of product at the forecast time, and determine whether each type of product needs to be replenished through commodity inventory management analysis.

[0013] As a further solution of the present invention: a specified period is selected, all order data in the specified period are combined into an order data set, and marked as D={D i}, i = 1, 2, ... n, where D i represents the i-th order, and n is the total number of orders;

[0014] At the same time, the attributes of each order are marked as Di=[T i ,P i ,Q i ], where T i is the order time of the i-th order, P i is the product name of the i-th order, Q i is the number of products in the i-th order.

[0015] As a further solution of the present invention: the order frequency of each type of goods and the average quantity in each order in the order analysis process are obtained as follows:

[0016] Step M1. In the order data set, classify the products according to their names and obtain a set of product types.

[0017] The method is to classify the order data with the same product name into one type of product, and so on, until all the order data in the order data set are classified, and a product type set consisting of multiple types of products is obtained;

[0018] And mark the product type set as P0 j , j = 1, 2, ... m, m represents the number of types of products;

[0019] Step M2, through: ;

[0020] Calculate the order frequency F of each type of product j ;

[0021] In the formula, Indicates that it contains product type P0 j The total number of orders, S (D i , P0 j ) is the indicator function, the order data D i Contains product type P0 j , then S(D i , P0 j ) is 1, order data D i Does not contain product type P0 j , then S(D i , P0 j ) has a value of 0;

[0022] Step M3, get each type of product P0 j In each order data D i The number of products in Q i and relabel it as Q0 i，j ;

[0023] Then through:

[0024] Calculate the average order quantity Q1 for each type of product j , which is the average quantity of each type of product in each order.

[0025] As a further solution of the present invention: the division method of high-frequency commodities and low-frequency commodities in order analysis and processing is as follows:

[0026] The order frequency F of each type of product j Compare with the preset frequency threshold Fy:

[0027] When F j ≥Fy, then the product of this type is considered a high-frequency product;

[0028] When F j <Fy, then this type of product is judged as a low-frequency product.

[0029] As a further solution of the present invention: the division method of large quantity order goods and small quantity order goods in order analysis processing is as follows:

[0030] The average order quantity Q1 of each type of product j Compare with the preset quantity threshold Qy:

[0031] When Q1 j≥Qy, then the product of this type is determined to be a large quantity order product;

[0032] When Q1 j <Qy, then this type of product is judged to be a small quantity order product.

[0033] As a further solution of the present invention: the inventory demand forecasting and analysis method is as follows:

[0034] Step K1. For high-frequency products or products with large orders, select a type of product as an example and calculate the inventory demand forecast value of this type of product at the forecast time t0;

[0035] Among them, the prediction time t0 is a preset value;

[0036] The method is as follows:

[0037] Step K1.1, taking the current time node as the boundary and combining the order time in the order data, obtain the first u order data adjacent to the current time node;

[0038] Step K1.2. Extract the order quantity of this type of product from u order data and mark it as Q k , k = 1, 2, ..., u, Q k is the order quantity of this type of product in the kth order data;

[0039] Step K1.3, count the time difference between the order time and the current time node in the u order data respectively, and select the set of time differences with the largest absolute value of the difference as the analysis time, and mark it as t1;

[0040] Step K1.4, through: ;

[0041] Calculate the inventory demand forecast value QC of this type of product at the forecast time t0;

[0042] Step K2: For low-frequency products with small order quantities, select a type of product as an example and calculate the inventory demand forecast value of this type of product at the forecast time t0;

[0043] The method is as follows:

[0044] Step K2.1, taking the current time node as the boundary and combining the order time in the order data, obtain the first u order data adjacent to the current time node;

[0045] Step K2.2. Extract the order quantity of this type of product from u order data and mark it as Q k , k = 1, 2, ..., u, Q kis the order quantity of this type of product in the kth order data;

[0046] Step K2.3. Extract the corresponding order time from the u order data and mark it as T k ;

[0047] Step K2.4, through: ;

[0048] Calculate the inventory demand forecast value QC of this type of product at the forecast time t0;

[0049] Step K3: Follow the method from Step K1 to Step K2 to obtain the inventory demand forecast value of each type of product at the forecast time.

[0050] As a further solution of the present invention: the commodity inventory management analysis method is as follows:

[0051] Step L1, obtain the current inventory data of each type of product and mark it as S j ;

[0052] At the same time, the inventory demand forecast value of each type of product at the forecast time is re-marked as QC j ;

[0053] Step L2, through:

[0054] Calculate the inventory fulfillment rate M for each type of product j ;

[0055] Step L3, then calculate the inventory satisfaction rate M of each type of product j Compare with the corresponding preset inventory replenishment threshold My:

[0056] When M j When <My, the corresponding type of product inventory replenishment signal is generated, and then: , calculate the inventory replenishment quantity B of the corresponding type of product j :

[0057] When M j ≥My, no inventory replenishment signal for the corresponding type of product will be generated.

[0058] As a further solution of the present invention: the inventory replenishment signal is used to send a replenishment order to the supplier, and the replenishment order includes the product name and inventory replenishment quantity corresponding to the corresponding type of product when the inventory replenishment signal is generated.

[0059] An inventory management method based on order data, the method is implemented by an inventory management system based on order data, and the method comprises the following steps:

[0060] Step 1: Data Collection

[0061] Get order data;

[0062] Step 2: Order Analysis

[0063] Perform order analysis and processing based on order data, and obtain the order frequency of each type of goods and the average quantity in each order based on the order analysis and processing results, and then classify the goods into high-frequency goods and low-frequency goods based on the order frequency, and classify the goods into large-quantity order goods and small-quantity order goods based on the average quantity of each type of goods in each order;

[0064] Step 3: Inventory Forecast

[0065] Combined with the order analysis and processing results, inventory demand forecast analysis is performed, and the inventory demand forecast value of each type of product at the forecast time is determined through inventory demand forecast analysis;

[0066] Step 4: Inventory Management

[0067] Carry out commodity inventory management analysis based on the inventory demand forecast value of each type of product at the forecast time, and determine whether each type of product needs to be replenished through commodity inventory management analysis.

[0068] Beneficial effects of the present invention:

[0069] Accurately classify goods: Through in-depth analysis of order data, goods are divided into high-frequency goods and low-frequency goods according to order frequency, and goods are divided into large-quantity order goods and small-quantity order goods according to the average quantity of each type of goods in each order. This classification method can understand the sales characteristics of different goods in more detail, provide accurate basic data for subsequent inventory management, avoid the extensive management of all goods in traditional inventory management, and thus improve the pertinence and accuracy of inventory management.

[0070] Predictions for different product characteristics: Different inventory demand forecasting and analysis methods are used for high-frequency products or products with large orders, as well as low-frequency products with small orders. Taking into account factors such as order time and order quantity, and combining historical order data for forecasting, it is possible to more accurately grasp the inventory demand of different types of products at a specific time in the future. For example, in the forecasting method for high-frequency products or products with large orders, the first u order data adjacent to the current time node are selected, and factors such as time difference are considered, so that the forecast results are closer to the actual sales situation, reducing inventory backlogs or out-of-stock phenomena caused by inaccurate inventory forecasts, and improving inventory turnover and capital utilization.

[0071] Automated inventory management process: The system automatically obtains order data, performs order analysis and processing, inventory demand forecast analysis, and commodity inventory management analysis, which greatly reduces manual intervention and tedious data statistics work and improves the efficiency of inventory management. Inventory managers can focus more on decision-making and optimizing management strategies instead of spending time on data collection and calculation.

[0072] Real-time inventory monitoring and early warning: It can obtain the current inventory data of various types of products in real time, compare it with the predicted inventory demand, and calculate the inventory fulfillment rate. When the inventory fulfillment rate is lower than the preset inventory replenishment threshold, it automatically triggers the generation of inventory replenishment signals, calculates the corresponding inventory replenishment quantity, and sends replenishment orders to suppliers in a timely manner. This real-time monitoring and automatic early warning mechanism can ensure that inventory is always maintained at a reasonable level, avoid sales affected by out-of-stock, and prevent excessive inventory from occupying funds and increasing storage costs.

[0073] Efficient communication with suppliers: Inventory replenishment signals directly include key information such as the product name and inventory replenishment quantity of the corresponding type of products, and can be accurately and quickly transmitted to suppliers, so that suppliers can understand replenishment needs in a timely manner and make supply preparations in advance. This enhances the synergy and communication efficiency between enterprises and suppliers, helps to build a more stable and efficient supply chain system, reduce supply chain risks, and improve the operational efficiency and competitiveness of the entire supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] The present invention will be further described below in conjunction with the accompanying drawings.

[0075] Figure 1 It is a system block diagram of an inventory management system based on order data of the present invention.

[0076] Figure 2 It is a flow chart of an inventory management method based on order data of the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] Embodiment 1

[0079] See also Figure 1 As shown, the present invention is an inventory management system based on order data, comprising:

[0080] The data collection unit is used to obtain order data; the order data includes order number, order time, product name, product quantity, and customer information;

[0081] Select a specified period, combine all order data in the specified period into an order data set, and mark it as D={D i}, i = 1, 2, ... n, where D i represents the i-th order, and n is the total number of orders;

[0082] At the same time, the attributes of each order are marked as Di=[ID i ,T i ,P i ,Q i ,C i ], where ID i is the order number of the i-th order, T i is the order time of the i-th order, P i is the product name of the i-th order, Q i is the number of products in the i-th order, C i is the customer information of the i-th order;

[0083] The order analysis unit is used to perform order analysis and processing based on order data in the following ways:

[0084] Step M1. In the order data set, classify the products according to their names and obtain a set of product types.

[0085] The method is to classify the order data with the same product name into one type of product, and so on, until all the order data in the order data set are classified, and a product type set consisting of multiple types of products is obtained;

[0086] And mark the product type set as P0 j , j = 1, 2, ... m, m represents the number of types of products;

[0087] Step M2, through: ;

[0088] Calculate the order frequency F of each type of product j ;

[0089] In the formula, Indicates that it contains product type P0 j The total number of orders, S (D i , P0 j ) is the indicator function, the order data D i Contains product type P0 j , then S(D i , P0j ) is 1, order data D i Does not contain product type P0 j , then S(D i , P0 j ) has a value of 0;

[0090] Then, the products are divided into high-frequency products and low-frequency products according to the order frequency. The method is as follows: the order frequency F of each type of product j Compare with the preset frequency threshold Fy:

[0091] When F j ≥Fy, then the product of this type is considered a high-frequency product;

[0092] When F j <Fy, then the product of this type is judged as a low-frequency product;

[0093] Step M3, get each type of product P0 j In each order data D i The number of products in Q i and relabel it as Q0 i，j ;

[0094] Then through:

[0095] Calculate the average order quantity Q1 for each type of product j , which is the average quantity of each type of product in each order;

[0096] Then according to the average order quantity Q1 j The products are divided into large quantity order products and small quantity order products by: taking the average order quantity Q1 of each type of product j Compare with the preset quantity threshold Qy:

[0097] When Q1 j ≥Qy, then the product of this type is determined to be a large quantity order product;

[0098] When Q1 j <Qy, then the product of this type is judged to be a small quantity order product;

[0099] This embodiment obtains detailed order data through the data collection unit, and classifies the order data according to the product name in the order analysis unit to obtain a product type set, and then based on the calculation of order frequency and average order quantity and comparison with corresponding thresholds, it can accurately distinguish between high-frequency products, low-frequency products, large-quantity order products, and small-quantity order products, which helps enterprises to have a clearer understanding of the performance of different products in orders and provide a basic basis for subsequent inventory management and other related decisions.

[0100] Embodiment 2

[0101] See also Figure 1 As shown, as the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of this embodiment is different from that of the first embodiment only in that the second embodiment further includes:

[0102] The inventory forecasting unit is used to perform inventory demand forecasting analysis based on the order analysis and processing results, and the method is as follows:

[0103] Step K1. For high-frequency products or products with large orders, select a type of product as an example and calculate the inventory demand forecast value of this type of product at the forecast time t0;

[0104] Among them, the prediction time t0 is a preset value;

[0105] The method is as follows:

[0106] Step K1.1, taking the current time node as the boundary and combining the order time in the order data, obtain the first u order data adjacent to the current time node;

[0107] Step K1.2. Extract the order quantity of this type of product from u order data and mark it as Q k , k = 1, 2, ..., u, Q k is the order quantity of this type of product in the kth order data;

[0108] Step K1.3, count the time difference between the order time and the current time node in the u order data respectively, and select the set of time differences with the largest absolute value of the difference as the analysis time, and mark it as t1;

[0109] Step K1.4, through: ;

[0110] Calculate the inventory demand forecast value QC of this type of product at the forecast time t0;

[0111] Step K2: For low-frequency products with small order quantities, select a type of product as an example and calculate the inventory demand forecast value of this type of product at the forecast time t0;

[0112] The method is as follows:

[0113] Step K2.1, taking the current time node as the boundary and combining the order time in the order data, obtain the first u order data adjacent to the current time node;

[0114] Step K2.2. Extract the order quantity of this type of product from u order data and mark it as Q k , k = 1, 2, ..., u, Q k is the order quantity of this type of product in the kth order data;

[0115] Step K2.3. Extract the corresponding order time from the u order data and mark it as T k ;

[0116] Step K2.4, through:

[0117] Calculate the inventory demand forecast value QC of this type of product at the forecast time t0;

[0118] Step K3, according to the method from Step K1 to Step K2, obtain the inventory demand forecast value of each type of product at the forecast time;

[0119] This embodiment adds an inventory forecasting unit on the basis of the first embodiment. For different types of commodities, such as high-frequency commodities or commodities with large orders, and low-frequency commodities with small orders, the inventory demand forecast value at a preset forecast time is predicted through a specific calculation method in combination with information such as the order time in the order data. This allows the enterprise to know the future inventory demand situation of different types of products in advance, facilitates the corresponding preparations in advance, avoids problems such as inventory backlogs or out-of-stocks, and optimizes inventory resource allocation.

[0120] Embodiment 3

[0121] See also Figure 1 As shown, as the third embodiment of the present invention, when the present application is implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is that this embodiment also includes:

[0122] The inventory management unit is used to perform commodity inventory management analysis based on the inventory demand forecast value of each type of product at the forecast time, and the method is as follows:

[0123] Step L1, obtain the current inventory data of each type of product and mark it as S j ;

[0124] At the same time, the inventory demand forecast value of each type of product at the forecast time is re-marked as QC j ;

[0125] Step L2, through:

[0126] Calculate the inventory fulfillment rate M for each type of product j ;

[0127] Step L3, then calculate the inventory satisfaction rate M of each type of product j Compare with the corresponding preset inventory replenishment threshold My:

[0128] When M j When <My, the corresponding type of product inventory replenishment signal is generated, and then: , calculate the inventory replenishment quantity B of the corresponding type of product j :

[0129] The inventory replenishment signal is used to send a replenishment order to the supplier. The replenishment order contains the product name and inventory replenishment quantity corresponding to the corresponding type of product when the inventory replenishment signal is generated;

[0130] When M j When ≥My, no inventory replenishment signal for the corresponding type of product is generated;

[0131] This embodiment further incorporates an inventory management unit on the basis of Embodiment 1 and Embodiment 2, calculates the inventory satisfaction rate based on the inventory demand forecast value of each type of product at the forecast time and the current inventory data, and compares it with the preset inventory replenishment threshold to determine whether to trigger the inventory replenishment signal and calculate the corresponding inventory replenishment amount. This method can help enterprises manage commodity inventory scientifically and reasonably, accurately control the timing and quantity of replenishment, ensure that the inventory level can not only meet market demand, but also avoid unnecessary inventory cost expenditure, thereby improving overall operational efficiency and economic benefits.

[0132] Embodiment 4

[0133] See also Figure 1 As shown, as the fourth embodiment of the present invention, when the present application is implemented specifically, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second, third and fourth embodiments.

[0134] This embodiment combines and implements the solutions of the previous embodiments 1, 2, and 3, giving full play to the role of each link, from order data collection and analysis, to inventory demand forecasting, and then to forecast-based inventory management decisions, to form a complete and coherent inventory management system based on order data, which helps enterprises to manage inventory in a refined and scientific manner in all aspects, enhance the control ability of enterprises in the supply chain, improve customer satisfaction, and ensure the stable operation and sustainable development of enterprises.

[0135] See also Figure 2As shown, an inventory management method based on order data is implemented by an inventory management system based on order data. The method includes the following steps:

[0136] Step 1: Data Collection

[0137] Get order data;

[0138] Step 2: Order Analysis

[0139] Perform order analysis and processing based on order data, and obtain the order frequency of each type of goods and the average quantity in each order based on the order analysis and processing results, and then classify the goods into high-frequency goods and low-frequency goods based on the order frequency, and classify the goods into large-quantity order goods and small-quantity order goods based on the average quantity of each type of goods in each order;

[0140] Step 3: Inventory Forecast

[0141] Combined with the order analysis and processing results, inventory demand forecast analysis is performed, and the inventory demand forecast value of each type of product at the forecast time is determined through inventory demand forecast analysis;

[0142] Step 4: Inventory Management

[0143] Carry out commodity inventory management analysis based on the inventory demand forecast value of each type of product at the forecast time, and determine whether each type of product needs to be replenished through commodity inventory management analysis.

[0144] It should be stated that all order data collected in this application are collected with the user's consent and authorization, and the use of the order data is legal and compliant, and the use and processing of the order data comply with the relevant laws, regulations and standards of the relevant regions.

[0145] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An inventory management system based on order data, characterized in that: include: A data collection unit, used to obtain order data; Order data includes order time, product name, and product quantity; An order analysis unit is used to perform order analysis and processing based on order data, and to obtain the order frequency of each type of goods and the average quantity in each order based on the order analysis and processing results, and then to classify the goods into high-frequency goods and low-frequency goods based on the order frequency, and to classify the goods into large-quantity order goods and small-quantity order goods based on the average quantity of each type of goods in each order; The inventory forecasting unit is used to perform inventory demand forecasting analysis in combination with the order analysis and processing results, and determine the inventory demand forecast value of each type of product at the forecast time through the inventory demand forecasting analysis; The inventory management unit is used to perform commodity inventory management analysis based on the inventory demand forecast value of each type of product at the forecast time, and determine whether each type of product needs to be replenished through commodity inventory management analysis.

2. The inventory management system based on order data according to claim 1, characterized in that: Select a specified period, combine all order data in the specified period into an order data set, and mark it as D={D i }, i = 1, 2, ... n, where D i represents the i-th order, and n is the total number of orders; At the same time, the attributes of each order are marked as Di=[T i ,P i ,Q i ], where T i is the order time of the i-th order, P i is the product name of the i-th order, Q i is the number of products in the i-th order.

3. The inventory management system based on order data according to claim 2, characterized in that: The order frequency of each type of product in the order analysis process and its average quantity in each order are obtained as follows: Step M1. In the order data set, classify the products according to their names and obtain a set of product types. The method is to classify the order data with the same product name into one type of product, and so on, until all the order data in the order data set are classified, and a product type set consisting of multiple types of products is obtained; And mark the product type set as P0 j , j = 1, 2, ... m, m represents the number of types of products; Step M2, through: ; Calculate the order frequency F of each type of product j ; In the formula, Indicates that it contains type product P0 j The total number of orders, S (D i , P0 j ) is the indicator function, the order data D i Contains product type P0 j , then S(D i , P0 j ) is 1, order data D i Does not contain product type P0 j , then S(D i , P0 j ) has a value of 0; Step M3, get each type of product P0 j In each order data D i The number of products in Q i and relabel it as Q0 i，j ; Then through: Calculate the average order quantity Q1 for each type of product j , which is the average quantity of each type of product in each order.

4. The inventory management system based on order data according to claim 3, characterized in that: The classification of high-frequency and low-frequency products in order analysis is as follows: The order frequency F of each type of product j Compare with the preset frequency threshold Fy: When F j ≥Fy, then the product of this type is considered a high-frequency product; When F j <Fy, then this type of product is judged as a low-frequency product.

5. The inventory management system based on order data according to claim 3, characterized in that: The classification of large quantity order items and small quantity order items in order analysis processing is as follows: The average order quantity Q1 of each type of product j Compare with the preset quantity threshold Qy: When Q1 j ≥Qy, then the product of this type is determined to be a large quantity order product; When Q1 j <Qy, then this type of product is judged to be a small quantity order product.

6. The inventory management system based on order data according to claim 3, characterized in that: Inventory demand forecast analysis is as follows: Step K1. For high-frequency products or products with large orders, select a type of product as an example and calculate the inventory demand forecast value of this type of product at the forecast time t0; Among them, the prediction time t0 is a preset value; The method is as follows: Step K1.1, taking the current time node as the boundary and combining the order time in the order data, obtain the first u order data adjacent to the current time node; Step K1.

2. Extract the order quantity of this type of product from u order data and mark it as Q k , k = 1, 2, ... u, Q k is the order quantity of this type of product in the kth order data; Step K1.3, count the time difference between the order time and the current time node in the u order data respectively, and select the set of time differences with the largest absolute value of the difference as the analysis time, and mark it as t1; Step K1.4, through: ; Calculate the inventory demand forecast value QC of this type of product at the forecast time t0; Step K2: For low-frequency products with small order quantities, select a type of product as an example and calculate the inventory demand forecast value of this type of product at the forecast time t0; The method is as follows: Step K2.1, taking the current time node as the boundary and combining the order time in the order data, obtain the first u order data adjacent to the current time node; Step K2.

2. Extract the order quantity of this type of product from u order data and mark it as Q k , k = 1, 2, ... u, Q k is the order quantity of this type of product in the kth order data; Step K2.

3. Extract the corresponding order time from the u order data and mark it as T k ; Step K2.4, through: ; Calculate the inventory demand forecast value QC of this type of product at the forecast time t0; Step K3: Follow the method from Step K1 to Step K2 to obtain the inventory demand forecast value of each type of product at the forecast time.

7. The inventory management system based on order data according to claim 6, characterized in that: The commodity inventory management analysis method is as follows: Step L1, obtain the current inventory data of each type of product and mark it as S j ; At the same time, the inventory demand forecast value of each type of product at the forecast time is re-marked as QC j ; Step L2, through: Calculate the inventory fulfillment rate M for each type of product j ; Step L3, then calculate the inventory satisfaction rate M of each type of product j It is compared with the corresponding preset inventory replenishment threshold My, and based on the comparison result, it is determined whether to generate an inventory replenishment signal for the corresponding type of product.

8. The inventory management system based on order data according to claim 7, characterized in that: The comparison method in StepL3 is as follows: When M j When <My, the corresponding type of product inventory replenishment signal is generated, and then: , calculate the inventory replenishment quantity B of the corresponding type of product j : When M j ≥My, no inventory replenishment signal for the corresponding type of product will be generated.

9. The inventory management system based on order data according to claim 8, characterized in that: The inventory replenishment signal is used to send a replenishment order to the supplier. The replenishment order contains the product name and inventory replenishment quantity corresponding to the corresponding type of product when the inventory replenishment signal is generated.

10. An inventory management method based on order data, characterized in that: The method is implemented by an order data-based inventory management system as described in any one of claims 1-9.

Images