A method, system, device and medium for managing warehouse goods based on inventory-to-sales ratio

Abstract

The present invention discloses a storage goods management method, system, equipment and medium based on inventory-to-sales ratio, which relates to the technical field of warehouse management, including: constructing a data extraction neural network model, extracting characteristic information of the aggregated neighborhood nodes of the historical order data of commercial enterprises, obtaining the central time node aggregated characteristic vector of the historical order data of the N+1th commercial enterprise after the aggregation of the Nth commercial enterprise, and using the central time node aggregated characteristic vector as the input value of the neuron of the data extraction neural network model, setting the replenishment cycle, and outputting the combined characteristic vector of the historical order data arranged in chronological order; setting the same replenishment cycle, and obtaining the combined characteristic vector of the industrial enterprise production data within the same time; constructing an inventory-to-sales ratio demand forecasting model, inputting the combined characteristic vector of the historical order data and the combined characteristic vector of the industrial enterprise production data into the inventory-to-sales ratio demand forecasting model, and outputting the storage goods management result. The present invention can improve the storage efficiency of goods.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to a method, system, equipment and medium for managing stored goods based on inventory-to-sales ratio. Background Art

[0002] When delivering products from the factory to the customer, it is hoped that the products will be delivered in a short time from the time the customer has a demand. Warehouse cargo management is a very important link in logistics companies. The improvement of warehouse management system can greatly increase the efficiency of logistics transportation.

[0003] However, the existing warehouse cargo management has the following defects:

[0004] 1) Low level of informatization:

[0005] The warehouse management of many companies still relies on traditional manual records and manual operations. This method is not only inefficient but also prone to errors, leading to problems such as inaccurate warehouse inventory quantities and incomplete inventory records.

[0006] 2) Inaccurate purchase, sales and inventory data:

[0007] Due to the low level of informatization and erroneous operations caused by human factors, warehouse purchase and sales data are inaccurate, affecting the company's business management decisions.

[0008] 3) Employees’ work processes are not standardized:

[0009] Employees' non-standard operations and lack of necessary operational training lead to non-standard warehouse operation processes and manual recording of goods storage time. When goods arrive, it is not easy to find a warehouse with suitable space for the corresponding types of goods. At the same time, due to improper time monitoring, goods in the warehouse may be piled up and expired, making it difficult to ensure efficient scheduling and reducing the efficiency of warehouse acquisition management. Summary of the invention

[0010] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent, by proposing a warehouse goods management method, system, equipment and medium based on inventory-to-sales ratio, which are used to solve the technical problems existing in the above-mentioned prior art.

[0011] To achieve the above objectives, in a first aspect, the present invention provides a method for managing warehouse goods based on inventory-to-sales ratio, comprising the following steps:

[0012] Step 1: Obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods, and organize the historical order data of the business enterprise and the historical production data of the industrial enterprise;

[0013] Step 2: Construct a data extraction neural network model, extract the characteristic information of the neighborhood nodes of the aggregation of the historical order data of the business enterprise, obtain the central time node aggregation feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and use the central time node aggregation feature vector as the input value of the neuron of the data extraction neural network model, set the replenishment cycle, and output the combined feature vector of the historical order data arranged in chronological order;

[0014] Step 3: Set the same replenishment cycle and obtain the combined characteristic vector of industrial enterprise production data within the same period;

[0015] Step 4: Construct a demand forecasting model for inventory-to-sales ratio, input the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data into the demand forecasting model, and output the warehouse goods management result.

[0016] Furthermore, the step 1 comprises:

[0017] Step 1.1: Obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods;

[0018] Step 1.2: Clean, integrate and standardize the collected historical order data of the commercial enterprise and the historical production data of the industrial enterprise to eliminate outliers and noise in the data.

[0019] Furthermore, the business enterprise's historical order data includes: order date, order quantity, product type, and customer type information.

[0020] Furthermore, the historical production data of the industrial enterprise includes: production volume, production cost, production efficiency, and raw material supply data.

[0021] Furthermore, the data extraction neural network model includes: an input layer, a hidden layer, a neighborhood aggregation layer, a central time node feature conversion layer, a time series processing layer, and an output layer;

[0022] Among them, the input layer receives the central time node aggregated feature vector of the Nth commercial enterprise as input, the hidden layer extracts features useful for predicting the next commercial enterprise, the neighborhood aggregation layer aggregates the feature information of these neighborhood nodes, the central time node feature conversion layer fuses the aggregated feature vector information, the time series processing layer generates a combined feature vector of historical order data arranged in chronological order according to the chronological order of the commercial enterprise's historical order data, and outputs the combined feature vector of historical order data arranged in chronological order through the output layer.

[0023] Furthermore, the number of hidden layers is 3, and each hidden layer includes a multi-head attention mechanism module and a feedforward neural network module, and the feature information of the aggregated neighborhood nodes of the historical order data is extracted through the multi-head attention mechanism module and the feedforward neural network module.

[0024] Furthermore, the expression of replenishment cycle is:

[0025]

[0026] Where D is the average daily demand, S S is the safety stock level, L is the total production and delivery time of the enterprise, and I is the inventory level at the time of replenishment.

[0027] In a second aspect, the present invention provides a warehouse goods management system based on inventory-to-sales ratio, applicable to a warehouse goods management method based on inventory-to-sales ratio, comprising:

[0028] Data acquisition module: acquires the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods, and organizes the historical order data of the business enterprise and the historical production data of the industrial enterprise;

[0029] Feature extraction module: construct a data extraction neural network model, extract the feature information of the aggregated neighborhood nodes of the business enterprise's historical order data, obtain the central time node aggregated feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and use the central time node aggregated feature vector as the input value of the neuron of the data extraction neural network model, set the replenishment cycle, and output the combined feature vector of the historical order data arranged in chronological order;

[0030] Data alignment module: Set the same replenishment cycle to obtain the combined feature vector of industrial and enterprise production data within the same period of time;

[0031] Management module: construct a demand forecasting model for inventory-to-sales ratio, input the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data into the inventory-to-sales ratio demand forecasting model, and output the warehouse goods management results.

[0032] In a third aspect, the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are performed.

[0033] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in the above method are performed.

[0034] Beneficial effects of the present invention: The present invention provides a method, system, device and medium for managing stored goods based on the inventory-to-sales ratio. First, the present invention constructs a data extraction neural network model based on the historical order data of each business enterprise that needs stored goods and the historical production data of the industrial enterprises that produce the stored goods, extracts the feature information of the aggregated neighborhood nodes of the historical order data of the business enterprises, obtains the central time node aggregated feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and uses the central time node aggregated feature vector as the input value of the neuron of the data extraction neural network model, sets the replenishment cycle, and outputs the combined feature vector of the historical order data arranged in chronological order; secondly, sets the same replenishment cycle, and obtains the combined feature vector of the industrial enterprise production data within the same time; finally, constructs an inventory-to-sales ratio demand forecasting model, inputs the combined feature vector of the historical order data and the combined feature vector of the industrial enterprise production data into the inventory-to-sales ratio demand forecasting model, and outputs the warehouse goods management result. The present invention accurately controls the inventory level through the inventory-to-sales ratio, reduces unnecessary inventory backlogs, makes the warehousing and outbound transportation of goods more efficient, and reduces labor costs. At the same time, it can improve the order delivery rate, reduce the risk of unsalable goods, reduce warehouse congestion, improve the storage environment, and improve the storage efficiency of goods.

[0035] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of the steps of the method of the present invention;

[0037] Figure 2 It is a functional block diagram of the system of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] See also Figure 1 As shown, in the first aspect, the present application provides a method for managing warehouse goods based on inventory-to-sales ratio, comprising the following steps:

[0040] Step 1: Obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods, and organize the historical order data of the business enterprises and the historical production data of the industrial enterprise;

[0041] Step 2: Construct a data extraction neural network model, extract the characteristic information of the aggregated neighborhood nodes of the business enterprise's historical order data, obtain the central time node aggregated feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and use the central time node aggregated feature vector as the input value of the neuron of the data extraction neural network model, set the replenishment cycle, and output the combined feature vector of the historical order data arranged in chronological order;

[0042] Step 3: Set the same replenishment cycle and obtain the combined characteristic vector of industrial enterprise production data within the same period;

[0043] Step 4: Construct a demand forecasting model for inventory-to-sales ratio, input the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data into the demand forecasting model, and output the warehouse goods management results.

[0044] Specifically, step 1 includes:

[0045] Step 1.1: Obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods;

[0046] Step 1.2: Clean, integrate and standardize the collected historical order data of commercial enterprises and historical production data of industrial enterprises to eliminate outliers and noise in the data.

[0047] Specifically, the business's historical order data includes: order date, order quantity, product type, and customer type information.

[0048] Specifically, the historical production data of industrial enterprises include: production volume, production cost, production efficiency, and raw material supply data.

[0049] Specifically, the data extraction neural network model includes: input layer, hidden layer, neighborhood aggregation layer, central time node feature conversion layer, time series processing layer and output layer;

[0050] Among them, the input layer receives the central time node aggregated feature vector of the Nth commercial enterprise as input, the hidden layer extracts features that are useful for predicting the next commercial enterprise, the neighborhood aggregation layer aggregates the feature information of these neighborhood nodes, the central time node feature conversion layer fuses the aggregated feature vector information, and the time series processing layer generates a combined feature vector of historical order data arranged in chronological order according to the time sequence of the commercial enterprise's historical order data, and outputs the combined feature vector of historical order data arranged in chronological order through the output layer.

[0051] Specifically, the number of hidden layers is 3, and each hidden layer includes a multi-head attention mechanism module and a feedforward neural network module, through which the feature information of the aggregated neighborhood nodes of the historical order data is extracted.

[0052] Specifically, the expression of replenishment cycle is:

[0053]

[0054] Where D is the average daily demand, S S is the safety stock level, L is the total production and delivery time of the enterprise, and I is the inventory level at the time of replenishment.

[0055] Specifically, the inventory-to-sales ratio (ISR) is usually defined as:

[0056] [ISR = \frac{\text{Inventory}}{\text{Sales}}];

[0057] Among them, inventory volume refers to the inventory quantity at a certain point in time, and sales volume can be the total sales volume within a certain period of time.

[0058] Specifically, the output of warehouse goods management results includes: based on the inventory-to-sales ratio and the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data, the required inventory is obtained to formulate an inventory adjustment strategy. For example, if the current inventory is lower than the required inventory, the inventory needs to be increased; if the current inventory is higher than the required inventory, the inventory needs to be reduced.

[0059] See also Figure 2 As shown, in a second aspect, the present invention provides a warehouse goods management system based on inventory-to-sales ratio, which is applicable to a warehouse goods management method based on inventory-to-sales ratio, including:

[0060] Data acquisition module: obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods, and organize the historical order data of the business enterprise and the historical production data of the industrial enterprise;

[0061] Feature extraction module: Build a data extraction neural network model, extract the feature information of the aggregated neighborhood nodes of the business enterprise's historical order data, obtain the central time node aggregated feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and use the central time node aggregated feature vector as the input value of the neuron of the data extraction neural network model, set the replenishment cycle, and output the combined feature vector of the historical order data arranged in chronological order;

[0062] Data alignment module: Set the same replenishment cycle to obtain the combined feature vector of industrial and enterprise production data within the same period of time;

[0063] Management module: Build a demand forecasting model for inventory-to-sales ratio, input the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data into the demand forecasting model, and output the warehouse goods management results.

[0064] In a third aspect, the present invention provides an electronic device including a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of a warehouse goods management method based on inventory-to-sales ratio are executed.

[0065] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are executed. Through the above technical solution, when the computer program is executed by the processor, the method in any optional implementation of the above embodiment is executed to realize the function of a warehouse goods management method based on inventory-to-sales ratio.

[0066] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0067] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

Claims

1. A method for managing warehouse goods based on inventory-to-sales ratio, characterized in that: include: Step 1: Obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods, and organize the historical order data of the business enterprise and the historical production data of the industrial enterprise; Step 2: Construct a data extraction neural network model, extract the characteristic information of the neighborhood nodes of the aggregation of the historical order data of the business enterprise, obtain the central time node aggregation feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and use the central time node aggregation feature vector as the input value of the neuron of the data extraction neural network model, set the replenishment cycle, and output the combined feature vector of the historical order data arranged in chronological order; Step 3: Set the same replenishment cycle and obtain the combined characteristic vector of industrial enterprise production data within the same period; Step 4: Construct a demand forecasting model for inventory-to-sales ratio, input the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data into the inventory-to-sales ratio demand forecasting model, and output the warehouse goods management result; The data extraction neural network model includes: an input layer, a hidden layer, a neighborhood aggregation layer, a central time node feature conversion layer, a time series processing layer and an output layer; The input layer receives the central time node aggregated feature vector of the Nth commercial enterprise as input, the hidden layer extracts features useful for predicting the next commercial enterprise, the neighborhood aggregation layer aggregates the feature information of these neighborhood nodes, the central time node feature conversion layer fuses the aggregated feature vector information, the time series processing layer generates a combined feature vector of historical order data arranged in chronological order according to the chronological order of the commercial enterprise's historical order data, and the output layer outputs the combined feature vector of historical order data arranged in chronological order; The number of hidden layers is 3, and each hidden layer includes a multi-head attention mechanism module and a feedforward neural network module. The multi-head attention mechanism module and the feedforward neural network module are used to extract the feature information of the neighborhood nodes of the historical order data aggregation.

2. A method for managing warehouse goods based on inventory-to-sales ratio according to claim 1, characterized in that: The step 1 comprises: Step 1.1: Obtain the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods; Step 1.2: Clean, integrate and standardize the collected historical order data of the commercial enterprise and the historical production data of the industrial enterprise to eliminate outliers and noise in the data.

3. A method for managing warehouse goods based on inventory-to-sales ratio according to claim 1, characterized in that: The business enterprise's historical order data includes: order date, order quantity, product type, and customer type information.

4. A method for managing warehouse goods based on inventory-to-sales ratio according to claim 1, characterized in that: The industrial enterprise's historical production data includes: production volume, production cost, production efficiency, and raw material supply data.

5. A method for managing warehouse goods based on inventory-to-sales ratio according to claim 1, characterized in that: The expression of replenishment cycle is: Where D is the average daily demand, is the safety stock level, The total production and delivery time of the industrial enterprise, The inventory level at the time of replenishment.

6. A warehouse goods management system based on inventory-to-sales ratio, applicable to a warehouse goods management method based on inventory-to-sales ratio according to any one of claims 1 to 5, characterized in that: include: Data acquisition module: acquires the historical order data of each business enterprise that needs to store goods and the historical production data of the industrial enterprise that produces the stored goods, and organizes the historical order data of the business enterprise and the historical production data of the industrial enterprise; Feature extraction module: construct a data extraction neural network model, extract the feature information of the aggregated neighborhood nodes of the business enterprise's historical order data, obtain the central time node aggregated feature vector of the historical order data of the N+1th business enterprise after the Nth business enterprise is aggregated, and use the central time node aggregated feature vector as the input value of the neuron of the data extraction neural network model, set the replenishment cycle, and output the combined feature vector of the historical order data arranged in chronological order; Data alignment module: Set the same replenishment cycle to obtain the combined feature vector of industrial and enterprise production data within the same period of time; Management module: construct a demand forecasting model for inventory-to-sales ratio, input the combined feature vector of historical order data and the combined feature vector of industrial enterprise production data into the inventory-to-sales ratio demand forecasting model, and output the warehouse goods management results.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 5 are executed.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are executed.

Images