A warehouse optimization method, device and medium based on code recognition

Abstract

The present invention discloses a storage optimization method, device and medium based on code identification, which relates to the field of data processing technology, including: step 1: determining the product types stored in the target warehouse, and setting unique code identification for different types of products; step 2: using the information of the product identification as the characteristic data of the product type, and establishing a multivariate linear relationship between the storage quantity and the characteristic data of the product type; step 3: determining the storage prediction value of each product type based on the multivariate linear relationship between the storage quantity and the characteristic data of the product type; step 4: performing storage optimization based on the storage prediction value of each product type. The present invention can improve the efficiency of storage management.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a warehouse optimization method, device and medium based on code identification. Background Art

[0002] Warehouse management is an important task that cannot be ignored by enterprises. It is an important form of effective material management. It is the place where various actions such as storing and retrieving materials are carried out in the production process of the entire enterprise.

[0003] Existing warehouse management does not take into account the relationship between storage volume and product types. Since the demand for each product type is different, it may lead to problems such as inventory backlog and out-of-stock, low storage space utilization and supply chain instability. Summary of the invention

[0004] 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 optimization method, device and medium based on code recognition, which are used to solve the technical problems existing in the above-mentioned prior art.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a storage optimization method based on label recognition, comprising:

[0006] Step 1: Determine the types of products stored in the target warehouse and set unique coding labels for different types of products;

[0007] Step 2: Use the product identification information as the characteristic data of the product category, and establish a multivariate linear relationship between the storage volume and the characteristic data of the product category;

[0008] Step 3: Determine the storage forecast value of each product type based on the multivariate linear relationship between storage volume and characteristic data of product types;

[0009] Step 4: Perform warehouse optimization based on the warehouse forecast value of each product type.

[0010] Furthermore, the code label includes: product type information, product size information and storage location.

[0011] Furthermore, the step 2 comprises:

[0012] Step 2.1: Use the product identification information as the characteristic data of the product category;

[0013] Step 2.2: Preprocess the characteristic data of product categories;

[0014] Step 2.3: Construct a multivariate linear regression model to establish the multivariate linear relationship between the storage volume and the characteristic data of product types based on the preprocessed characteristic data.

[0015] Furthermore, the step 2.2: preprocessing the feature data includes: missing value filling processing, outlier processing, and feature encoding processing.

[0016] Furthermore, the step 2.3: constructing a multivariate linear regression model, establishing a multivariate linear relationship between the storage volume and the characteristic data of the product type according to the preprocessed characteristic data, includes:

[0017] Select the indicators that have an impact on sales in the characteristic data of the target product category as independent variables;

[0018] Select the output of the target product category as the dependent variable;

[0019] Construct a multiple linear regression model, the expression is:

[0020] Y=a+b1X1+b2X2+…+b n X n ;

[0021] In the formula, Y represents the dependent variable, a represents the intercept term, b1, b2…b n Represent different independent variables, X1, X2…X n Respectively represent the weight coefficient of each independent variable;

[0022] The multivariate linear regression model is used to obtain the multivariate linear relationship between the storage volume and the characteristic data of the product types.

[0023] Furthermore, the weight coefficient of the independent variable is calculated as follows:

[0024]

[0025] In the formula, |C n | represents the importance score of the nth independent variable in the dependent variable, |Z n | represents the total importance of n independent variables in the dependent variable.

[0026] Furthermore, the step 3 determines the storage forecast value of each product type based on the multivariate linear relationship between the storage volume and the characteristic data of the product type, including:

[0027] Step 3.1: Create a feature dataset containing product features and storage quantity based on the multivariate linear relationship between the feature data of storage quantity and product types;

[0028] Step 3.2: The feature data set is a training set and a test set;

[0029] Step 3.4: Build a neural network prediction model and use the training set data for training;

[0030] Step 3.5: The test set evaluates the performance of the neural network prediction model;

[0031] Step 3.6: The trained neural network prediction model is used to predict the characteristic data of the product type to be tested, and the predicted storage value is output.

[0032] Furthermore, the neural network prediction model includes a convolution operation, a weighted sum operation and an activation function, which is expressed as:

[0033]

[0034] In the formula, f represents the activation function, M i 、N i Respectively represent the vectors of feature data of the i-th input; represents the i-th feature data in the k-1th layer, (m,n) represents the value of the position, represents the convolution kernel from the feature data of the i-th input to the feature data of the j-th output in the k-th layer, M j represents the index set of all input feature data related to the jth output feature data, represents the bias top of the j-th output feature data in the k-th layer, Represents the storage value of the j-th output prediction in the k-th layer.

[0035] In a second 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.

[0036] In a third 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.

[0037] The present invention proposes a storage optimization method, device and medium based on code recognition, and the beneficial effects are as follows:

[0038] 1) By setting unique labels for different types of products, fast and accurate product identification is achieved, thereby improving the efficiency of warehouse management. This method avoids the errors that may occur in manually recording product information and reduces the time to find and check products;

[0039] 2) Establish a multivariate linear relationship between storage volume and product type feature data, so that companies can accurately predict the storage demand of various products based on historical data and current market trends. This prediction not only helps companies avoid inventory backlogs, but also ensures that they can replenish stocks in time to meet market demand when needed;

[0040] 3) Warehousing optimization based on warehousing forecast values ​​can help enterprises adjust their inventory structure and make inventory more reasonable. By reducing the inventory of slow-moving products and increasing the inventory of popular products, enterprises can use storage space more effectively and reduce inventory costs;

[0041] 4) Accurate warehouse forecasting and optimization can help companies reduce inventory risks. By avoiding inventory backlogs and out-of-stock situations, companies can reduce losses caused by inventory problems;

[0042] 5) With the development of the business and the increase of product types, new coding labels and feature data can be easily added to meet different warehouse management needs.

[0043] 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

[0044] Figure 1 The figure is a flow chart of the steps of the method of the present invention. DETAILED DESCRIPTION

[0045] 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.

[0046] Example 1, please refer to Figure 1 As shown, in the first aspect, the present application provides a warehouse optimization method based on label recognition, comprising:

[0047] Step 1: Determine the types of products stored in the target warehouse and set unique coding labels for different types of products;

[0048] Step 2: Use the product identification information as the characteristic data of the product category, and establish a multivariate linear relationship between the storage volume and the characteristic data of the product category;

[0049] Step 3: Determine the storage forecast value of each product type based on the multivariate linear relationship between storage volume and characteristic data of product types;

[0050] Step 4: Perform warehouse optimization based on the warehouse forecast value of each product type.

[0051] Specifically, the code label includes: product type information, product size information and storage location.

[0052] Specifically, step 2 includes:

[0053] Step 2.1: Use the product identification information as the characteristic data of the product category;

[0054] Step 2.2: Preprocess the characteristic data of product categories;

[0055] Step 2.3: Construct a multivariate linear regression model to establish the multivariate linear relationship between the storage volume and the characteristic data of product types based on the preprocessed characteristic data.

[0056] Specifically, step 2.2: preprocessing of feature data includes: missing value filling processing, outlier processing, and feature encoding processing.

[0057] Specifically, step 2.3: construct a multivariate linear regression model, and establish a multivariate linear relationship between the characteristic data of storage volume and product type based on the preprocessed characteristic data, including:

[0058] Select the indicators that have an impact on sales in the characteristic data of the target product category as independent variables;

[0059] Select the output of the target product category as the dependent variable;

[0060] Construct a multiple linear regression model, the expression is:

[0061] Y=a+b1X1+b2X2+…+b n X n ;

[0062] In the formula, Y represents the dependent variable, a represents the intercept term, b1, b2…b n Represent different independent variables, X1, X2…X n Respectively represent the weight coefficient of each independent variable;

[0063] The multivariate linear relationship between the storage volume and the characteristic data of product types was obtained based on the multivariate linear regression model.

[0064] Specifically, the calculation method of the weight coefficient of the independent variable is:

[0065]

[0066] In the formula, |C n | represents the importance score of the nth independent variable in the dependent variable, |Z n | represents the total importance of n independent variables in the dependent variable.

[0067] Specifically, step 3 determines the storage forecast value of each product type based on the multivariate linear relationship between the storage volume and the characteristic data of the product type, including:

[0068] Step 3.1: Create a feature dataset containing product features and storage quantity based on the multivariate linear relationship between the feature data of storage quantity and product types;

[0069] Step 3.2: Divide the feature data set into training set and test set;

[0070] Step 3.4: Build a neural network prediction model and train it using the training set data;

[0071] Step 3.5: The test set evaluates the performance of the neural network prediction model;

[0072] Step 3.6: The trained neural network prediction model is used to predict the characteristic data of the product type to be tested, and the predicted storage value is output.

[0073] Specifically, the neural network prediction model includes convolution operation, weighted sum operation and activation function, which can be expressed as:

[0074]

[0075] In the formula, f represents the activation function, M i 、N i Respectively represent the vectors of feature data of the i-th input; represents the i-th feature data in the k-1th layer, (m, n) represents the value of the position, represents the convolution kernel from the feature data of the i-th input to the feature data of the j-th output in the k-th layer, M j represents the index set of all input feature data related to the jth output feature data, represents the bias top of the j-th output feature data in the k-th layer, Represents the storage value of the j-th output prediction in the k-th layer.

[0076] Specifically, M. i and N i are the i-th input feature vectors; Represents the value of the i-th feature data at position (m, n) in the k-1-th layer; Represents the value of the convolution kernel at position (m, n) from the i-th input feature data to the j-th output feature data in the k-th layer; the internal double summation implements the convolution operation, that is, traversing all positions of the input feature data and the convolution kernel, and multiplying the elements at the corresponding positions and then summing them. The external summation implements the weighted summation of all input feature data related to the j-th output feature data. Finally, the result of the weighted summation is nonlinearly transformed by the activation function f() to obtain the j-th output feature data in the k-th layer.

[0077] In a second aspect, the present application provides an electronic device, including 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.

[0078] In a third 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 performed.

[0079] 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.

[0080] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Wherein, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a disk or an 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] 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 storage optimization method based on label recognition, characterized in that: include: Step 1: Determine the types of products stored in the target warehouse and set unique coding labels for different types of products; Step 2: Use the product identification information as the characteristic data of the product category, and establish a multivariate linear relationship between the storage volume and the characteristic data of the product category; Step 3: Determine the storage forecast value of each product type based on the multivariate linear relationship between storage volume and characteristic data of product types; Step 4: Optimize storage based on the storage forecast value of each product type; Wherein, the step 2 comprises: Step 2.1: Use the product identification information as the characteristic data of the product category; Step 2.2: Preprocess the characteristic data of product categories; Step 2.3: Construct a multivariate linear regression model to establish the multivariate linear relationship between the storage volume and the characteristic data of product types based on the preprocessed characteristic data, including: Select the indicators that have an impact on sales in the characteristic data of the target product category as independent variables; Select the output of the target product category as the dependent variable; Construct a multiple linear regression model, the expression is: In the formula, represents the dependent variable, a represents the intercept term, represent different independent variables, Respectively represent the weight coefficient of each independent variable; Obtaining a multivariate linear relationship between storage volume and characteristic data of product types according to the multivariate linear regression model; The step 3 determines the storage forecast value of each product type based on the multivariate linear relationship between the storage volume and the characteristic data of the product type, including: Step 3.1: Create a feature dataset containing product features and storage quantity based on the multivariate linear relationship between the feature data of storage quantity and product types; Step 3.2: The feature data set is a training set and a test set; Step 3.3: Build a neural network prediction model and use the training set data for training; Step 3.4: The test set evaluates the performance of the neural network prediction model; Step 3.5: The trained neural network prediction model is used to predict the characteristic data of the product type to be tested, and the predicted storage value is output; The neural network prediction model includes a convolution operation, a weighted sum operation, and an activation function, which is expressed as: In the formula, represents the activation function, Respectively represent the vectors of feature data of the i-th input; represents the i-th feature data in the k-1th layer, The value representing the position, Represents the convolution kernel from the feature data of the i-th input to the feature data of the j-th output in the k-th layer, represents the index set of all input feature data related to the jth output feature data, represents the bias top of the j-th output feature data in the k-th layer, Represents the storage value of the j-th output prediction in the k-th layer.

2. A storage optimization method based on label recognition according to claim 1, characterized in that: The labeling includes: product type information, product size information and storage location.

3. The storage optimization method based on label recognition according to claim 1 is characterized in that: The step 2.2: preprocessing the feature data includes: missing value filling processing, outlier processing, and feature encoding processing.

4. The storage optimization method based on label recognition according to claim 1 is characterized in that: The calculation method of the weight coefficient of the independent variable is: In the formula, It indicates the importance score of the nth independent variable in the dependent variable. It represents the total importance of n independent variables in the dependent variable.

5. 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 4 are executed.

6. 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 4 are executed.

Images