Barcode printing method, device and equipment for air conditioner packaging box and medium

Abstract

The invention discloses a bar code printing method, device and equipment for an air conditioner packaging box and a medium. The method comprises the steps of obtaining order bar code information of a packaging box through radio frequency identification, and obtaining a bar code template and sheet number information corresponding to the order bar code according to the order bar code; controlling bar code printing equipment to print bar codes according to the bar code template and the sheet number information to obtain a plurality of bar codes; image information of each bar code is obtained, bar code qualification detection is carried out on the image information of each bar code according to a preset bar code image detection model, and the bar codes which are detected to be qualified are pasted to the packaging box. The order bar code information is automatically obtained through radio frequency identification and matched with the corresponding bar code template and the number of pieces, automatic printing of the bar codes is achieved, qualification detection is conducted on each bar code based on the preset bar code image detection model, automatic quality inspection of the bar codes is achieved, it is ensured that only qualified bar codes are pasted to the packaging box, and the production efficiency is improved. The problems that manual printing is low in efficiency and prone to making mistakes are solved, and efficiency and accuracy are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intelligent manufacturing technology, and in particular to a barcode printing method, device, equipment, and medium for an air conditioner packaging box. Background Art

[0002] The barcodes on the packaging boxes of air conditioner indoor and outdoor units serve as carriers of product information and customer data. Their accuracy plays a decisive role in production process control and after-sales quality traceability systems. In current industrial scenarios, packaging box barcodes are distributed in a diverse range of types due to product model iterations, customer customization requirements, and differences in appearance design specifications. Furthermore, the fact that each product corresponds to an independent barcode makes the total amount of printing extremely large. Existing technologies use a manual printing mode, relying on operators to match barcode templates based on order information and execute the printing operation. This mode has two drawbacks: on the one hand, the high-intensity manual operation leads to limited production capacity and is difficult to adapt to the needs of large-scale production; on the other hand, the lack of an automated quality inspection mechanism leads to frequent quality defects such as blurred barcodes, high reprint rates, and format deviations. This not only results in material waste and loss of work time, but also affects the efficiency of after-sales response due to the failure of traceability information. Especially in mass production scenarios, the consistency defects of manual operation and the structural lack of quality inspection links have become key pain points that restrict the progress of intelligent manufacturing. Automation technology innovation is urgently needed to break through the existing bottlenecks. Summary of the Invention

[0003] The present invention provides a barcode printing method, device, equipment and medium for air conditioner packaging boxes, aiming to solve the problem that the barcodes on the existing air conditioner indoor and outdoor unit packaging boxes require operators to frequently check order information and manually select corresponding barcode templates, resulting in high human resource consumption and low operating efficiency.

[0004] In a first aspect, an embodiment of the present invention provides a barcode printing method for an air conditioner packaging box, the method comprising:

[0005] Obtain the order barcode information of the packaging box through radio frequency identification, and obtain the corresponding barcode template and number of sheets according to the order barcode;

[0006] Controlling a barcode printing device to print a plurality of barcodes according to the barcode template and the number of sheets information;

[0007] The image information of each barcode is obtained, the image information of each barcode is subjected to a barcode qualification test according to a preset barcode image detection model, and the qualified barcodes are pasted on the packaging box.

[0008] In a second aspect, the present invention further provides a barcode printing device for an air conditioner packaging box, comprising a unit for executing the above method.

[0009] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0010] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program can implement the above method when executed by a processor.

[0011] The present invention provides a barcode printing method, device, equipment, and medium for air conditioner packaging boxes. The method comprises: obtaining order barcode information for the packaging box through radio frequency identification, and obtaining a corresponding barcode template and number of sheets based on the order barcode; controlling a barcode printing device to print a plurality of barcodes based on the barcode template and the number of sheets; obtaining image information of each barcode, performing a barcode qualification test on the image information of each barcode based on a preset barcode image detection model, and pasting the qualified barcodes onto the packaging box. The present invention automatically obtains order barcode information through radio frequency identification and matches the corresponding barcode template and number of sheets, thereby achieving automatic barcode printing. Furthermore, based on a preset barcode image detection model, each barcode is tested for qualification, achieving automatic barcode quality inspection, ensuring that only qualified barcodes are pasted onto the packaging box, thereby solving the problems of low efficiency and easy errors in manual printing, improving efficiency and accuracy, and significantly enhancing production efficiency and barcode quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 Schematic diagram of the steps of the barcode printing method for an air conditioner packaging box according to an embodiment of the present invention;

[0014] Figure 2 for Figure 1 A schematic flow chart of sub-steps of step S110;

[0015] Figure 3 for Figure 1 A schematic flow chart of sub-steps of step S130;

[0016] Figure 4 for Figure 3 A schematic flow chart of sub-steps of step S133;

[0017] Figure 5A schematic flow chart of the steps of a barcode printing method for an air conditioner packaging box according to another embodiment of the present invention;

[0018] Figure 6 This is a logic diagram of a barcode printing method for an air conditioner packaging box according to an embodiment of the present invention;

[0019] Figure 7 A schematic block diagram of a barcode printing device for an air conditioner packaging box provided by an embodiment of the present invention;

[0020] Figure 8 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] In the existing barcode printing process for air conditioner packaging, operators must manually verify order information and select the corresponding barcode template. This not only consumes a large amount of manpower but also easily leads to printing errors and format confusion, severely restricting production efficiency and increasing the difficulty of quality traceability. An automated solution is urgently needed to improve barcode printing accuracy and efficiency.

[0027] To this end, the present invention proposes a barcode printing method, device, equipment, and medium for air conditioner packaging boxes, which can achieve automatic barcode printing and automatic quality inspection, solving the problems of low efficiency and easy errors in manual printing, improving efficiency and accuracy, and significantly enhancing production efficiency and barcode quality. The details are as follows:

[0028] See also Figure 1 , Figure 1 A schematic flow chart of a method for printing a barcode on an air conditioner packaging box according to an embodiment of the present invention is provided. The method includes steps S110 to S130.

[0029] S110, obtaining order barcode information of the packaging box through radio frequency identification, and obtaining the corresponding barcode template and number of sheets according to the order barcode;

[0030] In this embodiment, radio frequency identification (RFID) refers to the technology that automatically identifies electronic tags attached to packaging boxes through radio frequency signals and acquires data. The order barcode information is the unique identification code stored in the electronic tag, which contains key data such as product model, batch number, and customer information. The barcode template is a standardized barcode format file pre-stored in the Manufacturing Execution System (MES). The number of sheets refers to the number of barcodes required to be printed for the current order. In specific implementation, the operator transports the packaging box containing the air conditioner to the RFID read / write area. The RFID reader automatically scans the electronic tag on the packaging box to obtain the order barcode information. The automatic barcode printing system then initiates a query request to the MES system based on the order barcode information. The MES system matches the corresponding barcode template file and the required print quantity and returns it to the printing system. This step, through the automated information acquisition and matching mechanism, completely eliminates the risk of manual error in checking and selecting barcode templates, enabling efficient and accurate acquisition of barcode printing parameters, significantly reducing labor costs and improving the efficiency of the production preparation stage, significantly improving production cycle efficiency.

[0031] In one embodiment, if Figure 2 As shown, the step S110 includes: S111-S112.

[0032] S111, uploading the order barcode information to the barcode automatic printing system;

[0033] S112. Obtaining, by the automatic barcode printing system, a barcode template and sheet quantity information matching the order barcode information from a manufacturing execution system according to the order barcode information.

[0034] In this embodiment, the barcode automatic printing system refers to an intelligent printing control terminal deployed on the packaging production line, and the manufacturing execution system (MES) is an enterprise-level production management system. In specific implementation, the order barcode information obtained by the RFID reader is transmitted to the data receiving module of the barcode automatic printing system through the 6G millimeter wave communication network combined with the data transmission mechanism of the message queue. The module verifies and formats the data and generates a query instruction. It establishes a communication connection with the MES system through the OPC UA protocol. After receiving the query request, the MES system uses the order barcode information as an index to retrieve the associated barcode template file (including parameters such as barcode size, encoding rules and content layout) and the total number of barcodes required to be printed for the order in its database. The query results are returned to the printing system in JSON data format. The configuration parsing module of the printing system parses the received data and stores it in the cache queue. This step avoids the tedious operation of manually logging into the system to query the template through an automated data interaction link. Compared with the traditional manual template matching method, it shortens the time consumption and eliminates printing errors caused by manual template selection, thereby improving the accuracy and efficiency of production data interaction.

[0035] S120, controlling a barcode printing device to print a plurality of barcodes according to the barcode template and the number of barcodes;

[0036] In this embodiment, the barcode printing device is an industrial-grade device with automatic data reception and batch printing capabilities, supporting the generation of standard barcode labels based on electronic templates. During specific implementation, the barcode automatic printing system sends the acquired barcode template and sheet quantity information to the barcode printing device via a message queue. After the device parses the barcode format, character encoding, and other parameters in the template, it initiates the batch printing process based on the sheet quantity information and generates the corresponding number of barcodes on the label paper. This step replaces the traditional manual operation mode through automated instruction transmission and printing control, achieving unmanned intervention in the barcode printing process, effectively avoiding format errors caused by manual parameter input, and improving the efficiency and consistency of barcode printing.

[0037] S130: Obtain image information of each barcode, perform barcode qualification detection on the image information of each barcode according to a preset barcode image detection model, and stick the qualified barcodes on the packaging box.

[0038] In this embodiment, the barcode image detection model refers to an algorithm model for analyzing the quality of a barcode image and determining whether it meets the standard. The barcode image detection model can be various image detection models and is not limited here. In specific implementation, the industrial camera collects images of each barcode after printing. The image processing module pre-processes the collected barcode image and inputs it into the barcode image detection model. The model analyzes the image features of the barcode to determine whether the barcode has quality problems such as blur, defect, contamination or encoding errors. For barcodes that pass the inspection, the robot automatically absorbs and accurately pastes them to the designated position of the packaging box. For barcodes that fail the inspection, the system automatically triggers an alarm and records the unqualified information. At the same time, it controls the barcode printing device to reprint the barcode and continues to inspect the reprinted barcode through the barcode image detection model. This step realizes the automatic detection of barcode quality, ensures that only qualified barcodes are applied to the packaging box, improves the reliability of barcode recognition, replaces manual visual inspection with automated visual inspection, realizes the objective evaluation of barcode quality, and timely handles unqualified products to avoid delays in subsequent production links.

[0039] In one embodiment, if Figure 3 As shown, the step S130 includes: S131-S133.

[0040] S131, performing image preprocessing on the image information of the barcode;

[0041] S132. Extracting spatial feature information from the image information after image preprocessing using a pretrained convolutional neural network model, wherein the barcode image detection model is the convolutional neural network model;

[0042] S133: Determine whether the barcode is qualified based on the spatial feature information.

[0043] In this embodiment, image preprocessing includes grayscaling, binarization, denoising, and edge enhancement. Spatial feature information refers to the characteristic vector that reflects the quality of the barcode image. In specific implementation, after acquiring the barcode image information through an industrial camera, the preprocessing module performs grayscale conversion on the image, converting the RGB three-channel image into a single-channel grayscale image to reduce the data dimension. Next, Gaussian filtering is performed to denoise the image, convolving the image with a 3×3 Gaussian kernel matrix to reduce salt and pepper noise caused by ink splashes or equipment vibration during printing. Histogram equalization is then used to enhance contrast, stretching the image pixel value distribution to the full grayscale range [0, 255] to highlight the boundary difference between the barcode lines and the background. The preprocessed image is then input into a pre-trained convolutional neural network model. The barcode image detection model of this embodiment adopts a convolutional neural network model. The model first extracts the first feature of the image through a 5×5 convolution layer to capture the basic line contour of the barcode. After the GELU activation function introduces nonlinear mapping, the key features are retained and the dimension is reduced through a 2×2 maximum pooling layer. The 3×3 convolution layer is then used to further extract detailed features such as the bar-space ratio and module spacing. After GELU activation and maximum pooling again, the fully connected layer fuses the multi-layer features into a 128-dimensional feature vector. Each dimension in the vector corresponds to a key quality indicator such as barcode clarity (calculated by line edge gradient value), edge integrity (based on contour closure evaluation), and module contrast (bar-space grayscale difference). Based on the feature vector, the system outputs a qualified probability value between 0 and 1 through a regression layer. If the probability value is greater than a preset threshold of 0.8, it is judged to be qualified, or the feature vector is input into a fully connected layer and a Sigmoid classifier for binary classification (qualified / unqualified) and triggers a reprinting mechanism. This step achieves intelligent and accurate detection of barcode quality through multi-level feature extraction of deep convolutional networks and comprehensive judgment of machine learning algorithms. It can effectively identify various defects such as blur, defects, and contamination, significantly improving detection accuracy and automation level.

[0044] In one embodiment, if Figure 4 As shown, the steps of step S133 include: S1331-S1332.

[0045] S1331, performing linear regression prediction on the spatial feature information of the barcode to output a qualified probability value corresponding to the barcode;

[0046] S1332: If the qualified probability value is greater than a preset qualified threshold value, the barcode qualification test result of the barcode is determined to be qualified.

[0047] In this embodiment, linear regression prediction refers to prediction by establishing a linear relationship model between the feature vector and the target value. The qualified probability value is the degree of possibility of the barcode being qualified, which is calculated by the model. The preset qualified threshold value is the judgment standard value set according to the actual production requirements. In specific implementation, the fully connected layer of the convolutional neural network maps the extracted multi-dimensional spatial feature information into one-dimensional spatial feature information. The system inputs the feature vector of the one-dimensional spatial feature information extracted by the convolutional neural network into the linear regression prediction layer. This layer assigns different weights to each feature dimension and adds a bias term. After conversion by the Sigmoid function, it outputs a qualified probability value between 0 and 1. When the output probability value is greater than the preset qualified threshold value of 0.85, the system determines that the barcode quality is qualified and allows it to enter the pasting process. Otherwise, it is judged as unqualified and triggers the automatic rejection and reprinting process. This step evaluates the quality of the barcode by quantifying the probability value, achieves the consistency and adjustability of the detection standard, avoids the subjective differences in manual judgment, and provides an objective basis for quality traceability.

[0048] In one embodiment, the construction of the convolutional neural network model includes: collecting image samples of qualified barcodes and unqualified barcodes, labeling each image sample as qualified or unqualified, and performing data enhancement processing on the image samples, wherein the data enhancement processing includes: random rotation, random flipping and random scaling; dividing the image samples into a training set, a validation set and a test set, and performing image normalization preprocessing on the image samples; constructing a convolutional neural network model, wherein the convolutional neural network model includes a sequentially progressive input layer, at least one group of network structures, a fully connected layer and a regression layer, and the network structure includes a convolution layer, an activation layer and a pooling layer; inputting the training set into the constructed convolutional neural network model for training, and evaluating the trained convolutional neural network model through the validation set and the test set.

[0049] Specifically, the convolutional neural network-based construction process is implemented as follows: First, an industrial camera is used to collect barcode image data for different product models and template specifications. Quality inspectors then annotate the images as "qualified barcode" (labeled as 1) or "unqualified barcode" (labeled as 0) based on barcode printing quality standards. Unqualified samples include typical defects such as blur, damage, and deformation. Three data augmentation processes are then performed on the annotated dataset: random rotation to obtain barcode images at different angles, random flipping to obtain horizontal and vertical barcode images, and random scaling to obtain barcode images of different sizes. In practice, random rotation (generating barcode images at different perspectives within a range of ±15 degrees), random flipping (generating mirror images horizontally or vertically), and random scaling (generating images of different sizes by 0.8-1.2 times) are used to improve the model's adaptability to real-world scene changes. Next, the enhanced dataset is divided into training, validation, and test sets in a 6:2:2 ratio. The pixel values are mapped from [0, 255] to the [0, 1] interval through linear scaling. This is achieved using the formula x' = (x-x_min) / (x_max-x_min), where x is the pixel value. This helps eliminate brightness and contrast differences between images, making it easier for the model to learn common features of images. At the same time, it accelerates the model training process, improves the model's robustness to image features, and reduces the impact of brightness and contrast changes. Then, a convolutional neural network model was constructed. The model set the input layer to receive the preprocessed image and connected two groups of network structures in sequence: the first group of network structures included a 5×5 convolutional layer to extract the basic contour features of the barcode, a GELU activation layer to introduce nonlinear transformation, and a 2×2 maximum pooling layer to compress the feature dimension. The second group of network structures included a 3×3 convolutional layer to capture detailed features such as the bar-space ratio, a GELU activation layer to enhance feature expression, and a 2×2 maximum pooling layer to further reduce the dimension. Subsequently, a fully connected layer was used to map the multidimensional features into a one-dimensional vector, and finally a regression layer output a qualified probability value between 0 and 1. The training set was input into the model for 100 rounds of iterative training. The Adam optimizer was used to minimize the mean squared error loss function. The model generalization ability was evaluated on the validation set every 5 rounds, and the model accuracy was finally verified on the test set. This step improved the robustness of the model through data augmentation and normalization. The constructed hierarchical feature extraction architecture effectively captured the barcode quality characteristics, realized the standardized process of model training and evaluation, and ensured the reliability of the model in judging barcode quality under different working conditions.

[0050] In one embodiment, if Figure 5 As shown, the method also includes: S141-S143.

[0051] S141. Obtain operating parameters that affect dust deposition on the packaging box surface and input the operating parameters into a simulation tool. The operating parameters include wind speed, ambient humidity, ambient temperature, dust concentration, dust particle size, dust accumulation time, and the material of the packaging box surface.

[0052] S142. Based on the force equation of dust on the surface of the packaging box, a simulation model of the dust amount on the surface of the packaging box is constructed using the simulation tool, and the dust amount on the surface of the packaging box is output;

[0053] S143: If the amount of dust on the surface of the packaging box reaches a preset removal threshold, dust removal is performed on the surface of the packaging box.

[0054] In this embodiment, the working condition parameters refer to the workshop environment parameters and dust characteristic parameters and packaging box surface parameters that affect dust deposition. The dust quantity simulation model is a mathematical simulation model established through numerical simulation to predict the amount of dust deposition on the packaging box surface. The preset removal threshold is the maximum allowable value of dust set according to the production quality standard. The simulation software can be selected from ANSYS Fluent, Phoenics and cfx. In specific implementation, the system collects workshop wind speed (0.1-2m / s), relative humidity (30-70% RH), temperature (15-30℃) and dust concentration (0.1-5mg / m 3 ) and other parameters, while also obtaining data on the surface material properties and average dust particle size (1-100μm) of the current batch of packaging boxes. These parameters are then input into ANSYS Fluent simulation software. The simulation software constructs a 3D model based on the force equation for the dust on the packaging box surface, using the packaging box as the main body. By analyzing the force on the dust, the basis for dust deposition on the packaging box surface is determined: when the adhesion force is greater than the detachment force, the dust will deposit on the packaging box surface. The specific force analysis is as follows:

[0055] F vdw +F e +F cap +F g sinθ≥F d +F L +F g cosθ+F impact

[0056] Among them, θ is the tilt angle of the packaging box, F vdw is the van der Waals force, F e is the electrostatic force, F cap is the liquid bridge force, F g sinθ is the vertical component of gravity, F g cosθ is the horizontal component of gravity, F d is the fluid drag, FL is the lift and F impact For elasticity.

[0057] In the simulation tool, a three-dimensional model is constructed with the packaging box as the main body, and the workshop space is set as the simulation environment. According to the dust force equation, the combined effects of adhesion forces such as van der Waals force, liquid bridge force, and electrostatic force, and separation forces such as fluid drag and lift are considered. The dust movement and deposition rules are configured, and the deposition process of dust on the packaging box surface in the workshop is simulated through finite element calculation. The dust deposition mass on the packaging box surface in mg is output. When the simulation results show that the dust amount exceeds the preset removal threshold (such as 2mg / m 2 ), the system triggers the dust removal device (such as high-pressure air gun, electrostatic adsorption device) to automatically clean the surface of the packaging box; this step uses numerical simulation technology to accurately predict the amount of dust deposition, avoiding the problem of excessive or insufficient cleaning, ensuring the cleanliness of the packaging box surface and optimizing the dust removal energy consumption. At the same time, the model batch processing function can adapt to the rapid switching needs of different batches of products.

[0058] In summary, if Figure 6 As shown, the present invention uses radio frequency identification technology to automatically acquire packaging box order information and integrates it with an automatic barcode printing system. It then employs a convolutional neural network to intelligently detect barcode quality. A simulation model is then used to measure dust deposition on the packaging box surface and guide dust removal operations. Ultimately, automated equipment allows for precise barcode application, creating a complete intelligent packaging barcode management system. This embodiment automates the entire process, from information acquisition and barcode generation to quality testing and packaging box surface cleaning. This addresses the low efficiency, high error rate, and uncontrollable quality inherent in traditional manual operations, significantly improving the intelligence level of the production line and the consistency of product packaging quality.

[0059] Figure 7 FIG. 2 is a schematic block diagram of a barcode printing device 200 for an air conditioner packaging box provided by an embodiment of the present invention. Figure 7 As shown, corresponding to the above barcode printing method for air conditioner packaging box, the present invention also provides a barcode printing device 200 for air conditioner packaging box. The barcode printing device 200 for air conditioner packaging box includes a unit for executing the above barcode printing method for air conditioner packaging box, and the device can be configured in a computer device. Specifically, please refer to Figure 7 The barcode printing device 200 for the air conditioner packaging box includes: an acquisition unit 201, a printing unit 202 and a detection unit 203.

[0060] Among them, the acquisition unit 201 is used to obtain the order barcode information of the packaging box through radio frequency identification, and obtain the corresponding barcode template and number information based on the order barcode; the printing unit 202 is used to control the barcode printing device to print the barcode according to the barcode template and the number information to obtain multiple barcodes; the detection unit 203 is used to obtain the image information of each barcode, perform barcode qualification detection on the image information of each barcode according to a preset barcode image detection model, and paste the qualified barcodes on the packaging box.

[0061] In one embodiment, the acquisition unit 201 is further used to: upload the order barcode information to the barcode automatic printing system; and obtain the barcode template and number of sheets matching the order barcode information from the manufacturing execution system through the barcode automatic printing system according to the order barcode information.

[0062] In one embodiment, the detection unit 203 is further used to: perform image preprocessing on the image information of the barcode; extract spatial feature information from the image information after image preprocessing through a pre-trained convolutional neural network model, wherein the barcode image detection model is the convolutional neural network model; and determine whether the barcode is qualified based on the spatial feature information.

[0063] In one embodiment, the barcode printing device 200 for the air conditioner packaging box further includes: a convolutional neural network model building unit.

[0064] Among them, the convolutional neural network model construction unit is used to collect image samples of qualified barcodes and unqualified barcodes, label each image sample as qualified or unqualified, and perform data enhancement processing on the image samples, wherein the data enhancement processing includes: random rotation, random flipping and random scaling; dividing the image samples into a training set, a validation set and a test set, and performing image normalization preprocessing on the image samples; constructing a convolutional neural network model, wherein the convolutional neural network model includes a sequentially progressive input layer, at least one group of network structures, a fully connected layer and a regression layer, and the network structure includes a convolution layer, an activation layer and a pooling layer; inputting the training set into the constructed convolutional neural network model for training, and evaluating the trained convolutional neural network model through the validation set and the test set.

[0065] In one embodiment, the detection unit 203 is further used to: perform linear regression prediction on the spatial feature information of the barcode to output a qualified probability value corresponding to the barcode; if the qualified probability value is greater than a preset qualified threshold, the barcode qualification detection result of the barcode is determined to be qualified.

[0066] In one embodiment, the barcode printing device 200 for the air conditioner packaging box further includes: a simulation unit.

[0067] Among them, the simulation unit is used to obtain the operating parameters that affect the dust deposition on the surface of the packaging box and input the operating parameters into the simulation tool. The operating parameters include: wind speed, ambient humidity, ambient temperature, dust concentration, dust particle size and dust accumulation time, as well as the material of the packaging box surface; based on the force equation of dust on the packaging box surface, the simulation tool is used to construct a simulation model of the dust amount on the packaging box surface and output the dust amount on the packaging box surface; if the dust amount on the packaging box surface reaches a preset removal threshold, the packaging box surface is dust-removed. The force equation of dust on the packaging box surface includes:

[0068] F vdw +F e +F cap +F g sinθ≥F d +F L +F g cosθ+F impact

[0069] Among them, θ is the tilt angle of the packaging box, F vdw is the van der Waals force, F e is the electrostatic force, F cap is the liquid bridge force, F g sinθ is the vertical component of gravity, F g cosθ is the horizontal component of gravity, F d is the fluid drag, F L is the lift and F impact For elasticity.

[0070] The barcode printing device 200 for the air conditioner packaging box can be implemented in the form of a computer program. The computer program can be used in Figure 8 Runs on the computer device shown.

[0071] See also Figure 8 , Figure 8 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal.

[0072] See Figure 8 The computer device 500 includes a processor 502 , a memory, and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0073] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, which, when executed, can enable the processor 502 to execute a barcode printing method for an air conditioner packaging box.

[0074] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0075] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a barcode printing method for an air conditioner packaging box.

[0076] The network interface 505 is used to communicate with other devices through the network. Figure 8 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0077] The processor 502 is configured to run a computer program 5032 stored in the memory to implement the steps of the above method.

[0078] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0079] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program includes program instructions, which can be stored in a storage medium that is computer-readable. The program instructions are executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0080] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor performs the steps of the above method.

[0081] The storage medium may be any computer-readable storage medium that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0082] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0083] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0084] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0085] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes a number of instructions for causing a computer device to execute all or part of the steps of the method described in various embodiments of the present invention.

[0086] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0087] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, to the extent such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to encompass such changes and modifications.

[0088] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A barcode printing method for an air conditioner packaging box, characterized in that: include: Obtain the order barcode information of the packaging box through radio frequency identification, and obtain the corresponding barcode template and number of sheets according to the order barcode; Controlling a barcode printing device to print a plurality of barcodes according to the barcode template and the number of sheets information; The image information of each barcode is obtained, the image information of each barcode is subjected to a barcode qualification test according to a preset barcode image detection model, and the qualified barcodes are pasted on the packaging box.

2. The method according to claim 1, characterized in that The step of obtaining the corresponding barcode template and number of sheets according to the order barcode includes: Uploading the order barcode information to the barcode automatic printing system; The barcode automatic printing system obtains the barcode template and number of sheets matching the order barcode information from the manufacturing execution system according to the order barcode information.

3. The method according to claim 1, characterized in that The step of performing barcode eligibility detection on the image information of each barcode according to a preset barcode image detection model includes: performing image preprocessing on the image information of the barcode; Extracting spatial feature information from the image information after image preprocessing through a pre-trained convolutional neural network model, wherein the barcode image detection model is the convolutional neural network model; Whether the barcode is qualified is determined based on the spatial feature information.

4. The method according to claim 3, characterized in that The construction of the convolutional neural network model includes: Collecting image samples of qualified barcodes and unqualified barcodes, labeling each image sample as qualified or unqualified, and performing data enhancement processing on the image samples, wherein the data enhancement processing includes: random rotation, random flipping, and random scaling; Dividing the image samples into a training set, a validation set, and a test set, and performing image normalization preprocessing on the image samples; Constructing a convolutional neural network model, wherein the convolutional neural network model includes an input layer, at least one set of network structures, a fully connected layer, and a regression layer in sequence, and the network structure includes a convolution layer, an activation layer, and a pooling layer; The training set is input into the constructed convolutional neural network model for training, and the trained convolutional neural network model is evaluated using the validation set and the test set.

5. The method according to claim 4, characterized in that The step of judging whether the barcode is qualified according to the spatial feature information includes: Performing linear regression prediction on the spatial feature information of the barcode to output a qualified probability value corresponding to the barcode; If the qualified probability value is greater than the preset qualified threshold value, the barcode qualification test result of the barcode is determined to be qualified.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Obtaining operating parameters that affect dust deposition on the packaging box surface and inputting the operating parameters into a simulation tool, the operating parameters including wind speed, ambient humidity, ambient temperature, dust concentration, dust particle size, dust accumulation time, and the material of the packaging box surface; Based on the force equation of dust on the surface of the packaging box, a simulation model of the dust amount on the surface of the packaging box is constructed by the simulation tool and the dust amount on the surface of the packaging box is output; If the amount of dust on the surface of the packaging box reaches a preset removal threshold, the surface of the packaging box is subjected to dust removal.

7. The method according to claim 6, characterized in that The force equations of the dust on the surface of the packaging box include: F vdw +F e +F cap +F g sinθ≥F d +F L +F g cosθ+F impact Among them, θ is the tilt angle of the packaging box, F vdw is the van der Waals force, F e is the electrostatic force, F cap is the liquid bridge force, F g sinθ is the vertical component of gravity, F g cosθ is the horizontal component of gravity, F d is the fluid drag, F L is the lift and F impact For elasticity.

8. A barcode printing device for an air conditioner packaging box, characterized in that: The apparatus comprises means for executing the method according to any one of claims 1 to 7 above.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images