Automatic container labeling method and device

Abstract

The present invention discloses a method and device for automatic labeling of containers, the method comprising: obtaining basic information of containers; performing data preprocessing operations according to the basic information of containers to obtain label data and label three-dimensional coordinates; performing importance score calculation operations according to the label data and the label three-dimensional coordinates to obtain label importance scores; performing label position adjustment operations according to the label data, the label three-dimensional coordinates and the label importance scores to obtain label labeling positions; performing label sequence generation operations according to the label labeling positions and the label importance scores to obtain label labeling sequences; performing automatic labeling operations according to the label labeling sequences, the label labeling positions and the label three-dimensional coordinates to label the containers. The method can realize accurate and rapid automatic labeling under complex backgrounds.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic labeling, and in particular to a method and device for automatic labeling of containers. Background Art

[0002] At present, in modern business operations, especially in the fields of logistics distribution, warehouse management and production line automation, there is an increasing demand for labeling containers and packaging boxes. Traditional manual labeling is not only inefficient but also prone to errors. Although existing automation technologies such as methods based on optical scanning and position positioning have improved the speed, they are still unable to cope with objects of complex shapes and dynamically changing scenes. Although RFID technology can achieve non-contact recognition, it has limitations in accurate labeling, especially when labeling irregular objects, and it is difficult to adapt to rapidly changing working environments. In addition, although some studies have proposed using three-dimensional and two-dimensional codes combined with laser scanning technology to improve this situation, they have not completely solved the problem of accurate labeling in complex backgrounds, and have also ignored the impact of label importance on automatic labeling strategies. Therefore, it is particularly important to develop a new generation of automatic labeling methods that can flexibly cope with objects of different shapes, adapt to a variety of working environments, and consider label priority, in order to achieve more efficient and accurate labeling.

[0003] In one existing technology, an automated labeling method based on RFID (radio frequency identification) is widely used in the field of logistics and warehouse management. RFID technology uses radio frequency signals to read the tag information attached to an object through a non-contact automatic identification method, thereby realizing the rapid tracking and management of items. However, although RFID technology has improved the speed and accuracy of data collection, it still has shortcomings in handling complex-shaped items and adaptability in dynamically changing environments. For example, when faced with irregular-shaped goods, RFID tags cannot be accurately placed or read, resulting in information loss or errors. In addition, RFID systems require a specific reader layout to ensure that tags can be effectively read, which poses challenges in situations where space is limited or the environment is changing. Another technology that attempts to solve the above problems is to use three-dimensional QR codes combined with laser scanning for dynamic labeling. This method attempts to improve the accuracy of labeling by three-dimensional modeling of objects, but it performs poorly in situations such as complex backgrounds, poor lighting conditions, and frequent movement of objects. More importantly, these solutions often ignore the differences in importance between different tags and fail to optimize labeling strategies based on the criticality of tags, which limits the flexibility and efficiency of the overall system.

[0004] In summary, the existing technology is not adaptable enough under complex backgrounds and cannot perform accurate and fast automatic labeling. Summary of the invention

[0005] The present invention provides a method and device for automatic labeling of containers, so as to realize accurate and rapid automatic labeling under complex backgrounds.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a method for automatically labeling a container, comprising:

[0007] Get basic container information;

[0008] Perform data preprocessing operations according to the basic information of the container to obtain label data and label three-dimensional coordinates;

[0009] Performing an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score;

[0010] According to the label data, the label three-dimensional coordinates and the label importance score, a label position adjustment operation is performed to obtain a label position;

[0011] According to the labeling positions and the label importance scores, a labeling sequence generation operation is performed to obtain a labeling sequence;

[0012] According to the labeling sequence, the labeling positions and the three-dimensional coordinates of the labels, an automatic labeling operation is performed to label the labels on the container.

[0013] Preferably, in an optional implementation manner, obtaining basic container information includes:

[0014] Through the laser sensor, laser scanning operation is performed to obtain the container point cloud data;

[0015] According to the container point cloud data, data processing operations are performed to obtain basic container information.

[0016] Preferably, in an optional implementation, a data preprocessing operation is performed according to the basic information of the container to obtain label data and label three-dimensional coordinates, including:

[0017] Performing a label data encoding operation according to the basic information of the container to obtain label data;

[0018] Constructing a three-dimensional label space description model according to the basic information of the container and the label data to obtain a theoretical three-dimensional label space description model;

[0019] According to the theoretical label three-dimensional space description model and the basic information of the container, a coordinate difference calculation operation is performed to obtain an actual label three-dimensional space description model;

[0020] A coordinate extraction operation is performed according to the actual label three-dimensional space description model to obtain the label three-dimensional coordinates.

[0021] Preferably, in an optional implementation, performing an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain the tag importance score includes:

[0022] Performing importance feature mapping calculation according to the tag data and the tag three-dimensional coordinates to obtain an importance feature value;

[0023] Calculate the importance score according to the importance feature value to obtain the tag importance score;

[0024] The calculation formula for calculating the importance feature map is as follows:

[0025]

[0026] The calculation formula for calculating the importance score is as follows:

[0027]

[0028] in, Indicates The importance feature value, Indicates The importance score of the tags, Indicates the total number of tags, Indicates the number of tag types, Indicates Tags in The coefficients under the label type, Indicates Tags in The importance score of the tag type when there are tag types, Indicates Tags in importance feature The coefficients below, Indicates Tags in The original coordinate values ​​on the coordinate axis.

[0029] Preferably, in an optional implementation, performing a label position adjustment operation according to the label data, the label three-dimensional coordinates and the label importance score to obtain the label position includes:

[0030] The calculation formula for the label position adjustment operation is as follows:

[0031]

[0032] in, Indicates Tags in The adjusted coordinate values ​​on the coordinate axis are Indicates Tags in The original coordinate values ​​on the coordinate axis, Indicates the label order adjustment value. Indicates the adjustment range.

[0033] Preferably, in an optional implementation, a labeling sequence generation operation is performed according to the labeling position and the label importance score to obtain the labeling sequence, including:

[0034] According to the label position and the label importance score, a priority generation operation is performed to obtain the label priority;

[0035] Calculate the labeling sequence according to the labeling position and the labeling priority to obtain the labeling sequence;

[0036] The calculation formula for the label sequence calculation is as follows:

[0037]

[0038] in, Indicates The order of labeling of labels, Indicates The importance score of the tags, Indicates The weight coefficient of each coordinate axis, Indicates Tags in The coordinate values ​​on the coordinate axis, is the total number of tags, Indicates Tags in The coordinate values ​​on the coordinate axis.

[0039] Preferably, in an optional embodiment, according to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, an automatic labeling operation is performed to label the label on the container, including:

[0040] According to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, a data conversion operation is performed to obtain a control signal of the automatic labeling equipment;

[0041] According to the automatic labeling equipment control signal, it is input to the automatic labeling equipment, and the automatic labeling equipment performs the labeling operation and feeds back the labeling result to the label management system.

[0042] In a second aspect, the present invention provides an automatic container labeling device, comprising:

[0043] Data acquisition module, used to obtain basic information of containers;

[0044] A data encoding module, used to perform data preprocessing operations according to the basic information of the container to obtain label data and label three-dimensional coordinates;

[0045] An importance score calculation module, used to perform an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score;

[0046] A label position generating module, used to perform a label position adjustment operation according to the label data, the label three-dimensional coordinates and the label importance score to obtain a label position;

[0047] A labeling sequence generation module, used to perform a labeling sequence generation operation according to the labeling positions and the label importance scores to obtain a labeling sequence;

[0048] The automatic labeling module is used to perform automatic labeling operations according to the labeling sequence, the labeling positions and the three-dimensional coordinates of the labels, and label the containers.

[0049] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned methods for automatic labeling of containers when executing the computer program.

[0050] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned container automatic labeling methods.

[0051] Compared with the prior art, the present invention has the following beneficial effects: first, a laser scanning operation is performed by a laser sensor to obtain the container point cloud data, and then the basic information of the container is obtained through data processing operations. Next, the label data is encoded and the label three-dimensional space description model is constructed according to the basic information of the container to obtain the actual label three-dimensional coordinates. Subsequently, the importance of each label is quantitatively evaluated using the importance feature mapping calculation and the importance score calculation formula. Based on the importance score of the label, the system will adjust the label position to ensure that the key information is preferentially and accurately affixed. In addition, through the label sequence generation operation, the system can generate the optimal label sequence according to the importance and position of the label, thereby improving the overall labeling efficiency. Finally, according to the generated label sequence, label position and label three-dimensional coordinates, the automatic labeling equipment accurately affixes the label to the container. This comprehensive solution not only overcomes the problems of low efficiency and error-proneness of traditional manual labeling methods, but also solves the limitations of existing automation technologies in processing complex-shaped objects and dynamically changing scenes, especially the deficiencies in RFID technology and three-dimensional and two-dimensional code combined with laser scanning technology. By introducing the concept of label importance, the present invention can optimize the labeling strategy according to the criticality of different labels, ensuring that high-priority information is processed in a timely manner, thereby improving the accuracy and efficiency of labeling and enhancing the flexibility and adaptability of the system.

[0052] In summary, the present invention provides a method and device for automatic labeling of containers, which obtains label data and three-dimensional coordinates of labels by acquiring basic information of containers and performing data preprocessing operations, and then calculates the importance score of the labels based on these data, and adjusts the label position and the label generation order accordingly, and finally performs automatic labeling operations. This comprehensive solution not only overcomes the problems of low efficiency and error-proneness of traditional manual labeling methods, but also solves the limitations of existing automation technologies such as methods based on optical scanning and positioning when dealing with complex-shaped objects and dynamically changing scenes, especially the deficiencies in RFID technology and three-dimensional and two-dimensional code combined with laser scanning technology. By introducing the concept of label importance, the present invention can optimize labeling strategies according to the criticality of different labels, ensuring that high-priority information is processed in a timely manner, thereby improving the accuracy and efficiency of labeling and enhancing the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the process of the automatic container labeling method provided by the first embodiment of the present invention;

[0054] Figure 2 It is a schematic structural diagram of an automatic container labeling device provided by a second embodiment of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] Reference Figure 1 The first embodiment of the present invention provides a method for automatically labeling a container, comprising the following steps:

[0057] S11, obtaining basic information of the container;

[0058] S12, performing data preprocessing operations according to the basic information of the container to obtain label data and label three-dimensional coordinates;

[0059] S13, performing an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score;

[0060] S14, performing a label position adjustment operation according to the label data, the label three-dimensional coordinates and the label importance score to obtain a label position;

[0061] S15, performing a labeling sequence generation operation according to the labeling positions and the label importance scores to obtain a labeling sequence;

[0062] S16, performing an automatic labeling operation according to the label labeling sequence, the label labeling position and the label three-dimensional coordinates, and labeling the label onto the container.

[0063] It should be noted that the present invention provides a method and device for automatic labeling of containers, which obtains label data and three-dimensional coordinates of labels by acquiring basic information of containers and performing data preprocessing operations. Then, the importance score of each label is calculated based on these data, and the label position of the label is adjusted and the optimal label order is generated accordingly. Finally, the automatic labeling operation is performed according to the generated label order, label position and three-dimensional coordinates, and the labels are accurately affixed to the container. The method first uses a laser sensor to perform a laser scanning operation to obtain container point cloud data, and then obtains basic information of the container through data processing; then, based on the basic information of the container, the label data is encoded and the three-dimensional space description model of the label is constructed to obtain the actual three-dimensional coordinates of the label; then, the importance of each label is quantitatively evaluated through importance feature mapping calculation and importance score calculation formula; based on the importance score of the label, the system adjusts the label position of the label to ensure that the key information is affixed first and accurately, and generates the optimal label order according to the importance and position of the label through the label order generation operation, thereby improving the overall labeling efficiency. This comprehensive solution not only overcomes the inefficiency and error-proneness of traditional manual labeling, but also solves the limitations of existing automation technologies such as methods based on optical scanning and location positioning in dealing with complex-shaped objects and dynamically changing scenes, especially the deficiencies in RFID technology and three-dimensional and two-dimensional code combined with laser scanning technology. By introducing the concept of label importance, the present invention can optimize labeling strategies according to the criticality of different labels, ensuring that high-priority information is processed in a timely manner, thereby improving the accuracy and efficiency of labeling and enhancing the flexibility and adaptability of the system.

[0064] In step S11, basic container information is obtained, including:

[0065] Through the laser sensor, laser scanning operation is performed to obtain the container point cloud data;

[0066] According to the container point cloud data, data processing operations are performed to obtain basic container information.

[0067] It should be noted that in step S11, the specific implementation process of obtaining the basic information of the container is as follows: First, the laser scanning operation is performed on the container through the laser sensor. The laser sensor emits a laser beam and receives the reflected signal to generate point cloud data on the surface of the container. Point cloud data is a set of a series of three-dimensional coordinate points, each point representing a position on the surface of the container. These point cloud data can accurately describe the shape, size and surface features of the container. Next, the acquired point cloud data is processed. The data processing operation includes steps such as filtering, denoising, and segmentation of the point cloud data to ensure the accuracy and integrity of the data. Filtering can remove noise points to make the point cloud data clearer; denoising further removes abnormal points caused by environmental interference or sensor errors; segmentation is to classify the point cloud data according to different features (such as planes and surfaces) for subsequent processing. After these processing steps, the basic information of the container is finally obtained, including the geometric shape, size, surface features, etc. of the container. In the specific example, there is a standard 20-foot container, and the laser sensor scans it from multiple angles to generate a data set of millions of points. By filtering and denoising these point cloud data, abnormal points caused by changes in ambient light or errors in the sensor itself can be removed. Then, the algorithm is used to segment the point cloud data and identify the planes and edges of the container. The RANSAC (Random Sampling Consensus) algorithm can be used to detect the main planes of the container, and the length, width, and height of the container can be determined by plane fitting. In addition, the raised parts and other special structures on the container, such as door handles and locks, can also be identified by methods such as surface fitting. In short, in step S11, the point cloud data of the container is obtained by the laser sensor, and after a series of data processing operations, the basic information of the container is finally obtained, providing accurate data support for subsequent data preprocessing and labeling operations. This technical solution based on laser scanning can effectively deal with containers with complex shapes and ensure the accuracy and reliability of the subsequent automated labeling process.

[0068] It is worth noting that in order to improve the efficiency and accuracy of data processing, the present invention adopts advanced point cloud processing technology, such as deep learning-based methods, to automatically identify and classify different parts of the container. This method can extract the key features of the container more quickly and reduce the need for manual intervention.

[0069] In step S12, data preprocessing is performed according to the basic information of the container to obtain label data and label three-dimensional coordinates, including:

[0070] Performing a label data encoding operation according to the basic information of the container to obtain label data;

[0071] Constructing a three-dimensional label space description model according to the basic information of the container and the label data to obtain a theoretical three-dimensional label space description model;

[0072] According to the theoretical label three-dimensional space description model and the basic information of the container, a coordinate difference calculation operation is performed to obtain an actual label three-dimensional space description model;

[0073] A coordinate extraction operation is performed according to the actual label three-dimensional space description model to obtain the label three-dimensional coordinates.

[0074] It should be noted that in step S12, the specific implementation process of performing data preprocessing operations according to the basic information of the container to obtain the label data and the three-dimensional coordinates of the label is as follows: First, based on the basic information of the container obtained from step S11, a label data encoding operation is performed. The label data encoding operation includes determining the content, type and related attribute information of each label. This information can be text, barcode, QR code or other forms of identifiers. Through the encoding operation, the system can convert the label content into a machine-readable form for subsequent processing. Next, based on the basic information of the container and the label data, a three-dimensional space description model of the label is constructed. This process involves placing the label at a theoretical position on the surface of the container and generating a three-dimensional model to describe the relative position relationship between the label and the container. The model takes into account the geometric shape and size of the container to ensure that the label can be accurately attached to the specified position. For example, if the container is a standard cuboid, the system will determine the best attachment position of the label based on its length, width and height. Then, based on the theoretical label three-dimensional space description model and the basic information of the container, a coordinate difference calculation operation is performed. The purpose of this operation is to correct the difference between the theoretical model and the actual container surface. Due to manufacturing errors or uneven surfaces in actual containers, the theoretical model deviates from the actual situation. By calculating the coordinate difference, the system can adjust the theoretical position of the label to make it closer to the actual position where it should be attached. This step involves further analysis of the point cloud data to identify and correct any slight deviations. Finally, based on the actual label three-dimensional space description model, a coordinate extraction operation is performed to obtain the three-dimensional coordinates of the label. The coordinate extraction operation is to extract the exact position coordinates of each label from the adjusted three-dimensional model. These coordinates are the actual attachment positions of the labels on the surface of the container, which are used for subsequent label position adjustment and automatic labeling operations. Specifically, the extracted coordinates include the X, Y, and Z coordinate values ​​of the center point of each label, which will be used to guide the automatic labeling equipment for precise positioning.

[0075] It is worth noting that the present invention uses computer vision technology and image processing methods to further optimize the coordinate extraction process and ensure the high accuracy of the label coordinates. In step S12, the label data and the three-dimensional coordinates of the label are finally obtained by encoding the basic information of the container, building a three-dimensional space description model, calculating the coordinate difference, and extracting the coordinates. These data provide the necessary basic information for the subsequent importance score calculation, label position adjustment, and automatic labeling operation, ensuring the accuracy and reliability of the entire automatic labeling process.

[0076] In step S13, an importance score calculation operation is performed according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score, including:

[0077] Performing importance feature mapping calculation according to the tag data and the tag three-dimensional coordinates to obtain an importance feature value;

[0078] Calculate the importance score according to the importance feature value to obtain the tag importance score;

[0079] The calculation formula for calculating the importance feature map is as follows:

[0080]

[0081] The calculation formula for calculating the importance score is as follows:

[0082]

[0083] in, Indicates The importance feature value, Indicates The importance score of the tags, Indicates the total number of tags, Indicates the number of tag types, Indicates Tags in The coefficients under the label type, Indicates Tags in The importance score of the tag type when there are tag types, Indicates Tags in importance feature The coefficients below, Indicates Tags in The original coordinate values ​​on the coordinate axis.

[0084] It should be noted that in step S13, the importance score calculation operation is performed according to the tag data and the three-dimensional coordinates of the tag, and the specific implementation process of obtaining the tag importance score is as follows: First, the importance characteristic value of each tag is determined by importance feature mapping calculation. The importance characteristic value is calculated based on the three-dimensional coordinates of the tag and its attribute information, and is used to evaluate the importance of each tag under specific characteristics. This step is based on the three-dimensional coordinates of the tag and its attribute information such as content and type. Exemplarily, the importance feature is the location significance of the label (such as whether it is located in a conspicuous position on the container). Of course, depending on the actual application and user needs, the importance feature can be the importance of the content of the label (such as whether it contains information related to transportation safety) and the type of label (such as barcode, QR code or text), and the present invention is not limited to this. Indicates Tags in importance feature The coefficient under this factor reflects the contribution of the label to a specific importance feature. For example, is the positional prominence, then labels located in prominent locations on containers will have a higher value.

[0085] It is worth noting that the importance score of each tag is calculated using the importance score calculation formula based on the importance feature value. This score comprehensively considers the type of tag and its importance under different types. Indicates Tags in The coefficient under each label type reflects the importance of the label for a specific type. For example, dangerous goods labels will have a higher value. Indicates Tags in The importance score of each label type is pre-set based on the importance of the label type itself and the application requirements. The purpose of importance feature map calculation and importance score calculation is to quantify the relative importance of each label in the entire labeling process. The final data is the importance score of each label. , which is a value that combines the prominence of the label position, the importance of the content, and the type of label. These scores help the system determine the order and optimal position of the labels, ensuring that key information is processed first and accurately. For example, a label containing a hazardous material logo requires a higher importance score because it involves the safety of the goods; while an ordinary packing list label will have a lower importance score.

[0086] In step S14, a label position adjustment operation is performed according to the label data, the label three-dimensional coordinates and the label importance score to obtain the label position, including:

[0087] The calculation formula for the label position adjustment operation is as follows:

[0088]

[0089] in, Indicates Tags in The adjusted coordinate values ​​on the coordinate axis are Indicates Tags in The original coordinate values ​​on the coordinate axis, Indicates the label order adjustment value. Indicates the adjustment range.

[0090] It should be noted that, based on the label importance scores obtained from step S13, the system will adjust the initial label positions of the labels according to these scores. The purpose of the adjustment is to ensure that labels with high importance can be attached to the container preferentially and accurately. Through the label position adjustment operation formula, the system can dynamically adjust the label position of each label according to the importance score of each label. For example, for labels with high importance scores (such as dangerous goods labels), the system will adjust their label positions to more conspicuous positions for quick identification and processing. For labels with low importance scores (such as ordinary packing lists), the system will place them in relatively less conspicuous but still reasonable positions. In addition, the label position adjustment also needs to consider the relationship between the labels and the actual layout of the container surface. For example, if multiple labels need to be attached to the same area, the system will optimize their relative positions based on the importance scores and other constraints (such as label size, shape, etc.) to avoid overlap or occlusion.

[0091] It is worth mentioning that Indicates Tags in The coordinate value adjusted on the coordinate axis is the final position after adjustment and is used to guide the automatic labeling equipment to attach the label to the container. Indicates Tags in The original coordinate value on the axis, which is the initial position of the label before any adjustment. Indicates the label order adjustment value, which reflects the priority of the label in the label order. High-importance labels will have higher values ​​to ensure they are processed first. Indicates the adjustment amplitude, this value determines the degree of label position adjustment. Values ​​result in larger position adjustments, smaller Smaller values ​​result in smaller position adjustments.

[0092] In step S15, a labeling sequence generation operation is performed according to the labeling position and the label importance score to obtain the labeling sequence, including:

[0093] According to the label position and the label importance score, a priority generation operation is performed to obtain the label priority;

[0094] Calculate the labeling sequence according to the labeling position and the labeling priority to obtain the labeling sequence;

[0095] The calculation formula for the label sequence calculation is as follows:

[0096]

[0097] in, Indicates The order of labeling of labels, Indicates The importance score of the tags, Indicates The weight coefficient of each coordinate axis, Indicates Tags in The coordinate values ​​on the coordinate axis, is the total number of tags, Indicates Tags in The coordinate values ​​on the coordinate axis.

[0098] It should be noted that Indicates The labeling order of the labels. This value determines the order of the labels in the actual labeling process. The larger the value, the higher the priority. Indicates The importance score of each tag is calculated by the importance feature map and the importance score in step S13. Indicates The weight coefficients of the coordinate axes reflect the relative importance of different coordinate axes (X, Y, Z) in the labeling order calculation. For example, if you want a more prominent position in a certain direction to have a higher priority, you can set a larger weight coefficient in that direction. Indicates Tags in The coordinate value on the coordinate axis is the specific position of the label on the surface of the container. is the total number of tags, Indicates Tags in The coordinate values ​​on the coordinate axis.

[0099] It is worth noting that in step S15, a labeling sequence generation operation is performed according to the labeling position and the label importance score to obtain the labeling sequence. First, based on the labeling position obtained from step S14 and the label importance score calculated in step S13, the system performs a priority generation operation. This step is to determine the priority of each label in the labeling process. The generation of the priority takes into account the importance score of the label and its specific position on the container. For example, labels with high importance scores will be given higher priorities to ensure that they can be processed first. Through the calculation formula for labeling sequence calculation, the system can comprehensively consider the importance score of the label and its position in three-dimensional space to determine the optimal labeling sequence. Specifically, the numerator in the formula reflects the weighted influence of the importance score of the label and its position, while the denominator is the sum of the weighted importance scores of all labels. In this way, labels with higher importance scores and labels located in key positions will obtain higher labeling sequence values, thereby ensuring that they can be processed first. In addition, in practical applications, other factors need to be considered, such as the relationship between labels, the actual layout of the container surface, etc. For example, if multiple high-importance labels need to be affixed to the same area, the system will further optimize their relative order to avoid overlap or occlusion. At the same time, the system can also set some constraints, such as minimum spacing requirements, to ensure that there is enough space between labels for easy identification and reading. Through a comprehensive analysis of the labeling position and importance scores, the system is able to generate the optimal labeling order to ensure that key information is processed first and accurately. This dynamic adjustment mechanism based on importance and position not only improves the efficiency of labeling, but also enhances the flexibility and adaptability of the system, making the entire automatic labeling process more efficient and reliable. Next, based on the labeling position and the generated labeling priority, the system will perform a labeling order calculation to determine the final labeling order.

[0100] In step S16, according to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, an automatic labeling operation is performed to label the label on the container, including:

[0101] According to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, a data conversion operation is performed to obtain a control signal of the automatic labeling equipment;

[0102] According to the automatic labeling equipment control signal, it is input to the automatic labeling equipment, and the automatic labeling equipment performs the labeling operation and feeds back the labeling result to the label management system.

[0103] It should be noted that the system will perform data conversion operations based on the labeling order, labeling position and three-dimensional coordinates of the labels obtained from step S15. This step is to convert the calculated labeling information into control signals that the automatic labeling device can understand and execute. These control signals include detailed instructions such as the specific position of the label (X, Y, Z coordinates), rotation angle, labeling action, etc. In this way, the system ensures that the automatic labeling device can accurately locate the position where each label should be attached. Next, these control signals will be input into the automatic labeling device. The automatic labeling device can be a robot arm or other automated mechanical device, which is equipped with a high-precision positioning system and labeling tools. After receiving the control signal, the automatic labeling device will attach the labels to the container in the specified order and position. In order to ensure the accuracy of labeling, the automatic labeling device will also be equipped with a visual system and a sensor to correct the position deviation in real time to ensure that each label can be accurately placed at the predetermined position. During the labeling process, the automatic labeling device will perform a series of actions, such as moving to a specified position, adjusting the angle, and releasing the label. Once the label is successfully attached, the equipment will perform a confirmation check to ensure that the label is firmly fixed to the surface of the container and is not offset or damaged. If any problems are detected, the system will trigger an alarm and re-execute the labeling operation. Finally, after the automatic labeling equipment completes the labeling, it will feedback the labeling results to the label management system. This feedback mechanism can include a variety of information, such as whether the labeling is successful, the actual location of the label, the labeling timestamp, etc. This information is very important for subsequent quality control and tracking, and can help managers monitor the entire labeling process and respond to problems in a timely manner.

[0104] In summary, the present invention provides a method and device for automatic labeling of containers. The method comprises the following steps: first, a laser sensor is used to scan the container to obtain point cloud data, and after filtering, denoising and segmentation, basic information of the container is obtained, including geometric shape, size and surface features. Then, based on these basic information, label data encoding and three-dimensional space description model construction are performed to determine the three-dimensional coordinates of the label. Then, according to the label data and three-dimensional coordinates, the importance score of each label is calculated, and this process involves importance feature mapping and importance score calculation. Next, the system adjusts the label position according to the importance score of the label and generates the optimal label order. Finally, according to the generated label order, label position and three-dimensional coordinates, the control signal is input into the automatic labeling device to perform accurate automatic labeling operations, and the results are fed back to the label management system. The whole process ensures that the labels can be attached to the container according to their importance priority and accuracy, improves the efficiency and accuracy of labeling, and enhances the flexibility and adaptability of the system. This method not only overcomes the inefficiency and error-proneness of traditional manual labeling, but also solves the limitations of existing automation technology in dealing with complex-shaped objects and dynamically changing scenes.

[0105] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0106] There is a need to automate the labeling management of container locations within a large port. This port will be used to handle a variety of goods, so the labeling and positioning of containers are very demanding to ensure fast and accurate loading and unloading of goods.

[0107] Step 1: Obtain basic information about the container. First, use the laser scanner carried by the drone to scan the containers in the port. Due to the large area of ​​the port, multiple scans are required in different areas. Specifically, the port is divided into several scanning areas, and detailed scans are performed in each area to obtain the precise location and size of the container. The drone automatically performs the scanning task according to the preset flight path and stores the point cloud data in real time.

[0108] Step 2: Data processing operations. The scanned point cloud data is then input into a data processing program. The program first filters and denoises the point cloud data to improve data quality and highlight the characteristics of the container. Then, through 3D reconstruction technology, these data are converted into 3D models of the container. Finally, spatial correction technology is used to align these models with the port's geographic information system (GIS) data to ensure the accuracy of the model.

[0109] Step 3: Tag data and 3D coordinate generation. Based on the 3D model of the container, the tag data encoding operation is performed to generate a unique identifier for each container. Then, based on the 3D model of the container and the layout of the port, the optimal position of each tag is determined and the 3D coordinates of each tag are calculated.

[0110] Step 4: Importance score calculation. According to the location, content and type of each tag, the importance feature mapping calculation is performed to obtain the importance feature value of each tag. Then, based on these feature values ​​and the preset weights, the importance score of each tag is calculated.

[0111] Step 5: Label position and order generation. According to the label importance score and three-dimensional coordinates, the label position adjustment operation is performed to ensure that the label of key information is attached to a prominent position first. Then, according to the label importance score and position, the optimal label order is generated.

[0112] Step 6: Execute automatic labeling operation. According to the generated labeling sequence and position, the automatic labeling robot is controlled to perform the labeling task. The robot accurately attaches each label to the predetermined position according to the control signal. After labeling is completed, the robot scans the label and container to confirm the correctness and completeness of the label, and feeds the result back to the port management system.

[0113] Reference Figure 2 The second embodiment of the present invention provides an automatic container labeling device, comprising:

[0114] Data acquisition module, used to obtain basic information of containers;

[0115] A data encoding module, used to perform data preprocessing operations according to the basic information of the container to obtain label data and label three-dimensional coordinates;

[0116] An importance score calculation module, used to perform an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score;

[0117] A label position generating module, used to perform a label position adjustment operation according to the label data, the label three-dimensional coordinates and the label importance score to obtain a label position;

[0118] A labeling sequence generation module, used to perform a labeling sequence generation operation according to the labeling positions and the label importance scores to obtain a labeling sequence;

[0119] The automatic labeling module is used to perform automatic labeling operations according to the labeling sequence, the labeling positions and the three-dimensional coordinates of the labels, and label the containers.

[0120] It should be noted that the automatic container labeling device provided in the embodiment of the present invention is used to execute all the process steps of the automatic container labeling method in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated.

[0121] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a container automatic labeling program. When the processor executes the computer program, the steps in the above-mentioned container automatic labeling method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as the importance score calculation module.

[0122] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0123] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0124] The processor may be a central processing unit (CPU), 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. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0125] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0126] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0127] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0128] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for automatically labeling a container, characterized in that: Executed by a computer, including: Get basic container information; Perform data preprocessing operations according to the basic information of the container to obtain label data and label three-dimensional coordinates; Performing an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score; According to the label data, the label three-dimensional coordinates and the label importance score, a label position adjustment operation is performed to obtain a label position; According to the labeling positions and the label importance scores, a labeling sequence generation operation is performed to obtain a labeling sequence; According to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, an automatic labeling operation is performed to label the container; Among them, obtaining basic container information includes: Through the laser sensor, laser scanning operation is performed to obtain the container point cloud data; Performing data processing operations according to the container point cloud data to obtain basic information of the container; According to the basic information of the container, data preprocessing operations are performed to obtain label data and label three-dimensional coordinates, including: Performing a label data encoding operation according to the basic information of the container to obtain label data; Constructing a three-dimensional label space description model according to the basic information of the container and the label data to obtain a theoretical three-dimensional label space description model; According to the theoretical label three-dimensional space description model and the basic information of the container, a coordinate difference calculation operation is performed to obtain an actual label three-dimensional space description model; Performing a coordinate extraction operation according to the actual label three-dimensional space description model to obtain the label three-dimensional coordinates; The importance score calculation operation is performed according to the tag data and the tag three-dimensional coordinates to obtain the tag importance score, including: Performing importance feature mapping calculation according to the tag data and the tag three-dimensional coordinates to obtain an importance feature value; Calculate the importance score according to the importance feature value to obtain the tag importance score; The calculation formula for calculating the importance feature map is as follows: The calculation formula for calculating the importance score is as follows: in, Indicates The importance feature value, Indicates The importance score of the tags, Indicates the total number of tags, Indicates the number of tag types, Indicates Tags in The coefficients under the label type, Indicates Tags in The importance score of the tag type when there are tag types, Indicates Tags in importance feature The coefficients below, Indicates Tags in The original coordinate values ​​on the coordinate axis.

2. The automatic container labeling method according to claim 1, characterized in that: According to the label data, the label three-dimensional coordinates and the label importance score, a label position adjustment operation is performed to obtain the label position, including: The calculation formula for the label position adjustment operation is as follows: in, Indicates Tags in The adjusted coordinate values ​​on the coordinate axis are Indicates Tags in The original coordinate values ​​on the coordinate axis, Indicates the label order adjustment value. Indicates the adjustment range.

3. The automatic container labeling method according to claim 1, characterized in that: According to the labeling position and the label importance score, a labeling sequence generation operation is performed to obtain a labeling sequence, including: According to the label position and the label importance score, a priority generation operation is performed to obtain the label priority; Calculate the labeling sequence according to the labeling position and the labeling priority to obtain the labeling sequence; The calculation formula for the label sequence calculation is as follows: in, Indicates The order of labeling of labels, Indicates The importance score of the tags, Indicates The weight coefficient of the coordinate axis, Indicates Tags in The coordinate values ​​on the coordinate axis, is the total number of tags, Indicates Tags in The coordinate values ​​on the coordinate axis.

4. The automatic container labeling method according to claim 1, characterized in that: According to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, an automatic labeling operation is performed to label the label on the container, including: According to the labeling sequence, the labeling position and the three-dimensional coordinates of the label, a data conversion operation is performed to obtain a control signal of the automatic labeling equipment; According to the automatic labeling equipment control signal, it is input to the automatic labeling equipment, and the automatic labeling equipment performs the labeling operation and feeds back the labeling result to the label management system.

5. An automatic container labeling device, characterized in that: A method for automatically labeling a container according to any one of claims 1 to 4, comprising: Data acquisition module, used to obtain basic information of containers; A data encoding module, used to perform data preprocessing operations according to the basic information of the container to obtain label data and label three-dimensional coordinates; An importance score calculation module, used to perform an importance score calculation operation according to the tag data and the tag three-dimensional coordinates to obtain a tag importance score; A label position generating module, used to perform a label position adjustment operation according to the label data, the label three-dimensional coordinates and the label importance score to obtain a label position; A labeling sequence generation module, used to perform a labeling sequence generation operation according to the labeling positions and the label importance scores to obtain a labeling sequence; The automatic labeling module is used to perform automatic labeling operations according to the labeling sequence, the labeling positions and the three-dimensional coordinates of the labels, and label the containers.

6. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the automatic container labeling method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the automatic container labeling method according to any one of claims 1 to 4.

Images