Method and apparatus for inspecting package of hosted object, device, medium, and program product
By acquiring images of the consigned items and using image recognition technology and deep learning models to automatically determine whether the packaging meets the standards, the problem of low efficiency and false detection in manual sampling inspection is solved, achieving high efficiency, accuracy and consistency in the inspection of consigned item packaging.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SF TECH CO LTD
- Filing Date
- 2025-10-24
- Publication Date
- 2026-07-02
Smart Images
Figure CN2025129828_02072026_PF_FP_ABST
Abstract
Description
Testing methods, apparatus, equipment, media and procedures for consigned goods packaging
[0001] Related applications
[0002] This application claims priority to Chinese patent application filed on December 24, 2024, application number 2024119352006, entitled "Detection Method, Apparatus, Equipment, Media and Procedure Product for Consigned Goods Packaging", the entire contents of which are incorporated herein by reference. Technical Field
[0003] This application relates to the field of image recognition technology, and in particular to a method, apparatus, equipment, medium, and program product for detecting consigned goods packaging. Background Technology
[0004] Currently, for consigned items, large express delivery companies typically require couriers to take photos of the consigned items and their inner and outer packaging during the collection process, and to manually check whether the packaging process complies with regulations through random sampling. However, the inventors realized that manual sampling is inefficient, costly, and easily affected by subjective factors, lacking consistency. Furthermore, due to the diversity of packaging materials, sizes, and shapes, as well as obstructions and deformations in complex environments, accurate detection is often difficult, easily leading to missed or false detections. Summary of the Invention
[0005] According to various embodiments of this application, a method, apparatus, device, medium, and procedure for detecting consignment packaging are provided.
[0006] A method for detecting consignment packaging includes:
[0007] Acquire the image to be detected corresponding to the target consigned item, the image to be detected including the item image, the outer packaging image and the inner packaging image;
[0008] The image of the item, the image of the outer packaging, and the image of the inner packaging are identified to obtain the first packaging information corresponding to the target consigned item; wherein, the first packaging information is used to identify the actual packaging information used for the target consigned item;
[0009] Determine the type of the target consignment, and determine the second packaging information corresponding to the type of the target consignment; wherein the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment; and
[0010] The first packaging information and the second packaging information are compared, and the packaging inspection result of the target consignment is determined based on the comparison result.
[0011] A detection device for consigned goods packaging, comprising:
[0012] The acquisition module is used to acquire the image to be detected corresponding to the target consigned item, the image to be detected including the item image, the outer packaging image and the inner packaging image;
[0013] The identification module is used to identify the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain first packaging information corresponding to the target consignment; wherein, the first packaging information is used to identify the actual packaging information used for the target consignment;
[0014] The determining module is used to determine the type of the target consignment and to determine second packaging information corresponding to the type of the target consignment; wherein the second packaging information is used to identify packaging standard information corresponding to the type of the target consignment; and
[0015] The comparison module is used to compare the first packaging information and the second packaging information, and determine the packaging inspection result of the target consignment based on the comparison result.
[0016] A computer device includes a memory and one or more processors, the memory storing computer-readable instructions that, when executed by the processors, implement the steps of the method for detecting consigned packages provided in any embodiment of this application.
[0017] One or more non-volatile computer-readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to implement the steps of the method for detecting consignment packaging provided in any embodiment of this application.
[0018] A computer program product includes computer-readable instructions that, when executed by a processor, implement the steps of the method for detecting consignment packaging provided in any embodiment of this application.
[0019] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the disclosed drawings without creative effort.
[0021] Figure 1 is a flowchart illustrating a method for detecting consignment packaging according to one or more embodiments.
[0022] Figure 2 is a flowchart illustrating a detection method for another consignment package according to one or more embodiments.
[0023] Figure 3 is a flowchart illustrating a detection method for another consignment package according to one or more embodiments.
[0024] Figure 4 is a block diagram of a detection device for consigned goods packaging according to one or more embodiments.
[0025] Figure 5 is a block diagram of a computer device according to one or more embodiments. Detailed Implementation
[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0027] With the rapid development of e-commerce, consumers' demand for valuable and fragile items is increasing, placing higher demands on express delivery companies. Compared to ordinary goods, fragile and high-value items (such as electronic products, high-end liquor, and fresh food) require particularly stringent packaging standards. Inadequate packaging not only easily leads to damage during transportation but can also trigger disputes and claims between merchants and consumers, resulting in significant economic losses for e-commerce platforms and express delivery companies.
[0028] Currently, for high-value, fragile items, large express delivery companies typically require couriers to photograph and document the items and their inner and outer packaging during the pickup process, and to manually check the compliance of the packaging process through random sampling. However, manual sampling is inefficient, costly, and easily influenced by subjective factors, lacking consistency. Meanwhile, although traditional computer vision and rule-based detection methods are used, they often struggle to accurately detect items due to the diversity of packaging materials, sizes, and shapes, as well as occlusion and deformation in complex scenarios, easily leading to missed or false detections.
[0029] In view of this, the technical solution of the present invention obtains first packaging information by acquiring and identifying images of the item, outer packaging, and inner packaging of the target consignment; then determines second packaging information according to the type of consignment, and compares the first packaging information and the second packaging information to obtain the packaging inspection result, thereby improving the efficiency and accuracy of packaging quality control.
[0030] According to an embodiment of the present invention, an embodiment of a method for detecting consigned packages is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0031] This embodiment provides a method for detecting consignment packaging, which can be used in computer equipment such as desktop computers and laptops. Figure 1 is a flowchart of the method for detecting consignment packaging according to an embodiment of the present invention. As shown in Figure 1, the process includes the following steps:
[0032] Step S101: Obtain the image to be detected corresponding to the target consignment. The image to be detected includes the image of the item, the image of the outer packaging, and the image of the inner packaging.
[0033] The target shipment refers to items requiring packaging inspection, or items to be mailed or transported. The image to be inspected refers to an image obtained through photography or scanning that includes the target shipment and its packaging. The image to be inspected includes images of the item, outer packaging, and inner packaging under the same waybill number. The item image shows the appearance of the target shipment itself, including its shape, size, color, and surface features. The outer packaging image shows the outer packaging of the shipment after it has been packaged (e.g., cardboard box, plastic bag, wooden crate). The inner packaging image shows the internal packaging layers of the shipment (e.g., foam, bubble wrap, plastic bag, styrofoam). Specifically, initial images of the target shipment and its packaging can be obtained using photographic equipment (e.g., camera) or scanners. During the actual pickup process, the item image, outer packaging image, and inner packaging image are collected at different points. First, the pickup personnel take an image of the item upon receipt to record its appearance characteristics; then, after packaging is completed, an image of the inner packaging is taken to confirm its condition; finally, an image of the outer packaging is taken to confirm its condition. The acquisition of these images ensured a comprehensive record of the target shipment and its packaging, providing an accurate basis for subsequent packaging inspection.
[0034] Furthermore, to comprehensively capture all aspects of the shipment, images can be taken from different angles, such as the front, side, and top, while simultaneously recording details of both the outer and inner packaging. Each image recording point can include multiple photos to ensure a comprehensive view of the shipment from multiple perspectives and levels of detail.
[0035] Step S102: Identify the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain the first packaging information corresponding to the target consignment; wherein, the first packaging information is used to identify the actual packaging information used for the target consignment.
[0036] The first packaging information refers to key information related to the actual state of the consigned item and its packaging. This may include the actual state of the consigned item itself (e.g., shape, size, surface features), the actual state of the outer packaging (e.g., material, size, condition, and sealing), and the actual state of the inner packaging (e.g., inner packaging material, adequate protection, and how the consigned item is secured within the packaging). Specifically, useful image features can be extracted from images of the item, outer packaging, and inner packaging, and these extracted features can be comprehensively analyzed to obtain the first packaging information.
[0037] Step S103: Determine the type of the target consignment and determine the second packaging information corresponding to the type of the target consignment; wherein, the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment.
[0038] Secondary packaging information refers to the standardized packaging requirements or specifications pre-defined based on the type of the target shipment. These requirements include the packaging method, materials, and protective measures. Specifically, based on the type of the target shipment, the required packaging requirements or specifications can be determined by consulting the relevant packaging standards, and secondary packaging information corresponding to the type of target shipment can be generated accordingly. This secondary packaging information may include suitable packaging materials for this type of shipment (such as cartons, foam, bubble wrap, cardboard, etc.), specific packaging requirements (such as packaging thickness, number of inner and outer packaging layers, fillers used, etc.), and special protection needs (such as shockproof, moisture-proof, anti-static, leak-proof, etc.), etc., which are not limited here.
[0039] Step S104: Compare the first packaging information and the second packaging information, and determine the packaging inspection result of the target consignment based on the comparison result.
[0040] Packaging inspection results refer to determining whether the packaging of the target shipment meets predetermined packaging requirements or standards by comparing primary and secondary packaging information. Specifically, primary and secondary packaging information is extracted and analyzed, and their differences or similarities are compared using established rules or algorithms. If they match, the packaging meets the specifications, and the inspection result is qualified; if there are differences or it does not meet the standards, the inspection result is unqualified.
[0041] The packaging inspection method for consigned goods provided in this invention acquires an initial image of the target consigned goods and performs comprehensive identification on it. This allows for accurate extraction of relevant information about the consigned goods, outer packaging, and inner packaging, ensuring the comprehensiveness and accuracy of packaging inspection. The method automatically determines the corresponding packaging information based on the type of the target consigned goods, effectively improving the intelligence and adaptability of the inspection. By comparing the actual packaging information with preset packaging standards, it can accurately determine whether the packaging meets the standards, thereby improving the efficiency and accuracy of packaging quality control and reducing the need for manual intervention.
[0042] This embodiment provides a method for detecting consignment packaging, which can be used in computer equipment such as desktop computers and laptops. Figure 2 is a flowchart of the method for detecting consignment packaging according to an embodiment of the present invention. As shown in Figure 2, the process includes the following steps:
[0043] Step S201: Obtain the image to be detected corresponding to the target consignment. The image to be detected includes an image of the item, an image of the outer packaging, and an image of the inner packaging. For details, please refer to step S101 of the embodiment shown in Figure 1, which will not be repeated here.
[0044] Step S202: Identify the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain the first packaging information corresponding to the target consignment; wherein, the first packaging information is used to identify the actual packaging information used for the target consignment.
[0045] Specifically, step S202 includes:
[0046] Step S2021: Extract the first image quality feature from the item image, extract the second image quality feature from the outer packaging image, and extract the third image quality feature from the inner packaging image.
[0047] The first, second, and third image quality features refer to the image quality features extracted from the item image, outer packaging image, and inner packaging image, respectively. These features include one or more of the following image features: sharpness, detail contrast, color saturation, and edge sharpness. They are used to filter out blurry, poorly shot, and copied images, retaining only images with acceptable shooting quality. Specifically, different image analysis algorithms (such as edge detection, texture analysis, and color histogram analysis) can be used to extract corresponding image quality features based on the characteristics of each type of image. Different types of images (such as item images, outer packaging images, and inner packaging images) have different characteristics and shooting requirements, therefore the algorithms used differ. For example, item images focus more on texture analysis and sharpness detection, while outer packaging images focus on edge sharpness and integrity analysis, and inner packaging images focus more on color saturation and detail contrast.
[0048] Step S2022: Based on the first image quality feature, the second image quality feature, and the third image quality feature, determine whether the shooting quality of the item image, the outer packaging image, and the inner packaging image is qualified.
[0049] By analyzing image quality features extracted from product images, outer packaging images, and inner packaging images, the quality of these images is evaluated to determine whether they meet preset standards. Specifically, quantitative analysis is performed based on the first, second, and third image quality features extracted from each product image, outer packaging image, and inner packaging image, such as sharpness, contrast, sharpness, and color saturation. Using set quality thresholds, each image is judged to meet standards such as sharpness, no blurring, no overexposure, and no noise. If the quality features of the product image, outer packaging image, and inner packaging image meet the requirements, the image quality is deemed acceptable.
[0050] Each image type (item image, outer packaging image, inner packaging image) has its own specific quality standards and is evaluated using different detection methods. For example, item images focus on sharpness and detail capture, outer packaging images emphasize integrity and edge sharpness, while inner packaging images require accurate detail contrast and color reproduction.
[0051] Step S2023: If the shooting quality of the item image, outer packaging image and inner packaging image is qualified, the image to be detected is determined as the target packaging image, and the target packaging image is input into the pre-trained packaging image detection model to obtain the first packaging information corresponding to the target packaging image.
[0052] Target packaging images refer to images that have passed quality screening and meet shooting standards, used for subsequent processing or verification. Specifically, the quality of the item image, outer packaging image, and inner packaging image is assessed to ensure that their clarity, contrast, sharpness, and other indicators meet the requirements. If the shooting quality of all three types of images is deemed acceptable, then the image to be inspected corresponding to the target shipment is considered a standard-compliant target packaging image.
[0053] A packaging image detection model is a model pre-trained using deep learning or other machine learning methods to analyze and identify key information in packaging images. Specifically, by inputting a target packaging image into the packaging image detection model, the model automatically extracts important information from the image and generates corresponding primary packaging information based on the features it has learned during training, such as image type (e.g., shipment, outer packaging, inner packaging) and packaging status (e.g., intact, damaged, or broken).
[0054] The first step in training a packaging image detection model is to construct an optimized dataset. This dataset includes various types of packaging images and their corresponding label information, such as image category (outer packaging, inner packaging, consignment, etc.) and packaging status (intact, damaged, broken, etc.). Data collection involves acquiring packaging images manually or using automated tools, and providing annotations for each image to ensure accurate classification and status information. The annotated optimized dataset, with real labels, serves as input samples. This image data is then fed into the training framework of the packaging image detection model, where it is trained using machine learning algorithms (such as backpropagation in deep learning). During training, the model adjusts its internal parameters (such as weights) to more accurately identify categories, packaging status, and other information in the images. Furthermore, some implementations include extracting textual descriptions related to the packaging images. These texts typically include packaging type, status, and label information to further help the model understand the image content. Visual features, such as color, shape, and texture, are extracted from the images using deep learning methods such as convolutional neural networks (CNNs), while natural language processing techniques (such as BERT, GPT, RNNs) are used to process the textual descriptions and extract keywords and category information. Ultimately, image features and text features are combined, and through optimized training, the model is able to simultaneously understand and process image and text information, thereby achieving accurate packaged image recognition and text matching.
[0055] In some optional implementations, step S2023 above includes:
[0056] Step a1: If the image quality of the item image, outer packaging image, and inner packaging image are all qualified, then the image to be tested is determined as the target packaging image.
[0057] Step a2: Extract the fourth image feature from the target packaging image, input the fourth image feature into the packaging image detection model, obtain the output result of the packaging image detection model, and determine the image type and text description information corresponding to the target packaging image. The image type includes the type of consignment, the type of inner packaging, and the type of outer packaging. The text description information is used to characterize the packaging status information of the target packaging image. The first packaging information includes the image type and the text description information.
[0058] Step a3: When it is determined that the target packaging image is missing at least one of the following: the type of consignment, the type of outer packaging, and the type of inner packaging, the packaging of the target consignment is deemed unqualified.
[0059] Image processing techniques (such as convolutional neural networks) are used to analyze the target packaging image and extract the corresponding fourth image features. The extracted fourth image features are then input into a pre-trained packaging image detection model, which uses these features to determine the image type of each packaging image.
[0060] By inputting image features into a packaging image detection model, textual descriptions of the target packaging image are generated. These textual descriptions reflect the state of the packaging image, such as whether the packaging is intact, damaged, or meets standards.
[0061] Check whether the target packaging image is missing necessary packaging information. Specifically, if at least one of the following is detected missing in the target packaging image: the type of consignment, the type of inner packaging, or the type of outer packaging, the packaging is deemed defective and the consignment is considered unqualified.
[0062] In the above embodiments, image features are used to identify the image type of the target packaging image, including the type of consignment, the type of inner packaging, and the type of outer packaging, achieving comprehensive identification of different packaging layers. The packaging image detection model can also generate text description information to accurately reflect packaging status information, such as packaging integrity and whether there is damage. Therefore, this method not only improves the efficiency of packaging image detection and reduces manual intervention, but also improves the accuracy and consistency of detection. By automating the processing of image type and packaging status information, it can better support subsequent logistics management and quality control. Through comprehensive detection of the consignment type, outer packaging type, and inner packaging type in the target packaging image, key missing parts of the packaging can be quickly and accurately identified. When the system detects the absence of any type of image, it automatically determines that the packaging of the target consignment is unqualified, thereby reducing the complexity and error rate of manual judgment.
[0063] Step S2024: Remove images of items, outer packaging, and inner packaging that are of substandard quality.
[0064] The quality of each image in the product image, outer packaging image, and inner packaging image is evaluated, and its compliance with standards is determined based on the image's quality characteristics. If the quality characteristics of an image do not meet the preset quality standards (e.g., blurry, overexposed, or excessively noisy), the image is discarded, ensuring that only images that meet the quality requirements are retained for subsequent packaging information recognition and detection processes.
[0065] Step S203: Determine the type of the target consignment and determine the second packaging information corresponding to the type of the target consignment; wherein, the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment. For details, please refer to step S103 of the embodiment shown in Figure 1, which will not be repeated here.
[0066] Step S204: Compare the first packaging information and the second packaging information, and determine the packaging inspection result of the target shipment based on the comparison result. For details, please refer to step S104 of the embodiment shown in Figure 1, which will not be repeated here.
[0067] The packaging detection method provided in this invention can automatically identify and determine whether the shooting quality of various images meets the standards by comparing the first image quality feature, the second image quality feature, and the third image quality feature, ensuring the accuracy and reliability of subsequent packaging detection results. If the image quality is qualified, it can be used as the target packaging image and input into a pre-trained detection model for further analysis, thereby improving the detection accuracy and automation level. Removing images of items, outer packaging, and inner packaging that do not meet the shooting quality standards can effectively improve the accuracy and reliability of the detection results. By removing blurry or distorted images, misjudgments and unnecessary computational burdens caused by low-quality images are avoided, thereby improving processing efficiency and overall accuracy.
[0068] This embodiment provides a method for detecting consignment packaging, which can be used in computer equipment such as desktop computers and laptops. Figure 3 is a flowchart of the method for detecting consignment packaging according to an embodiment of the present invention. As shown in Figure 3, the process includes the following steps:
[0069] Step S301: Obtain the image to be detected corresponding to the target consignment. The image to be detected includes an image of the item, an image of the outer packaging, and an image of the inner packaging. For details, please refer to step S201 of the embodiment shown in Figure 2, which will not be repeated here.
[0070] Step S302 involves recognizing the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain the first packaging information corresponding to the target consigned item; wherein, the first packaging information is used to identify the actual packaging information used for the target consigned item. For details, please refer to step S202 of the embodiment shown in Figure 2, which will not be repeated here.
[0071] Step S303: Determine the type of the target consignment and determine the second packaging information corresponding to the type of the target consignment; wherein, the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment. For details, please refer to step S203 of the embodiment shown in Figure 2, which will not be repeated here.
[0072] Step S304: Compare the first packaging information and the second packaging information, and determine the packaging inspection result of the target consignment based on the comparison result.
[0073] Specifically, step S304 includes:
[0074] Step S3041: Extract the first inner packaging information and the first outer packaging information corresponding to the target consignment from the first packaging information; wherein, the first inner packaging information is used to identify the inner packaging information actually used for the target consignment; the first outer packaging information is used to identify the outer packaging information actually used for the target consignment.
[0075] The first inner packaging information is used to characterize the actual inner packaging of the target shipment, and the first outer packaging information is used to characterize the actual outer packaging of the target shipment. Specifically, the actual inner packaging information and the actual outer packaging information corresponding to the target shipment are extracted from the first packaging information.
[0076] Step S3042: Extract second packaging information corresponding to the type of the target consignment from the preset packaging knowledge base. The second packaging information includes second inner packaging information and second outer packaging information. The second inner packaging information is used to identify the inner packaging standard information corresponding to the type of the target consignment. The second outer packaging information is used to identify the outer packaging standard information corresponding to the type of the target consignment.
[0077] The second inner packaging information is used to characterize the standard inner packaging of the target shipment, and the second outer packaging information is used to characterize the standard outer packaging of the target shipment. Specifically, based on the type of the target shipment, the standard inner packaging information and standard outer packaging information corresponding to that type of shipment are retrieved from the company's packaging specification knowledge base.
[0078] Step S3043: Compare the first inner packaging information and the second inner packaging information, and compare the first outer packaging information and the second outer packaging information to obtain the comparison results of the packaging information.
[0079] The actual first inner packaging information is compared with the standard second inner packaging information, and the first outer packaging information is also compared with the standard second outer packaging information to check whether the inner and outer packaging of the target shipment meets the standard packaging requirements. Specifically, by comparing the first and second inner packaging information, it is checked whether the actual inner packaging meets the specified requirements for materials, dimensions, and protection methods, such as checking whether the cushioning material of the inner packaging completely fills the gaps. By comparing the first and second outer packaging information, it is checked whether the outer packaging meets the standards for materials, dimensions, and structure. For example, it is checked whether the outer packaging is damaged.
[0080] Step S3044: If the comparison results indicate that the information of the first inner packaging matches the information of the second inner packaging, and the information of the first outer packaging matches the information of the second outer packaging, then the packaging inspection of the target consigned item is determined to be qualified.
[0081] If the actual packaging information (first inner packaging and first outer packaging) matches the standard packaging information (second inner packaging and second outer packaging) perfectly, the packaging of the target shipment is deemed to meet the requirements, i.e., the packaging of the target shipment is deemed acceptable. Conversely, if any mismatch is found, the packaging is deemed unacceptable.
[0082] The packaging inspection method for consigned goods provided in this invention acquires the actual inner and outer packaging information of the target consigned goods and compares it with preset standard packaging information, which helps ensure that the packaging of the target consigned goods meets predetermined specifications. By comparing the inner and outer packaging information, abnormalities or non-compliance with standards can be effectively identified, thereby improving the accuracy and reliability of the inspection. In addition, judging the conformity of packaging based on the comparison results can automatically screen out non-conforming packaging, reduce manual intervention, improve efficiency, and ensure the safety and integrity of products during transportation.
[0083] This embodiment also provides a detection device for consigned packages, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0084] This embodiment provides a detection device for consigned goods packaging, as shown in Figure 4, including:
[0085] The acquisition module 401 is used to acquire the image to be detected corresponding to the target consigned item. The image to be detected includes the item image, the outer packaging image, and the inner packaging image.
[0086] The identification module 402 is used to identify the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain the first packaging information corresponding to the target consignment; wherein, the first packaging information is used to identify the actual packaging information used for the target consignment;
[0087] The determining module 403 is used to determine the type of the target consignment and to determine the second packaging information corresponding to the type of the target consignment; wherein, the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment;
[0088] The comparison module 404 is used to compare the first packaging information and the second packaging information, and determine the packaging inspection result of the target consignment based on the comparison result.
[0089] In some alternative implementations, the identification module 402 includes:
[0090] The first extraction submodule is used to extract a first image quality feature from the item image, a second image quality feature from the outer packaging image, and a third image quality feature from the inner packaging image;
[0091] The first determining submodule is used to determine whether the shooting quality of the item image, outer packaging image and inner packaging image is qualified based on the first image quality feature, the second image quality feature and the third image quality feature, respectively.
[0092] The second determination submodule is used to determine the image to be detected as the target packaging image if the shooting quality of the item image, outer packaging image and inner packaging image are all qualified, and input the target packaging image into the pre-trained packaging image detection model to obtain the first packaging information corresponding to the target packaging image.
[0093] In some optional implementations, the identification module 402 further includes:
[0094] The rejection submodule is used to reject images of items, outer packaging, and inner packaging that do not meet the required image quality standards.
[0095] In some optional implementations, the second determining submodule includes:
[0096] The extraction unit is used to extract a fourth image feature from the target packaging image, input the fourth image feature into the packaging image detection model, obtain the output result of the packaging image detection model, and determine the image type and text description information corresponding to the target packaging image. The image type includes the type of consignment, the type of inner packaging, and the type of outer packaging. The text description information is used to characterize the packaging status information of the target packaging image. The first packaging information includes the image type and the text description information.
[0097] In some optional implementations, the second determining submodule further includes:
[0098] The first determining unit is used to determine that the packaging of the target shipment is unqualified when the target packaging image is missing at least one of the following: the type of shipment, the type of outer packaging, and the type of inner packaging.
[0099] In some alternative implementations, the comparison module 404 includes:
[0100] The second extraction submodule is used to extract the first inner packaging information and the first outer packaging information corresponding to the target consignment from the first packaging information; wherein, the first inner packaging information is used to identify the inner packaging information actually used for the target consignment; and the first outer packaging information is used to identify the outer packaging information actually used for the target consignment.
[0101] The third extraction submodule is used to extract second packaging information corresponding to the type of the target consigned item from a preset packaging knowledge base. The second packaging information includes second inner packaging information and second outer packaging information. The second inner packaging information is used to identify the inner packaging standard information corresponding to the type of the target consigned item, and the second outer packaging information is used to identify the outer packaging standard information corresponding to the type of the target consigned item.
[0102] The comparison submodule is used to compare the first inner packaging information and the second inner packaging information, and to compare the first outer packaging information and the second outer packaging information to obtain the comparison results of the packaging information;
[0103] The detection submodule is used to determine that the packaging of the target shipment is qualified if the comparison results indicate that the information of the first inner packaging and the information of the second inner packaging match, and the information of the first outer packaging and the information of the second outer packaging match.
[0104] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0105] In this embodiment, the detection device for the consignment packaging is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0106] The packaging inspection device provided in this invention acquires an initial image of the target shipment and performs comprehensive identification, accurately extracting relevant information about the shipment, outer packaging, and inner packaging, ensuring the comprehensiveness and accuracy of packaging inspection. It automatically determines the corresponding packaging information based on the type of the target shipment, effectively improving the intelligence and adaptability of the inspection. By comparing the actual packaging information with preset packaging standards, it can accurately determine whether the packaging meets the standards, thereby improving the efficiency and accuracy of packaging quality control and reducing the need for manual intervention.
[0107] This invention also provides a computer device having the detection device for consigned packages shown in FIG4.
[0108] Please refer to Figure 5, which is a schematic diagram of a computer device according to an optional embodiment of the present invention. As shown in Figure 5, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 uses one processor 10 as an example.
[0109] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0110] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.
[0111] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0112] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0113] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30 and output device 40 can be connected via a bus or other means; Figure 5 shows an example of a connection via a bus.
[0114] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.
[0115] The computer device also includes a communication interface for communicating with other devices or communication networks.
[0116] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0117] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0118] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for detecting consignment packaging, the method comprising: Acquire the image to be detected corresponding to the target consigned item, the image to be detected including the item image, the outer packaging image and the inner packaging image; The image of the item, the image of the outer packaging, and the image of the inner packaging are identified to obtain the first packaging information corresponding to the target consigned item; wherein, the first packaging information is used to identify the actual packaging information used for the target consigned item; Determine the type of the target consignment, and determine the second packaging information corresponding to the type of the target consignment; wherein the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment; and The first packaging information and the second packaging information are compared, and the packaging inspection result of the target consignment is determined based on the comparison result.
2. The method of claim 1, wherein, The step of identifying the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain the first packaging information corresponding to the target consigned item includes: Extract a first image quality feature from the image of the item, extract a second image quality feature from the image of the outer packaging, and extract a third image quality feature from the image of the inner packaging; Based on the first image quality feature, the second image quality feature, and the third image quality feature, determine whether the shooting quality of the item image, the outer packaging image, and the inner packaging image is qualified; and If the image quality of the item image, the outer packaging image, and the inner packaging image are all deemed acceptable, then the image to be detected is identified as the target packaging image, and the target packaging image is input into a pre-trained packaging image detection model to obtain the first packaging information corresponding to the target packaging image.
3. The method of claim 2, wherein, Also includes: Images of items, outer packaging, and inner packaging that do not meet quality standards will be removed.
4. The method of claim 2, wherein, The target packaging image is input into a pre-trained packaging image detection model to obtain the first packaging information corresponding to the target packaging image, including: A fourth image feature is extracted from the target packaging image, and the fourth image feature is input into the packaging image detection model. The output result of the packaging image detection model is obtained, and the image type and text description information corresponding to the target packaging image are determined. The image type includes the type of consigned item, the type of inner packaging, and the type of outer packaging. The text description information is used to characterize the packaging status information of the target packaging image. The first packaging information includes the image type and the text description information.
5. The method of claim 4, wherein, Also includes: When it is determined that the target packaging image is missing at least one of the following: the type of consignment, the type of outer packaging, and the type of inner packaging, the packaging of the target consignment is deemed unqualified.
6. The method of claim 1, wherein, The comparison of the first packaging information and the second packaging information, and the determination of the packaging inspection result of the target shipment based on the comparison result, includes: Extract the first inner packaging information and the first outer packaging information corresponding to the target consignment from the first packaging information; wherein, the first inner packaging information is used to identify the actual inner packaging information used for the target consignment; the first outer packaging information is used to identify the actual outer packaging information used for the target consignment; The second packaging information corresponding to the type of the target consigned item is extracted from a preset packaging knowledge base. The second packaging information includes second inner packaging information and second outer packaging information. The second inner packaging information is used to identify the inner packaging standard information corresponding to the type of the target consigned item. The second outer packaging information is used to identify the outer packaging standard information corresponding to the type of the target consigned item. The first inner packaging information and the second inner packaging information are compared, and the first outer packaging information and the second outer packaging information are compared to obtain the comparison results of the packaging information; and If the comparison results indicate that the first inner packaging information and the second inner packaging information match, and the first outer packaging information and the second outer packaging information match, then the packaging inspection of the target consigned item is determined to be qualified.
7. The method of claim 1, wherein, The acquisition of the image to be detected corresponding to the target consignment includes: The image to be detected is obtained by taking a picture or scanning the target container. The images to be detected include images of the items, outer packaging, and inner packaging under the same waybill number.
8. A detection device for consigned goods packaging, comprising: The acquisition module is used to acquire the image to be detected corresponding to the target consigned item, the image to be detected including the item image, the outer packaging image and the inner packaging image; The identification module is used to identify the image of the item, the image of the outer packaging, and the image of the inner packaging to obtain the first packaging information corresponding to the target consignment; wherein, the first packaging information is used to identify the actual packaging information used for the target consignment; The determining module is used to determine the type of the target consignment and to determine the second packaging information corresponding to the type of the target consignment; wherein the second packaging information is used to identify the packaging standard information corresponding to the type of the target consignment; The comparison module is used to compare the first packaging information and the second packaging information, and determine the packaging inspection result of the target consignment based on the comparison result.
9. The apparatus of claim 8, wherein, The identification module includes: The first extraction submodule is used to extract a first image quality feature from the item image, a second image quality feature from the outer packaging image, and a third image quality feature from the inner packaging image; The first determining submodule is used to determine whether the shooting quality of the item image, the outer packaging image, and the inner packaging image is qualified based on the first image quality feature, the second image quality feature, and the third image quality feature, respectively. The second determining submodule is used to determine the image to be detected as the target packaging image if the shooting quality of the item image, the outer packaging image, and the inner packaging image are all qualified, and input the target packaging image into a pre-trained packaging image detection model to obtain the first packaging information corresponding to the target packaging image.
10. The apparatus of claim 9, wherein, The identification module further includes: The rejection submodule is used to reject images of items, outer packaging, and inner packaging that do not meet the required image quality standards.
11. The apparatus of claim 9, wherein, The second determining submodule includes: An extraction unit is configured to extract a fourth image feature from the target packaging image, input the fourth image feature into the packaging image detection model, obtain the output result of the packaging image detection model, and determine the image type and text description information corresponding to the target packaging image. The image type includes the type of consignment, the type of inner packaging, and the type of outer packaging. The text description information is used to characterize the packaging status information of the target packaging image. The first packaging information includes the image type and the text description information.
12. The apparatus of claim 11, wherein, The second determining submodule also includes: The first determining unit is configured to determine that the packaging of the target shipment is unqualified when it is determined that the target packaging image is missing at least one of the following: shipment type, outer packaging type, and inner packaging type.
13. The apparatus of claim 8, wherein, The comparison module includes: The second extraction submodule is used to extract the first inner packaging information and the first outer packaging information corresponding to the target consignment from the first packaging information; wherein, the first inner packaging information is used to identify the inner packaging information actually used by the target consignment; and the first outer packaging information is used to identify the outer packaging information actually used by the target consignment. The third extraction submodule is used to extract the second packaging information corresponding to the type of the target consigned item from a preset packaging knowledge base. The second packaging information includes second inner packaging information and second outer packaging information. The second inner packaging information is used to identify the inner packaging standard information corresponding to the type of the target consigned item. The second outer packaging information is used to identify the outer packaging standard information corresponding to the type of the target consigned item. The comparison submodule is used to compare the first inner packaging information with the second inner packaging information, and to compare the first outer packaging information with the second outer packaging information to obtain the comparison result of the packaging information; The detection submodule is used to determine that the packaging inspection of the target shipment is qualified if the comparison result indicates that the first inner packaging information and the second inner packaging information match, and the first outer packaging information and the second outer packaging information match.
14. A computer device comprising a memory and one or more processors, the memory storing computer-readable instructions which, when executed by the processors, perform the steps of the method according to any one of claims 1 to 7.
15. One or more non-transitory computer-readable storage media storing computer- readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the method of any of claims 1-7.
16. A computer program product comprising computer-readable instructions that, when executed by a processor, implement the steps of the method of any of claims 1-7.