Weight rechecking method, apparatus, computer device and storage medium

Abstract

The present application relates to a weight rechecking method, an apparatus, a computer device and a storage medium. The method comprises: acquiring a plurality of uploaded images used for rechecking the weight of a target object, the plurality of images being images acquired during the process of weighing the target object (202); identifying the image category of each image to obtain an image category identification result, the image category identification result comprising a weighing panoramic image, a dial image, and a waybill image (204); determining the image quality of the dial image and the waybill image among the plurality of images to obtain a quality determination result (206); according to the image category identification result and the quality determination result, determining whether the uploaded images are compliant (208); if so, identifying the compliant dial image to obtain a dial reading, and identifying the compliant waybill image to obtain a waybill identifier (210); and, according to the waybill identifier and the dial reading, rechecking the weight of the target object (212). The method can improve the efficiency and accuracy of weight rechecking.

Description

Weight verification method, device, computer equipment and storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 2023118700479, filed on December 30, 2023, entitled “Weight Review Method, Device, Computer Equipment and Storage Medium,” the entire text of which is incorporated herein by reference. Technical Field

[0003] The present application relates to the field of computer vision technology, and in particular to a weight verification method, apparatus, computer equipment, and storage medium. Background Art

[0004] In logistics scenarios, freight is generally charged based on the weight of the shipment, cargo, or parcel. When passing through a transit station, the weight must be verified using measuring equipment such as DWS (Dimension Weight and Scanning). If the verified weight differs from the weight originally recorded in the system, the difference in freight will be charged. However, for shipments, cargo, or parcels that do not pass through a transit station, the weight cannot be automatically verified using the transit station's measuring equipment. Instead, the courier at the end of the delivery process must manually verify the weight. Due to the many uncertainties associated with manual weight verification, it is difficult to ensure the accuracy of the weight verification. Summary of the Invention

[0005] Various embodiments of the present application provide a weight verification method, apparatus, computer device, computer-readable storage medium, and computer program product.

[0006] In a first aspect, the present application provides a weight verification method. The method comprises:

[0007] Acquire multiple uploaded images for weight verification of a target object; the multiple images are images captured during the weighing process of the target object;

[0008] Identify the image category of each of the images to obtain an image category recognition result; the image category recognition result includes a panoramic weighing image, a dial image, and a waybill image; the panoramic weighing image is an image containing an entire scene of weighing the target object; the dial image is an image containing the dial of the scale being weighed; and the waybill image is an image containing the waybill of the target object;

[0009] Performing image quality judgment on the dial image and the waybill image in the plurality of images to obtain a quality judgment result;

[0010] Determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result;

[0011] If it is compliant, the compliant dial image is identified to obtain the dial reading, and the compliant waybill image is identified to obtain the waybill identifier;

[0012] The weight of the target object is reviewed based on the waybill identification and the dial indication.

[0013] In one embodiment, identifying the image category of each of the images to obtain an image category recognition result includes:

[0014] Performing image detection on each of the images to obtain an image detection result of the image; the image detection result includes at least one of a weighing panorama, a dial, and a waybill;

[0015] An image category of the image is determined according to the image detection result, and an image category recognition result of the image is obtained.

[0016] In one embodiment, determining the image category of the image based on the image detection result to obtain the image category recognition result of the image includes at least one of the following:

[0017] If the image detection result includes both the weighing panorama and the dial, determining that the image category of the image is a weighing panorama image;

[0018] If the image detection result only includes the dial but does not include the weighing panorama and the waybill, determining that the image category of the image is a dial image;

[0019] If the image detection result only includes the waybill but does not include the weighing panorama and the dial, the image category of the image is determined to be a waybill image.

[0020] In one embodiment, performing image quality judgment on the dial image and the waybill image in the plurality of images to obtain a quality judgment result includes:

[0021] Inputting the dial image and the waybill image from the multiple images into a pre-trained quality judgment model respectively, and outputting a quality judgment result;

[0022] The quality judgment model is a classification model pre-trained based on positive samples and negative samples; the negative samples include samples obtained by performing motion blur processing on the positive samples.

[0023] In one embodiment, determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result includes:

[0024] If the image category recognition result indicates that the uploaded multiple images include a weighing panoramic image, a dial image and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete, then the uploaded image is determined to be compliant.

[0025] In one embodiment, the checking the weight of the target object according to the waybill identification and the dial indication includes:

[0026] Comparing the waybill identifier with the waybill identifier corresponding to the target object recorded in the system;

[0027] If the waybill identification is consistent, the dial reading is compared with the weight of the target object recorded in the system to obtain a weight verification result.

[0028] In one embodiment, determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result includes:

[0029] Determine whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, and obtain preliminary compliant weighing panoramic image, dial image, and waybill image;

[0030] After determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, the method further includes:

[0031] Performing feature extraction on image content corresponding to the dial area in the preliminarily compliant panoramic weighing image to obtain a first feature vector, and performing feature extraction on image content corresponding to the waybill area in the preliminarily compliant panoramic weighing image to obtain a second feature vector;

[0032] Performing feature extraction on image content corresponding to the dial area in the preliminarily compliant dial image to obtain a third feature vector;

[0033] Performing feature extraction on image content corresponding to a region of the waybill in the preliminarily compliant waybill image to obtain a fourth feature vector;

[0034] calculating a first similarity between the first eigenvector and the third eigenvector, and a second similarity between the second eigenvector and the fourth eigenvector;

[0035] Based on the first similarity and the second similarity, an advanced compliance judgment is performed on the initially compliant image to obtain a compliant weighing panoramic image, a dial image and a waybill image, and the identification of the compliant dial image is executed to obtain the dial reading, and the compliant waybill image is identified to obtain the waybill logo.

[0036] In a second aspect, the present application further provides a weight verification device. The device comprises:

[0037] An image acquisition module is used to acquire a plurality of uploaded images for weight verification of a target object; the plurality of images are images collected during the weighing process of the target object;

[0038] an image category recognition module, configured to identify the image category of each of the images and obtain an image category recognition result; the image category recognition result includes a panoramic weighing image, a dial image, and a waybill image; the panoramic weighing image is an image of an overall view of the weighing of the target object; the dial image is an image of the dial of the scale being weighed; and the waybill image is an image of the waybill of the target object;

[0039] An image quality judgment module, configured to perform image quality judgment on the dial image and the waybill image in the plurality of images to obtain a quality judgment result;

[0040] An image compliance judgment module, configured to determine whether the uploaded image complies with the regulations based on the image category recognition result and the quality judgment result;

[0041] A character recognition module is used to identify the compliant dial image to obtain the dial reading if the dial is compliant, and to identify the compliant waybill image to obtain the waybill identifier;

[0042] The weight verification module is used to verify the weight of the target object according to the waybill identification and the dial indication.

[0043] In one embodiment, the image category recognition module is further used to perform image detection on each of the images to obtain an image detection result of the image; the image detection result includes at least one of a weighing panorama, a dial, and a waybill; and the image category of the image is determined based on the image detection result to obtain an image category recognition result of the image.

[0044] In one embodiment, the image category recognition module is further used to perform at least one of the following: if the image detection result includes both the weighing panorama and the dial, then the image category of the image is determined to be a weighing panorama image; if the image detection result only includes the dial but does not include the weighing panorama and the waybill, then the image category of the image is determined to be a dial image; if the image detection result only includes the waybill but does not include the weighing panorama and the dial, then the image category of the image is determined to be a waybill image.

[0045] In one embodiment, the image quality judgment module is further used to input the dial image and the waybill image in the multiple images into a pre-trained quality judgment model, and output a quality judgment result; wherein, the quality judgment model is a classification model pre-trained based on positive samples and negative samples; the negative samples include samples obtained by motion blurring the positive samples.

[0046] In one embodiment, the image compliance judgment module is also used to determine that the uploaded image is compliant if the image category recognition result indicates that the uploaded multiple images include a weighing panoramic image, a dial image and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete.

[0047] In one embodiment, the weight verification module is further used to compare the waybill identifier with the waybill identifier corresponding to the target object recorded in the system; if the waybill identifiers are consistent, the dial reading is compared with the weight of the target object recorded in the system to obtain a weight verification result.

[0048] In one embodiment, the image compliance judgment module is further used to determine whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, and obtain preliminary compliant weighing panoramic image, dial image and waybill image; feature extraction is performed on the image content corresponding to the dial area in the preliminary compliant weighing panoramic image to obtain a first feature vector, and feature extraction is performed on the image content corresponding to the waybill area in the preliminary compliant weighing panoramic image to obtain a second feature vector; feature extraction is performed on the image content corresponding to the dial area in the preliminary compliant dial image to obtain a third feature vector; feature extraction is performed on the image content corresponding to the waybill area in the preliminary compliant waybill image to obtain a fourth feature vector; calculate the first similarity between the first feature vector and the third feature vector, and the second similarity between the second feature vector and the fourth feature vector; based on the first similarity and the second similarity, perform advanced compliance judgment on the preliminary compliant image to obtain compliant weighing panoramic image, dial image and waybill image, execute the identification of the compliant dial image to obtain the dial reading, and identify the compliant waybill image to obtain the waybill identification.

[0049] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the weight verification method described in each embodiment of the present application.

[0050] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of the weight verification method described in each embodiment of the present application.

[0051] In a fifth aspect, the present application further provides a computer program product, which includes a computer program that, when executed by a processor, causes the processor to execute the steps of the weight verification method described in each embodiment of the present application.

[0052] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0054] FIG1 is a diagram showing an application environment of a weight verification method in some embodiments.

[0055] FIG2 is a schematic flow chart of a weight verification method in some embodiments.

[0056] FIG3 is a schematic diagram of the overall flow of the weight verification method in some embodiments.

[0057] FIG4 is a schematic diagram of labeling of a first sample image in some embodiments.

[0058] FIG5 is a schematic diagram of labeling of a second sample image in some embodiments.

[0059] FIG6 is a structural block diagram of a weight verification device in some embodiments.

[0060] FIG7 is a diagram illustrating the internal structure of a computer device in some embodiments. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0062] The weight verification method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. In the process of using the scale to weigh the target object, the weighing personnel can use the terminal 102 to capture images to obtain multiple images, and the terminal 102 can upload the multiple images to the server 104. The server 104 can execute the weight verification method in each embodiment of the present application to automatically verify the weight based on the uploaded multiple images. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0063] In other embodiments, the terminal 102 may also independently execute the weight verification method in each embodiment of the present application without transmitting the image to the server for execution.

[0064] In some embodiments, as shown in FIG2 , a weight verification method is provided. The method is described by taking the application of the method to the server 104 in FIG1 as an example, including the following steps:

[0065] Step 202 : Acquire multiple uploaded images for weight verification of the target object; the multiple images are images captured during the weighing process of the target object.

[0066] The target object is the object that requires weight verification. Weight verification refers to reweighing the target object to verify whether the weight originally recorded in the system is authentic and valid.

[0067] In some embodiments, the target object may be a parcel, package, or cargo in logistics.

[0068] In some embodiments, the reviewer may use a scale to weigh the target object, and use a terminal to capture images while weighing to obtain multiple images, and the terminal uploads the multiple images to the server.

[0069] In some embodiments, if the number of uploaded images is greater than or equal to 2, step 204 and subsequent steps may be executed; if the number is less than 2, a prompt message indicating that the number of images is insufficient may be output.

[0070] Step 204, identify the image category of each image and obtain an image category recognition result; the image category recognition result includes a weighing panoramic image, a dial image and a waybill image; the weighing panoramic image is an image of the entire picture of weighing the target object; the dial image is an image of the dial of the scale being weighed; and the waybill image is an image of the waybill of the target object.

[0071] In some embodiments, the weighing panoramic image may include at least a scale and a target object.

[0072] In some embodiments, the dial image may include at least the dial of the scale being weighed. In other embodiments, the dial image may include the dial and the entire scale being weighed.

[0073] In some embodiments, the waybill image includes at least the waybill of the target object. In other embodiments, the waybill image may include the waybill and the entire target object.

[0074] Step 206 : Perform image quality judgment on the dial image and the waybill image in the multiple images to obtain a quality judgment result.

[0075] In some embodiments, image quality assessment is used to determine whether an image is clear and whether the content in the image is complete. The quality assessment result for a dial image is used to determine whether the dial image is clear and whether the dial in the dial image is complete. The quality assessment result for a waybill image is used to determine whether the waybill image is clear and whether the waybill in the waybill image is complete.

[0076] In some embodiments, the server may first crop the dial image and the waybill image from the multiple images to obtain a first image and a second image, then perform an image quality assessment on the first image and the second image to obtain a quality assessment result, and then perform step 210 based on the first image and the second image. The first image is an image obtained by cropping the dial area from the dial image, and the second image is an image obtained by cropping the waybill area from the waybill image.

[0077] Step 208: Determine whether the uploaded image is compliant based on the image category recognition result and the quality judgment result.

[0078] In some embodiments, if the image is in compliance, step 210 is executed; if the image is not in compliance, the server may output a non-compliant prompt message to the terminal. In some embodiments, if the image is not in compliance, the server may also output the reason for the non-compliance to the terminal to prompt the weighing personnel to supplement the compliant image.

[0079] Step 210: If it is compliant, identify the compliant dial image to obtain the dial reading, and identify the compliant waybill image to obtain the waybill identifier.

[0080] The dial reading represents the weight of the target object measured on the scale. The waybill identifier is used to uniquely identify the waybill of the target object. For example, the waybill identifier can be the waybill number.

[0081] In some embodiments, the multiple images uploaded may include a dial image and a waybill image. If compliance is determined, the server can identify the dial image and the waybill image to obtain the dial reading and the waybill identification. In other embodiments, the multiple images uploaded may also include one or more of the following: multiple dial images, multiple waybill images. The server can determine the compliant dial image and compliant waybill image from the multiple dial images and multiple waybill images, identify the compliant dial image and compliant waybill image, and obtain the dial reading and waybill identification.

[0082] In some embodiments, the server may use OCR (Optical Character Recognition) technology to recognize a qualified dial image and obtain the dial reading.

[0083] In some embodiments, the server can identify the graphic code on the waybill in the compliant waybill image to obtain the waybill identifier. The graphic code can be a one-dimensional code or a two-dimensional code. In some embodiments, the server can use the Zbar algorithm (an open source library for graphic code scanning) to identify the graphic code.

[0084] Step 212: Check the weight of the target object based on the waybill identification and the dial reading.

[0085] In some embodiments, the server can compare the waybill identifier with the waybill identifier corresponding to the target object recorded in the system. If the waybill identifiers are consistent, the dial reading is compared with the weight of the target object recorded in the system to obtain a weight verification result.

[0086] Figure 3 shows the overall flow of the weight compliance method. The weigher uses a terminal to capture and upload multiple images. If the number of images is less than two, a result indicating insufficient images can be returned. If the number of images is greater than or equal to two, the detection network determines the image category (weighing panorama, dial, and waybill). The classification network then determines whether the dial and waybill images are clear and complete. The results of the detection and classification networks are then integrated to return a result indicating image compliance or non-compliance, along with the reason for the non-compliance. Finally, the character recognition network identifies the waybill and dial images to obtain the waybill logo and dial reading.

[0087] The weight verification method captures multiple uploaded images for weight verification of a target object, identifies the image category of each image, and obtains an image category recognition result, which includes a panoramic weighing image, a dial image, and a waybill image. The image quality of the dial image and the waybill image among the multiple images is then judged to obtain a quality judgment result. Based on the image category recognition and quality judgment results, the method determines whether the uploaded image is compliant. If compliant, the compliant dial image is identified to obtain the dial reading, and the compliant waybill image is identified to obtain the waybill identifier. Based on the waybill identifier and the dial reading, the weight of the target object is verified. This method enables automatic weight verification based on the uploaded images by simply capturing and uploading them. Furthermore, by determining whether the uploaded images are compliant based on the image category recognition and quality judgment results, the compliance of the images can be accurately guaranteed, thereby improving the accuracy of weight verification. Furthermore, a three-level cascade architecture is adopted, utilizing visual algorithms to analyze the uploaded images, enabling weight verification without additional hardware overhead. This approach is simple to use and resource-efficient.

[0088] In some embodiments, identifying the image category of each image and obtaining an image category recognition result may include: performing image detection on each image separately to obtain an image detection result of the image; the image detection result includes at least one of a weighing panorama, a dial, and a waybill; determining the image category of the image based on the image detection result to obtain an image category recognition result of the image.

[0089] The weighing panorama may include a scale and a target object.

[0090] In some embodiments, the server may input each image into a pre-trained image detection model and output an image detection result.

[0091] In some embodiments, each first sample image used to train the image detection model can be annotated in advance in the manner shown in Figure 4. The weighing panorama, dial and waybill in each first sample image are marked. Whether the dial reading is clear and complete, and whether the text on the waybill is clear and complete, they can all be marked. Among them, the weighing panorama can be a platform scale + weighing object, an electronic scale + weighing object, or a portable scale + weighing object, etc. The dial can be a portable scale dial, a platform scale dial, or an electronic scale dial, etc. The server can perform model training based on the annotated first sample image to obtain a trained image detection model.

[0092] In some embodiments, the image detection model can be a YOLO series model such as YOLOv8 or a model of the Transformer architecture series. If a YOLO series model is used, multiscale must be disabled.

[0093] In some embodiments, if the image detection result includes a weighing panorama, the image category of the image is determined to be a weighing panorama image; if the image detection result only includes a dial but does not include a weighing panorama and a waybill, the image category of the image is determined to be a dial image; if the image detection result only includes a waybill but does not include a weighing panorama and a dial, the image category of the image is determined to be a waybill image.

[0094] In some embodiments, the image detection results may also include interfering objects other than the scale and the target object. The server can determine whether the interfering object is located on the scale surface or the target object. If so, it outputs a prompt message that the weighing method is incorrect; if not, it continues to execute the steps of determining the image category of the image based on the image detection results and obtaining the image category recognition result of the image and subsequent steps.

[0095] In the above embodiment, image detection is performed on each image to obtain an image detection result of the image, which includes at least one of the weighing panorama, the dial and the waybill. Then, the image category of the image is determined based on the image detection result to obtain an image category recognition result of the image. The image category can be accurately determined based on the result detected in the image.

[0096] In some embodiments, the image category of the image is determined based on the image detection result, and the image category recognition result of the image includes at least one of the following: if the image detection result includes both the weighing panorama and the dial, the image category of the image is determined to be a weighing panorama image; if the image detection result only includes the dial but does not include the weighing panorama and the waybill, the image category of the image is determined to be a dial image; if the image detection result only includes the waybill but does not include the weighing panorama and the dial, the image category of the image is determined to be a waybill image.

[0097] It is understandable that during the experimental phase, through analysis of the training and inference results, it was found that the model's detection accuracy for weighing panoramas was poor, because the model tended to detect images that did not contain a dial but only contained a weighing object as a weighing panorama. The reason for this is that the weighing object accounts for a large proportion in the annotation box of the weighing panorama, and the model will extract the feature vector of the weighing object when performing image feature extraction. To solve this problem and improve the accuracy of the entire process, this embodiment, combined with business logic, defines during model inference that if the image detection result only contains a weighing panorama but not a dial, the image category of the image will not be determined as a weighing panorama image. Only when the image detection result contains both a weighing panorama and a dial will the image category of the image be determined to be a weighing panorama image.

[0098] In the above embodiment, if the image detection result only includes the weighing panorama but not the dial, the image category of the image will not be determined as a weighing panoramic image. Only when the image detection result includes both the weighing panorama and the dial will the image category of the image be determined as a weighing panoramic image, thereby improving the accuracy of identifying the weighing panoramic image.

[0099] In some embodiments, image quality judgment is performed on the dial image and the waybill image in the multiple images to obtain a quality judgment result, including: inputting the dial image and the waybill image in the multiple images into a pre-trained quality judgment model respectively, and outputting the quality judgment result; wherein the quality judgment model is a classification model pre-trained based on positive samples and negative samples; the negative samples include samples obtained by motion blurring the positive samples.

[0100] In some embodiments, the dial area and the waybill area can be cropped to obtain multiple second sample images for training the quality judgment model. Each second sample image is then annotated using the annotation method shown in FIG5 . The server can perform model training based on the annotated second sample images to obtain a trained quality judgment model.

[0101] In some embodiments, the second sample image may include a positive sample and a negative sample. A positive sample refers to an image with clear and complete image content. A negative sample refers to an image with unclear or incomplete image content.

[0102] In some embodiments, the negative sample may include a directly captured image, or may include a sample image obtained by performing motion blur processing on the positive sample.

[0103] Understandably, in actual operations, the statistical data shows that the number of complete and clear images is larger than the number of incomplete or unclear images. Furthermore, the ever-changing styles of incomplete or unclear images make it difficult to learn features. Therefore, data augmentation is used to increase the diversity of negative samples. Data augmentation methods such as RandomClip (random clipping), CenterClip (center clipping), rotation, or motion blur are used to batch increase the amount of incomplete and unclear image data. Note that this process simulates the actual situation that occurs when taking photos. In this business scenario, the majority of image blur is motion blur, not other blurs. Therefore, generating negative samples by motion blurring the positive samples is more realistic.

[0104] In some embodiments, the classification model may use an efficient-net series model, a ViT model, or a transformer architecture series model, etc.

[0105] In the above embodiment, a classification model is pre-trained based on positive samples and negative samples to perform image quality judgment. The negative samples include samples obtained by motion blurring the positive samples, thereby expanding the data volume of negative samples and increasing the diversity of training samples, thereby improving the accuracy of the trained quality judgment model.

[0106] In some embodiments, whether the uploaded image is compliant is determined based on the image category recognition result and the quality judgment result, including: if the image category recognition result indicates that the uploaded multiple images include a weighing panoramic image, a dial image and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete, then the uploaded image is determined to be compliant.

[0107] In the above embodiment, the multiple images uploaded include a panoramic weighing image, a dial image and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete, then it is determined that the uploaded image is compliant, thereby ensuring the compliance of the weighing process and improving the accuracy of weight verification.

[0108] In some embodiments, the weight of the target object is reviewed based on the waybill identification and the dial indication, including: comparing the waybill identification with the waybill identification corresponding to the target object recorded in the system; if the waybill identifications are consistent, comparing the dial indication with the weight of the target object recorded in the system to obtain a weight review result.

[0109] In some embodiments, if the waybill identification is inconsistent, a prompt message indicating that the waybill is inconsistent is output.

[0110] In some embodiments, if the waybill identifiers are matched, the meter reading is compared with the weight of the target object recorded in the system. If the difference between the meter reading and the weight of the target object recorded in the system is greater than or equal to a preset difference threshold, the weight verification result is determined to be a weight discrepancy. If the difference between the meter reading and the weight of the target object recorded in the system is less than the preset difference threshold, the weight verification result is determined to be a weight consistency.

[0111] In some embodiments, if the weight review result is that the weight does not match, the server may initiate a freight review and freight recovery process for the logistics order of the target object.

[0112] In the above embodiment, the waybill identifier is compared with the waybill identifier corresponding to the target object recorded in the system. If the waybill identifiers are consistent, the dial reading is compared with the weight of the target object recorded in the system to obtain the weight verification result, which can efficiently and accurately perform weight verification.

[0113] In some embodiments, determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result includes: determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, and obtaining a preliminary compliant weighing panoramic image, dial image and waybill image; after determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, the method also includes: extracting features of the image content corresponding to the area of ​​the dial in the preliminary compliant weighing panoramic image to obtain a first feature vector, extracting features of the image content corresponding to the area of ​​the waybill in the preliminary compliant weighing panoramic image to obtain a second feature vector. vector; perform feature extraction on the image content corresponding to the dial area in the preliminary compliant dial image to obtain a third feature vector; perform feature extraction on the image content corresponding to the waybill area in the preliminary compliant waybill image to obtain a fourth feature vector; calculate a first similarity between the first feature vector and the third feature vector, and a second similarity between the second feature vector and the fourth feature vector; perform advanced compliance judgment on the preliminary compliant image based on the first similarity and the second similarity to obtain a compliant weighing panoramic image, dial image and waybill image, perform recognition of the compliant dial image to obtain the dial reading, and recognize the compliant waybill image to obtain the waybill identification.

[0114] In some embodiments, the server may calculate the cosine similarity between the first feature vector and the third feature vector to obtain the first similarity, and calculate the cosine similarity between the second feature vector and the fourth feature vector to obtain the second similarity.

[0115] In some embodiments, if the first similarity is greater than or equal to a first similarity threshold and the second similarity is greater than or equal to a second similarity threshold, the advanced compliance determination of the preliminarily compliant image is passed.

[0116] In some embodiments, when the number of uploaded images is greater than three, the server may further screen the qualified images for a panoramic weighing image, a dial image, and a waybill image based on the first similarity and the second similarity, identify the qualified dial image to obtain the dial reading, and identify the qualified waybill image to obtain the waybill identifier. For example, if five images are uploaded and the image quality is judged to be clear and complete, the server may further screen the three images with the highest similarity (the panoramic weighing image, the dial image, and the waybill image) based on the similarity to identify the qualified dial image to obtain the dial reading, and identify the qualified waybill image to obtain the waybill identifier.

[0117] In the above embodiment, the similarity between the feature vector of the area of ​​the dial in the panoramic image and the feature vector of the area of ​​the dial in the dial image, as well as the similarity between the feature vector of the area of ​​the waybill in the panoramic image and the feature vector of the area of ​​the waybill in the waybill image, is calculated to further determine whether the image is compliant. This ensures that the uploaded images come from the same weighing process, thereby improving the accuracy of weight verification.

[0118] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0119] Based on the same inventive concept, the present application also provides a weight verification device for implementing the weight verification method mentioned above. The solution provided by the device is similar to the solution described in the above method. Therefore, the specific limitations of one or more weight verification device embodiments provided below can be found in the above-mentioned limitations of the weight verification method and will not be repeated here.

[0120] In some embodiments, as shown in FIG6 , a weight verification device 600 is provided, comprising: an image acquisition module 602 , an image category recognition module 604 , an image quality determination module 606 , an image compliance determination module 608 , a character recognition module 610 , and a weight verification module 612 , wherein:

[0121] The image acquisition module 602 is used to acquire multiple uploaded images for weight verification of the target object; the multiple images are images collected during the weighing process of the target object.

[0122] The image category recognition module 604 is used to identify the image category of each image and obtain an image category recognition result; the image category recognition result includes a weighing panoramic image, a dial image and a waybill image; the weighing panoramic image is an image of the entire picture of weighing the target object; the dial image is an image of the dial of the scale being weighed; and the waybill image is an image of the waybill containing the target object.

[0123] The image quality judgment module 606 is used to perform image quality judgment on the dial image and the waybill image in the multiple images to obtain a quality judgment result.

[0124] The image compliance judgment module 608 is used to determine whether the uploaded image is compliant based on the image category recognition result and the quality judgment result.

[0125] The character recognition module 610 is used to identify the compliant dial image to obtain the dial reading if it is compliant, and to identify the compliant waybill image to obtain the waybill logo.

[0126] The weight verification module 612 is used to verify the weight of the target object according to the waybill mark and the dial reading.

[0127] In some embodiments, the image category recognition module 604 is also used to perform image detection on each image separately to obtain an image detection result of the image; the image detection result includes at least one of the weighing panorama, dial and waybill; the image category of the image is determined according to the image detection result to obtain an image category recognition result of the image.

[0128] In some embodiments, the image category recognition module 604 is also used to perform at least one of the following: if the image detection result includes both a weighing panorama and a dial, then the image category of the image is determined to be a weighing panorama image; if the image detection result only includes a dial but does not include a weighing panorama and a waybill, then the image category of the image is determined to be a dial image; if the image detection result only includes a waybill but does not include a weighing panorama and a dial, then the image category of the image is determined to be a waybill image.

[0129] In some embodiments, the image quality judgment module 606 is also used to input the dial image and the waybill image in the multiple images into a pre-trained quality judgment model respectively, and output the quality judgment result; wherein the quality judgment model is a classification model pre-trained based on positive samples and negative samples; the negative samples include samples obtained by motion blurring the positive samples.

[0130] In some embodiments, the image compliance judgment module 608 is also used to determine that the uploaded image is compliant if the image category recognition result indicates that the uploaded multiple images include a weighing panoramic image, a dial image and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete.

[0131] In some embodiments, the weight verification module 612 is also used to compare the waybill identifier with the waybill identifier corresponding to the target object recorded in the system; if the waybill identifiers are consistent, the dial reading is compared with the weight of the target object recorded in the system to obtain the weight verification result.

[0132] In some embodiments, the image compliance judgment module 608 is also used to determine whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, and obtain preliminary compliant weighing panoramic image, dial image and waybill image; feature extraction is performed on the image content corresponding to the area of ​​the dial in the preliminary compliant weighing panoramic image to obtain a first feature vector, and feature extraction is performed on the image content corresponding to the area of ​​the waybill in the preliminary compliant weighing panoramic image to obtain a second feature vector; feature extraction is performed on the image content corresponding to the area of ​​the dial in the preliminary compliant dial image to obtain a third feature vector; feature extraction is performed on the image content corresponding to the area of ​​the waybill in the preliminary compliant waybill image to obtain a fourth feature vector; calculate the first similarity between the first feature vector and the third feature vector, and the second similarity between the second feature vector and the fourth feature vector; based on the first similarity and the second similarity, perform advanced compliance judgment on the preliminary compliant image to obtain compliant weighing panoramic image, dial image and waybill image, perform recognition of the compliant dial image to obtain the dial reading, and recognize the compliant waybill image to obtain the waybill identification.

[0133] The above-mentioned weight verification device obtains multiple uploaded images for weight verification of the target object, identifies the image category of each image, and obtains image category recognition results. The image category recognition results include a panoramic weighing image, a dial image and a waybill image. The dial image and the waybill image in the multiple images are judged for image quality to obtain a quality judgment result. Based on the image category recognition result and the quality judgment result, it is determined whether the uploaded image is compliant. If compliant, the compliant dial image is identified to obtain the dial reading, and the compliant waybill image is identified to obtain the waybill logo. Based on the waybill logo and the dial reading, the weight of the target object is verified, thereby realizing that only multiple images need to be taken and uploaded to automatically perform weight verification based on the uploaded multiple images. Moreover, by determining whether the uploaded image is compliant based on the image category recognition result and the quality judgment result, the compliance of the image can be accurately guaranteed, thereby improving the accuracy of weight verification.

[0134] Each module in the weight verification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software so that the processor can call and execute the corresponding operations of each module.

[0135] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7 . The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device can be used to store weight data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a weight verification method is implemented.

[0136] Those skilled in the art will understand that the structure shown in FIG7 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0137] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0138] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0139] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0140] It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all data authorized by the user or fully authorized by all parties.

[0141] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0142] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A weight verification method, the method comprising: Obtaining multiple uploaded images for weight verification of a target object; The multiple images are images collected during the weighing process of the target object; Identifying the image categories of each of the images to obtain an image category recognition result; the image category recognition result includes a weighing panoramic image, a dial image, and a waybill image; the weighing panoramic image is an image containing the overall picture of weighing the target object; the dial image is an image containing the dial of the scale being weighed; the waybill image is an image containing the waybill of the target object; Judging the image quality of the dial images and waybill images in the multiple images to obtain a quality judgment result; Determining whether the uploaded images are compliant according to the image category recognition result and the quality judgment result; If compliant, identifying the dial reading from the compliant dial image and identifying the waybill identifier from the compliant waybill image; Verifying the weight of the target object according to the waybill identifier and the dial reading.

2. The method according to claim 1, wherein the identifying the image categories of each of the images to obtain an image category recognition result includes: Performing image detection on each of the images respectively to obtain an image detection result of the image; The image detection result includes at least one of a weighing panorama, a dial, and a waybill; Determining the image category of the image according to the image detection result to obtain the image category recognition result of the image.

3. The method according to claim 2, wherein the determining the image category of the image according to the image detection result to obtain the image category recognition result of the image includes at least one of the following: If the image detection result contains both the weighing panorama and the dial, determining the image category of the image as a weighing panoramic image; If the image detection result only contains the dial and does not contain the weighing panorama and the waybill, determining the image category of the image as a dial image; If the image detection result only contains the waybill and does not contain the weighing panorama and the dial, determining the image category of the image as a waybill image.

4. The method according to claim 1, wherein the judging the image quality of the dial images and waybill images in the multiple images to obtain a quality judgment result includes: Inputting the dial images and waybill images in the multiple images into a pre-trained quality judgment model respectively to output a quality judgment result; Wherein, the quality judgment model is a classification model pre-trained based on positive samples and negative samples; the negative samples include samples obtained by performing motion blur processing on the positive samples.

5. The method according to any one of claims 1 to 4, wherein the determining whether the uploaded images are compliant according to the image category recognition result and the quality judgment result includes: If the image category recognition result indicates that the uploaded multiple images include a weighing panoramic image, a dial image, and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete, it is determined that the uploaded images are compliant.

6. The method according to any one of claims 1 to 4, wherein the rechecking the weight of the target object according to the waybill identifier and the dial reading comprises: comparing the waybill identifier with the waybill identifier corresponding to the target object recorded in the system; If the comparison of the waybill identifiers is consistent, then comparing the dial reading with the weight of the target object recorded in the system to obtain a weight recheck result.

7. The method according to any one of claims 1 to 4, wherein the determining whether the uploaded images are compliant according to the image category recognition result and the quality judgment result comprises: determining whether the uploaded images are compliant according to the image category recognition result and the quality judgment result to obtain a preliminarily compliant weighing panoramic image, dial image, and waybill image; After determining whether the uploaded images are compliant according to the image category recognition result and the quality judgment result, the method further comprises: extracting feature vectors from the image content corresponding to the dial area in the preliminarily compliant weighing panoramic image to obtain a first feature vector, and extracting feature vectors from the image content corresponding to the waybill area in the preliminarily compliant weighing panoramic image to obtain a second feature vector; extracting feature vectors from the image content corresponding to the dial area in the preliminarily compliant dial image to obtain a third feature vector; extracting feature vectors from the image content corresponding to the waybill area in the preliminarily compliant waybill image to obtain a fourth feature vector; calculating a first similarity between the first feature vector and the third feature vector, and a second similarity between the second feature vector and the fourth feature vector; According to the first similarity and the second similarity, performing an advanced compliance judgment on the preliminarily compliant images to obtain a compliant weighing panoramic image, dial image, and waybill image, executing recognizing the compliant dial image to obtain the dial reading, and recognizing the compliant waybill image to obtain the waybill identifier.

8. A weight rechecking device, the device comprising: an image acquisition module, configured to acquire multiple uploaded images for rechecking the weight of a target object; The multiple images are images acquired during the weighing process of the target object; an image category recognition module, configured to recognize the image category of each of the images to obtain an image category recognition result; the image category recognition result includes a weighing panoramic image, a dial image, and a waybill image; the weighing panoramic image is an image including the overall picture of weighing the target object; the dial image is an image including the dial of the scale being weighed; the waybill image is an image including the waybill of the target object; an image quality judgment module, configured to perform an image quality judgment on the dial image and the waybill image in the multiple images to obtain a quality judgment result; An image compliance judgment module, configured to determine whether the uploaded image is compliant according to the image category recognition result and the quality judgment result; A character recognition module, configured to, if compliant, recognize the dial indication number from the compliant dial image and recognize the waybill identifier from the compliant waybill image; A weight verification module, configured to verify the weight of the target object according to the waybill identifier and the dial indication number.

9. The device according to claim 8, wherein the image category recognition module is further configured to perform image detection on each of the images to obtain an image detection result of the image; the image detection result includes at least one of a weighing panorama, a dial, and a waybill; and determine the image category of the image according to the image detection result to obtain the image category recognition result of the image.

10. The device according to claim 9, wherein the image category recognition module is further configured to perform at least one of the following: if the image detection result includes both the weighing panorama and the dial, determine that the image category of the image is a weighing panorama image; if the image detection result only includes the dial and does not include the weighing panorama and the waybill, determine that the image category of the image is a dial image; if the image detection result only includes the waybill and does not include the weighing panorama and the dial, determine that the image category of the image is a waybill image.

11. The apparatus according to claim 8, wherein the image quality determination module is further configured to respectively input the dial image and the waybill image in the multiple images into a pre-trained quality determination model, and output a quality determination result; wherein, The quality judgment model is a classification model pre-trained based on positive samples and negative samples; the negative samples include samples obtained by performing motion blur processing on the positive samples.

12. The device according to any one of claims 8 to 11, wherein the image compliance judgment module is further configured to, if the image category recognition result indicates that the uploaded multiple images include a weighing panorama image, a dial image, and a waybill image, and the quality judgment result indicates that the image quality of the dial image and the waybill image is clear and the image content is complete, determine that the uploaded image is compliant.

13. The device according to any one of claims 8 to 11, wherein the weight verification module is further configured to compare the waybill identifier with the waybill identifier corresponding to the target object recorded in the system; if the waybill identifier comparison is consistent, compare the dial indication number with the weight of the target object recorded in the system to obtain a weight verification result.

14. The apparatus according to any one of claims 8 to 11, wherein the image compliance judgment module is further configured to determine whether the uploaded image is compliant according to the image category recognition result and the quality judgment result, so as to obtain a preliminarily compliant weighing panoramic image, dial image, and waybill image; extract feature vectors from the image content corresponding to the dial area in the preliminarily compliant weighing panoramic image to obtain a first feature vector, and extract feature vectors from the image content corresponding to the waybill area in the preliminarily compliant weighing panoramic image to obtain a second feature vector; extract feature vectors from the image content corresponding to the dial area in the preliminarily compliant dial image to obtain a third feature vector; extract feature vectors from the image content corresponding to the waybill area in the preliminarily compliant waybill image to obtain a fourth feature vector; calculate a first similarity between the first feature vector and the third feature vector, and a second similarity between the second feature vector and the fourth feature vector; perform an advanced compliance judgment on the preliminarily compliant images according to the first similarity and the second similarity, so as to obtain a compliant weighing panoramic image, dial image, and waybill image, execute the operation of identifying the compliant dial image to obtain the dial reading, and identify the compliant waybill image to obtain the waybill identifier.

15. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

16. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images