Material warehousing method and device, electronic equipment and storage medium
By combining QR code recognition of material packages with various image processing technologies, the problem of manual counting errors in the material receiving process has been solved, achieving a highly accurate material receiving process.
Patent Information
- Application Number
- CN202511224700.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-29
- Publication Date
- 2026-01-23
AI Technical Summary
During the material receiving process, due to the large quantity and variety of goods, manual counting is prone to errors, resulting in inaccurate receiving information.
By acquiring the target material package and delivery note QR code, the material type and quantity are obtained through QR code identification. Combining camera array, perspective image acquisition device and infrared thermal imaging array, package anomaly identification is performed, including damage, material counting and thermal anomaly identification. Anomaly confirmation is performed using a preset anomaly detection model and material knowledge graph. Finally, the material is put into storage based on the warehousing permit certification information.
This improves the accuracy of material receiving inspections, reduces human error, and ensures the accuracy and efficiency of material receiving.
Smart Images
Figure CN121391124A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of image processing, and in particular to a material warehousing method and device, an electronic device, and a storage medium. BACKGROUND
[0002] Material warehousing refers to a series of processes such as receiving and accepting materials after purchasing materials or goods, and the like. For example, after purchasing parts of a camera, a supplier delivers the materials according to the purchase order. After receiving the goods, the warehouse personnel will count the materials according to the purchase information. In the process of material warehousing, manual counting and inspection of the materials are usually performed. However, due to the large number of goods and the complex types of materials, manual counting is prone to errors, resulting in inaccurate warehousing information. Therefore, how to improve the inspection accuracy in the process of material warehousing and reduce human errors has become a problem to be solved. SUMMARY
[0003] The main purpose of the embodiments of the present application is to provide a material warehousing method and device, an electronic device, and a storage medium, which aims to improve the inspection accuracy in the process of material warehousing and reduce human errors.
[0004] To achieve the above-mentioned purpose, a first aspect of the embodiments of the present application provides a material warehousing method, which comprises:
[0005] obtaining a target material package and a target material delivery order; wherein the target material delivery order has a delivery order two-dimensional code;
[0006] performing two-dimensional code recognition on the delivery order two-dimensional code to obtain a target material type and a target material quantity;
[0007] performing package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain package anomaly information;
[0008] determining warehousing permission authentication information of the target material package according to the package anomaly information;
[0009] performing material warehousing on the target material package according to the warehousing permission authentication information.
[0010] In some embodiments, the package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain the package anomaly information comprises:
[0011] performing package damage recognition on the target material package to obtain package damage information;
[0012] performing material counting on the target material package according to the target material type and the target material quantity to obtain material counting information;
[0013] performing thermal anomaly identification on the target material package to obtain package thermal anomaly information;
[0014] performing anomaly confirmation according to the package damage information, the material counting information, the package thermal anomaly information, and a preset anomaly confirmation rule to obtain the package anomaly information.
[0015] In some embodiments, the performing package damage identification on the target material package to obtain package damage information comprises:
[0016] performing image shooting on the target material package through a preset camera array to obtain package outer packaging images;
[0017] performing anomaly detection on the package outer packaging images through a preset package anomaly detection model to obtain the package damage information.
[0018] In some embodiments, after the performing anomaly detection on the package outer packaging images through the preset package anomaly detection model to obtain the package damage information, the method further comprises:
[0019] performing character recognition on the package outer packaging images through a preset character recognition model to obtain outer packaging characters;
[0020] performing knowledge query on a preset material knowledge graph according to the target material type to obtain material embedding vectors;
[0021] performing vector embedding on the outer packaging characters to obtain character embedding vectors;
[0022] calculating similarity between the character embedding vectors and the material embedding vectors to obtain vector similarity;
[0023] if the vector similarity is less than a preset threshold, updating the package damage information.
[0024] In some embodiments, the performing material counting on the target material package according to the target material type and the target material quantity to obtain material counting information comprises:
[0025] performing scanning on the target material package through a preset perspective view collector to obtain material perspective images;
[0026] performing query on a preset database according to the target material type to obtain reference perspective views;
[0027] performing material counting on the target material package according to the material perspective images, the reference perspective views, and the target material quantity to obtain the material counting information.
[0028] In some embodiments, the inventorying the target material package according to the material perspective view, the reference perspective view and the target material quantity to obtain the inventorying information comprises:
[0029] performing target detection on the material perspective image to obtain at least one perspective sub-image;
[0030] calculating the similarity between each of the perspective sub-images and the reference perspective view to obtain the similarity of each of the perspective sub-images;
[0031] counting the perspective sub-images with the similarity greater than a preset similarity threshold to obtain a qualified material quantity;
[0032] if the qualified material quantity is the same as the target material quantity, determining that the inventorying information of the target material package is preset qualified information.
[0033] In some embodiments, the performing thermal anomaly recognition on the target material package to obtain package thermal anomaly information comprises:
[0034] performing image acquisition on the target material package through a preset infrared thermal imaging array to obtain a package thermal image;
[0035] performing image segmentation on the package thermal image to obtain a thermal sub-image;
[0036] comparing the thermal sub-image with a preset temperature threshold to determine the package thermal anomaly information.
[0037] To achieve the above-mentioned purposes, a second aspect of the embodiments of the present application proposes a material warehousing device, which comprises:
[0038] an acquisition data module configured to acquire a target material package and a target material delivery order; wherein the target material delivery order has a delivery order two-dimensional code;
[0039] a two-dimensional code recognition module configured to perform two-dimensional code recognition on the delivery order two-dimensional code to obtain a target material type and a target material quantity;
[0040] an anomaly recognition module configured to perform package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain package anomaly information;
[0041] an information determination module configured to determine warehousing permission authentication information of the target material package according to the package anomaly information;
[0042] a material warehousing module configured to perform material warehousing on the target material package according to the warehousing permission authentication information.
[0043] To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.
[0044] To achieve the above object, a fourth aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.
[0045] The material warehousing method and device, electronic device and storage medium provided by the present application can obtain a target material package and a target material delivery order, wherein the target material delivery order has a delivery order two-dimensional code, then perform two-dimensional code identification on the delivery order two-dimensional code to obtain a target material type and a target material quantity, then perform package anomaly identification on the target material package according to the target material type and the target material quantity to obtain package anomaly information, then determine warehousing permission authentication information of the target material package according to the package anomaly information, and finally perform material warehousing on the target material package according to the warehousing permission authentication information. In this way, the embodiments of the present application can accurately extract the type and quantity of the target material by identifying the two-dimensional code of the target material delivery order, and perform anomaly identification on the material package according to the information, thereby avoiding errors caused by manual counting and improving the accuracy and efficiency of material warehousing. BRIEF DESCRIPTION OF DRAWINGS
[0046] Figure 1 is a flowchart of the material warehousing method provided by the embodiments of the present application;
[0047] Figure 2 is Figure 1 a flowchart of step S103 in
[0048] Figure 3 is Figure 2 a flowchart of step S201 in
[0049] Figure 4 is a flowchart of the material warehousing method provided by another embodiment of the present application;
[0050] Figure 5 is Figure 2 a flowchart of step S202 in
[0051] Figure 6 is Figure 5 a flowchart of step S503 in
[0052] Figure 7 is Figure 2 a flowchart of step S203 in
[0053] Figure 8 is a structural schematic diagram of a material warehousing device provided by an embodiment of the present application;
[0054] Figure 9 is a hardware structure schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.
[0056] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.
[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.
[0058] First, the terms involved in the present application are analyzed:
[0059] Camera Array: A group of cameras arranged in a specific position and working cooperatively, usually used to take pictures of an object from multiple perspectives. Camera array is commonly used in pipeline applications for comprehensive scanning and detection of objects, which can take pictures from six surfaces of the object (front, back, left side, right side, top and bottom) simultaneously or in sequence. Through multi-angle image acquisition, it can provide a full view of the object, which is used for precise dimension measurement, defect detection, identification and classification, etc. Camera array is widely used in automated production lines, quality control, material tracking, etc. It can improve detection accuracy and efficiency, and reduce manual intervention.
[0060] Character Recognition Model: A model that utilizes computer vision and machine learning techniques to automatically recognize characters appearing in images. Character recognition models are commonly used to process handwritten or printed text, converting characters in images into a computer-readable text format. This model is an important branch of pattern recognition and image processing, widely applied in fields such as document digitization, automated input, license plate recognition, and bill identification. Character recognition models usually include feature extraction, classification, and post-processing steps, and common techniques include convolutional neural networks (CNN), recurrent neural networks (RNN), and traditional machine learning methods. Through training on a large number of sample data, character recognition models can gradually improve recognition accuracy and handle various font, noise, and deformation challenges.
[0061] Perspective Imaging Scanner: A device that uses X-ray technology to image objects, allowing users to clearly observe the internal structure and composition of objects without disassembly. Perspective imaging scanners emit X-rays and receive the rays that pass through the object, combining the signals captured by the detector to generate a two-dimensional perspective image of the object. This technology is commonly used in industrial detection, security checks, medical imaging, and other fields. In material storage, logistics transportation, and security checks, perspective imaging scanners are widely used to quickly identify whether there are foreign objects, defects, or dangerous goods inside the object. Perspective imaging scanners usually use high-sensitivity detectors, precise X-ray beam control, and imaging systems to provide high-quality images for further analysis and processing.
[0062] Infrared Thermal Imaging Array: A device that uses infrared technology to image the temperature distribution of objects, generating thermal images by capturing infrared radiation emitted by the object's surface. The infrared thermal imaging array is composed of multiple infrared sensors that can sense different wavelengths of infrared radiation and generate images based on temperature differences on the object's surface. Infrared thermal imaging arrays are widely used in industrial detection, building detection, electrical equipment maintenance, medical diagnosis, security monitoring, and other fields. In these applications, infrared thermal imaging arrays can help detect temperature anomalies in objects, such as overheating circuits, mechanical component wear, or human health abnormalities, providing accurate temperature distribution information and real-time analysis. Infrared thermal imaging technology does not rely on visible light, so it can effectively image in low-light or dark environments.
[0063] Material warehousing refers to a series of processes such as receiving and accepting materials sent by a supplier according to purchase information after purchasing materials or materials. For example, after purchasing the parts of a camera, the supplier sends the materials according to the purchase order. After receiving the goods, the warehouse personnel will count the materials according to the purchase information. During the material warehousing process, manual counting and inspection of the materials are usually performed. However, due to the large number of goods and the variety of materials, manual counting is prone to errors, resulting in inaccurate warehousing information. Therefore, how to improve the inspection accuracy in the material warehousing process and reduce human error has become a problem to be solved.
[0064] Based on this, the embodiment of the application provides a material warehousing method and device, an electronic device and a storage medium, aiming to improve the inspection accuracy in the material warehousing process and reduce human error.
[0065] The material warehousing method and device, the electronic device and the storage medium provided by the embodiment of the application are specifically explained by the following embodiments. First, the material warehousing method in the embodiment of the application is described.
[0066] The embodiment of the application can acquire and process related data based on artificial intelligence technology. Artificial intelligence (AI) is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0067] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. Artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.
[0068] The material warehousing method provided by the embodiment of the application relates to the field of image processing. The material warehousing method provided by the embodiment of the application can be applied in a terminal, can be applied in a server end, and can also be software running in a terminal or a server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as an independent physical server, can be configured as a server cluster or a distributed system composed of multiple physical servers, can also be configured as a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and basic cloud computing services such as big data and artificial intelligence platforms; the software can be an application that implements the material warehousing method, etc., but is not limited to the above forms.
[0069] The application is operable in a variety of general purpose or special purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations that can be suitable for use with the application include personal computers, server computers, handheld or laptop devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.
[0070] Figure 1 is an optional flowchart of the material warehousing method provided by the embodiment of the application, Figure 1 The method in the embodiment can include, but is not limited to, steps S101 to S105.
[0071] Step S101, obtaining a target material package and a target material delivery order; wherein the target material delivery order has a delivery order two-dimensional code;
[0072] Step S102, performing two-dimensional code recognition on the delivery order two-dimensional code to obtain a target material type and a target material quantity;
[0073] Step S103, performing package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain package anomaly information;
[0074] Step S104, determining warehousing permission authentication information of the target material package according to the package anomaly information;
[0075] Step S105, performing material warehousing on the target material package according to the warehousing permission authentication information.
[0076] The steps S101 to S105 shown in the embodiments of the present application are as follows: a target material package and a target material delivery note are obtained, wherein the target material delivery note has a delivery note two-dimensional code; then, the delivery note two-dimensional code is recognized to obtain a target material type and a target material quantity; then, the target material package is subjected to package anomaly recognition according to the target material type and the target material quantity to obtain package anomaly information; then, the storage permission authentication information of the target material package is determined according to the package anomaly information; and finally, the target material package is subjected to material storage according to the storage permission authentication information. In this way, the embodiments of the present application can accurately extract the type and quantity of the target material by recognizing the target material delivery note two-dimensional code, and can perform anomaly recognition on the material package according to the information, so as to avoid errors caused by manual counting and improve the accuracy and efficiency of material storage.
[0077] In step S101 of some embodiments, the target material package refers to a package containing camera-related accessories, such as camera lenses, batteries, sensor modules, etc. The target material delivery note refers to a document provided together with the material by the supplier when shipping according to the purchase order. The target material delivery note contains detailed information about the material, such as material type, quantity, and related logistics information, etc.
[0078] The delivery note two-dimensional code is the two-dimensional code information contained in the target material delivery note. The two-dimensional code contains detailed information of the material delivery note, such as material type, quantity, and supplier information, etc.
[0079] In step S102 of some embodiments, the two-dimensional code recognition is performed by scanning the delivery note two-dimensional code by a scanning device, such as a code scanning gun or a code scanning device. The target material type refers to the classification information of the target material, such as the type of camera accessories, such as lenses, sensors, batteries, etc. The target material quantity refers to the quantity of the target material.
[0080] Please refer to Figure 2 In some embodiments, step S103 can include but is not limited to steps S201 to S204:
[0081] Step S201, performing package damage recognition on the target material package to obtain package damage information;
[0082] Step S202, performing material counting on the target material package according to the target material type and the target material quantity to obtain material counting information;
[0083] Step S203, performing heat anomaly recognition on the target material package to obtain package heat anomaly information;
[0084] Step S204, performing anomaly confirmation according to the package damage information, the material counting information, the package heat anomaly information, and a preset anomaly confirmation rule to obtain package anomaly information.
[0085] The steps S201 to S204 shown in the embodiments of the present application perform package damage identification on the target material package to obtain package damage information; perform material counting on the target material package according to the target material type and the target material quantity to obtain material counting information; perform thermal anomaly identification on the target material package to obtain package thermal anomaly information; and perform anomaly confirmation according to the package damage information, the material counting information, the package thermal anomaly information, and a preset anomaly confirmation rule to obtain package anomaly information. In this way, the embodiments of the present application can comprehensively identify the anomaly of the material package by performing package damage identification, material counting, and thermal anomaly identification on the target material package in combination with the preset anomaly confirmation rule, thereby improving the accuracy and comprehensiveness of the material package anomaly detection.
[0086] Please refer to Figure 3 In some embodiments, the step S201 can include but is not limited to steps S301 to S302:
[0087] In step S301, a preset camera array is used to capture images of the target material package to obtain package outer packaging images.
[0088] In step S302, a preset package anomaly detection model is used to perform anomaly detection on the package outer packaging images to obtain package damage information.
[0089] The steps S301 to S302 shown in the embodiments of the present application use a preset camera array to capture images of the target material package to obtain package outer packaging images, and use a preset package anomaly detection model to perform anomaly detection on the package outer packaging images to obtain package damage information. In this way, the embodiments of the present application use a camera array to capture images of the target material package, and use a package anomaly detection model to detect the captured package outer packaging images, thereby solving the problem of missing in manual inspection and improving the accuracy and efficiency of package damage detection.
[0090] In step S301 of some embodiments, the target material package is usually placed on an acrylic transmission plate during transportation. The camera array is arranged at multiple positions of the transmission plate and can capture six faces of the target material package from different angles at the same time.
[0091] In step S302 of some embodiments, the package anomaly detection model is used to process and analyze the captured package outer packaging images to determine whether there is any anomaly such as damage in the images. The package anomaly detection model can be a pre-trained convolutional neural network. By inputting the package outer packaging images, the package anomaly detection model can automatically detect and identify damage, stains, or indentations in the package images.
[0092] The package damage information refers to the specific location and quantity statistics of the package abnormal area obtained by the anomaly detection model. For example, the package damage information includes the coordinates of each damage location and the number of damages. For example, the model detects that the first face of the package has a damage at coordinates (X1, Y1), the second face has a damage at coordinates (X2, Y2), and a total of N number of package damages are detected.
[0093] Referring to Figure 4 In some embodiments, step S302 can further include, but is not limited to, steps S401 to S405:
[0094] Step S401, performing character recognition on the package outer packaging image by a preset character recognition model to obtain outer package characters;
[0095] Step S402, performing knowledge query on the preset material knowledge graph according to the target material type to obtain a material embedding vector;
[0096] Step S403, performing vector embedding on the outer package characters to obtain a character embedding vector;
[0097] Step S404, calculating the similarity between the character embedding vector and the material embedding vector to obtain a vector similarity;
[0098] Step S405, if the vector similarity is less than a preset threshold, updating the package damage information.
[0099] The steps S401 to S405 shown in the embodiments of the present application perform character recognition on the package outer packaging image, query the material knowledge graph according to the material type, and thus generate a corresponding embedding vector for the character information of the package. Then, by calculating the similarity between the character embedding vector and the material embedding vector, the consistency between the outer packaging characters and the material type can be compared. If the similarity is lower than the preset threshold, it is considered that the package may have an anomaly, and the package damage information is updated. In this way, the embodiments of the present application realize effective matching and verification between the character information and the material type by combining character recognition and material embedding vector calculation, and further improve the accuracy of the package damage information.
[0100] In step S401 of some embodiments, the character recognition model is a model that extracts and recognizes character information from an image. A common character recognition model can be a convolutional neural network (CNN) or an ORC model. The outer package characters refer to the text information on the package outer packaging image, such as material number, barcode, supplier information, delivery address, etc. For example, for a package of camera-related accessories, the outer package characters can include "lens 001", "sensor XYZ", etc.
[0101] In step S402 of some embodiments, the material knowledge graph is a structured database for storing material information, including detailed attributes, categories, characteristics, and other data of different materials. Through the material knowledge graph, the information of a specific material type can be queried, including the classification, specifications, purposes, suppliers, and other related information of the material.
[0102] Knowledge query refers to searching in the material knowledge graph according to the target material type, so as to obtain information related to the material type. For example, the target material type is a photoelectric sensor, and after knowledge query, a series of information including the type, model, supplier, and other information of the photoelectric sensor can be obtained.
[0103] The material embedding vector is a vector obtained after knowledge query, reflecting various characteristic information of the material. For example, the material embedding vector of the photoelectric sensor may include high-dimensional representations of the model, purpose, brand, and other characteristics of the sensor.
[0104] In step S403 of some embodiments, vector embedding is the conversion of the outer wrapping character into a vector shape. A pre-trained embedding model such as Word2Vec or BERT can be used.
[0105] In step S404 of some embodiments, similarity refers to the matching degree between the character embedding vector and the material embedding vector by calculation. In one embodiment, the character embedding vector is obtained by calculating the matching degree between the character embedding vector and the material embedding vector in advance.
[0106] In step S405 of some embodiments, if the vector similarity obtained by calculation is lower than the preset threshold, it means that the matching degree between the character information on the outer package and the target material type is not high, which may be caused by label error, material information error, or other problems. For example, assuming that the target material type is "photoelectric sensor", and the outer wrapping character on the package is "camera lens". It means that the character on the outer wrapping of the package does not match the target material type, and the package may have problems such as material identification error or damage. Then it is determined that the package damage information is: package error.
[0107] Please refer to Figure 5 In some embodiments, step S202 includes but is not limited to steps S501 to S503:
[0108] Step S501, scanning the target material package by a preset perspective view collector to obtain a material perspective image;
[0109] Step S502, querying a preset database according to the target material type to obtain a reference perspective view;
[0110] In step S503, the target material package is counted according to the material perspective view, the reference perspective view and the target material quantity, and material counting information is obtained.
[0111] The steps S501 to S503 shown in the embodiments of the present application are used to scan the target material package by using a perspective view collector to obtain a material perspective image. According to the target material type, a reference perspective view is obtained by querying a preset database. By comparing the material perspective image with the reference perspective view and combining the target material quantity, the target material package is counted to obtain accurate material counting information, so that the counting of the material can be realized without opening the package.
[0112] In step S501 of some embodiments, it should be noted that the products in the target material package should be arranged in a single layer. For example, the products in the target material package are arranged in N*M*K, where N, M and K are three dimensions of the material arrangement, and at least one of N, M or K is 1. Next, the perspective view collector is used to scan the target material package from X, Y and Z directions to obtain perspective images from the three directions. Then, an image showing the target material in the target material package without overlapping is selected as the material perspective image.
[0113] For example, the target material in the material perspective image is arranged in 2*3*1, that is, two in the X direction, three in the Y direction and one layer in the Z direction, and then the perspective view of the Z axis is selected as the material perspective image.
[0114] In step S502 of some embodiments, specifically comprising:
[0115] The shooting angle of the target material in the material perspective image is obtained.
[0116] The database is queried according to the target material type to obtain a three-dimensional structure diagram corresponding to the target material.
[0117] The three-dimensional structure diagram corresponding to the target material is image-acquired according to the shooting angle of the target material to obtain a two-dimensional structure diagram.
[0118] The two-dimensional structure diagram is perspective-processed to obtain a reference perspective view.
[0119] For example, it is assumed that the target material is a camera lens module and the shooting angle is 30 degrees. After querying the database according to the material type, a three-dimensional structure diagram of the camera lens module is obtained. Then, the three-dimensional structure diagram is image-acquired according to the shooting angle of 30 degrees to obtain a two-dimensional structure diagram of the material. After obtaining the two-dimensional structure diagram, perspective processing is performed to finally obtain a reference perspective view.
[0120] It should be noted that in the same batch of materials, the arrangement of the materials can be in multiple situations, and the actual arrangement of the materials can be iterated multiple times, so as to count each material. For example, in the first iteration, the material arranged at 30 degrees is counted, and in the second iteration, the material arranged at 50 degrees is counted.
[0121] Please refer to Figure 6 In some embodiments, step S503 includes but is not limited to steps S601 to S604:
[0122] Step S601, target detection is performed on the material perspective image to obtain at least one perspective sub-image;
[0123] Step S602, the similarity between each perspective sub-image and the reference perspective view is calculated to obtain the similarity of each perspective sub-image;
[0124] Step S603, the perspective sub-images with a similarity greater than a preset similarity threshold are counted to obtain the number of qualified materials;
[0125] Step S604, if the number of qualified materials is the same as the number of target materials, it is determined that the material counting information of the target material package is the preset qualified information.
[0126] The steps S601 to S604 shown in the embodiments of the present application perform target detection on the material perspective image to obtain at least one perspective sub-image; calculate the similarity between each perspective sub-image and the reference perspective view to obtain the similarity of each perspective sub-image; count the perspective sub-images with a similarity greater than a preset similarity threshold to obtain the number of qualified materials; and if the number of qualified materials is the same as the number of target materials, it is determined that the material counting information of the target material package is the preset qualified information. In this way, the embodiments of the present application realize effective counting of the packaged materials by performing target detection on the material perspective image, calculating the similarity between the perspective sub-image and the reference perspective view, and then counting the number of perspective sub-images with a similarity greater than a preset threshold, thereby solving the problem of difficult material counting in the case of external packaging.
[0127] In step S601 of some embodiments, target detection refers to identifying the specific position of each material in the image. The implementation of target detection is as follows: first, a deep learning model such as a convolutional neural network (CNN) is used to process the material perspective image, automatically identify each material, and generate a corresponding bounding box. For example, for the perspective image of the camera lens module, each lens module in it is identified and its position is marked with a rectangular box. The perspective sub-image is the sub-region of each detected material cut from the material perspective image after target detection.
[0128] In step S602 of some embodiments, edge features in the perspective sub-image and the reference perspective image are first identified by an edge detection algorithm. Then, the similarity value is obtained by calculating the edge matching degree between the perspective sub-image and the reference perspective image, for example, based on cosine similarity or normalized cross-correlation method.
[0129] In step S603 of some embodiments, the number of perspective sub-images with similarity greater than a preset similarity threshold is counted to determine whether the material in the target material package meets the predetermined quality standard. If the similarity of a certain perspective sub-image is higher than the set threshold, it is considered that the material represented by the perspective sub-image is qualified.
[0130] In step S604 of some embodiments, when the number of qualified materials obtained by counting is the same as the number of target materials, it is determined that the material counting information of the target material package is the preset qualified information. If the number of qualified materials does not match the number of target materials, it means that there is a material loss or material damage, which can be counted on one hand and the quality of the target material on the other hand.
[0131] Please refer to Figure 7 In some embodiments, step S203 can include but is not limited to steps S701-S703:
[0132] Step S701, image acquisition of the target material package is performed by a preset infrared thermal imaging array to obtain a package thermal image;
[0133] Step S702, image segmentation is performed on the package thermal image to obtain a thermal sub-image;
[0134] Step S703, comparison is made between the thermal sub-image and a preset temperature threshold to determine the package thermal anomaly information.
[0135] The steps S701-S703 shown in the embodiments of the present application perform thermal image acquisition of the target material package by using a preset infrared thermal imaging array, perform image segmentation on the acquired thermal image to obtain a thermal sub-image, and then compare the thermal sub-image with a preset temperature threshold to determine the package thermal anomaly information, thereby identifying the thermal anomaly of the package material.
[0136] In step S701 of some embodiments, the infrared thermal imaging array acquires the thermal image of the target material package by emitting infrared rays and receiving infrared radiation reflected from the surface of the material package.
[0137] In step S702 of some embodiments, the implementation method of image segmentation is the watershed algorithm, which divides different temperature regions in the thermal image into a plurality of sub-regions, i.e., thermal sub-images, thereby segmenting the package thermal image and identifying the temperature change of each region on the surface of the material package.
[0138] In step S703 of some embodiments, by comparing the obtained thermal sub-image with the preset temperature threshold, it can be judged which area has abnormal temperature change. If the temperature value of the thermal sub-image exceeds the preset high temperature threshold, it is determined that there is a thermal abnormal problem. If the temperature value of the thermal sub-image is lower than the preset low temperature threshold, it is determined that there is a thermal abnormal problem.
[0139] It should be noted that in the camera material warehousing, if the temperature value of the thermal sub-image exceeds the preset high temperature threshold, it may indicate that the battery inside the material package has a leakage or short circuit condition, resulting in excessive heat generated by the battery. For example, the battery may leak due to external force or quality problems during transportation or storage, thereby causing overheating. Through monitoring of the thermal image.
[0140] On the other hand, if the temperature value of the thermal sub-image is lower than the preset low temperature threshold, it may indicate that the camera material has a water problem, resulting in abnormal temperature drop inside the camera. For example, the camera may be damaged or poorly sealed during logistics transportation, which may cause water to penetrate, thereby affecting the normal temperature state of the camera.
[0141] In step S204 of some embodiments, when the package damage information, the material inventory information and the package thermal abnormal information are all normal, the package abnormal information is determined to be normal according to the preset abnormality confirmation rule, otherwise it is determined to be abnormal.
[0142] In step S104 of some embodiments, the warehouse permission authentication information indicates that the package can be successfully warehoused.
[0143] Referring to Figure 8 The embodiments of the present application also provide a material warehousing device, which can implement the above-mentioned material warehousing method. The device comprises:
[0144] The data acquisition module 801 is configured to acquire a target material package and a target material delivery note. The target material delivery note has a delivery note two-dimensional code.
[0145] The two-dimensional code identification module 802 is configured to perform two-dimensional code identification on the delivery note two-dimensional code to obtain a target material type and a target material quantity.
[0146] The abnormality identification module 803 is configured to perform package abnormality identification on the target material package according to the target material type and the target material quantity to obtain package abnormality information.
[0147] The information determination module 804 is configured to determine warehouse permission authentication information of the target material package according to the package abnormality information.
[0148] The material warehousing module 805 is configured to perform material warehousing on the target material package according to the warehousing permission authentication information.
[0149] The specific implementation of the material warehousing device is basically the same as the specific implementation of the above-mentioned material warehousing method, and will not be repeated here.
[0150] The embodiments of the present application also provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above-mentioned material warehousing method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.
[0151] Please refer to Figure 9 , Figure 9 The hardware structure of the electronic device of another embodiment is illustrated, which includes:
[0152] The processor 901 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., and is used to execute related programs to implement the technical solutions provided by the embodiments of the present application.
[0153] The memory 902 can be implemented in the form of a ROM (ReadOnly Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), etc. The memory 902 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 902 and are called and executed by the processor 901 to implement the material warehousing method of the embodiments of the present application.
[0154] The input / output interface 903 is used to realize information input and output.
[0155] The communication interface 904 is used to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).
[0156] The bus 905 is used to transmit information between various components (for example, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904) of the device.
[0157] The processor 901, the memory 902, the input / output interface 903, and the communication interface 904 are communicatively connected with each other through the bus 905.
[0158] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the material warehousing method.
[0159] The memory is a non-transitory computer readable storage medium, and can be used to store a non-transitory software program and a non-transitory computer executable program. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and the remote memory can be connected to the processor through a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.
[0160] The material warehousing method, the material warehousing device, the electronic device, and the storage medium provided by the embodiment of the present application obtain a target material package and a target material delivery order, wherein the target material delivery order has a delivery order two-dimensional code; then, the delivery order two-dimensional code is identified to obtain a target material type and a target material quantity; then, the target material package is identified for package abnormality according to the target material type and the target material quantity, to obtain package abnormality information; then, the warehousing permission authentication information of the target material package is determined according to the package abnormality information; finally, the target material package is warehoused according to the warehousing permission authentication information. In this way, the embodiment of the present application identifies the target material delivery order two-dimensional code, accurately extracts the type and quantity of the target material, and identifies the material package for abnormality according to the information, thereby avoiding errors caused by manual counting, and improving the accuracy and efficiency of material warehousing.
[0161] The embodiments described in the embodiment of the present application are used to more clearly illustrate the technical solutions of the embodiment of the present application, and do not constitute a limitation on the technical solutions provided by the embodiment of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiment of the present application are also applicable to similar technical problems.
[0162] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiment of the present application, and can include more or fewer steps than the figures, or combine certain steps, or different steps.
[0163] The apparatus embodiments described above are merely exemplary, and the units described as separate units can or can not be physically separate, i.e., can be located in one place, or can be distributed over multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.
[0164] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and appropriate combinations thereof.
[0165] The terms "first", "second", "third", "fourth" and the like in the description of the application and in the claims of the foregoing drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so
[0166] It should be understood that in this application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that there are three cases: only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents that the associated objects before and after are a "or" relationship. "At least one of the following" or the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c, can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.
[0167] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are merely illustrative, for example, the division of the above units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.
[0168] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they can be located in one place or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
[0169] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.
[0170] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that makes a contribution or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.
[0171] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, but this does not limit the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.
Claims
1. A method of storing material, characterized by, The method comprises: acquiring a target material package and a target material delivery order; wherein the target material delivery order has a delivery order two-dimensional code; performing two-dimensional code recognition on the delivery order two-dimensional code to obtain a target material type and a target material quantity; performing package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain package anomaly information; determining warehouse entry permission authentication information of the target material package according to the package anomaly information; performing material warehousing on the target material package according to the warehouse entry permission authentication information.
2. The method of claim 1, wherein, The package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain the package anomaly information comprises: performing package damage recognition on the target material package to obtain package damage information; performing material inventory on the target material package according to the target material type and the target material quantity to obtain material inventory information; performing thermal anomaly recognition on the target material package to obtain package thermal anomaly information; performing anomaly confirmation according to the package damage information, the material inventory information, the package thermal anomaly information, and a preset anomaly confirmation rule to obtain the package anomaly information.
3. The method of claim 1, wherein, The package damage recognition on the target material package to obtain the package damage information comprises: performing image shooting on the target material package through a preset camera array to obtain package outer packaging images; performing anomaly detection on the package outer packaging images through a preset package anomaly detection model to obtain the package damage information.
4. The method of claim 3, wherein, After the anomaly detection on the package outer packaging images through the preset package anomaly detection model to obtain the package damage information, the method further comprises: performing character recognition on the package outer packaging images through a preset character recognition model to obtain outer packaging characters; performing knowledge query on a preset material knowledge graph according to the target material type to obtain a material embedding vector; performing vector embedding on the outer packaging characters to obtain a character embedding vector; calculating a similarity between the character embedding vector and the material embedding vector to obtain a vector similarity; if the vector similarity is less than a preset threshold, updating the package damage information.
5. The method of claim 1, wherein, The material inventory on the target material package according to the target material type and the target material quantity to obtain the material inventory information comprises: performing scanning on the target material package through a preset perspective view collector to obtain material perspective images; performing query on a preset database according to the target material type to obtain reference perspective views; performing material inventory on the target material package according to the material perspective images, the reference perspective views, and the target material quantity to obtain the material inventory information.
6. The method of claim 5, wherein, The material inventory on the target material package according to the material perspective images, the reference perspective views, and the target material quantity to obtain the material inventory information comprises: performing target detection on the material perspective images to obtain at least one perspective sub-image; calculating a similarity between each of the perspective sub-images and the reference perspective views to obtain a similarity of each of the perspective sub-images; and The perspective sub-images with a statistical similarity greater than a preset similarity threshold are obtained to obtain a qualified material quantity; If the qualified material quantity is the same as the target material quantity, it is determined that the material counting information of the target material package is preset qualified information.
7. The method of claim 2, wherein, The target material package is subjected to thermal anomaly recognition to obtain package thermal anomaly information, including: An infrared thermal imaging array is used to collect images of the target material package to obtain a package thermal image; The package thermal image is subjected to image segmentation to obtain a thermal sub-image; The thermal sub-image is compared with a preset temperature threshold to determine the package thermal anomaly information.
8. A material storing device characterized by comprising: The device includes: An acquisition data module is configured to acquire a target material package and a target material delivery order, wherein the target material delivery order has a delivery order two-dimensional code; A two-dimensional code recognition module is configured to perform two-dimensional code recognition on the delivery order two-dimensional code to obtain a target material type and a target material quantity; An anomaly recognition module is configured to perform package anomaly recognition on the target material package according to the target material type and the target material quantity to obtain package anomaly information; An information determination module is configured to determine storage permission authentication information of the target material package according to the package anomaly information; A material storage module is configured to store the target material package according to the storage permission authentication information.
9. An electronic device, comprising: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the material storage method in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. The computer program is executed by the processor to implement the material storage method in any one of claims 1 to 7.