Product detection abnormal information generation system and method

Abstract

The invention relates to the technical field of product anomaly detection, in particular to a product detection anomaly information generation system and method.The system comprises a data acquisition module, a data configuration module, an anomaly detection module and a data reporting module.The data acquisition module is used for acquiring product production data; the data configuration module is used for pre-storing a product standard information association table; the anomaly detection module is used for performing detection according to the product production data and the product standard information association table to obtain product anomaly data; the data reporting module is used for sending product abnormal data to a data terminal, the data acquisition module and the data configuration module are electrically connected with the abnormity detection module, and the abnormity detection module is electrically connected with the data reporting module. According to the invention, the automatic generation and efficient management of the product detection abnormal information are realized, the accuracy and efficiency of product detection are improved, the requirements of manual editing and gathering of the abnormal information are reduced, and errors and delay caused by human factors are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of product anomaly detection. Specifically, it relates to a product detection anomaly information generation system and method. Background Art

[0002] In the field of intelligent manufacturing, the anomaly management of the production and manufacturing process is the core link to ensure production continuity, product quality, and cost control. The currently widely used manual anomaly information processing mode in the industry has significant technical bottlenecks.

[0003] Workshop anomalies involve multi-dimensional data (such as product name, work section, defect location, etc.). Manual entry is prone to errors and omissions, affecting the timeliness and accuracy of information feedback. Anomaly handling relies on manual reporting step by step, and multi-terminal real-time linkage cannot be achieved. Research shows that more than 60% of production downtime is due to information transmission delays. Although existing technologies can achieve anomaly alarms, they do not solve the problem that the standardized processing process still relies on manual filling of the "Anomaly Report Form", and there are defects such as fragmented information, poor accuracy, and low work efficiency. Summary of the Invention

[0004] In view of this, the present invention proposes a product detection anomaly information generation system and method, aiming to solve the problems existing in the current technology.

[0005] On the one hand, the present invention proposes a product detection anomaly information generation system, including a data acquisition module, a data configuration module, an anomaly detection module, and a data reporting module. Among them, the data acquisition module is used to acquire product production data; the data configuration module is used to pre-store a product standard information association table; the anomaly detection module is used to detect and obtain product anomaly data according to the product production data and the product standard information association table; the data reporting module is used to send the product anomaly data to a data terminal. The data acquisition module and the data configuration module are respectively electrically connected to the anomaly detection module, and the anomaly detection module is electrically connected to the data reporting module.

[0006] In some embodiments of the present application, the product production data includes the operator's department and the product image.

[0007] In some embodiments of the present application, the content storage format of the product standard information association table is production department - product type - product standard image - product partition location map.

[0008] In some embodiments of the present application, the data acquisition module includes a shooting unit and a data transceiver module. The shooting unit is used to shoot the product image after production is completed, and the data transceiver module is used to acquire the operator's department and the product image and send them to the anomaly detection module.

[0009] In some embodiments of the present application, the anomaly detection module includes a type determination module and an anomaly handling module; the type determination module is configured to compare the operator's department with the production department in the product standard information association table to determine the corresponding product type, and the anomaly determination module is configured to obtain the corresponding product standard image according to the corresponding product type, and compare the corresponding product standard image with the product image. When there is a discrepancy between the corresponding product standard image and the product image, the anomaly determination module determines an anomaly and marks the product image as an abnormal product image. When there is no discrepancy between the corresponding product standard image and the product image, it is determined that the product is qualified and the next product inspection is carried out.

[0010] In some embodiments of the present application, the anomaly detection module further includes a defective list integration module, which is configured to obtain the corresponding product partition point map according to the corresponding product standard image. The defective list integration module integrates the abnormal product image, the product standard image, and the corresponding product partition point map into a product defective list, and the content storage format of the product defective list is abnormal product image - product standard image - corresponding product partition point map.

[0011] In some embodiments of the present application, the anomaly detection module further includes an anomaly data transceiver module, which is configured to send the product defective list to the data processing center for image comparison, and receive the product anomaly data output by the data processing center and send it to the data reporting module.

[0012] In some embodiments of the present application, the product anomaly data includes the defective area and defective item with anomalies.

[0013] In some embodiments of the present application, when the data processing center performs image comparison and outputs product anomaly data, it includes: comparing the abnormal product image and the product standard image in the product defective list through visual recognition technology to obtain the defective items with anomalies, and comparing the abnormal product image and the corresponding product partition point map in the product defective list through visual recognition technology to obtain the defective areas with anomalies.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: First of all, a product inspection anomaly information generation system provided by the present invention realizes the automatic generation and efficient management of product inspection anomaly information by integrating data acquisition, configuration, detection, and reporting functions, significantly improving the accuracy and efficiency of product inspection, reducing the need for manual editing and summarizing anomaly information, and thus avoiding errors and delays caused by human factors.

[0015] Secondly, through detailed data configuration and an anomaly detection mechanism, this system can accurately identify and locate defective areas and items in products. This not only improves the accuracy of product detection but also provides strong data support for subsequent product improvement and quality control, helping to continuously optimize the production process and enhance product quality.

[0016] In addition, the data reporting module of this system ensures the timely transmission of anomaly information. Once a product anomaly is detected, the system can quickly send relevant information to the data terminal, facilitating rapid response and action by relevant departments. The timely information feedback mechanism helps enterprises quickly address problems in the production process, reduce the generation of defective products, and further improve overall production quality and efficiency.

[0017] In summary, the product detection anomaly information generation system of the present invention significantly improves the accuracy and efficiency of product detection through automated, precise, and efficient management methods, reduces the impact of human factors on detection results, provides strong support for subsequent product improvement and quality control, and ensures the timely transmission and rapid response of anomaly information, further enhancing overall production quality and efficiency.

[0018] On the other hand, the present invention also proposes a method for generating product detection anomaly information, including: S1: Pre-store the product standard information association table; S2: Obtain product production data; S3: Perform detection based on the product standard information association table in S1 and the product production data in S2 to obtain product anomaly data; S4: Send the product anomaly data in S3 to the data terminal.

[0019] It can be understood that the method for generating product detection anomaly information in this embodiment has the same beneficial effects as the above-mentioned product detection anomaly information generation system and will not be elaborated here. Description of the Drawings

[0020] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 is a structural block diagram of a product detection anomaly information generation system provided by an embodiment of the present invention; Figure 2 is a flowchart of a method for generating product detection anomaly information provided by an embodiment of the present invention. Detailed Embodiments

[0021] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] See also Figure 1 This embodiment provides a product detection anomaly information generation system proposed by the present invention, including a data acquisition module, a data configuration module, an anomaly detection module and a data reporting module, wherein the data acquisition module is used to acquire product production data; the data configuration module is used to pre-store a product standard information association table; the anomaly detection module is used to detect and acquire product anomaly data according to the product production data and the product standard information association table; the data reporting module is used to send the product anomaly data to a data terminal, the data acquisition module and the data configuration module are respectively electrically connected to the anomaly detection module, and the anomaly detection module is electrically connected to the data reporting module.

[0023] It is understandable that in this embodiment, by obtaining product production data, it is ensured that abnormal situations can be discovered and handled in time. Through the pre-stored product standard information association table, the system can detect product data in a standardized manner to ensure the consistency and accuracy of the detection process. The abnormal detection module can efficiently identify abnormal information from production data, reduce manual intervention, and improve detection efficiency. Once abnormal data is detected, the system can quickly report the information to the data terminal, so that relevant personnel can take timely measures. The data acquisition module and the data configuration module are electrically connected to the abnormal detection module, and the abnormal detection module is electrically connected to the data reporting module. Such a design makes the system structure clear and easy to maintain and upgrade. Through the comparison of accurate abnormal detection algorithms and standard information, the system can reduce false alarms and improve the accuracy of abnormal information. The abnormal data collected by the system can be used as decision support to help enterprises analyze the root causes of problems, optimize production processes, and improve product quality. The entire system, from data acquisition to abnormal detection to data reporting, achieves a high degree of automation, reduces labor costs, and improves work efficiency.

[0024] In a specific embodiment of the present application, the product production data includes an operator department and a product image.

[0025] In a specific embodiment of the present application, the content storage format of the product standard information association table is production department-product type-product standard image-product partition point map.

[0026] It can be understood that the collection of product production data in this embodiment includes the operator's department and product images, which helps in quality control during the product production process. The product standard information association table adopts a specific storage format, namely production department - product type - product standard image - product partition location map. The formatted storage method helps to quickly retrieve and match product standards, improving the efficiency and accuracy of anomaly detection.

[0027] In a specific embodiment of the present application, the data acquisition module includes a shooting unit and a data transceiver module. The shooting unit is used to capture product images after production is completed, and the data transceiver module is used to obtain the operator's department and product images and send them to the anomaly detection module.

[0028] Specifically, the shooting unit in this embodiment can be devices such as industrial cameras, intelligent cameras, 3D scanners, infrared thermal imagers, high-speed cameras, etc. The specific selection can be made according to the actual scenario, and this embodiment does not make specific limitations in this regard.

[0029] It can be understood that in this embodiment, the data acquisition module includes a shooting unit and a data transceiver module. The shooting unit is responsible for capturing high-definition product images after production is completed, while the data transceiver module is responsible for collecting operator's department information and product images, and sending this data to the anomaly detection module, ensuring the real-time and accuracy of the data, and providing a solid data foundation for subsequent anomaly detection and quality analysis.

[0030] In a specific embodiment of the present application, the anomaly detection module includes a type judgment module and an anomaly processing module; the type judgment module is used to compare with the production department in the product standard information association table according to the operator's department to determine the corresponding product type, and the anomaly judgment module is used to obtain the corresponding product standard image according to the corresponding product type, and compare the corresponding product standard image with the product image. When there is an inconsistency between the corresponding product standard image and the product image, the anomaly judgment module determines an anomaly and marks the product image as an abnormal product image. When there is no inconsistency between the corresponding product standard image and the product image, it is determined that the product is qualified, and the next product is detected.

[0031] It can be understood that in this embodiment, the anomaly detection module improves the detection efficiency and accuracy through the collaborative work of the type judgment module and the anomaly handling module. The type judgment module quickly determines the product type by comparing the department information of the operator with the production department in the product standard information association table, thereby providing an accurate reference basis for subsequent anomaly judgment. The anomaly judgment module then compares the obtained product standard image with the actual product image, and detects whether there are defects or non-compliance situations in the product through visual recognition technology. When it is found that the product image is inconsistent with the standard image, the anomaly judgment module can timely mark the abnormal product image, which is convenient for subsequent processing and analysis. This can not only reduce the workload of manual review, but also achieve automated detection, greatly improving the production efficiency and the level of product quality control.

[0032] In a specific embodiment of the present application, the anomaly detection module further includes a defective list integration module. The defective list integration module is used to obtain the corresponding product partition point map according to the corresponding product standard image. The defective list integration module integrates the abnormal product image, the product standard image, and the corresponding product partition point map into a product defective list. The content storage format of the product defective list is abnormal product image - product standard image - corresponding product partition point map.

[0033] It can be understood that in this embodiment, the integration module integrates the abnormal product image, the product standard image, and the product partition point map together to form a detailed and intuitive defective list, which helps to quickly identify and locate product defects, and improve the production efficiency and the accuracy of quality control.

[0034] Specifically, the product partition point map in this embodiment may specifically include a water ripple area point map, an OCABubble area point map, a scratch area point map, a LIPO area point map, a receiver area point map, a middle plate area point map, etc., so as to quickly locate the defective areas where different product defect types exist. The specific product partition point map can be divided according to the actual situation, and this embodiment does not make specific limitations on this.

[0035] In a specific embodiment of the present application, the anomaly detection module further includes an anomaly data transceiver module. The anomaly data transceiver module is used to send the product defective list to the data processing center for image comparison, and receive the product anomaly data output by the data processing center and send it to the data reporting module.

[0036] It can be understood that in this embodiment, the anomaly data transceiver module sends the product defective list to the data processing center and receives the product anomaly data output by the data processing center and sends it to the data reporting module, which can achieve the rapid identification and response to the product defective situation, and improve the production efficiency and the accuracy of product quality control.

[0037] In a specific embodiment of the present application, the product abnormal data includes abnormal defective areas and defective items.

[0038] In a specific embodiment of the present application, when the data processing center performs image comparison and outputs product abnormal data, it includes: comparing the abnormal product image in the product defect list with the product standard image through visual recognition technology to obtain the defective items with abnormalities, and comparing the abnormal product image in the product defect list with the corresponding product partition point map through visual recognition technology to obtain the defective areas with abnormalities.

[0039] Specifically, in this embodiment, when comparing through visual recognition technology to obtain the defective items with abnormalities, the following two solutions may be included: The first solution: Use a deep learning model (such as Siamese network, ResNet, YOLO series, etc.) to extract the feature vectors of the images, and calculate the similarity between the image to be detected and the standard image. Specifically, it includes: collecting the standard image and the abnormal image to construct a training data set; using a deep learning framework (such as TensorFlow, PyTorch) to train the image comparison model; extracting the feature vectors of the image to be detected and the standard image; calculating the similarity between the feature vectors through cosine similarity or Euclidean distance; if the similarity is lower than the preset threshold, it is determined as abnormal.

[0040] The second solution: Use traditional image processing algorithms (such as histogram comparison, template matching, PSNR, SSIM, etc.) to perform image comparison and determine whether there are differences. Specifically, it includes: performing normalization processing on the images (adjusting brightness, contrast, resolution); extracting the features of the images (such as color, texture, edges, etc.); calculating the differences between the image to be detected and the standard image through histogram comparison, template matching, etc.; if the difference exceeds the preset threshold, it is determined as abnormal.

[0041] Specifically, in this embodiment, when comparing through visual recognition technology to obtain the defective areas with abnormalities, the following two solutions may be included: The first solution: Use a superpixel segmentation algorithm (such as SLIC) to divide the image into multiple superpixel regions, and combine with the product partition point map to locate the different regions. Specifically, it includes: dividing the image to be detected and the partition point map into superpixel regions respectively; matching the superpixel regions of the image to be detected with the regions of the partition point map; locating the regions where the difference is greater than the preset threshold by calculating the similarity of the matching regions; marking the different regions on the image.

[0042] Second solution: Use a template matching algorithm (such as the matchTemplate function in OpenCV), take the partition bitmap as a template to locate the abnormal area in the image to be detected. Specifically, it includes: taking the partition bitmap as a template to extract the key area; sliding a window in the image to be detected to find the area that best matches the template; calculating the similarity of the matching area to locate the area where the difference is greater than the preset threshold; marking the difference area on the image.

[0043] It can be understood that in this embodiment, a dual comparison method is implemented, which not only improves the accuracy of abnormal detection but also helps to quickly locate the problem, providing strong support for subsequent problem-solving and product improvement. By collecting and analyzing abnormal situations that occur during product production or use, the problem can be quickly located, thereby improving product quality and production efficiency. At the same time, recording defective items helps to trace the source of the problem and provides data support for subsequent quality improvement and preventive measures.

[0044] Refer to Figure 2 , on the other hand, the present invention also proposes a method for generating abnormal information for product detection, including: S1: Pre-store the product standard information association table; S2: Obtain product production data; S3: Perform detection based on the product standard information association table in S1 and the product production data in S2 to obtain product abnormal data; S4: Send the product abnormal data in S3 to the data terminal.

[0045] Among them, the product production data includes the operator's department and the product image, and the content storage format of the product standard information association table is production department - product type - product standard image - product partition bitmap.

[0046] In step S3, it specifically includes: S31: Compare the operator's department with the production department in the product standard information association table to determine the corresponding product type; S32: Obtain the corresponding product standard image according to the corresponding product type, and compare the corresponding product standard image with the product image. When there is an inconsistency between the corresponding product standard image and the product image, the abnormal judgment module determines an abnormality and marks the product image as an abnormal product image. When there is no inconsistency between the corresponding product standard image and the product image, it is determined that the product is qualified and the next product detection is carried out.

[0047] S33: Obtain the corresponding product partition bitmap according to the corresponding product standard image, and integrate the abnormal product image, the product standard image, and the corresponding product partition bitmap into a product defect list.

[0048] Among them, the content storage format of the product defect list is abnormal product image - product standard image - corresponding product partition position map.

[0049] S34: Compare the abnormal product image and the product standard image in the product defect list through visual recognition technology to obtain the defective items with abnormalities; compare the abnormal product image in the product defect list and the corresponding product partition position map through visual recognition technology to obtain the defective areas with abnormalities.

[0050] Specifically, a method for generating abnormal information in product detection in this embodiment has the same beneficial effects as the above-mentioned system for generating abnormal information in product detection, and will not be elaborated here.

[0051] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0053] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps of the functions specified in one block or a plurality of blocks.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement without departing from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A product detection abnormality information generation system, characterized in that: It includes a data acquisition module, a data configuration module, an anomaly detection module and a data reporting module, wherein the data acquisition module is used to acquire product production data; the data configuration module is used to pre-store a product standard information association table; the anomaly detection module is used to detect and acquire product abnormal data according to the product production data and the product standard information association table; the data reporting module is used to send the product abnormal data to a data terminal, the data acquisition module and the data configuration module are electrically connected to the anomaly detection module respectively, and the anomaly detection module is electrically connected to the data reporting module.

2. A product detection abnormality information generation system according to claim 1, characterized in that: The product production data includes operator departments and product images.

3. A product detection abnormality information generation system according to claim 2, characterized in that: The content storage format of the product standard information association table is production department-product type-product standard image-product partition point map.

4. A product detection abnormality information generation system according to claim 3, characterized in that: The data acquisition module includes a shooting unit and a data transceiver module. The shooting unit is used to shoot images of products after production is completed. The data transceiver module is used to obtain operator departments and product images and send them to the abnormality detection module.

5. A product detection abnormality information generation system according to claim 4, characterized in that: The abnormality detection module includes a type judgment module and an abnormality handling module; the type judgment module is used to determine the corresponding product type by comparing the operator department with the production department in the product standard information association table; the abnormality judgment module is used to obtain the corresponding product standard image according to the corresponding product type, and compare the corresponding product standard image with the product image. When there is an inconsistency between the corresponding product standard image and the product image, the abnormality judgment module determines the abnormality and marks the product image as an abnormal product image. When there is no inconsistency between the corresponding product standard image and the product image, the product is determined to be qualified and the next product detection is carried out.

6. A product detection abnormality information generation system according to claim 5, characterized in that: The anomaly detection module also includes a defect list integration module, which is used to obtain a corresponding product partition point map based on the corresponding product standard image. The defect list integration module integrates the abnormal product image, the product standard image and the corresponding product partition point map into a product defect list. The content storage format of the product defect list is abnormal product image-product standard image-corresponding product partition point map.

7. A product detection abnormality information generation system according to claim 6, characterized in that: The abnormality detection module also includes an abnormality data transceiving module, which is used to send the product defect list to the data processing center for image comparison, and receive the product abnormality data output by the data processing center and send it to the data reporting module.

8. A product detection abnormality information generation system according to claim 7, characterized in that: The product abnormality data includes abnormal defective areas and defective items.

9. A product detection abnormality information generation system according to claim 8, characterized in that: When the data processing center performs image comparison and outputs product abnormality data, it includes: comparing the abnormal product image in the product defect list with the product standard image through visual recognition technology to obtain abnormal defective items, and comparing the abnormal product image in the product defect list with the corresponding product partition point map through visual recognition technology to obtain abnormal defective areas.

10. A method for generating product detection abnormality information, characterized in that: Applied to a product detection abnormality information generation system as claimed in any one of claims 1 to 9, specifically comprising the following steps: S1: pre-store product standard information association table; S2: Obtain product production data; S3: Perform detection to obtain product abnormality data according to the product standard information association table in S1 and the product production data in S2; S4: Send the product abnormality data in S3 to the data terminal.

Images