Intelligent quality inspection method and system for intelligent production of security and protection equipment

Abstract

The invention discloses an intelligent quality inspection method and system for intelligent production of security and protection equipment. The method comprises the following steps: acquiring product image information; preprocessing the product image information to obtain target processing image information; and performing detection analysis processing on the target processing image information by using the target quality inspection analysis model to obtain target quality inspection result information. According to the invention, the obtained product image information is analyzed and processed for automatic intelligent quality inspection of the product, so that the quality inspection accuracy is effectively improved, the application range is effectively widened, the quality inspection efficiency is improved, and the labor intensity of operators is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection, and in particular to an intelligent quality inspection method and system for intelligent production of security equipment. Background Art

[0002] With the rapid development of the security equipment industry, product quality requirements are getting higher and higher, especially under the trend of intelligent and automated production, which puts forward higher requirements for quality control in the production process. In the traditional production process of security equipment, quality inspection mainly relies on manual visual inspection. This method has the following problems: low efficiency, slow manual inspection speed, and cannot meet the needs of large-scale and high-efficiency production; insufficient accuracy, manual inspection is easily affected by subjective factors, resulting in misjudgment and missed judgment, affecting product quality; high cost, with the increase of labor costs, the cost of manual inspection gradually increases, which is not conducive to the long-term development of enterprises; difficult to trace: manual inspection lacks effective data recording and analysis, and it is difficult to trace and analyze problems in the production process. Therefore, an intelligent quality inspection method and system for intelligent production of security equipment is provided to adapt to the changing production environment, accurately identify and handle various complex product defect problems, improve the efficiency and accuracy of product quality inspection, and thus improve the production efficiency and product quality of security equipment. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent quality inspection method and system for the intelligent production of security equipment, which is conducive to adapting to the changing production environment, accurately identifying and processing various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0004] In order to solve the above technical problems, the first aspect of the embodiment of the present invention discloses an intelligent quality inspection method for intelligent production of security equipment, the method comprising:

[0005] Get product image information;

[0006] Preprocessing the product image information to obtain target processed image information;

[0007] The target quality inspection analysis model is used to detect and analyze the target processing image information to obtain target quality inspection result information.

[0008] A second aspect of an embodiment of the present invention discloses an intelligent quality inspection system for intelligent production of security equipment, the system comprising:

[0009] An acquisition module, used to acquire product image information;

[0010] A first processing module, used for preprocessing the product image information to obtain target processed image information;

[0011] The second processing module is used to use the target quality inspection analysis model to detect and analyze the target processing image information to obtain target quality inspection result information.

[0012] The third aspect of the present invention discloses another intelligent quality inspection system for intelligent production of security equipment, the system comprising:

[0013] A memory storing executable program code;

[0014] a processor coupled to the memory;

[0015] The processor calls the executable program code stored in the memory to execute part or all of the steps in the intelligent quality inspection method for intelligent production of security equipment disclosed in the first aspect of the embodiment of the present invention.

[0016] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the intelligent quality inspection method for intelligent production of security equipment disclosed in the first aspect of an embodiment of the present invention.

[0017] Due to the application of the above technical solution, the present invention has the following advantages compared with the prior art:

[0018] 1. The method and system of the present invention are suitable for different production environments, can accurately identify and process various complex product defect problems through images, improve the efficiency and accuracy of product quality inspection, improve the production efficiency and product quality of security equipment, and can also effectively reduce the labor intensity of operators and reduce labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a schematic diagram of a scenario of an intelligent quality inspection system for intelligent production of security equipment provided by an embodiment of the present invention;

[0021] Figure 2 It is a flow chart of an intelligent quality inspection method for intelligent production of security equipment disclosed in an embodiment of the present invention;

[0022] Figure 3 It is a structural schematic diagram of an intelligent quality inspection system for intelligent production of security equipment disclosed in an embodiment of the present invention;

[0023] Figure 4 It is a structural schematic diagram of another intelligent quality inspection system for intelligent production of security equipment disclosed in an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of a target quality inspection analysis model disclosed in an embodiment of the present invention.

[0025] Figure 6 This is a schematic diagram of the structure of a first feature extraction module disclosed in an embodiment of the present invention.

[0026] Figure 7 This is a schematic diagram of the structure of a first feature analysis module disclosed in an embodiment of the present invention.

[0027] Figure 8 It is a structural schematic diagram of a second feature analysis module disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0030] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0031] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0032] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data for processing by the computer device. The details will not be repeated here.

[0033] It should be noted that the artificial intelligence related technologies that may be involved in this application are briefly described. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0034] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0035] Computer Vision (CV) is a science that studies how to make machines "see". To put it more specifically, it refers to machine vision such as using cameras and computers to replace human eyes to identify and measure targets, and further perform graphic processing so that computer processing becomes an image that is more suitable for human eye observation or transmission to instrument detection. As a scientific discipline, computer vision studies related theories and technologies, and attempts to establish an artificial intelligence system that can obtain information from images or multi-dimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous positioning and map construction, and other technologies, as well as common biometric recognition technologies such as face recognition and fingerprint recognition.

[0036] Unimodal information is data of only one type, such as text, image, audio, video, electromagnetic signal, etc. Multimodal information is data that includes at least two types of unimodal information. Furthermore, multimodal information is suitable for complex tasks that require the integration of multiple information sources, such as sentiment analysis, robot interaction, autonomous driving, etc. By integrating information from multiple modalities, higher performance and accuracy can usually be achieved on the task.

[0037] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model generally refers to a model with hundreds of millions to trillions of parameters. Models usually need to be trained on large-scale data sets and require a large amount of computing resources to be optimized and adjusted. Large models are often used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is an AI that can create new content and ideas, including conversations, stories, images, videos, and music. In an embodiment of the present application, the large model may be ChatGPT, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Tongwen Qianyi model, MiniMax model, Spark model, Llama model, 360GPT model, Qwen model, Baichuan model, Skylark model, vivoLM model, and Wenxin Yiyan scale language models, which are not limited in the embodiments of the present application.

[0038] The embodiments of the present application provide an intelligent quality inspection method, system, computer device and computer-readable storage medium for intelligent production of security equipment, which are described in detail below.

[0039] See also Figure 1 , Figure 1Schematic diagram of a scenario of an intelligent quality inspection system for intelligent production of security equipment provided in an embodiment of the present application. The intelligent quality inspection system for intelligent production of security equipment may include a computer device 100, in which the intelligent quality inspection system for intelligent production of security equipment is integrated, such as Figure 1 Computer equipment in.

[0040] In the embodiment of the present application, the computer device 100 is mainly used to obtain product image information;

[0041] Preprocess product image information to obtain target processed image information;

[0042] The target quality inspection analysis model is used to detect and analyze the target processing image information to obtain the target quality inspection result information.

[0043] It can adapt to changing production environments, accurately identify and handle various complex product defect problems, improve the efficiency and accuracy of product quality inspection, and thus improve the production efficiency and product quality of security equipment.

[0044] In the embodiment of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiment of the present application includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of a plurality of servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0045] It is understandable that the computer device 100 used in the embodiments of the present application may be a device including both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The specific computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may also be one of a mobile phone, a tablet computer, a laptop computer, etc.

[0046] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less computer equipment as shown in Figure 1 Only one computer device is shown. It can be understood that the intelligent quality inspection system for intelligent production of security equipment can also include one or more other services, which are not specifically limited here.

[0047] In addition, if Figure 1 As shown, the intelligent quality inspection system for intelligent production of security equipment may also include a memory 200 for storing data, such as image data, location information, etc.

[0048] It should be noted that Figure 1 The scenario diagram of the intelligent quality inspection system for the intelligent production of security equipment shown is merely an example. The intelligent quality inspection system and scenario for the intelligent production of security equipment described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the intelligent quality inspection system for the intelligent production of security equipment and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0049] The present invention discloses an intelligent quality inspection method and system for intelligent production of security equipment, which is conducive to adapting to the changing production environment, accurately identifying and processing various complex product defects, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment. The following are detailed descriptions.

[0050] Embodiment 1

[0051] See also Figure 2 , Figure 2 The figure is a flow chart of an intelligent quality inspection method for intelligent production of security equipment disclosed in an embodiment of the present invention. Figure 2 The described intelligent quality inspection method for intelligent production of security equipment is applied to a management system, such as a local server or a cloud server for management, and the embodiments of the present invention are not limited thereto. Figure 2 As shown, the intelligent quality inspection method for intelligent production of security equipment may include the following operations:

[0052] 101. Obtain product image information.

[0053] 102. Preprocess the product image information to obtain target processed image information.

[0054] 103. Use the target quality inspection analysis model to detect and analyze the target processing image information to obtain the target quality inspection result information.

[0055] It should be noted that the above-mentioned product image information is obtained by taking high-definition photos of components (such as doors, rotating pairs, etc.) of financial security equipment, and the embodiments of the present invention do not limit this.

[0056] It should be noted that the above-mentioned target quality inspection result information represents the quality inspection test results of the components of the financial security equipment, which is not limited by the embodiment of the present invention. Furthermore, after obtaining the target quality inspection result information, the target quality inspection result information can also be visualized using a large model, and the visualized information can be divided into a proportional diagram and an example diagram of significant defects, thereby forming a chart of the yield rate and defective products of the product quality inspection, which is convenient for users to visualize the quality inspection situation, so as to be more conducive to the intelligent production scheduling of the intelligent production of security equipment, which is not limited by the embodiment of the present invention.

[0057] In this optional embodiment, as an optional implementation manner, the above-mentioned preprocessing of the product image information to obtain the target processed image information includes:

[0058] Performing contrast adjustment on the product image information to obtain first adjusted image information;

[0059] filtering the first adjusted image information to obtain second adjusted image information;

[0060] The second adjusted image information is subjected to image size adjustment to obtain target processed image information.

[0061] It should be noted that the above-mentioned contrast adjustment of the product image information is to achieve a change in the visual effect of the image by stretching or compressing the pixel value range to increase or decrease the difference between pixel values ​​without changing the overall brightness of the image, and the embodiments of the present invention are not limited thereto.

[0062] It should be noted that the above-mentioned filtering processing of the first adjusted image information is to filter out the uneven edge positions of the image through Gaussian filtering, smooth the image, thereby reducing the noise in the image, and retain the edge features of the image, thereby optimizing the image quality, which is more conducive to subsequent model quality inspection and analysis processing, and the embodiments of the present invention are not limited to this.

[0063] It should be noted that the above-mentioned image resizing of the second adjusted image information is to adjust the image size to 256*256 so that the target quality inspection analysis model can recognize and process it, and the embodiment of the present invention does not limit this.

[0064] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0065] In an optional embodiment, if Figure 5As shown, the target quality inspection and analysis model includes a first convolution module, a first pooling module, a first activation module, a first feature extraction module, a second feature extraction module, a third feature extraction module, a fourth feature extraction module, a first feature analysis module and a second feature analysis module; wherein,

[0066] The input end of the first convolution module is configured to receive model input information of the target quality inspection and analysis model, and the output end of the first convolution module is connected to the input end of the first pooling module; the output end of the first pooling module is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the first feature extraction module; the output end of the first feature extraction module is connected to the input end of the second feature extraction module; the output end of the second feature extraction module is respectively connected to the input end of the third feature extraction module and the input end of the first feature analysis module; the output end of the third feature extraction module is respectively connected to the input end of the fourth feature extraction module and the input end of the first feature analysis module; the output end of the fourth feature extraction module is connected to the input end of the first feature analysis module; the output end of the first feature analysis module is connected to the input end of the second feature analysis module; the output end of the second feature analysis module is configured to output the model output information of the target quality inspection and analysis model.

[0067] It should be noted that the model architectures of the first feature extraction module, the second feature extraction module, the third feature extraction module, and the fourth feature extraction module are consistent, and the embodiments of the present invention do not limit this. Furthermore, feature extraction of multiple links can be realized through multiple feature extraction modules, and in-depth extraction of image features of different gradients can be realized, so that features of different depths and gradients can be input into the feature analysis module for feature analysis, and the quality inspection and testing of multiple types of security equipment products can be further improved, so as to be more conducive to accurate quality inspection and testing analysis and efficiency improvement of the target quality inspection and analysis model, and the embodiments of the present invention do not limit this.

[0068] It should be noted that the convolution kernel size of the above-mentioned first convolution module is 3×3, which is not limited in the embodiment of the present invention.

[0069] It should be noted that the above-mentioned first pooling module is constructed based on the maximum pooling layer, which is not limited in the embodiment of the present invention.

[0070] It should be noted that the above-mentioned first activation module is constructed based on the Relu activation function, which is not limited in the embodiment of the present invention.

[0071] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to a changing production environment. By accurately identifying and processing various complex product defect problems through images, the efficiency and accuracy of product quality inspection can be improved, thereby improving the production efficiency and product quality of security equipment.

[0072] In another optional embodiment, Figure 6 As shown, the first feature extraction module includes a first convolution unit, a second convolution unit, a third convolution unit, a fourth convolution unit, a fifth convolution unit, a first pooling unit, a second pooling unit, a third pooling unit, a fourth pooling unit, a fifth pooling unit, a first activation unit, a second activation unit, a third activation unit, a fourth activation unit, a fifth activation unit, a first slicing unit and a first fusion unit; wherein,

[0073] The first convolution unit is configured to receive the first module input information of the first feature extraction module, the output end of the first convolution unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the first activation unit; the output end of the first activation unit is connected to the input end of the second convolution unit; the output end of the second convolution unit is connected to the input end of the second pooling unit; the output end of the second pooling unit is connected to the input end of the second activation unit; the output end of the second activation unit is respectively connected to the input end of the first slicing unit and the input end of the first fusion unit; the output end of the first slicing unit is respectively connected to the input end of the first fusion unit and the input end of the third convolution unit; the output end of the third convolution unit is connected The input end of the third pooling unit; the output end of the third pooling unit is connected to the input end of the third activation unit; the output end of the third activation unit is connected to the input end of the fourth convolution unit; the output end of the fourth convolution unit is connected to the input end of the fourth pooling unit; the output end of the fourth pooling unit is connected to the input end of the fourth activation unit; the output end of the fourth activation unit is connected to the input end of the first fusion unit; the output end of the first fusion unit is connected to the input end of the fifth convolution unit; the output end of the fifth convolution unit is connected to the input end of the fifth pooling unit; the output end of the fifth pooling unit is connected to the input end of the fifth activation unit; the output end of the fifth activation unit is configured to output the first module output information of the first feature extraction module.

[0074] It should be noted that the convolution kernel size of the first convolution unit, the second convolution unit, the third convolution unit, the fourth convolution unit, and the fifth convolution unit is 3×3, which is not limited in the embodiment of the present invention.

[0075] It should be noted that the above-mentioned first pooling unit, second pooling unit, third pooling unit, fourth pooling unit, and fifth pooling unit are constructed based on the maximum pooling layer, which is not limited in the embodiment of the present invention.

[0076] It should be noted that the first activation unit, the second activation unit, the third activation unit, the fourth activation unit, and the fifth activation unit are constructed based on the Silu activation function, which is not limited in the embodiment of the present invention.

[0077] It should be noted that the above-mentioned first slicing unit is constructed based on the split operation, which is not limited in the embodiment of the present invention.

[0078] It should be noted that the above-mentioned first fusion unit is constructed based on a splicing operation, which is not limited in the embodiment of the present invention.

[0079] It should be noted that a batch normalization layer is inserted between the above-mentioned convolution unit and pooling unit, which is not limited in the embodiment of the present invention.

[0080] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0081] In yet another optional embodiment, Figure 7 As shown, the module output information of the first feature analysis module includes first submodule output information, second submodule output information and third submodule output information;

[0082] The first feature analysis module includes a sixth convolution unit, a seventh convolution unit, an eighth convolution unit, a ninth convolution unit, a tenth convolution unit, an eleventh convolution unit, a twelfth convolution unit, a thirteenth convolution unit, a fourteenth convolution unit, a sixth pooling unit, a seventh pooling unit, an eighth pooling unit, a ninth pooling unit, a tenth pooling unit, an eleventh pooling unit, a twelfth pooling unit, a thirteenth pooling unit, a fourteenth pooling unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a second fusion unit, a third fusion unit, a fourth fusion unit, a fifth fusion unit, a sixth fusion unit, a seventh fusion unit, an eighth fusion unit, a first sampling unit, a second sampling unit, and a second slicing unit; wherein,

[0083] The input end of the sixth convolution unit is connected to the output end of the fourth feature extraction module, and the output end of the sixth convolution unit is connected to the input end of the seventh convolution unit; the output end of the seventh convolution unit is connected to the input end of the eighth convolution unit; the output end of the eighth convolution unit is respectively connected to the input end of the sixth pooling unit, the input end of the seventh pooling unit, the input end of the eighth pooling unit and the input end of the second fusion unit; the output end of the sixth pooling unit, the output end of the seventh pooling unit and the output end of the eighth pooling unit are all connected to the input end of the second fusion unit; the output end of the second fusion unit is connected to the input end of the tenth convolution unit; the output end of the tenth convolution unit is connected to the input end of the eleventh convolution unit; the output end of the eleventh convolution unit is connected to the input end of the third fusion unit. The input end of the ninth convolution unit is connected to the output end of the fourth feature extraction module, and the output end of the ninth convolution unit is connected to the input end of the third fusion unit; the output end of the third fusion unit is connected to the input end of the twelfth convolution unit; the output end of the twelfth convolution unit is connected to the input end of the first sampling unit; the output end of the first sampling unit and the output end of the third feature extraction module are both connected to the input end of the fourth fusion unit; the output end of the fourth fusion unit is respectively connected to the input end of the thirteenth convolution unit and the input end of the eighth fusion unit; the output end of the thirteenth convolution unit is connected to the input end of the ninth pooling unit; the output end of the ninth pooling unit is connected to the input end of the sixth activation unit; the output ends of the sixth activation unit are respectively connected to The input end of the second slicing unit and the input end of the fifth fusion unit; the output end of the second slicing unit is respectively connected to the input end of the fourteenth convolution unit and the input end of the fifth fusion unit; the output end of the fourteenth convolution unit is connected to the input end of the fifteenth convolution unit; the output end of the fifteenth convolution unit is connected to the input end of the fifth fusion unit; the output end of the fifth fusion unit is respectively connected to the input end of the second sampling unit and the input end of the seventh fusion unit; the output end of the second sampling unit is connected to the input end of the sixth fusion unit; the input end of the sixth fusion unit is also connected to the output end of the second feature extraction module, and the output end of the sixth fusion unit is connected to the input end of the sixteenth convolution unit; the output end of the sixteenth convolution unit is connected to the input end of the tenth pooling unit. The output end of the tenth pooling unit is connected to the input end of the seventh activation unit; the output end of the seventh activation unit is connected to the input end of the seventeenth convolution unit, and the output end of the seventh activation unit is also configured to output the first sub-module output information corresponding to the module output information of the first feature analysis module; the output end of the seventeenth convolution unit is connected to the input end of the eleventh pooling unit; the output end of the eleventh pooling unit is connected to the input end of the eighth activation unit; the output end of the eighth activation unit is connected to the input end of the seventh fusion unit; the output end of the seventh fusion unit is connected to the input end of the twelfth convolution unit; the output end of the twelfth convolution unit is connected to the input end of the twelfth pooling unit; the output end of the twelfth pooling unit is connected to the input end of the ninth activation unit;The output end of the ninth activation unit is connected to the input end of the thirteenth convolution unit, and is configured to output the second submodule output information corresponding to the module output information of the first feature analysis module; the output end of the thirteenth convolution unit is connected to the input end of the thirteenth pooling unit; the output end of the thirteenth pooling unit is connected to the input end of the tenth activation unit; the output end of the tenth activation unit is connected to the input end of the eighth fusion unit; the output end of the eighth fusion unit is connected to the input end of the fourteenth convolution unit; the output end of the fourteenth convolution unit is connected to the input end of the fourteenth pooling unit; the output end of the fourteenth pooling unit is connected to the input end of the eleventh activation unit; the output end of the eleventh activation unit is configured to output the third submodule output information corresponding to the module output information of the first feature analysis module. ;

[0084] It should be noted that the above-mentioned first feature analysis module uses multiple convolution units (different convolution kernels) to extract features of different scales, then uses a pooling unit to perform image restoration processing, and then uses a fusion unit to fuse features of different scales, thereby improving the detection and analysis accuracy and efficiency of the model, thereby achieving fast and efficient problem detection of security equipment products and improving quality inspection efficiency and results, which is not limited to the embodiments of the present invention.

[0085] It should be noted that the convolution kernel size of the sixth convolution unit, the seventh convolution unit, the eighth convolution unit, the eleventh convolution unit, the thirteenth convolution unit, and the fourteenth convolution unit is 3×1, which is not limited in the embodiment of the present invention.

[0086] It should be noted that the convolution kernel sizes of the ninth convolution unit, the tenth convolution unit, and the twelfth convolution unit are 1×1, which is not limited in the embodiment of the present invention.

[0087] It should be noted that the above-mentioned second slicing unit is constructed based on the split operation, which is not limited in the embodiment of the present invention.

[0088] It should be noted that the second fusion unit, the third fusion unit, the fourth fusion unit, the fifth fusion unit, the sixth fusion unit, the seventh fusion unit and the eighth fusion unit are all constructed based on the splicing operation, which is not limited in the embodiment of the present invention.

[0089] It should be noted that the first sampling unit and the second sampling unit are both constructed based on the upsampling operation, which is not limited in the embodiment of the present invention.

[0090] It should be noted that the sixth pooling unit, the seventh pooling unit, the eighth pooling unit, the ninth pooling unit, the tenth pooling unit, the eleventh pooling unit, the twelfth pooling unit, the thirteenth pooling unit, and the fourteenth pooling unit are all constructed based on the maximum pooling layer, which is not limited in the embodiments of the present invention.

[0091] It should be noted that the sixth activation unit, the seventh activation unit, the eighth activation unit, the ninth activation unit, the tenth activation unit, and the eleventh activation unit are constructed based on the Relu activation function, which is not limited in the embodiment of the present invention.

[0092] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0093] In yet another optional embodiment, Figure 8 As shown, the module input information of the second feature analysis module includes first submodule input information, second submodule input information and third submodule input information;

[0094] The second feature analysis module includes a fifteenth convolution unit, a sixteenth convolution unit, a seventeenth convolution unit, an eighteenth convolution unit, a nineteenth convolution unit, a twentieth convolution unit, a fifteenth pooling unit, a sixteenth pooling unit, a seventeenth pooling unit, an eighteenth pooling unit, a nineteenth pooling unit, a twentieth pooling unit, a twenty-first convolution unit, a twelfth activation unit, a thirteenth activation unit, a fourteenth activation unit, a fifteenth activation unit, a sixteenth activation unit, a seventeenth activation unit and a first connection unit; wherein,

[0095] The input end of the fifteenth convolution unit and the input end of the sixteenth convolution unit are both configured to receive the first submodule input information of the second feature analysis module; the output end of the fifteenth convolution unit is connected to the input end of the fifteenth pooling unit; the output end of the fifteenth pooling unit is connected to the input end of the twelfth activation unit; the output end of the twelfth activation unit is connected to the input end of the first connection unit; the output end of the sixteenth convolution unit is connected to the input end of the sixteenth pooling unit; the output end of the sixteenth pooling unit is connected to the input end of the thirteenth activation unit; the output end of the thirteenth activation unit is connected to the input end of the first connection unit; the input end of the seventeenth convolution unit and the input end of the eighteenth convolution unit are both configured to receive the second submodule input information of the second feature analysis module; the output end of the seventeenth convolution unit is connected to the input end of the seventeenth pooling unit; the output end of the seventeenth pooling unit is connected to the input end of the fourteenth activation unit; the output end of the fourteenth activation unit is connected to the input end of the first connection unit; The output end of the unit is connected to the input end of the eighteenth pooling unit; the output end of the eighteenth pooling unit is connected to the input end of the fifteenth activation unit; the output end of the fifteenth activation unit is connected to the input end of the first connection unit; the input end of the nineteenth convolution unit and the input end of the twentieth convolution unit are both configured to receive input information of the third submodule of the second feature analysis module; the output end of the nineteenth convolution unit is connected to the input end of the nineteenth pooling unit; the output end of the nineteenth pooling unit is connected to the input end of the sixteenth activation unit; the output end of the sixteenth activation unit is connected to the input end of the first connection unit; the output end of the second convolution unit is connected to the input end of the twentieth pooling unit; the output end of the twentieth pooling unit is connected to the input end of the seventeenth activation unit; the output end of the seventeenth activation unit is connected to the input end of the first connection unit; the output end of the first connection unit is connected to the input end of the twenty-first convolution unit; the output end of the twenty-first convolution unit is configured to output the model output information of the target quality inspection analysis model.

[0096] It should be noted that the above-mentioned second feature analysis module directly performs defect classification and identification after the feature extraction of multiple feature extraction modules and the first feature analysis module, thereby improving the defect detection efficiency of security equipment products while ensuring a certain defect detection accuracy, thereby improving the quality inspection efficiency of intelligent production of security equipment, and the embodiments of the present invention are not limited to this.

[0097] It should be noted that the first submodule input information, the second submodule input information and the third submodule input information correspond to the first submodule output information, the second submodule output information and the third submodule output information respectively, which is not limited in the embodiment of the present invention.

[0098] It should be noted that the convolution kernel sizes of the fifteenth convolution unit, the sixteenth convolution unit, the seventeenth convolution unit, the eighteenth convolution unit, the nineteenth convolution unit, the twentieth convolution unit, and the twenty-first convolution unit are 3×3, which is not limited in the embodiment of the present invention.

[0099] It should be noted that the fifteenth pooling unit, the sixteenth pooling unit, the seventeenth pooling unit, the eighteenth pooling unit, the nineteenth pooling unit, and the twentieth pooling unit are all constructed based on the maximum pooling layer, which is not limited in the embodiment of the present invention.

[0100] It should be noted that the twelfth activation unit, the thirteenth activation unit, the fourteenth activation unit, the fifteenth activation unit, the sixteenth activation unit, and the seventeenth activation unit are constructed based on the Relu activation function, which is not limited in the embodiment of the present invention.

[0101] It should be noted that the above-mentioned first connection unit is constructed based on the fully connected layer, which is not limited in the embodiment of the present invention.

[0102] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0103] In an optional embodiment, the target quality inspection analysis model is obtained based on the following method:

[0104] Obtaining first training sample information;

[0105] Determining target training sample information from the first training sample information;

[0106] The basic quality inspection and analysis model is trained using the target training sample information to obtain the training quality inspection and analysis model and model training result information;

[0107] Determine whether the model training result information satisfies the termination training condition to obtain a conditional judgment result; the termination training condition includes that the second loss value is within the loss value interval, and / or the number of training times is equal to the number threshold;

[0108] When the result of the conditional judgment is no, the training quality inspection analysis model is determined as a new basic quality inspection analysis model, and the determination of target training sample information from the first training sample information is triggered;

[0109] When the conditional judgment result is yes, the training quality inspection analysis model is determined as the target quality inspection analysis model.

[0110] It should be noted that the above loss value interval and number threshold can be set by the user or by the default value given by the system, which is not limited in the embodiment of the present invention. Furthermore, the above loss value interval can be an interval between [0.1, 0.5], which is not limited in the embodiment of the present invention. Furthermore, the above number threshold is a positive integer not less than 500, which is not limited in the embodiment of the present invention.

[0111] It should be noted that the first training sample information includes several first training samples, which is not limited in the embodiment of the present invention. Further, the first training sample can be a photo taken by a high-definition camera, and then annotated by a user using an annotation tool to form a training sample, which is not limited in the embodiment of the present invention.

[0112] It should be noted that the above-mentioned determination of the target training sample information from the first training sample information is to randomly select a first training sample from a plurality of first training samples as the target training sample information, which is not limited in the embodiment of the present invention.

[0113] It should be noted that the above training times represent the number of times the model is trained, and it automatically increases once each time training is performed, and the embodiment of the present invention does not limit this.

[0114] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0115] In another optional embodiment, determining whether the model training result information satisfies the training termination condition to obtain the conditional determination result includes:

[0116] The model training result information is calculated and processed using the first loss calculation model to obtain first loss value information; the first loss value information includes a first loss parameter value, a second loss parameter value, and a third loss parameter value;

[0117] Among them, the first loss calculation model is:

[0118]

[0119] Wherein, SS1, SS2 and SS3 represent the first loss parameter value, the second loss parameter value and the third loss parameter value respectively; a1 and a2 represent the first calculation parameter and the second calculation parameter respectively; c2, c4 and c6 represent the first sample annotation parameter, the second sample annotation parameter and the third sample annotation parameter in the target training sample information respectively; c1, c3, c5 and c7 represent the first training result parameter, the second training result parameter, the third training result parameter and the fourth training result parameter in the model training result information respectively;

[0120] Calculating and processing the first loss value information and the model training result information to obtain second loss value information;

[0121] Determine whether the second loss value in the second loss value information is within a loss value interval, and obtain an interval determination result;

[0122] When the interval judgment result is yes, the condition judgment result is determined to be yes;

[0123] When the interval judgment result is no, it is judged whether the number of training times in the model training result information is equal to the number threshold, and the number judgment result is obtained;

[0124] When the result of the number judgment is yes, the result of the condition judgment is determined to be yes;

[0125] When the number of times is judged as negative, the determination condition is judged as negative.

[0126] It should be noted that the above σ(·) represents the Euclidean distance calculation, which is not limited in the embodiment of the present invention.

[0127] In this optional embodiment, as an optional implementation, the above-mentioned calculation and processing of the first loss value information and the model training result information to obtain the second loss value information includes:

[0128] Using the second loss calculation model to calculate the first loss value information and the model training result information to obtain the second loss value information;

[0129] Among them, the second loss calculation model is:

[0130] DESS=a3-e -SS1·c8 -e -SS1·c9 +(1-e -SS2 ) a4 +(1-e -SS3 ) a4 ;

[0131] In the formula, DESS represents the second loss value in the second loss value information; a3 and a4 represent the third calculation parameter and the fourth calculation parameter respectively; c8 and c9 represent the fifth training result parameter and the sixth training result parameter in the model training result information respectively.

[0132] It should be noted that the first calculation parameter, the second calculation parameter, the third calculation parameter and the fourth calculation parameter may be set by the user or may be a default value given by the system, which is not limited in the embodiment of the present invention. Furthermore, the values ​​of the above calculation parameters are between [1,6], which is not limited in the embodiment of the present invention.

[0133] It should be noted that the first sample annotation parameter, the second sample annotation parameter and the third sample annotation parameter respectively represent the center point coordinates, the width and the length of the rectangular box annotated on the target training sample in the target training sample information, which is not limited in the embodiment of the present invention.

[0134] It should be noted that the above-mentioned first training result parameter, second training result parameter, third training result parameter, fourth training result parameter, fifth training result parameter and sixth training result parameter respectively represent the diagonal length of the minimum circumscribed rectangle of the image prediction rectangular box and the annotated rectangular box corresponding to the model training result information, the center point coordinates of the image prediction rectangular box, the width of the image prediction rectangular box, the length of the image prediction rectangular box, the square value corresponding to the ratio of the horizontal distance between the center points of the image prediction rectangular box and the annotated rectangular box to the width of the minimum circumscribed rectangle of the image prediction rectangular box and the annotated rectangular box, and the square value corresponding to the ratio of the plumb line distance between the center points of the image prediction rectangular box and the annotated rectangular box to the height of the minimum circumscribed rectangle of the image prediction rectangular box and the annotated rectangular box, which is not limited in the embodiments of the present invention.

[0135] It should be noted that the above-mentioned judgment of whether the second loss value in the second loss value information is within the loss value interval is to judge whether the currently calculated second loss value and the 10 second loss values ​​calculated previously are all within the loss value interval. If all are, the characterization interval judgment result is yes, otherwise it is no, and the embodiment of the present invention does not limit this.

[0136] It should be noted that the first loss calculation model and the second loss calculation model adopted in this application to calculate the loss function value in the model training process can solve the problem of unstable parameter optimization caused by object occlusion in the model training process, and the calculation complexity is relatively lower, and the demand for hardware resources such as memory and GPU is relatively less. It can achieve the premise of ensuring the quality of model training. Improve the speed of model training, which is not limited to the embodiments of the present invention.

[0137] It can be seen that the implementation of the intelligent quality inspection method for intelligent production of security equipment described in the embodiment of the present invention is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0138] Embodiment 2

[0139] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of an intelligent quality inspection system for intelligent production of security equipment disclosed in an embodiment of the present invention. Figure 3 The described system can be applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. Figure 3 As shown, the system may include:

[0140] Acquisition module 201, used to acquire product image information;

[0141] The first processing module 202 is used to pre-process the product image information to obtain target processed image information;

[0142] The second processing module 203 is used to use the target quality inspection analysis model to perform detection and analysis on the target processing image information to obtain target quality inspection result information.

[0143] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0144] In another optional embodiment, Figure 5 As shown, the target quality inspection and analysis model includes a first convolution module, a first pooling module, a first activation module, a first feature extraction module, a second feature extraction module, a third feature extraction module, a fourth feature extraction module, a first feature analysis module, and a second feature analysis module; wherein,

[0145] The input end of the first convolution module is configured to receive model input information of the target quality inspection and analysis model, and the output end of the first convolution module is connected to the input end of the first pooling module; the output end of the first pooling module is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the first feature extraction module; the output end of the first feature extraction module is connected to the input end of the second feature extraction module; the output end of the second feature extraction module is respectively connected to the input end of the third feature extraction module and the input end of the first feature analysis module; the output end of the third feature extraction module is respectively connected to the input end of the fourth feature extraction module and the input end of the first feature analysis module; the output end of the fourth feature extraction module is connected to the input end of the first feature analysis module; the output end of the first feature analysis module is connected to the input end of the second feature analysis module; the output end of the second feature analysis module is configured to output the model output information of the target quality inspection and analysis model.

[0146] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0147] In yet another optional embodiment, Figure 6 As shown, the first feature extraction module includes a first convolution unit, a second convolution unit, a third convolution unit, a fourth convolution unit, a fifth convolution unit, a first pooling unit, a second pooling unit, a third pooling unit, a fourth pooling unit, a fifth pooling unit, a first activation unit, a second activation unit, a third activation unit, a fourth activation unit, a fifth activation unit, a first slicing unit and a first fusion unit; wherein,

[0148] The first convolution unit is configured to receive the first module input information of the first feature extraction module, the output end of the first convolution unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the first activation unit; the output end of the first activation unit is connected to the input end of the second convolution unit; the output end of the second convolution unit is connected to the input end of the second pooling unit; the output end of the second pooling unit is connected to the input end of the second activation unit; the output end of the second activation unit is respectively connected to the input end of the first slicing unit and the input end of the first fusion unit; the output end of the first slicing unit is respectively connected to the input end of the first fusion unit and the input end of the third convolution unit; the output end of the third convolution unit is connected The input end of the third pooling unit; the output end of the third pooling unit is connected to the input end of the third activation unit; the output end of the third activation unit is connected to the input end of the fourth convolution unit; the output end of the fourth convolution unit is connected to the input end of the fourth pooling unit; the output end of the fourth pooling unit is connected to the input end of the fourth activation unit; the output end of the fourth activation unit is connected to the input end of the first fusion unit; the output end of the first fusion unit is connected to the input end of the fifth convolution unit; the output end of the fifth convolution unit is connected to the input end of the fifth pooling unit; the output end of the fifth pooling unit is connected to the input end of the fifth activation unit; the output end of the fifth activation unit is configured to output the first module output information of the first feature extraction module.

[0149] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0150] In yet another optional embodiment, Figure 7 As shown, the module output information of the first feature analysis module includes first submodule output information, second submodule output information and third submodule output information;

[0151] The first feature analysis module includes a sixth convolution unit, a seventh convolution unit, an eighth convolution unit, a ninth convolution unit, a tenth convolution unit, an eleventh convolution unit, a twelfth convolution unit, a thirteenth convolution unit, a fourteenth convolution unit, a sixth pooling unit, a seventh pooling unit, an eighth pooling unit, a ninth pooling unit, a tenth pooling unit, an eleventh pooling unit, a twelfth pooling unit, a thirteenth pooling unit, a fourteenth pooling unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a second fusion unit, a third fusion unit, a fourth fusion unit, a fifth fusion unit, a sixth fusion unit, a seventh fusion unit, an eighth fusion unit, a first sampling unit, a second sampling unit, and a second slicing unit; wherein,

[0152] The input end of the sixth convolution unit is connected to the output end of the fourth feature extraction module, and the output end of the sixth convolution unit is connected to the input end of the seventh convolution unit; the output end of the seventh convolution unit is connected to the input end of the eighth convolution unit; the output end of the eighth convolution unit is respectively connected to the input end of the sixth pooling unit, the input end of the seventh pooling unit, the input end of the eighth pooling unit and the input end of the second fusion unit; the output end of the sixth pooling unit, the output end of the seventh pooling unit and the output end of the eighth pooling unit are all connected to the input end of the second fusion unit; the output end of the second fusion unit is connected to the input end of the tenth convolution unit; the output end of the tenth convolution unit is connected to the input end of the eleventh convolution unit; the output end of the eleventh convolution unit is connected to the input end of the third fusion unit. The input end of the ninth convolution unit is connected to the output end of the fourth feature extraction module, and the output end of the ninth convolution unit is connected to the input end of the third fusion unit; the output end of the third fusion unit is connected to the input end of the twelfth convolution unit; the output end of the twelfth convolution unit is connected to the input end of the first sampling unit; the output end of the first sampling unit and the output end of the third feature extraction module are both connected to the input end of the fourth fusion unit; the output end of the fourth fusion unit is respectively connected to the input end of the thirteenth convolution unit and the input end of the eighth fusion unit; the output end of the thirteenth convolution unit is connected to the input end of the ninth pooling unit; the output end of the ninth pooling unit is connected to the input end of the sixth activation unit; the output ends of the sixth activation unit are respectively connected to The input end of the second slicing unit and the input end of the fifth fusion unit; the output end of the second slicing unit is respectively connected to the input end of the fourteenth convolution unit and the input end of the fifth fusion unit; the output end of the fourteenth convolution unit is connected to the input end of the fifteenth convolution unit; the output end of the fifteenth convolution unit is connected to the input end of the fifth fusion unit; the output end of the fifth fusion unit is respectively connected to the input end of the second sampling unit and the input end of the seventh fusion unit; the output end of the second sampling unit is connected to the input end of the sixth fusion unit; the input end of the sixth fusion unit is also connected to the output end of the second feature extraction module, and the output end of the sixth fusion unit is connected to the input end of the sixteenth convolution unit; the output end of the sixteenth convolution unit is connected to the input end of the tenth pooling unit. The output end of the tenth pooling unit is connected to the input end of the seventh activation unit; the output end of the seventh activation unit is connected to the input end of the seventeenth convolution unit, and the output end of the seventh activation unit is also configured to output the first sub-module output information corresponding to the module output information of the first feature analysis module; the output end of the seventeenth convolution unit is connected to the input end of the eleventh pooling unit; the output end of the eleventh pooling unit is connected to the input end of the eighth activation unit; the output end of the eighth activation unit is connected to the input end of the seventh fusion unit; the output end of the seventh fusion unit is connected to the input end of the twelfth convolution unit; the output end of the twelfth convolution unit is connected to the input end of the twelfth pooling unit; the output end of the twelfth pooling unit is connected to the input end of the ninth activation unit;The output end of the ninth activation unit is connected to the input end of the thirteenth convolution unit, and is configured to output the second submodule output information corresponding to the module output information of the first feature analysis module; the output end of the ninth activation unit is connected to the input end of the thirteenth convolution unit; the output end of the thirteenth convolution unit is connected to the input end of the thirteenth pooling unit; the output end of the thirteenth pooling unit is connected to the input end of the tenth activation unit; the output end of the tenth activation unit is connected to the input end of the eighth fusion unit; the output end of the eighth fusion unit is connected to the input end of the fourteenth convolution unit; the output end of the fourteenth convolution unit is connected to the input end of the fourteenth pooling unit; the output end of the fourteenth pooling unit is connected to the input end of the eleventh activation unit; the output end of the eleventh activation unit is configured to output the third submodule output information corresponding to the module output information of the first feature analysis module. ;

[0153] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0154] In yet another optional embodiment, Figure 8 As shown, the module input information of the second feature analysis module includes first submodule input information, second submodule input information and third submodule input information;

[0155] The second feature analysis module includes a fifteenth convolution unit, a sixteenth convolution unit, a seventeenth convolution unit, an eighteenth convolution unit, a nineteenth convolution unit, a twentieth convolution unit, a fifteenth pooling unit, a sixteenth pooling unit, a seventeenth pooling unit, an eighteenth pooling unit, a nineteenth pooling unit, a twentieth pooling unit, a twenty-first convolution unit, a twelfth activation unit, a thirteenth activation unit, a fourteenth activation unit, a fifteenth activation unit, a sixteenth activation unit, a seventeenth activation unit and a first connection unit; wherein,

[0156] The input end of the fifteenth convolution unit and the input end of the sixteenth convolution unit are both configured to receive the first submodule input information of the second feature analysis module; the output end of the fifteenth convolution unit is connected to the input end of the fifteenth pooling unit; the output end of the fifteenth pooling unit is connected to the input end of the twelfth activation unit; the output end of the twelfth activation unit is connected to the input end of the first connection unit; the output end of the sixteenth convolution unit is connected to the input end of the sixteenth pooling unit; the output end of the sixteenth pooling unit is connected to the input end of the thirteenth activation unit; the output end of the thirteenth activation unit is connected to the input end of the first connection unit; the input end of the seventeenth convolution unit and the input end of the eighteenth convolution unit are both configured to receive the second submodule input information of the second feature analysis module; the output end of the seventeenth convolution unit is connected to the input end of the seventeenth pooling unit; the output end of the seventeenth pooling unit is connected to the input end of the fourteenth activation unit; the output end of the fourteenth activation unit is connected to the input end of the first connection unit; The output end of the unit is connected to the input end of the eighteenth pooling unit; the output end of the eighteenth pooling unit is connected to the input end of the fifteenth activation unit; the output end of the fifteenth activation unit is connected to the input end of the first connection unit; the input end of the nineteenth convolution unit and the input end of the twentieth convolution unit are both configured to receive input information of the third submodule of the second feature analysis module; the output end of the nineteenth convolution unit is connected to the input end of the nineteenth pooling unit; the output end of the nineteenth pooling unit is connected to the input end of the sixteenth activation unit; the output end of the sixteenth activation unit is connected to the input end of the first connection unit; the output end of the second convolution unit is connected to the input end of the twentieth pooling unit; the output end of the twentieth pooling unit is connected to the input end of the seventeenth activation unit; the output end of the seventeenth activation unit is connected to the input end of the first connection unit; the output end of the first connection unit is connected to the input end of the twenty-first convolution unit; the output end of the twenty-first convolution unit is configured to output the model output information of the target quality inspection analysis model.

[0157] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0158] In yet another optional embodiment, Figure 3 As shown in the figure, the target quality inspection analysis model is obtained based on the following method:

[0159] Obtaining first training sample information;

[0160] Determining target training sample information from the first training sample information;

[0161] The basic quality inspection and analysis model is trained using the target training sample information to obtain the training quality inspection and analysis model and model training result information;

[0162] Determine whether the model training result information satisfies the termination training condition to obtain a conditional judgment result; the termination training condition includes that the second loss value is within the loss value interval, and / or the number of training times is equal to the number threshold;

[0163] When the result of the conditional judgment is no, the training quality inspection analysis model is determined as a new basic quality inspection analysis model, and the determination of target training sample information from the first training sample information is triggered;

[0164] When the conditional judgment result is yes, the training quality inspection analysis model is determined as the target quality inspection analysis model.

[0165] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0166] In yet another optional embodiment, Figure 3 As shown, it is determined whether the model training result information meets the termination training condition, and the conditional judgment result is obtained, including:

[0167] The model training result information is calculated and processed using the first loss calculation model to obtain first loss value information; the first loss value information includes a first loss parameter value, a second loss parameter value, and a third loss parameter value;

[0168] Among them, the first loss calculation model is:

[0169]

[0170] Wherein, SS1, SS2 and SS3 represent the first loss parameter value, the second loss parameter value and the third loss parameter value respectively; a1 and a2 represent the first calculation parameter and the second calculation parameter respectively; c2, c4 and c6 represent the first sample annotation parameter, the second sample annotation parameter and the third sample annotation parameter in the target training sample information respectively; c1, c3, c5 and c7 represent the first training result parameter, the second training result parameter, the third training result parameter and the fourth training result parameter in the model training result information respectively;

[0171] Calculating and processing the first loss value information and the model training result information to obtain second loss value information;

[0172] Determine whether the second loss value in the second loss value information is within a loss value interval, and obtain an interval determination result;

[0173] When the interval judgment result is yes, the condition judgment result is determined to be yes;

[0174] When the interval judgment result is no, it is judged whether the number of training times in the model training result information is equal to the number threshold, and the number judgment result is obtained;

[0175] When the result of the number judgment is yes, the result of the condition judgment is determined to be yes;

[0176] When the number of times is judged as negative, the determination condition is judged as negative.

[0177] It can be seen that implementation Figure 3 The described intelligent quality inspection system for intelligent production of security equipment is conducive to adapting to the changing production environment, accurately identifying and handling various complex product defect problems, improving the efficiency and accuracy of product quality inspection, and thus improving the production efficiency and product quality of security equipment.

[0178] Embodiment 3

[0179] See also Figure 4 , Figure 4 This is a structural diagram of another intelligent quality inspection system for intelligent production of security equipment disclosed in an embodiment of the present invention. Figure 4 The described system can be applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. Figure 4 As shown, the system may include:

[0180] A memory 301 storing executable program codes;

[0181] a processor 302 coupled to the memory 301;

[0182] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the intelligent quality inspection method for intelligent production of security equipment described in the first embodiment.

[0183] Embodiment 4

[0184] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the intelligent quality inspection method for intelligent production of security equipment described in the first embodiment.

[0185] Embodiment 5

[0186] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the intelligent quality inspection method for intelligent production of security equipment described in Example 1.

[0187] The system embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative labor.

[0188] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0189] Finally, it should be noted that the intelligent quality inspection method and system for intelligent production of security equipment disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent quality inspection method for intelligent production of security equipment, characterized in that: The method comprises: Get product image information; Preprocessing the product image information to obtain target processed image information; The target quality inspection analysis model is used to detect and analyze the target processing image information to obtain target quality inspection result information.

2. The intelligent quality inspection method for intelligent production of security equipment according to claim 1, characterized in that: The target quality inspection and analysis model includes a first convolution module, a first pooling module, a first activation module, a first feature extraction module, a second feature extraction module, a third feature extraction module, a fourth feature extraction module, a first feature analysis module and a second feature analysis module; wherein, The input end of the first convolution module is configured to receive model input information of the target quality inspection and analysis model, and the output end of the first convolution module is connected to the input end of the first pooling module; the output end of the first pooling module is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the first feature extraction module; the output end of the first feature extraction module is connected to the input end of the second feature extraction module; the output end of the second feature extraction module is respectively connected to the input end of the third feature extraction module and the input end of the first feature analysis module; the output end of the third feature extraction module is respectively connected to the input end of the fourth feature extraction module and the input end of the first feature analysis module; the output end of the fourth feature extraction module is connected to the input end of the first feature analysis module; the output end of the first feature analysis module is connected to the input end of the second feature analysis module; the output end of the second feature analysis module is configured to output the model output information of the target quality inspection and analysis model.

3. The intelligent quality inspection method for intelligent production of security equipment according to claim 2, characterized in that: The first feature extraction module includes a first convolution unit, a second convolution unit, a third convolution unit, a fourth convolution unit, a fifth convolution unit, a first pooling unit, a second pooling unit, a third pooling unit, a fourth pooling unit, a fifth pooling unit, a first activation unit, a second activation unit, a third activation unit, a fourth activation unit, a fifth activation unit, a first slicing unit and a first fusion unit; wherein, The first convolution unit is configured to receive the first module input information of the first feature extraction module, the output end of the first convolution unit is connected to the input end of the first pooling unit; the output end of the first pooling unit is connected to the input end of the first activation unit; the output end of the first activation unit is connected to the input end of the second convolution unit; the output end of the second convolution unit is connected to the input end of the second pooling unit; the output end of the second pooling unit is connected to the input end of the second activation unit; the output end of the second activation unit is respectively connected to the input end of the first slicing unit and the input end of the first fusion unit; the output end of the first slicing unit is respectively connected to the input end of the first fusion unit and the input end of the third convolution unit; the output end of the third convolution unit is connected The input end of the third pooling unit; the output end of the third pooling unit is connected to the input end of the third activation unit; the output end of the third activation unit is connected to the input end of the fourth convolution unit; the output end of the fourth convolution unit is connected to the input end of the fourth pooling unit; the output end of the fourth pooling unit is connected to the input end of the fourth activation unit; the output end of the fourth activation unit is connected to the input end of the first fusion unit; the output end of the first fusion unit is connected to the input end of the fifth convolution unit; the output end of the fifth convolution unit is connected to the input end of the fifth pooling unit; the output end of the fifth pooling unit is connected to the input end of the fifth activation unit; the output end of the fifth activation unit is configured to output the first module output information of the first feature extraction module.

4. The intelligent quality inspection method for intelligent production of security equipment according to claim 2, characterized in that: The module output information of the first feature analysis module includes first submodule output information, second submodule output information and third submodule output information; The first feature analysis module includes a sixth convolution unit, a seventh convolution unit, an eighth convolution unit, a ninth convolution unit, a tenth convolution unit, an eleventh convolution unit, a twelfth convolution unit, a thirteenth convolution unit, a fourteenth convolution unit, a sixth pooling unit, a seventh pooling unit, an eighth pooling unit, a ninth pooling unit, a tenth pooling unit, an eleventh pooling unit, a twelfth pooling unit, a thirteenth pooling unit, a fourteenth pooling unit, a sixth activation unit, a seventh activation unit, an eighth activation unit, a ninth activation unit, a tenth activation unit, an eleventh activation unit, a second fusion unit, a third fusion unit, a fourth fusion unit, a fifth fusion unit, a sixth fusion unit, a seventh fusion unit, an eighth fusion unit, a first sampling unit, a second sampling unit, and a second slicing unit; wherein, The input end of the sixth convolution unit is connected to the output end of the fourth feature extraction module, and the output end of the sixth convolution unit is connected to the input end of the seventh convolution unit; the output end of the seventh convolution unit is connected to the input end of the eighth convolution unit; the output end of the eighth convolution unit is respectively connected to the input end of the sixth pooling unit, the input end of the seventh pooling unit, the input end of the eighth pooling unit and the input end of the second fusion unit; the output end of the sixth pooling unit, the output end of the seventh pooling unit and the output end of the eighth pooling unit are all connected to the input end of the second fusion unit; the output end of the second fusion unit is connected to the input end of the tenth convolution unit; the output end of the tenth convolution unit is connected to the input end of the tenth The input end of the first convolution unit is connected to the input end of the third fusion unit; the output end of the eleventh convolution unit is connected to the input end of the third fusion unit; the input end of the ninth convolution unit is connected to the output end of the fourth feature extraction module, and the output end of the ninth convolution unit is connected to the input end of the third fusion unit; the output end of the third fusion unit is connected to the input end of the twelfth convolution unit; the output end of the twelfth convolution unit is connected to the input end of the first sampling unit; the output end of the first sampling unit and the output end of the third feature extraction module are both connected to the input end of the fourth fusion unit; the output end of the fourth fusion unit is respectively connected to the input end of the thirteenth convolution unit and the input end of the eighth fusion unit; the output end of the thirteenth convolution unit is connected to The output end of the ninth pooling unit is connected to the input end of the sixth activation unit; the output end of the sixth activation unit is respectively connected to the input end of the second slicing unit and the input end of the fifth fusion unit; the output end of the second slicing unit is respectively connected to the input end of the fourteenth convolution unit and the input end of the fifth fusion unit; the output end of the fourteenth convolution unit is connected to the input end of the fifteenth convolution unit; the output end of the fifteenth convolution unit is connected to the input end of the fifth fusion unit; the output end of the fifth fusion unit is respectively connected to the input end of the second sampling unit and the input end of the seventh fusion unit; the output end of the second sampling unit is connected to the input end of the sixth fusion unit end; the input end of the sixth fusion unit is also connected to the output end of the second feature extraction module, and the output end of the sixth fusion unit is connected to the input end of the sixteenth convolution unit; the output end of the sixteenth convolution unit is connected to the input end of the tenth pooling unit; the output end of the tenth pooling unit is connected to the input end of the seventh activation unit; the output end of the seventh activation unit is connected to the input end of the seventeenth convolution unit, and the output end of the seventh activation unit is also configured to output the first sub-module output information corresponding to the module output information of the first feature analysis module; the output end of the seventeenth convolution unit is connected to the input end of the eleventh pooling unit; the output end of the eleventh pooling unit is connected to the input end of the eighth activation unit;The output end of the eighth activation unit is connected to the input end of the seventh fusion unit; the output end of the seventh fusion unit is connected to the input end of the twelfth convolution unit; the output end of the twelfth convolution unit is connected to the input end of the twelfth pooling unit; the output end of the twelfth pooling unit is connected to the input end of the ninth activation unit; the output end of the ninth activation unit is connected to the input end of the thirteenth convolution unit, and is configured to output the second sub-module output information corresponding to the module output information of the first feature analysis module; the output end of the ninth activation unit is connected to the input end of the thirteenth convolution unit; the thirteenth convolution The output end of the unit is connected to the input end of the thirteenth pooling unit; the output end of the thirteenth pooling unit is connected to the input end of the tenth activation unit; the output end of the tenth activation unit is connected to the input end of the eighth fusion unit; the output end of the eighth fusion unit is connected to the input end of the fourteenth convolution unit; the output end of the fourteenth convolution unit is connected to the input end of the fourteenth pooling unit; the output end of the fourteenth pooling unit is connected to the input end of the eleventh activation unit; the output end of the eleventh activation unit is configured to output the third submodule output information corresponding to the module output information of the first feature analysis module. ; 5. The intelligent quality inspection method for intelligent production of security equipment according to claim 2, characterized in that: The module input information of the second feature analysis module includes first submodule input information, second submodule input information and third submodule input information; The second feature analysis module includes a fifteenth convolution unit, a sixteenth convolution unit, a seventeenth convolution unit, an eighteenth convolution unit, a nineteenth convolution unit, a twentieth convolution unit, a fifteenth pooling unit, a sixteenth pooling unit, a seventeenth pooling unit, an eighteenth pooling unit, a nineteenth pooling unit, a twentieth pooling unit, a twenty-first convolution unit, a twelfth activation unit, a thirteenth activation unit, a fourteenth activation unit, a fifteenth activation unit, a sixteenth activation unit, a seventeenth activation unit and a first connection unit; wherein, The input end of the fifteenth convolution unit and the input end of the sixteenth convolution unit are both configured to receive the first submodule input information of the second feature analysis module; the output end of the fifteenth convolution unit is connected to the input end of the fifteenth pooling unit; the output end of the fifteenth pooling unit is connected to the input end of the twelfth activation unit; the output end of the twelfth activation unit is connected to the input end of the first connection unit; the output end of the sixteenth convolution unit is connected to the input end of the sixteenth pooling unit; the output end of the sixteenth pooling unit is connected to the input end of the thirteenth activation unit; the output end of the thirteenth activation unit is connected to the input end of the first connection unit; the input end of the seventeenth convolution unit and the input end of the eighteenth convolution unit are both configured to receive the second submodule input information of the second feature analysis module; the output end of the seventeenth convolution unit is connected to the input end of the seventeenth pooling unit; the output end of the seventeenth pooling unit is connected to the input end of the fourteenth activation unit; the output end of the fourteenth activation unit is connected to the input end of the first connection unit; The output end of the convolution unit is connected to the input end of the eighteenth pooling unit; the output end of the eighteenth pooling unit is connected to the input end of the fifteenth activation unit; the output end of the fifteenth activation unit is connected to the input end of the first connection unit; the input end of the nineteenth convolution unit and the input end of the twentieth convolution unit are both configured to receive input information of the third submodule of the second feature analysis module; the output end of the nineteenth convolution unit is connected to the input end of the nineteenth pooling unit; the output end of the nineteenth pooling unit is connected to the input end of the sixteenth activation unit; the output end of the sixteenth activation unit is connected to the input end of the first connection unit; the output end of the second convolution unit is connected to the input end of the twentieth pooling unit; the output end of the twentieth pooling unit is connected to the input end of the seventeenth activation unit; the output end of the seventeenth activation unit is connected to the input end of the first connection unit; the output end of the first connection unit is connected to the input end of the twenty-first convolution unit; the output end of the twenty-first convolution unit is configured to output the model output information of the target quality inspection analysis model.

6. The intelligent quality inspection method for intelligent production of security equipment according to claim 1, characterized in that: The target quality inspection analysis model is obtained based on the following method: Obtaining first training sample information; Determining target training sample information from the first training sample information; Using the target training sample information to perform model training on the basic quality inspection and analysis model to obtain a training quality inspection and analysis model and model training result information; Determine whether the model training result information meets the training termination condition, and obtain a conditional judgment result; The termination training condition includes that the second loss value is within the loss value interval, and / or the number of training times is equal to the number threshold; When the result of the conditional judgment is no, the training quality inspection analysis model is determined as a new basic quality inspection analysis model, and the determination of target training sample information from the first training sample information is triggered to be executed; When the conditional judgment result is yes, the training quality inspection analysis model is determined as the target quality inspection analysis model.

7. The intelligent quality inspection method for intelligent production of security equipment according to claim 6, characterized in that: The determining whether the model training result information satisfies the training termination condition to obtain the conditional determination result includes: Using a first loss calculation model to calculate and process the model training result information to obtain first loss value information; the first loss value information includes a first loss parameter value, a second loss parameter value, and a third loss parameter value; Wherein, the first loss calculation model is: Wherein, SS1, SS2 and SS3 represent the first loss parameter value, the second loss parameter value and the third loss parameter value respectively; a1 and a2 represent the first calculation parameter and the second calculation parameter respectively; c2, c4 and c6 represent the first sample annotation parameter, the second sample annotation parameter and the third sample annotation parameter in the target training sample information respectively; c1, c3, c5 and c7 represent the first training result parameter, the second training result parameter, the third training result parameter and the fourth training result parameter in the model training result information respectively; Calculating and processing the first loss value information and the model training result information to obtain second loss value information; Determine whether the second loss value in the second loss value information is within the loss value interval, and obtain an interval determination result; When the interval judgment result is yes, determining the condition judgment result is yes; When the interval judgment result is no, judging whether the number of training times in the model training result information is equal to the number threshold, and obtaining a number judgment result; When the number of times is yes, determining that the condition is yes; When the number of times judgment result is no, it is determined that the condition judgment result is no.

8. An intelligent quality inspection system for intelligent production of security equipment, characterized in that: The system comprises: An acquisition module, used to acquire product image information; A first processing module, used for preprocessing the product image information to obtain target processed image information; The second processing module is used to use the target quality inspection analysis model to detect and analyze the target processing image information to obtain target quality inspection result information.

9. An intelligent quality inspection system for intelligent production of security equipment, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent quality inspection method for intelligent production of security equipment as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when called, are used to execute the intelligent quality inspection method for intelligent production of security equipment as described in any one of claims 1-7.

Images