Electrical assembly process report generation method, system, and computer equipment

Abstract

This application relates to electrical assembly process technology and discloses a method, system, and computer device for generating an electrical assembly process report. The method includes: acquiring an electrical assembly image; performing image recognition on the electrical assembly image to obtain contour information in the electrical assembly image; performing character recognition on the electrical assembly image to obtain technical requirements information and position number information of each component in the electrical assembly image; obtaining an adjacency matrix of the electrical assembly image based on the contour information and position number information; inputting the contour information, adjacency matrix, technical requirements information, and position number information into a graph neural network to generate an assembly logic file; and inputting a preset process rule set and the assembly logic file into a process report generation model to generate an electrical assembly process report. By extracting electrical assembly image information through image and character recognition technology and automatically generating a process report based on process rules, the efficiency and accuracy of report generation are improved.

Description

Technical Field

[0001] The present application relates to the field of electrical assembly process technology, and in particular to a method, system, and computer equipment for generating an electrical assembly process report. Background Art

[0002] Traditionally, the preparation of electrical assembly process reports relies on manual analysis of drawings, searching for component parameters, and writing the report. Specifically, engineers spend a significant amount of time interpreting circuit diagrams and searching various reference materials for specific component information. This process is not only time-consuming but can also lead to the omission of critical data or misunderstanding of design intent. Furthermore, manually compiled process documents often lack standardized formats and offer vague descriptions, increasing confusion and the risk of operational errors. This significantly impacts production efficiency and consistent product quality. Summary of the Invention

[0003] In view of this, the embodiments of the present application provide a method, system, and computer equipment for generating an electrical assembly process report, which can effectively solve the problems in the prior art where the preparation of electrical assembly process reports relies on manual identification of drawings, searching for component parameters, and manual writing of process reports, resulting in low efficiency, proneness to errors, and poor standardization, which seriously affects the consistency of production efficiency and product quality.

[0004] In a first aspect, an embodiment of the present application provides a method for generating an electrical assembly process report, the method comprising:

[0005] Acquire electrical assembly images;

[0006] Performing image recognition on the electrical assembly image to obtain contour information in the electrical assembly image;

[0007] Performing character recognition on the electrical assembly image to obtain technical requirement information of the electrical assembly image and bit number information of each component;

[0008] Obtaining an adjacency matrix of the electrical assembly image according to the outline information and each of the bit number information;

[0009] Inputting the outline information, the adjacency matrix, the technical requirement information and each of the position number information into a graph neural network to generate an assembly logic file;

[0010] The preset process rule set and the assembly logic file are input into a process report generation model to generate an electrical assembly process report.

[0011] In some embodiments, after obtaining the adjacency matrix of the electrical assembly image based on the outline information and each bit number information, the method further includes:

[0012] Get the material list;

[0013] Query the model information of each component corresponding to each bit number information in the material list;

[0014] Obtaining the three-dimensional spatial structure information of each component in a preset component database according to each model information;

[0015] The three-dimensional spatial structure information, the contour information, the adjacency matrix, each of the position number information and the technical requirement information are input into the graph neural network to generate the assembly logic file.

[0016] In some embodiments, performing image recognition on the electrical assembly image to obtain contour information in the electrical assembly image includes:

[0017] Using OpenCV to extract the contours in the electrical assembly image to obtain contour information of each connection line, contour information of each component, and center coordinates of each component;

[0018] The contour information of each component is classified using a visual macro model to obtain contour categories, and the connection relationship of each component is obtained based on the contour information of each connection line. The contour information includes the center coordinates, contour categories and connection relationships.

[0019] In some embodiments, obtaining an adjacency matrix of the electrical assembly image according to the outline information and each of the bit number information includes:

[0020] According to the bit number information, the center coordinates and the connection relationship, the adjacency matrix with each component as a node is obtained.

[0021] In some embodiments, the edge weights of the adjacency matrix include: the distances and connection types between the nodes.

[0022] In some embodiments, after inputting the preset process rule set and the assembly logic file into the process report generation model to generate the electrical assembly process report, the method further includes:

[0023] Extracting information from the electrical assembly process report using regular expressions according to a preset standard template;

[0024] The extracted information is filled into the preset standard template to generate a process procedure card.

[0025] In some embodiments, before inputting the preset process rule set and the assembly logic file into the process report generation model to generate the electrical assembly process report, the method further includes:

[0026] Collect historical electrical assembly images, historical material lists, and historical electrical assembly process reports to form an electrical assembly data sample set;

[0027] Preprocessing the electrical assembly data sample set to obtain a standard electrical assembly data sample set;

[0028] The standard electrical assembly data sample set is input into a universal language model for optimization training to obtain the trained process report generation model.

[0029] In a second aspect, an embodiment of the present application provides an electrical assembly process report generation system, comprising:

[0030] An image acquisition module, which acquires electrical assembly images;

[0031] an image recognition module, performing image recognition on the electrical assembly image to obtain contour information in the electrical assembly image;

[0032] a character recognition module, performing character recognition on the electrical assembly image to obtain technical requirement information of the electrical assembly image and position number information of each component;

[0033] A matrix acquisition module, which obtains an adjacency matrix of the electrical assembly image according to the outline information and each bit number information;

[0034] An assembly logic file generation module, inputting the outline information, the adjacency matrix, the technical requirement information and each bit number information into a graph neural network to generate an assembly logic file;

[0035] The report generation module inputs the preset process rule set and the assembly logic file into the process report generation model to generate an electrical assembly process report.

[0036] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the above-mentioned method for generating an electrical assembly process report.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed on a processor, implements the above-mentioned method for generating an electrical assembly process report.

[0038] The embodiments of the present application have the following beneficial effects:

[0039] The electrical assembly process report generation method of the embodiment of the present application includes: obtaining an electrical assembly image; performing image recognition on the electrical assembly image to obtain contour information in the electrical assembly image; performing character recognition on the electrical assembly image to obtain technical requirement information of the electrical assembly image and position number information of each component; obtaining an adjacency matrix of the electrical assembly image based on the contour information and each position number information; inputting the contour information, adjacency matrix, technical requirement information and each position number information into a graph neural network to generate an assembly logic file; inputting a preset process rule set and the assembly logic file into a process report generation model to generate an electrical assembly process report. The electrical assembly image information is extracted through character recognition and image recognition, and the process report generation model is automatically generated into an electrical assembly process report in combination with the process rules, which greatly improves the efficiency and accuracy of report generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A first flow chart of a method for generating an electrical assembly process report according to an embodiment of the present application is shown;

[0042] Figure 2 A second flow chart of the method for generating an electrical assembly process report according to an embodiment of the present application is shown;

[0043] Figure 3 A third flow chart of the method for generating an electrical assembly process report according to an embodiment of the present application is shown;

[0044] Figure 4 A fourth flow chart of the method for generating an electrical assembly process report according to an embodiment of the present application is shown;

[0045] Figure 5 A fifth flow chart of the method for generating an electrical assembly process report according to an embodiment of the present application is shown;

[0046] Figure 6 A structural schematic diagram of an electrical assembly process report generation system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0048] The components of the embodiments of the present application generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but rather merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort are within the scope of protection of the present application.

[0049] Hereinafter, the terms "including", "having" and their cognates used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the aforementioned items, and should not be understood as excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the aforementioned items or adding the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the aforementioned items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and should not be understood as indicating or implying relative importance.

[0050] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as in the context of the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0051] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0052] Considering the existing technology, the preparation of electrical assembly process reports relies on manual identification of drawings, searching for component parameters, and manually writing process reports, which leads to low efficiency, prone to errors, and poor standardization, seriously affecting production efficiency and product quality consistency. This application provides a method, system, and computer device for generating electrical assembly process reports. These methods extract electrical assembly image information through character recognition and image recognition, and combine process rules to enable a process report generation model to automatically generate electrical assembly process reports, greatly improving the efficiency and accuracy of report generation.

[0053] The electrical assembly process report generation method is described below with reference to some specific embodiments.

[0054] Figure 1A flow chart of a method for generating an electrical assembly process report according to an embodiment of the present application is shown. It is understood that the electrical assembly process report can be in the form of a process document or in natural language. The electrical assembly process report includes the assembly sequence, wiring logic, and process requirements of each component. Exemplarily, the report generation method is executed by a processor in a computer device and includes steps S101 to S106:

[0055] S101, acquiring an electrical assembly image.

[0056] It is understandable that the relevant functions of OpenCV can be used to load drawings and convert them into image formats. The user uploads the electrical assembly image and saves it to the database. The processor obtains the electrical assembly image from the database. It is understandable that the electrical assembly image can be an image in any format, such as DWG format or PDF format.

[0057] In one embodiment, the electrical assembly image can be a two-dimensional planar structure image or a three-dimensional spatial structure image. For example, a two-dimensional planar structure electrical assembly image includes the position number, two-dimensional planar structure and angle of each component, as well as textual information such as technical requirements, and can describe the two-dimensional planar structure position relationship, connection relationship, and assembly requirements of each component; a three-dimensional spatial structure electrical assembly image includes the position number, three-dimensional spatial structure and angle of each component, as well as textual information such as technical requirements, and can describe the three-dimensional spatial structure position relationship, connection relationship, and assembly requirements of each component.

[0058] S102: Perform image recognition on the electrical assembly image to obtain contour information in the electrical assembly image.

[0059] Image recognition algorithms are used to perform image recognition to extract contour information from the image. Contour information includes the position, size, and shape of the contours of each component in the image, as well as the position, size, and shape of the contours of the connecting lines.

[0060] For example, in one embodiment, Figure 2 As shown, S102 includes the following sub-steps:

[0061] S201 , using OpenCV to extract the contours in the electrical assembly image, to obtain contour information of each connection line, contour information of each component, and center coordinates of each component.

[0062] OpenCV is a computer vision library with rich image processing and computer vision functions. Furthermore, before contour extraction, the image can be preprocessed. Specifically, the image can be loaded using the relevant functions of OpenCV and converted into the required image format. Alternatively, before contour extraction, if the processor receives an electrical assembly drawing, the drawing can also be preprocessed. Specifically, the drawing can be loaded using the relevant functions of OpenCV and converted into an image format. The color image can then be converted into a grayscale image, and Gaussian blur can be used to remove image noise. The denoised image can then be converted into a binary image to facilitate contour extraction.

[0063] Next, an edge detection function (such as Canny edge detection) is used to extract all contours in the image, including the contours of each component and each connecting line. Geometric features such as area, perimeter, and center coordinates of each contour are calculated. It is understood that the contours in the electrical assembly image can be two-dimensional or three-dimensional. For two-dimensional contours, the contours of each component represent the two-dimensional structure of each component. For three-dimensional contours, the contours of each component represent the three-dimensional structure of each component.

[0064] S202 , using the visual macro model to classify the contour information of each component to obtain each contour category, and based on each connection line contour information, obtain the connection relationship of each component, the contour information includes each center coordinate, each contour category and the connection relationship.

[0065] Specifically, the large visual model can be selected according to the actual application situation. A model based on a convolutional neural network, a model based on a Transformer architecture, or a hybrid model combining the two can be selected.

[0066] Exemplarily, the model is trained using the templates or features of the components so that the model can obtain the component type corresponding to the outline through the outline information or outline features of each component. The outline information of each component is input into the model so that the model compares the outline information of each component with the known component template to identify the type of component; or the outline features of each component are input into the model so that the model compares the outline features of each component with the features of the component to identify the specific component type, such as resistors, capacitors, switches, etc.

[0067] A connection line detection model can be configured, and the contour information of each connection line is input into the connection line detection model to extract the path information of the connection line.

[0068] OpenCV and the visual big model are used to perform image recognition on electrical assembly images to obtain the contour information of the electrical assembly images. OpenCV can quickly and accurately extract key contour information from electrical assembly images, and the visual big model can further improve the accuracy of contour extraction, greatly improving processing speed and accuracy, while reducing the risk caused by human error.

[0069] S103 , performing character recognition on the electrical assembly image to obtain technical requirement information of the electrical assembly image and bit number information of each component.

[0070] Use OCR tools such as Tesseract and PaddleOCR to extract text from images, obtain the component part number information and the technical requirements information in the image, match the extracted part number information with the component outline information, and determine the part number of each component outline information. Use OCR to recognize the characters in the image and obtain the technical requirements and part number information of the image. OCR technology can quickly scan and recognize large numbers of images, greatly reducing the time spent on manual reading and recording. It can also convert the extracted information into a standardized data format for subsequent processing and analysis. This improves work efficiency, reduces errors, and reduces labor costs.

[0071] S104: Obtain an adjacency matrix of the electrical assembly image based on the outline information and each bit number information.

[0072] Based on the position information, center coordinates, and connection relationships, an adjacency matrix is ​​generated, with each component as a node. Edge weights in this adjacency matrix can be set based on the actual application. For example, edge weights include the distance between nodes and the connection type. If the electrical assembly image is a three-dimensional spatial structure image, the edge weights in the adjacency matrix may also include the hierarchical relationships between nodes.

[0073] Specifically, each component is regarded as a node, and information such as the component type, center coordinates, and position number are recorded. A node list is constructed for all components according to the position number, and an initial adjacency matrix is ​​created. The initial value is set to infinity or zero, indicating that there is no direct connection between nodes.

[0074] The distance between components is calculated based on the path information of the connecting lines. The connecting lines and components are matched to obtain the connection relationship of each component. The connection type between each pair of components is determined from the connection relationship data. The connection type is converted into a numerical weight coefficient. The distance between each node is calculated. The distance between the nodes and the weight coefficient of the connection type are combined to form a comprehensive weight. The comprehensive weight is written into the initial adjacency matrix, and the initial adjacency matrix is ​​updated until all connection relationships are processed.

[0075] Based on the contour information and each bit number information, the adjacency matrix of the electrical assembly image is obtained. The adjacency matrix is ​​a structured data representation method that can clearly show the connection relationship between components and facilitate computer program processing. Through the adjacency matrix, more reasonable component layout and wiring planning can be carried out, reducing routing length and reducing electromagnetic interference.

[0076] S105: Input the outline information, adjacency matrix, technical requirement information and each position number information into the graph neural network to generate an assembly logic file.

[0077] Specifically, if the image is an electrical assembly image of a three-dimensional spatial structure, the contour information includes the three-dimensional spatial structure of each component. The contour information, adjacency matrix, technical requirement information and each position number information can be directly input into the graph neural network to generate an assembly logic file. If the image is an image of a two-dimensional plane structure, it is necessary to obtain the three-dimensional spatial structure of each component, and then input the three-dimensional spatial structure information, contour information, adjacency matrix, technical requirement information and each position number information into the graph neural network to generate an assembly logic file.

[0078] For example, in one embodiment, Figure 3 As shown, after obtaining the adjacency matrix, the electrical assembly process report generation method further includes S301-S303:

[0079] S301, obtain the material list.

[0080] Specifically, the bill of materials includes the part numbers and model numbers of each component in the electrical assembly image, with the part numbers and model numbers corresponding one to one. Users can upload the bill of materials in advance and save it to the database, from which the processor retrieves the bill of materials. The bill of materials can be in any format; exemplarily, it is in Word format.

[0081] S302: Query the model information of each component corresponding to each bit number information in the material list.

[0082] You can use the hash table to query the material details table to obtain the corresponding model of each component.

[0083] S303 , obtaining three-dimensional spatial structure information of each component from a preset component database according to each model information.

[0084] It is understood that the preset component database stores the three-dimensional structure and model of various components, and the component model corresponds to the three-dimensional structure of the component. Furthermore, the database can also include information such as the material and weight of the component.

[0085] Based on the model of each component as the primary key, the corresponding record is searched in the preset component database to obtain the three-dimensional spatial structure information of the component, the three-dimensional spatial structure information of the component is read from the database, and the structure of the three-dimensional spatial structure information is converted and output according to the actual application situation. For example, the three-dimensional spatial structure information can be converted into JSON format.

[0086] Look up the model number in the material list according to the position number, and obtain the three-dimensional spatial structure information based on the model number. Through the three-dimensional spatial structure information, the position of each component in the assembly can be determined more accurately, thereby optimizing the overall layout and improving assembly efficiency and quality.

[0087] S304: Input the three-dimensional spatial structure information, contour information, adjacency matrix, various position number information and technical requirement information into the graph neural network to generate an assembly logic file.

[0088] Specifically, each component can be used as a node of the graph to construct a graph structure. The characteristics of the node are set as three-dimensional spatial structure information, contour information, adjacency matrix and position number information. The edges of the graph are constructed according to the adjacency matrix. The characteristics of the edges include distance, connection type, hierarchical relationship and technical requirement information, etc. The technical requirement information can also be used as a global feature and input into the graph neural network.

[0089] Use graph neural network models such as graph convolutional networks or graph attention networks to process graph structure data to obtain assembly logic. The assembly logic output by the model can be converted into a specific assembly logic file format, such as XML format, JSON format, etc. The assembly logic file can include information such as assembly sequence, assembly path, and assembly tool selection.

[0090] Inputting three-dimensional spatial structure information, contour information, adjacency matrix, various position number information and technical requirement information into the graph neural network to generate assembly logic files can optimize the assembly sequence, improve assembly accuracy, and also improve the accuracy and consistency of process reports.

[0091] S106 , inputting the preset process rule set and the assembly logic file into the process report generation model to generate an electrical assembly process report.

[0092] It is understood that the preset process rule geometry may include process constraints, operating specifications, priorities, and standard procedures, etc. The preset process rule set and assembly logic file are input into the process report generation model. Before generating the electrical assembly process report, the model may be trained using historical data.

[0093] For example, in one embodiment, Figure 4 As shown, the training method includes S401-S403:

[0094] S401, collecting historical electrical assembly images, historical material lists, and historical electrical assembly process reports to form an electrical assembly data sample set.

[0095] After classifying each data, relevant information is extracted to form an electrical assembly data sample set.

[0096] S402 , preprocessing the electrical assembly data sample set to obtain a standard electrical assembly data sample set.

[0097] Specifically, the data in the electrical assembly data sample set can be cleaned and converted. Furthermore, a small amount of noise can be added to the data to improve the robustness of the model.

[0098] S403: Input the standard electrical assembly data sample set into the general language model for optimization training to obtain a trained process report generation model.

[0099] You can choose to optimize and train models based on rules or machine learning. For example, a model based on the Transformer architecture was used to train a general language model using a standard electrical assembly data sample set. This model extracts key information from the input data and generates a complete report according to a predefined template. The module can be configured based on the actual application to ensure that the generated report content is accurate, formatted in a standardized manner, and meets practical requirements.

[0100] The preset process rule set and assembly logic file are input into the trained model, the constraints and operation requirements are extracted from the process rules, and the component connection sequence and operation steps are extracted from the assembly logic. The model performs reasoning based on the input process rules and assembly logic to generate an electrical assembly process report.

[0101] Through the automated process report generation model, preset process rules and assembly logic can be quickly integrated, thereby significantly reducing the time for manually writing process reports. The preset process rule set can provide unified standards and specifications for the entire process, ensuring that each generated process report follows the same technical requirements and operating specifications, significantly improving the standardization of electrical assembly processes.

[0102] Furthermore, after the electrical assembly process report is generated, a process specification card may be generated according to the content of the electrical assembly process report. For example, in one embodiment, Figure 5 As shown, after S106, the process specification card is generated through the following sub-steps:

[0103] S501: extract information from the electrical assembly process report using a regular expression according to a preset standard template.

[0104] Preset standard templates can be customized based on actual application needs. For example, a standard template can be created based on the process standards of different companies. Standard templates can include formatted process cards, for example. Regular expressions are used to analyze electrical assembly process reports and extract key fields that need to be populated on the process cards, such as process name, equipment parameters, and operating steps.

[0105] S502, filling the extracted information into a preset standard template to generate a process procedure card.

[0106] Output templates can be automatically adjusted based on the process standard libraries of different companies to ensure that the generated process cards fully meet company requirements. Furthermore, format verification and version management can be performed on process cards. This automated process from electrical images to process cards significantly improves process compilation efficiency.

[0107] like Figure 6 As shown, based on the method of the above embodiment, this embodiment provides an electrical assembly process report generation system. Exemplarily, the electrical assembly process report generation system 100 includes:

[0108] An image acquisition module 110 acquires an electrical assembly image;

[0109] An image recognition module 120 performs image recognition on the electrical assembly image to obtain contour information in the electrical assembly image;

[0110] The character recognition module 130 performs character recognition on the electrical assembly image to obtain technical requirements information of the electrical assembly image and the position number information of each component;

[0111] The matrix acquisition module 140 obtains the adjacency matrix of the electrical assembly image based on the contour information and each bit number information;

[0112] The assembly logic file generation module 150 inputs the outline information, adjacency matrix, technical requirements information and each bit number information into the graph neural network to generate the assembly logic file;

[0113] The report generation module 160 inputs the preset process rule set and the assembly logic file into the process report generation model to generate an electrical assembly process report.

[0114] It can be understood that the system of this embodiment corresponds to the control method of the above embodiment, and the optional items in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0115] The present application also provides a computer device. Exemplarily, the computer device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the device to execute the functions of the various modules in the above-mentioned electrical assembly process report generation method or the above-mentioned electrical assembly process report generation system.

[0116] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, etc., and can implement or execute the various methods, S, and logic block diagrams disclosed in the embodiments of this application.

[0117] The memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), and electrically erasable programmable read-only memory (EEPROM). The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.

[0118] This application also provides a computer-readable storage medium for storing a computer program used in the aforementioned computer device. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or flowchart, and the combination of boxes in the structure diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0120] In addition, the functional modules or units in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0121] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a smart phone, personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0122] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for generating an electrical assembly process report, characterized in that: The method comprises: Acquire electrical assembly images; Performing image recognition on the electrical assembly image to obtain contour information in the electrical assembly image, including: extracting contours in the electrical assembly image using OpenCV to obtain contour information of each connecting line, contour information of each component, and center coordinates of each component; Using a visual macro model to classify the contour information of each component to obtain each contour category, and obtaining a connection relationship between each component based on the contour information of each connection line, the contour information including each center coordinate, each contour category, and the connection relationship; Performing character recognition on the electrical assembly image to obtain technical requirement information of the electrical assembly image and bit number information of each component; Obtaining an adjacency matrix with each component as a node according to each of the bit number information, each of the center coordinates, and the connection relationship; Get the material list; Query the model information of each component corresponding to each bit number information in the material list; Obtaining the three-dimensional spatial structure information of each component in a preset component database according to each model information; Inputting the three-dimensional spatial structure information, the contour information, the adjacency matrix, each of the position number information and the technical requirement information into a graph neural network to generate an assembly logic file; The preset process rule set and the assembly logic file are input into a process report generation model to generate an electrical assembly process report.

2. The method for generating an electrical assembly process report according to claim 1, wherein: The edge weights of the adjacency matrix include: the distance between the nodes and the connection type.

3. The method for generating an electrical assembly process report according to claim 1, wherein: After inputting the preset process rule set and the assembly logic file into the process report generation model to generate the electrical assembly process report, the method further includes: Extracting information from the electrical assembly process report using regular expressions according to a preset standard template; The extracted information is filled into the preset standard template to generate a process procedure card.

4. The method for generating an electrical assembly process report according to claim 1, wherein: Before inputting the preset process rule set and the assembly logic file into the process report generation model to generate the electrical assembly process report, the method further includes: Collect historical electrical assembly images, historical material lists, and historical electrical assembly process reports to form an electrical assembly data sample set; Preprocessing the electrical assembly data sample set to obtain a standard electrical assembly data sample set; The standard electrical assembly data sample set is input into a universal language model for optimization training to obtain the trained process report generation model.

5. An electrical assembly process report generation system, characterized in that: include: An image acquisition module, which acquires electrical assembly images; An image recognition module performs image recognition on the electrical assembly image to obtain contour information in the electrical assembly image, including: extracting contours in the electrical assembly image using OpenCV to obtain contour information of each connecting line, contour information of each component, and center coordinates of each component; Using a visual macro model to classify the contour information of each component to obtain each contour category, and obtaining a connection relationship between each component based on the contour information of each connection line, the contour information including each center coordinate, each contour category, and the connection relationship; a character recognition module, performing character recognition on the electrical assembly image to obtain technical requirement information of the electrical assembly image and position number information of each component; A matrix acquisition module, which obtains an adjacency matrix with each of the components as a node according to each of the bit number information, each of the center coordinates and the connection relationship; Material list acquisition module, to obtain the material list; A model query module is configured to query the model information of each component corresponding to each bit number information in the material list; a three-dimensional spatial structure information acquisition module, which acquires the three-dimensional spatial structure information of each component from a preset component database based on the model information; an assembly logic file generation module, which inputs the three-dimensional spatial structure information, the outline information, the adjacency matrix, the respective bit number information, and the technical requirement information into a graph neural network to generate an assembly logic file; The report generation module inputs the preset process rule set and the assembly logic file into the process report generation model to generate an electrical assembly process report.

6. A computer device, characterized in that: The computer device comprises: a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the method for generating an electrical assembly process report according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The device stores a computer program, which, when executed on a processor, implements the method for generating an electrical assembly process report according to any one of claims 1 to 4.

Images