Technological process card generation method and device based on CAD drawing and storage medium

Abstract

The invention relates to a technical process card generation method and device based on a CAD drawing and a storage medium, and the technical process card generation method comprises the steps: obtaining the CAD drawing, and carrying out the preprocessing of the CAD drawing; key information extraction is completed through visual understanding and natural language processing capability of the multi-modal large model; based on the drawing key information, processing rules are matched, and a technological process card is generated; and constructing a data set, performing fine tuning on the multi-modal large model, and completing the production process card by using the multi-modal large model after fine tuning. According to the technical scheme of the invention, the generation efficiency and quality of the technical process card can be improved, and errors and uncertainty caused by manual intervention can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and mechanical processing technology, and in particular to a method, device and storage medium for generating a process card based on a CAD drawing. Background Art

[0002] In the manufacturing process of existing technology, the preparation of process cards is mainly done manually. Process personnel need to carefully study CAD drawings and extract various key information from them, such as the size, shape, tolerance requirements, material properties, etc. of parts. Then, based on their own experience and process knowledge, they determine the processing procedures, select processing equipment, calculate processing hours, and fill in this information one by one in the process card. This manual preparation method has many disadvantages:

[0003] (1) Manual reading and analysis of CAD drawings is prone to errors and omissions. CAD drawings usually contain a large amount of complex graphics and text information. Human attention and energy are limited. Long hours of work can easily lead to fatigue and negligence, resulting in inaccurate or incomplete information extracted, which in turn affects the quality of process cards and may lead to processing errors, increased scrap, and low production efficiency during the production process.

[0004] (2) Manual preparation of process cards is inefficient. For complex product drawings, process personnel may need to spend hours or even days to complete the preparation of a process card. This seriously restricts the company's production progress and market response speed in the modern manufacturing environment of large-scale production and rapid product updates.

[0005] (3) Manually compiling process cards is highly dependent on the experience and skills of process personnel. Different process personnel may formulate different processing techniques based on their own experience and understanding, which makes it difficult to ensure the consistency of process cards, which is not conducive to the standardized production and quality management of the enterprise.

[0006] Therefore, it is urgent to design an efficient, accurate and universal method for automatically generating process cards based on CAD drawings. Summary of the invention

[0007] In order to solve the technical problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a process card generation method, equipment and storage medium based on CAD drawings, which can improve the generation efficiency and quality of process cards and reduce the errors and uncertainties caused by human intervention.

[0008] To achieve the above-mentioned object of the invention, the present invention provides a method for generating a process card based on a CAD drawing, comprising the following steps:

[0009] Step S1, obtaining a CAD drawing and preprocessing the CAD drawing;

[0010] Step S2: extract key information through the visual understanding and natural language processing capabilities of the multimodal large model;

[0011] Step S3, based on the key information of the drawing, matching the processing rules, and generating a process card;

[0012] Step S4: construct a data set and fine-tune the multimodal large model.

[0013] According to a technical solution of the present invention, the step S1 specifically includes:

[0014] Step S11, obtaining a CAD drawing, and converting the CAD drawing into an image format recognizable by the multimodal large model;

[0015] Step S12: Divide the drawing in image format into regions to obtain a drawing view region, a text description region and a table content region.

[0016] According to a technical solution of the present invention, in step S2, for the extraction of table content, the visual understanding and natural language processing capabilities of the multimodal large model are used to directly identify and parse the structured information in the table and convert it into text data for subsequent processing;

[0017] For the text description area, the visual understanding and natural language processing capabilities of the multimodal large model are used to extract text information and capture technical requirements and process annotations.

[0018] According to a technical solution of the present invention, in step S2, the view information is extracted into single view information extraction and multi-view information extraction;

[0019] For single-view information extraction, multimodal large models are used to identify part features and annotation information, and relevant parameter data is directly extracted;

[0020] For multi-view information extraction, the reasoning method of thinking chain COT is adopted to determine the required parameters step by step to ensure the completeness and accuracy of information extraction.

[0021] According to a technical solution of the present invention, the file format of the CAD drawing includes DWG, DXF or other formats supported by other CAD software;

[0022] The image formats recognizable by the multimodal large model include at least BMP format, JPEG format, GIF format, TIFF format, and PNG format.

[0023] According to a technical solution of the present invention, the COT method of extracting multi-view information specifically includes:

[0024] Step S201: Divide all views of the drawing to clarify the types and quantities of existing views;

[0025] Step S202: Select the optimal view for extracting relevant information according to preset rules and logic;

[0026] Step S203: perform integrity verification and calculation on the extracted relevant information.

[0027] According to a technical solution of the present invention, in the step S3, based on the key information of the drawing, the predefined processing rules are matched, and the processing rules are stored in the form of; the corresponding processing rules are obtained by parsing the Excel table through code;

[0028] Any of the processing rules presets judgment conditions based on key parameters of the drawing and technical requirements. When the extracted drawing information meets the corresponding judgment conditions, the corresponding process will be determined and added to the process card.

[0029] According to a technical solution of the present invention, in step S4, a data set is constructed, and the data set includes a text pair of a CAD drawing and an expected large model output, and the text pair includes: text content obtained based on a table content area, text content obtained based on a text description area, and parameters to be extracted obtained based on a drawing view area.

[0030] According to one aspect of the present invention, there is provided an electronic device, comprising: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, and the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory, so that the electronic device executes a method for generating a process card based on a CAD drawing as described in any one of the above technical solutions.

[0031] According to one aspect of the present invention, a non-transitory readable storage medium is provided for storing computer instructions. When the computer instructions are executed by a processor, a method for generating a process card based on a CAD drawing as described in any one of the above technical solutions is implemented.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention proposes a method, device and storage medium for generating process cards based on CAD drawings. A multimodal large model is used to automatically generate process cards from CAD drawings, which abandons the traditional method of manually extracting information and compiling process cards. The drawings can be quickly parsed and information extracted, which greatly shortens the time for generating process cards, is conducive to improving the generation efficiency and quality of process cards, and reducing errors and uncertainties caused by manual intervention.

[0034] In the present invention, in the link of extracting key information from drawings, the multimodal large model accurately divides the drawing area, including the view area, the text description area and the table content area, and uses its powerful visual understanding and natural language processing capabilities to perform identification and extraction, so as to accurately obtain various key information and avoid errors such as negligence and misjudgment that may occur in manual reading and recording, thereby significantly improving the accuracy of information extraction and further ensuring the accuracy of the process card.

[0035] In the present invention, since the multimodal large model extracts information and generates process cards according to preset procedures and algorithms, its processing process is highly consistent. Compared with manual operation, which may cause inconsistent content of process cards due to factors such as personnel experience, skill level and working status, the present invention can ensure that the generation of each process card follows the same standards and procedures, thereby ensuring the consistency of the process cards and facilitating the standardization and normalization of the production process.

[0036] Compared with the method of parsing preset template parameters by software, the technology based on the multimodal large model of the present invention does not rely on the specific format and structure of the original file, solves the problem that the software parsing the preset template parameters usually requires the drawings to meet specific format requirements, and has low requirements on the integrity and standardization of the original file. The present invention only needs to convert the CAD drawings into an image format that can be recognized by the multimodal large model to complete the generation of the process card, that is, only the drawing image is needed to extract the drawing information, which is not limited by the original file format and content details, has stronger versatility, can adapt to CAD drawings of different sources and formats, and broadens the application scope of this technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 The flowchart of the method for generating a process card based on a CAD drawing provided in accordance with one embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0039] The description of the embodiments of this specification should be combined with the corresponding drawings, which should be considered as part of the complete specification. In the drawings, the shape or thickness of the embodiments may be enlarged and indicated for simplification or convenience. Furthermore, the parts of each structure in the drawings will be described separately. It is worth noting that the elements not shown in the drawings or not described in words are in a form known to ordinary technicians in the relevant technical field.

[0040] The description of the embodiments herein and any reference to directions and orientations are only for the convenience of description and are not to be construed as any limitation on the scope of protection of the present invention. The following description of the preferred embodiments may involve combinations of features, which may exist independently or in combination, and the present invention is not particularly limited to the preferred embodiments. The scope of the present invention is defined by the claims.

[0041] like Figure 1 As shown, the method for generating process cards based on CAD drawings of the present invention has the characteristics of high efficiency, high accuracy, high consistency and good versatility, can improve the generation efficiency and quality of process cards, and reduce errors and uncertainties caused by manual intervention.

[0042] like Figure 1 As shown, a method for generating a process card based on a CAD drawing of the present invention comprises the following steps:

[0043] Step S1: Obtain CAD drawings and preprocess the CAD drawings, specifically including:

[0044] Step S11, obtaining a CAD drawing, and converting the CAD drawing into an image format recognizable by the multimodal large model;

[0045] Step S12: Divide the drawing in image format into regions to obtain a drawing view region, a text description region and a table content region.

[0046] Before generating the process card, it is necessary to convert CAD drawings of various formats (DWG, DXF or other formats supported by CAD software, etc.) into image formats that can be recognized by the multimodal large model (such as BMP format, JPEG format, GIF format, TIFF format, PNG format, etc.), to ensure that the converted image can accurately and completely retain all the information in the CAD drawing, including graphics, text, dimensioning, etc. Through a specific conversion algorithm (such as using CAD to directly export the file to a picture format, or using other software to convert it into other formats that are faster recognized by the multimodal large model), the vector data in the CAD drawing is converted into image data represented by pixels. Different image formats have different data compression and storage algorithms. The fundamental goal is to present the CAD drawing to the multimodal large model in the form of pixels.

[0047] After the drawing format conversion is completed, the image is divided into regions. Using image analysis technology and preset region division rules, the drawing is divided into different regions, mainly including the drawing view region, text description region and table content region.

[0048] The drawing view area includes the main view, left view, bottom view, etc. These view areas contain the shape and size information of the parts; the text description area includes text description information such as technical requirements and processing precautions; the table content area includes information in tabular form such as figure number, name, material specification, quantity, etc. The purpose of regional division is to improve the accuracy and pertinence of information extraction from multi-modal large models, so that the model can more efficiently identify and extract key information in each area and avoid information confusion and erroneous extraction.

[0049] Step S2: Extract key information through the visual understanding and natural language processing capabilities of the multimodal large model. The table content area and text area use the OCR-like capabilities of the large model. Input the prompt words and pictures to the large model to obtain the table content and text information. For information that needs to be extracted from the drawing view, such as height, width, holes, etc., the simple ones can be directly identified by identifying the features of the components to find out the parameters of the components, while the complex ones need to be obtained through reasoning.

[0050] Prompt words refer to the instructions input to the big model, which can be understood as instructing the big model what to do and how to do it.

[0051] For the extraction of table content, the visual understanding and natural language processing capabilities of the multimodal large model are used to directly identify and parse the structured information in the table and convert it into text data for subsequent processing;

[0052] For the divided table area, its image is input into the multimodal large model and combined with the corresponding prompt words. The multimodal large model uses its visual understanding and natural language processing capabilities to identify and parse the content in the table. The prompt words serve as instructions to tell the large model which fields and information in the table need to be paid attention to, such as "extract part name, drawing number and material specification". In this way, the multimodal large model can accurately extract the key information in the table and convert it into a structured data format for subsequent use in process card generation.

[0053] For the text description area, the visual understanding and natural language processing capabilities of the multimodal large model are used to extract text information and capture technical requirements and process annotations.

[0054] For the text description area, its image and specific prompt words are also input into the multimodal large model. The multimodal large model extracts key information such as technical requirements, processing technology description, and quality control points by recognizing and understanding the text. The above key information in text form plays an important guiding role in determining the processing procedures, selecting processing equipment, and formulating processing parameters. It can make the generated process card more in line with actual production needs and ensure the processing quality and performance of the product.

[0055] View information extraction is divided into single view information extraction and multi-view information extraction.

[0056] For single-view information extraction, multimodal large models are used to identify part features and annotation information, and relevant parameter data is directly extracted;

[0057] When all the parameters required for a machining process are in a single view, the multimodal large model identifies and analyzes the features of the part in that view. For example, for a gear part, if its thickness and aperture parameters only need to be obtained in the main view, the multimodal model will use a specific feature extraction algorithm to identify the gear's profile, hole shape and other features, and accurately extract the thickness and aperture values. Single view information recognition can quickly and accurately obtain the parameters required for some machining processes, improving the efficiency and accuracy of information extraction.

[0058] For multi-view information extraction, the COT reasoning method is used to determine the required parameters step by step to ensure the integrity and accuracy of information extraction. The COT method of multi-view information extraction specifically includes:

[0059] Step S201: Divide all views of the drawing to clarify the types and quantities of existing views;

[0060] Step S202: Select the optimal view for extracting relevant information according to preset rules and logic;

[0061] Step S203: perform integrity verification and calculation on the extracted relevant information.

[0062] Example 1: Taking the extraction of height and width parameters as an example, the specific steps include: first, comprehensively sort out and divide all views of the drawing to clarify the types and quantities of existing views; second, according to the preset rules and logic, select the view that is most suitable for extracting height and width information. For example, when there is an expanded view, obtain relevant dimension information from the expanded view first; finally, verify and calculate the integrity of the extracted height and width data to determine whether the height and width cover the part size. For incomplete annotations, the model automatically extracts the segmented annotation data and obtains accurate height and width values ​​through mathematical operations to meet the needs of subsequent process planning.

[0063] Example 2: Taking the extraction of bending (angle, radius, length) parameters as an example, the specific operations are as follows: Step 1, divide all views of the drawing to clarify the types and number of views that exist; Step 2, carefully search for the location information of the bend in each view according to the preset rules and logic, determine whether there is a bend in the drawing and the specific location and number of the bend; Step 3, accurately extract the bending angle and radius. These parameters are usually marked near the bend, and the model accurately locates and extracts them through its recognition ability; Step 4, find the bend line in the unfolded view and extract its length information; Step 5, for the case where there are multiple bends, match and integrate the information according to a specific direction order (such as from right to left or the opposite direction) and the position relationship of the bend, complete the integrity verification and calculation, ensure that the extracted bending information combination is accurate, and provide reliable data support for the subsequent processing technology formulation.

[0064] Step S3, based on the key information of the drawing, matching the processing rules, and generating a process card;

[0065] Based on the key information of the drawing, match the predefined processing rules, which are stored in the form of; parse the Excel table through code to obtain the corresponding processing rules;

[0066] Any of the processing rules presets judgment conditions based on key parameters of the drawing and technical requirements. When the extracted drawing information meets the corresponding judgment conditions, the corresponding process will be determined and added to the process card.

[0067] Processing rules can be stored in an Excel table in a simple mapping relationship. Each rule sets specific judgment conditions and corresponding process steps, process content, processing equipment, and time calculation methods. For example, when the height and width of the extracted parts are greater than the set threshold, the processing rules may specify the addition of a shot blasting process to improve the surface quality of the parts; for parts with threaded holes, regardless of the size of the threaded holes, a tapping process is required. By writing code to parse and match the processing rules in the Excel table, when the extracted drawing information meets the judgment conditions of a certain rule, the process steps and content corresponding to the rule are added to the process card, and the equipment required for the process and the estimated processing time are determined according to the processing equipment and time calculation method specified in the rule. Through the automated rule matching process, process cards that meet production requirements can be generated quickly and accurately, greatly improving the generation efficiency and standardization of process cards.

[0068] Step S4: construct a data set and fine-tune the multimodal large model;

[0069] A data set is constructed, wherein the data set includes a text pair of a CAD drawing and an expected large model output, wherein the text pair includes: text content obtained based on a table content area, text content obtained based on a text description area, and parameters to be extracted obtained based on a drawing view area.

[0070] In order to further improve the performance and accuracy of the multimodal large model in CAD drawing information extraction, four corresponding data sets are prepared for different information extraction tasks such as table content area, text description area, single view recognition area, and multi-view recognition area. One data set including table content area, text description area, and single view recognition area and another data set including table content area, text description area, and multi-view recognition area can also be prepared. The data set consists of a large number of CAD drawing image samples and text pairs expected to be output by the multimodal large model. For example, in the table dataset, various types of CAD drawing images and corresponding table content texts are included; in the text description dataset, drawings with different text descriptions and corresponding text information texts are collected; in the view recognition dataset, not only drawings images are included, but also detailed annotations of the parameters to be extracted and the thinking chain COT reasoning process used in multi-view information extraction. Taking hole recognition as an example, it is necessary to identify the position and size of the hole. The text content is: This mechanical drawing has 3 hole marks: there is 1 hole with a diameter of 30mm, marked as Φ30H8, located at (384,163), (467,193); there are 3 holes with a diameter of 14mm, marked as 3×M14, located at (449,379), (480,398); there are 4 holes with a diameter of 10mm, marked as 4×M10, located at (314,677), (344,695). Then, 1+3+4=8, so there are 8 holes in total. .

[0071] By inputting the above data sets into the multimodal large model, the preset fine-tuning algorithms and training strategies, such as SFT (Supervised Fine-Tuning), are used to adjust and optimize the parameters of the model so that it can better adapt to the task of CAD drawing information extraction. It should be noted that if the multimodal large model already has a strong information extraction capability in the initial state and can meet the requirements of accuracy and efficiency in the actual process card generation application, then the model can be used directly without fine-tuning; however, if the model performs poorly on some complex drawings or specific information extraction tasks, or in order to further improve the performance and adaptability of the model, it can be fine-tuned through the data set to continuously optimize the parameters and structure of the model, thereby improving its overall performance in CAD drawing information extraction and process card generation, and providing more reliable and efficient technical support for manufacturing production.

[0072] The production process card is completed using the fine-tuned multimodal macro model.

[0073] The fine-tuned multimodal large model is deployed to the server, and reasoning is performed based on the input CAD drawings to generate process cards.

[0074] Among them, step S1 to step S3 are the work flow, and step S4 is the fine-tuning process. The fine-tuning is to obtain a powerful multi-modal large model, and the work is to use the capabilities of the large model to generate process cards.

[0075] According to one aspect of the present invention, there is provided an electronic device, comprising: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, and the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory, so that the electronic device executes a method for generating a process card based on a CAD drawing as described in any one of the above technical solutions.

[0076] According to one aspect of the present invention, a non-transitory readable storage medium is provided for storing computer instructions. When the computer instructions are executed by a processor, a method for generating a process card based on a CAD drawing as described in any of the above technical solutions is implemented.

[0077] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0078] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] It should also be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0081] Finally, it should be noted that the above is a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for those skilled in the art, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A method for generating a process card based on a CAD drawing, characterized in that: The following steps are involved: Step S1, obtaining a CAD drawing and preprocessing the CAD drawing; Step S2: extract key information through the visual understanding and natural language processing capabilities of the multimodal large model; Step S3, based on the key information of the drawing, matching the processing rules, and generating a process card; Step S4: construct a data set and fine-tune the multimodal large model.

2. The method for generating a process card based on a CAD drawing according to claim 1, characterized in that: The step S1 specifically includes: Step S11, obtaining a CAD drawing, and converting the CAD drawing into an image format recognizable by the multimodal large model; Step S12: Divide the drawing in image format into regions to obtain a drawing view region, a text description region and a table content region.

3. The method for generating a process card based on a CAD drawing according to claim 1 or 2, characterized in that: In step S2, for the extraction of table content, the visual understanding and natural language processing capabilities of the multimodal large model are used to directly identify and parse the structured information in the table and convert it into text data for subsequent processing; For the text description area, the visual understanding and natural language processing capabilities of the multimodal large model are used to extract text information and capture technical requirements and process annotations.

4. The method for generating a process card based on a CAD drawing according to claim 3, characterized in that: In the step S2, the view information is extracted into single view information extraction and multi-view information extraction; For single-view information extraction, multimodal large models are used to identify part features and annotation information, and relevant parameter data is directly extracted; For multi-view information extraction, the reasoning method of thinking chain COT is adopted to determine the required parameters step by step to ensure the completeness and accuracy of information extraction.

5. The method for generating a process card based on a CAD drawing according to claim 3, characterized in that: The file format of the CAD drawing includes DWG, DXF or other formats supported by other CAD software; The image formats recognizable by the multimodal large model include at least BMP format, JPEG format, GIF format, TIFF format, and PNG format.

6. The method for generating a process card based on a CAD drawing according to claim 4, characterized in that: The COT method of multi-view information extraction specifically includes: Step S201: Divide all views of the drawing to clarify the types and quantities of existing views; Step S202: Select the optimal view for extracting relevant information according to preset rules and logic; Step S203: perform integrity verification and calculation on the extracted relevant information.

7. The method for generating a process card based on a CAD drawing according to claim 1, characterized in that: In the step S3, based on the key information of the drawing, predefined processing rules are matched, and the processing rules are stored in the form of; the corresponding processing rules are obtained by parsing the Excel table through code; Any of the processing rules presets judgment conditions based on key parameters of the drawing and technical requirements. When the extracted drawing information meets the corresponding judgment conditions, the corresponding process will be determined and added to the process card.

8. The method for generating a process card based on a CAD drawing according to claim 5, characterized in that: In step S4, a data set is constructed, which includes a text pair of a CAD drawing and an expected large model output, and the text pair includes: text content obtained based on a table content area, text content obtained based on a text description area, and parameters to be extracted obtained based on a drawing view area.

9. An electronic device, characterized in that: include: One or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, and the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory to enable the electronic device to execute the process card generation method based on CAD drawings as described in any one of claims 1 to 8.

10. A non-transitory readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, implement the method for generating a process card based on a CAD drawing as claimed in any one of claims 1 to 8.

Images