An artificial intelligence-based mold CAD drawing intelligent analysis and generation method, system, terminal and storage medium

Abstract

The application relates to the field of artificial intelligence aided design, and discloses a method, a system, a terminal and a storage medium for intelligent analysis and generation of mold CAD drawings based on artificial intelligence. The method comprises the following steps: a first AI intelligent agent is used to construct a correlation data set; a target part drawing is acquired and stored as structured part data in combination with the correlation data set; and a mold type and built-in standard library parameters are acquired and stored as a mold configuration file. A second AI intelligent agent performs process planning according to the correlation data set, the structured part data and the mold configuration file, generates process planning data, generates a mold CAD file according to the process planning data, and displays the mold CAD file in CAD software for manual checking; if the checking fails, feedback is acquired and the mold CAD file is modified until the checking passes. Finally, the mold CAD file that passes the checking is output. The application realizes automatic generation of part drawings to mold drawings, shortens the design cycle, and reduces the dependence on manpower.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence-aided design technology, and in particular to an intelligent analysis and generation method, system, terminal, and computer-readable storage medium for mold CAD drawings based on artificial intelligence. Background Technology

[0002] In the existing mold design process, the generation of mold drawings from part drawings heavily relies on manual operation. Specifically, engineers first need to manually analyze features such as geometric contours, hole positions, and bending lines in the part drawings, as well as process parameters such as material, thickness, and tolerances. Then, based on personal experience, they select the appropriate mold type (such as progressive dies or single-punch dies) and consult design manuals to obtain standard parameters. Next, they manually draw or repeatedly modify mold drawings such as strip diagrams and structural diagrams in CAD software. Finally, they rely on manual review and correction. In this process, inconsistent drawing formats (such as a mix of PDF, images, and DWG files), reliance on visual identification for feature extraction, reliance on the experience of senior engineers for process planning, and manual drawing and modification all result in a very low degree of automation in the entire design process. Furthermore, when engineers discover problems in the drawings, they need to manually locate and modify them, lacking an automated feedback and iteration mechanism, which further prolongs the design cycle and increases labor costs.

[0003] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0004] The main objective of this invention is to provide an intelligent analysis and generation method, system, terminal, and computer-readable storage medium for mold CAD drawings based on artificial intelligence, aiming to solve the problems of low automation and heavy reliance on manual operation in the existing mold design process, from part drawings to mold drawings.

[0005] To achieve the above objectives, this invention provides an intelligent analysis and generation method for mold CAD drawings based on artificial intelligence. This method includes the following steps: Construct a related dataset using the first AI agent; The first AI agent acquires the target part drawing, extracts the geometric features and process parameters from the target part drawing, and stores the geometric features and process parameters as structured part data according to the correlation dataset to obtain structured part data; The first AI agent acquires the predetermined mold type and built-in design standard library parameters, and stores the mold type and the built-in design standard library parameters as a mold configuration file; The second AI agent acquires the correlation dataset, the structured part data, and the mold configuration file, and performs process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data. The second AI agent generates a mold CAD file based on the process planning data and the correlation dataset, displays the mold CAD file in CAD software for manual verification, obtains human feedback when the manual verification fails, and performs modification operations on the mold CAD file based on the human feedback until the manual verification passes. The manually verified mold CAD file is output to obtain the target mold CAD file.

[0006] Furthermore, the construction of the related dataset through the first AI agent specifically includes: CAD drawing samples are obtained through the first AI agent; Machine learning is used to extract the associated features from the CAD drawing samples, and an associated dataset is constructed based on these features.

[0007] Furthermore, the first AI agent acquires the target part drawing, extracts the geometric features and process parameters from the target part drawing, and stores the geometric features and process parameters as structured part data according to the correlation dataset, thereby obtaining structured part data, specifically including: The first AI agent acquires the target part drawing and converts the target part drawing into a standard CAD format target part drawing; Extract the geometric features and process parameters from the target part drawing in the standard CAD format. The geometric features include geometric contours, hole position information, and bending line information. The process parameters include material information, thickness information, and tolerance information. Based on the correlation dataset, the geometric features and the process parameters are associated and stored as structured part data to obtain structured part data.

[0008] Furthermore, the first AI agent acquires a predetermined mold type and built-in design standard library parameters, and stores the mold type and the built-in design standard library parameters as a mold configuration file, specifically including: The first AI agent obtains a predetermined mold type based on the correlation dataset, wherein the mold type includes progressive dies and single-punch dies; The first AI agent calls the corresponding standard parameters from the built-in design standard library according to the mold type, and stores the mold type and the standard parameters as a mold configuration file.

[0009] Furthermore, the second AI agent acquires the correlation dataset, the structured part data, and the mold configuration file, and performs process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data, specifically including: The related dataset, the structured part data, and the mold configuration file are obtained through a second AI agent; The second AI agent, based on the built-in mold design standard library and process rule library, performs process planning according to the correlation dataset, the structured part data and the mold configuration file, to obtain the process arrangement and structural layout of the target mold; The second AI agent generates process planning data based on the correlation dataset, the process arrangement, and the structural layout.

[0010] Furthermore, the second AI agent generates a mold CAD file based on the process planning data and the correlation dataset, displays the mold CAD file in CAD software for manual verification, obtains human feedback when the manual verification fails, and performs modification operations on the mold CAD file based on the human feedback until the manual verification passes, specifically including: The second AI agent generates mold CAD files based on the process planning data and the correlation dataset; The second AI agent loads the mold CAD file into the graphical interface of the CAD software for display and receives the judgment result of manual verification; When the judgment result is "not passed", the second AI agent obtains the text feedback input by the human through the user interface as human feedback, performs modification operation on the mold CAD file according to the human feedback, obtains the updated mold CAD file, and returns the updated mold CAD file to the display stage until it passes human verification.

[0011] Furthermore, the step of outputting the manually verified mold CAD file to obtain the target mold CAD file specifically includes: Received manual verification passed instruction; According to the manual verification pass instruction, the mold CAD file that has passed the manual verification is saved and output to obtain the target mold CAD file.

[0012] Furthermore, to achieve the above objectives, the present invention also provides an intelligent analysis and generation system for mold CAD drawings based on artificial intelligence. This system is used to implement the intelligent analysis and generation method for mold CAD drawings based on artificial intelligence as described above. The intelligent analysis and generation system for mold CAD drawings based on artificial intelligence includes: The data construction module is used to build a related dataset through the first AI agent; The drawing parsing module is used to control the first AI agent to acquire the target part drawing, extract the geometric features and process parameters in the target part drawing, and store the geometric features and process parameters as structured part data according to the correlation dataset to obtain structured part data; The parameter configuration module is used to obtain the predetermined mold type and built-in design standard library parameters through the first AI agent, and store the mold type and the built-in design standard library parameters as a mold configuration file; The process planning module is used to obtain the correlation dataset, the structured part data, and the mold configuration file through a second AI agent, and to perform process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data. The verification and modification module is used to control the second AI agent to generate a mold CAD file based on the process planning data and the correlation dataset, display the mold CAD file in the CAD software for manual verification, obtain manual feedback when the manual verification fails, and perform modification operations on the mold CAD file based on the manual feedback until the manual verification passes. The file output module is used to output the mold CAD file that has passed manual verification, thus obtaining the target mold CAD file.

[0013] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and an AI-based intelligent analysis and generation program for mold CAD drawings stored in the memory and executable on the processor, wherein when the AI-based intelligent analysis and generation program for mold CAD drawings is executed by the processor, it implements the steps of the AI-based intelligent analysis and generation method for mold CAD drawings as described above.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an intelligent analysis and generation program for mold CAD drawings based on artificial intelligence, and when the intelligent analysis and generation program for mold CAD drawings based on artificial intelligence is executed by a processor, it implements the steps of the intelligent analysis and generation method for mold CAD drawings based on artificial intelligence as described above.

[0015] The beneficial effects of this invention are as follows: By constructing a relational dataset through a first AI agent, standardized feature association rules can be established for subsequent processing, thereby improving the accuracy and consistency of drawing element recognition. Based on this, the first AI agent extracts geometric features and process parameters from the target part drawing and stores them as structured part data. This transforms unstructured raw drawings into standardized, computable structured information, facilitating efficient subsequent retrieval. Simultaneously, storing the predetermined mold type and built-in design standard library parameters as a mold configuration file solidifies design specifications and user intent within the system, providing clear constraints and parameter benchmarks for process planning. Subsequently, a second AI agent executes process planning based on the aforementioned structured part data, mold configuration file, and relational dataset, automatically generating process planning data containing reasonable process arrangements, achieving intelligent mapping from part features to process solutions. Next, the second AI agent generates mold CAD files based on the process planning data, and obtains feedback when manual verification fails, iteratively modifying the files until verification passes, thus forming a closed-loop correction mechanism for human-machine collaboration, continuously improving the accuracy and standardization of generated drawings. Ultimately, the output is a validated mold CAD file, achieving a fully automated generation effect from inputting part drawings to outputting usable mold drawings, significantly shortening the design cycle and reducing reliance on human labor. Attached Figure Description

[0016] Figure 1 This is a flowchart of a preferred embodiment of the intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to the present invention; Figure 2 This is a structural diagram of a preferred embodiment of the intelligent analysis and generation system for mold CAD drawings based on artificial intelligence of the present invention; Figure 3 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0017] This application provides an intelligent analysis and generation method, system, terminal, and storage medium for mold CAD drawings based on artificial intelligence. It is particularly suitable for the automatic generation and modification of engineering drawings for progressive dies and single-stamp dies, and can be widely applied in the design of stamping dies for hardware, plastics, and other industries. To make the objectives, technical solutions, and effects of this application clearer and more explicit, the following detailed description, with reference to the accompanying drawings and embodiments, further illustrates this application. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0019] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0020] The preferred embodiment of the present invention describes an intelligent analysis and generation method for mold CAD drawings based on artificial intelligence, such as... Figure 1 As shown, the intelligent analysis and generation method for mold CAD drawings based on artificial intelligence includes the following steps: S10. Construct a related dataset through the first AI agent.

[0021] The purpose of this step is to provide a standardized set of feature association rules that can be understood by machine learning models for subsequent part feature extraction, process planning, and drawing generation, thereby solving the problem of unclear mapping relationships between graphic elements (such as points, lines, surfaces, and annotations) and engineering semantics (such as holes, bends, materials, and tolerances) in different CAD drawings.

[0022] Furthermore, the construction of the relational dataset through the first AI agent specifically includes: CAD drawing samples are obtained through the first AI agent; Machine learning is used to extract the associated features from the CAD drawing samples, and an associated dataset is constructed based on these features.

[0023] In this embodiment, the first AI agent (Artificial Intelligence Agent, AIA) acquires a large number of historical mold CAD drawing samples. These samples cover various types, including progressive dies and single-punch dies, as well as hardware and plastic parts with different complexities (punching, bending, blanking, stretching). Then, machine learning algorithms (such as Convolutional Neural Networks (CNNs) or Graph Neural Networks (GNNs)) are used to extract associated features from the CAD drawing samples. For example, it learns that "concentric circles with center lines" typically represent "circular hole features," "polygonal regions with bending lines represent "bending features," and the correspondence between "specific text labels within the drawing frame" and "material and thickness" parameters. Through this learning, the first AI agent constructs an association dataset, which is essentially a knowledge graph or rule base containing feature mapping rules, geometric constraints, and process parameter associations. It should be noted that this association dataset is iteratively updatable; feedback from each subsequent manual verification can be processed and used to optimize the dataset, thereby continuously improving the recognition accuracy of the first AI agent.

[0024] S20. The first AI agent acquires the target part drawing, extracts the geometric features and process parameters from the target part drawing, and stores the geometric features and process parameters as structured part data according to the correlation dataset to obtain structured part data.

[0025] The purpose of this step is to automatically convert unstructured, diverse target part drawings (such as PDFs, images, and non-standard DWGs) into standardized, structured data that can be efficiently parsed by computers, completely eliminating the reliance on human visual recognition and experience-based analysis.

[0026] Further, the first AI agent acquires the target part drawing, extracts the geometric features and process parameters from the target part drawing, and stores the geometric features and process parameters as structured part data according to the correlation dataset, thereby obtaining structured part data, specifically including: The first AI agent acquires the target part drawing and converts the target part drawing into a standard CAD format target part drawing; Extract the geometric features and process parameters from the target part drawing in the standard CAD format. The geometric features include geometric contours, hole position information, and bending line information. The process parameters include material information, thickness information, and tolerance information. Based on the correlation dataset, the geometric features and the process parameters are associated and stored as structured part data to obtain structured part data.

[0027] In this embodiment, the first AI agent acquires the target part drawing uploaded by the user (e.g., a hardware part drawing made of SPCC material with a thickness of 1.0mm) and converts it into a target part drawing in standard CAD (Computer-Aided Design) format, such as DWG or DXF format. Then, the first AI agent calls its built-in drawing parsing module (which can be implemented based on open-source libraries such as LibreDWG or ODA Teigha) to read the target part drawing in standard CAD format and extract its geometric features and process parameters: geometric features include the part's geometric contour (80mm long, 50mm wide), hole position information (punch diameter 5mm), bending line information (bending angle 90°), etc.; process parameters include material information (SPCC), thickness information (1.0mm), tolerance information (national standard stamping grade II), burr direction, and layout direction, etc. Finally, the first AI agent performs semantic association and standardized encoding on the extracted geometric features and process parameters based on the correlation dataset constructed in step S10. For example, it labels "contour set" as "shape_blank" and "circle_diameter 5mm" as "punching_M5 mounting hole". The associated data is stored as structured part data (such as JSON or XML format), and information such as part ID, feature type, geometric parameters, and process requirements are clearly recorded.

[0028] S30. The first AI agent obtains the predetermined mold type and built-in design standard library parameters, and stores the mold type and the built-in design standard library parameters as a mold configuration file.

[0029] The purpose of this step is to solidify the user's design intent and industry standards in a structured form, providing clear constraints and design basis for subsequent AI process planning, and ensuring the standardization and compliance of the generated drawings.

[0030] Furthermore, the first AI agent acquires a predetermined mold type and built-in design standard library parameters, and stores the mold type and the built-in design standard library parameters as a mold configuration file, specifically including: The first AI agent obtains a predetermined mold type based on the correlation dataset, wherein the mold type includes progressive dies and single-punch dies; The first AI agent calls the corresponding standard parameters from the built-in design standard library according to the mold type, and stores the mold type and the standard parameters as a mold configuration file.

[0031] In this embodiment, the first AI agent provides a user interface to obtain the user's predetermined mold type. The user selects "continuous mold" through a drop-down menu and prioritizes a 1219mm roll slitting and two-out-one-out-two-out layout strategy. Based on the user's selection of "continuous mold," the first AI agent automatically retrieves the corresponding standard parameters from its built-in design standard library, including: overlap value (front 2.5mm, rear 2.0mm), pitch (85mm), blade gap (0.1mm), strip layout rule (double-row facing), and roll slitting rule (width 125mm), etc. Finally, the first AI agent combines the mold type (continuous mold) and these standard parameters and stores them as a structured mold configuration file.

[0032] It should be noted that the mold type can also be obtained through intelligent recommendation.

[0033] S40. Obtain the correlation dataset, the structured part data, and the mold configuration file through the second AI agent, and perform process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data.

[0034] The purpose of this step is to enable AI to automatically make intelligent decisions from part features to mold process solutions, replacing the traditional complex process planning process that relies on the experience of senior engineers, and solving the problems of low efficiency and error-proneness in process planning.

[0035] Furthermore, the second AI agent acquires the correlation dataset, the structured part data, and the mold configuration file, and performs process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data, specifically including: The related dataset, the structured part data, and the mold configuration file are obtained through a second AI agent; The second AI agent, based on the built-in mold design standard library and process rule library, performs process planning according to the correlation dataset, the structured part data and the mold configuration file, to obtain the process arrangement and structural layout of the target mold; The second AI agent generates process planning data based on the correlation dataset, the process arrangement, and the structural layout.

[0036] In this embodiment, the second AI agent first acquires the correlation dataset from step S10, the structured part data from step S20, and the mold configuration file from step S30. Then, based on its built-in mold design standard library and process rule library, the second AI agent executes process planning using a hybrid strategy of "rule engine + few-shot learning": first, the rule engine covers the process planning for conventional parts; for the punching, bending, and blanking features in this embodiment, the process is generated according to the "step distance" and "overlap value" rules in the mold configuration file; then, the processing of complex irregular parts is optimized using a CNN (Convolutional Neural Networks) / Transformer model. The planned process arrangement for the target mold is "blanking → punching → bending → shaping," with a structural layout where each station is arranged sequentially along the material feed direction, with a station spacing of 85mm. Finally, based on the correlation dataset, the second AI agent structurally encapsulates the above process arrangement and structural layout to generate a complete process planning data, including specific process parameters for each station (such as the center coordinates of the punching force, unloading force, etc.).

[0037] S50. The second AI agent generates a mold CAD file based on the process planning data and the correlation dataset, displays the mold CAD file in CAD software for manual verification, obtains manual feedback when the manual verification fails, and performs modification operations on the mold CAD file based on the manual feedback until the manual verification passes.

[0038] The purpose of this step is to achieve automatic drawing from process plans to editable mold drawings, and to establish an efficient human-machine collaborative closed-loop verification mechanism. AI is driven by human feedback to make rapid corrections, balancing automation efficiency with the reliability of the final drawings.

[0039] Furthermore, the second AI agent generates a mold CAD file based on the process planning data and the correlation dataset, displays the mold CAD file in CAD software for manual verification, obtains human feedback when the manual verification fails, and performs modification operations on the mold CAD file based on the human feedback until the manual verification passes, specifically including: The second AI agent generates mold CAD files based on the process planning data and the correlation dataset; The second AI agent loads the mold CAD file into the graphical interface of the CAD software for display and receives the judgment result of manual verification; When the judgment result is "not passed", the second AI agent obtains the text feedback input by the human through the user interface as human feedback, performs modification operation on the mold CAD file according to the human feedback, obtains the updated mold CAD file, and returns the updated mold CAD file to the display stage until it passes human verification.

[0040] In this embodiment, the second AI agent, based on the process planning data from step S40 and the correlation dataset from step S10, calls the CAD drawing generation / modification unit to automatically generate a mold CAD file. This unit automatically draws a continuous mold strip diagram: automatically optimizes the part contour chamfer (R2mm), adjusts the cutting edge clearance (0.1mm), unifies CAD layers (contour layer, annotation layer, process layer), and standardizes blocks. The generated mold CAD file includes a strip diagram, process layout diagram, mold structure diagram, and part unfolding diagram. Then, the second AI agent loads the mold CAD file into the graphical interface of CAD software (such as ZWCAD or AutoCAD) via the CAD interaction module for manual preview and verification by mold engineers. Engineer verification includes mold structure interference, dimensional accuracy, process rationality (whether the strip arrangement is reasonable), and part stability. If the engineer finds that the guide pin position is not marked, it is judged as "failed". The second AI agent obtains the manually input text feedback "supplement guide pin position annotation" through the user interface. Based on this feedback, the AI ​​agent automatically locates the corresponding workstation in the drawing, performs the supplementary annotation operation, and obtains the updated mold CAD file. The updated file was then displayed in the CAD software until the engineer confirmed that all issues had been corrected and gave a "pass" result.

[0041] S60. Output the mold CAD file that has passed manual verification to obtain the target mold CAD file.

[0042] The purpose of this step is to solidify the final, confirmed mold drawings into the official version, complete the entire design process from part drawings to deliverable mold drawings, and achieve standardized archiving of design results.

[0043] Furthermore, the step of outputting the manually verified mold CAD file to obtain the target mold CAD file specifically includes: Received manual verification passed instruction; According to the manual verification pass instruction, the mold CAD file that has passed the manual verification is saved and output to obtain the target mold CAD file.

[0044] In this embodiment, the system receives the "Verification Passed" command clicked by the engineer on the interface through the CAD interaction module. Based on this command, the system saves the currently modified and finally confirmed mold CAD file (i.e., the continuous mold strip drawing with the guide pin position annotations added), and outputs it to a specified path according to preset naming rules and directory structure. Simultaneously, the system archives all data generated throughout the entire design process (including original part drawings, intermediate format files, structured part data, mold configuration files, process planning data, AI inference result files, and the final target mold CAD file) to the data storage module for version tracking and subsequent model training and optimization. At this point, the entire AI-based intelligent generation and optimization process for mold CAD drawings is complete, resulting in a target mold CAD file that can be directly used for production.

[0045] Furthermore, such as Figure 2 As shown, based on the above-mentioned intelligent analysis and generation method for mold CAD drawings based on artificial intelligence, the present invention also provides an intelligent analysis and generation system for mold CAD drawings based on artificial intelligence, the intelligent analysis and generation system for mold CAD drawings based on artificial intelligence includes: Data construction module 51 is used to construct a related dataset through the first AI agent; The drawing parsing module 52 is used to control the first AI agent to acquire the target part drawing, extract the geometric features and process parameters in the target part drawing, and store the geometric features and process parameters as structured part data according to the correlation dataset to obtain structured part data; The parameter configuration module 53 is used to obtain the predetermined mold type and built-in design standard library parameters through the first AI agent, and store the mold type and the built-in design standard library parameters as a mold configuration file; The process planning module 54 is used to obtain the correlation dataset, the structured part data and the mold configuration file through the second AI agent, and to perform process planning based on the correlation dataset, the structured part data and the mold configuration file to obtain process planning data; The verification and modification module 55 is used to control the second AI agent to generate a mold CAD file based on the process planning data and the correlation dataset, display the mold CAD file in the CAD software for manual verification, obtain manual feedback when the manual verification fails, and perform modification operations on the mold CAD file based on the manual feedback until the manual verification passes. The file output module 56 is used to output the mold CAD file that has passed manual verification to obtain the target mold CAD file.

[0046] Furthermore, such as Figure 3 As shown, based on the above-mentioned intelligent analysis and generation method and system for mold CAD drawings based on artificial intelligence, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 3 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0047] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores an AI-based intelligent analysis and generation program 40 for mold CAD drawings. This AI-based intelligent analysis and generation program 40 can be executed by the processor 10, thereby implementing the AI-based intelligent analysis and generation method for mold CAD drawings in this application.

[0048] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the intelligent analysis and generation method of the mold CAD drawing based on artificial intelligence.

[0049] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0050] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an intelligent analysis and generation program for mold CAD drawings based on artificial intelligence, and the intelligent analysis and generation program for mold CAD drawings based on artificial intelligence, when executed by a processor, implements the steps of the intelligent analysis and generation method for mold CAD drawings based on artificial intelligence as described above.

[0051] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0052] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0053] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for intelligent analysis and generation of mold CAD drawings based on artificial intelligence, characterized in that, The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence includes the following steps: Construct a related dataset using the first AI agent; The first AI agent acquires the target part drawing, extracts the geometric features and process parameters from the target part drawing, and stores the geometric features and process parameters as structured part data according to the correlation dataset to obtain structured part data; The first AI agent acquires the predetermined mold type and built-in design standard library parameters, and stores the mold type and the built-in design standard library parameters as a mold configuration file; The second AI agent acquires the correlation dataset, the structured part data, and the mold configuration file, and performs process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data. The second AI agent generates a mold CAD file based on the process planning data and the correlation dataset, displays the mold CAD file in CAD software for manual verification, obtains human feedback when the manual verification fails, and performs modification operations on the mold CAD file based on the human feedback until the manual verification passes. The manually verified mold CAD file is output to obtain the target mold CAD file.

2. The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to claim 1, characterized in that, The construction of the correlated dataset through the first AI agent specifically includes: CAD drawing samples are obtained through the first AI agent; Machine learning is used to extract the associated features from the CAD drawing samples, and an associated dataset is constructed based on these features.

3. The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to claim 1, characterized in that, The first AI agent acquires the target part drawing, extracts the geometric features and process parameters from the target part drawing, and stores the geometric features and process parameters as structured part data based on the correlation dataset, thus obtaining structured part data, specifically including: The first AI agent acquires the target part drawing and converts the target part drawing into a standard CAD format target part drawing; Extract the geometric features and process parameters from the target part drawing in the standard CAD format. The geometric features include geometric contours, hole position information, and bending line information. The process parameters include material information, thickness information, and tolerance information. Based on the correlation dataset, the geometric features and the process parameters are associated and stored as structured part data to obtain structured part data.

4. The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to claim 1, characterized in that, The first AI agent acquires a predetermined mold type and built-in design standard library parameters, and stores the mold type and the built-in design standard library parameters as a mold configuration file, specifically including: The first AI agent obtains a predetermined mold type based on the correlation dataset, wherein the mold type includes progressive dies and single-punch dies; The first AI agent calls the corresponding standard parameters from the built-in design standard library according to the mold type, and stores the mold type and the standard parameters as a mold configuration file.

5. The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to claim 1, characterized in that, The second AI agent acquires the correlation dataset, the structured part data, and the mold configuration file, and performs process planning based on these data to obtain process planning data, specifically including: The related dataset, the structured part data, and the mold configuration file are obtained through a second AI agent; The second AI agent, based on the built-in mold design standard library and process rule library, performs process planning according to the correlation dataset, the structured part data and the mold configuration file, to obtain the process arrangement and structural layout of the target mold; The second AI agent generates process planning data based on the correlation dataset, the process arrangement, and the structural layout.

6. The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to claim 1, characterized in that, The second AI agent generates a mold CAD file based on the process planning data and the correlation dataset. The mold CAD file is then displayed in CAD software for manual verification. If the manual verification fails, feedback is obtained, and modifications are made to the mold CAD file based on this feedback until the manual verification passes. Specifically, this includes: The second AI agent generates mold CAD files based on the process planning data and the correlation dataset; The second AI agent loads the mold CAD file into the graphical interface of the CAD software for display and receives the judgment result of manual verification; When the judgment result is "not passed", the second AI agent obtains the text feedback input by the human through the user interface as human feedback, performs modification operation on the mold CAD file according to the human feedback, obtains the updated mold CAD file, and returns the updated mold CAD file to the display stage until it passes human verification.

7. The intelligent analysis and generation method for mold CAD drawings based on artificial intelligence according to claim 1, characterized in that, The step of outputting the manually verified mold CAD file to obtain the target mold CAD file specifically includes: Received manual verification passed instruction; According to the manual verification pass instruction, the mold CAD file that has passed the manual verification is saved and output to obtain the target mold CAD file.

8. An intelligent analysis and generation system for mold CAD drawings based on artificial intelligence, characterized in that, The AI-based intelligent analysis and generation system for mold CAD drawings is used to implement the AI-based intelligent analysis and generation method for mold CAD drawings as described in any one of claims 1-7. The AI-based intelligent analysis and generation system for mold CAD drawings includes: The data construction module is used to build a related dataset through the first AI agent; The drawing parsing module is used to control the first AI agent to acquire the target part drawing, extract the geometric features and process parameters in the target part drawing, and store the geometric features and process parameters as structured part data according to the correlation dataset to obtain structured part data; The parameter configuration module is used to obtain the predetermined mold type and built-in design standard library parameters through the first AI agent, and store the mold type and the built-in design standard library parameters as a mold configuration file; The process planning module is used to obtain the correlation dataset, the structured part data, and the mold configuration file through a second AI agent, and to perform process planning based on the correlation dataset, the structured part data, and the mold configuration file to obtain process planning data. The verification and modification module is used to control the second AI agent to generate a mold CAD file based on the process planning data and the correlation dataset, display the mold CAD file in the CAD software for manual verification, obtain manual feedback when the manual verification fails, and perform modification operations on the mold CAD file based on the manual feedback until the manual verification passes. The file output module is used to output the mold CAD file that has passed manual verification, thus obtaining the target mold CAD file.

9. A terminal, characterized in that, The terminal includes: a memory, a processor, and an AI-based intelligent analysis and generation program for mold CAD drawings stored in the memory and executable on the processor. When the AI-based intelligent analysis and generation program for mold CAD drawings is executed by the processor, it implements the steps of the AI-based intelligent analysis and generation method for mold CAD drawings as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an intelligent analysis and generation program for mold CAD drawings based on artificial intelligence. When the intelligent analysis and generation program for mold CAD drawings based on artificial intelligence is executed by a processor, it implements the steps of the intelligent analysis and generation method for mold CAD drawings based on artificial intelligence as described in any one of claims 1-7.

Images