Computer-aided design model generation method, apparatus, device, and storage medium

Abstract

This application discloses a method, apparatus, device, and storage medium for generating computer-aided design models, relating to the field of computer-aided design technology. The method includes: constructing an expert skill knowledge base based on expert knowledge data; receiving a variation request based on a component family type, and retrieving a corresponding target skill from the expert skill knowledge base based on the variation request; obtaining a target preset template based on the variation request based on the component family type and the target skill; and generating a computer-aided design model based on the target preset template. By using variation requests based on component family types and constructing an expert skill knowledge base, the workload of repeatedly constructing modeling processes during variation design of similar components can be effectively reduced, thus improving the efficiency of generating computer-aided design models.

Description

Technical Field

[0001] This application relates to the field of computer-aided design technology, and in particular to methods, apparatus, devices and storage media for generating computer-aided design models. Background Technology

[0002] With the deepening of digital transformation in the manufacturing industry, CAD (Computer-Aided Design) is a core part of product development, and its modeling efficiency directly affects the product iteration speed and the competitiveness of enterprises.

[0003] Existing computer-aided design model generation primarily relies on user input and the model's own reasoning capabilities. However, it cannot be guaranteed that user input is comprehensive or accurate. When user input is vague, incomplete, or only describes high-level design intent, the efficiency of generating computer-aided design models will be low. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, device, and storage medium for generating computer-aided design models, aiming to solve the technical problem that current computer-aided design model generation is easily affected by user input information, resulting in low efficiency.

[0005] To achieve the above objectives, this application proposes a computer-aided design model generation method, which includes: Build an expert skills knowledge base based on expert knowledge data; Receive a variant request based on a component family type, and retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type; A target preset template is obtained based on the variant request based on the component family type and the target skill; A computer-aided design model is generated based on the target preset template.

[0006] In one embodiment, the step of constructing an expert skills knowledge base based on expert knowledge data includes: Acquire expert knowledge data, wherein the expert knowledge data includes at least the macro records, operation history, feature tree, drawing instructions, parameter table, engineering description and boundary requirements of computer-aided design; The expert knowledge data is preprocessed to obtain a normalized computer-aided design operation sequence; An expert skills knowledge base is constructed based on the normalized computer-aided design operation sequence.

[0007] In one embodiment, the step of constructing an expert skills knowledge base based on the normalized computer-aided design operation sequence includes: The semantic modeling stage is obtained based on the operation sequence; The operation sequence is parameterized to obtain the parameter information of the component family, wherein the parameter information includes at least the parameter mode, default value, and valid range; Generate historical preset templates based on the semantic modeling stage and the parameter information; The component skills are combined based on the project description, the parameter information, and the historical preset templates. An expert skills knowledge base is built based on the skills of the components.

[0008] In one embodiment, the step of preprocessing the expert knowledge data to obtain a normalized computer-aided design operation sequence includes: The expert knowledge data is parsed to obtain the initial computer-aided design operation sequence; Irrelevant operations are removed and filtered from the initial computer-aided design operation sequence to obtain a filtered computer-aided design operation sequence. The parameters and formats in the filtered computer-aided design operation sequence are normalized to obtain a normalized computer-aided design operation sequence.

[0009] In one embodiment, the step of obtaining the target preset template based on the variant request based on the component family type and the target skill includes: Based on the variant request based on the component family type and the target skill, retrieve historical preset templates from the expert skill knowledge base; The operation parameters in the historical preset template are filled or updated to obtain the first target template; By inserting or modifying local operations in the first target template, a second target template is obtained. The target preset template is obtained based on the second target template.

[0010] In one embodiment, the step of generating a computer-aided design model based on the target preset template includes: The target preset template is parsed to obtain general feature operations; The general feature operations are translated to obtain the target backend call sequence; A computer-aided design model is generated based on the target backend call sequence.

[0011] In one embodiment, after the step of generating a computer-aided design model based on the target preset template, the method further includes: Based on the computer-aided design model, generate multi-view renderings and structured summaries; Feedback information is obtained based on the multi-view rendering graph and the structured summary; The acceptance criteria are determined based on the feedback information. If the acceptance condition does not meet the target requirements, return to the step of obtaining the target preset template based on the variant request based on the component family type and the target skill, until the acceptance condition meets the target requirements.

[0012] Furthermore, to achieve the above objectives, this application also proposes a computer-aided design model generation device, which includes: The module is used to build an expert skills knowledge base based on expert knowledge data; The retrieval module is used to receive a variant request based on the component family type, and retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type; The generation module is used to obtain a target preset template based on the variant request based on the component family type and the target skill; The generation module is also used to generate a computer-aided design model based on the target preset template.

[0013] In addition, to achieve the above objectives, this application also proposes a computer-aided design model generation device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the computer-aided design model generation method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the computer-aided design model generation method described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the computer-aided design model generation method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: 1) By using variant requests based on component family types and building an expert skills knowledge base, the workload of repeatedly constructing modeling processes when designing variants of similar components can be effectively reduced, thus improving the efficiency of generating computer-aided design models.

[0017] 2) By building historical preset templates in the construction phase and instantiating the templates in the generation phase to obtain the target preset template, the missing modeling steps, referenced entities, parameter dependencies and verification rules can be automatically completed when the user's variation request is vague, incomplete or only describes the high-level design intent, thereby improving the integrity and executability of the CAD model generation process.

[0018] 3) By returning the execution status, generating entity identifiers, feature trees, logs, and diagnostic information, it is possible to continuously maintain a traceable modeling history and entity reference relationships during the CAD model generation process, making the final generated CAD model more suitable for subsequent engineering inspection, parameter adjustment, and feature editing. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating an embodiment of the computer-aided design model generation method of this application. Figure 2 This application provides a schematic diagram of the overall framework of a computer-aided design model generation system according to an embodiment of the computer-aided design model generation method. Figure 3 This is a flowchart illustrating Embodiment 2 of the computer-aided design model generation method of this application. Figure 4 This is a flowchart illustrating Embodiment 3 of the computer-aided design model generation method of this application. Figure 5 This is a schematic diagram of the module structure of the computer-aided design model generation device according to an embodiment of this application; Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the computer-aided design model generation method in this application embodiment.

[0022] Explanation of icon numbers: The system includes a computer-aided design model generation system 100, an expert knowledge acquisition module 110, a macro record parsing module 120, a skill distillation module 130, a skill knowledge base 140, a request parsing and skill retrieval module 150, a CAD intermediate representation generation and rewriting module 160, a CAD backend execution layer 170, a CAD tool calling interface 171, a CAD software command executor 172, a multimodal CAD evaluation module 180, and a state memory and control module 190.

[0023] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0024] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0025] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0026] The main solution of this application embodiment is: to construct an expert skill knowledge base based on expert knowledge data; to receive a variant request based on a component family type, and to retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type; to obtain a target preset template based on the variant request based on the component family type and the target skill; and to generate a computer-aided design model based on the target preset template.

[0027] Current technologies rely on user input and the model's reasoning capabilities. However, they cannot guarantee that user input is comprehensive or accurate. When user input is vague, incomplete, or only describes high-level design intent, it leads to low efficiency in generating computer-aided design models.

[0028] This application provides a solution that utilizes expert knowledge data to construct an expert skills knowledge base. It extracts and receives variation requests based on component family types based on user input, and retrieves target skills from the expert skills knowledge base based on these requests. This reduces the workload of repeatedly constructing modeling processes when designing variations of similar components. Furthermore, it generates computer-aided design models based on the variation requests and target skills, improving the stability of the computer-aided design model generation process.

[0029] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or computer-aided design model generation system capable of performing the above functions. The following description uses a computer-aided design model generation system as an example to illustrate this embodiment and the subsequent embodiments. All actions involving the acquisition of signals, information, or data in this application are performed in accordance with the relevant data protection regulations of the country where the application is located and with authorization from the owner of the corresponding device.

[0030] Based on this, embodiments of this application provide a computer-aided design model generation method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the computer-aided design model generation method of this application.

[0031] In this embodiment, the computer-aided design model generation method includes steps S10 to S40: Step S10: Construct an expert skills knowledge base based on expert knowledge data.

[0032] It should be noted that expert knowledge data includes at least the macro records, operation history, feature trees, drawing instructions, parameter tables, engineering descriptions, and boundary requirements of computer-aided design; the expert skills knowledge base is used for the retrieval of the target skills required by the user.

[0033] like Figure 2 As shown, Figure 2 A schematic diagram of the overall framework of the computer-aided design model generation system is shown. The computer-aided design model generation system 100 includes an expert knowledge acquisition module 110, a macro record parsing module 120, a skill distillation module 130, a skill knowledge base 140, a request parsing and skill retrieval module 150, a CAD intermediate representation generation and rewriting module 160, a CAD back-end execution layer 170, a multimodal CAD evaluation module 180, a state memory and control module 190, user variation requests, generated CAD models, and feedback information. The CAD back-end execution layer 170 includes a CAD tool call interface 171 and a CAD software command executor 172.

[0034] The expert knowledge acquisition module 110 acquires expert knowledge data, including macro records, drawing instructions, parameter tables, engineering descriptions, feature trees, and operation history. The macro record parsing module 120 parses macro records or command history into normalized CAD operations; the skill distillation module 130 performs semantic segmentation, parameter abstraction, and historical preset template generation on CAD operations to obtain component skills; the skill knowledge base 140 stores component skills verified through playback; when a user modification request is received, the request parsing and skill retrieval module 150 retrieves the target skill from the skill knowledge base 140. The CAD intermediate representation generation and rewriting module 160 instantiates the historical preset template into a target preset template; the CAD backend execution layer 170 converts the target preset template into CAD tool calls and generates a CAD model through the CAD software command executor 172 or other industrial CAD backends; the multimodal CAD evaluation module 180 generates feedback information based on multi-view renderings and structured CAD summaries; the state memory and control module 190 maintains operation history, entity identifiers, feedback records, and model state, and controls iteration termination, thereby completing the overall process of computer-aided design model generation.

[0035] It is understandable that building an expert skills knowledge base is a knowledge distillation process, a pre-built database. The expert skills knowledge base can contain multiple different component families, covering different part types, and one component family corresponds to one template CAD-IR (CAD Intermediate Representation). It should be noted that, in order to distinguish between the template CAD-IR in the construction process and the template CAD-IR instantiated in the generation process, some content below will refer to the template CAD-IR in the construction process as the historical preset template, and the template CAD-IR instantiated in the generation process as the target preset template.

[0036] For example, for a family of automotive reinforcement plate components, the engineer completes the initial component modeling in CAD software. The system records the corresponding CAD software macro log, operation history, feature tree, parameter table, and drawing instructions. The macro log parsing module 120 parses operations such as creating a reference plane, drawing a sketch, extruding, sweeping, splitting, drilling, adding reinforcement ribs, rounding corners, and exporting from the log into a unified operation format. The skill distillation module 130 groups the low-level operations into the following semantic stages based on the operation sequence: (1) Create the base reference system and datum plane; (2) Create a sketch of the substrate outline; (3) Generate the main surface or solid; (4) Create bent areas or recessed structures; (5) Add mounting holes and hole arrays; (6) Add local reinforcing ribs; (7) Add boundary flanges, fillets, or chamfers; (8) Perform verification, naming, saving and export.

[0037] Subsequently, the system abstracts the specific dimensions into parameters such as plate_width, plate_length, tray_depth, hole_count, hole_diameter, hole_pitch, rib_height, flange_width, and fillet_radius, and records the default values ​​and valid ranges. The system writes the above semantic stages and parameter patterns into the template CAD-IR and verifies them through CAD backend playback. After successful verification, the automotive reinforcement plate component skill is formed.

[0038] Additionally, it's important to note that CAD-IR is not limited to a specific CAD backend. The system can map the same CAD-IR or a subset thereof to different CAD software or scripted CAD backends based on the backend tool bindings in the tools field; for production-grade industrial parts, it is preferable to use an industrial CAD backend capable of generating editable CAD models.

[0039] Step S20: Receive a variant request based on the component family type, and retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type.

[0040] Understandably, component family type refers to the different categories into which component families are divided based on geometric similarity, modeling logic, and parametric structure; target skill is the corresponding relevant skill retrieved by the system from the expert skill knowledge base based on the user's input information and variant request. For example, when the user inputs "deeper the hinge reinforcement plate tray while keeping the mounting hole layout unchanged", the system will confirm that the component family type of the variant request required by the user is automotive reinforcement plate, and retrieve the automotive reinforcement plate skill from the expert skill knowledge base.

[0041] Step S30: Obtain the target preset template based on the variant request based on the component family type and the target skill.

[0042] In one embodiment, the target preset template refers to the instantiated CAD-IR. Step S30 can also be considered as instantiating the template CAD-IR (historical preset template) in the expert skill knowledge base based on the variant request based on the component family type and the target skill, and receiving the user's variant request for the same or similar component families; for example, when the user inputs "deeper the hinge reinforcement plate tray while keeping the mounting hole layout unchanged", the system will confirm that the component family type of the variant request required by the user is automotive reinforcement plate, retrieve the automotive reinforcement plate skill from the expert skill knowledge base, and determine that the variant request mainly modifies the tray_depth parameter, while keeping the hole_count, hole_diameter, hole_pitch and hole position dependency unchanged. The template CAD-IR is instantiated through the CAD intermediate representation generation and rewriting module 160. The steps for instantiating the template CAD-IR for the user's variant request can be referred to as follows: (1) Update the tray depth parameter; (2) Adjust the stretching or sweeping parameters related to the pallet depth; (3) Maintain the reference plane and hole spacing parameters that the hole array operation depends on; (4) Maintain the operating sequence of the base plate, reinforcing ribs, and boundary flanges; (5) Update the verification rules to check tray depth, hole layout and boundary connections.

[0043] After completing these 5 instantiation steps, you will obtain the instantiated CAD-IR (target preset template).

[0044] Step S40: Generate a computer-aided design model based on the target preset template.

[0045] Computer-aided design model, or CAD model, in this embodiment, can be at least a B-Rep (Boundary Representation) model.

[0046] In one embodiment, the step of generating a computer-aided design model based on the target preset template may include: parsing the target preset template to obtain general feature operations; translating the general feature operations to obtain a target backend call sequence; and generating a computer-aided design model based on the target backend call sequence.

[0047] Specifically, the instantiated CAD-IR is parsed to extract a queue of generic feature operation instructions independent of specific CAD software. Using a predefined API (Application Programming Interface) mapping table, each generic feature operation is translated into a local API call sequence specific to the CAD backend. At the CAD execution layer, the APIs are called line by line strictly according to the local API call sequence of the specific CAD backend to generate the CAD model. For example, after parsing the instantiated CAD-IR to obtain the target backend call sequence, the CAD backend execution layer 170 executes the target backend call sequence to generate a CAD model editable by the CAD software (such as a B-Rep model).

[0048] In addition, while generating the CAD model, it can also return five pieces of information: execution status, generated entity identifiers, feature tree, logs, and diagnostic information.

[0049] This implementation maps CAD-IR to executable modeling commands in CAD software through the CAD backend execution layer, and returns the execution status, generated entity identifiers, feature trees, logs and diagnostic information. It can continuously maintain a traceable modeling history and entity reference relationships during the generation process, making the final model more suitable for subsequent engineering inspection, parameter adjustment and feature editing.

[0050] In one possible implementation, steps A11-A14 may be included after step S40: Step A11: Generate multi-view renderings and structured summaries based on the computer-aided design model; Understandably, multi-view renderings and structured summaries are both optional derivative outputs of CAD models. Multi-view renderings are two-dimensional images obtained by rendering the generated 3D entity with lighting and materials from multiple standard perspectives (such as front, back, left, right, top, bottom, and axonometric views). Structured summaries are lightweight model "identity cards" that extract key design and geometric information from the generated CAD model and organize it according to a fixed data structure.

[0051] Step A12: Obtain feedback information based on the multi-view rendering diagram and the structured summary; Feedback information typically refers to the feedback information generated after the CAD model, multi-view rendering, and structured summary are produced, in combination with user requests and verification rules; verification rules are evaluation criteria for judging whether the generated results are compliant.

[0052] Step A13: Obtain the acceptance criteria based on the feedback information; In this embodiment, the acceptance criteria are usually the final delivery judgment criteria set by the user or other objectives, which are above the verification rules. The acceptance criteria are usually used to determine whether the user request and the verification rules are met.

[0053] Step A14: When the acceptance condition does not meet the target requirements, return to the step of obtaining the target preset template based on the variant request based on the component family type and the target skill, until the acceptance condition meets the target requirements.

[0054] Understandably, when the acceptance criteria fail to meet the target requirements, the process returns to the step of instantiating the template CAD-IR (historical preset template) in the expert skills knowledge base based on the variant request and target skills according to the component family type, until the acceptance criteria are met or the iteration budget is reached. For example, after generating the CAD model, the multimodal CAD evaluation module 180 outputs multi-view renderings and structured summaries, and checks whether the pallet reaches the target depth, whether the holes are retained, whether the flanges are continuous, and whether the entity is editable. If the evaluation results indicate that the pallet sidewall is not smooth or the holes interfere with the new depth structure (i.e., the verification rule is non-compliant) or does not meet user expectations, the system generates a CAD-IR patch to enable rapid design iteration, such as modifying the sidewall transition fillet radius or adjusting the parameters of specific segmentation operations, and then returns to the step of obtaining the target preset template until the acceptance criteria are met or the iteration budget is reached.

[0055] This embodiment generates CAD-IR patches based on verification conditions and feedback information obtained from user requests, instead of directly rewriting the entire backend script. This limits the scope of correction to relevant parameters, operations, or dependencies, improves the efficiency of iterative correction, and reduces uncontrollable changes caused by regenerating long scripts.

[0056] This embodiment provides a method for generating computer-aided design models. It constructs an expert skills knowledge base based on expert knowledge data; receives a variation request based on a component family type, and retrieves the corresponding target skill from the expert skills knowledge base based on the variation request; obtains a target preset template based on the variation request and the target skill; and generates a computer-aided design model based on the target preset template. By using variation requests based on component family types and constructing an expert skills knowledge base, the method effectively reduces the workload of repeatedly constructing modeling processes when designing variation variations of similar components, thus improving the efficiency of generating computer-aided design models.

[0057] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S10 includes steps S101 to S103: Step S101: Obtain expert knowledge data, wherein the expert knowledge data includes at least the macro records, operation history, feature tree, drawing instructions, parameter table, engineering description and boundary requirements of computer-aided design.

[0058] It should be noted that expert knowledge data typically originates from engineers' design experience, operation records, and engineering specifications, serving as the original knowledge source for the system to achieve knowledge reuse and automated modeling. Computer-aided design macro records refer to operation scripts recorded by CAD software, usually computer code, recording the API call sequence corresponding to user interface operations. Operation history typically refers to user operation logs automatically recorded by CAD software, saving each interaction in chronological order. Feature trees typically refer to the design history tree organizing features in a parametric CAD model, displaying the name, type, and parent-child relationships of each feature in a hierarchical structure. Drawing instructions are usually additional technical requirements, annotations, and text descriptions attached to two-dimensional engineering drawings, usually located above the title block or in a blank area. Parameter tables are typically lists of variable dimensions and specifications for parts or component families defined in tabular form, commonly found in configuration tables, design tables, or family tables. Engineering descriptions are typically natural language or semi-structured text descriptions of the function, purpose, and structural characteristics of parts or components, which can come from design specifications, BOM (Bill of Materials) notes, or PDM (Product Data Management). Management attributes; boundary requirements are usually explicit geometric or physical boundary conditions in the design, such as maximum external dimensions, weight limits, interface mating dimensions, no-fabrication areas, etc.

[0059] Step S102: Preprocess the expert knowledge data to obtain a normalized computer-aided design operation sequence.

[0060] It should be noted that normalized CAD operation sequences refer to standardized low-level operation sequences with unified format, standardized terminology, symbolized parameters, and direct calculation capability.

[0061] In one embodiment, the step of preprocessing the expert knowledge data to obtain a normalized computer-aided design operation sequence includes: parsing the expert knowledge data to obtain an initial computer-aided design operation sequence; deleting and filtering irrelevant operations in the initial computer-aided design operation sequence to obtain a filtered computer-aided design operation sequence; and normalizing the parameters and formats in the filtered computer-aided design operation sequence to obtain a normalized computer-aided design operation sequence.

[0062] Specifically, the goal of this step is to transform expert knowledge data from different sources and in different formats into standardized low-level operation sequences with unified format, standardized terminology, symbolized parameters, and direct computability. First, macros from different languages ​​(such as Python) in the computer are uniformly parsed into an internal representation of "operation code + parameter list + reference object" (i.e., the initial computer-aided design operation sequence). Then, non-modeling actions such as view switching, measurement, and selection are removed from the initial CAD operation sequence, retaining only geometric operations such as feature creation and modification to obtain a filtered CAD operation sequence. The parameters of the filtered CAD operation sequence are symbolized and normalized: hard-coded numerical values ​​(such as 10.0) are replaced with symbolic variables (such as d1), and units, coordinate systems, and naming rules are unified, allowing operation sequences recorded by different projects or different engineers to be compared and merged. Finally, each operation is standardized into a unified format, resulting in a normalized CAD operation sequence.

[0063] Step S103: Construct an expert skills knowledge base based on the normalized computer-aided design operation sequence.

[0064] In one embodiment, the step of constructing an expert skill knowledge base based on the normalized computer-aided design operation sequence includes: obtaining a semantic modeling stage based on the operation sequence; performing parameter abstraction on the operation sequence to obtain parameter information of a component family, wherein the parameter information includes at least parameter mode, default value, and effective range; generating a historical preset template based on the semantic modeling stage and the parameter information; combining the project description, the parameter information, and the historical preset template into component skills; and constructing an expert skill knowledge base based on the component skills.

[0065] Understandably, a normalized CAD operation sequence is a standardized, ordered set of low-level operations. Therefore, performing low-level operation grouping on this normalized CAD operation sequence yields a semantic modeling stage (by analyzing the object reference chains, feature dependencies, and time windows within the normalized CAD operation sequence, consecutive atomic operations are aggregated into a semantic modeling stage with design significance). Dimensions, referenced entities, and constraints in the normalized CAD operation sequence are parameterized to form parameter information for the component family (parameter mode, default value, and effective range). By combining the component family's parameter information with the semantic modeling stage, extracting key dependencies from the semantic modeling stage, and supplementing validation rules from the parameter information, a complete template CAD-IR (historical preset template) can be obtained. The CAD-IR records global parameters, required backend tools, sequentially arranged CAD operations, generated entities, dependencies, and validation rules.

[0066] Engineering descriptions provide semantic identifiers and classification criteria for component skills, clarifying the function, category, applicable standards, and design intent of parts using natural language or semi-structured text. This enables skills to possess searchable and matchable metadata, ensuring that the system can accurately identify and invoke corresponding design knowledge when faced with high-level intents or fuzzy inputs. Parameter information defines the variable interface and constraint space of component skills, including parameter modes, default values, and valid ranges, and clarifies the driving relationships between parameters. It enables skills to have specification variation capabilities, allowing instantiation and assignment within the allowed value space when receiving specific variation requests, and accepting compliance verification at the parameter level. Template CAD-IR, as the core of component skills, encapsulates software-independent local operation sequences, key dependencies, and verification rules. It records the complete semantic modeling process from base construction to detail finishing, solidifying expert modeling logic in a structured intermediate representation form. This ensures that, given parameter values, skills can be accurately translated into backend CAD tool calls, generating B-Rep entities and feature trees that conform to engineering specifications. Therefore, by structurally integrating engineering descriptions, parameter information, and template CAD-IR, component skills for intelligent design and automatic generation systems can be constructed. Finally, based on different types of component skills, and after verification through CAD backend playback, they can be stored in the skill knowledge base to construct an expert skill knowledge base.

[0067] This embodiment acquires expert knowledge data, which includes at least macro records, operation history, feature trees, drawing instructions, parameter tables, engineering descriptions, and boundary requirements for computer-aided design. The expert knowledge data is preprocessed to obtain a normalized sequence of computer-aided design operations. An expert skill knowledge base is then constructed based on this normalized sequence. By parsing, semantically segmenting, and abstracting parameters from the expert knowledge data, a one-time expert modeling process can be transformed into reusable, parameterizable, and verifiable component skills. This allows expert experience to be structurally stored in the skill knowledge base, reducing the workload of repeatedly constructing modeling processes for subsequent variations of similar components.

[0068] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 Step S30 includes steps S301 to S304: Step S301: Obtain historical preset templates from the expert skill knowledge base according to the variant request based on the component family type and the target skill.

[0069] It should be understood that, based on the variant request and the target skill, the corresponding template CAD-IR (historical preset template) can be retrieved from the expert skill knowledge base; the historical preset template usually refers to the pre-constructed parameterized template of the component family that is parsed, distilled and built from expert knowledge data and can be directly reused.

[0070] Step S302: Fill or update the operation parameters in the historical preset template to obtain the first target template.

[0071] It is understandable that some operation parameters may be missing or not explicitly recorded in the historical preset templates extracted from the expert knowledge database, or the existing operation parameter values ​​may be unreasonable or out of sync, or they may need to be adapted to new design intentions (for example, if the hole diameter is changed from 8 to 10, the corresponding shaft diameter also needs to be updated). In such cases, it is necessary to supplement the missing operation parameter definitions or modify the default values ​​and effective ranges of the operation parameters, or rebind the relationship between parameters and operations, based on default value rules, symmetry inference, engineering standards, or statistics of similar characteristics, to obtain the first target template.

[0072] Step S303: Insert or modify the local operations in the first target template to obtain the second target template.

[0073] In addition, the first target template may lack a certain necessary feature or the operation order may be incorrect (for example, chamfering before drilling results in the chamfer being on the edge of the hole, when drilling should be done before chamfering). In this case, it is necessary to add a new local operation (such as adding a draft angle) or adjust the type, order, and parameterization method of the existing local operations to obtain the second target template.

[0074] Step S304: Obtain the target preset template based on the second target template.

[0075] Understandably, since any modifications made in the above steps may result in the loss of reference surfaces, failure of feature regeneration, or violation of design specifications, it is necessary to maintain a dynamic consistency of key dependencies and verification rules based on the second target template: the dependencies between the modified or inserted reference surfaces and features are still valid, the parameters are still within the valid range, the geometry does not self-intersect, and the verification rules still meet the engineering specifications. After maintaining a dynamic consistency of key dependencies and verification rules based on the second target template, the instantiated template CAD-IR (target preset template) can be obtained. The target preset template refers to an intermediate representation for a specific specification part that can be directly translated and executed after replacing the abstract parameters in the historical preset template with specific values ​​requested by the user or derived by the system.

[0076] This embodiment retrieves historical preset templates from the expert skill knowledge base based on the variant request based on the component family type and the target skill; it fills or updates the operation parameters in the historical preset templates to obtain a first target template; it inserts or modifies local operations in the first target template to obtain a second target template; and it obtains a target preset template based on the first target template and the second target template. By maintaining key dependencies and verification rules when instantiating CAD-IR, and modifying only the parameters and local operations related to the variant request, it can maintain a stable modeling paradigm for the component family when generating a new variant model, reducing unstable results caused by re-inferring the entire modeling process.

[0077] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the computer-aided design model generation method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0078] This application also provides a computer-aided design model generation device; please refer to... Figure 5 The computer-aided design model generation device includes: Module 10 is used to build an expert skills knowledge base based on expert knowledge data.

[0079] The retrieval module 20 is used to receive a variant request based on the component family type, and retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type.

[0080] The generation module 30 is used to obtain a target preset template based on the variant request based on the component family type and the target skill.

[0081] The generation module 30 is also used to generate a computer-aided design model based on the target preset template.

[0082] The computer-aided design model generation apparatus provided in this application, employing the computer-aided design model generation method described in the above embodiments, can solve the technical problem that current computer-aided design model generation is easily affected by user input information, resulting in low efficiency. Compared with the prior art, the beneficial effects of the computer-aided design model generation apparatus provided in this application are the same as those of the computer-aided design model generation method provided in the above embodiments, and other technical features in the computer-aided design model generation apparatus are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0083] In one embodiment, the construction module 10 is further configured to acquire expert knowledge data, wherein the expert knowledge data includes at least macro records, operation history, feature trees, drawing instructions, parameter tables, engineering descriptions, and boundary requirements of computer-aided design; preprocess the expert knowledge data to obtain a normalized operation sequence of computer-aided design; and construct an expert skill knowledge base based on the normalized operation sequence of computer-aided design.

[0084] In one embodiment, the construction module 10 is further configured to: obtain a semantic modeling stage based on the operation sequence; perform parameter abstraction on the operation sequence to obtain parameter information of the component family, wherein the parameter information includes at least parameter mode, default value and effective range; generate a historical preset template based on the semantic modeling stage and the parameter information; combine the project description, the parameter information and the historical preset template into component skills; and construct an expert skill knowledge base based on the component skills.

[0085] In one embodiment, the construction module 10 is further configured to parse the expert knowledge data to obtain an initial computer-aided design operation sequence; delete and filter irrelevant operations in the initial computer-aided design operation sequence to obtain a filtered computer-aided design operation sequence; and normalize the parameters and formats in the filtered computer-aided design operation sequence to obtain a normalized computer-aided design operation sequence.

[0086] In one embodiment, the generation module 30 is further configured to: obtain historical preset templates from the expert skill knowledge base according to the variant request based on the component family type and the target skill; fill or update the operation parameters in the historical preset templates to obtain a first target template; insert or modify the local operations in the first target templates to obtain a second target template; and obtain a target preset template based on the first target template and the second target template.

[0087] In one embodiment, the generation module 30 is further configured to parse the target preset template to obtain general feature operations; translate the general feature operations to obtain a target backend call sequence; and generate a computer-aided design model based on the target backend call sequence.

[0088] In one embodiment, the generation module 30 is further configured to generate a multi-view rendering and a structured summary based on the computer-aided design model; obtain feedback information based on the multi-view rendering and the structured summary; obtain acceptance conditions based on the feedback information; and, when the acceptance conditions do not meet the user's requirements, return to the step of obtaining the target preset template based on the variant request based on the component family type and the target skill, until the acceptance conditions meet the user's requirements.

[0089] This application provides a computer-aided design model generation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the computer-aided design model generation method in Embodiment 1 above.

[0090] The following is for reference. Figure 6 The diagram illustrates a structural schematic of a computer-aided design model generation device suitable for implementing embodiments of this application. The computer-aided design model generation device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The computer-aided design model generation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0091] like Figure 6As shown, the computer-aided design model generation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the computer-aided design model generation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the computer-aided design model generation device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a computer-aided design model generation device with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0092] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0093] The computer-aided design model generation device provided in this application, employing the computer-aided design model generation method described in the above embodiments, can solve the technical problem that current computer-aided design model generation is easily affected by user input information, resulting in low efficiency. Compared with the prior art, the beneficial effects of the computer-aided design model generation device provided in this application are the same as those of the computer-aided design model generation method provided in the above embodiments, and other technical features in this computer-aided design model generation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0094] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0095] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0096] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the computer-aided design model generation method in the above embodiments.

[0097] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0098] The aforementioned computer-readable storage medium may be included in the computer-aided design model generation device; or it may exist independently and not be assembled into the computer-aided design model generation device.

[0099] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a computer-aided design model generation device, the computer-aided design model generation device: constructs an expert skill knowledge base based on expert knowledge data; receives a variant request based on a component family type, and retrieves a corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type; obtains a target preset template based on the variant request based on the component family type and the target skill; and generates a computer-aided design model based on the target preset template.

[0100] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0103] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described computer-aided design model generation method. This solves the technical problem that current computer-aided design model generation is easily affected by user input information, leading to low efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the computer-aided design model generation method provided in the above embodiments, and will not be repeated here.

[0104] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the computer-aided design model generation method described above.

[0105] The computer program product provided in this application can solve the technical problem that the generation of computer-aided design models is easily affected by user input information, resulting in low efficiency. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the computer-aided design model generation method provided in the above embodiments, and will not be repeated here.

[0106] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for generating computer-aided design models, characterized in that, The computer-aided design model generation method includes: Build an expert skills knowledge base based on expert knowledge data; Receive a variant request based on a component family type, and retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type; A target preset template is obtained based on the variant request based on the component family type and the target skill; A computer-aided design model is generated based on the target preset template; The step of constructing an expert skills knowledge base based on expert knowledge data includes: Acquire expert knowledge data, wherein the expert knowledge data includes at least the macro records, operation history, feature tree, drawing instructions, parameter table, engineering description and boundary requirements of computer-aided design; The expert knowledge data is preprocessed to obtain a normalized computer-aided design operation sequence; An expert skills knowledge base is constructed based on the normalized computer-aided design operation sequence.

2. The method as described in claim 1, characterized in that, The step of constructing an expert skills knowledge base based on the normalized computer-aided design operation sequence includes: The semantic modeling stage is obtained based on the operation sequence; The operation sequence is parameterized to obtain the parameter information of the component family, wherein the parameter information includes at least the parameter mode, default value, and valid range; Generate historical preset templates based on the semantic modeling stage and the parameter information; The component skills are combined based on the project description, the parameter information, and the historical preset templates. An expert skills knowledge base is built based on the skills of the components.

3. The method as described in claim 1, characterized in that, The steps of preprocessing the expert knowledge data to obtain a normalized computer-aided design operation sequence include: The expert knowledge data is parsed to obtain the initial computer-aided design operation sequence; Irrelevant operations are removed and filtered from the initial computer-aided design operation sequence to obtain a filtered computer-aided design operation sequence. The parameters and formats in the filtered computer-aided design operation sequence are normalized to obtain a normalized computer-aided design operation sequence.

4. The method as described in claim 1, characterized in that, The step of obtaining the target preset template based on the variant request based on the component family type and the target skill includes: Based on the variant request based on the component family type and the target skill, retrieve historical preset templates from the expert skill knowledge base; The operation parameters in the historical preset template are filled or updated to obtain the first target template; By inserting or modifying local operations in the first target template, a second target template is obtained. The target preset template is obtained based on the second target template.

5. The method as described in claim 1, characterized in that, The step of generating a computer-aided design model based on the target preset template includes: The target preset template is parsed to obtain general feature operations; The general feature operations are translated to obtain the target backend call sequence; A computer-aided design model is generated based on the target backend call sequence.

6. The method according to any one of claims 1 to 5, characterized in that, Following the step of generating a computer-aided design model based on the target preset template, the method further includes: Based on the computer-aided design model, generate multi-view renderings and structured summaries; Feedback information is obtained based on the multi-view rendering graph and the structured summary; The acceptance criteria are determined based on the feedback information. If the acceptance condition does not meet the target requirements, return to the step of obtaining the target preset template based on the variant request based on the component family type and the target skill, until the acceptance condition meets the target requirements.

7. A computer-aided design model generation device, characterized in that, The computer-aided design model generation device includes: The module is used to build an expert skills knowledge base based on expert knowledge data; The retrieval module is used to receive a variant request based on the component family type, and retrieve the corresponding target skill from the expert skill knowledge base based on the variant request based on the component family type; The generation module is used to obtain a target preset template based on the variant request based on the component family type and the target skill; The generation module is also used to generate a computer-aided design model based on the target preset template.

8. A computer-aided design model generation device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the computer-aided design model generation method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the computer-aided design model generation method as described in any one of claims 1 to 6.

Images