Intelligent annotation method and plug-in for CAD drawing

Abstract

The present invention discloses an intelligent annotation method and plug-in for CAD drawing, which relates to data processing related fields, including: calling a native interface to traverse the CAD drawing set to extract annotation objects, and obtain multiple annotation attribute original information of multiple original drawings; interactively obtaining assembly relationship characteristics of multiple assembly entities; performing conflict correction on the annotation attribute original information to obtain corrected attribute information; performing non-standard symbol matching conversion on the corrected attribute information to obtain symbolic attribute information; structurally incrementing the symbolic attribute information on the original drawing; performing index analysis on the corrected attribute information to construct functional index annotation of the annotated drawing. The method solves the technical problem of the lack of comprehensive consideration of assembly logical relationships in existing CAD drawing annotations, resulting in insufficient annotation conflict discovery and correction capabilities, and achieves accurate identification and efficient correction of CAD drawing annotation conflicts, thereby improving the accuracy and reliability of CAD drawing annotations.

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to an intelligent annotation method and plug-in for CAD drawing. Background Art

[0002] In the field of CAD drawing, accurate, efficient, and standardized annotations are crucial for accurately conveying design intent and facilitating subsequent drawing interpretation and use, directly impacting the efficiency and quality of engineering design and manufacturing. Currently, resolving annotation conflicts in CAD drawings primarily relies on manual inspection and verification. This manual inspection method is not only labor-intensive and time-consuming, but also prone to overlooking annotation conflicts due to human negligence when working with complex assembly drawings. This makes it impossible to guarantee the full accuracy of annotations, resulting in a large number of hidden annotation conflicts in the drawings, seriously affecting their readability and subsequent engineering applications.

[0003] In the current related technologies, CAD drawing annotation lacks comprehensive consideration of assembly logical relationships, resulting in technical problems such as insufficient ability to discover and correct annotation conflicts. Summary of the Invention

[0004] The present application provides an intelligent annotation method and plug-in for CAD drawing. The method first calls the native interface of the CAD software to traverse the atlas to extract the annotation objects, obtains the original information of the annotation attributes of multiple original drawings, and then interactively obtains the assembly relationship characteristics of the assembly entity. Based on this feature, the original information of the annotation attributes is corrected to obtain the corrected attribute information. Then, a predefined rule library is loaded, and the corrected attribute information is converted to non-standard symbol matching to obtain symbolic attribute information. The symbolic attribute information is then annotated to the original drawing in a structured incremental manner to obtain the annotated CAD drawing. Finally, the corrected attribute information is indexed and analyzed, and functional index annotation is constructed. The technical means solves the technical problem of the lack of comprehensive consideration of assembly logical relationships in existing CAD drawing annotations, resulting in insufficient annotation conflict detection and correction capabilities, and achieves the technical effect of accurately identifying and efficiently correcting CAD drawing annotation conflicts, thereby improving the accuracy and reliability of CAD drawing annotations.

[0005] The present application provides an intelligent annotation method for CAD drawing, comprising: calling a native interface of CAD software to traverse a CAD atlas to extract annotation objects, and obtain multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities; interactively obtaining multiple assembly relationship features of the multiple assembly entities; performing conflict correction on the multiple annotation attribute original information according to the multiple assembly relationship features, and obtain multiple corrected attribute information; loading a predefined symbol annotation rule library, performing non-standard symbol matching conversion on the multiple corrected attribute information, and obtain multiple symbolized attribute information; structurally incrementally annotating the multiple symbolized attribute information on the multiple original CAD drawings, and obtain multiple annotated CAD drawings; and constructing functional index annotations of the multiple annotated CAD drawings by performing index analysis on the multiple corrected attribute information.

[0006] In a possible implementation, based on the multiple assembly relationship features, the multiple annotation attribute original information is conflict-corrected to obtain multiple corrected attribute information, and the following processing is performed: based on the multiple assembly relationship features, the multiple annotation attribute original information is restored with missing annotations through adjacent entity annotation deduction to obtain multiple restored attribute information; based on the multiple assembly relationship features, the multiple restored attribute information is geometrically tolerated across drawings to obtain a cross-drawing conflict set; based on the cross-drawing conflict set, the multiple restored attribute information is directional-corrected to obtain the multiple corrected attribute information.

[0007] In a possible implementation, based on the multiple assembly relationship features, the multiple restored attribute information are subjected to cross-drawing geometric tolerance verification to obtain a cross-drawing conflict set. Before that, the following processing is performed: based on the entity type of the multiple assembly entities, multiple single-drawing conflict rules are retrieved online; based on the first single-drawing conflict rule, the first restored attribute information is traversed to perform internal self-consistent verification of the single drawing to obtain a first single-drawing conflict defect set; based on the first single-drawing conflict defect set, a first correction information library is retrieved and called; the first single-drawing conflict defect set is used to traverse the first correction information library to extract a first single-drawing conflict correction set; the first single-drawing conflict correction set is used to perform local attribute replacement on the first restored attribute information to obtain first single-drawing attribute information; and so on, single-drawing conflict correction is performed on the multiple restored attribute information according to the multiple single-drawing conflict rules to obtain multiple single-drawing attribute information; based on the multiple assembly relationship features, cross-drawing geometric tolerance verification is performed on the multiple single-drawing attribute information.

[0008] In a possible implementation, the first correction information library is retrieved and called based on the first single drawing conflict defect set, and the following processing is performed: the first entity structure feature is extracted from the first original CAD drawing; the first single drawing conflict defect set is filtered out from the first restored attribute information to obtain the first compliance attribute information; the first compliance attribute information and the first entity structure feature are used as retrieval conditions, and the first correction information library is called through local matching.

[0009] In a possible implementation, based on the multiple assembly relationship features, the multiple restoration attribute information are verified for geometric tolerances across drawings to obtain a cross-drawing conflict set, and the following processing is performed: a global assembly tree of the target assembly structure is constructed based on the multiple assembly relationship features, wherein the global assembly tree is a P-layer; starting from the P-1 layer, the global assembly tree is decomposed layer by layer at the component level to obtain a multi-layer component-level assembly subtree set; after performing fitting tolerance correction on the part entities within the monomer component-level assembly subtree of the multi-layer component-level assembly subtree set, a hierarchical dimension chain closure verification is performed on the multi-layer component-level assembly subtree set from the bottom up to locate the cross-drawing conflict set.

[0010] In a possible implementation, the following processing is also performed: interactively obtaining multiple groups of sample tolerance combinations for multiple sample part combinations in multiple sample matching scenarios; associating and storing the multiple sample part combinations, multiple sample matching scenarios and multiple groups of sample tolerance combinations to complete the construction of a matching rule library; parsing the cross-drawing conflict set, and outputting O real-time matching scenarios of O real-time part combinations; using the O real-time part combinations and O real-time matching scenarios as two-dimensional matching conditions, traversing the matching rule library to obtain O sample tolerance combinations; using the cross-drawing conflict set as a correction guide, using the O sample tolerance combinations to perform tolerance correction on the multi-layer component-level assembly subtree set.

[0011] In a possible implementation, based on the cross-drawing conflict set, the multiple restored attribute information are subjected to directional conflict correction to obtain the multiple corrected attribute information, and the following processing is also performed: calling the conflict priority rule; aggregating the cross-drawing conflict set according to the conflict priority rule to obtain a multi-level priority conflict set; after correcting the multi-level priority conflict set according to the multi-level conflict correction strategy mapping, performing closed-loop feedback verification until the update result of the cross-drawing conflict set is an empty set, and outputting a conflict correction information set; based on the cross-drawing conflict set, using the conflict correction information set to perform local attribute replacement on the multiple restored attribute information to obtain the multiple corrected attribute information.

[0012] In a possible implementation, by performing index analysis on the multiple correction attribute information, functional index annotations of the multiple annotated CAD drawings are constructed, and the following processing is also performed: multimodal index analysis is performed on the multiple correction attribute information to obtain multiple index sub-topologies of the multiple assembly entities; the multiple index sub-topologies are fused to construct a CAD drawing index topology; the multiple annotated CAD drawings are stored in the CAD drawing index topology to complete the functional index annotation of the CAD atlas.

[0013] In a possible implementation, the following processing is further performed: after fuzzy correction is performed on the multiple corrected attribute information, the multiple corrected attribute information are converted into non-standard symbols using the symbol annotation rule library to obtain the multiple symbolized attribute information.

[0014] The present application also provides an intelligent annotation plug-in for CAD drawing, including: an annotation object extraction module, which is used to call the native interface of the CAD software to traverse the CAD atlas to extract annotation objects, and obtain multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities; an assembly relationship feature acquisition module, which is used to interactively obtain multiple assembly relationship features of the multiple assembly entities; a conflict correction module, which is used to perform conflict correction on the multiple annotation attribute original information according to the multiple assembly relationship features, and obtain multiple corrected attribute information; a non-standard symbol matching conversion module, which is used to load a predefined symbol annotation rule library, perform non-standard symbol matching conversion on the multiple corrected attribute information, and obtain multiple symbolized attribute information; an annotation module, which is used to structurally incrementally annotate the multiple symbolized attribute information on the multiple original CAD drawings, and obtain multiple annotated CAD drawings; an index analysis module, which is used to construct functional index annotations of the multiple annotated CAD drawings by performing index analysis on the multiple corrected attribute information.

[0015] The intelligent annotation method and plug-in for CAD drawing proposed in this application first calls the native interface of the CAD software to traverse the CAD atlas to extract annotation objects, and obtains multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities, and then interactively obtains multiple assembly relationship features of the multiple assembly entities. Then, based on the multiple assembly relationship features, the multiple annotation attribute original information is corrected for conflicts to obtain multiple corrected attribute information, and then the predefined symbol annotation rule library is loaded, and the multiple corrected attribute information is converted to non-standard symbols to obtain multiple symbolized attribute information. Then, the multiple symbolized attribute information is incrementally annotated in a structured manner on the multiple original CAD drawings to obtain multiple annotated CAD drawings. Finally, by performing index analysis on the multiple corrected attribute information, functional index annotations of the multiple annotated CAD drawings are constructed. This achieves the technical effect of accurately identifying and efficiently correcting CAD drawing annotation conflicts and improving the accuracy and reliability of CAD drawing annotations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following is a brief introduction to the accompanying drawings of the embodiments of the present invention. Flowcharts are used in this application to illustrate the operations performed by the plug-in according to the embodiments of the present application. It should be understood that the preceding or following operations do not necessarily need to be performed in precise order. Instead, various steps may be processed in reverse order or simultaneously, as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of an intelligent annotation method for CAD drawing provided in an embodiment of the present application.

[0018] Figure 2 A schematic diagram of the structure of an intelligent annotation plug-in for CAD drawing provided in an embodiment of the present application.

[0019] Description of the accompanying drawings: annotation object extraction module 10, assembly relationship feature acquisition module 20, conflict correction module 30, non-standard symbol matching and conversion module 40, annotation module 50, index analysis module 60. DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The present application provides an intelligent annotation method for CAD drawing, such as Figure 1 As shown, the method includes:

[0024] Step S100 , calling the native interface of the CAD software to traverse the CAD drawing set to extract the annotation objects, and obtaining multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities.

[0025] Specifically, the native interface of the CAD software refers to the programming interface provided by the CAD software, which is used to access and operate CAD files. The annotation object refers to the element that needs to be annotated on the drawing, such as dimension lines, tolerance symbols, etc. The original information of the annotation attribute refers to the attributes of the annotation object. The assembly entity refers to the various parts or components that make up the assembly. Specifically, the CAD atlas is accessed through a programming interface (such as AutoLISP, NET API of AutoCAD or API of SolidWorks). Use a recursive or iterative algorithm to traverse all drawings in the atlas, and use the query function of the CAD software to extract the attribute information of the annotation object, including the dimension value, tolerance zone, associated geometric entity ID and coordinate range.

[0026] For example, suppose there is a set of mechanical assembly drawings, including a gear, a shaft and a housing. Through the AutoCAD API, the drawings are traversed to extract the diameter of the gear marked as "D30mm", the length of the shaft marked as "L50mm", and the size of the housing marked as "W100mm×H80mm".

[0027] Step S200 , interactively obtaining a plurality of assembly relationship features of the plurality of assembly entities.

[0028] Specifically, assembly relationship features refer to the assembly methods and connection relationships between parts, such as threaded connections, welding, and interference fits. A user interface is developed to allow users to input or select relationships between assembly entities. The user-entered assembly relationship features are stored in a database or memory for subsequent processing. Geometric analysis algorithms can also be used to automatically identify some assembly relationships, such as by identifying contact surfaces or axis alignments between geometric entities.

[0029] For example, a web-based interactive interface can be designed where users can define assembly relationships by dragging part models and confirm the relationship type (such as threaded connection, welding, etc.) by clicking a button. For example, a user can define the gear-shaft fit relationship as "interference fit" and the housing-gear fit relationship as "embedded assembly" through the interactive interface.

[0030] Step S300 : performing conflict correction on the plurality of original annotation attribute information according to the plurality of assembly relationship features to obtain a plurality of corrected attribute information.

[0031] Specifically, conflict correction involves adjusting annotation information to resolve conflicts between annotations and assembly relationships. This involves checking the logical consistency between annotation attributes and assembly relationships. For example, it checks whether dimensions meet assembly requirements. Conflicting annotation attributes are automatically corrected based on predefined rules (such as dimensional tolerances and clearances). After the automatic corrections are made, a user interface is provided to allow the user to confirm or modify the corrections.

[0032] For example, when matching gears and shafts, the system checks whether the gear ID is consistent with the shaft OD. If not, the gear ID is automatically adjusted based on the tolerance range. For example, a correction rule might be as follows: If the gear ID is greater than the shaft OD + the upper tolerance limit, the gear ID is adjusted to the shaft OD + the upper tolerance limit; if the gear ID is less than the shaft OD - the lower tolerance limit, the gear ID is adjusted to the shaft OD - the lower tolerance limit.

[0033] In one possible implementation, based on the multiple assembly relationship features, the multiple original annotation attribute information is conflict-corrected to obtain multiple corrected attribute information. Step S300 further includes step S310, based on the multiple assembly relationship features, the multiple original annotation attribute information is restored by adjacent entity annotation deduction to obtain multiple restored attribute information. Specifically, the missing annotation information is derived by analyzing the annotation information and assembly relationship of adjacent entities. For example, if two parts are connected by threads and the thread size of one part is known, the thread size of the other part can be derived. Alternatively, geometric analysis tools (such as computational geometry libraries) are used to analyze the geometric relationships between parts, such as contact surfaces, alignment relationships, etc., to assist in the derivation of missing annotations. Alternatively, deduction is performed according to predefined rules (such as standard assembly specifications). For example, if two parts are coaxially assembled, their axis coordinates should be consistent.

[0034] For example, suppose a gear and shaft are connected by a keyway. The gear keyway dimensions are dimensioned as "W10mm × L20mm," but the shaft keyway dimensions are not. By analyzing the assembly relationship (if two parts are connected by a keyway, their keyway width and length should be the same) and the known dimensions, it can be deduced that the shaft keyway dimensions should also be "W10mm × L20mm."

[0035] In step S320, based on the multiple assembly relationship features, the multiple restoration attribute information is subjected to cross-drawing geometric tolerance verification to generate a cross-drawing conflict set. Specifically, the annotation information on different drawings is checked to see if it meets the geometric tolerance requirements. For example, tolerance analysis tools (such as tolerance stackup analysis) are used to check if the dimensional tolerances of the two mating parts are within the allowable range. The cross-drawing geometric tolerances are verified, and any annotation information that does not meet the tolerance requirements is recorded to form a cross-drawing conflict set.

[0036] For example, suppose a gear drawing specifies an inner diameter of "D30mm ± 0.1mm" and a shaft drawing specifies an outer diameter of "D30.2mm ± 0.1mm." A cross-drawing geometric tolerance verification reveals that the maximum inner diameter of the gear (30.1mm) is equal to the minimum outer diameter of the shaft (30.1mm). This means that in the most extreme case (maximum inner diameter of the gear, minimum outer diameter of the shaft), the two dimensions will precisely match, with no clearance. This situation can lead to assembly difficulties or even impossibility, as actual machining errors may cause the dimensions to exceed the tolerance range, resulting in a conflict.

[0037] In step S330, based on the cross-drawing conflict set, directional conflict correction is performed on the multiple restored attribute information to obtain the multiple corrected attribute information. Specifically, based on the cross-drawing conflict set, the annotation information is automatically adjusted to resolve the conflict. For example, the tolerance range of the gear inner diameter or the size of the shaft outer diameter may be adjusted. Predefined correction rules are used to ensure that the corrected annotation information meets assembly requirements. After the automatic correction, a user interface is provided to allow the user to confirm or modify the correction results.

[0038] For example, based on the above conflict set and correction rules, the tolerance range of the gear inner diameter is automatically adjusted to "D30mm±0.2mm" to ensure that the maximum value of the gear inner diameter (30.2mm) can accommodate the minimum value of the shaft outer diameter (30.1mm).

[0039] This approach automatically restores missing annotation information by inferring adjacent entity annotations, reducing omissions in manual annotations. Cross-drawing geometric tolerance verification and orientation conflict correction ensure consistency and accuracy of annotation information across different drawings.

[0040] In one possible implementation, based on the multiple assembly relationship features, the multiple restored attribute information is subjected to cross-drawing geometric tolerance verification to obtain a cross-drawing conflict set. Prior to this, step S300 further includes step S340, where a plurality of single-drawing conflict rules are retrieved online based on the entity types of the multiple assembly entities. Specifically, a database containing conflict rules for various entity types is maintained, and this database or knowledge base is connected to the database via a network to retrieve single-drawing conflict rules related to the assembly entity type. Specifically, the type of each assembly entity (e.g., gear, shaft, housing, etc.) is identified, and corresponding conflict rules are obtained based on the type.

[0041] For example, assuming that the assembly entity includes gears and shafts, examples of single drawing conflict rules retrieved online are as follows: Gear conflict rules: "Inner diameter tolerance range should be less than or equal to outer diameter tolerance range" and "The number of teeth must be an integer"; Shaft conflict rules: "Outer diameter tolerance range should be greater than inner diameter tolerance range" and "Axial length should be greater than or equal to the minimum assembly length".

[0042] Step S350: Based on the first single-drawing conflict rule, the first restored attribute information is traversed to perform internal self-consistency verification of the single drawing, obtaining a first single-drawing conflict defect set. Specifically, a rule engine is used to verify the restored attribute information according to the retrieved conflict rule, traversing all annotations on the single drawing to check whether they comply with the conflict rule. Annotations that do not comply with the rule are recorded to form a conflict defect set.

[0043] Step S360, retrieve and call the first correction information library based on the first single drawing conflict defect set. Specifically, maintain a database containing correction suggestions for retrieving corresponding correction information based on the conflict defect set. Use the retrieval algorithm to retrieve specific correction suggestions based on the conflict type and entity type. For example, the correction suggestion corresponding to "the inner diameter tolerance range should be less than or equal to the outer diameter tolerance range" is "adjust the inner diameter tolerance range to ±0.05mm". Step S370, use the first single drawing conflict defect set to traverse the first correction information library and extract the first single drawing conflict correction set. Specifically, based on the information in the conflict defect set, extract specific correction suggestions from the correction information library to generate a set containing all correction suggestions.

[0044] Step S380, use the first single drawing conflict correction set to perform partial attribute replacement on the first restored attribute information to obtain the first single drawing attribute information. Specifically, according to the suggestions in the correction set, perform partial replacement on the annotation information, and update the replaced annotation information to the drawing. For example, replace the gear inner diameter annotation from "D30mm±0.1mm" to "D30mm±0.2mm". Step S390, and so on, perform single drawing conflict correction on the multiple restored attribute information according to the multiple single drawing conflict rules to obtain multiple single drawing attribute information. Specifically, repeat the above steps for all drawings and entity types to ensure that the annotation information on each drawing is corrected. All corrected annotation information is aggregated to form multiple single drawing attribute information.

[0045] Step S3100: Based on the multiple assembly relationship features, the multiple single-drawing attribute information is subjected to cross-drawing geometric tolerance verification. Specifically, a tolerance analysis tool is used to check whether the annotation information on different drawings meets the geometric tolerance requirements, thereby verifying the cross-drawing geometric tolerance. Annotation information that does not meet the tolerance requirements is recorded to form a cross-drawing conflict set.

[0046] This implementation utilizes a phased conflict resolution mechanism, first ensuring the consistency of annotation information within each drawing, reducing the complexity of cross-drawing verification. After conflicts within a single drawing are resolved, cross-drawing geometric tolerance verification is then performed to ensure the reliability of the overall assembly.

[0047] In one possible implementation, the first correction information library is retrieved and invoked based on the first single drawing conflict defect set. Step S360 further includes step S361, where structural features of the first entity are extracted from the first original CAD drawing. Specifically, structural features of the entity in the drawing, such as geometric shape, dimensions, tolerances, and relationships, are extracted using the CAD software API or geometric analysis tools. The extracted structural features are stored as structured data for subsequent processing.

[0048] For example, assuming the first original CAD drawing is a gear drawing, the extracted structural features include: Gear type: spur gear; Module: 2; Number of teeth: 20; Inner diameter: D30mm ± 0.1mm; Outer diameter: D50mm ± 0.1mm; Tooth width: 10mm. The extracted structural features are stored in JSON format.

[0049] Step S362: Filter out the first single drawing conflict defect set from the first restored attribute information to obtain first compliance attribute information. Specifically, based on the annotation information in the conflict defect set, filter out non-compliant portions from the restored attribute information, retain the annotation information that complies with the rules, and form the compliance attribute information.

[0050] For example, suppose the first restored attribute information includes: Inner diameter: D30mm±0.1mm; Outer diameter: D50mm±0.1mm; Tooth width: 10mm. Suppose the conflicting defect set is: Inner diameter: D30mm±0.1mm. After removing the conflicting defects, the first compliant attribute information is: Outer diameter: D50mm±0.1mm; Tooth width: 10mm.

[0051] In step S363, the first compliance attribute information and the first entity structure feature are used as search criteria to locally match and call the first correction information library. Specifically, the compliance attribute information and the entity structure feature are combined into a search criterion. In the local correction information library, corresponding correction suggestions are matched according to the search criterion, and the matched correction suggestions are extracted to form a correction set.

[0052] This approach extracts structural features from entities, providing richer context for revisions, making revision suggestions more tailored to actual design needs. By filtering out conflicting defects and ensuring the accuracy of compliance attribute information, it prevents erroneous information from interfering with the revision process.

[0053] In one possible implementation, based on the multiple assembly relationship features, the multiple restoration attribute information is subjected to geometric tolerance verification across drawings to obtain a cross-drawing conflict set. Step S320 further includes step S321, constructing a global assembly tree of the target assembly structure based on the multiple assembly relationship features, wherein the global assembly tree is a P-layer. Specifically, by analyzing the assembly relationship features, a hierarchical structure of the assembly tree is constructed. Each node represents a component or part, and the parent-child relationship represents the assembly relationship. A tree-shaped data structure is used to store the global assembly tree, and the hierarchy, part information, and assembly relationship of each node are recorded. According to the complexity of the assembly, the assembly tree is divided into P layers, where P is the maximum number of levels.

[0054] For example, suppose a mechanical assembly includes a housing, gears, and shafts. The global assembly tree is as follows: Level 1: housing, gears, shafts; Level 2: gears, shafts; Level 3: shafts.

[0055] Step S322 , starting from layer P-1, performs component-level decomposition of the global assembly tree layer by layer to obtain a multi-layer component-level assembly subtree set. Specifically, starting from layer P-1, the global assembly tree is decomposed layer by layer to generate component-level assembly subtrees at each layer, where each subtree contains the component at the current layer and its subordinate parts or components.

[0056] Step S323, after correcting the fit tolerance of the part entities within the monomer component-level assembly subtree of the multi-layer component-level assembly subtree set, perform a hierarchical dimension chain closure verification from the bottom up on the multi-layer component-level assembly subtree set to locate the cross-drawing conflict set. Specifically, within each component-level assembly subtree, correct the fit tolerance of the part entities to ensure that the direct fit relationship between parts within the same level meets the tolerance requirements. Starting from the bottom subtree, verify the closure of the dimension chain layer by layer to check whether there is a cross-level dimension conflict. Record the conflicts found during the verification process to form a cross-drawing conflict set.

[0057] For example, within level 2 (gears, shafts), a fit tolerance correction is performed: gear inner diameter: D30mm±0.1mm, shaft outer diameter: D30.2mm±0.1mm. After the correction, the gear inner diameter is adjusted to D30mm±0.2mm to accommodate the shaft outer diameter. A dimension chain closure verification is performed at level 1 (housing, gears, shafts): assuming the housing inner diameter is marked as D80mm±0.2mm, it is necessary to verify whether the overall dimensions of the gear assembly (gears and shaft) are compatible with the housing inner diameter. The overall dimension of the gear assembly is the gear outer diameter (which is the dimension that directly mates with the housing inner diameter) D50mm±0.1mm. Verify the parent level marking: the housing inner diameter is D80mm±0.2mm, which is compatible with the gear assembly dimension of 50mm±0.1mm, and passes the verification.

[0058] This implementation ensures that the dimensions of each component are within the tolerance range of the parent level by accumulating and verifying dimensions from the bottom up. Tolerance correction and dimension chain closure verification are performed at the component level, which can effectively detect and resolve dimension conflicts across drawings.

[0059] In one possible implementation, step S323 further includes step S3231, interactively obtaining multiple sets of sample tolerance combinations for multiple sample part combinations in multiple sample fit scenarios. Specifically, tolerance combinations for different part combinations in different fit scenarios are collected through experiments or historical data. A user interface is designed to allow the user to enter or select part combinations and fit scenarios.

[0060] Step S3232 associates and stores the multiple sample part combinations, multiple sample fit scenarios, and multiple sets of sample tolerance combinations to complete the construction of a fit rule library. Specifically, a database is designed to store the association information of part combinations, fit scenarios, and tolerance combinations, and the part combinations and fit scenarios are associated with the corresponding tolerance combinations.

[0061] Step S3233: Analyze the cross-drawing conflict set and output O real-time coordination scenarios for the O real-time part combinations. Specifically, analyze the cross-drawing conflict set to identify real-time part combinations and coordination scenarios. Output the identified part combinations and coordination scenarios as structured data.

[0062] In step S3234, the O real-time part combinations and O real-time coordination scenarios are used as two-dimensional matching conditions, and the coordination rule library is traversed to obtain O sample tolerance combinations. Specifically, a matching sample tolerance combination is searched in the coordination rule library based on the real-time part combinations and coordination scenarios, and a sample tolerance combination that matches the real-time conditions is retrieved from the coordination rule library.

[0063] Step S3235: Using the cross-drawing conflict set as a correction guide, the O sample tolerance combinations are used to correct the tolerances of the multi-layer component-level assembly subtree set. Specifically, the cross-drawing conflict set is used to guide the tolerance correction process, and the tolerances in the multi-layer component-level assembly subtree set are corrected based on the sample tolerance combinations.

[0064] This approach ensures that tolerance corrections are consistent with actual fit requirements and historical experience through the sample tolerance combinations provided by the fit rule library. Furthermore, by utilizing verified sample tolerance combinations for tolerance corrections, the reliability and consistency of assembly are improved.

[0065] In one possible implementation, based on the cross-drawing conflict set, targeted conflict correction is performed on the multiple restored attribute information to obtain the multiple corrected attribute information. Step S330 further includes step S331, invoking conflict priority rules. Specifically, a set of rules is defined to prioritize conflicts, for example, based on the severity of the impact on the assembly or the difficulty of resolving the conflict. These rules are invoked during conflict resolution to determine the order of resolution.

[0066] Step S332 aggregates the cross-drawing conflict set according to the conflict priority rules to obtain a multi-level priority conflict set. Specifically, a priority label is assigned to each conflict according to the priority rules, and conflicts within the conflict set are categorized and aggregated. For example, the conflict set can be categorized into three priority levels: high, medium, and low. High priority refers to conflicts that affect final assembly, medium priority refers to conflicts that affect partial functionality, and low priority refers to conflicts with minimal impact.

[0067] In step S333, after correcting the multi-level priority conflict set according to the multi-level conflict correction strategy mapping, closed-loop feedback verification is performed until the updated cross-drawing conflict set is an empty set, and a conflict correction information set is output. Specifically, a correction strategy is developed for each conflict priority. After correction, verification is performed, and all conflicts are rechecked. If unresolved, the correction process is re-entered until no new conflicts arise, ensuring that conflicts are resolved. When all conflicts are resolved, an empty set is output, indicating that conflict correction is complete.

[0068] Step S334: Based on the cross-drawing conflict set, the conflict correction information set is used to perform partial attribute replacement on the multiple restored attribute information to obtain the multiple corrected attribute information. Specifically, based on the conflict correction information set, the restored attribute information is replaced as necessary to generate a corrected attribute information set.

[0069] This implementation uses priority rules and multi-level conflict correction strategies to more effectively manage and resolve conflicts, prioritizing the most important issues. Closed-loop feedback verification ensures that all conflicts are resolved, improving design consistency and reliability.

[0070] Step S400 : loading a predefined symbol annotation rule library, performing non-standard symbol matching conversion on the plurality of modified attribute information, and obtaining a plurality of symbolized attribute information.

[0071] Specifically, a symbol annotation rule library is created to store the mapping relationship between standard symbols and annotation attributes, the revised annotation attributes are matched with the standard symbols in the symbol rule library, and the matched standard symbols replace the original non-standard annotation symbols to obtain symbolic attribute information.

[0072] For example, convert the corrected dimension to the standard symbol, such as converting "D30.1mm" to "D30.1".

[0073] In a possible implementation, the method further includes: after fuzzy correction is performed on the multiple corrected attribute information, the multiple corrected attribute information are converted into non-standard symbols by using the symbol annotation rule library to obtain the multiple symbolized attribute information.

[0074] Specifically, fuzzy logic is used to process modified attribute information to accommodate situations where boundaries are unclear or subject to multiple interpretations. Fuzzy correction of attribute information can involve fine-tuning numerical values ​​or appropriately expanding tolerance ranges. For example, if the inner diameter of a gear is marked as "D30mm±0.1mm," fuzzy correction would adjust the tolerance range to "D30mm±0.15mm" based on actual conditions and design requirements. Fuzzy correction allows designers to adjust attribute information appropriately to meet specific design requirements without violating design principles, enhancing design flexibility.

[0075] Step S500 : structurally and incrementally annotate the plurality of symbolic attribute information on the plurality of original CAD drawings to obtain a plurality of annotated CAD drawings.

[0076] Specifically, use the CAD software's annotation tools (such as AutoCAD's Dimension command) to annotate symbolic attribute information onto the drawing. Automatically adjust the position of new annotations based on the drawing layout and existing annotations to avoid overlap. For example, annotate the symbolic annotation "D30.1" on a gear drawing above the gear center; annotate "L50" on a shaft drawing at the shaft end.

[0077] Step S600 : constructing functional index annotations of the plurality of annotated CAD drawings by performing index analysis on the plurality of modified attribute information.

[0078] Specifically, functional index annotation is an indexing tool for quickly finding and locating annotation information on drawings. Corrected annotation attribute information is categorized and indexed, and the indexed information is stored in a database for quick access. Add index annotations to CAD drawings, such as using tables or annotations. For example, add a table in the corner of a drawing to list all part annotation information and their corresponding drawing locations.

[0079] In one possible implementation, functional index annotations for the multiple annotated CAD drawings are constructed by performing index analysis on the multiple modified attribute information. Step S600 further includes step S610, in which multimodal index analysis is performed on the multiple modified attribute information to obtain multiple index subtopologies for the multiple assembly entities. Specifically, the modified attribute information is indexed and analyzed based on multiple attributes (such as size, material, function, etc.) to generate multiple index subtopologies. An index subtopology is created for each assembly entity to represent its attributes and relationships. For example, index analysis is performed on the modified attribute information for a gear, a shaft, and a housing to obtain their respective index subtopologies.

[0080] Step S620: Fusing the multiple index sub-topologies to construct a CAD drawing index topology. Specifically, the index sub-topologies of all assembly entities are fused into a unified CAD drawing index topology, constructing an index topology that includes all assembly entity attributes and relationships. For example, the index sub-topologies of the gear, shaft, and housing are fused to construct a CAD drawing index topology.

[0081] Step S630: Store the multiple annotated CAD drawings in the CAD drawing index topology, completing the functional index annotation of the CAD atlas. Specifically, the annotated CAD drawings are stored in association with the index topology, allowing the drawings to be retrieved and managed using the index topology. For example, the annotated CAD drawings of gears, shafts, and housings are stored in the index topology to complete the functional index annotation.

[0082] This implementation adopts a structured index topology, which makes the management of drawings more orderly, easier to maintain and update, and enhances the manageability and searchability of drawings, thereby improving the retrieval and management efficiency of drawings.

[0083] The embodiment of the present application adopts the method of first calling the native interface of the CAD software to traverse the atlas and extract the annotation objects, obtaining the original information of the annotation attributes of multiple original drawings, and then interactively obtaining the assembly relationship characteristics of the assembly entity, and performing conflict correction on the original information of the annotation attributes based on this characteristic to obtain the corrected attribute information, and then loading the predefined rule library, performing non-standard symbol matching conversion on the corrected attribute information to obtain symbolic attribute information, and then annotating the symbolic attribute information to the original drawing in a structured incremental manner to obtain the annotated CAD drawing, and finally performing index analysis on the corrected attribute information, constructing functional index annotation and other technical means, which solves the technical problem of the lack of comprehensive consideration of assembly logical relationships in existing CAD drawing annotations, resulting in insufficient annotation conflict discovery and correction capabilities, and achieves the technical effect of accurately identifying and efficiently correcting CAD drawing annotation conflicts, and improving the accuracy and reliability of CAD drawing annotations.

[0084] In the above, refer to Figure 1 The intelligent annotation method for CAD drawing according to the embodiment of the present invention is described in detail. Figure 2 An intelligent annotation plug-in for CAD drawing according to an embodiment of the present invention is described.

[0085] The intelligent annotation plug-in for CAD drawing according to an embodiment of the present invention is used to address the technical problem of existing CAD drawing annotations, which lacks comprehensive consideration of assembly logical relationships, resulting in insufficient ability to detect and correct annotation conflicts. The plug-in achieves the technical effect of accurately identifying and efficiently correcting CAD drawing annotation conflicts, thereby improving the accuracy and reliability of CAD drawing annotations. The intelligent annotation plug-in for CAD drawing includes: an annotation object extraction module 10, an assembly relationship feature acquisition module 20, a conflict correction module 30, a non-standard symbol matching and conversion module 40, an annotation module 50, and an index analysis module 60.

[0086] The annotation object extraction module 10 is used to call the native interface of the CAD software to traverse the CAD drawing set to extract the annotation objects, and obtain multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities; the assembly relationship feature acquisition module 20 is used to interactively obtain multiple assembly relationship features of the multiple assembly entities; the conflict correction module 30 is used to perform conflict correction on the multiple annotation attribute original information according to the multiple assembly relationship features, and obtain multiple corrected attribute information; the non-standard symbol matching conversion module 40 is used to load the predefined symbol annotation rule library, perform non-standard symbol matching conversion on the multiple corrected attribute information, and obtain multiple symbolized attribute information; the annotation module 50 is used to structurally incrementally annotate the multiple symbolized attribute information on the multiple original CAD drawings, and obtain multiple annotated CAD drawings; the index analysis module 60 is used to construct functional index annotations of the multiple annotated CAD drawings by performing index analysis on the multiple corrected attribute information.

[0087] The specific configuration of the conflict correction module 30 will be described in detail below. As described above, based on the multiple assembly relationship features, the multiple annotation attribute original information is conflict-corrected to obtain multiple corrected attribute information. The conflict correction module 30 may further include: a missing annotation restoration unit for restoring the missing annotations of the multiple annotation attribute original information based on the multiple assembly relationship features through adjacent entity annotation deduction to obtain multiple restored attribute information; a geometric tolerance verification unit for performing cross-drawing geometric tolerance verification on the multiple restored attribute information based on the multiple assembly relationship features to obtain a cross-drawing conflict set; and a directional conflict correction unit for performing directional conflict correction on the multiple restored attribute information based on the cross-drawing conflict set to obtain the multiple corrected attribute information.

[0088] wherein, according to the multiple assembly relationship features, the multiple restored attribute information are subjected to cross-drawing geometric tolerance verification to obtain a cross-drawing conflict set, and before that, the conflict correction module 30 may further include: a network retrieval unit for network retrieval of multiple single-drawing conflict rules according to the entity types of the multiple assembly entities; an internal self-consistent verification unit for traversing the first restored attribute information based on the first single-drawing conflict rule to perform internal self-consistent verification of the single drawing to obtain a first single-drawing conflict defect set; a correction information library calling unit for retrieving and calling the first correction information library based on the first single-drawing conflict defect set; a traversal unit for traversing the first correction information library using the first single-drawing conflict defect set to extract a first single-drawing conflict correction set; a local attribute replacement unit for performing local attribute replacement on the first restored attribute information using the first single-drawing conflict correction set to obtain first single-drawing attribute information; an iteration unit for, by analogy, performing single-drawing conflict correction on the multiple restored attribute information according to the multiple single-drawing conflict rules to obtain multiple single-drawing attribute information; and a geometric tolerance verification unit for performing cross-drawing geometric tolerance verification on the multiple single-drawing attribute information according to the multiple assembly relationship features.

[0089] Among them, the first correction information library is retrieved and called according to the first single drawing conflict defect set, and the correction information library calling unit may further include: an entity structure feature extraction subunit for extracting the first entity structure feature from the first original CAD drawing; a screening subunit for screening the first single drawing conflict defect set from the first restored attribute information to obtain the first compliance attribute information; and a local matching calling subunit for locally matching and calling the first correction information library using the first compliance attribute information and the first entity structure feature as retrieval conditions.

[0090] Wherein, according to the multiple assembly relationship features, the multiple restoration attribute information are subjected to cross-drawing geometric tolerance verification to obtain a cross-drawing conflict set, and the geometric tolerance verification unit may further include: a global assembly tree construction subunit for constructing a global assembly tree of the target assembly structure according to the multiple assembly relationship features, wherein the global assembly tree is P layers; a component-level layer-by-layer decomposition subunit for performing component-level layer-by-layer decomposition on the global assembly tree starting from the P-1 layer to obtain a multi-layer component-level assembly subtree set; a hierarchical dimension chain closure verification subunit for performing hierarchical dimension chain closure verification on the multi-layer component-level assembly subtree set from the bottom up after performing fitting tolerance correction on part entities within the monomer component-level assembly subtree to locate the cross-drawing conflict set.

[0091] Among them, the hierarchical dimension chain closure verification sub-unit can further include: a sample tolerance combination acquisition component for interactively obtaining multiple groups of sample tolerance combinations of multiple sample part combinations in multiple sample matching scenarios; a matching rule library construction component for associatively storing the multiple sample part combinations, multiple sample matching scenarios and multiple groups of sample tolerance combinations to complete the construction of the matching rule library; a cross-drawing conflict set parsing component for parsing the cross-drawing conflict set and outputting O real-time matching scenarios of O real-time part combinations; a two-dimensional matching component for using the O real-time part combinations and O real-time matching scenarios as two-dimensional matching conditions, traversing the matching rule library, and obtaining O sample tolerance combinations; a tolerance correction component for using the cross-drawing conflict set as a correction guide and using the O sample tolerance combinations to perform tolerance correction on the multi-layer component-level assembly subtree set.

[0092] Among them, according to the cross-drawing conflict set, the multiple restored attribute information are subjected to directional conflict correction to obtain the multiple corrected attribute information. The directional conflict correction unit may further include: a conflict priority rule calling subunit for calling the conflict priority rule; an aggregation subunit for aggregating the cross-drawing conflict set according to the conflict priority rule to obtain a multi-level priority conflict set; a closed-loop feedback verification subunit for correcting the multi-level priority conflict set according to the multi-level conflict correction strategy mapping, and then performing closed-loop feedback verification until the update result of the cross-drawing conflict set is an empty set, and outputting a conflict correction information set; a local attribute replacement subunit for performing local attribute replacement on the multiple restored attribute information using the conflict correction information set based on the cross-drawing conflict set to obtain the multiple corrected attribute information.

[0093] The specific configuration of the index analysis module 60 will be described in detail below. As described above, by performing index analysis on the multiple corrected attribute information to construct functional index annotations for the multiple annotated CAD drawings, the index analysis module 60 may further include: a multimodal index analysis unit for performing multimodal index analysis on the multiple corrected attribute information to obtain multiple index sub-topologies of the multiple assembly entities; a CAD drawing index topology construction unit for fusing the multiple index sub-topologies to construct a CAD drawing index topology; and a storage unit for storing the multiple annotated CAD drawings in the CAD drawing index topology to complete the functional index annotation of the CAD atlas.

[0094] The plug-in may further include: a fuzzy correction module for performing fuzzy correction on the multiple correction attribute information, and then using the symbol annotation rule library to perform non-standard symbol matching conversion on the multiple correction attribute information to obtain the multiple symbolized attribute information.

[0095] The intelligent annotation plug-in for CAD drawing provided by the embodiment of the present invention can execute the intelligent annotation method for CAD drawing provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0096] Although this application makes various references to certain modules in the plug-in according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0097] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An intelligent annotation method for CAD drawing, characterized in that: The method comprises: Calling a native interface of the CAD software to traverse the CAD drawing set to extract annotation objects, and obtaining multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities; interactively obtaining a plurality of assembly relationship features of the plurality of assembly entities; performing conflict correction on the plurality of original annotation attribute information according to the plurality of assembly relationship features to obtain a plurality of corrected attribute information; Loading a predefined symbol annotation rule library, performing non-standard symbol matching conversion on the plurality of modified attribute information to obtain a plurality of symbolized attribute information; Incrementally marking the plurality of symbolic attribute information on the plurality of original CAD drawings to obtain a plurality of marked CAD drawings; By performing index analysis on the multiple correction attribute information, functional index annotations of the multiple annotated CAD drawings are constructed.

2. The intelligent annotation method for CAD drawing according to claim 1, wherein: According to the plurality of assembly relationship features, conflict correction is performed on the plurality of original annotation attribute information to obtain a plurality of corrected attribute information, the method comprising: Based on the multiple assembly relationship features, the multiple original information of the annotation attributes is restored by deducing the adjacent entity annotations to obtain multiple restored attribute information; performing cross-drawing geometric tolerance verification on the multiple restoration attribute information according to the multiple assembly relationship features to obtain a cross-drawing conflict set; According to the cross-drawing conflict set, directional conflict correction is performed on the plurality of restored attribute information to obtain the plurality of corrected attribute information.

3. The intelligent annotation method for CAD drawing according to claim 2, wherein: According to the multiple assembly relationship features, the multiple restoration attribute information is subjected to cross-drawing geometric tolerance verification to obtain a cross-drawing conflict set. Previously, the method includes: Retrieving a plurality of single drawing conflict rules based on entity types of the plurality of assembly entities through a network; Based on the first single drawing conflict rule, the first restored attribute information is traversed to perform internal self-consistent verification of the single drawing, thereby obtaining a first single drawing conflict defect set; Retrieving and calling a first correction information library according to the first single drawing conflict defect set; Using the first single drawing conflict defect set to traverse the first correction information library, extracting the first single drawing conflict correction set; Using the first single drawing conflict correction set to perform partial attribute replacement on the first restored attribute information to obtain first single drawing attribute information; Similarly, single drawing conflict correction is performed on the multiple restored attribute information according to the multiple single drawing conflict rules to obtain multiple single drawing attribute information; According to the multiple assembly relationship features, the multiple single-drawing attribute information is subjected to cross-drawing geometric tolerance verification.

4. The intelligent annotation method for CAD drawing according to claim 3, wherein: Retrieving and calling a first correction information library according to the first single drawing conflict defect set, the method includes: extracting a first entity structure feature from a first original CAD drawing; Filtering the first single drawing conflict defect set from the first restoration attribute information to obtain first compliance attribute information; The first compliance attribute information and the first entity structure feature are used as search conditions, and the first correction information library is called through local matching.

5. The intelligent annotation method for CAD drawing according to claim 2, wherein: According to the multiple assembly relationship features, the multiple restoration attribute information is subjected to cross-drawing geometric tolerance verification to obtain a cross-drawing conflict set, the method comprising: Constructing a global assembly tree of the target assembly structure according to the multiple assembly relationship features, wherein the global assembly tree is a P layer; Starting from the P-1th layer, the global assembly tree is decomposed layer by layer at the component level to obtain a multi-layer component-level assembly subtree set; After the fitting tolerance of the part entities in the monomeric component-level assembly subtree of the multi-layer component-level assembly subtree set is corrected, the hierarchical dimension chain closure verification from the bottom up is performed on the multi-layer component-level assembly subtree set to locate the cross-drawing conflict set.

6. The intelligent annotation method for CAD drawing according to claim 5, characterized in that: The method further comprises: Interactively obtain multiple sets of sample tolerance combinations for multiple sample part combinations in multiple sample matching scenarios; Associatively storing the plurality of sample part combinations, the plurality of sample matching scenarios, and the plurality of sample tolerance combinations, to complete the construction of a matching rule library; Analyze the cross-drawing conflict set and output O real-time coordination scenarios of O real-time part combinations; Taking the O real-time part combinations and O real-time matching scenarios as two-dimensional matching conditions, traversing the matching rule library to obtain O sample tolerance combinations; Taking the cross-drawing conflict set as a correction guide, the O sample tolerance combinations are used to perform tolerance correction on the multi-layer component-level assembly subtree set.

7. The intelligent annotation method for CAD drawing according to claim 2, wherein: According to the cross-drawing conflict set, directional conflict correction is performed on the plurality of restored attribute information to obtain the plurality of corrected attribute information. The method further includes: Invoke conflicting priority rules; Aggregating the cross-drawing conflict set according to the conflict priority rule to obtain a multi-level priority conflict set; After correcting the multi-level priority conflict set according to the multi-level conflict correction strategy mapping, closed-loop feedback verification is performed until the update result of the cross-drawing conflict set is an empty set, and a conflict correction information set is output; According to the cross-drawing conflict set, the conflict correction information set is used to perform local attribute replacement on the plurality of restored attribute information to obtain the plurality of corrected attribute information.

8. The intelligent annotation method for CAD drawing according to claim 1, wherein: By performing index analysis on the plurality of modified attribute information, functional index annotations of the plurality of annotated CAD drawings are constructed, the method further comprising: Performing multimodal index analysis on the plurality of modified attribute information to obtain a plurality of index sub-topologies of the plurality of assembly entities; Merging the multiple index sub-topologies to construct a CAD drawing index topology; The multiple annotated CAD drawings are stored in the CAD drawing index topology to complete the functional index annotation of the CAD atlas.

9. The intelligent annotation method for CAD drawing according to claim 1, wherein: The method further comprises: After fuzzy correction is performed on the multiple corrected attribute information, the symbol annotation rule library is used to perform non-standard symbol matching conversion on the multiple corrected attribute information to obtain the multiple symbolized attribute information.

10. Intelligent annotation plug-in for CAD drawing, characterized by: The plug-in is used to implement the intelligent annotation method for CAD drawing according to any one of claims 1 to 9, and the plug-in includes: Annotation object extraction module, configured to call a native interface of CAD software to traverse the CAD drawing set to extract annotation objects, thereby obtaining multiple annotation attribute original information of multiple original CAD drawings, wherein the multiple original CAD drawings correspond to multiple assembly entities; An assembly relationship feature acquisition module, configured to interactively acquire a plurality of assembly relationship features of the plurality of assembly entities; a conflict correction module, configured to perform conflict correction on the plurality of original annotation attribute information according to the plurality of assembly relationship features to obtain a plurality of corrected attribute information; a non-standard symbol matching conversion module, configured to load a predefined symbol annotation rule library, perform non-standard symbol matching conversion on the plurality of modified attribute information, and obtain a plurality of symbolized attribute information; An annotation module, configured to annotate the plurality of symbolic attribute information in a structured incremental manner on the plurality of original CAD drawings to obtain a plurality of annotated CAD drawings; The index analysis module is used to construct functional index annotations of the multiple annotated CAD drawings by performing index analysis on the multiple modified attribute information.

Images