Intelligent modeling and parameter complementing method, system and equipment for ship CAD (Computer Aided Design) structural component

Abstract

The invention relates to the technical field of CAD modeling, in particular to a ship CAD structural member intelligent modeling and parameter completion method, system and equipment, and the method comprises the steps: obtaining user voice information, and converting the voice information into text information; matching the user text information with ship structural member parameterized modeling instruction set knowledge base information to obtain instruction information expressed in the user voice text information, and outputting a required parameter list and parameter meanings corresponding to the instruction information in the knowledge base according to the matched instruction information; performing parameter extraction on the text information of the user according to the output required parameter list and parameter meaning, outputting a parameter list, integrating an instruction matching result and a parameter extraction result, combining to generate a complete parameterized modeling instruction, and outputting the parameterized modeling instruction in a standardized JSON (JavaScript Object Notation) format; and inputting the parameterized modeling instruction generated by combination into the rear end of CAD software, analyzing the parameterized modeling instruction, executing a corresponding parameterized modeling interface, and completing a corresponding modeling operation.

Description

Technical Field

[0001] The present invention relates to the technical field of CAD modeling, and particularly to a method, system, and device for intelligent modeling and parameter completion of ship CAD structural components. Background Art

[0002] In the work of ship structure design, when designers perform modeling of ship structural components, they usually need to manually select function options in CAD software and gradually fill in parameters to complete the modeling task. Although this traditional operation mode is powerful, it relies on manual clicking and input by designers and involves a large amount of repetitive and precise work, which is time-consuming and laborious.

[0003] With the rapid development of speech recognition technology and large language model technology, introducing voice interaction into the CAD modeling process and using voice commands to replace manual operations have become a new design requirement. However, the introduction of voice modeling also brings new challenges: compared with the precise clicking operations in CAD software or the clear parameters input by the keyboard, the commands input by users through voice tend to be more ambiguous and abbreviated. For example, a designer may say "cover the just-built pipe with brackets", but does not clearly specify parameters such as the information of the built pipe, the type and quantity of the brackets to be built, etc. This ambiguity makes it difficult to directly convert voice commands into executable modeling operations through traditional parametric modeling and other methods.

[0004] Based on the above, ship designers have put forward higher requirements for efficient and intelligent voice modeling technology: a method that can not only make full use of voice commands to improve modeling efficiency, but also intelligently understand the user's intention and make up for the deficiencies such as the ambiguity of voice commands and the lack of context information, so as to ensure modeling accuracy and completion while improving work efficiency. Therefore, it involves a method, system, and device for intelligent modeling and parameter completion of ship CAD structural components based on voice input. Summary of the Invention

[0005] (1) Object of the Invention

[0006] To solve the technical problems in the background art, the present invention proposes a method for intelligent modeling and parameter completion of ship CAD structural components. By inputting the user's voice commands and performing speech-to-text recognition, a large language model agent is used to infer the user's intention, that is, the parametric modeling function and corresponding parameters of the ship structural components that the user hopes to use and execute, so as to improve the modeling efficiency of ship CAD structural components and simplify the work process of designers.

[0007] (2) Technical Solution

[0008] To solve the above problems, the first aspect of the present invention provides a method for intelligent modeling and parameter completion of ship CAD structural components, including:

[0009] Step S100: Obtain the user's voice information and convert the voice information into text information;

[0010] Step S200: Conduct intent analysis on the text information, match the user's text information with the information in the knowledge base of parametric modeling instructions for ship structural components to obtain the instruction information expressed in the user's voice text information, and save the instruction matching result;

[0011] Step S300: According to the matched instruction information, output the required parameter list and parameter meaning corresponding to the instruction information in the knowledge base;

[0012] Step S400: Extract parameters from the user's text information according to the output required parameter list and parameter meaning, then output the parameter list, and save the parameter extraction result;

[0013] Step S500: Integrate the instruction matching result and the parameter extraction result, combine to generate a complete parametric modeling instruction, and output it in the standardized JSON format;

[0014] Step S600: Input the parametric modeling instruction generated by combination into the CAD software backend and parse it, execute the corresponding parametric modeling interface, and complete the corresponding modeling operation.

[0015] As a technical solution of the present invention, it further includes a large language model workflow for processing the text information. The workflow is at least composed of three collaborative large model agents, denoted as M1, M2, and M3 respectively. The M1, M2, and M3 are respectively driven by different prompt words and knowledge bases;

[0016] M1 is used to execute Steps S200 - S300;

[0017] M2 is used to execute Step S400;

[0018] M3 is used to execute Step S500; where:

[0019] M1 parses the text information to obtain the user's intent, conducts a similarity match of the user's intent in the knowledge base of parametric modeling instructions for ship structural components, and screens out the CAD modeling instruction that is most similar to the user's intent parsed from the text information, as well as the parameter list and parameter meaning required to execute the instruction;

[0020] M2 reads the parameter list and parameter meaning required for the instruction and outputs the parameter list;

[0021] M3 integrates the output results of M1 and M2 to form a complete parametric modeling instruction for ship structural components.

[0022] As a technical solution of the present invention, in the step S400, parameter extraction is performed on the text information provided by the user, specifically including:

[0023] Extract explicit parameters, and directly obtain the parameters clearly input in the text information converted by the user through voice conversion;

[0024] Infer implicit parameters, and infer according to the current modeling environment knowledge and historical modeling records to supplement the missing parameters.

[0025] As a technical solution of the present invention, in the step S500, the integration process includes parameter verification and logical verification to determine whether the parametric modeling instruction is complete, so that the parametric modeling instruction can be executed in the CAD environment. If the parametric modeling instruction is incomplete, the user is prompted to re-enter. If the parametric modeling instruction is complete, the parametric modeling instruction is output in a standardized JSON format.

[0026] As a technical solution of the present invention, the knowledge base at least includes operations for adjusting the viewing angle, selection operations, undo operations, and parametric ship structural members, plate models, rib models, hole models, beam models, grillage models, and includes a list of names, descriptions, usage scenarios, required parameter lists, and parameter meanings of the corresponding parametric instructions.

[0027] As a technical solution of the present invention, the current modeling environment knowledge and historical modeling records specifically include the user's voice text input and instruction output in the previous n rounds, the model file currently being operated by the user, and the model currently selected by the user.

[0028] As a technical solution of the present invention, in the acquisition of the user's intention, it also includes analyzing the user's voice text input in the previous n rounds and judging the user's intention in combination with the user's current voice text information.

[0029] A second aspect of the present invention proposes a ship CAD structural member intelligent modeling and parameter complementing system, including:

[0030] An acquisition unit for acquiring user voice information and converting the voice information into text information;

[0031] A matching unit for performing intention analysis on the text information, matching the user text information with the knowledge base information of the ship structural member parametric modeling instruction set to obtain the instruction information expressed in the user voice text information, and saving the instruction matching result;

[0032] A first output unit for outputting the required parameter list and parameter meaning corresponding to the instruction information in the knowledge base according to the matched instruction information;

[0033] A second output unit, configured to extract parameters from the user's text information according to the output required parameter list and parameter meanings, and then output a parameter list, and save the parameter extraction result;

[0034] An integration unit, which integrates the instruction matching result and the parameter extraction result, combines and generates a complete parametric modeling instruction, and outputs it in a standardized JSON format;

[0035] An execution unit, which inputs the combined parametric modeling instruction into the CAD software backend for parsing, executes the corresponding parametric modeling interface, and completes the corresponding modeling operation.

[0036] A third aspect of the present invention provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus; wherein, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0037] The memory is used to store a computer program;

[0038] The processor, when executing the program stored in the memory, implements the steps in the above-mentioned intelligent modeling and parameter completion method for ship CAD structural parts.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps in the above-mentioned intelligent modeling and parameter completion method for ship CAD structural parts.

[0040] The above technical solutions of the present invention have the following beneficial technical effects:

[0041] The voice-driven modeling method can greatly reduce the manual operations of ship designer users and achieve efficient interaction;

[0042] Using large language models and agents to analyze the intent and infer parameters of user instructions can automatically complete modeling requirements and achieve intelligent modeling;

[0043] The parametric modeling instruction library for ship structural parts can be extended through new parametric models and added to the system to adapt to different ship modeling requirements and achieve extensibility of the instruction set. Description of the Drawings

[0044] Figure 1 It is a flowchart of the method of the present invention;

[0045] Figure 2 It is a flowchart of the implementation of the present invention. Detailed Embodiments

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present invention.

[0047] Reference Figure 1-2 , to solve the above problems, the present application adopts the following technical solutions:

[0048] The intelligent modeling and parameter completion method for ship CAD structural components proposed in the first aspect of the present invention includes:

[0049] (1) Voice input and processing:

[0050] Step S100, obtain the user's voice information and convert the voice information into text information;

[0051] Step S200, perform intent analysis on the text information, match the user's text information with the knowledge base information of the parametric modeling instruction set for ship structural components, so as to obtain the instruction information expressed in the user's voice text information, and save the instruction matching result;

[0052] Specifically, the user inputs a voice command through a sound collection device (microphone), uses a speech-to-text model (Speech2Text) to convert the voice command into a text command, and then transmits the text command into the large language model workflow. The workflow contains three large model agents that work together and have different divisions of labor: M1, M2, and M3, which are driven by different prompt words and knowledge bases respectively.

[0053] Among them, M1 is responsible for outputting the instruction name after parsing the text command and has a knowledge base of the parametric modeling instruction set for ship structural components. The knowledge base covers common operations and common parametric instructions in ship modeling, including general perspective adjustment operations, selection operations, undo operations, and common parametric ship structural components such as plate models, rib models, hole models, beam models, and grillage models, and includes the name list, description, usage scenarios, required parameter list, parameter meaning, and other related knowledge of the above parametric instructions. M2 is responsible for outputting the parameter list after parameter extraction and collection and has the current modeling environment knowledge and historical modeling records, including: the user's voice text input and instruction output in the previous n rounds, the model file that the user is currently operating on, and the model currently selected by the user. M3 also has a knowledge base of the parametric modeling instruction set for ship structural components and is responsible for judging whether the instruction can be completely organized by organizing the instruction name output by M1 and the parameter list output by M2, and outputting the instruction that can be read and executed by the modeling interface of the CAD software in JSON format.

[0054] That is, M1 parses the text information to obtain the user's intention, performs a similarity matching of the user's intention in the knowledge base of the parametric modeling instruction set for ship structural components, and screens out the CAD modeling instruction that is most similar to the user's intention parsed from the text information, as well as the parameter list and parameter meaning required to execute the instruction; M2 reads the parameter list and parameter meaning required for the instruction and outputs the parameter list; M3 integrates the output results of M1 and M2 to form a complete parametric modeling instruction for ship structural components.

[0055] (2) Intention analysis and instruction retrieval

[0056] Step S300: According to the matched instruction information, output the parameter list and parameter meaning required for the corresponding instruction information in the knowledge base.

[0057] (3) Parameter extraction and reasoning

[0058] Step S400: After parameter extraction from the user's text information according to the output parameter list and parameter meaning, output the parameter list and save the parameter extraction result.

[0059] (4) Parameter instruction organization and generation

[0060] Step S500: Integrate the instruction matching result and the parameter extraction result, combine them to generate a complete parametric modeling instruction, and output it in the standardized JSON format.

[0061] Specifically, referring to Figure 2 , the integration process includes parameter verification and logical verification to determine whether the parametric modeling instruction is complete, so that the parametric modeling instruction can be executed in the CAD environment. If the parametric modeling instruction is incomplete, prompt the user to re-enter. If the parametric modeling instruction is complete, output the parametric modeling instruction in the standardized JSON format.

[0062] (5) Instruction execution

[0063] Step S600: Input the parametric modeling instruction generated by combination into the CAD software backend and parse it, execute the corresponding parametric modeling interface, and complete the corresponding modeling operation.

[0064] In the above embodiment, the knowledge base includes at least operations for adjusting the viewing angle, selection operation, undo operation, and parametric ship structural components, plate model, rib model, hole model, beam model, grillage model, and includes a name list, description, usage scenario, required parameter list, and parameter meaning of the corresponding parametric instructions.

[0065] In the above embodiments, in the acquisition of the user intention, it further includes analyzing the user's voice text inputs in the previous n rounds, and combining the user's current voice text information to determine the user intention.

[0066] For example, when the user modeled a tube with a diameter of 4 cm and a thickness of 1 cm in the fourth round, and the voice information input by the user in the third round was "put a protective sleeve on the tube", then the inner diameter of the sleeve automatically modeled by the above solution should be automatically adapted to the above 4 cm. This is only for illustration and does not limit the present application in any way.

[0067] A ship CAD structural member intelligent modeling and parameter complementing system proposed in the second aspect of the present invention includes: an acquisition unit for acquiring user voice information and converting the voice information into text information; a matching unit for performing intention analysis on the text information, matching the user text information with the information in the ship structural member parametric modeling instruction set knowledge base to obtain the instruction information expressed in the user voice text information, and saving the instruction matching result; a first output unit for outputting the required parameter list and parameter meaning corresponding to the instruction information in the knowledge base according to the matched instruction information; a second output unit for extracting parameters from the user's text information according to the output required parameter list and parameter meaning and then outputting the parameter list, and saving the parameter extraction result; an integration unit for integrating the instruction matching result and the parameter extraction result, combining to generate a complete parametric modeling instruction, and outputting it in a standardized JSON format; an execution unit for inputting the combined parametric modeling instruction into the CAD software backend and parsing it, executing the corresponding parametric modeling interface, and completing the corresponding modeling operation.

[0068] An electronic device proposed in the third aspect of the present invention includes: a processor, a communication interface, a memory, and a communication bus; wherein, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0069] The memory is used for storing a computer program;

[0070] The processor is used for implementing the steps in the above ship CAD structural member intelligent modeling and parameter complementing method when executing the program stored on the memory.

[0071] A computer-readable storage medium proposed in the fourth aspect of the present invention has a computer program stored thereon, and when the program is executed by a processor, it implements the steps in the above ship CAD structural member intelligent modeling and parameter complementing method.

[0072] The execution entity of the intelligent modeling and parameter completion method for ship CAD structural parts can be a computer or other devices capable of implementing the charging and swapping scheduling based on the prediction of the composite energy storage power. For example, the method can be executed by a terminal device, a server, or other processing devices. Among them, the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the intelligent modeling and parameter completion method for ship CAD structural parts can be implemented by a processor invoking computer-readable instructions stored in a memory.

[0073] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and all these changes and improvements fall within the scope of the present invention claimed.

Claims

1. Intelligent modeling and parameter completion method for ship CAD structural parts, characterized in that: include: Step S100, obtaining user voice information and converting the voice information into text information; Step S200, performing intent analysis on the text information, matching the user text information with the ship structure parameter modeling instruction set knowledge base information to obtain the instruction information expressed in the user voice text information, and saving the instruction matching result; Step S300, outputting a required parameter list and parameter meanings corresponding to the instruction information in the knowledge base according to the matched instruction information; Step S400, extracting parameters from the user's text information according to the output required parameter list and parameter meanings, outputting a parameter list, and saving the parameter extraction result; Step S500, integrating the instruction matching result and the parameter extraction result, combining and generating a complete parameterized modeling instruction, and outputting it in a standardized JSON format; Step S600, input the combined generated parametric modeling instructions into the CAD software backend and parse them, execute the corresponding parametric modeling interface, and complete the corresponding modeling operation.

2. The method for intelligent modeling and parameter completion of ship CAD structural parts according to claim 1 is characterized in that: It also includes a large language model workflow for processing the text information, wherein the workflow is composed of at least three large model agents working in collaboration, respectively denoted as M1, M2, and M3, wherein M1, M2, and M3 are driven by different prompt words and knowledge bases respectively; M1 is used to execute steps S200-S300; M2 is used to execute the step S400; M3 is used to execute the step S500; wherein: The M1 parses the text information to obtain the user's intention, performs similarity matching on the user's intention in the knowledge base of the ship structure parametric modeling instruction set, and screens out the CAD modeling instruction that is most similar to the user's intention parsed from the text information, and executes the parameter list and parameter meaning required for the instruction; The M2 reads the parameter list and parameter meanings required by the instruction, and outputs the parameter list; The M3 integrates the output results of M1 and M2 to form a complete parameterized modeling instruction for ship structure parts.

3. The method for intelligent modeling and parameter completion of ship CAD structural parts according to claim 2 is characterized in that: In step S400, parameter extraction is performed on the text information provided by the user, specifically including: Extract explicit parameters, directly obtain the parameters explicitly input by the user in the text information after voice conversion; Reasoning about implicit parameters, based on the knowledge of the current modeling environment and historical modeling records, supplements the missing parameters.

4. The method for intelligent modeling and parameter completion of ship CAD structural parts according to claim 1 is characterized in that: In step S500, the integration process includes parameter verification and logic verification to determine whether the parametric modeling instructions are complete so that the parametric modeling instructions can be executed in the CAD environment. If the parametric modeling instructions are incomplete, the user is prompted to re-enter them. If the parametric modeling instructions are complete, the parametric modeling instructions are output in a standardized JSON format.

5. The method for intelligent modeling and parameter completion of ship CAD structural parts according to claim 1 is characterized in that: The knowledge base includes at least operations for adjusting viewing angles, selecting operations, undoing operations, and parameterized ship structures, plate models, rib models, hole models, beam models, and plate frame models, and includes a name list, description, usage scenario, required parameter list, and parameter meaning of corresponding parameterized instructions.

6. The method for intelligent modeling and parameter completion of ship CAD structural parts according to claim 3 is characterized in that: The current modeling environment knowledge and historical modeling records specifically include the user's previous n rounds of voice text input and command output, the model file the user is currently operating, and the model currently selected by the user.

7. The method for intelligent modeling and parameter completion of ship CAD structural parts according to claim 6 is characterized in that: The method of obtaining the user's intention also includes analyzing the user's previous n rounds of voice and text input, and determining the user's intention in combination with the user's current voice and text information.

8. Intelligent modeling and parameter completion system for ship CAD structural parts, characterized by: include: An acquisition unit, used to acquire user voice information and convert the voice information into text information; A matching unit, used to perform intention analysis on the text information, match the user text information with the ship structure component parametric modeling instruction set knowledge base information to obtain the instruction information expressed in the user voice text information, and save the instruction matching result; A first output unit, configured to output a required parameter list and parameter meanings corresponding to the instruction information in the knowledge base according to the matched instruction information; A second output unit, configured to extract parameters from the user's text information according to the output required parameter list and parameter meanings, output a parameter list, and save the parameter extraction result; An integration unit integrates the instruction matching result and the parameter extraction result, generates a complete parameterized modeling instruction, and outputs it in a standardized JSON format; The execution unit inputs the combined generated parametric modeling instructions into the CAD software backend and parses them, executes the corresponding parametric modeling interface, and completes the corresponding modeling operation.

9. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory is used to store computer programs; The processor is used to implement the steps in the ship CAD structural component intelligent modeling and parameter completion method as described in any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the method for intelligent modeling and parameter completion of ship CAD structural parts as described in any one of claims 1 to 7 are implemented.

Images