Method and device for generating parameterized model, medium and program product

Abstract

The invention provides a method and a device for generating a parameterized model, a medium and a program product. The method comprises the following steps: S1, receiving text data which is input by a user and is related to a design intention or a command; s2, preprocessing the text data through a predetermined natural language processing algorithm to obtain structured parameter information of the text data; and S3, constructing a parameterized model through predetermined modeling software according to the structured parameter information. By means of the technical scheme, the modeling efficiency can be improved, the quality and consistency of the model are guaranteed, and the maintainability of the model is further enhanced.

Description

Technical Field

[0001] The present invention relates to the field of industrial modeling, and particularly to a method, device, medium and program product for generating a parametric model. Background Art

[0002] In recent years, with the rapid development of generative artificial intelligence technology and its continuous deepening application in many fields, the limitations of traditional CAD parametric modeling methods have gradually emerged. Traditional methods mainly rely on sketch plane constraints and gradually transition from two-dimensional design to three-dimensional modeling. This method not only requires users to have professional drawing skills and strong spatial imagination ability, but also the entire modeling process is cumbersome and complex, requiring frequent switching between different modeling tools and views. The correlation relationship between parameters is also extremely complex, and it is easy to make mistakes during modification, making it difficult to quickly realize the design intention, thus greatly reducing the design efficiency. However, with the breakthrough of large language model (LLM) technology, computers can now more accurately understand and respond to users' natural language input, which provides the possibility for deeply integrating generative AI technology with traditional CAD platforms such as MicroStation. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, medium and program product for generating a parametric model to improve the modeling efficiency, ensure the quality and consistency of the model, and further enhance the maintainability of the model.

[0004] To achieve the above object, on the one hand, a method for generating a parametric model is provided, and the method includes:

[0005] S1, receiving text data related to design intention or command input by a user; the text data is used to define parameters, create specific types of geometric elements, and / or specify transformation operations;

[0006] S2, preprocessing the text data through a predetermined natural language processing algorithm to obtain structured parameter information of the text data; wherein, the preprocessing includes: word segmentation, part-of-speech tagging, information extraction, and context correlation analysis of the text data;

[0007] The structured parameter information includes: operation type, geometric type, at least one parameter included in the geometric type, the dependency relationship between each parameter, and / or the parameter value of each parameter; the operation type is an operation performed on the geometric type or the at least one parameter, including: creation, modification, and transformation;

[0008] S3, constructing a parametric model according to the structured parameter information through a predetermined modeling software, including:

[0009] S31. Obtain the primitive corresponding to the geometric type according to the parametric primitive library of the MicroStation platform, and construct a parameter dependency graph based on the dependency relationship between each parameter.

[0010] S32. Construct a parametric model based on the operation type, the primitive, the parameter values of each parameter, and the parameter dependency graph.

[0011] Preferably, in the method for generating a parametric model, in step S2, the text data is preprocessed by a predetermined natural language processing algorithm to obtain the structured parameter information of the text data, and it further includes:

[0012] The text data extracts the information required for design through the natural language processing algorithm, and the information required for design is processed through a preset parameter type, a preset parameter expression rule, and a preset operation function library to obtain at least one parameter included in the geometric type in the structured parameter information and the dependency relationship between each parameter. Among them, the parameter type includes: basic type, engineering parameter, and standard part parameter; the parameter expression includes: arithmetic operation, comparison operation, logical operation, and conditional expression operation; the operation function library includes: mathematical function, string processing, engineering calculation, and data query.

[0013] The parameter information conforms to a predetermined syntax rule and geometric constraint condition; and / or

[0014] When a predetermined default parameter is missing in the parameter information, fill in the default parameter and the parameter value of the default parameter according to a preset filling rule.

[0015] Preferably, in the method for generating a parametric model, the parameter type further includes: text, boolean value, color, and material; among them,

[0016] The basic type includes: decimal, integer, and angle;

[0017] The engineering parameter includes: length, area, volume, and weight;

[0018] The standard part parameter includes: steel channel specification, angle steel specification, I-beam specification, H-beam specification, and bolt specification;

[0019] The mathematical function includes: basic operation, trigonometric function, and rounding function;

[0020] The string processing includes: string concatenation, string splitting, extracting numerical values from a string, and formatting a string;

[0021] The engineering calculation includes: unit conversion, area calculation, volume calculation, and weight calculation.

[0022] Preferably, for the method of generating a parametric model, in step S32, constructing a parametric model based on the operation type, the graphic element, the parameter value of each parameter, and the parameter dependency graph includes:

[0023] S321, constructing at least one geometric entity based on the graphic element, the parameter value of each parameter, and the parameter dependency graph; wherein, the constraint relationship between the geometric entities conforms to a predetermined design rule, and the constraint relationship includes: the relative position and dimensional relationship between the geometric entities;

[0024] S322, performing corresponding operations on each geometric entity according to the operation type and a predetermined three-dimensional transformation rule, and performing feature editing on each geometric entity to obtain a parametric model; the feature editing includes: adding chamfers, adding fillets, or performing a Boolean operation on the relationship between the geometric entities.

[0025] Preferably, for the method of generating a parametric model, in performing corresponding operations on each geometric entity according to the operation type and a predetermined three-dimensional transformation rule, the three-dimensional transformation rule includes: basic transformation, composite transformation, and advanced transformation, wherein, the basic transformation includes: translation transformation, rotation transformation, and scaling transformation; the composite transformation includes: mirror operation and array replication; the advanced transformation includes: deformation operation and alignment operation.

[0026] Preferably, for the method of generating a parametric model, after generating the parametric model in step S32, it further includes:

[0027] When the user modifies the parametric model through text input, modifying the parametric model according to the parameter information extracted from the text input and the parameter dependency graph established in step S32.

[0028] On the other hand, another embodiment of the present invention provides an apparatus for generating a parametric model, which includes a memory and a processor, the memory stores at least one segment of program, and the at least one segment of program is executed by the processor to implement the method of generating a parametric model as described in any one of the above.

[0029] In yet another aspect, another embodiment of the present invention provides a computer-readable storage medium, wherein at least one segment of program is stored in the storage medium, and the at least one segment of program is executed by the processor to implement the method of generating a parametric model as described in any one of the above.

[0030] In yet another aspect, another embodiment of the present invention provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method of generating a parametric model as described in any one of the above.

[0031] The above technical solution has the following technical effects:

[0032] In the embodiments of the present invention, by intelligently parsing the text data input by the user, the text data described in natural language is converted into structured parameter information; and based on the parametric basic primitive library of the MicroStation platform, a parameter dependency graph is constructed using the structured parameter information, and an accurate parametric model is generated accordingly. This not only realizes the rapid conversion from the design concept to the 3D model, but also greatly improves the modeling efficiency, reduces the usage threshold, and provides an intelligent, flexible and efficient digital transformation solution for the engineering design field. Brief Description of the Drawings

[0033] Figure 1 It is a schematic flowchart of a method for generating a parametric model according to an embodiment of the present invention;

[0034] Figure 2 It is a schematic structural diagram of a device for generating a parametric model according to an embodiment of the present invention. Detailed Embodiments

[0035] To further illustrate the embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used to explain the operating principle of the embodiments in conjunction with the relevant descriptions in the specification. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are usually used to represent similar components.

[0036] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0037] Embodiment 1:

[0038] Traditional parametric modeling relies on sketch plane constraints, and there are multiple limitations in the process of transitioning from 2D design to 3D modeling. For example: users need to have professional drawing skills and strong spatial imagination, the modeling process is cumbersome and requires frequent switching between tools and views, complex parameter association relationships are prone to errors during modification, and it is difficult to quickly realize the design intention, thus reducing the design efficiency. Therefore, in order to improve the modeling efficiency, reduce the user learning threshold, and ensure the quality and consistency of the model, the embodiments of the present invention provide a method for generating a parametric model. Figure 1 It is a schematic flowchart of a method for generating a parametric model according to an embodiment of the present invention. As Figure 1 shown, the method includes:

[0039] S1, receiving text data related to the design intention or command input by the user; the text data is used to define parameters, create specific types of primitives, and / or specify transformation operations;

[0040] S2. Preprocess the text data through a predetermined natural language processing algorithm to obtain the structured parameter information of the text data; wherein, the preprocessing includes: tokenizing the text data, part-of-speech tagging, information extraction, and context correlation analysis;

[0041] The structured parameter information includes: operation type, geometric type, at least one parameter included in the geometric type, the dependency relationship between each parameter, and / or the parameter value of each parameter; the operation type is an operation performed on the geometric type or at least one parameter, including: creation, modification, and transformation;

[0042] S3. Construct a parametric model according to the structured parameter information through a predetermined modeling software, including:

[0043] S31. Obtain the primitive corresponding to the geometric type according to the parametric primitive library of the MicroStation platform, and construct a parameter dependency graph according to the dependency relationship between each parameter;

[0044] S32. Construct a parametric model according to the operation type, primitive, the parameter value of each parameter, and the parameter dependency graph.

[0045] Embodiment 2:

[0046] Another embodiment of the present invention provides a method for generating a parametric model, and the method includes:

[0047] 1. Receive text data input by the user related to the design intention or command; the text data is used to define parameters, create specific types of primitives, and / or specify transformation operations;

[0048] In a specific embodiment, the user inputs commands such as parameter definition, standard part creation, basic primitive, transformation operation, attribute modification, and Boolean operation through natural language;

[0049] Preferably, the parameter definition is, for example: "Define parameter A as 100"; the standard part creation is, for example: "Create channel steel specification B, default is C10"; the basic primitive is, for example: "Create a cylinder, the diameter is D, and the height is H"; the transformation operation is, for example: "Move the cylinder, move B + 100 in the x direction"; the attribute modification is, for example: "Set the height of cylinder a to H * 0.5"; the Boolean operation is, for example: "Subtract cylinder c from cylinder d to generate a circular tube".

[0050] In a specific embodiment, when the user inputs text data, it further includes: functions such as automatically completing commands according to the context, prompting available parameters and their value ranges, automatically correcting common input errors, and providing intelligent modeling suggestions, to help the user input commands more efficiently.

[0051] 2. Preprocess the text data through a predetermined natural language processing algorithm to obtain the structured parameter information of the text data; wherein, the preprocessing includes: tokenizing the text data, part-of-speech tagging, information extraction, coreference resolution processing, and context correlation analysis;

[0052] The structured parameter information includes: operation type, geometric type, at least one parameter included in the geometric type, the dependency relationship between each parameter, and / or the parameter value of each parameter; the operation type is an operation performed on the geometric type or at least one parameter, including: creation, modification, and transformation;

[0053] In a specific embodiment, preprocessing the text data through a predetermined natural language processing algorithm to obtain the structured parameter information of the text data further includes: parsing the text data into specific interpretable commands, for example:

[0054] The interpretable commands parsed from "Define parameter L, default value is 100, define parameter W = 200, define parameter H is 300, create a rectangle, length L, width W, height H, move L / 2 in the x direction" are:

[0055] param L type=Length,value=100;

[0056] param W type=Length,value=200;

[0057] param H type=Length,value=300;

[0058] create BoxSolid box Length=L,Width=W,Height=H;

[0059] move box OffsetX=L / 2;

[0060] Define three parameters: length L, width W, and height H, all of type length, with default values of 100, 200, and 300 respectively. Then, create a cuboid named box, and then move box along the negative x-axis by a length of L / 2;

[0061] Preferably, when there are multiple interpretable commands, perform optimization processing on the interpretable commands, including: merging similar commands, parallel computing, cache utilization, and / or incremental update.

[0062] In a specific embodiment, information required for design is extracted from text data through natural language processing algorithms. The information required for design is processed through preset parameter types, preset parameter expression rules, and a preset operation function library to obtain at least one parameter included in the geometric type in the structured parameter information and the dependency relationship between each parameter. Among them, the information required for design, for example: from "Define parameter L, the default value is 100, define parameter W = 200, define parameter H as 300, create a rectangle with length L, width W, and height H, and move it L / 2 in the x direction", the information required for design extracted is: "Parameters: L, W, H", "Default values: 100, 200, 300", "Create a rectangle", "Length = L, width = W, height = H", "Move the rectangle", "X direction", and "Moving distance L / 2".

[0063] Preferably, the parameter types include: basic types, engineering parameters, and standard part parameters; the parameter expressions include: arithmetic operations, comparison operations, logical operations, and conditional expression operations; the operation function library includes: mathematical functions, string processing, engineering calculations, and data queries;

[0064] Preferably, the parameter information conforms to predetermined syntax rules and geometric constraint conditions;

[0065] Preferably, when the predetermined default parameters are missing in the parameter information, the default parameters and their parameter values are filled according to the preset completion rules.

[0066] Preferably, the parameter types also include: text, boolean, color, and material; among them, the basic types include: decimals, integers, and angles; the engineering parameters include: length, area, volume, and weight; the standard part parameters include: steel channel specifications, angle steel specifications, I-beam specifications, H-beam specifications, and bolt specifications;

[0067] Preferably, the mathematical functions include: basic operations, trigonometric functions, and rounding functions; the string processing includes: string concatenation, string splitting, extracting numerical values from strings, and formatting strings; the engineering calculations include: unit conversion, area calculation, volume calculation, and weight calculation.

[0068] 3. Construct a parametric model according to the structured parameter information through a predetermined modeling software, including:

[0069] 3.1. Obtain the primitives corresponding to the geometric type according to the parametric basic primitive library of the MicroStation platform, and construct a parameter dependency graph according to the dependency relationship between each parameter;

[0070] Preferably, the embodiments of the present invention adopt a brand-new parametric design concept, describing and controlling the shape, position, and transformation of entities entirely through parameters. This approach is similar to describing three-dimensional objects with mathematical formulas. All three-dimensional objects can be completely described by a set of parameters, and mathematical relationships, i.e., dependency relationships, can be established between the parameters. Modifying any one parameter will automatically update the shape related to that parameter, without the need for complex geometric constraints. The design intent is directly expressed mathematically. For example:

[0071]

[0072] Moreover, operations such as moving, rotating, and scaling in traditional CAD can all be described by parameters in this method. This is like setting a motion formula for an object. Adjusting the parameters can change the position and direction of the object. The moving distance can be represented by parameters, such as "move forward 100". Multiple transformations of one parameter can be combined and used. For example:

[0073]

[0074]

[0075] The association between parameters is like building a mathematical building block. Modifying any one parameter will automatically update the relevant parameters, reducing manual modification and adjustment and maintaining the design intent unchanged. For example:

[0076]

[0077] 3.2. Construct a parametric model according to the operation type, graphic elements, parameter values of each parameter, and the parameter dependency graph.

[0078] In a specific embodiment, step 3.2 includes:

[0079] 3.2.1. Construct at least one geometric entity according to the graphic elements, parameter values of each parameter, and the parameter dependency graph; wherein, the constraint relationships between geometric entities conform to predetermined design rules, and the constraint relationships include: the relative position and dimension relationships between geometric entities;

[0080] 3.2.2. Perform corresponding operations on each geometric entity according to the operation type and predetermined three-dimensional transformation rules, and perform feature editing on each geometric entity to obtain a parametric model; feature editing includes: adding chamfers, adding fillets, or performing Boolean operations on the relationships between geometric entities.

[0081] Preferably, the three-dimensional transformation rules include: basic transformation, composite transformation, and advanced transformation. Among them, the basic transformation includes: translation transformation, rotation transformation, and scaling transformation; the composite transformation includes: mirror operation and array replication; the advanced transformation includes: deformation operation and alignment operation.

[0082] In a specific embodiment, after generating the parametric model in step 3.2, the following steps are further included:

[0083] When the user modifies the parametric model through text input, the parametric model is modified according to the parameter information extracted through text input and the parameter dependency graph established in step 3.2.

[0084] Embodiment III:

[0085] The present invention further provides a device for generating a parametric model, as Figure 2 shown. The device includes a processor 201, a memory 202, a bus 203, and a computer program stored in the memory 202 and operable on the processor 201. The processor 201 includes one or more processing cores. The memory 202 is connected to the processor 201 through the bus 203. The memory 202 is used to store program instructions. When the processor 201 executes the computer program, the steps in the above method embodiment of Embodiment I of the present invention are implemented.

[0086] Furthermore, as an executable solution, the device for generating a parametric model may be a computer unit, and the computer unit may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer unit may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above composition structure of the computer unit is only an example of the computer unit and does not constitute a limitation on the computer unit. It may include more or fewer components than the above, or combine some components, or different components. For example, the computer unit may further include input / output devices, network access devices, a bus, etc., and the present invention embodiment does not make any limitation thereto.

[0087] Furthermore, as an executable solution, the so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the computer unit and connects various parts of the entire computer unit through various interfaces and lines.

[0088] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and invoking the data stored in the memory, the processor realizes various functions of the computer unit. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0089] Embodiment 4:

[0090] The present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiments of the present invention are implemented.

[0091] If the modules / units integrated in the computer unit are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0092] Embodiment 5:

[0093] The present invention also provides a computer program product including a computer program, and when the computer program is executed by a processor, the steps of the method as described above are implemented.

[0094] Although the present invention has been specifically shown and described in connection with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the present invention without departing from the spirit and scope of the present invention as defined by the appended claims, and all such changes are within the scope of protection of the present invention.

Claims

1. A method for generating a parametric model, characterized in that, Including: S1, receiving text data related to design intent or commands input by a user; the text data is used to define parameters, create specific types of graphic elements, and / or specify transformation operations; S2, preprocessing the text data through a predetermined natural language processing algorithm to obtain structured parameter information of the text data; wherein, the preprocessing includes: word segmentation, part-of-speech tagging, information extraction, and context correlation analysis of the text data; The structured parameter information includes: operation type, geometric type, at least one parameter included in the geometric type, the dependency relationship between each parameter, and / or the parameter value of each parameter; the operation type is an operation performed on the geometric type or the at least one parameter, including: creation, modification, and transformation; S3, constructing a parametric model according to the structured parameter information through a predetermined modeling software, including: S31, obtaining the graphic element corresponding to the geometric type according to the parametric basic graphic element library of the MicroStation platform, and constructing a parameter dependency graph according to the dependency relationship between each parameter; S32, constructing a parametric model according to the operation type, the graphic element, the parameter value of each parameter, and the parameter dependency graph.

2. The method for generating a parametric model according to claim 1, characterized in that, In step S2, preprocessing the text data through a predetermined natural language processing algorithm to obtain the structured parameter information of the text data further includes: The text data extracts design required information through the natural language processing algorithm, and the design required information is processed through a preset parameter type, a preset parameter expression rule, and a preset operation function library to obtain at least one parameter included in the geometric type in the structured parameter information and the dependency relationship between each parameter, wherein the parameter type includes: basic type, engineering parameter, and standard part parameter; the parameter expression includes: arithmetic operation, comparison operation, logical operation, and conditional expression operation; the operation function library includes: mathematical function, string processing, engineering calculation, and data query; The parameter information conforms to a predetermined syntax rule and geometric constraint condition; and / or When a predetermined default parameter is missing in the parameter information, filling the default parameter and the parameter value of the default parameter according to a preset filling rule.

3. The method for generating a parametric model according to claim 2, wherein The parameter type further includes: text, boolean value, color, and material; wherein, The basic type includes: decimal, integer, and angle; The engineering parameter includes: length, area, volume, and weight; The standard part parameter includes: steel channel specification, angle steel specification, I-beam specification, H-beam specification, and bolt specification; The mathematical function includes: basic operation, trigonometric function, and rounding function; The string processing includes: string concatenation, string splitting, extracting numerical values from a string, and formatting a string; The engineering calculation includes: unit conversion, area calculation, volume calculation, and weight calculation.

4. The method for generating a parametric model according to claim 1, wherein, In step S32, constructing a parametric model according to the operation type, the graphic element, the parameter value of each parameter, and the parameter dependency graph includes: S321. Construct at least one geometric entity according to the graphic element, the parameter value of each parameter, and the parameter dependency graph; wherein, the constraint relationship between the geometric entities conforms to a predetermined design rule, and the constraint relationship includes: the relative position and dimensional relationship between the geometric entities. S322. Perform corresponding operations on each geometric entity according to the operation type and the predetermined three-dimensional transformation rules, and perform feature editing on each geometric entity to obtain a parametric model; the feature editing includes: adding chamfers, adding fillets, or performing Boolean operations on the relationship between the geometric entities.

5. The method for generating a parametric model according to claim 4, wherein In performing corresponding operations on each geometric entity according to the operation type and the predetermined three-dimensional transformation rules, the three-dimensional transformation rules include: basic transformation, composite transformation, and advanced transformation, wherein the basic transformation includes: translation transformation, rotation transformation, and scaling transformation; the composite transformation includes: mirror operation and array replication; the advanced transformation includes: deformation operation and alignment operation.

6. The method for generating a parametric model according to claim 1, wherein After step S32 generates the parametric model, it further includes: When the user modifies the parametric model through text input, modify the parametric model according to the parameter information extracted from the text input and the parameter dependency graph established in step S32.

7. An apparatus for generating a parametric model, characterized in that It includes a memory and a processor, and the memory stores at least one program, and the at least one program is executed by the processor to implement the method for generating a parametric model as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, At least one program is stored in the storage medium, and the at least one program is executed by the processor to implement the method for generating a parametric model as described in any one of claims 1 to 6.

9. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for generating a parametric model as described in any one of claims 1 to 6.

Images