Intelligent interaction three-dimensional modeling method, device and equipment and storage medium

Abstract

The application belongs to the field of industrial internet, and particularly relates to a kind of intelligent interaction three-dimensional modeling method, device, equipment and storage medium. First, in response to the interaction operation triggered by the client, the modeling text is determined, then the workpiece to be assembled and its three-dimensional modeling parameters are determined according to the modeling text, the corresponding three-dimensional modeling template is found out and spliced with the parameters to generate a three-dimensional modeling scheme, then the scheme is input into the preset modeling model to obtain a three-dimensional target model, and finally the model is output. The method automatically analyzes the modeling text and completes three-dimensional modeling with the help of the preset template and model, solves the problem that non-professional users cannot operate modeling software for modeling, realizes efficient and convenient three-dimensional modeling, and reduces the modeling threshold.

Description

Technical Field

[0001] This application belongs to the field of industrial internet, specifically relating to an intelligent interactive 3D modeling method, device, equipment, and storage medium. Background Technology

[0002] With the rapid development of computer technology and the continuous advancement of intelligent transformation in the manufacturing industry, 3D modeling has become an indispensable key link in product design and manufacturing processes.

[0003] Existing 3D modeling methods mainly rely on manual operation, that is, professional users use corresponding modeling software to gradually build the 3D model of parts or assemblies through a series of steps such as parameter setting and feature operation.

[0004] However, this modeling method, which relies on manual operation, is not very user-friendly for non-professional users. It not only raises the threshold for modeling operations for non-professional groups and makes it difficult to effectively improve the overall modeling efficiency, but also brings a poor user experience to non-professional users. Summary of the Invention

[0005] This application provides an intelligent interactive 3D modeling method, apparatus, device, and storage medium to solve the problem that non-professional users cannot operate modeling software to perform modeling.

[0006] In a first aspect, this application provides a three-dimensional modeling method for intelligent interaction, comprising:

[0007] In response to client-triggered interactive actions, determine the modeling text;

[0008] Based on the modeling text, determine the workpiece to be assembled and the corresponding 3D modeling parameters of the workpiece to be assembled.

[0009] A 3D modeling template corresponding to the workpiece to be assembled is determined, and the 3D modeling template is spliced ​​with the 3D modeling parameters to generate a 3D modeling scheme;

[0010] The three-dimensional modeling scheme is input into a preset modeling model to obtain a three-dimensional target model generated by the modeling model;

[0011] Output the three-dimensional target model.

[0012] Optionally, determining the workpiece to be assembled and its corresponding 3D modeling parameters based on the modeling text includes:

[0013] The modeling text is subjected to intent recognition processing to obtain the workpiece to be assembled;

[0014] Based on the preset extraction function corresponding to the workpiece to be assembled, the modeling text is extracted and processed to obtain the three-dimensional modeling parameters corresponding to the workpiece to be assembled.

[0015] Optionally, the step of performing intent recognition processing on the modeling text to obtain the workpiece to be assembled includes:

[0016] Obtain a preset modeling intent vector library, which includes: multiple first intent vectors, and candidate assembly workpieces corresponding to each first intent vector;

[0017] The modeling text is vectorized to obtain the modeling text vector;

[0018] Based on the modeled text vector and each first intent vector, determine the first semantic similarity between the modeled text vector and each first intent vector;

[0019] Based on the first semantic similarity between the modeled text vector and each first intent vector, a second intent vector is determined from multiple first intent vectors, wherein the first semantic similarity corresponding to the second intent vector is greater than the first semantic similarity corresponding to other first intent vectors;

[0020] The candidate assembly workpiece corresponding to the second intention vector is determined as the workpiece to be assembled.

[0021] Optionally, the step of extracting the modeling text based on a preset extraction function corresponding to the workpiece to be assembled to obtain the three-dimensional modeling parameters corresponding to the workpiece to be assembled includes:

[0022] Based on the preset extraction function corresponding to the workpiece to be assembled, the modeling text is extracted and processed to obtain the first structured parameters of the workpiece to be assembled.

[0023] According to the preset verification rules, the first structured parameter is verified to obtain the first verification result of the first structured parameter;

[0024] If the first verification result is successful, the first structured parameter is determined as the three-dimensional modeling parameter.

[0025] Optionally, the method further includes:

[0026] If the first verification result is a verification failure, the first structured parameter is corrected according to the preset repair rules to obtain the second structured parameter.

[0027] According to the verification rules, the second structured parameter is verified to obtain a second result of the second structured parameter. If the second result is a verification failure, this step is repeated until the second result of the second structured parameter is a verification success, or the number of verifications of the second structured parameter reaches a preset number.

[0028] Optionally, the method further includes:

[0029] Obtain the modified text of the three-dimensional target model;

[0030] Based on the modified text, the three-dimensional target model is modified to obtain the modified three-dimensional target model.

[0031] Optionally, the method further includes:

[0032] Obtain the sketch image input by the user;

[0033] The sketch image is processed to extract its image features;

[0034] Based on the image features, the 3D modeling scheme is modified to obtain a revised 3D modeling scheme.

[0035] The step of inputting the 3D modeling scheme into a preset modeling model to obtain the 3D target model generated by the modeling model includes:

[0036] The modified 3D modeling scheme is input into the modeling model to obtain the modified 3D target model, and the modified 3D target model is output.

[0037] Secondly, this application provides an intelligent interactive 3D modeling device, comprising:

[0038] The determination module is used to determine the modeling text in response to interactive operations triggered by the client;

[0039] The determining module is further configured to determine the workpiece to be assembled and the corresponding three-dimensional modeling parameters of the workpiece to be assembled based on the modeling text.

[0040] The determining module is also used to determine a three-dimensional modeling template corresponding to the workpiece to be assembled;

[0041] The splicing module is used to splice the 3D modeling template and the 3D modeling parameters to generate a 3D modeling scheme;

[0042] The input module is used to input the three-dimensional modeling scheme into a preset modeling model to obtain a three-dimensional target model generated by the modeling model;

[0043] The output module is used to output the three-dimensional target model.

[0044] Optionally, the device further includes: a processing module;

[0045] The processing module is specifically used to perform intent recognition processing on the modeling text to obtain the workpiece to be assembled.

[0046] The processing module is specifically used to extract the modeling text based on a preset extraction function corresponding to the workpiece to be assembled, so as to obtain the three-dimensional modeling parameters corresponding to the workpiece to be assembled.

[0047] Optionally, the device further includes: an acquisition module;

[0048] The acquisition module is used to acquire a preset modeling intent vector library, which includes: multiple first intent vectors and candidate assembly workpieces corresponding to each first intent vector;

[0049] The processing module is also used to vectorize the modeling text to obtain a modeling text vector;

[0050] The determining module is further configured to determine a first semantic similarity between the modeling text vector and each first intent vector based on the modeling text vector and each first intent vector;

[0051] The determining module is further configured to determine a second intention vector from multiple first intention vectors based on the first semantic similarity between the modeling text vector and each first intention vector, wherein the first semantic similarity corresponding to the second intention vector is greater than the first semantic similarity corresponding to other first intention vectors;

[0052] The determining module is specifically used to determine the candidate assembly workpiece corresponding to the second intention vector as the workpiece to be assembled.

[0053] Optionally, the processing module is further configured to extract the modeling text based on a preset extraction function corresponding to the workpiece to be assembled, so as to obtain the first structured parameters of the workpiece to be assembled.

[0054] The processing module is further configured to perform verification processing on the first structured parameter according to a preset verification rule, and obtain a first verification result of the first structured parameter.

[0055] The determining module is specifically used to determine the first structured parameter as the three-dimensional modeling parameter when the first verification result is that the verification passes.

[0056] Optionally, the processing module is further configured to, in the case that the first verification result is a verification failure, correct the first structured parameter according to a preset repair rule to obtain the second structured parameter;

[0057] The processing module is further configured to perform verification processing on the second structured parameter according to the verification rules to obtain a second result of the second structured parameter. If the second result is a verification failure, this step is repeated until the second result of the second structured parameter is a verification success, or the number of verifications of the second structured parameter reaches a preset number.

[0058] Optionally, the acquisition module is used to acquire the modified text of the three-dimensional target model;

[0059] The processing module is further configured to modify the three-dimensional target model according to the modified text to obtain the modified three-dimensional target model.

[0060] Optionally, the acquisition module is used to acquire the sketch image input by the user;

[0061] The processing module is also used to extract the sketch image to obtain the image features of the sketch image;

[0062] The processing module is also used to modify the three-dimensional modeling scheme based on the image features to obtain a corrected three-dimensional modeling scheme.

[0063] The input module is also used to input the modified 3D modeling scheme into the modeling model to obtain the modified 3D target model;

[0064] The output module is also used to output the modified three-dimensional target model.

[0065] Thirdly, this application provides an intelligent interactive 3D modeling device, comprising:

[0066] Memory;

[0067] processor;

[0068] The memory stores computer-executed instructions;

[0069] The processor executes computer execution instructions stored in the memory to implement the intelligent interactive 3D modeling method as described in the first aspect and various possible implementations of the first aspect above.

[0070] Fourthly, this application provides a computer storage medium storing computer execution instructions thereon, which are executed by a processor to implement the intelligent interactive 3D modeling method as described in the first aspect and various possible implementations of the first aspect above.

[0071] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the intelligent interactive 3D modeling method described above.

[0072] The intelligent interactive 3D modeling method provided in this application first responds to the interactive operation triggered by the client, determines the modeling text, then determines the workpiece to be assembled and its corresponding 3D modeling parameters based on the modeling text, subsequently matches the 3D modeling template corresponding to the workpiece to be assembled, and concatenates the template and 3D modeling parameters to generate a 3D modeling scheme. Next, this scheme is input into a preset modeling model to generate the corresponding 3D target model, and finally, the 3D target model is output. This method, through receiving construction instructions in the form of modeling text, parses the workpiece and modeling parameters based on the modeling text, combines the modeling template to generate a modeling scheme, and drives the modeling model to automatically generate a 3D target model, is an automated modeling process. It eliminates the need for users to manually operate the modeling software to complete various modeling operations, solving the problem that non-professional users cannot operate the modeling software to perform modeling, lowering the operational threshold of 3D modeling, and allowing non-professional users to complete 3D modeling through simple modeling text instructions, thereby improving 3D modeling efficiency and simplifying the modeling operation process. Attached Figure Description

[0073] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0074] Figure 1 The process of the intelligent interactive 3D modeling method provided in this application Figure 1 ;

[0075] Figure 2 The process of the intelligent interactive 3D modeling method provided in this application Figure 2 ;

[0076] Figure 3 The process of the intelligent interactive 3D modeling method provided in this application Figure 3 ;

[0077] Figure 4 This is a schematic diagram of the structure of the intelligent interactive 3D modeling device provided in this application;

[0078] Figure 5 This is a structural schematic diagram of the intelligent interactive 3D modeling device provided in this application.

[0079] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0081] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0082] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0083] With the advancement of technology and the diversification of product design requirements, 3D modeling has become a crucial step in the product design and manufacturing process. 3D modeling not only visually presents design concepts but also improves the accuracy and efficiency of the design process through digital means.

[0084] Existing 3D modeling methods mainly rely on manual operation, that is, professional users use corresponding modeling software to gradually build the 3D model of parts or assemblies through a series of steps such as parameter setting and feature operation.

[0085] However, this modeling method, which relies on manual operation, is not very user-friendly for non-professional users. It not only raises the threshold for modeling operations for non-professional groups and makes it difficult to effectively improve the overall modeling efficiency, but also brings a poor user experience to non-professional users.

[0086] To address the aforementioned issues, this application provides an intelligent interactive 3D modeling method. First, responding to an interactive operation triggered by the client, the method determines the modeling text. Then, based on the modeling text, it determines the workpiece to be assembled and its 3D modeling parameters. Next, it finds the corresponding 3D modeling template and combines it with the parameters to generate a 3D modeling scheme. Subsequently, the scheme is input into a preset modeling model to obtain the 3D target model, and finally, the model is output. This method automatically parses the modeling text and completes 3D modeling with the help of preset templates and models, solving the problem that non-professional users cannot operate modeling software, achieving efficient and convenient 3D modeling, and lowering the modeling threshold.

[0087] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0088] Figure 1 The flowchart of the intelligent interactive 3D modeling method provided in this embodiment Figure 1 The execution entity in this embodiment can be, for example, a modeling system, such as... Figure 1 As shown, the intelligent interactive 3D modeling method provided in this embodiment includes:

[0089] S101: In response to an interactive action triggered by the client, determine the modeling text.

[0090] Interactive operations refer to actions performed by users on the interactive interface provided by the client to express their 3D modeling design needs, and are used to convey modeling intentions to the modeling system. Interactive operations include, but are not limited to, manually entering modeling text into text input boxes on the client's interactive interface, and inputting modeling text via voice and converting it into text form through voice recognition.

[0091] A client is the front-end runtime environment that hosts and runs a 3D modeling system, providing an interactive interface and interface to the user. A client can be, for example, a computer with the 3D modeling system installed, or a mobile terminal with the 3D modeling system installed.

[0092] Modeling text is natural language text used by users to express their 3D modeling design needs. It is written by users in a natural language form that is easy to understand and express in everyday life. For example, the modeling text might be "Create a cylinder with a radius of 20mm and a height of 50mm".

[0093] The purpose of this step is to obtain the user's 3D modeling design requirements.

[0094] Understandably, users input their modeling intentions through the interactive interface provided by the client, but the modeling system cannot directly understand these intentions. Therefore, by responding to interactive operations triggered by the client, modeling text can be generated, which can reflect the 3D modeling needs of non-professional users.

[0095] S102: Based on the modeling text, determine the workpiece to be assembled and its corresponding 3D modeling parameters.

[0096] In this context, the workpiece to be assembled refers to the modeling object specified by the user through modeling text, which requires 3D modeling and can subsequently participate in product assembly. The workpiece to be assembled can be, for example, a single mechanical part, which refers to a basic mechanical component with a specific function that cannot be further divided into multiple independent assembly units, such as a bolt; or it can be an independently assembled component, which refers to an assembly composed of multiple single mechanical parts that forms a complete functional module. This assembly can participate independently in higher-level product assembly as a whole, such as a bearing housing assembly.

[0097] 3D modeling parameters refer to various parameters required to construct a 3D model of a workpiece to be assembled, which can characterize the workpiece's geometry, dimensions, and structural features. For example, if the workpiece to be assembled is a deep groove ball bearing, its corresponding 3D modeling parameters include an inner diameter of 20mm, an outer diameter of 47mm, a width of 14mm, a ball diameter of 7.938mm, and a number of 8 balls.

[0098] The purpose of this step is to analyze and extract the user design requirements carried in the modeling text, and to transform the natural language modeling requirements into specific modeling elements.

[0099] Understandably, modeling text represents abstract design requirements expressed by users in natural language, and the modeling system cannot directly perform modeling operations based on natural language. Therefore, it is necessary to use the modeling text as a basis to parse and determine the workpiece to be assembled, as well as the corresponding 3D modeling parameters for that workpiece.

[0100] S103: Determine the 3D modeling template corresponding to the workpiece to be assembled, and combine the 3D modeling template with the 3D modeling parameters to generate a 3D modeling scheme.

[0101] Among them, the 3D modeling scheme is a set of instructions that exist in the form of code files and can be directly parsed and executed by the modeling system.

[0102] The purpose of this step is to combine the workpiece to be assembled and the 3D modeling parameters obtained from the analysis with the 3D modeling template corresponding to the workpiece to be assembled, and transform them into a 3D modeling scheme that can be operated by the modeling system.

[0103] Understandably, 3D modeling templates are standardized modeling frameworks pre-set for various workpieces to be assembled, while 3D modeling parameters are personalized structural parameters required to construct the workpieces to be assembled. Therefore, by combining 3D modeling templates and 3D modeling parameters, the modeling framework and structural parameters can be integrated to form a 3D modeling solution that combines standardization and customization.

[0104] S104: Input the 3D modeling scheme into the preset modeling model to obtain the 3D target model generated by the modeling model.

[0105] Among them, modeling software refers to 3D modeling software that has the ability to analyze, calculate and construct 3D models.

[0106] This is understandable. First, a 3D modeling scheme is an executable file of modeling instructions and cannot directly generate a visualized 3D model. Second, the modeling model has the ability to perform 3D modeling calculations and generate models, and can parse various parameters in the 3D modeling scheme and automatically execute modeling operations.

[0107] Therefore, by inputting the 3D modeling scheme into the preset modeling model, the modeling model can complete the entire process of automated modeling according to the 3D modeling scheme, and thus obtain the 3D target model generated by the modeling model.

[0108] This step could be, for example, starting the 3D modeling software (i.e., the modeling model) according to a preset call command, completing the initial loading of the modeling software, and ensuring that the software is in a ready state to receive commands and perform modeling operations; then, inputting the previously generated 3D modeling scheme into the started modeling software, which then analyzes the 3D modeling scheme line by line and extracts the structural parameters; finally, based on the analysis results, the modeling software automatically performs the modeling operation to generate a 3D target model that matches the user's requirements.

[0109] S105: Output the three-dimensional target model.

[0110] The purpose of this step is to present the automatically generated 3D target model to the outside world, so that users can intuitively obtain 3D modeling results that meet their design needs.

[0111] This step outputs the 3D target model in various ways, such as visualizing it on a client interface with a modeling system, or generating a link to a 3D model file for users to download and export. This application does not impose any special restrictions on this.

[0112] The intelligent interactive 3D modeling method provided in this embodiment first responds to the interactive operation triggered by the client to determine the modeling text. Then, based on the modeling text, it determines the workpiece to be assembled and its 3D modeling parameters. Next, it finds the corresponding 3D modeling template and splices it with the parameters to generate a 3D modeling scheme. Subsequently, it inputs the scheme into a preset modeling model to obtain a 3D target model, and finally outputs the model. This method solves the problem that non-professional users cannot operate modeling software to perform modeling, making it easier for users to perform 3D modeling. It also improves modeling efficiency and accuracy, reduces learning costs, and thus promotes the simplification and optimization of the design process.

[0113] Figure 2 The flowchart of the intelligent interactive 3D modeling method provided in this embodiment Figure 2 .like Figure 2 As shown. This embodiment is in Figure 1 Based on the embodiments, the implementation process of 3D modeling is described in detail. The intelligent interactive 3D modeling method provided in this embodiment includes:

[0114] S201: In response to an interactive action triggered by the client, determine the modeling text.

[0115] The explanation of step S201 is the same as that in the above embodiments, and will not be repeated here.

[0116] S202: Perform intent recognition processing on the modeling text to obtain the workpiece to be assembled.

[0117] The purpose of this step is to perform semantic-level intent parsing on the modeling text expressed by the user in natural language, and to extract the modeling target, namely the workpiece to be assembled.

[0118] Optionally, this application provides a possible implementation, including:

[0119] The first step is to obtain a preset modeling intent vector library, which includes: multiple first intent vectors, and candidate assembly workpieces corresponding to each first intent vector.

[0120] In particular, by acquiring a pre-defined modeling intent vector library, reference samples that can be directly called can be provided for subsequent semantic matching operations of modeling text.

[0121] The method for obtaining the preset modeling intent vector library in this step can be, for example, by calling it from the local modeling system or by obtaining it from the local database. This application does not impose any special restrictions on this.

[0122] For example, suppose the modeling intent vector library includes a first intent vector A and a first intent vector B, where the candidate assembly workpiece corresponding to the first intent vector A is a bolt and the candidate assembly workpiece corresponding to the first intent vector B is a bearing.

[0123] The second step is to vectorize the modeling text to obtain the modeling text vector.

[0124] The purpose of this step is to convert the modeling text expressed by the user in natural language into vector form.

[0125] This step of vectorizing the modeling text can be done, for example, through a bag-of-words model. The bag-of-words model is a natural language processing model that transforms text into word frequency feature vectors. It only counts the frequency and distribution characteristics of words in the modeling text, without considering word order or semantic relationships.

[0126] The specific process of vectorizing the modeling text using the bag-of-words model is as follows: First, in the text preprocessing layer, the modeling text is segmented and stop word removed to extract valid words and eliminate meaningless words. Next, in the vocabulary statistics layer, the preprocessed words are statistically analyzed to calculate the frequency of each word in the text. Finally, this frequency information is mapped to a fixed-dimensional feature vector, which is the modeling text vector.

[0127] The third step is to determine the first semantic similarity between the modeling text vector and each first intent vector based on the modeling text vector and each first intent vector.

[0128] The first semantic similarity is used to characterize the degree of similarity between the modeling text vector and the first intent vector. A higher first semantic similarity indicates a higher degree of similarity between the modeling text vector and each first intent vector; a lower first semantic similarity indicates a lower degree of similarity between the modeling text vector and the first intent vector.

[0129] The purpose of this step is to determine the semantic fit between the modeling text vector and each first intent vector in the modeling intent vector library, and to obtain a one-to-one first semantic similarity.

[0130] The fourth step is to determine the second intent vector from multiple first intent vectors based on the first semantic similarity between the modeled text vector and each first intent vector, wherein the first semantic similarity of the second intent vector is greater than the first semantic similarity of the other first intent vectors.

[0131] Understandably, different primary intent vectors represent different modeling intentions, while modeling text vectors can reflect the user's specific modeling needs. Semantic similarity can measure the semantic closeness between modeling text vectors and primary intent vectors.

[0132] Therefore, by comparing the first semantic similarity between the modeling text vector and each first intent vector, the intent vector that best matches the semantics of the modeling text can be found, namely the second intent vector.

[0133] The fifth step is to determine the candidate assembly workpiece corresponding to the second intention vector as the workpiece to be assembled.

[0134] Understandably, the second intent vector is the vector with the highest semantic similarity to the modeling text vector selected from the modeling intent vector library. Its corresponding candidate assembly artifact is the modeling object in the modeling intent vector library that best matches the user's actual modeling intent. Therefore, the candidate assembly artifact corresponding to the second intent vector can be identified as the artifact to be assembled.

[0135] S203: Based on the preset extraction function corresponding to the workpiece to be assembled, the modeling text is extracted and processed to obtain the three-dimensional modeling parameters corresponding to the workpiece to be assembled.

[0136] Different types of workpieces to be assembled correspond to different preset extraction functions. For example, when the workpiece to be assembled is a bolt, the preset extraction function will extract the bolt's diameter, length, and thread specification from the modeling text. When the workpiece to be assembled is a cylinder, the preset extraction function will extract the cylinder's length, height, and base radius from the modeling text.

[0137] Understandably, after determining the workpiece to be assembled, the preset retrieval function corresponding to the workpiece can be called. This function will perform semantic analysis and structured decomposition on the modeling text according to preset rules, automatically identify and extract the numerical values, units and feature type information related to the workpiece in the text, and finally integrate this information into a set of 3D modeling parameters that can be directly used for modeling.

[0138] Optionally, this application provides a possible implementation, including:

[0139] The first step is to extract the modeling text based on the preset extraction function corresponding to the workpiece to be assembled, and obtain the first structured parameters of the workpiece to be assembled.

[0140] The first structured parameter includes, but is not limited to: radius, height, and length.

[0141] The purpose of this step is to extract structured parameter information directly related to the workpiece to be assembled from the user's modeling text.

[0142] Understandably, different types of workpieces to be assembled require different feature parameters. The preset extraction function is specifically designed for the feature requirements of this type of workpiece and can accurately locate the parameter information related to the workpiece in the text.

[0143] Therefore, by extracting the first structured parameters from the modeling text using the preset extraction function corresponding to the workpiece to be assembled, it can be ensured that the extracted parameters are highly matched with the feature requirements of the workpiece to be assembled, providing a reliable initial data source for the subsequently generated 3D modeling scheme.

[0144] For example, if the modeling text is to create a cylinder with a radius of 20mm and a height of 50mm, and the workpiece to be assembled is a cylinder, then the first structured parameter is: {(radius, 20, mm), (height, 50, mm)}.

[0145] Optionally, the preset extraction function provided in this application can be represented in the following ways, including:

[0146]

[0147] Where p represents the 3D modeling parameters; Indicates the parameter type; Indicates the specific numerical value of the parameter; Indicates the unit of the parameter; , as well as Each represents a set of complete parameter information, including parameter type, specific value, and unit.

[0148] For example, if the workpiece to be assembled is a door, the parameter types include: length, width, and height, with the corresponding unit being millimeters; if the workpiece to be assembled is a nut, the parameter types include: thread specification, width across flats, and thickness, with the corresponding unit being millimeters.

[0149] The second step is to perform verification processing on the first structured parameter according to the preset verification rules, and obtain the first verification result of the first structured parameter.

[0150] The validation rules are used to measure whether each parameter in the first structured parameter set conforms to the preset modeling parameter standards. Validation rules include, but are not limited to: whether the parameter units are missing and whether the numerical range is reasonable.

[0151] Understandably, by performing verification processing on the first structured parameter according to the preset verification rules, it is possible to check whether each parameter in the first structured parameter meets the preset modeling parameter standard, such as determining whether the parameter is missing a unit, and thus obtain the first verification result corresponding to the first structured parameter.

[0152] The third step is to determine the first structured parameter as the 3D modeling parameter if the first verification result is successful.

[0153] Understandably, when the first verification result is successful, it means that each parameter in the first structured parameter conforms to the preset modeling parameter standard, and there are no issues such as missing units or unreasonable values, thus meeting the requirements for subsequent 3D modeling. Therefore, the first structured parameter can be determined as the 3D modeling parameter.

[0154] The fourth step is to correct the first structured parameter according to the preset repair rules if the first verification result is a verification failure, so as to obtain the second structured parameter.

[0155] The repair rules include, but are not limited to: parameter unit completion and numerical range correction.

[0156] Understandably, when the first verification result is a verification failure, it means that the first structured parameter does not meet the preset modeling parameter standard. Therefore, the first structured parameter that failed the verification can be specifically corrected and improved through the preset repair rules to solve problems such as missing units, unreasonable values, and non-standard formats in the parameters, and generate the repaired second structured parameter.

[0157] Fifth step: According to the verification rules, the second structured parameter is verified to obtain the second result of the second structured parameter. If the second result is a verification failure, this step is repeated until the second result of the second structured parameter is a verification success, or the number of verifications of the second structured parameter reaches the preset number.

[0158] The preset number of times can be, for example, 3 or 4. This application does not impose any special restrictions on this.

[0159] Understandably, by verifying the repaired second structured parameters and using a cyclical verification method, it can be ensured that the final structured parameters meet the preset modeling standards.

[0160] In addition, setting an upper limit on the number of verifications can avoid meaningless repetitive operations, ensure the integrity and accuracy of modeling parameters, control the execution efficiency of the parameter repair process, and thus provide qualified parameter basis for subsequent determination of 3D modeling parameters.

[0161] S204: Determine the 3D modeling template corresponding to the workpiece to be assembled, and combine the 3D modeling template with the 3D modeling parameters to generate a 3D modeling scheme.

[0162] Optionally, this application provides a possible implementation method for determining the 3D modeling template corresponding to the workpiece to be assembled, including:

[0163] The first step is to determine the target number corresponding to the workpiece to be assembled.

[0164] Understandably, after identifying the workpiece to be assembled based on the construction text, the system will assign a unique target number to the workpiece to be assembled, so as to serve as the basis for subsequent selection of modeling templates.

[0165] The second step is to obtain a preset modeling template library, which contains multiple first numbers and candidate modeling templates corresponding to each first number.

[0166] The purpose of this step is to obtain a pre-defined modeling template library as data support for subsequent template matching.

[0167] This step involves obtaining the modeling template library, for example, by retrieving it from the local modeling system or from the local database; this application does not impose any special restrictions on this.

[0168] The third step is to determine the second number from multiple first numbers in the modeling template library based on the target number corresponding to the workpiece to be assembled, wherein the second number matches the target number.

[0169] Understandably, by selecting a matching second number from the first number in the modeling template library based on the unique target number of the workpiece to be assembled, a relationship can be established between the workpiece to be assembled and the corresponding number in the modeling template library. This provides a numbering basis for retrieving suitable candidate modeling templates from the library, thus enabling targeted selection of modeling templates.

[0170] The fourth step is to select the candidate modeling template corresponding to the second number in the modeling template library as the 3D modeling template for the workpiece to be assembled.

[0171] The purpose of this step is to identify the candidate modeling templates associated with the workpiece to be assembled in the modeling template library as the exclusive 3D modeling templates for that workpiece, thereby completing the screening and locking of modeling templates.

[0172] S205: Input the 3D modeling scheme into the preset modeling model to obtain the 3D target model generated by the modeling model.

[0173] S206: Output the three-dimensional target model.

[0174] The explanation of step S206 is the same as that in the above embodiments, and will not be repeated here.

[0175] S207: Obtain the modified text of the 3D target model.

[0176] The purpose of this step is to obtain the user's modification request text for the generated 3D target model.

[0177] Understandably, firstly, the generated 3D target model may not fully meet the user's final design requirements. The user will propose adjustments based on actual use or design considerations, and these requirements will be presented as modification text in natural language.

[0178] Secondly, the system cannot proactively perceive the user's intended modifications to the model; only by obtaining the modification text can the direction of the user's modifications to the 3D target model be determined. Therefore, in order to obtain the user's specific modification requirements, it is necessary to obtain the modification text of the 3D target model.

[0179] S208: Based on the modified text, modify the 3D target model to obtain the modified 3D target model.

[0180] Understandably, by making targeted adjustments to the generated 3D target model based on the user's suggested modifications, the user's natural language modification requests can be translated into actual adjustment actions for the 3D target model, generating a modified 3D target model that meets the user's design requirements, thus ensuring that the 3D model matches the user's needs.

[0181] The intelligent interactive 3D modeling method provided in this embodiment first responds to the interactive operation triggered by the client, determines the modeling text, performs intent recognition processing on the modeling text to determine the workpiece to be assembled, and then extracts the matching 3D modeling parameters from the modeling text based on the preset extraction function corresponding to the workpiece; subsequently, it matches the corresponding 3D modeling template, splices the template and modeling parameters to generate a 3D modeling scheme, inputs the scheme into the preset modeling model to generate and output a 3D target model; it can also further obtain the modification text of the 3D target model, and modify the 3D target model according to the modification text to obtain the modified 3D target model.

[0182] This method automatically generates a 3D model by recognizing the intent and extracting parameters from the modeling text, combining it with a modeling template to generate a modeling scheme, and driving the modeling model to automatically generate a 3D model. It also supports subsequent adjustments to the model by modifying the text. The entire process does not require non-professional users to manually operate the modeling software to perform various modeling and modification operations, thus solving the problem that non-professional users cannot operate the modeling software to perform modeling. This lowers the professional operation threshold of 3D modeling, allowing non-professional users to complete the creation and modification of 3D models through text commands only, thereby improving the overall operational efficiency and flexibility of 3D modeling.

[0183] Figure 3 The flowchart of the intelligent interactive 3D modeling method provided in this embodiment Figure 2 .like Figure 3 As shown. This embodiment, based on the above embodiments, provides a modified method for a 3D modeling scheme, including:

[0184] S301: Obtain the sketch image input by the user.

[0185] Among them, sketch images are two-dimensional visual images drawn by the user by hand or with the help of simple drawing tools, used to express the approximate shape and key features of a three-dimensional model.

[0186] Understandably, by obtaining the sketch image input by the user, we can obtain the user's design intent for the 3D target model at the visual level, and thus provide a visual basis for the subsequent generation of the 3D target model.

[0187] S302: Extract and process the sketch image to obtain the image features of the sketch image.

[0188] Image features include, but are not limited to: contour features, structural layout features, and size ratio features.

[0189] Understandably, sketch images may contain irrelevant visual distractions, such as blurry smudges. Therefore, by extracting and processing sketch images, we can obtain the visual elements that best reflect the user's design intent, and then identify these visual elements as image features, providing a basis for subsequently constructing the 3D target model.

[0190] S303: Based on image features, modify the 3D modeling scheme to obtain a revised 3D modeling scheme.

[0191] The purpose of this step is to optimize and adjust the preliminary 3D modeling scheme based on the extracted image features.

[0192] Understandably, image features can reflect the user's visual design requirements for the 3D target model. Therefore, modifying the 3D modeling scheme based on image features can integrate the visual design intent into the 3D modeling scheme and carry out targeted optimization and adjustment, thereby obtaining a revised 3D modeling scheme that better meets the user's overall design intent.

[0193] S304: Input the revised 3D modeling scheme into the modeling model to obtain the modified 3D target model, and output the modified 3D target model.

[0194] Understandably, inputting a revised 3D modeling scheme that aligns with the user's visual design intent from the sketch into the modeling model, transforming it into a concrete 3D target model, and then outputting it allows the user to obtain a 3D model that meets their visual design requirements, thereby satisfying the user's actual need to conduct 3D modeling based on sketches.

[0195] The intelligent interactive 3D modeling method provided in this embodiment first acquires a sketch image input by the user, performs feature extraction processing on the sketch image to obtain the image features corresponding to the sketch image, then, based on the extracted image features, performs targeted modification processing on the existing 3D modeling scheme to generate a modified 3D modeling scheme, and finally inputs the modified 3D modeling scheme into a preset modeling model, which generates the modified 3D target model and outputs the modified 3D target model. This method, by fusing sketch images to modify the 3D modeling scheme obtained from construction instructions, can more comprehensively capture user needs and significantly improve the accuracy of model generation and user satisfaction.

[0196] Figure 4 A schematic diagram of the structure of the intelligent interactive 3D modeling device provided in this application. Figure 4 As shown, this application provides an intelligent interactive 3D modeling device, the intelligent interactive 3D modeling device 400 comprising:

[0197] Module 401 is used to determine the modeling text in response to interactive operations triggered by the client;

[0198] The determination module 401 is also used to determine the workpiece to be assembled and the corresponding 3D modeling parameters of the workpiece to be assembled based on the modeling text.

[0199] The determination module 401 is also used to determine the three-dimensional modeling template corresponding to the workpiece to be assembled;

[0200] The splicing module 402 is used to splice the 3D modeling template and 3D modeling parameters to generate a 3D modeling scheme;

[0201] The input module 403 is used to input the 3D modeling scheme into the preset modeling model to obtain the 3D target model generated by the modeling model;

[0202] Output module 404 is used to output a three-dimensional target model.

[0203] Optionally, the device may also include: a processing module 405;

[0204] Processing module 405 is specifically used to perform intent recognition processing on the modeling text to obtain the workpiece to be assembled;

[0205] The processing module 405 is specifically used to extract and process the modeling text based on the preset extraction function corresponding to the workpiece to be assembled, so as to obtain the three-dimensional modeling parameters corresponding to the workpiece to be assembled.

[0206] Optionally, the device may also include: an acquisition module 406;

[0207] The acquisition module 406 is used to acquire a preset modeling intent vector library, which includes: multiple first intent vectors and candidate assembly workpieces corresponding to each first intent vector;

[0208] Processing module 405 is also used to vectorize the modeling text to obtain the modeling text vector;

[0209] The determination module 401 is further configured to determine the first semantic similarity between the modeling text vector and each first intent vector based on the modeling text vector and each first intent vector;

[0210] The determining module 401 is further configured to determine a second intention vector from multiple first intention vectors based on the first semantic similarity between the modeling text vector and each first intention vector, wherein the first semantic similarity corresponding to the second intention vector is greater than the first semantic similarity corresponding to the other first intention vectors;

[0211] The determination module 401 is specifically used to determine the candidate assembly workpiece corresponding to the second intention vector as the workpiece to be assembled.

[0212] Optionally, the processing module 405 is also used to extract and process the modeling text based on the preset extraction function corresponding to the workpiece to be assembled, so as to obtain the first structured parameters of the workpiece to be assembled.

[0213] The processing module 405 is also used to perform verification processing on the first structured parameter according to the preset verification rules, and obtain the first verification result of the first structured parameter;

[0214] The determination module 401 is specifically used to determine the first structured parameter as the 3D modeling parameter if the first verification result is that the verification passes.

[0215] Optionally, the processing module 405 is also used to correct the first structured parameter according to a preset repair rule to obtain the second structured parameter if the first verification result is a verification failure.

[0216] The processing module 405 is also used to perform verification processing on the second structured parameter according to the verification rules to obtain the second result of the second structured parameter. If the second result is a verification failure, this step is repeated until the second result of the second structured parameter is a verification success, or the number of verifications of the second structured parameter reaches the preset number.

[0217] Optionally, module 406 is used to acquire the modified text of the 3D target model;

[0218] The processing module 405 is also used to modify the three-dimensional target model according to the modified text to obtain the modified three-dimensional target model.

[0219] Optionally, module 406 is used to acquire the sketch image input by the user;

[0220] The processing module 405 is also used to extract and process the sketch image to obtain the image features of the sketch image;

[0221] The processing module 405 is also used to modify the 3D modeling scheme based on image features to obtain a corrected 3D modeling scheme.

[0222] The input module 403 is also used to input the revised 3D modeling scheme into the modeling model to obtain the modified 3D target model;

[0223] Output module 404 is also used to output the modified 3D target model.

[0224] Figure 5 A schematic diagram of the structure of the intelligent interactive 3D modeling device provided in this application. Figure 5 As shown, this application provides an intelligent interactive 3D modeling device 500, which includes: a receiver 501, a transmitter 502, a processor 503, and a memory 504.

[0225] Receiver 501 is used to receive instructions and data;

[0226] Transmitter 502 is used to send commands and data;

[0227] Memory 504 is used to store instructions executed by the computer;

[0228] The processor 503 is used to execute computer execution instructions stored in the memory 504 to implement the various steps performed by the intelligent interactive 3D modeling method in the above embodiments. For details, please refer to the relevant descriptions in the foregoing embodiments of the intelligent interactive 3D modeling method.

[0229] Optionally, the memory 504 can be either standalone or integrated with the processor 503.

[0230] When the memory 504 is set up independently, the electronic device also includes a bus for connecting the memory 504 and the processor 503.

[0231] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the intelligent interactive 3D modeling method performed by the aforementioned intelligent interactive 3D modeling device.

[0232] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0233] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for intelligent interactive 3D modeling, characterized in that, The method includes: In response to client-triggered interactive actions, determine the modeling text; Based on the modeling text, determine the workpiece to be assembled and the corresponding 3D modeling parameters of the workpiece to be assembled. A 3D modeling template corresponding to the workpiece to be assembled is determined, and the 3D modeling template is spliced ​​with the 3D modeling parameters to generate a 3D modeling scheme; The three-dimensional modeling scheme is input into a preset modeling model to obtain a three-dimensional target model generated by the modeling model; Output the three-dimensional target model.

2. The method according to claim 1, characterized in that, The step of determining the workpiece to be assembled and its corresponding 3D modeling parameters based on the modeling text includes: The modeling text is subjected to intent recognition processing to obtain the workpiece to be assembled; Based on the preset extraction function corresponding to the workpiece to be assembled, the modeling text is extracted and processed to obtain the three-dimensional modeling parameters corresponding to the workpiece to be assembled.

3. The method according to claim 2, characterized in that, The process of performing intent recognition processing on the modeled text to obtain the workpiece to be assembled includes: Obtain a preset modeling intent vector library, which includes: multiple first intent vectors, and candidate assembly workpieces corresponding to each first intent vector; The modeling text is vectorized to obtain the modeling text vector; Based on the modeled text vector and each first intent vector, determine the first semantic similarity between the modeled text vector and each first intent vector; Based on the first semantic similarity between the modeled text vector and each first intent vector, a second intent vector is determined from multiple first intent vectors, wherein the first semantic similarity corresponding to the second intent vector is greater than the first semantic similarity corresponding to other first intent vectors; The candidate assembly workpiece corresponding to the second intention vector is determined as the workpiece to be assembled.

4. The method according to claim 2, characterized in that, The step of extracting the modeling text based on a preset extraction function corresponding to the workpiece to be assembled, and obtaining the three-dimensional modeling parameters corresponding to the workpiece to be assembled, includes: Based on the preset extraction function corresponding to the workpiece to be assembled, the modeling text is extracted and processed to obtain the first structured parameters of the workpiece to be assembled. According to the preset verification rules, the first structured parameter is verified to obtain the first verification result of the first structured parameter; If the first verification result is successful, the first structured parameter is determined as the three-dimensional modeling parameter.

5. The method according to claim 4, characterized in that, The method further includes: If the first verification result is a verification failure, the first structured parameter is corrected according to the preset repair rules to obtain the second structured parameter. According to the verification rules, the second structured parameter is verified to obtain a second result of the second structured parameter. If the second result is a verification failure, this step is repeated until the second result of the second structured parameter is a verification success, or the number of verifications of the second structured parameter reaches a preset number.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Obtain the modified text of the three-dimensional target model; Based on the modified text, the three-dimensional target model is modified to obtain the modified three-dimensional target model.

7. The method according to any one of claims 1-5, characterized in that, The method further includes: Obtain the sketch image input by the user; The sketch image is processed to extract its image features; Based on the image features, the 3D modeling scheme is modified to obtain a revised 3D modeling scheme. The step of inputting the 3D modeling scheme into a preset modeling model to obtain the 3D target model generated by the modeling model includes: The modified 3D modeling scheme is input into the modeling model to obtain the modified 3D target model, and the modified 3D target model is output.

8. A smart interactive 3D modeling device, characterized in that, include: The determination module is used to determine the modeling text in response to interactive operations triggered by the client; The determining module is further configured to determine the workpiece to be assembled and the corresponding three-dimensional modeling parameters of the workpiece to be assembled based on the modeling text. The determining module is also used to determine a three-dimensional modeling template corresponding to the workpiece to be assembled; The splicing module is used to splice the 3D modeling template and the 3D modeling parameters to generate a 3D modeling scheme; The input module is used to input the three-dimensional modeling scheme into a preset modeling model to obtain a three-dimensional target model generated by the modeling model; The output module is used to output the three-dimensional target model.

9. An intelligent interactive 3D modeling device, characterized in that, include: Memory; processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the intelligent interactive 3D modeling method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the intelligent interactive three-dimensional modeling method as described in any one of claims 1-7.

Images