Artificial Intelligence-Based 3D Model Generation Control Method and System

Abstract

This invention relates to the field of artificial intelligence technology, and discloses a method and system for generating and controlling 3D models based on artificial intelligence. The method includes: analyzing a target planar image to be modeled to obtain first multi-dimensional information; acquiring second multi-dimensional information corresponding to the modeling requester; and analyzing the modeling requester's target modeling requirements for the target planar image based on the second multi-dimensional information; selecting modeling reference data matching the target modeling requirements from historical modeling data based on the first multi-dimensional information and the target modeling requirements; generating modeling control parameters corresponding to the target planar image based on the modeling reference data and the target modeling requirements, combined with a pre-trained and converged modeling parameter generation model; and performing 3D modeling operations on the target planar image based on the modeling control parameters to obtain a target 3D model corresponding to the target planar image. Therefore, this invention can improve the efficiency of 3D model generation while increasing the matching degree between the generated 3D model and actual needs.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method and system for generating and controlling three-dimensional models based on artificial intelligence. Background Technology

[0002] Due to its ability to provide intuitive multi-angle displays, 3D models have been widely used in several key industries, such as the medical and construction industries. Furthermore, 3D models can help relevant personnel better understand the structure and form of relevant objects (such as a building or a body part of a person).

[0003] In practical applications, traditional 3D model generation primarily relies on drafters manually drawing based on collected data. This method depends heavily on the drafter's experience and the accuracy and comprehensiveness of the collected data, resulting in both low efficiency and low reliability in 3D model generation. With the emergence of intelligent tools, drafters can utilize these tools to generate 3D models. While this method improves efficiency and reliability to some extent compared to manual drawing, it is still limited by the drawing capabilities of existing intelligent tools, hindering the accurate matching of the generated 3D model with actual needs.

[0004] Therefore, it is particularly important to improve the matching degree between the generated 3D model and the actual needs while increasing the efficiency of 3D model generation. Summary of the Invention

[0005] This invention provides an artificial intelligence-based method and system for generating and controlling 3D models, which can improve the efficiency of 3D model generation while increasing the matching degree between the generated 3D model and actual needs.

[0006] The first aspect of this invention discloses a three-dimensional model generation and control method based on artificial intelligence, the method comprising:

[0007] The method includes:

[0008] A target planar image to be modeled is determined, and the target planar image is analyzed to obtain first multi-dimensional information, which includes multiple image information corresponding to the target planar image;

[0009] Obtain the second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirements of the modeling requester for the target planar diagram based on the second multi-dimensional information;

[0010] Based on the first multi-dimensional information and the target modeling requirements, modeling reference data that matches the target modeling requirements is selected from historical modeling data;

[0011] Based on the modeling reference data and the target modeling requirements, and combined with the modeling parameter generation model that has been pre-trained to convergence, the modeling control parameters corresponding to the target planar diagram are generated.

[0012] Based on the modeling control parameters, a three-dimensional modeling operation is performed on the target plan view to obtain the target three-dimensional model corresponding to the target plan view.

[0013] As an optional implementation, in the first aspect of the present invention, the modeling control parameters include at least one pair of modeling control sub-parameters; each pair of modeling control sub-parameters includes at least a modeling quality control sub-parameter and a modeling cost parameter corresponding to the modeling quality control sub-parameter.

[0014] The step of performing a 3D modeling operation on the target planar map based on the modeling control parameters to obtain the target 3D model corresponding to the target planar map includes:

[0015] Based on the target modeling requirements and the historical modeling data, determine the target balance point between modeling quality and modeling cost for this 3D modeling.

[0016] Based on the target balance requirement point, select the target modeling control sub-parameter pair that has the highest matching degree with the balance requirement point from the modeling control parameters;

[0017] Based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pair, a 3D modeling operation is performed on the target planar diagram to obtain the target 3D model corresponding to the target planar diagram.

[0018] As an optional implementation, in a first aspect of the present invention, the first multi-dimensional information includes at least the completeness of the target planar image, wherein the completeness is used to indicate whether the target planar image is a fragmented planar image obtained after image segmentation of a certain complete planar image;

[0019] The step of determining the target balance point between modeling quality and modeling cost for this 3D modeling based on the target modeling requirements and the historical modeling data includes:

[0020] Based on the target modeling requirements and the historical modeling data, determine the initial balance point between the modeling quality and modeling cost for this 3D modeling.

[0021] When the completeness indicates that the target planar map is a fragmented planar map, it is determined whether a verification operation needs to be performed on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map. If so, a verification operation is performed on the initial balance requirement point to obtain the target balance requirement point between modeling quality and modeling cost corresponding to this 3D modeling.

[0022] As an optional implementation, in the first aspect of the present invention, when the completeness indicates that the target planar map is the fragmented planar map, the step of determining whether a verification operation needs to be performed on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map includes:

[0023] Analyze the positional weight of the fragmented planar diagram within the complete planar diagram;

[0024] Analyze the proportion of the target image content carried by the fragmented planar image in the complete planar image;

[0025] Based on the location weight and the content weight, calculate the overall weight of the fragmented planar map in the complete planar map;

[0026] If the overall proportion is greater than or equal to a preset proportion threshold, it is determined whether the initial balance requirement point matches the overall proportion. If they do not match, it is determined that a verification operation needs to be performed on the initial balance requirement point.

[0027] As an optional implementation, in the first aspect of the present invention, the method further includes:

[0028] If the completeness indicates that the target planar map is a fragmented planar map, then after obtaining the target 3D model corresponding to the target planar map, at least one other historical 3D model corresponding to a fragmented planar map that has a modeling relationship with the target planar map is selected from the historical modeling data.

[0029] Based on the modeling association between each of the other fragmented planar maps and the target planar map, a fusion operation is performed on the target 3D model and the historical 3D model corresponding to each of the other fragmented planar maps to obtain the fused 3D model.

[0030] As an optional implementation, in the first aspect of the present invention, the method further includes:

[0031] For any obtained current fused 3D model, determine whether the current fused 3D model is the current fused 3D model corresponding to the complete planar view. If so, analyze the 3D model operation requirements corresponding to the modeling user based on the target modeling requirements.

[0032] Based on the operational requirements of the 3D model, output control parameters corresponding to the current fused 3D model are generated, and the current fused 3D model is output to the modeling user based on the output control parameters.

[0033] The output control parameters include explicit information output control parameters for the current fused model, implicit information output control parameters for the current fused model, and output triggering conditions for implicit information of the current fused model. The output triggering conditions for implicit information indicate that the implicit information is output based on the implicit information output control parameters when the output triggering conditions for implicit information are met. The output triggering conditions for implicit information include direct output triggering conditions and indirect output triggering conditions. The direct output triggering conditions include at least a fixed output triggering time, and the indirect output triggering conditions include at least a non-fixed output triggering timing.

[0034] As an optional implementation, in the first aspect of the present invention, the step of analyzing the modeling requirements of the modeling requester for the target planar diagram based on the second multi-dimensional information includes:

[0035] Based on the second multi-dimensional information, analyze the direct modeling needs of the modeling requesters for the target plan and the corresponding proportion of the first modeling needs;

[0036] Based on the second multi-dimensional information and the direct modeling requirements, analyze the indirect modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of the second modeling requirements;

[0037] Based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements, the derivative modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of their third modeling requirements are analyzed.

[0038] Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements, and their respective proportions, the target modeling requirements of the modeling requester for the target plan are generated.

[0039] A second aspect of this invention discloses an artificial intelligence-based 3D model generation and control system, the system comprising:

[0040] The first analysis module is used to determine the target planar image to be modeled and analyze the target planar image to obtain first multi-dimensional information, the first multi-dimensional information including multiple image information corresponding to the target planar image;

[0041] The second analysis module is used to obtain the second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirements of the modeling requester for the target planar diagram based on the second multi-dimensional information.

[0042] The filtering module is used to filter modeling reference data that matches the target modeling requirements from historical modeling data based on the first multi-dimensional information and the target modeling requirements.

[0043] The parameter generation module is used to generate the modeling control parameters corresponding to the target planar map based on the modeling reference data and the target modeling requirements, and in combination with the pre-trained and converged modeling parameter generation model.

[0044] The modeling control module is used to perform a three-dimensional modeling operation on the target planar diagram based on the modeling control parameters, so as to obtain the target three-dimensional model corresponding to the target planar diagram.

[0045] As an optional implementation, in a second aspect of the present invention, the modeling control parameters include at least one pair of modeling control sub-parameters; each pair of modeling control sub-parameters includes at least a modeling quality control sub-parameter and a modeling cost parameter corresponding to the modeling quality control sub-parameter.

[0046] The specific methods by which the modeling control module performs a 3D modeling operation on the target planar map based on the modeling control parameters to obtain the target 3D model corresponding to the target planar map include:

[0047] Based on the target modeling requirements and the historical modeling data, determine the target balance point between modeling quality and modeling cost for this 3D modeling.

[0048] Based on the target balance requirement point, select the target modeling control sub-parameter pair that has the highest matching degree with the balance requirement point from the modeling control parameters;

[0049] Based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pair, a 3D modeling operation is performed on the target planar diagram to obtain the target 3D model corresponding to the target planar diagram.

[0050] As an optional implementation, in a second aspect of the present invention, the first multi-dimensional information includes at least the completeness of the target planar image, wherein the completeness is used to indicate whether the target planar image is a fragmented planar image obtained after image segmentation of a certain complete planar image;

[0051] The specific methods by which the modeling control module determines the target balance point between modeling quality and modeling cost for this 3D modeling based on the target modeling requirements and the historical modeling data include:

[0052] Based on the target modeling requirements and the historical modeling data, determine the initial balance point between the modeling quality and modeling cost for this 3D modeling.

[0053] When the completeness indicates that the target planar map is a fragmented planar map, it is determined whether a verification operation needs to be performed on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map. If so, a verification operation is performed on the initial balance requirement point to obtain the target balance requirement point between modeling quality and modeling cost corresponding to this 3D modeling.

[0054] As an optional implementation, in a second aspect of the present invention, when the completeness indicates that the target planar map is a fragmented planar map, the specific method by which the modeling control module determines whether a verification operation needs to be performed on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map includes:

[0055] Analyze the positional weight of the fragmented planar diagram within the complete planar diagram;

[0056] Analyze the proportion of the target image content carried by the fragmented planar image in the complete planar image;

[0057] Based on the location weight and the content weight, calculate the overall weight of the fragmented planar map in the complete planar map;

[0058] If the overall proportion is greater than or equal to a preset proportion threshold, it is determined whether the initial balance requirement point matches the overall proportion. If they do not match, it is determined that a verification operation needs to be performed on the initial balance requirement point.

[0059] As an optional implementation, in a second aspect of the invention, the system further includes:

[0060] The model fusion module is configured to, if the completeness indicates that the target planar map is a fragmented planar map, then after obtaining the target 3D model corresponding to the target planar map, select from the historical modeling data at least one historical 3D model corresponding to another fragmented planar map that has a modeling association relationship with the target planar map; and, based on the modeling association relationship between each other fragmented planar map and the target planar map, perform a fusion operation on the target 3D model and the historical 3D model corresponding to each other fragmented planar map to obtain a fused 3D model.

[0061] As an optional implementation, in a second aspect of the invention, the system further includes:

[0062] The model output control module is used to determine, for any obtained current fused 3D model, whether the current fused 3D model is the same as the current fused 3D model corresponding to the complete planar view; if so, to analyze the 3D model operation requirements corresponding to the modeling user based on the target modeling requirements; and to generate output control parameters corresponding to the current fused 3D model according to the 3D model operation requirements, and to output the current fused 3D model to the modeling user according to the output control parameters.

[0063] The output control parameters include explicit information output control parameters for the current fused model, implicit information output control parameters for the current fused model, and output triggering conditions for implicit information of the current fused model. The output triggering conditions for implicit information indicate that the implicit information is output based on the implicit information output control parameters when the output triggering conditions for implicit information are met. The output triggering conditions for implicit information include direct output triggering conditions and indirect output triggering conditions. The direct output triggering conditions include at least a fixed output triggering time, and the indirect output triggering conditions include at least a non-fixed output triggering timing.

[0064] As an optional implementation, in a second aspect of the present invention, the specific method by which the second analysis module analyzes the target modeling requirements of the modeling requester for the target planar diagram based on the second multi-dimensional information includes:

[0065] Based on the second multi-dimensional information, analyze the direct modeling needs of the modeling requesters for the target plan and the corresponding proportion of the first modeling needs;

[0066] Based on the second multi-dimensional information and the direct modeling requirements, analyze the indirect modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of the second modeling requirements;

[0067] Based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements, the derivative modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of their third modeling requirements are analyzed.

[0068] Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements, and their respective proportions, the target modeling requirements of the modeling requester for the target plan are generated.

[0069] A third aspect of this invention discloses another artificial intelligence-based 3D model generation and control system, the system comprising:

[0070] Memory containing executable program code;

[0071] A processor coupled to the memory;

[0072] The processor calls the executable program code stored in the memory to execute the steps in the artificial intelligence-based 3D model generation and control method according to any of the first aspects of the present invention.

[0073] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute the steps in the artificial intelligence-based three-dimensional model generation and control method described in any of the first aspects of the present invention.

[0074] Compared with the prior art, the present invention has the following beneficial effects:

[0075] This invention enables 3D modeling control of planar diagrams. Specifically, after determining the target planar diagram to be modeled, it automatically analyzes its corresponding first multi-dimensional information and, based on the second multi-dimensional information of the modeling requester, automatically analyzes the target modeling requirements of the requester. Based on the aforementioned first multi-dimensional information and target modeling requirements, it filters matching modeling reference data from historical modeling data. Then, based on the modeling reference data and the analyzed target modeling requirements, it generates modeling control parameters using a pre-trained and converged modeling parameter generation model, and completes the target 3D model for the target planar diagram based on the modeling control parameters. Therefore, this invention enables automated 3D modeling, which improves 3D modeling efficiency. Furthermore, during the 3D modeling process, it achieves adaptive 3D modeling based on the multi-dimensional information of the planar diagram, the target modeling requirements of the requester, and the modeling control parameters generated by the modeling parameter generation model. This improves both the efficiency of 3D model generation and the matching degree between the generated 3D model and actual needs.Furthermore, the modeling control parameters generated by the training-to-convergence modeling parameter generation model can include multiple pairs of modeling control sub-parameters. Each pair further includes a modeling quality control sub-parameter and its corresponding modeling cost parameter. During actual modeling, the modeling control sub-parameters can automatically determine the target balance point between modeling quality and modeling cost, thereby selecting matching target modeling control sub-parameter pairs. 3D modeling is then completed based on the target modeling quality control sub-parameters in these pairs. This achieves an adaptive balance between modeling quality and modeling cost during 3D modeling, which is beneficial for further improving the matching degree between 3D modeling and actual modeling requirements. Additionally, during modeling, the modeling control sub-parameters can also be used to model the plane... A completeness analysis of the diagram is performed. If the analyzed completeness indicates that the planar diagram to be modeled is a fragmented planar diagram of a complete planar diagram, it can be verified and judged after the initial balance requirement points are analyzed. This helps improve the reliability of determining the balance requirement points between modeling quality and modeling cost, and thus improves the efficiency and reliability of screening modeling control sub-parameter pairs. In addition, when verifying and judging the initial balance requirement points, the positional and content weights of the fragmented planar diagrams within the complete planar diagrams are considered simultaneously. Based on the positional and content weights, the comprehensive weight of the fragmented planar diagrams is calculated, which helps improve the accuracy of the calculation of the comprehensive weight corresponding to the fragmented planar diagrams. Furthermore, if the comprehensive weight is large, then... The system first determines whether the initial balance requirement point matches the overall weighting. If they don't match, the initial balance requirement point needs to be verified, which improves the accuracy and reliability of the verification. Furthermore, if the current planar map to be modeled is fragmented, it can automatically merge with the 3D models of associated fragmented planar maps after modeling. The merging process is specifically based on the modeling relationships, improving the accuracy of merging associated 3D models. Moreover, after all the 3D models of fragmented planar maps have been merged, the system can analyze the user's operational needs for the merged 3D model based on the user's target modeling requirements, and then... Developing output control parameters improves the match between these parameters and the operational needs of the modelers. Furthermore, these parameters include not only explicit but also implicit information, enhancing both the privacy and reliability of implicit information. Additionally, analyzing target modeling needs based on the second multi-dimensional information allows consideration of direct, indirect, and derived modeling requirements, along with their respective proportions. This improves the accuracy and comprehensiveness of the target modeling analysis, which in turn enhances the accuracy and comprehensiveness of historical modeling data selection. Attached Figure Description

[0076] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0077] Figure 1 This is a flowchart illustrating a three-dimensional model generation and control method based on artificial intelligence disclosed in an embodiment of the present invention.

[0078] Figure 2 This is a schematic diagram of the structure of a three-dimensional model generation and control system based on artificial intelligence disclosed in an embodiment of the present invention;

[0079] Figure 3 This is a schematic diagram of another artificial intelligence-based 3D model generation and control system disclosed in an embodiment of the present invention;

[0080] Figure 4 This is a schematic diagram of another artificial intelligence-based three-dimensional model generation and control system disclosed in an embodiment of the present invention. Detailed Implementation

[0081] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0082] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0083] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0084] This invention discloses an artificial intelligence-based method and system for generating and controlling 3D models. It enables automated 3D modeling, improving efficiency. Furthermore, during the 3D modeling process, it achieves adaptive 3D modeling based on multi-dimensional information from planar diagrams, the user's target modeling needs, and the modeling control parameters generated by the modeling parameter generation model. This improves both the efficiency of 3D model generation and the degree of matching between the generated 3D model and actual requirements. Detailed explanations follow.

[0085] Example 1

[0086] Please see Figure 1 , Figure 1 This is a flowchart illustrating a three-dimensional model generation and control method based on artificial intelligence disclosed in an embodiment of the present invention. Figure 1 The method shown is applied to a 3D model generation and control system, which can be set up locally or in the cloud; this embodiment of the invention does not impose any limitations. Figure 1 As shown, the AI-based 3D model generation and control method may include the following steps:

[0087] 101. Determine the target planar image to be modeled, and analyze the target planar image to obtain the first multi-dimensional information, which includes multiple image information corresponding to the target planar image.

[0088] In this embodiment of the invention, the multiple image information corresponding to the target plan view may include the size information, viewpoint information, image content information, completeness, edge information, and the source of the target plan view (hand-drawn, photographed, etc.). Optionally, the image content information corresponding to the target plan view may include at least the image content corresponding to the main target object and the image content corresponding to the secondary target object. The main target object is the actual modeling object (such as a building), and the secondary target object is an auxiliary object that has a reference relationship with the modeling object, such as a traffic light or green belt next to a building.

[0089] 102. Obtain the second multi-dimensional information corresponding to the modeling requester, and analyze the modeling requester's target modeling requirements for the target planar diagram based on the second multi-dimensional information.

[0090] In this embodiment of the invention, the second multi-dimensional information corresponding to the modeling requester includes the modeling requester's identity information, the modeling request triggering timing information, the modeling request triggering scenario, and the modeling request triggering reference factor, etc., which are not limited in this embodiment of the invention.

[0091] 103. Based on the first multi-dimensional information and the target modeling requirements, select modeling reference data that matches the target modeling requirements from historical modeling data.

[0092] In this embodiment of the invention, historical modeling data includes historically modeled 3D models, historical modeling control parameters of historical 3D models, historical modeling requirements corresponding to historical 3D models, multi-dimensional planar plot information corresponding to historical 3D models, adjustment records after historical 3D models are modeled, direct modeling costs after historical 3D models are modeled, and indirect modeling costs incurred in adjusting historical 3D models after modeling. This embodiment of the invention does not limit the scope of the data.

[0093] 104. Based on the modeling reference data and target modeling requirements, and combined with the pre-trained and converged modeling parameters, generate the modeling control parameters corresponding to the target planar diagram.

[0094] In this embodiment of the invention, the modeling parameter generation model is obtained by training the initial modeling parameter generation model using historical modeling data as training sample data. The initial modeling parameter generation model can be composed of 3D-GAN, VAEs, Transformers, and GNNs, where 3D-GAN is used to generate 3D shapes, VAEs are used for parameter optimization, Transformers are used for structured parameter generation, and GNNs are used for mesh optimization.

[0095] 105. Perform 3D modeling operations on the target planar diagram based on the modeling control parameters to obtain the target 3D model corresponding to the target planar diagram.

[0096] It is evident that implementing the method described in the embodiments of the present invention can achieve automated modeling of three-dimensional models, which is beneficial to improving the efficiency of three-dimensional modeling. At the same time, in the process of three-dimensional modeling, adaptive three-dimensional modeling can be achieved based on the multi-dimensional information of the planar diagram, the target modeling requirements of the modeling client, and the modeling control parameters generated by the modeling parameter generation model. This improves the efficiency of three-dimensional model generation while also increasing the matching degree between the generated three-dimensional model and the actual requirements.

[0097] In an optional embodiment, the above-mentioned modeling control parameters include at least one pair of modeling control sub-parameters, each pair of modeling control sub-parameters including at least a modeling quality control sub-parameter and a modeling cost parameter (such as a modeling time cost parameter, a modeling resource consumption cost parameter, etc.) corresponding to the modeling quality control sub-parameter. In this optional embodiment, the above-mentioned process of performing a 3D modeling operation on the target planar map based on the modeling control parameters to obtain a target 3D model corresponding to the target planar map may include:

[0098] Based on the target modeling requirements and historical modeling data, determine the target balance point between modeling quality and modeling cost for this 3D modeling.

[0099] Based on the target balance requirement point, select the target modeling control sub-parameter pair that best matches the balance requirement point from the modeling control parameters;

[0100] Based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pair, perform 3D modeling operations on the target planar diagram to obtain the target 3D model corresponding to the target planar diagram.

[0101] Optionally, modeling quality control sub-parameters may include modeling geometry parameters, modeling texture / material parameters, physical / animation parameters, topology optimization parameters, semantic / label parameters, etc.

[0102] As can be seen, the modeling control parameters generated by the modeling parameter generation model based on the training to convergence in this optional embodiment may include multiple modeling control sub-parameter pairs. Each modeling control sub-parameter pair further includes a modeling quality control sub-parameter and its corresponding modeling cost parameter. In actual modeling, the target demand balance point between modeling quality and modeling cost can be automatically determined, thereby filtering out matching target modeling control sub-parameter pairs, and completing 3D modeling based on the target modeling quality control sub-parameter in the target modeling control sub-parameter pair. In this way, an adaptive balance between modeling quality and modeling cost is achieved in 3D modeling, which is conducive to further improving the matching degree between 3D modeling and actual modeling requirements.

[0103] In another optional embodiment, when the completeness of the target planar image included in the first multi-dimensional information is used to indicate whether the target planar image is a fragmented planar image obtained after image segmentation of a certain complete planar image. In this optional embodiment, the above-mentioned determination of the target balance requirement point between modeling quality and modeling cost corresponding to this 3D modeling based on the target modeling requirements and historical modeling data may include:

[0104] Based on the target modeling requirements and historical modeling data, determine the initial balance point between the modeling quality and modeling cost for this 3D modeling.

[0105] When the completeness indicates that the target planar map is a fragmented planar map, it is determined whether to perform a verification operation on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map. If so, the verification operation is performed on the initial balance requirement point to obtain the target balance requirement point between the modeling quality and the modeling cost corresponding to this 3D modeling.

[0106] As can be seen, this optional embodiment can also perform a completeness analysis on the planar diagram to be modeled during modeling. If the analyzed completeness indicates that the planar diagram to be modeled is a fragmented planar diagram of a complete planar diagram, it can also verify and judge the initial balance requirement point after analysis. This is beneficial to improving the reliability of determining the balance requirement point between modeling quality and modeling cost, and thus beneficial to improving the screening efficiency and screening reliability of modeling control sub-parameter pairs.

[0107] In another optional embodiment, when the completeness of the target planar map indicates that the target planar map is a fragmented planar map, the above-mentioned determination of whether to perform a verification operation on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map may include:

[0108] Analyze the positional proportions of fragmented planar diagrams within the complete planar diagram;

[0109] Analyze the proportion of target image content carried by the fragmented planar image within the complete planar image;

[0110] Calculate the overall weight of the fragmented plan view within the complete plan view based on the weight of location and content;

[0111] If the overall proportion is greater than or equal to the preset proportion threshold, it is determined whether the initial balance requirement point matches the overall proportion. If they do not match, it is determined that a verification operation needs to be performed on the initial balance requirement point.

[0112] In this embodiment of the invention, if the overall weight is large, it indicates that the fragmented planar map is more important, and when determining the balance requirement point, the modeling quality should be given priority; if the overall weight is large, it indicates that the fragmented planar map is relatively unimportant, and when determining the balance requirement point, the modeling cost should be given priority, mainly by sacrificing a certain degree of modeling quality to reduce the modeling cost.

[0113] As can be seen, this optional embodiment considers both the positional and content weights of the fragmented planar graph within the complete planar graph when verifying the initial balance requirement point. It calculates the comprehensive weight of the fragmented planar graph based on the positional and content weights, which helps improve the accuracy of the calculation of the comprehensive weight corresponding to the fragmented planar graph. Furthermore, if the comprehensive weight is large, it further determines whether the initial balance requirement point matches the comprehensive weight. If they do not match, it is determined that the initial balance requirement point needs to be verified, which helps improve the accuracy and reliability of the verification and judgment of the initial balance requirement point.

[0114] In yet another optional embodiment, the method may further include:

[0115] If the completeness indicates that the target planar map is a fragmented planar map, then after obtaining the target 3D model corresponding to the target planar map, at least one other historical 3D model corresponding to a fragmented planar map that has a modeling relationship with the target planar map is selected from the historical modeling data.

[0116] Based on the modeling relationship between each other fragmented planar map and the target planar map, a fusion operation is performed on the target 3D model and the historical 3D model corresponding to each other fragmented planar map to obtain the fused 3D model.

[0117] The modeling of relationships includes at least the positional relationships (such as adjacency) and content relationships between the target planar map and other fragmented planar maps.

[0118] As can be seen, in this optional embodiment, if the current planar view to be modeled is a fragmented planar view, then after modeling, it can automatically achieve fusion with the 3D model of the associated fragmented planar view. Moreover, the fusion is specifically performed according to the modeling association relationship, which helps to improve the fusion accuracy of the associated 3D models.

[0119] In yet another optional embodiment, the method may further include:

[0120] For any obtained current fused 3D model, determine whether the current fused 3D model is the same as the current fused 3D model corresponding to the complete planar map. If so, analyze the 3D model operation requirements of the modeling user based on the target modeling requirements.

[0121] Based on the operational requirements of the 3D model, the output control parameters corresponding to the current fused 3D model are generated, and the current fused 3D model is output to the modeling user based on the output control parameters.

[0122] The output control parameters include explicit information output control parameters for the current fused model, implicit information output control parameters for the current fused model, and output triggering conditions for implicit information of the current fused model. The output triggering conditions for implicit information are used to indicate that implicit information is output based on the implicit information output control parameters when the output triggering conditions for implicit information are met. The output triggering conditions for implicit information include direct output triggering conditions and indirect output triggering conditions. Direct output triggering conditions include at least a fixed output triggering time, and indirect output triggering conditions include at least a non-fixed output triggering timing.

[0123] As can be seen, after the 3D models of all fragmented planar maps are fused, this optional embodiment can analyze the operational needs of the modeling user for the fused 3D model based on the modeling user's target modeling needs, and then generate output control parameters based on the operational needs. This helps to improve the matching degree between the output control parameters and the operational needs of the modeling user. Moreover, the output control parameters not only include explicit information output control parameters, but also implicit information output control parameters, which can improve the privacy of implicit information and ensure the reliability of the output of implicit information.

[0124] In yet another optional embodiment, the aforementioned target modeling requirements of the user requesting the target planar map based on the second multi-dimensional information analysis modeling can include:

[0125] Based on the second multi-dimensional information, we analyze the direct modeling needs of modeling users for the target planar diagram and the corresponding proportion of their first modeling needs.

[0126] Based on the second multi-dimensional information and direct modeling needs, we analyze the indirect modeling needs of modeling users for the target planar diagram and the corresponding proportion of second modeling needs.

[0127] Based on the second multi-dimensional information, direct modeling needs, and indirect modeling needs, we analyze the derived modeling needs of modeling users for the target planar diagram and the corresponding proportion of their third modeling needs.

[0128] Based on direct modeling needs, indirect modeling needs, and derived modeling needs, as well as their respective proportions, the target modeling needs of the modeling requesters for the target planar diagram are generated.

[0129] For example, the direct modeling requirement for a target floor plan could be a direct viewing requirement, while the indirect modeling requirement could be a demonstration / teaching requirement or a simulation operation requirement. Derivative modeling requirements could be performance testing requirements or educational testing requirements. If the purpose of modeling is for teaching demonstrations, the proportion of modeling requirements for direct viewing is lower than the proportion of modeling requirements for demonstration / teaching needs.

[0130] As can be seen, this optional embodiment, when analyzing target modeling requirements based on the second multi-dimensional information, can consider not only direct modeling requirements, indirect modeling requirements, and derived modeling requirements, but also the proportion of modeling requirements corresponding to the aforementioned three types of modeling requirements. This is conducive to improving the accuracy and comprehensiveness of the analysis of target modeling requirements, and further conducive to improving the accuracy and comprehensiveness of the screening of historical modeling data.

[0131] Example 2

[0132] Please see Figure 2 , Figure 2This is a schematic diagram of the structure of a three-dimensional model generation and control system based on artificial intelligence, as disclosed in an embodiment of the present invention. Wherein, Figure 2 The 3D model generation and control system shown can be set up locally or in the cloud; this embodiment of the invention does not impose any limitation. Figure 2 As shown, the system is used to execute some or all of the steps in any of the AI-based 3D model generation control methods in Embodiment 1, and the system may include:

[0133] The first analysis module 201 is used to determine the target planar image to be modeled and analyze the target planar image to obtain first multi-dimensional information, which includes multiple image information corresponding to the target planar image.

[0134] The second analysis module 202 is used to obtain the second multi-dimensional information corresponding to the modeling requester, and analyze the modeling requester's target modeling requirements for the target planar diagram based on the second multi-dimensional information.

[0135] The filtering module 203 is used to filter modeling reference data that matches the target modeling requirements from historical modeling data based on the first multi-dimensional information and the target modeling requirements.

[0136] The parameter generation module 204 is used to generate the modeling control parameters corresponding to the target planar map based on the modeling reference data and the target modeling requirements, and in combination with the pre-trained and converged modeling parameter generation model.

[0137] The modeling control module 205 is used to perform three-dimensional modeling operations on the target planar diagram based on the modeling control parameters to obtain the target three-dimensional model corresponding to the target planar diagram.

[0138] It is evident that implementation Figure 2 The described system can automate the modeling of 3D models, which is beneficial to improving the efficiency of 3D modeling. At the same time, in the process of 3D modeling, it can achieve adaptive 3D modeling based on the multi-dimensional information of the planar diagram, the target modeling requirements of the modeling client, and the modeling control parameters generated by the modeling parameter generation model. This improves the efficiency of 3D model generation and the matching degree between the generated 3D model and the actual requirements.

[0139] In an optional embodiment, the modeling control parameters include at least one pair of modeling control sub-parameters; each pair of modeling control sub-parameters includes at least a modeling quality control sub-parameter and a modeling cost parameter corresponding to the modeling quality control sub-parameter.

[0140] The modeling control module 205 performs 3D modeling operations on the target planar map based on modeling control parameters to obtain the target 3D model corresponding to the target planar map. The specific methods include:

[0141] Based on the target modeling requirements and historical modeling data, determine the target balance point between modeling quality and modeling cost for this 3D modeling.

[0142] Based on the target balance requirement point, select the target modeling control sub-parameter pair that best matches the balance requirement point from the modeling control parameters;

[0143] Based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pair, perform 3D modeling operations on the target planar diagram to obtain the target 3D model corresponding to the target planar diagram.

[0144] As can be seen, the modeling control parameters generated by the modeling parameter generation model based on the training to convergence in this optional embodiment may include multiple modeling control sub-parameter pairs. Each modeling control sub-parameter pair further includes a modeling quality control sub-parameter and its corresponding modeling cost parameter. In actual modeling, the target demand balance point between modeling quality and modeling cost can be automatically determined, thereby filtering out matching target modeling control sub-parameter pairs, and completing 3D modeling based on the target modeling quality control sub-parameter in the target modeling control sub-parameter pair. In this way, an adaptive balance between modeling quality and modeling cost is achieved in 3D modeling, which is conducive to further improving the matching degree between 3D modeling and actual modeling requirements.

[0145] In another optional embodiment, the aforementioned first multi-dimensional information includes at least the completeness of the target planar image, whereby the completeness indicates whether the target planar image is a fragmented planar image obtained after image segmentation of a complete planar image. Specifically, the modeling control module 205 determines the target balance point between modeling quality and modeling cost for this 3D modeling based on the target modeling requirements and historical modeling data, including the following methods:

[0146] Based on the target modeling requirements and historical modeling data, determine the initial balance point between the modeling quality and modeling cost for this 3D modeling.

[0147] When the completeness indicates that the target planar map is a fragmented planar map, it is determined whether to perform a verification operation on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map. If so, the verification operation is performed on the initial balance requirement point to obtain the target balance requirement point between the modeling quality and the modeling cost corresponding to this 3D modeling.

[0148] As can be seen, this optional embodiment can also perform a completeness analysis on the planar diagram to be modeled during modeling. If the analyzed completeness indicates that the planar diagram to be modeled is a fragmented planar diagram of a complete planar diagram, it can also verify and judge the initial balance requirement point after analysis. This is beneficial to improving the reliability of determining the balance requirement point between modeling quality and modeling cost, and thus beneficial to improving the screening efficiency and screening reliability of modeling control sub-parameter pairs.

[0149] In another optional embodiment, when the completeness indicates that the target planar map is a fragmented planar map, the modeling control module 205 determines whether a verification operation needs to be performed on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map. The specific methods include:

[0150] Analyze the positional proportions of fragmented planar diagrams within the complete planar diagram;

[0151] Analyze the proportion of target image content carried by the fragmented planar image within the complete planar image;

[0152] Calculate the overall weight of the fragmented plan view within the complete plan view based on the weight of location and content;

[0153] If the overall proportion is greater than or equal to the preset proportion threshold, it is determined whether the initial balance requirement point matches the overall proportion. If they do not match, it is determined that a verification operation needs to be performed on the initial balance requirement point.

[0154] As can be seen, this optional embodiment considers both the positional and content weights of the fragmented planar graph within the complete planar graph when verifying the initial balance requirement point. It calculates the comprehensive weight of the fragmented planar graph based on the positional and content weights, which helps improve the accuracy of the calculation of the comprehensive weight corresponding to the fragmented planar graph. Furthermore, if the comprehensive weight is large, it further determines whether the initial balance requirement point matches the comprehensive weight. If they do not match, it is determined that the initial balance requirement point needs to be verified, which helps improve the accuracy and reliability of the verification and judgment of the initial balance requirement point.

[0155] In yet another alternative embodiment, such as Figure 3 As shown, the system may also include:

[0156] The model fusion module 206 is used to, if the completeness representation of the target planar map is a fragmented planar map, after obtaining the target 3D model corresponding to the target planar map, select at least one historical 3D model corresponding to another fragmented planar map that has a modeling relationship with the target planar map from the historical modeling data; and, based on the modeling relationship between each other fragmented planar map and the target planar map, perform a fusion operation on the target 3D model and the historical 3D model corresponding to each other fragmented planar map to obtain the fused 3D model.

[0157] As can be seen, in this optional embodiment, if the current planar view to be modeled is a fragmented planar view, then after modeling, it can also automatically achieve fusion with the 3D model of the associated fragmented planar view. Moreover, the fusion is specifically performed according to the modeling relationship, which is beneficial to improving the fusion accuracy of the associated 3D models.

[0158] In yet another alternative embodiment, such as Figure 3 As shown, the system may also include:

[0159] The model output control module 207 is used to determine whether the current fused 3D model is the same as the current fused 3D model corresponding to the complete planar view for any obtained current fused 3D model. If so, it analyzes the 3D model operation requirements of the modeling user based on the target modeling requirements; and generates the output control parameters corresponding to the current fused 3D model according to the 3D model operation requirements, and outputs the current fused 3D model to the modeling user according to the output control parameters.

[0160] The output control parameters include explicit information output control parameters for the current fused model, implicit information output control parameters for the current fused model, and output triggering conditions for implicit information of the current fused model. The output triggering conditions for implicit information are used to indicate that implicit information is output based on the implicit information output control parameters when the output triggering conditions for implicit information are met. The output triggering conditions for implicit information include direct output triggering conditions and indirect output triggering conditions. Direct output triggering conditions include at least a fixed output triggering time, and indirect output triggering conditions include at least a non-fixed output triggering timing.

[0161] As can be seen, after the 3D models of all fragmented planar maps are fused, this optional embodiment can analyze the operational needs of the modeling user for the fused 3D model based on the modeling user's target modeling needs, and then generate output control parameters based on the operational needs. This helps to improve the matching degree between the output control parameters and the operational needs of the modeling user. Moreover, the output control parameters not only include explicit information output control parameters, but also implicit information output control parameters, which can improve the privacy of implicit information and ensure the reliability of the output of implicit information.

[0162] In yet another optional embodiment, the second analysis module 102 analyzes and models the target modeling needs of the target planar map based on the second multi-dimensional information, specifically in the following ways:

[0163] Based on the second multi-dimensional information, we analyze the direct modeling needs of modeling users for the target planar diagram and the corresponding proportion of their first modeling needs.

[0164] Based on the second multi-dimensional information and direct modeling needs, we analyze the indirect modeling needs of modeling users for the target planar diagram and the corresponding proportion of second modeling needs.

[0165] Based on the second multi-dimensional information, direct modeling needs, and indirect modeling needs, we analyze the derived modeling needs of modeling users for the target planar diagram and the corresponding proportion of their third modeling needs.

[0166] Based on direct modeling needs, indirect modeling needs, and derived modeling needs, as well as their respective proportions, the target modeling needs of the modeling requesters for the target planar diagram are generated.

[0167] As can be seen, this optional embodiment, when analyzing target modeling requirements based on the second multi-dimensional information, can consider not only direct modeling requirements, indirect modeling requirements, and derived modeling requirements, but also the proportion of modeling requirements corresponding to the aforementioned three types of modeling requirements. This is conducive to improving the accuracy and comprehensiveness of the analysis of target modeling requirements, and further conducive to improving the accuracy and comprehensiveness of the screening of historical modeling data.

[0168] Example 3

[0169] Please see Figure 4 , Figure 4 This is a schematic diagram of another artificial intelligence-based 3D model generation and control system disclosed in an embodiment of the present invention. Wherein, Figure 4 The described system can be set up locally or in the cloud; this invention does not limit this. Figure 4 As shown, the system may include:

[0170] Memory 301 storing executable program code;

[0171] Processor 302 coupled to memory 301;

[0172] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in any of the artificial intelligence-based 3D model generation and control methods described in Embodiment 1.

[0173] Example 4

[0174] This invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute steps in any of the artificial intelligence-based 3D model generation and control methods described in Embodiment 1.

[0175] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0176] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0177] Finally, it should be noted that the artificial intelligence-based three-dimensional model generation and control method and system disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating and controlling 3D models based on artificial intelligence, characterized in that, The method includes: A target planar image to be modeled is determined, and the target planar image is analyzed to obtain first multi-dimensional information, which includes multiple image information corresponding to the target planar image; Obtain second multi-dimensional information corresponding to the modeling requester, the second multi-dimensional information including the modeling requester's identity information, the modeling request triggering timing information, the modeling request triggering scenario, and the modeling request triggering reference factor; and analyze the modeling requester's target modeling needs for the target planar map based on the second multi-dimensional information. Based on the first multi-dimensional information and the target modeling requirements, modeling reference data that matches the target modeling requirements is selected from historical modeling data; Based on the modeling reference data and the target modeling requirements, and combined with the modeling parameter generation model that has been pre-trained to convergence, the modeling control parameters corresponding to the target planar diagram are generated. Based on the modeling control parameters, a three-dimensional modeling operation is performed on the target plan view to obtain the target three-dimensional model corresponding to the target plan view; The step of analyzing the modeling needs of the modeling requester for the target planar diagram based on the second multi-dimensional information includes: Based on the second multi-dimensional information, analyze the direct modeling needs of the modeling requesters for the target plan and the corresponding proportion of the first modeling needs; Based on the second multi-dimensional information and the direct modeling requirements, analyze the indirect modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of the second modeling requirements; Based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements, the derivative modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of their third modeling requirements are analyzed. Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements, and their respective proportions, the target modeling requirements of the modeling requester for the target plan are generated.

2. The artificial intelligence-based 3D model generation and control method according to claim 1, characterized in that, The modeling control parameters include at least one pair of modeling control sub-parameters; each pair of modeling control sub-parameters includes at least a modeling quality control sub-parameter and a modeling cost parameter corresponding to the modeling quality control sub-parameter. The step of performing a 3D modeling operation on the target planar map based on the modeling control parameters to obtain the target 3D model corresponding to the target planar map includes: Based on the target modeling requirements and the historical modeling data, determine the target balance point between modeling quality and modeling cost for this 3D modeling. Based on the target balance requirement point, select the target modeling control sub-parameter pair that has the highest matching degree with the balance requirement point from the modeling control parameters; Based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pair, a 3D modeling operation is performed on the target planar diagram to obtain the target 3D model corresponding to the target planar diagram.

3. The artificial intelligence-based 3D model generation and control method according to claim 2, characterized in that, The first multi-dimensional information includes at least the completeness of the target planar image, wherein the completeness is used to indicate whether the target planar image is a fragmented planar image obtained after image segmentation of a certain complete planar image; The step of determining the target balance point between modeling quality and modeling cost for this 3D modeling based on the target modeling requirements and the historical modeling data includes: Based on the target modeling requirements and the historical modeling data, determine the initial balance point between the modeling quality and modeling cost for this 3D modeling. When the completeness indicates that the target planar map is a fragmented planar map, it is determined whether a verification operation needs to be performed on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map. If so, a verification operation is performed on the initial balance requirement point to obtain the target balance requirement point between modeling quality and modeling cost corresponding to this 3D modeling.

4. The artificial intelligence-based 3D model generation and control method according to claim 3, characterized in that, When the completeness indicates that the target planar map is a fragmented planar map, the step of determining whether to perform a verification operation on the initial balance requirement point based on the third multi-dimensional information corresponding to the fragmented planar map includes: Analyze the positional weight of the fragmented planar diagram within the complete planar diagram; Analyze the proportion of the target image content carried by the fragmented planar image in the complete planar image; Based on the location weight and the content weight, calculate the overall weight of the fragmented planar map in the complete planar map; If the overall proportion is greater than or equal to a preset proportion threshold, it is determined whether the initial balance requirement point matches the overall proportion. If they do not match, it is determined that a verification operation needs to be performed on the initial balance requirement point.

5. The artificial intelligence-based 3D model generation and control method according to claim 3 or 4, characterized in that, The method further includes: If the completeness indicates that the target planar map is a fragmented planar map, then after obtaining the target 3D model corresponding to the target planar map, at least one other historical 3D model corresponding to a fragmented planar map that has a modeling relationship with the target planar map is selected from the historical modeling data. Based on the modeling association between each of the other fragmented planar maps and the target planar map, a fusion operation is performed on the target 3D model and the historical 3D model corresponding to each of the other fragmented planar maps to obtain the fused 3D model.

6. The artificial intelligence-based 3D model generation and control method according to claim 5, characterized in that, The method further includes: For any obtained current fused 3D model, determine whether the current fused 3D model is the current fused 3D model corresponding to the complete planar view. If so, analyze the 3D model operation requirements corresponding to the modeling user based on the target modeling requirements. Based on the operational requirements of the 3D model, output control parameters corresponding to the current fused 3D model are generated, and the current fused 3D model is output to the modeling user based on the output control parameters. The output control parameters include explicit information output control parameters for the current fused model, implicit information output control parameters for the current fused model, and output triggering conditions for implicit information of the current fused model. The output triggering conditions for implicit information indicate that the implicit information is output based on the implicit information output control parameters when the output triggering conditions for implicit information are met. The output triggering conditions for implicit information include direct output triggering conditions and indirect output triggering conditions. The direct output triggering conditions include at least a fixed output triggering time, and the indirect output triggering conditions include at least a non-fixed output triggering timing.

7. The artificial intelligence-based three-dimensional model generation and control method according to any one of claims 1-4 and 6, characterized in that, The analysis of the modeling needs of the modeling requester for the target planar diagram based on the second multi-dimensional information includes: Based on the second multi-dimensional information, analyze the direct modeling needs of the modeling requesters for the target plan and the corresponding proportion of the first modeling needs; Based on the second multi-dimensional information and the direct modeling requirements, analyze the indirect modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of the second modeling requirements; Based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements, the derivative modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of their third modeling requirements are analyzed. Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements, and their respective proportions, the target modeling requirements of the modeling requester for the target plan are generated.

8. A three-dimensional model generation and control system based on artificial intelligence, characterized in that, The system includes: The first analysis module is used to determine the target planar image to be modeled and analyze the target planar image to obtain first multi-dimensional information, the first multi-dimensional information including multiple image information corresponding to the target planar image; The second analysis module is used to obtain the second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requester's target modeling needs for the target planar map based on the second multi-dimensional information. The second multi-dimensional information includes the modeling requester's identity information, the modeling request triggering timing information, the modeling request triggering scenario, and the modeling request triggering reference factor. The filtering module is used to filter modeling reference data that matches the target modeling requirements from historical modeling data based on the first multi-dimensional information and the target modeling requirements. The parameter generation module is used to generate the modeling control parameters corresponding to the target planar map based on the modeling reference data and the target modeling requirements, and in combination with the pre-trained and converged modeling parameter generation model. The modeling control module is used to perform a three-dimensional modeling operation on the target planar diagram based on the modeling control parameters, so as to obtain a target three-dimensional model corresponding to the target planar diagram; The second analysis module analyzes the modeling needs of the modeling requester for the target planar diagram based on the second multi-dimensional information in the following specific ways: Based on the second multi-dimensional information, analyze the direct modeling needs of the modeling requesters for the target plan and the corresponding proportion of the first modeling needs; Based on the second multi-dimensional information and the direct modeling requirements, analyze the indirect modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of the second modeling requirements; Based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements, the derivative modeling requirements of the modeling requesters for the target planar diagram and the corresponding proportion of their third modeling requirements are analyzed. Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements, and their respective proportions, the target modeling requirements of the modeling requester for the target plan are generated.

9. A three-dimensional model generation and control system based on artificial intelligence, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to perform the steps in the artificial intelligence-based 3D model generation and control method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, execute the steps of the artificial intelligence-based 3D model generation control method as described in any one of claims 1-7.

Images