Three-dimensional model generation control method and system based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a three-dimensional model generation control method and system based on artificial intelligence, and the method comprises the steps: analyzing a to-be-modeled target plane graph to obtain first multi-dimensional information, obtaining second multi-dimensional information corresponding to a modeling demander, analyzing a target modeling demand of the modeling demander for the target planar graph based on the second multi-dimensional information; according to the first multi-dimensional information and a target modeling demand, screening modeling reference data matched with the target modeling demand from historical modeling data; generating a model according to the modeling reference data and the target modeling requirement in combination with a modeling parameter generation model which is trained to be converged in advance, and generating a modeling control parameter corresponding to the target plane graph; and performing three-dimensional modeling operation on the target planar graph based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target planar graph. Therefore, the matching degree of the generated three-dimensional model and the actual demand can be improved while the generation efficiency of the three-dimensional model is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a three-dimensional model generation control method and system based on artificial intelligence. Background Art

[0002] Due to its advantage of being able to display objects intuitively from multiple angles, three-dimensional models have been widely used in many key industries, such as the medical industry and the construction industry. Three-dimensional models can help relevant personnel better understand the structure and form of related objects (such as a building or a part of a person's body).

[0003] In practical applications, traditional 3D model generation relies primarily on manual drawing by cartographers based on collected data. This method relies on the cartographer's experience and the accuracy and comprehensiveness of the collected data, resulting in both low efficiency and reliability in 3D model generation. With the advent of intelligent tools, cartographers can now use them to generate 3D models. While this method improves the efficiency and reliability of 3D model generation to a certain extent compared to manual drawing, it is limited by the drawing capabilities of existing intelligent tools, making it difficult to ensure that the generated 3D models match actual needs.

[0004] It can be seen that it is particularly important to improve the matching degree between the generated 3D model and actual needs while improving the efficiency of 3D model generation. Summary of the Invention

[0005] The present invention provides a three-dimensional model generation control method and system based on artificial intelligence, which can improve the efficiency of three-dimensional model generation while improving the matching degree between the generated three-dimensional model and actual needs.

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

[0007] The method comprises:

[0008] Determining a target plane map to be modeled, and analyzing the target plane map to obtain first multi-dimensional information, where the first multi-dimensional information includes a plurality of image information corresponding to the target plane map;

[0009] Acquire second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirement of the modeling requester for the target plan based on the second multi-dimensional information;

[0010] screening, from historical modeling data, modeling reference data that matches the target modeling requirement based on the first multi-dimensional information and the target modeling requirement;

[0011] Generate modeling control parameters corresponding to the target plan view based on the modeling reference data and the target modeling requirements, and in combination with a modeling parameter generation model that has been pre-trained to convergence;

[0012] A three-dimensional modeling operation is performed on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image.

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

[0014] The performing of a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image includes:

[0015] Determining a target balance point between modeling quality and modeling cost corresponding to the current three-dimensional modeling based on the target modeling requirements and the historical modeling data;

[0016] According to the target balancing demand point, selecting a target modeling control sub-parameter pair with the highest matching degree with the balancing demand point from the modeling control parameters;

[0017] A three-dimensional modeling operation is performed on the target plane image according to the target modeling quality control sub-parameter in the target modeling control sub-parameter pair to obtain a target three-dimensional model corresponding to the target plane image.

[0018] As an optional implementation manner, in the first aspect of the present invention, the first multi-dimensional information includes at least the completeness of the target plan view, where the completeness is used to indicate whether the target plan view is a fragmented plan view obtained by performing image segmentation on a complete plan view;

[0019] The step of determining the target balance point between modeling quality and modeling cost corresponding to the current three-dimensional modeling based on the target modeling requirement and the historical modeling data includes:

[0020] Determining an initial balance point between modeling quality and modeling cost corresponding to the current 3D modeling based on the target modeling requirements and the historical modeling data;

[0021] When the completeness indicates that the target plan view is the fragmented plan view, it is determined whether it is necessary to perform a verification operation on the initial balance demand point based on the third multi-dimensional information corresponding to the fragmented plan view. If so, a verification operation is performed on the initial balance demand point to obtain the target balance demand point between the modeling quality and modeling cost corresponding to this three-dimensional modeling.

[0022] As an optional implementation manner, in the first aspect of the present invention, when the completeness indicates that the target plan view is the fragmented plan view, the determining whether it is necessary to perform a verification operation on the initial balancing demand point based on the third multi-dimensional information corresponding to the fragmented plan view includes:

[0023] Analyze the position proportion of the fragmented plan view in the complete plan view;

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

[0025] Calculating the comprehensive weight of the fragmented plan view in the complete plan view according to the position weight and the content weight;

[0026] If the comprehensive proportion is greater than or equal to the preset proportion threshold, it is determined whether the initial balance demand point matches the comprehensive proportion; if not, it is determined that a verification operation needs to be performed on the initial balance demand point.

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

[0028] If the completeness indicates that the target plan view is the fragmented plan view, after obtaining the target three-dimensional model corresponding to the target plan view, screening from the historical modeling data at least one historical three-dimensional model corresponding to another fragmented plan view that has a modeling association relationship with the target plan view;

[0029] Based on the modeling association relationship between each of the other fragmented plan views and the target plan view, a fusion operation is performed on the target three-dimensional model and the historical three-dimensional model corresponding to each of the other fragmented plan views to obtain a fused three-dimensional model.

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

[0031] For any currently fused three-dimensional model obtained, determining whether the currently fused three-dimensional model is the currently fused three-dimensional model corresponding to the complete plan view; if so, analyzing the corresponding three-dimensional model operation requirements of the modeling requester based on the target modeling requirements;

[0032] generating output control parameters corresponding to the current fused three-dimensional model according to the three-dimensional model operation requirements, and outputting the current fused three-dimensional model to the modeling requester according to the output control parameters;

[0033] Among them, 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 trigger conditions for the implicit information of the current fused model; the output trigger conditions of the implicit information are used to indicate that the implicit information is output based on the implicit information output control parameters when the output trigger conditions of the implicit information are met; the output trigger conditions of the implicit information include direct output trigger conditions and indirect output trigger conditions, the direct output trigger conditions at least include a fixed output trigger moment, and the indirect output trigger conditions at least include a non-fixed output trigger moment.

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

[0035] Based on the second multi-dimensional information, analyzing the direct modeling requirements of the modeling requester for the target plan and the proportion of the corresponding first modeling requirements;

[0036] Based on the second multi-dimensional information and the direct modeling requirements, analyzing the indirect modeling requirements of the modeling requester for the target plan and the corresponding proportion of the second modeling requirements;

[0037] Analyzing the derived modeling requirements of the modeling requester for the target plan and the proportion of the corresponding third modeling requirements based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements;

[0038] Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements and their corresponding modeling requirement ratios, a target modeling requirement of the modeling demander for the target plan is generated.

[0039] A second aspect of the present invention discloses a three-dimensional model generation control system based on artificial intelligence, the system comprising:

[0040] A first analysis module is configured to determine a target plane diagram to be modeled, and analyze the target plane diagram to obtain first multi-dimensional information, wherein the first multi-dimensional information includes a plurality of image information corresponding to the target plane diagram;

[0041] A second analysis module is configured to obtain second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirement of the modeling requester for the target plan based on the second multi-dimensional information;

[0042] a screening module, configured to screen modeling reference data that matches the target modeling requirement from the historical modeling data based on the first multi-dimensional information and the target modeling requirement;

[0043] A parameter generation module, configured to generate modeling control parameters corresponding to the target plan view based on the modeling reference data and the target modeling requirements, and in combination with a modeling parameter generation model that has been pre-trained to convergence;

[0044] A modeling control module is used to perform a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image.

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

[0046] The modeling control module performs a three-dimensional modeling operation on the target plane map based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane map in a specific manner including:

[0047] Determining a target balance point between modeling quality and modeling cost corresponding to the current three-dimensional modeling based on the target modeling requirements and the historical modeling data;

[0048] According to the target balancing demand point, selecting a target modeling control sub-parameter pair with the highest matching degree with the balancing demand point from the modeling control parameters;

[0049] A three-dimensional modeling operation is performed on the target plane image according to the target modeling quality control sub-parameter in the target modeling control sub-parameter pair to obtain a target three-dimensional model corresponding to the target plane image.

[0050] As an optional implementation manner, in the second aspect of the present invention, the first multi-dimensional information includes at least the completeness of the target plan view, where the completeness is used to indicate whether the target plan view is a fragmented plan view obtained by performing image segmentation on a complete plan view;

[0051] The specific manner in which the modeling control module determines the target balance point between the modeling quality and the modeling cost corresponding to the current three-dimensional modeling according to the target modeling requirement and the historical modeling data includes:

[0052] Determining an initial balance point between modeling quality and modeling cost corresponding to the current 3D modeling based on the target modeling requirements and the historical modeling data;

[0053] When the completeness indicates that the target plan view is the fragmented plan view, it is determined whether it is necessary to perform a verification operation on the initial balance demand point based on the third multi-dimensional information corresponding to the fragmented plan view. If so, a verification operation is performed on the initial balance demand point to obtain the target balance demand point between the modeling quality and modeling cost corresponding to this three-dimensional modeling.

[0054] As an optional implementation, in the second aspect of the present invention, when the completeness indicates that the target plan is the fragmented plan, the modeling control module determines whether it is necessary to perform a verification operation on the initial balancing demand point based on the third multi-dimensional information corresponding to the fragmented plan, and the specific manner includes:

[0055] Analyze the position proportion of the fragmented plan view in the complete plan view;

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

[0057] Calculating the comprehensive weight of the fragmented plan view in the complete plan view according to the position weight and the content weight;

[0058] If the comprehensive proportion is greater than or equal to the preset proportion threshold, it is determined whether the initial balance demand point matches the comprehensive proportion; if not, it is determined that a verification operation needs to be performed on the initial balance demand point.

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

[0060] A model fusion module is used to, if the completeness indicates that the target plan view is the fragmented plan view, then after obtaining the target three-dimensional model corresponding to the target plan view, screen out from the historical modeling data at least one historical three-dimensional model corresponding to other fragmented plan views that has a modeling association relationship with the target plan view; and, based on the modeling association relationship between each of the other fragmented plan views and the target plan view, perform a fusion operation on the target three-dimensional model and the historical three-dimensional model corresponding to each of the other fragmented plan views to obtain a fused three-dimensional model.

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

[0062] a model output control module, configured to determine, for any currently fused three-dimensional model obtained, whether the currently fused three-dimensional model is the currently fused three-dimensional model corresponding to the complete plan view; and if so, analyze the corresponding three-dimensional model operation requirements of the modeling user based on the target modeling requirements; and, based on the three-dimensional model operation requirements, generate output control parameters corresponding to the currently fused three-dimensional model, and output the currently fused three-dimensional model to the modeling user based on the output control parameters;

[0063] Among them, 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 trigger conditions for the implicit information of the current fused model; the output trigger conditions of the implicit information are used to indicate that the implicit information is output based on the implicit information output control parameters when the output trigger conditions of the implicit information are met; the output trigger conditions of the implicit information include direct output trigger conditions and indirect output trigger conditions, the direct output trigger conditions at least include a fixed output trigger moment, and the indirect output trigger conditions at least include a non-fixed output trigger moment.

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

[0065] Based on the second multi-dimensional information, analyzing the direct modeling requirements of the modeling requester for the target plan and the proportion of the corresponding first modeling requirements;

[0066] Based on the second multi-dimensional information and the direct modeling requirements, analyzing the indirect modeling requirements of the modeling requester for the target plan and the corresponding proportion of the second modeling requirements;

[0067] Analyzing the derived modeling requirements of the modeling requester for the target plan and the proportion of the corresponding third modeling requirements based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements;

[0068] Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements and their corresponding modeling requirement ratios, a target modeling requirement of the modeling demander for the target plan is generated.

[0069] A third aspect of the present invention discloses another artificial intelligence-based three-dimensional model generation control system, the system comprising:

[0070] a memory storing 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 any one of the artificial intelligence-based three-dimensional model generation control methods described in the first aspect of the present invention.

[0073] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in any of the artificial intelligence-based three-dimensional model generation control methods described in the first aspect of the present invention.

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

[0075] The present invention can realize three-dimensional modeling control for a plane map. Specifically, after determining the target plane map to be modeled, the first multi-dimensional information corresponding thereto is automatically analyzed, and based on the second multi-dimensional information corresponding to the modeling demander, the target modeling requirements of the modeling demander are automatically analyzed. Based on the aforementioned first multi-dimensional information and the target modeling requirements, matching modeling reference data are screened out from the historical modeling data; then, based on the modeling reference data and the analyzed target modeling requirements, the modeling control parameters are generated in combination with the modeling parameter generation model that has been pre-trained to convergence, and the target three-dimensional model for the target plane map is completed based on the modeling control parameters. It can be seen that the present invention can realize the automated modeling of three-dimensional models, which is conducive 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 realized based on the multi-dimensional information of the plane map, the target modeling requirements of the modeling demander, and the modeling control parameters generated by the modeling parameter generation model. This improves the efficiency of three-dimensional model generation while improving the matching degree between the generated three-dimensional model and the actual requirements.In addition, the modeling control parameters generated based on the modeling parameter generation model trained to convergence 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, which can automatically determine the target demand balance point between modeling quality and modeling cost during actual modeling, and then screen out the matching target modeling control sub-parameter pair, and complete the three-dimensional modeling based on the target modeling quality control sub-parameter in the target modeling control sub-parameter pair, thus achieving an adaptive balance between modeling quality and modeling cost during three-dimensional modeling, which is conducive to further improving the matching degree between three-dimensional modeling and actual modeling needs; in addition, during modeling, the plane of the modeling can also be treated The completeness analysis of the diagram is performed. If the analyzed completeness indicates that the plan to be modeled is a fragmented plan of a complete plan, it can also be verified and judged after the initial balance demand point is analyzed, which is beneficial to improving the reliability of determining the balance demand point between modeling quality and modeling cost, and thus beneficial to improving the screening efficiency and screening reliability of modeling control sub-parameter pairs; in addition, when verifying and judging the initial balance demand point, the position proportion and content proportion of the fragmented plan in the complete plan are considered at the same time, and the comprehensive proportion of the fragmented plan is calculated based on the position proportion and content proportion, which is beneficial to improving the calculation accuracy of the comprehensive proportion corresponding to the fragmented plan, and if the comprehensive proportion is large, then In the first step, it is determined whether the initial balance demand point matches the comprehensive proportion. If it does not match, it is determined that the initial balance demand point needs to be verified, which is beneficial to improving the accuracy and reliability of the verification judgment of the initial balance demand point; in addition, if the current plan to be modeled is a fragmented plan, it can automatically realize the fusion between the three-dimensional model of the associated fragmented plan after modeling, and the fusion is specifically carried out according to the modeling association relationship, which is beneficial to improve the fusion accuracy of the associated three-dimensional model; in addition, after the three-dimensional models of all fragmented plan views are fused, it is also possible to analyze the modeling demander's target modeling needs for the operation requirements of the fused three-dimensional model based on the operation requirements, and then analyze the operation requirements of the modeling demander based on the operation requirements. Generating output control parameters is beneficial to improving the matching degree between the output control parameters and the operational requirements of the modeling demanders, and the output control parameters include not only explicit information output control parameters, but also implicit information output control parameters, which can not only improve the privacy of implicit information, but also ensure the output reliability of implicit information; in addition, when analyzing the target modeling requirements based on the second multi-dimensional information, it is possible to consider not only direct modeling requirements, indirect modeling requirements and derived modeling requirements, but also the proportion of modeling requirements corresponding to the above three types of modeling requirements, which is beneficial to improving the analysis accuracy and comprehensiveness of the target modeling requirements, and further conducive to further improving the screening accuracy and comprehensiveness of historical modeling data. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0077] Figure 1 This is a flow chart of a three-dimensional model generation control method based on artificial intelligence disclosed in an embodiment of the present invention;

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

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

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

[0081] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0082] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed therein, or may optionally include other steps or elements inherent to such process, method, product, or end.

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

[0084] The present invention discloses an artificial intelligence-based 3D model generation control method and system, which can realize automated 3D modeling, thereby improving 3D modeling efficiency. Furthermore, during the 3D modeling process, adaptive 3D modeling can be achieved based on the multi-dimensional information of the plan view, the target modeling requirements of the modeler, and the modeling control parameters generated by the modeling parameter generation model. This improves the efficiency of 3D model generation while also enhancing the matching degree between the generated 3D model and actual requirements. These are described in detail below.

[0085] Example 1

[0086] See also Figure 1 , Figure 1 This is a flow chart of a method for controlling the generation of a three-dimensional model based on artificial intelligence disclosed in an embodiment of the present invention. Figure 1 The method shown is applied to a 3D model generation control system, which can be set locally or in the cloud, and the embodiment of the present invention does not limit this. Figure 1 As shown, the artificial intelligence-based three-dimensional model generation control method may include the following steps:

[0087] 101. Determine a target plan view to be modeled, and analyze the target plan view to obtain first multi-dimensional information, where the first multi-dimensional information includes a plurality of image information corresponding to the target plan view.

[0088] In an embodiment of the present invention, the multiple image information corresponding to the target plan view may include size information corresponding to the target plan view, viewing angle information corresponding to the target plan view, image content information corresponding to the target plan view, the completeness corresponding to the target plan view, image edge information corresponding to the target plan view, and the generation source of the target plan view (hand-drawn, photographed, etc.). Optionally, the image content information corresponding to the target plan view includes at least image content corresponding to the primary target object and image content corresponding to the secondary target object, where the primary 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 second multi-dimensional information corresponding to the modeling demander, and analyze the target modeling demand of the modeling demander for the target floor plan based on the second multi-dimensional information.

[0090] In an embodiment of the present invention, the second multi-dimensional information corresponding to the modeling demander includes the identity information corresponding to the modeling demander, the modeling demand triggering timing information corresponding to the modeling demander, the modeling demand triggering scenario corresponding to the modeling demander, the modeling demand triggering reference factor corresponding to the modeling demander, etc., which is not limited in the embodiment of the present invention.

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

[0092] In an embodiment of the present invention, historical modeling data includes the historical three-dimensional model that has been modeled, the historical modeling control parameters of the historical three-dimensional model, the historical modeling requirements corresponding to the historical three-dimensional model, the multi-dimensional plan view information corresponding to the historical three-dimensional model, the adjustment records after the historical three-dimensional model is modeled, the direct modeling cost after the historical three-dimensional model is modeled, the indirect modeling cost incurred for the adjustment after the historical three-dimensional model is modeled, etc., which is not limited in the embodiment of the present invention.

[0093] 104. Generate a model based on the modeling reference data and the target modeling requirements, and combine the modeling parameters that have been pre-trained to convergence to generate a model, and generate modeling control parameters corresponding to the target floor plan.

[0094] In an embodiment of the present invention, the modeling parameter generation model is obtained by training an initial modeling parameter generation model using historical modeling data as training sample data. The initial modeling parameter generation model may be composed of 3D-GAN, VAEs, Transformers, and GNNs, with 3D-GAN used for generating three-dimensional shapes, VAEs for parameter optimization, Transformers for structured parameter generation, and GNNs for mesh optimization.

[0095] 105. Perform a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image.

[0096] It can be seen that the implementation of the method described in the embodiment of the present invention can realize the automatic modeling of three-dimensional models, which is conducive to improving the efficiency of three-dimensional modeling. At the same time, in the three-dimensional modeling implementation process, adaptive three-dimensional modeling can be achieved based on the multi-dimensional information of the plan view, the target modeling requirements of the modeling demander, and the modeling control parameters generated by the modeling parameter generation model. In this way, the efficiency of three-dimensional model generation is improved while the matching degree between the generated three-dimensional model and actual needs is improved.

[0097] In an optional embodiment, the modeling control parameters include at least one modeling control sub-parameter pair, each modeling control sub-parameter pair including at least a modeling quality control sub-parameter and a modeling cost parameter corresponding to the modeling quality control sub-parameter (e.g., a modeling time cost parameter, a modeling resource consumption cost parameter, etc.). In this optional embodiment, performing a three-dimensional modeling operation on the target plan view based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plan view may include:

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

[0099] According to the target balanced demand point, the target modeling control sub-parameter pair with the highest matching degree with the balanced demand point is selected from the modeling control parameters;

[0100] A three-dimensional modeling operation is performed on the target plane image according to the target modeling quality control sub-parameters in the target modeling control sub-parameter pair to obtain a target three-dimensional model corresponding to the target plane image.

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

[0102] It can be seen that the modeling control parameters generated by the modeling parameter generation model trained to convergence in this optional embodiment may include multiple modeling control sub-parameter pairs, and each modeling control sub-parameter pair further includes a modeling quality control sub-parameter and its corresponding modeling cost parameter. During actual modeling, the target demand balance point between modeling quality and modeling cost can be automatically determined, and then matching target modeling control sub-parameter pairs can be screened out, and three-dimensional modeling can be completed based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pairs. In this way, an adaptive balance between modeling quality and modeling cost is achieved during three-dimensional modeling, which is conducive to further improving the matching degree between three-dimensional modeling and actual modeling requirements.

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

[0104] Determine the initial balance between modeling quality and modeling cost for this 3D modeling based on target modeling requirements and historical modeling data;

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

[0106] It can be seen that this optional embodiment can also perform a completeness analysis on the floor plan to be modeled during modeling. If the analyzed completeness indicates that the floor plan to be modeled is a fragmented floor plan of a complete floor plan, it can also be verified and judged after the initial balance demand point is analyzed, which is beneficial to improving the reliability of determining the balance demand point between modeling quality and modeling cost, and further beneficial to improving the screening efficiency and screening reliability of modeling control sub-parameter pairs.

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

[0108] Analyze the location ratio of the fragmented floor plan in the complete floor plan;

[0109] Analyze the proportion of the target image content carried by the fragmented plan view in the complete plan view;

[0110] Calculate the comprehensive proportion of the fragmented plan in the complete plan based on the position proportion and content proportion;

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

[0112] In the embodiment of the present invention, if the comprehensive proportion is large, it means that the fragmented plan view is more important, and when determining the balanced demand point, the modeling quality needs to be given priority; if the comprehensive proportion is large, it means that the fragmented plan view is relatively unimportant, and when determining the balanced demand point, the modeling cost needs to be given priority, mainly sacrificing a certain degree of modeling quality to reduce the modeling cost.

[0113] It can be seen that this optional embodiment, when verifying and judging the initial balance demand point, simultaneously considers the position proportion and content proportion of the fragmented plan view in the complete plan view, and calculates the comprehensive proportion of the fragmented plan view based on the position proportion and content proportion, which is beneficial to improving the calculation accuracy of the comprehensive proportion corresponding to the fragmented plan view, and if the comprehensive proportion is large, it is further judged whether the initial balance demand point matches the comprehensive proportion. If it does not match, it is determined that the initial balance demand point needs to be verified, which is beneficial to improving the verification and judgment accuracy and verification and judgment reliability of the initial balance demand point.

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

[0115] If the completeness indicates that the target plan is a fragmented plan, after obtaining the target three-dimensional model corresponding to the target plan, a historical three-dimensional model corresponding to at least one other fragmented plan that has a modeling association relationship with the target plan is screened from the historical modeling data;

[0116] Based on the modeling association relationship between each other fragmented plan view and the target plan view, a fusion operation is performed on the target three-dimensional model and the historical three-dimensional model corresponding to each other fragmented plan view to obtain a fused three-dimensional model.

[0117] The modeling association relationship at least includes a position association relationship (such as adjacent) and a content association relationship between the target plan view and other fragmented plan views.

[0118] It can be seen that in this optional embodiment, if the current plan to be modeled is a fragmented plan, it can be automatically fused with the three-dimensional model associated with the fragmented plan after modeling, and the fusion is specifically performed according to the modeling association relationship, which is conducive to improving the fusion accuracy of the associated three-dimensional model.

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

[0120] For any currently fused 3D model obtained, determine whether the currently fused 3D model is the currently fused 3D model corresponding to the complete plan view; if so, analyze the corresponding 3D model operation requirements of the modeling user based on the target modeling requirements;

[0121] According to the 3D model operation requirements, the output control parameters corresponding to the current fused 3D model are generated, and the current fused 3D model is output to the modeling demander according to the output control parameters.

[0122] Among them, 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 trigger conditions for the implicit information of the current fused model; the output trigger conditions of the implicit information are used to indicate that the implicit information is output based on the implicit information output control parameters when the output trigger conditions of the implicit information are met; the output trigger conditions of the implicit information include direct output trigger conditions and indirect output trigger conditions, the direct output trigger conditions include at least a fixed output trigger moment, and the indirect output trigger conditions include at least a non-fixed output trigger moment.

[0123] It can be seen that after the three-dimensional models of all fragmented plan views are fused, this optional embodiment can also analyze the modeling user's operational requirements for the fused three-dimensional model based on the modeling user's target modeling requirements, and then generate output control parameters based on the operational requirements, which is conducive to improving the matching degree between the output control parameters and the modeling user's operational requirements. The output control parameters not only include explicit information output control parameters, but also further include implicit information output control parameters, which can not only improve the privacy of implicit information, but also ensure the output reliability of implicit information.

[0124] In yet another optional embodiment, the target modeling requirements of the target floor plan analyzed by the modeling demander based on the second multi-dimensional information may include:

[0125] Based on the second multi-dimensional information, analyzing the direct modeling needs of the modeling demanders for the target floor plan and the corresponding proportion of the first modeling needs;

[0126] Based on the second multi-dimensional information and direct modeling needs, analyzing the indirect modeling needs of the modeling demanders for the target floor plan and the corresponding proportion of the second modeling needs;

[0127] Based on the second multi-dimensional information, direct modeling requirements and indirect modeling requirements, analyze the derived modeling requirements of the modeling demanders for the target floor plan and the corresponding proportion of the third modeling requirements;

[0128] Based on direct modeling requirements, indirect modeling requirements, derived modeling requirements and their corresponding proportions of modeling requirements, the target modeling requirements of the modeling demander for the target floor plan are generated.

[0129] For example, a direct modeling requirement for a target floor plan could be a direct viewing requirement, an indirect modeling requirement could be a demonstration teaching requirement or a simulated operation requirement, and a derived modeling requirement could be a performance testing requirement or a teaching test requirement. If the modeler's purpose is to demonstrate teaching, the proportion of modeling requirements for direct viewing is lower than the proportion for demonstration teaching requirements.

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

[0131] Example 2

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

[0133] A first analysis module 201 is configured to determine a target plan view to be modeled and analyze the target plan view to obtain first multi-dimensional information, where the first multi-dimensional information includes a plurality of image information corresponding to the target plan view;

[0134] The second analysis module 202 is configured to obtain second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirement of the modeling requester for the target plan based on the second multi-dimensional information;

[0135] A screening module 203 is configured to screen modeling reference data that matches the target modeling requirement from the historical modeling data based on the first multi-dimensional information and the target modeling requirement;

[0136] The parameter generation module 204 is used to generate the modeling control parameters corresponding to the target plan view based on the modeling reference data and the target modeling requirements, and in combination with the modeling parameters that have been pre-trained to convergence;

[0137] The modeling control module 205 is configured to perform a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image.

[0138] It can be seen that implementation Figure 2 The described system can realize the automatic modeling of three-dimensional models, which is conducive to improving the efficiency of three-dimensional modeling. At the same time, during the three-dimensional modeling implementation process, adaptive three-dimensional modeling can be realized based on the multi-dimensional information of the plan view, the target modeling requirements of the modeling demander, and the modeling control parameters generated by the modeling parameter generation model. In this way, the efficiency of three-dimensional model generation is improved while the matching degree between the generated three-dimensional model and actual needs is improved.

[0139] In an optional embodiment, the modeling control parameter includes at least one modeling control sub-parameter pair; each modeling control sub-parameter pair 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 a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image in the following specific manners:

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

[0142] According to the target balanced demand point, the target modeling control sub-parameter pair with the highest matching degree with the balanced demand point is selected from the modeling control parameters;

[0143] A three-dimensional modeling operation is performed on the target plane image according to the target modeling quality control sub-parameters in the target modeling control sub-parameter pair to obtain a target three-dimensional model corresponding to the target plane image.

[0144] It can be seen that the modeling control parameters generated by the modeling parameter generation model trained to convergence in this optional embodiment may include multiple modeling control sub-parameter pairs, and each modeling control sub-parameter pair further includes a modeling quality control sub-parameter and its corresponding modeling cost parameter. During actual modeling, the target demand balance point between modeling quality and modeling cost can be automatically determined, and then matching target modeling control sub-parameter pairs can be screened out, and three-dimensional modeling can be completed based on the target modeling quality control sub-parameters in the target modeling control sub-parameter pairs. In this way, an adaptive balance between modeling quality and modeling cost is achieved during three-dimensional modeling, which is conducive to further improving the matching degree between three-dimensional modeling and actual modeling requirements.

[0145] In another optional embodiment, the first multi-dimensional information includes at least the completeness of the target plan, which indicates whether the target plan is a fragmented plan obtained by segmenting a complete plan. Specifically, the modeling control module 205 determines the target balance between modeling quality and modeling cost for the current three-dimensional modeling based on the target modeling requirements and historical modeling data, including:

[0146] Determine the initial balance between modeling quality and modeling cost for this 3D modeling based on target modeling requirements and historical modeling data;

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

[0148] It can be seen that this optional embodiment can also perform a completeness analysis on the floor plan to be modeled during modeling. If the analyzed completeness indicates that the floor plan to be modeled is a fragmented floor plan of a complete floor plan, it can also be verified and judged after the initial balance demand point is analyzed, which is beneficial to improving the reliability of determining the balance demand point between modeling quality and modeling cost, and further 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 floor plan is a fragmented floor plan, the modeling control module 205 determines whether to perform a verification operation on the initial balancing demand point based on the third multi-dimensional information corresponding to the fragmented floor plan. The specific manner includes:

[0150] Analyze the location ratio of the fragmented floor plan in the complete floor plan;

[0151] Analyze the proportion of the target image content carried by the fragmented plan view in the complete plan view;

[0152] Calculate the comprehensive proportion of the fragmented plan in the complete plan based on the position proportion and content proportion;

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

[0154] It can be seen that this optional embodiment, when verifying and judging the initial balance demand point, simultaneously considers the position proportion and content proportion of the fragmented plan view in the complete plan view, and calculates the comprehensive proportion of the fragmented plan view based on the position proportion and content proportion, which is beneficial to improving the calculation accuracy of the comprehensive proportion corresponding to the fragmented plan view, and if the comprehensive proportion is large, it is further judged whether the initial balance demand point matches the comprehensive proportion. If it does not match, it is determined that the initial balance demand point needs to be verified, which is beneficial to improving the verification and judgment accuracy and verification and judgment reliability of the initial balance demand point.

[0155] In another optional embodiment, Figure 3 As shown, the system may further include:

[0156] The model fusion module 206 is used to, if the completeness indicates that the target plan view is a fragmented plan view, then after obtaining the target three-dimensional model corresponding to the target plan view, screen out from the historical modeling data at least one historical three-dimensional model corresponding to other fragmented plan views that has a modeling association relationship with the target plan view; and, based on the modeling association relationship between each other fragmented plan view and the target plan view, perform a fusion operation on the target three-dimensional model and the historical three-dimensional model corresponding to each other fragmented plan view to obtain a fused three-dimensional model.

[0157] It can be seen that in this optional embodiment, if the plan view to be modeled is a fragmented plan view, then after modeling, it can automatically be fused with the three-dimensional model of the associated fragmented plan view, and the fusion is specifically performed based on the modeling association relationship, which is conducive to improving the fusion accuracy of the associated three-dimensional model.

[0158] In another optional embodiment, Figure 3 As shown, the system may further include:

[0159] The model output control module 207 is configured to determine, for any currently fused 3D model obtained, whether the currently fused 3D model corresponds to the complete plan view; if so, analyze the corresponding 3D model operation requirements of the modeling user based on the target modeling requirements; and, based on the 3D model operation requirements, generate output control parameters corresponding to the currently fused 3D model, and output the currently fused 3D model to the modeling user based on the output control parameters.

[0160] Among them, 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 trigger conditions for the implicit information of the current fused model; the output trigger conditions of the implicit information are used to indicate that the implicit information is output based on the implicit information output control parameters when the output trigger conditions of the implicit information are met; the output trigger conditions of the implicit information include direct output trigger conditions and indirect output trigger conditions, the direct output trigger conditions include at least a fixed output trigger moment, and the indirect output trigger conditions include at least a non-fixed output trigger moment.

[0161] It can be seen that after the three-dimensional models of all fragmented plan views are fused, this optional embodiment can also analyze the modeling user's operational requirements for the fused three-dimensional model based on the modeling user's target modeling requirements, and then generate output control parameters based on the operational requirements, which is conducive to improving the matching degree between the output control parameters and the modeling user's operational requirements. The output control parameters not only include explicit information output control parameters, but also further include implicit information output control parameters, which can not only improve the privacy of implicit information, but also ensure the output reliability of implicit information.

[0162] In another optional embodiment, the second analysis module 102 analyzes the target modeling requirements of the target floor plan based on the second multi-dimensional information in the following manner:

[0163] Based on the second multi-dimensional information, analyzing the direct modeling needs of the modeling demanders for the target floor plan and the corresponding proportion of the first modeling needs;

[0164] Based on the second multi-dimensional information and direct modeling needs, analyzing the indirect modeling needs of the modeling demanders for the target floor plan and the corresponding proportion of the second modeling needs;

[0165] Based on the second multi-dimensional information, direct modeling requirements and indirect modeling requirements, analyze the derived modeling requirements of the modeling demanders for the target floor plan and the corresponding proportion of the third modeling requirements;

[0166] Based on direct modeling requirements, indirect modeling requirements, derived modeling requirements and their corresponding proportions of modeling requirements, the target modeling requirements of the modeling demander for the target floor plan are generated.

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

[0168] Example 3

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

[0170] A memory 301 storing executable program code;

[0171] a processor 302 coupled to the memory 301;

[0172] The processor 302 calls the executable program code stored in the memory 301 to execute any step of the artificial intelligence-based three-dimensional model generation control method described in the first embodiment.

[0173] Example 4

[0174] An embodiment of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute the steps of any one of the artificial intelligence-based three-dimensional model generation control methods described in Example 1.

[0175] The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0176] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0177] Finally, it should be noted that the artificial intelligence-based three-dimensional model generation control method and system disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A three-dimensional model generation control method based on artificial intelligence, characterized in that: The method comprises: Determining a target plane map to be modeled, and analyzing the target plane map to obtain first multi-dimensional information, where the first multi-dimensional information includes a plurality of image information corresponding to the target plane map; Acquire second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirement of the modeling requester for the target plan based on the second multi-dimensional information; screening, from historical modeling data, modeling reference data that matches the target modeling requirement based on the first multi-dimensional information and the target modeling requirement; Generate modeling control parameters corresponding to the target plan view based on the modeling reference data and the target modeling requirements, and in combination with a modeling parameter generation model that has been pre-trained to convergence; A three-dimensional modeling operation is performed on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image.

2. The artificial intelligence-based three-dimensional model generation control method according to claim 1, characterized in that: The modeling control parameter includes at least one modeling control sub-parameter pair; each of the modeling control sub-parameter pairs includes at least a modeling quality control sub-parameter and a modeling cost parameter corresponding to the modeling quality control sub-parameter; The performing of a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image includes: Determining a target balance point between modeling quality and modeling cost corresponding to the current three-dimensional modeling based on the target modeling requirements and the historical modeling data; According to the target balancing demand point, selecting a target modeling control sub-parameter pair with the highest matching degree with the balancing demand point from the modeling control parameters; A three-dimensional modeling operation is performed on the target plane image according to the target modeling quality control sub-parameter in the target modeling control sub-parameter pair to obtain a target three-dimensional model corresponding to the target plane image.

3. The artificial intelligence-based three-dimensional model generation control method according to claim 2, characterized in that: The first multi-dimensional information includes at least the completeness of the target plane image, where the completeness is used to indicate whether the target plane image is a fragmented plane image obtained by performing image segmentation on a complete plane image; The step of determining the target balance point between modeling quality and modeling cost corresponding to the current three-dimensional modeling based on the target modeling requirement and the historical modeling data includes: Determining an initial balance point between modeling quality and modeling cost corresponding to the current 3D modeling based on the target modeling requirements and the historical modeling data; When the completeness indicates that the target plan view is the fragmented plan view, it is determined whether it is necessary to perform a verification operation on the initial balance demand point based on the third multi-dimensional information corresponding to the fragmented plan view. If so, a verification operation is performed on the initial balance demand point to obtain the target balance demand point between the modeling quality and modeling cost corresponding to this three-dimensional modeling.

4. The artificial intelligence-based three-dimensional model generation control method according to claim 3, characterized in that: When the completeness indicates that the target plan view is the fragmented plan view, the determining whether it is necessary to perform a verification operation on the initial balancing demand point based on the third multi-dimensional information corresponding to the fragmented plan view includes: Analyze the position proportion of the fragmented plan view in the complete plan view; Analyze the content proportion of the target image content carried by the fragmented plan view in the complete plan view; Calculating the comprehensive weight of the fragmented plan view in the complete plan view according to the position weight and the content weight; If the comprehensive proportion is greater than or equal to the preset proportion threshold, it is determined whether the initial balance demand point matches the comprehensive proportion; if not, it is determined that a verification operation needs to be performed on the initial balance demand point.

5. The artificial intelligence-based three-dimensional model generation control method according to claim 3 or 4, characterized in that: The method further comprises: If the completeness indicates that the target plan view is the fragmented plan view, after obtaining the target three-dimensional model corresponding to the target plan view, screening from the historical modeling data at least one historical three-dimensional model corresponding to another fragmented plan view that has a modeling association relationship with the target plan view; Based on the modeling association relationship between each of the other fragmented plan views and the target plan view, a fusion operation is performed on the target three-dimensional model and the historical three-dimensional model corresponding to each of the other fragmented plan views to obtain a fused three-dimensional model.

6. The artificial intelligence-based three-dimensional model generation control method according to claim 5, characterized in that: The method further comprises: For any currently fused three-dimensional model obtained, determining whether the currently fused three-dimensional model is the currently fused three-dimensional model corresponding to the complete plan view; if so, analyzing the corresponding three-dimensional model operation requirements of the modeling requester based on the target modeling requirements; generating output control parameters corresponding to the current fused three-dimensional model according to the three-dimensional model operation requirements, and outputting the current fused three-dimensional model to the modeling requester according to the output control parameters; Among them, 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 trigger conditions for the implicit information of the current fused model; the output trigger conditions of the implicit information are used to indicate that the implicit information is output based on the implicit information output control parameters when the output trigger conditions of the implicit information are met; the output trigger conditions of the implicit information include direct output trigger conditions and indirect output trigger conditions, the direct output trigger conditions at least include a fixed output trigger moment, and the indirect output trigger conditions at least include a non-fixed output trigger moment.

7. The artificial intelligence-based three-dimensional model generation control method according to any one of claims 1 to 4 and 6, characterized in that: The analyzing the target modeling requirement of the modeling requester for the target plan based on the second multi-dimensional information includes: Based on the second multi-dimensional information, analyzing the direct modeling requirements of the modeling requester for the target plan and the proportion of the corresponding first modeling requirements; Based on the second multi-dimensional information and the direct modeling requirements, analyzing the indirect modeling requirements of the modeling requester for the target plan and the corresponding proportion of the second modeling requirements; Analyzing the derived modeling requirements of the modeling requester for the target plan and the proportion of the corresponding third modeling requirements based on the second multi-dimensional information, the direct modeling requirements, and the indirect modeling requirements; Based on the direct modeling requirements, the indirect modeling requirements, the derived modeling requirements and their corresponding modeling requirement ratios, a target modeling requirement of the modeling demander for the target plan is generated.

8. A three-dimensional model generation control system based on artificial intelligence, characterized in that: The system comprises: A first analysis module is configured to determine a target plane diagram to be modeled, and analyze the target plane diagram to obtain first multi-dimensional information, wherein the first multi-dimensional information includes a plurality of image information corresponding to the target plane diagram; A second analysis module is configured to obtain second multi-dimensional information corresponding to the modeling requester, and analyze the target modeling requirement of the modeling requester for the target plan based on the second multi-dimensional information; a screening module, configured to screen modeling reference data that matches the target modeling requirement from the historical modeling data based on the first multi-dimensional information and the target modeling requirement; A parameter generation module, configured to generate modeling control parameters corresponding to the target plan view based on the modeling reference data and the target modeling requirements, and in combination with a modeling parameter generation model that has been pre-trained to convergence; A modeling control module is used to perform a three-dimensional modeling operation on the target plane image based on the modeling control parameters to obtain a target three-dimensional model corresponding to the target plane image.

9. A three-dimensional model generation control system based on artificial intelligence, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the steps in the artificial intelligence-based three-dimensional model generation control method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores computer instructions, and when the computer instructions are called, the steps in the artificial intelligence-based three-dimensional model generation control method according to any one of claims 1 to 7 are executed.

Images