Large model three-dimensional modeling system and method based on artificial intelligence

Abstract

The invention discloses a large model three-dimensional modeling system and method based on artificial intelligence, particularly relates to the technical field of three-dimensional modeling, and comprises a large model three-dimensional modeling data acquisition module, a large model three-dimensional modeling data analysis module, a large model three-dimensional modeling data evaluation module and a large model three-dimensional modeling comprehensive analysis module. And a large model three-dimensional modeling man-machine interaction module. The large-model three-dimensional modeling data acquisition module is used for acquiring performance data for analyzing large-model three-dimensional modeling based on artificial intelligence to obtain various parameters for evaluating performance indexes of large-model three-dimensional modeling, and outputting the various parameters to the large-model three-dimensional modeling data analysis module; according to the method, the modeling efficiency parameters are analyzed, an index is obtained to measure the efficiency of the three-dimensional modeling process, various indexes in the modeling process are monitored in real time, an administrator can adjust a modeling strategy and optimize the modeling process according to the indexes, the modeling speed is increased, and resources are optimized.

Description

Technical Field

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

[0002] 3D modeling is the process of creating 3D objects through digital means. 3D models are usually composed of vertices, edges and faces, which can represent the geometric shape and structure of objects. They are widely used in game development, film production, virtual reality, medical imaging and other fields. With the rapid development of artificial intelligence technology, it is able to automatically learn and extract features from massive data, providing strong technical support for the automatic and intelligent generation, repair and optimization of 3D modeling.

[0003] Traditional 3D modeling methods often rely on 2D drawings or actual objects as references, which are inefficient, low-precision, and significantly more difficult and time-consuming to model when dealing with complex structures or fine textures, as well as high requirements for professional skills, leading to increased modeling difficulty and cost. With the development of science and technology, the demand for high-quality and efficient 3D modeling is growing, so the performance research of large-model 3D modeling systems is particularly important.

[0004] Therefore, the present invention proposes a system and method for large-model three-dimensional modeling based on artificial intelligence to solve the above problems, especially the analysis of the three-dimensional modeling performance of large models. By introducing large model technology, it can automatically mine and process large amounts of data and perform local analysis of data features, which helps to improve the automation and intelligence level of three-dimensional modeling, reduce the difficulty and cost of modeling, improve modeling efficiency, shorten modeling time, and generate models with high accuracy and authenticity, so that more people can easily participate in three-dimensional modeling, providing strong support for applications in multiple fields. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a system and method for large-scale three-dimensional modeling based on artificial intelligence to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a system for large-model three-dimensional modeling based on artificial intelligence, comprising a large-model three-dimensional modeling data acquisition module, a large-model three-dimensional modeling data analysis module, a large-model three-dimensional modeling data evaluation module, a large-model three-dimensional modeling comprehensive analysis module, and a large-model three-dimensional modeling human-computer interaction module;

[0007] The large model three-dimensional modeling data acquisition module is used to collect and analyze the performance data of the large model three-dimensional modeling based on artificial intelligence, obtain various parameters for evaluating the performance indicators of the large model three-dimensional modeling, and output the various parameters to the large model three-dimensional modeling data analysis module;

[0008] The large model three-dimensional modeling data analysis module includes a modeling efficiency index analysis unit, a model accuracy index analysis unit, a model data processing efficiency analysis unit, and a model stability and scalability index analysis unit, which are respectively used to calculate various parameters and output the corresponding calculation results to the large model three-dimensional modeling data evaluation module;

[0009] The large model three-dimensional modeling data evaluation module is used to compare the various indexes of the large model three-dimensional modeling obtained by the above data analysis module with the set values, and transmit the comparison results to the large model three-dimensional modeling comprehensive analysis module;

[0010] The large model three-dimensional modeling comprehensive analysis module is used to comprehensively analyze the performance evaluation factors of each index calculated by the above evaluation module, and transmit the comprehensive analysis results to the large model three-dimensional modeling human-computer interaction module;

[0011] The large model three-dimensional modeling human-computer interaction module is used to output the above-mentioned imported comprehensive analysis result large model three-dimensional modeling performance comprehensive index to the system administrator information terminal.

[0012] Preferably, the parameters in the large model three-dimensional modeling data acquisition module include system administrator identity authentication information, modeling efficiency parameters, model accuracy parameters, model data processing efficiency parameters, and model stability and scalability parameters, wherein the modeling efficiency parameters specifically include the number of tasks required for three-dimensional modeling, the actual completion time of the tasks, the expected fastest completion time for modeling, the expected time, the slowest time, the actual execution time of the CPU in modeling, the time when modeling is allocated to the CPU, the actual working time of the GPU in modeling, the GPU idle time, the total system memory, and the maximum value of the system lining occupied during the modeling process; the model accuracy parameters specifically include the number of texture features , texture features, the number of matched edge points, the coordinates of the model edge points, the coordinates of the predicted edge points, the actual volume of the model, and the predicted volume of the model; the model data processing efficiency parameters are specifically the end time of data loading, the start time of data loading, the expected time of data loading, the access time of the cache when hitting, the cache hit rate, the access time of the main memory when missing, the size of the original input data for modeling, and the size of the modeling completed file; the model stability and scalability parameters are specifically the average failure interval between models within one month, the average repair time, the number of model crashes within one month, the total number of model tests, the actual number of custom function points, and the expected number of custom function points.

[0013] Preferably, the model for obtaining the modeling efficiency index in the modeling efficiency index analysis unit is: Where Mei represents the modeling efficiency index, Mte represents the model building time efficiency, n represents the number of tasks required for 3D modeling, t i represents the actual completion time of the i-th task, l represents the modeling impact factor, T o Indicates the fastest time expected to complete modeling, T m represents the expected time, T p Indicates the slowest time, T o <T m <T p , and Represent the weights of the fastest time, expected time and slowest time respectively, E cpu Indicates the actual execution time of the CPU in modeling, T_et cpu Indicates the time that modeling is allocated to the CPU, Wt gpu Indicates the actual working time of GPU in modeling, Ft gpu represents GPU idle time, Sm represents the total system memory, and max(sm) represents the maximum value of the system memory occupied during the modeling process.

[0014] Preferably, the model for obtaining the model accuracy index in the model accuracy index analysis unit is: Mai=Ts×(1-OP)×Vf, wherein Mai represents the model accuracy index, Ts represents the texture similarity, m represents the number of texture features for comparison between the 3D model and the reference model, r l =(r l 1 ,r l 2 ,...,r l k ,...,r l m ), r l k represents the kth texture feature of 3D modeling, represents the kth texture feature of the reference model, represents the smaller of the two texture feature values, Op represents the model edge deviation, N represents the number of matched edge points, (x m,I ,y m,I ) represents the coordinates of the Ith edge point of the model, (x r,I ,y r,I ) represents the coordinates of the corresponding predicted edge points, Vf represents the model volume fidelity, V m Indicates the actual volume of the model, V r Represents the model predicted volume.

[0015] Preferably, the model for obtaining the model data processing efficiency index in the model data processing efficiency analysis unit is: Pei represents the model data processing efficiency, E_t represents the end time of data loading, s_t represents the start time of data loading, Elt represents the expected time of data loading, and Dcr represents the memory access efficiency. At c Indicates the access time of the cache when it hits, h indicates the cache hit rate, At m Indicates the access time of main memory when the miss occurs, Ds ori Indicates the size of the original input data for modeling, Ds yas represents the size of the modeling completed file, β1, β2, and β3 represent the influencing factors of data loading, memory access efficiency, and data compression, respectively.

[0016] Preferably, the model for obtaining the model stability and scalability index in the model stability and scalability index analysis unit is: Where Msi represents the model stability and scalability index, M represents the average failure interval of the model within one month, R represents the mean repair time, η1 represents the fault repair impact factor, η2 represents the model crash impact factor, Nc represents the number of model crashes within one month, Nt represents the total number of model tests, η3 represents the impact factor of the model supporting user-defined functions, Cfn represents the actual number of customized function points, and Cfn0 represents the expected number of customized function points.

[0017] Preferably, the data evaluation in the large model three-dimensional modeling data evaluation module includes the following steps:

[0018] Step 1: Substitute the modeling efficiency index analysis calculation result Mei obtained from the modeling efficiency index analysis unit into the formula: in represents the performance evaluation factor of the modeling efficiency index, Mei0 represents the set value;

[0019] Step 2: Substitute the model accuracy index analysis calculation result Mai obtained from the model accuracy index analysis unit into the formula: in represents the performance evaluation factor of the model accuracy index, Mai0 represents the set value;

[0020] Step 3: Substitute the model data processing efficiency index analysis calculation result Pei obtained in the model data processing efficiency analysis unit into the formula: in It represents the performance evaluation factor of the model data processing efficiency index, and Pei0 represents the set value;

[0021] Step 4: Substitute the model stability and scalability index analysis calculation result Msi obtained from the model stability and scalability index analysis unit into the formula: in It represents the performance evaluation factor of the model stability and scalability index, and Msi0 represents the set value.

[0022] Preferably, the comprehensive analysis model in the large model three-dimensional modeling comprehensive analysis module is: Among them, Mo_cpi represents the comprehensive performance index of large model 3D modeling. as well as They respectively represent the weight of each index of large model three-dimensional modeling.

[0023] A method for three-dimensional modeling of a large model based on artificial intelligence comprises the following steps:

[0024] Step 1: Analyze and collect the performance data of large model 3D modeling based on artificial intelligence to obtain various parameters for evaluating the performance indicators of large model 3D modeling;

[0025] Step 2: Based on the parameters in step 1, respectively calculate the modeling efficiency parameter, the model accuracy parameter, the model data processing efficiency parameter, and the model stability and scalability parameter to obtain the indexes of the large model three-dimensional modeling performance;

[0026] Step 3: Compare the calculation results of step 2 with the set values ​​to obtain the performance comparison results of each index of large model 3D modeling;

[0027] Step 4: Perform a comprehensive analysis based on the comparison results of step 3 to obtain comprehensive performance indicators of large-scale 3D modeling;

[0028] Step 5: Based on the comprehensive analysis results of step 4, the comprehensive performance indicators of the large model 3D modeling are displayed interactively by human-computer interaction.

[0029] Technical effects and advantages of the present invention:

[0030] 1. The present invention analyzes the modeling efficiency parameters to obtain an index to measure the efficiency of the 3D modeling process, and monitors the modeling time, computing resource consumption and other parameters in the modeling process in real time, which helps the administrator to adjust the modeling strategy according to these indexes, optimize the modeling process, and thus improve the modeling speed, optimize resource usage and improve the overall modeling quality;

[0031] 2. The present invention analyzes the model accuracy parameters to obtain an index to measure the accuracy of the large model in generating a 3D model in a 3D modeling task, which helps to evaluate the performance of the model and determine whether the model can meet specific modeling requirements, thereby helping to find out where the model is deficient and guide the model optimization work;

[0032] 3. The present invention analyzes the model data processing efficiency parameters to obtain an indicator to measure the speed and efficiency of 3D modeling in the data processing stage, which helps to improve the fluency of the modeling process and the speed of generating the final model, improve the model response speed, optimize resource utilization, support real-time modeling and indirectly improve model performance, thereby improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Embodiment 1:

[0036] See also Figure 1 As shown, the present invention provides a system for large model three-dimensional modeling based on artificial intelligence, including a large model three-dimensional modeling data acquisition module, a large model three-dimensional modeling data analysis module, a large model three-dimensional modeling data evaluation module, a large model three-dimensional modeling comprehensive analysis module, and a large model three-dimensional modeling human-computer interaction module;

[0037] The large model three-dimensional modeling data acquisition module is connected to the large model three-dimensional modeling data analysis module, the large model three-dimensional modeling data evaluation module is respectively connected to the large model three-dimensional modeling data analysis module and the large model three-dimensional modeling comprehensive analysis module, and the large model three-dimensional modeling human-computer interaction module is connected to the large model three-dimensional modeling comprehensive analysis module.

[0038] The large model three-dimensional modeling data acquisition module is used to collect and analyze the performance data of the large model three-dimensional modeling based on artificial intelligence, obtain various parameters for evaluating the performance indicators of the large model three-dimensional modeling, and output the various parameters to the large model three-dimensional modeling data analysis module;

[0039] The large model three-dimensional modeling data analysis module includes a modeling efficiency index analysis unit, a model accuracy index analysis unit, a model data processing efficiency analysis unit, and a model stability and scalability index analysis unit, which are respectively used to calculate various parameters and output the corresponding calculation results to the large model three-dimensional modeling data evaluation module;

[0040] The large model three-dimensional modeling data evaluation module is used to compare the various indexes of the large model three-dimensional modeling obtained by the above data analysis module with the set values, and transmit the comparison results to the large model three-dimensional modeling comprehensive analysis module;

[0041] The large model three-dimensional modeling comprehensive analysis module is used to comprehensively analyze the performance evaluation factors of each index calculated by the above evaluation module, and transmit the comprehensive analysis results to the large model three-dimensional modeling human-computer interaction module;

[0042] The large model three-dimensional modeling human-computer interaction module is used to output the above-mentioned imported comprehensive analysis results and the comprehensive performance indicators of the large model three-dimensional modeling to the system administrator information terminal. If the comprehensive performance indicators of the large model three-dimensional modeling are greater than the expected range, it means that the performance of the large model three-dimensional modeling is good. Otherwise, the system administrator is prompted to take timely measures to adjust the modeling strategy, optimize the modeling process, adjust the algorithm or increase the training data to improve the accuracy of the model, optimize the data processing process, and reduce the waste of resources.

[0043] In this embodiment, it should be specifically explained that the various parameters in the large model three-dimensional modeling data acquisition module include system administrator identity authentication information, modeling efficiency parameters, model accuracy parameters, model data processing efficiency parameters, and model stability and scalability parameters, wherein the modeling efficiency parameters are specifically the number of tasks required for three-dimensional modeling, the actual completion time of the tasks, the expected fastest completion time of the modeling, the expected time, the slowest time, the actual execution time of the CPU in modeling, the time when the modeling is allocated to the CPU, the actual working time of the GPU in modeling, the GPU idle time, the total system memory, and the maximum value of the system lining occupied during the modeling process; the model accuracy parameters are specifically The parameters of model data processing efficiency include the end time of data loading, the start time of data loading, the expected time of data loading, the access time of cache when hitting, the cache hit rate, the access time of main memory when missing, the size of original input data for modeling, and the size of modeling completed file; the parameters of model stability and scalability include the average failure interval of the model within one month, the average repair time, the number of model crashes within one month, the total number of model tests, the actual number of custom function points, and the expected number of custom function points.

[0044] In this embodiment, it should be specifically explained that the modeling efficiency index analysis unit in the large model three-dimensional modeling data analysis module is used to calculate the modeling efficiency parameters, the model accuracy index analysis unit is used to calculate the model accuracy parameters, the model data processing efficiency analysis unit is used to calculate the model data processing efficiency parameters, and the model stability and scalability index analysis unit is used to calculate the model stability and scalability parameters, and its data analysis includes the following steps:

[0045] Step 1: By analyzing the modeling efficiency parameters, it is used to measure and evaluate the efficiency of the 3D modeling process, which helps to improve the modeling speed, optimize resource usage, and improve the overall modeling quality. Taking into account the model building time and computing resource consumption, the model for obtaining the modeling efficiency index in the modeling efficiency index analysis unit is: Where Mei represents the modeling efficiency index, Mte represents the model building time efficiency, n represents the number of tasks required for 3D modeling, t i represents the actual completion time of the i-th task, l represents the modeling impact factor, T o Indicates the fastest time expected to complete modeling, T m represents the expected time, T p Indicates the slowest time, T o <T m <T p , and Represent the weights of the fastest time, expected time and slowest time respectively, generally The value of is set relatively large, because the expected time is the most likely completion time, Et cpu Indicates the actual execution time of the CPU in modeling, T_et cpu Indicates the time that modeling is allocated to the CPU, Wt gpu Indicates the actual working time of GPU in modeling, Ft gpu represents the GPU idle time, Sm represents the total system memory, and max(sm) represents the maximum value of the system memory occupied during the modeling process;

[0046] Step 2: By analyzing the model accuracy parameters, the accuracy of the large model in generating a 3D model in the 3D modeling task can be measured, which is helpful to evaluate the performance of the model and determine whether the model can meet specific modeling requirements. The model texture similarity, model edge offset, and model volume fidelity are comprehensively considered. Therefore, the model for obtaining the model accuracy index in the model accuracy index analysis unit is: Mai = Ts × (1-OP) × Vf, where Mai represents the model accuracy index, Ts represents the texture similarity, m represents the number of texture features for comparison between the 3D model and the reference model, r l =(r l 1 ,r l 2 ,...,r l k ,...,r l m ), r l k represents the kth texture feature of 3D modeling, represents the kth texture feature of the reference model, represents the smaller of the two texture feature values, Op represents the model edge deviation, N represents the number of matched edge points, (x m,I ,y m,I ) represents the coordinates of the Ith edge point of the model, (x r,I ,y r,I ) represents the coordinates of the corresponding predicted edge points, Vf represents the model volume fidelity, V m Indicates the actual volume of the model, V r represents the model predicted volume;

[0047] Step 3: By analyzing the model data processing efficiency parameters, the speed and efficiency of 3D modeling in the data processing stage can be measured, reflecting the fluency of the modeling process and the speed of generating the final model. The data loading efficiency, memory access efficiency and data compression ratio are comprehensively considered to improve the response speed of the model and optimize resource utilization. Therefore, the model for obtaining the model data processing efficiency index in the model data processing efficiency analysis unit is: Pei represents the model data processing efficiency, E_t represents the end time of data loading, s_t represents the start time of data loading, Elt represents the expected time of data loading. Data loading time mainly refers to the time required to read and load data from the data source (such as database, file system, etc.) into the target system (such as memory, application, etc.), Dcr represents the memory access efficiency, At c Indicates the access time of the cache when a hit occurs, h indicates the cache hit rate, which refers to the ratio of the number of times the CPU obtains data from the cache to the total number of CPU data requests. m Indicates the access time of main memory when the miss occurs, Ds ori Indicates the size of the original input data for modeling, Ds yas represents the size of the modeling completed file, β1, β2, and β3 represent the influencing factors of data loading, memory access efficiency, and data compression, respectively;

[0048] Step 4: By analyzing the model stability and scalability parameters, the performance of the model can be measured, which helps to improve the reliability and sustainability in practical applications. The model failure time, the number of model crashes, and the number of user-defined function points supported by the model are comprehensively considered, so as to provide a smoother and more realistic interactive experience, thereby improving user satisfaction. Therefore, the model for obtaining the model stability and scalability index in the model stability and scalability index analysis unit is: Where Msi represents the model stability and scalability index, M represents the average time between model failures within one month, R represents the mean repair time, η1 represents the failure repair impact factor, where model failure refers to the temporary suspension of system operation, η2 represents the model crash impact factor, Nc represents the number of model crashes within one month, Nt represents the total number of model tests, where model crashes refer to frequent computer freezes, inability to respond to external inputs, and inability of applications or system services to run normally, etc., η3 represents the impact factor of the model's support for user-defined functions, Cfn represents the actual number of customized function points, and Cfn0 represents the expected number of customized function points;

[0049] In this embodiment, it should be specifically explained that the data evaluation in the large model three-dimensional modeling data evaluation module includes the following steps:

[0050] Step 1: Substitute the modeling efficiency index analysis calculation result Mei obtained from the modeling efficiency index analysis unit into the formula: in represents the performance evaluation factor of the modeling efficiency index, Mei0 represents the set value, if is regarded as On the contrary, Transmit large model 3D modeling comprehensive analysis module;

[0051] Step 2: Substitute the model accuracy index analysis calculation result Mai obtained from the model accuracy index analysis unit into the formula: in represents the performance evaluation factor of the model accuracy index, Mai0 represents the set value, if is regarded as On the contrary, Transmit large model 3D modeling comprehensive analysis module;

[0052] Step 3: Substitute the model data processing efficiency index analysis calculation result Pei obtained in the model data processing efficiency analysis unit into the formula: in represents the performance evaluation factor of the model data processing efficiency index, Pei0 represents the set value, if is regarded as On the contrary, Transmit large model 3D modeling comprehensive analysis module;

[0053] Step 4: Substitute the model stability and scalability index analysis calculation result Msi obtained from the model stability and scalability index analysis unit into the formula: in represents the performance evaluation factor of the model stability and scalability index, Msi0 represents the set value, if is regarded as

[0054] On the contrary, Transmit large model 3D modeling comprehensive analysis module;

[0055] In this embodiment, it should be specifically explained that the large model three-dimensional modeling comprehensive analysis module combines the various indexes of the large model three-dimensional modeling and the corresponding performance evaluation factors, and then adds them up respectively to obtain the comprehensive performance index of the large model three-dimensional modeling. The comprehensive analysis model is:

[0056] Among them, Mo_cpi represents the comprehensive performance index of large model 3D modeling. as well as They respectively represent the weight of each index of large model three-dimensional modeling.

[0057] Embodiment 2:

[0058] For the parts not described in detail in this embodiment, please refer to the description of Embodiment 1. A method for three-dimensional modeling of a large model based on artificial intelligence is provided, which includes the following steps:

[0059] Step 1: Analyze and collect the performance data of large model 3D modeling based on artificial intelligence to obtain various parameters for evaluating the performance indicators of large model 3D modeling;

[0060] Step 2: Based on the parameters in step 1, respectively calculate the modeling efficiency parameter, the model accuracy parameter, the model data processing efficiency parameter, and the model stability and scalability parameter to obtain the indexes of the large model three-dimensional modeling performance;

[0061] Step 3: Compare the calculation results of step 2 with the set values ​​to obtain the performance comparison results of each index of large model 3D modeling;

[0062] Step 4: Perform a comprehensive analysis based on the comparison results of step 3 to obtain comprehensive performance indicators of large-scale 3D modeling;

[0063] Step 5: Based on the comprehensive analysis results of step 4, the comprehensive performance indicators of the large model 3D modeling are displayed interactively by human-computer interaction.

[0064] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0065] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for large-scale three-dimensional modeling based on artificial intelligence, characterized in that: It includes a large model 3D modeling data acquisition module, a large model 3D modeling data analysis module, a large model 3D modeling data evaluation module, a large model 3D modeling comprehensive analysis module, and a large model 3D modeling human-computer interaction module; The large model three-dimensional modeling data acquisition module is used to collect and analyze the performance data of the large model three-dimensional modeling based on artificial intelligence, obtain various parameters for evaluating the performance indicators of the large model three-dimensional modeling, and output the various parameters to the large model three-dimensional modeling data analysis module; The large model three-dimensional modeling data analysis module includes a modeling efficiency index analysis unit, a model accuracy index analysis unit, a model data processing efficiency analysis unit, and a model stability and scalability index analysis unit, which are respectively used to calculate various parameters and output the corresponding calculation results to the large model three-dimensional modeling data evaluation module; The large model three-dimensional modeling data evaluation module is used to compare the various indexes of the large model three-dimensional modeling obtained by the above data analysis module with the set values, and transmit the comparison results to the large model three-dimensional modeling comprehensive analysis module; The large model three-dimensional modeling comprehensive analysis module is used to comprehensively analyze the performance evaluation factors of each index calculated by the above evaluation module, and transmit the comprehensive analysis results to the large model three-dimensional modeling human-computer interaction module; The large model three-dimensional modeling human-computer interaction module is used to output the above-mentioned imported comprehensive analysis result large model three-dimensional modeling performance comprehensive index to the system administrator information terminal.

2. According to the system of claim 1, which is based on artificial intelligence and is characterized by: The characteristics are as follows: the various parameters in the large model three-dimensional modeling data acquisition module include system administrator identity authentication information, modeling efficiency parameters, model accuracy parameters, model data processing efficiency parameters, and model stability and scalability parameters, among which the modeling efficiency parameters are specifically the number of tasks required for three-dimensional modeling, the actual completion time of the tasks, the expected fastest completion time of modeling, the expected time, the slowest time, the actual execution time of the CPU in modeling, the time when modeling is allocated to the CPU, the actual working time of the GPU in modeling, the GPU idle time, the total system memory, and the maximum value of the system lining occupied during the modeling process; the model accuracy parameters are specifically the number of texture features. , texture features, the number of matched edge points, the coordinates of the model edge points, the coordinates of the predicted edge points, the actual volume of the model, and the predicted volume of the model; the model data processing efficiency parameters are specifically the end time of data loading, the start time of data loading, the expected time of data loading, the access time of the cache when hitting, the cache hit rate, the access time of the main memory when missing, the size of the original input data for modeling, and the size of the modeling completed file; the model stability and scalability parameters are specifically the average failure interval between models within one month, the average repair time, the number of model crashes within one month, the total number of model tests, the actual number of custom function points, and the expected number of custom function points.

3. The system for large-scale three-dimensional modeling based on artificial intelligence according to claim 1, characterized in that: The model for obtaining the modeling efficiency index in the modeling efficiency index analysis unit is: Where Mei represents the modeling efficiency index, Mte represents the model building time efficiency, n represents the number of tasks required for 3D modeling, t i represents the actual completion time of the i-th task, l represents the modeling impact factor, T o Indicates the fastest time expected to complete modeling, T m represents the expected time, T p Indicates the slowest time, T o <T m <T p , and Represent the weights of the fastest time, expected time and slowest time respectively, Et cpu Indicates the actual execution time of the CPU in modeling, T_et cpu Indicates the time that modeling is allocated to the CPU, Wt gpu Indicates the actual working time of GPU in modeling, Ft gpu represents GPU idle time, Sm represents the total system memory, and max(sm) represents the maximum value of the system memory occupied during the modeling process.

4. The system for large-scale three-dimensional modeling based on artificial intelligence according to claim 1, characterized in that: The model for obtaining the model accuracy index in the model accuracy index analysis unit is: Mai=Ts×(1-OP)×Vf, where Mai represents the model accuracy index, Ts represents the texture similarity, m represents the number of texture features for comparison between the 3D model and the reference model, represents the kth texture feature of 3D modeling, represents the kth texture feature of the reference model, represents the smaller of the two texture feature values, Op represents the model edge deviation, N represents the number of matched edge points, (x m,I ,y m,I ) represents the coordinates of the Ith edge point of the model, (x r,I ,y r,I ) represents the coordinates of the corresponding predicted edge points, Vf represents the model volume fidelity, V m Indicates the actual volume of the model, V r Represents the model predicted volume.

5. The system for large-scale three-dimensional modeling based on artificial intelligence according to claim 1, characterized in that: The model for obtaining the model data processing efficiency index in the model data processing efficiency analysis unit is: Pei represents the model data processing efficiency, E_t represents the end time of data loading, s_t represents the start time of data loading, Elt represents the expected time of data loading, and Dcr represents the memory access efficiency. At c Indicates the access time of the cache when it hits, h indicates the cache hit rate, At m Indicates the access time of main memory when the miss occurs, Ds ori Indicates the size of the original input data for modeling, Ds yas represents the size of the modeling completed file, β1, β2, and β3 represent the influencing factors of data loading, memory access efficiency, and data compression, respectively.

6. The system for large-scale three-dimensional modeling based on artificial intelligence according to claim 1, characterized in that: The model for obtaining the model stability and scalability index in the model stability and scalability index analysis unit is: Where Msi represents the model stability and scalability index, M represents the average failure interval of the model within one month, R represents the mean repair time, η1 represents the fault repair impact factor, η2 represents the model crash impact factor, Nc represents the number of model crashes within one month, Nt represents the total number of model tests, η3 represents the impact factor of the model supporting user-defined functions, Cfn represents the actual number of customized function points, and Cfn0 represents the expected number of customized function points.

7. The system for large-scale three-dimensional modeling based on artificial intelligence according to claim 1, characterized in that: The data evaluation in the large model 3D modeling data evaluation module includes the following steps: Step 1: Substitute the modeling efficiency index analysis calculation result Mei obtained from the modeling efficiency index analysis unit into the formula: in represents the performance evaluation factor of the modeling efficiency index, Mei0 represents the set value; Step 2: Substitute the model accuracy index analysis calculation result Mai obtained from the model accuracy index analysis unit into the formula: in represents the performance evaluation factor of the model accuracy index, Mai0 represents the set value; Step 3: Substitute the model data processing efficiency index analysis calculation result Pei obtained in the model data processing efficiency analysis unit into the formula: in It represents the performance evaluation factor of the model data processing efficiency index, and Pei0 represents the set value; Step 4: Substitute the model stability and scalability index analysis calculation result Msi obtained from the model stability and scalability index analysis unit into the formula: in It represents the performance evaluation factor of the model stability and scalability index, and Msi0 represents the set value.

8. The system for large-scale three-dimensional modeling based on artificial intelligence according to claim 1, characterized in that: The comprehensive analysis model in the large model three-dimensional modeling comprehensive analysis module is: Among them, Mo_cpi represents the comprehensive performance index of large model 3D modeling. as well as They respectively represent the weight of each index of large model three-dimensional modeling.

9. A method for three-dimensional modeling of a large model based on artificial intelligence, used for using a system for three-dimensional modeling of a large model based on artificial intelligence as described in any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Analyze and collect the performance data of large model 3D modeling based on artificial intelligence to obtain various parameters for evaluating the performance indicators of large model 3D modeling; Step 2: Based on the parameters in step 1, respectively calculate the modeling efficiency parameter, the model accuracy parameter, the model data processing efficiency parameter, and the model stability and scalability parameter to obtain the indexes of the large model three-dimensional modeling performance; Step 3: Compare the calculation results of step 2 with the set values ​​to obtain the performance comparison results of each index of large model 3D modeling; Step 4: Perform a comprehensive analysis based on the comparison results of step 3 to obtain comprehensive performance indicators of large-scale 3D modeling; Step 5: Based on the comprehensive analysis results of step 4, the comprehensive performance indicators of the large model 3D modeling are displayed interactively by human-computer interaction.

Images