A model checking quantity determination method, device and equipment

Abstract

The application discloses a model checking quantity determination method, device and equipment, and the method comprises the following steps: obtaining model information and checking parameters corresponding to a plurality of three-dimensional models respectively; classifying the plurality of three-dimensional models according to the model information, and determining a plurality of model sets; determining the similarity and complexity between the plurality of three-dimensional models according to the model information; and determining the checking quantity for indicating the quantity of to-be-checked models in each model set according to the checking parameters, the similarity and the complexity. The application adopts unified checking parameters to determine the checking quantity of different types of model sets, adopts a unified sampling standard to determine the checking quantity of each type of model, avoids the waste of operation resources and time cost caused by manual participation, and improves the accuracy of model sampling.

Description

Technical Field

[0001] This invention relates to the field of 3D model inspection technology, and in particular to a method, apparatus and equipment for determining the number of models to be inspected. Background Technology

[0002] In the data review of the resource library platform, quality inspection tools are often used to conduct a large-scale inspection of the quality of 3D models. Due to the large number of models to be inspected, it requires a lot of computing resources and time. Currently, there are two options for the detection methods used to inspect the quality of 3D models: full inspection and sampling inspection.

[0003] However, existing sampling methods lack consideration of type distribution, making it easy to miss key defects. Furthermore, the current inspection scope relies on manual input of numerical values, which varies from person to person, resulting in inconsistent inspection standards for the same type of model. If the number of inspections is set too high, it will consume a lot of computing resources and time.

[0004] Therefore, there is an urgent need for a method to determine the number of model checks without human intervention, so as to use a unified sampling standard to determine the number of checks for each type of model, avoid the waste of computing resources and time costs, and improve the accuracy of model sampling. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, the present invention aims to provide a method, apparatus and equipment for determining the number of model inspections, which adopts a unified sampling standard to determine the number of inspections for each type of model, avoids the waste of computing resources and time costs, and improves the accuracy of model sampling inspections.

[0006] To solve the above problems, the present invention is implemented according to the following solution:

[0007] A method for determining the number of model checks is provided, including:

[0008] Obtain model information and inspection parameters corresponding to multiple 3D models;

[0009] Based on the model information, multiple 3D models are classified to determine multiple model sets;

[0010] Based on the model information, determine the similarity and complexity between multiple 3D models;

[0011] Based on the inspection parameters, the similarity, and the complexity, the number of inspections used to indicate the number of models to be inspected in each model set is determined.

[0012] Compared with the prior art, the beneficial effects of the model inspection quantity determination method of the present invention are as follows: by using unified inspection parameters to determine the inspection quantity of different types of model sets, the inspection quantity of each type of model is determined by using unified sampling standards, avoiding the waste of computing resources and time costs caused by manual intervention, and improving the accuracy of model sampling.

[0013] Optionally, the model information includes the model type;

[0014] Based on the model information, multiple 3D models are classified to determine multiple model sets, including:

[0015] Based on the model type, 3D models of the same model type are grouped into a model set.

[0016] Optionally, the model information includes model variables and the basic model;

[0017] Based on the model information, the similarity between multiple 3D models is determined, including:

[0018] Based on the model variables, the common model variables of multiple 3D models are identified as common variables;

[0019] The number of common variables is defined as the set variable number, and the number of basic models is defined as the set basis modulus.

[0020] The similarity is determined based on the number of variables in the set and the base modulus of the set.

[0021] Optionally, the similarity is determined based on the number of variables in the set and the base modulus of the set, including:

[0022] When the number of variables in the set is less than or equal to a first preset value, and the set's basic modulus is equal to a second preset value, the similarity is determined using the first preset formula.

[0023] When the number of variables in the set is less than or equal to a first preset value, and the set's basis modulus is greater than a second preset value, the similarity is determined using a second preset formula.

[0024] When the number of variables in the set is greater than a first preset value, and the set basis modulus is greater than or equal to a second preset value, the similarity is determined using a third preset formula.

[0025] Optionally, the model information includes model variables, modeling sketches, and model features;

[0026] Based on the model information, determine the complexity among multiple 3D models, including:

[0027] Based on the model variables, the common model variables of multiple 3D models are identified as common variables;

[0028] The number of common variables is defined as the number of set variables, the number of modeling sketches is defined as the number of set sketches, and the number of model features is defined as the number of set features.

[0029] The complexity is determined based on the number of set variables, the number of set sketches, and the number of set features.

[0030] Optionally, based on the inspection parameters, the similarity, and the complexity, the number of inspections used to indicate the number of models to be inspected in each model set is determined, including:

[0031] Based on the inspection parameters and the similarity, determine the initial number of inspections corresponding to the model set;

[0032] Based on the inspection parameters, the complexity, and the initial number of inspections, the estimated inspection time corresponding to the model set is determined;

[0033] The number of inspections is determined based on the estimated inspection duration and the initial number of inspections.

[0034] Optionally, the inspection parameters include the maximum number of inspections;

[0035] Based on the inspection parameters and the similarity, the initial number of inspections corresponding to the model set is determined, including:

[0036] The number of the model set is determined as the number of model types;

[0037] Determine the number of 3D models in the model set;

[0038] The initial number of checks is determined based on the similarity, the number of 3D models, the maximum number of checks, and the number of model types.

[0039] Optionally, the inspection parameters include the maximum inspection duration;

[0040] The number of inspections is determined based on the estimated inspection duration and the initial number of inspections, including:

[0041] The average inspection time is determined based on the maximum inspection time and the number of model types.

[0042] If the estimated inspection time is less than or equal to the average inspection time, then the initial inspection quantity is taken as the inspection quantity.

[0043] If the estimated inspection time is greater than the average inspection time, then the number of inspections is determined based on the initial number of inspections, the average inspection time, and the estimated inspection time.

[0044] A model inspection quantity determination apparatus is also provided, which applies the above-described model inspection quantity determination method, including:

[0045] The data acquisition module is used to acquire model information and inspection parameters corresponding to multiple 3D models.

[0046] The data processing module is used for:

[0047] Based on the model information, multiple 3D models are classified to determine multiple model sets;

[0048] Based on the model information, determine the similarity and complexity between multiple 3D models;

[0049] The inspection quantity determination module is used to determine the inspection quantity, which indicates the number of models to be inspected in each model set, based on the inspection parameters, the similarity, and the complexity.

[0050] A computer device is also provided, including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the aforementioned method for determining the number of model checks. Attached Figure Description

[0051] Figure 1 This is a flowchart of the quantity determination method of the present invention;

[0052] Figure 2 This is the interface for determining the number of inspections by substituting specific numerical values ​​into the interface of this invention. Figure 1 ;

[0053] Figure 3 This is the interface for determining the number of inspections by substituting specific numerical values ​​into the interface of this invention. Figure 2 ;

[0054] Figure 4 This is the interface for determining the number of inspections by substituting specific numerical values ​​into the interface of this invention. Figure 3 ;

[0055] Figure 5 This is the interface for determining the number of inspections by substituting specific numerical values ​​into the interface of this invention. Figure 4 ;

[0056] Figure 6 This is the interface for determining the number of inspections by substituting specific numerical values ​​into the interface of this invention. Figure 5 . Detailed Implementation

[0057] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0058] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0059] See Figure 1 As shown, a method for determining the number of model checks according to the present invention includes:

[0060] S1: Obtain model information and inspection parameters corresponding to multiple 3D models.

[0061] In one embodiment of the present invention, the model information includes model type, model variables, base model, modeling sketch, and model features; wherein, the model type is used to indicate the application field classification of the 3D model, such as mechanical engineering, building information modeling, product design, etc.; the model variables are used to represent the variable attribute parameters of the model, including but not limited to geometric dimension parameters (such as length, width, height, radius of curvature), material parameters (such as density, surface roughness), and structural parameters (such as assembly hierarchy, component fit tolerances); the base model is used to indicate the original template model constituting the 3D model, including the standard geometric structure of the 3D model, etc.; the modeling sketch is used to indicate the two-dimensional contour sketch data of the 3D model in the modeling stage, including line coordinates, constraint relationships, and dimension annotation information; the model features include features not generated by the sketch, such as rounding, chamfering, mirroring, arraying, shelling, drafting, etc.

[0062] In one type of the present invention, the inspection parameters include a maximum number of inspections, a maximum inspection duration, and an inspection time constant; wherein, the maximum number of inspections is used to indicate the maximum value of the total number of sampled models of different model types in multiple 3D models, the maximum inspection duration is used to indicate the maximum value of the total inspection duration of sampled models of different model types, and the inspection time constant is used to indicate the time constant consumed in performing quality inspection on each 3D model.

[0063] S2: Based on model information, classify multiple 3D models to determine multiple model sets; wherein, model information includes model types used to indicate the application domain of the 3D models; in one embodiment of the present invention, classifying multiple 3D models to determine multiple model sets based on model information includes: classifying 3D models of the same model type into one model set based on model type.

[0064] By grouping 3D models of the same type into a model set, the number of models sampled in each model set is determined separately, thus avoiding uneven sampling among different model types. For example, if a uniform sampling strategy (such as randomly selecting a fixed number or proportion) is used without classifying the 3D models by type, types with a large number of models may be missed due to insufficient sampling coverage, while types with a small number of models may be over-sampled due to the randomness of sampling, leading to excessive consumption of computing resources and resulting in a situation where the number of samples does not match the number of models in each model type.

[0065] S3: Determine the similarity and complexity between multiple 3D models based on model information; wherein, model information includes model variables and base models; in one embodiment of the present invention, determining the similarity between multiple 3D models based on model information includes: determining common variables among multiple 3D models based on model variables; determining the number of common variables as the set variable number and the number of base models as the set basis modulus; determining the similarity based on the set variable number and the set basis modulus.

[0066] In one embodiment of the present invention, determining the similarity based on the number of set variables and the set basis modulus includes: when the number of set variables is less than or equal to a first preset value and the set basis modulus is equal to a second preset value, determining the similarity using a first preset formula; when the number of set variables is less than or equal to the first preset value and the set basis modulus is greater than the second preset value, determining the similarity using a second preset formula; and when the number of set variables is greater than the first preset value and the set basis modulus is greater than or equal to the second preset value, determining the similarity using a third preset formula.

[0067] In this invention, the first preset value is 10, the second preset value is 1, and N1 is the number of set variables, N2 is the set basis modulus, and α is the similarity. When N1≤10 and N2=1, the first preset formula α=1-(N1*5)% is used to calculate the similarity; when N1≤10 and N2>1, the second preset formula α=[1-(N1*5)%] / 2 is used to calculate the similarity; when N1>10 and N2=1, or N1>10 and N2>1, that is, when N1>10 and N2≥1, the third preset formula α=(1-50%) / 2 is used to calculate the similarity.

[0068] In one embodiment of the present invention, the model information includes model variables, modeling sketches, and model features; determining the complexity among multiple 3D models based on the model information includes: identifying common model variables among the multiple 3D models as common variables; determining the number of common variables as the set variable number, the number of modeling sketches as the set sketch number, and the number of model features as the set feature number; and determining the complexity based on the set variable number, set sketch number, and set feature number.

[0069] Assume N1 is the number of set variables, M1 is the number of set sketches, M2 is the number of set features, and β is the complexity. The formula for calculating the complexity is: β = 1 + (N1 - 10) / 100 + (M1 - 10) / 100 + (M2 - 10) / 100. The smaller the complexity value, the simpler the structure of the multiple 3D models, and the shorter the time consumed in checking these 3D models. The larger the complexity value, the more complex the structure of the multiple 3D models, and the longer the time consumed in checking these 3D models.

[0070] S4: Based on the inspection parameters, similarity, and complexity, determine the number of inspections to indicate the number of models to be inspected in each model set, including: determining the initial number of inspections for the model set based on the inspection parameters and similarity; determining the estimated inspection time for the model set based on the inspection parameters, complexity, and initial number of inspections; and determining the number of inspections based on the estimated inspection time and the initial number of inspections.

[0071] In one embodiment of the present invention, the inspection parameters include a maximum number of inspections; determining the initial number of inspections corresponding to the model set based on the inspection parameters and similarity includes: determining the number of the model set as the number of model types; determining the number of 3D models in the model set; and determining the initial number of inspections based on similarity, the number of 3D models, the maximum number of inspections, and the number of model types.

[0072] In one embodiment of the present invention, the inspection parameters include a maximum inspection duration; determining the inspection quantity based on the estimated inspection duration and the initial inspection quantity includes: determining an average inspection duration based on the maximum inspection duration and the number of model types; if the estimated inspection duration is less than or equal to the average inspection duration, then the initial inspection quantity is used as the inspection quantity; if the estimated inspection duration is greater than the average inspection duration, then the inspection quantity is determined based on the initial inspection quantity, the average inspection duration, and the estimated inspection duration.

[0073] Assume K is the maximum number of checks, S is the number of model types, q is the number of 3D models, α is the similarity, β is the complexity, e is the check time constant, T is the maximum check duration, Q' is the initial number of checks, Q is the number of checks, t is the estimated check duration, and T' is the average check duration. The maximum number of checks K, the number of model types S, and the number of 3D models q are all positive integers. The maximum number of checks K and the maximum check duration T are set based on the current limitations of the resource library's computing power and can be modified according to actual needs. The detection time constant e is fixed at 3.6.

[0074] When the number of 3D models q≤100, the initial number of checks Q'=min[(1-α)*q,K / S];

[0075] When the number of 3D models is 101≤q≤1000 (100<q≤1000), the initial number of checks Q'=min[(1-α)*q / 2,K / S];

[0076] When the number of 3D models is 1001≤q≤10000 (1000<q≤10000), the initial number of checks Q'=min[(1-α)*q / 10,K / S];

[0077] When the number of 3D models q ≥ 10001 (q > 10000), the initial number of checks Q' = K / S;

[0078] In the above calculation of the initial check quantity, there are three critical values ​​of 100, 1000, and 10000, as well as constants of 2 and 10 (q / 2, q / 10) in the formula. These are set based on the limited computing power resources of the current resource library for checking and the restriction that the check time of a single task is too long. Furthermore, if the initial check quantity Q' is not an integer, the initial check quantity Q' is rounded down.

[0079] In one embodiment of the present invention, the formula for calculating the estimated inspection time t is: t = β * Q' * e, and the formula for calculating the average inspection time T' is: T' = T / S.

[0080] If the estimated inspection time is less than or equal to the average inspection time (t≤T / S or t≤T'), then the initial inspection quantity is used as the inspection quantity, i.e., Q = Q'; if the estimated inspection time is greater than the average inspection time (t>T / S or t>T'), then the inspection quantity is determined based on the initial inspection quantity, the average inspection time, and the estimated inspection time, and the calculation formula is: Q = Q'*T / S / t or Q = Q'*T' / t.

[0081] See Figure 2-6 As shown, the quantity determination method of the present invention will be described in detail by substituting specific values:

[0082] Assume the maximum number of checks K is 3000, the maximum check duration T is 180 min (10800 s), the check time constant e is 3.6, and the number of model types S is 6 (see...). Figure 2 The six serial numbers shown each correspond to a model type. The number of 3D models is q1 = 56640, q2 = 9264, q3 = 3328, q4 = 897, q5 = 321, and q6 = 78 (corresponding to...). Figure 2 Showing the number of expansions in the 6 model types), and the number of set variables N1 = 4 (corresponding to...) Figure 3 The name in the set d), the base modulus N2 = 1 (corresponding to) Figure 4 The number of uploaded models), the number of set sketches M1 = 2 (corresponding to) Figure 5 The "Extended Boss / Base 3" and "Extended Removal 1" in the dataset), and the set feature number M2 = 2 (corresponding to Figure 5 (See "Fillet 1" and "Chamfer 1" under "Stretch Cut 1").

[0083] When N1 = 4 and N2 = 1, it meets the condition "N1 ≤ 10 and N2 = 1". The similarity is calculated using the first preset formula α = 1 - (N1 * 5)% and the result is α = 0.8. The complexity is calculated using β = 1 + (N1 - 10) / 100 + (M1 - 10) / 100 + (M2 - 10) / 100 and the result is β = 0.78.

[0084] ① Determine the sampling quantity for the model set with serial number 1.

[0085] q1 = 56640 belongs to the case where q ≥ 10001 (q > 10000). The calculation process is as follows:

[0086] The initial number of checks is Q1' = K / S = 3000 / 6 = 500;

[0087] Estimated inspection time t1 = β * Q1' * e = 0.78 * 500 * 3.6 = 1404 s;

[0088] Average inspection time T' = T / S = 180 / 6 = 30 min = 1800 s;

[0089] In the case where t1 ≤ T', the number of checks is Q1 = Q1' = 500, meaning that 500 3D models are randomly selected from the model set with index 1 for inspection (see [reference]). Figure 6 (As shown in the image, "Series number 1" is "Set the number of models to check").

[0090] ② Determine the sampling quantity for model set with serial number 2.

[0091] q² = 9264 falls under the case of 1001 ≤ q ≤ 10000 (1000 < q ≤ 10000). The calculation process is as follows:

[0092] The initial number of checks is Q2' = min[(1-α)*q2 / 10, K / S] = min[(1-0.8)*9264 / 10, 3000 / 6] = min(185.28, 500) = 185.28, which is rounded down to get Q2' = 185;

[0093] Estimated inspection time t2 = β * Q2' * e = 0.78 * 185 * 3.6 = 819.48 s;

[0094] Average inspection time T' = T / S = 180 / 6 = 30 min = 1800 s;

[0095] In the case where t2 ≤ T', the number of checks is Q2 = Q2' = 185, meaning 185 3D models are randomly selected from the model set with index 2 for checks (see [reference]). Figure 6 (As shown in the image, "Series number 2" is "Set the number of models to check").

[0096] ③ Determine the sampling quantity for model set number 3.

[0097] q3 = 3328 falls under the case of 1001 ≤ q ≤ 10000 (1000 < q ≤ 10000). The calculation process is as follows:

[0098] The initial number of checks is Q3' = min[(1-α)*q3 / 10, K / S] = min[(1-0.8)*3328 / 10, 3000 / 6] = min(66.56, 500) = 66.56, which is rounded down to get Q3' = 66;

[0099] Estimated inspection time t3 = β * Q3' * e = 0.78 * 66 * 3.6 = 185.33 s;

[0100] Average inspection time T' = T / S = 180 / 6 = 30 min = 1800 s;

[0101] In the case where t3 ≤ T', the number of checks is Q3 = Q3' = 66, meaning 66 3D models are randomly selected from the model set with index 3 for checks (see [reference]). Figure 6 (As shown in the image, "Series number 3" is "Set the number of models to check").

[0102] ④ Determine the sampling quantity for model set with serial number 4.

[0103] q4 = 897 falls under the case of 101 ≤ q ≤ 1000 (100 < q ≤ 1000). The calculation process is as follows:

[0104] The initial number of checks Q4' = min[(1-α)*q4 / 2, K / S] = min[(1-0.8)*897 / 2, 3000 / 6] = min(89.7, 500) = 89.7, which is rounded down to get Q4' = 89;

[0105] Estimated inspection time t4 = β * Q4' * e = 0.78 * 89 * 3.6 = 249.91 s;

[0106] Average inspection time T' = T / S = 180 / 6 = 30 min = 1800 s;

[0107] In the case where t4 ≤ T', the number of checks is Q4 = Q4' = 89, meaning that 89 3D models are randomly selected from the model set with index 4 for checks (see [reference]). Figure 6 (As shown in the image, "Series number 4" is the "Set the number of models to check").

[0108] ⑤ Determine the sampling quantity for model set number 5.

[0109] q5 = 321 falls under the case of 101 ≤ q ≤ 1000 (100 < q ≤ 1000). The calculation process is as follows:

[0110] The initial number of checks is Q5' = min[(1-α)*q5 / 2, K / S] = min[(1-0.8)*321 / 2, 3000 / 6] = min(32.1, 500) = 32.1, which is rounded down to get Q5' = 32;

[0111] Estimated inspection time t5 = β * Q5' * e = 0.78 * 32 * 3.6 = 89.86 s;

[0112] Average inspection time T' = T / S = 180 / 6 = 30 min = 1800 s;

[0113] In the case where t5 ≤ T', the number of checks is Q5 = Q5' = 32, meaning that 32 3D models are randomly selected from the model set with index 5 for checks (see [reference]). Figure 6 (As shown in the image, "Series number 5" is "Set the number of models to check").

[0114] ⑥ Determine the sampling quantity for model set number 6.

[0115] q6 = 78 falls under the case of q ≤ 100. The calculation process is as follows:

[0116] The initial number of checks is Q6' = min[(1-α)*q6, K / S] = min[(1-0.8)*78, 3000 / 6] = min(15.6, 500) = 15.6, which is rounded down to get Q6' = 15;

[0117] Estimated inspection time t6 = β * Q6' * e = 0.78 * 15 * 3.6 = 42.12 s;

[0118] Average inspection time T' = T / S = 180 / 6 = 30 min = 1800 s;

[0119] In the case where t6 ≤ T', the number of checks is Q6 = Q6' = 15, meaning that 15 3D models are randomly selected from the model set with index 6 for inspection (see [reference]). Figure 6 (As shown in the image, "Series number 6" is the "Set the number of models to check").

[0120] This invention calculates the optimal number of models to be checked (check count) for each model type from multiple dimensions, and takes into account factors such as the distribution of all types and the similarity and complexity of model series (similarity and complexity between multiple 3D models of different types), reducing computing resources and time costs; at the same time, it eliminates the need for manual setting of the check count, ensuring a uniform standard for the check count of different types.

[0121] The present invention provides a model inspection quantity determination apparatus, which applies the above-described model inspection quantity determination method, comprising:

[0122] The data acquisition module is used to acquire model information and inspection parameters corresponding to multiple 3D models.

[0123] The data processing module is used for:

[0124] Based on the model information, multiple 3D models are classified to determine multiple model sets;

[0125] Based on the model information, determine the similarity and complexity between multiple 3D models;

[0126] The inspection quantity determination module is used to determine the inspection quantity, which indicates the number of models to be inspected in each model set, based on inspection parameters, similarity, and complexity.

[0127] The computer device of the present invention includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the above-described quantity determination method.

[0128] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0129] The memory can be used to store the computer program or module. The processor implements various functions of the quantity determination method by running or executing the computer program or module stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0130] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining the number of model checks, characterized in that, include: Obtain model information and inspection parameters corresponding to multiple 3D models; Based on the model information, multiple 3D models are classified to determine multiple model sets; Based on the model information, determine the similarity and complexity between multiple 3D models; Based on the inspection parameters, the similarity, and the complexity, determine the number of inspections used to indicate the number of models to be inspected in each model set; The model information includes model variables and the basic model; Based on the model information, the similarity between multiple 3D models is determined, including: identifying common variables among the multiple 3D models based on the model variables; determining the number of common variables as the set variable number and the number of base models as the set basis modulus; and determining the similarity based on the set variable number and the set basis modulus. The model information also includes model variables, modeling sketches, and model features; based on the model information, the complexity among multiple 3D models is determined, including: based on the model variables, identifying common model variables among multiple 3D models; determining the number of common variables as the set variable number, the number of modeling sketches as the set sketch number, and the number of model features as the set feature number; and determining the complexity based on the set variable number, the set sketch number, and the set feature number. The number of checks used to indicate the number of models to be checked in each model set is determined based on the check parameters, the similarity, and the complexity, including: determining the initial number of checks corresponding to the model set based on the check parameters and the similarity; determining the estimated check duration corresponding to the model set based on the check parameters, the complexity, and the initial check duration; and determining the number of checks based on the estimated check duration and the initial check duration. The inspection parameters include the maximum number of inspections; determining the initial number of inspections corresponding to the model set based on the inspection parameters and the similarity includes: determining the number of the model set as the number of model types; determining the number of 3D models in the model set; and determining the initial number of inspections based on the similarity, the number of 3D models, the maximum number of inspections, and the number of model types.

2. The method for determining the number of model checks according to claim 1, characterized in that, The model information includes the model type; Based on the model information, multiple 3D models are classified to determine multiple model sets, including: Based on the model type, 3D models of the same model type are grouped into a model set.

3. The method for determining the number of model checks according to claim 1, characterized in that, Determining the similarity based on the number of variables in the set and the base modulus of the set includes: When the number of variables in the set is less than or equal to a first preset value, and the set's basic modulus is equal to a second preset value, the similarity is determined using a first preset formula, the expression of which is: α = 1 - (N1 * 5)%; When the number of variables in the set is less than or equal to a first preset value, and the number of basis moduli in the set is greater than a second preset value, the similarity is determined by a second preset formula, the expression of which is: α=[1-(N1*5)%] / 2; When the number of variables in the set is greater than a first preset value and the set basis modulus is greater than or equal to a second preset value, the similarity is determined by a third preset formula, the expression of which is: α=(1-50%) / 2; Where α is the similarity and N1 is the number of variables in the set.

4. The method for determining the number of model checks according to claim 1, characterized in that, The inspection parameters include the maximum inspection duration; The number of inspections is determined based on the estimated inspection duration and the initial number of inspections, including: The average inspection time is determined based on the maximum inspection time and the number of model types. If the estimated inspection time is less than or equal to the average inspection time, then the initial inspection quantity is taken as the inspection quantity. If the estimated inspection time is greater than the average inspection time, then the number of inspections is determined based on the initial number of inspections, the average inspection time, and the estimated inspection time.

5. A device for determining the number of model checks, employing the method for determining the number of model checks according to any one of claims 1-4, characterized in that, include: The data acquisition module is used to acquire model information and inspection parameters corresponding to multiple 3D models. The data processing module is used for: Based on the model information, multiple 3D models are classified to determine multiple model sets; Based on the model information, determine the similarity and complexity between multiple 3D models; The inspection quantity determination module is used to determine the inspection quantity, which indicates the number of models to be inspected in each model set, based on the inspection parameters, the similarity, and the complexity.

6. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one instruction, at least one program, code set, or instruction set, the at least one instruction, at least one program, code set, or instruction set being loaded and executed by the processor to implement a method for determining the number of model checks as described in any one of claims 1 to 4.

Images