Online denture design result detection method and system based on automatic verification

Abstract

The invention discloses an online denture design result detection method and system based on automatic verification, and the method comprises the steps: collecting denture result related data and patient related data, constructing a scheme detection model, and automatically detecting a denture design scheme; generating a false tooth entity model by utilizing a 3D printing technology, and comparing and detecting the entity model and the false tooth design model by utilizing an entity model detection function; the false tooth design result is uploaded to a platform, and the platform evaluates the false tooth design result in real time. The precision and consistency of denture design are improved, and subjective factors of manual inspection are reduced. And by utilizing the 3D printing technology and finite element analysis, multi-dimensional comprehensive evaluation is realized, and the design and manufacturing efficiency is improved. And a real-time feedback mechanism shortens the design period, enhances the personalized customization capability, and improves the product quality and reliability. The automatic process reduces cost and resource waste, facilitates data management and tracing, and provides data support for continuous improvement.

Description

Technical Field

[0001] The present invention relates to the technical field of denture design and detection, and in particular to an online denture design achievement detection method and system based on automatic verification. Background Art

[0002] With the rapid development of computer-aided design and 3D scanning, the design and manufacturing technology of dentures has been significantly improved. The application of CAD technology enables designers to create more accurate and personalized denture models, while 3D printing technology provides efficient and precise manufacturing means that can directly transform digital designs into physical products. The combination of these technologies makes the design and production process of dentures more flexible and efficient. In addition, the application of simulation technologies such as finite element analysis (FEA) also makes it possible to predict the mechanical properties and durability of dentures during the design stage, thereby improving the reliability and service life of the product.

[0003] However, although the above technologies have made great progress in denture design and manufacturing, the existing technologies still have some shortcomings. First, the traditional denture design evaluation method mainly relies on manual inspection and empirical judgment, which is not only time-consuming and labor-intensive, but also easily affected by human factors, resulting in the accuracy and consistency of the evaluation results. It is difficult to ensure. Secondly, the existing detection methods are mostly focused on the evaluation of a single dimension, such as dimensional accuracy or surface quality, and lack a comprehensive and multi-dimensional detection method for the results of denture design. In addition, although 3D printing technology can quickly generate physical models, how to effectively compare and analyze these physical models with the original design models is still a technical problem that needs to be solved urgently. Especially in the context of complex oral structures and personalized design needs, traditional evaluation methods and tools are particularly insufficient.

[0004] The existing denture design and detection technology still has the problem of poor real-time performance, and it is impossible to achieve real-time feedback and dynamic optimization during the design and production process. This leads to the problems of long design cycle and high modification cost, which is particularly inconvenient today when the demand for personalized medical care is increasing. We have invented an online denture design results detection method and system based on automatic verification. By collecting denture results-related data and patient-related data, a scheme detection model is constructed to realize the function of automatic detection of denture design schemes. At the same time, 3D printing technology is used to generate a denture physical model, and the physical model is compared and detected with the denture design model through the physical model detection function, which further improves the accuracy and efficiency of the detection. The denture design results are uploaded to the platform, and the platform evaluates the denture design results in real time, realizing dynamic optimization and real-time feedback of the design process, and significantly improving the quality and efficiency of denture design and manufacturing.

[0005] The existing denture design and detection technology has problems such as single evaluation means, time-consuming detection process, and poor real-time performance. The online denture design results detection method and system based on automatic verification invented by us solves these problems in the existing technology through the comprehensive application of data collection, 3D printing, automatic detection and real-time evaluation technology, and belongs to the field of denture design and manufacturing technology. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is: the existing cloud service platform calculation method has large power consumption, load rate rewards and penalties, high cost, and the optimization problem of how to distribute task requests to each host to achieve load balancing.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: an online denture design results detection method based on automatic verification, comprising:

[0009] Collect data related to denture results and patients, build a plan detection model, and automatically detect denture design plans;

[0010] Generate a denture solid model using 3D printing technology, and use the solid model detection function to compare and detect the solid model with the denture design model;

[0011] Upload the denture design results to the platform, and the platform will evaluate the denture design results in real time.

[0012] As a preferred solution of the online denture design results detection method based on automatic verification described in the present invention, the collection of denture results-related data and patient-related data includes obtaining a three-dimensional image of the patient's internal oral structure through a handheld 3D oral scanner; obtaining the patient's occlusion data using a bite recorder; obtaining the patient's oral health data through medical records; obtaining historical patient denture design and use data through a database; and using CMM to perform height geometric measurement of the solid model.

[0013] As a preferred solution of the online denture design results detection method based on automatic verification described in the present invention, wherein: collecting denture results-related data and patient-related data, building a solution detection model, and automatically detecting the denture design solution include, in order to automatically monitor and analyze whether the denture design solution complies with industry regulations, and simulate the mechanical properties of the denture design solution in real time, combining the denture design rules, FEA algorithm and machine learning to build a solution detection model, the formula is expressed as:

[0014]

[0015] Where D represents the result of the scheme detection, Φ(x, y, z) represents the displacement field function of the finite element analysis, α represents the attenuation coefficient, t represents the time variable, and V represents the volume of the denture design. represents the Laplace operator, w i represents the weight of the i-th rule, F i (x) represents the rule-based detection function, N represents the total number of rules, G j (y) represents the detection function of the machine learning model, y represents the input parameter set of the model, and M represents the total number of machine learning models;

[0016] In order to quantify the detection of denture design schemes, a scoring formula is designed, which is expressed as follows:

[0017]

[0018] Among them, S D Indicates the score of the design test result, H k (D) represents the kth detection index function, β k represents the weight coefficient of the indicator, P represents the total number of detection indicators, E(z) represents the normalized function based on the specific parameter set z, T represents the total time, Ψ(u,v) represents the two-dimensional variation function of the detection result, and u and υ are two variables of the function respectively;

[0019] The value range of D is from 0 to positive infinity. The larger the value of D is, the less the test results meet the design standards and requirements.

[0020] S D The value range of S is from 0 to positive infinity. The higher the value of S is, the higher the score of the detection result is.

[0021] As a preferred solution of the online denture design results detection method based on automatic verification described in the present invention, wherein: a denture solid model is generated by using 3D printing technology, and a solid model detection function is used to compare and detect the solid model with the denture design model, including, in order to reduce the error in denture production and solve the problem of whether the denture design model can be implemented, point cloud alignment and shape analysis are used to compare the 3D solid model measurement data with the original design model data, and a solid model detection function is constructed, and the formula is expressed as:

[0022]

[0023] Where M(P,Q) represents the solid model detection function, P(x,y,z) represents the point cloud of the designed model, Q(x′,y′,z′) represents the point cloud of the actual 3D printed model, R represents the rigid body transformation matrix, ||·|| represents the Euclidean distance, and λ represents the regularization parameter. represents the Laplace operator, Vp represents the volume integration area of ​​the denture design model, D i is the distance deviation of the i-th point, μ i is the expected distance deviation, α is the smoothing parameter, and N is the total number of points;

[0024] In order to quantify the detection results of the designed model, a scoring formula is designed, which is expressed as follows:

[0025]

[0026] Where S M represents the scoring function of the design model detection result, M j represents the model detection value of the jth detection point, β j represents the weight coefficient of the jth point, M represents the total number of detection points, Ψ(u,v) represents the two-dimensional change function of the detection result, u and v are the two variables of the function, and T represents the total time;

[0027] The value threshold of M(P,Q) ranges from 0 to positive infinity, and the lower the value, the smaller the deviation between the designed model and the actual model;

[0028] The value threshold of S(M) ranges from 0 to positive infinity. The higher the value, the higher the score of the test result, that is, the lower the quality of the denture design solution, indicating that the design needs further optimization and improvement.

[0029] As a preferred solution of the online denture design result detection method based on automatic verification described in the present invention, the denture design result is uploaded to the platform, and the platform evaluates the denture design result in real time, including, in order to conduct a comprehensive visual score evaluation of the denture design result, combining the design model detection result scoring function and the design detection result scoring, and considering the patient's denture design and use data, the denture design result is comprehensively scored, and the formula is expressed as:

[0030]

[0031] Among them, S total Indicates the comprehensive score, S M represents the score of the design model detection result, S D Indicates the design scheme test result score, S usage represents the patient's denture design and use data score, α, β, γ, δ represent the relative importance of different scores, V represents the volume integration area of ​​the model, T represents the total time, Represents the gradient of the design model detection result;

[0032] S total The value threshold is from 0 to positive infinity, S total The higher the value, the higher the overall score of the denture design outcome.

[0033] As a preferred solution of the online denture design result detection method based on automatic verification described in the present invention, wherein: uploading the denture design result to the platform, and the platform evaluating the denture design result in real time also includes: when S D When the score is >80, the denture design is excellent and the next step of evaluation will be entered directly;

[0034] When 60 D When <80, the denture design is medium, and the system will prompt the designer to check the specific inspection;

[0035] When S D <60, the system will mark the denture design as unqualified and redesign it;

[0036] S M When the score is >80, the model accuracy and consistency are good, and the next step of evaluation is directly entered;

[0037] When 50 M When <90, the system will prompt the designer to check the specific deviation points and perform local optimization;

[0038] When S M <50, the system will mark the design as unacceptable and require redesign or major revision.

[0039] 7. The method for detecting the online denture design results based on automatic verification according to claim 6, characterized in that: uploading the denture design results to the platform, and the platform evaluating the denture design results in real time further comprises: when S total When the score is >75, the functional test and performance of the denture design result meet the requirements and the design result passes the evaluation;

[0040] When 45 total When <75, there are some problems in the functional testing and performance of the denture design results. The following tests and optimizations are recommended;

[0041] When S total <45, the system will mark the denture design results as unqualified and redesign them.

[0042] As a preferred solution of the online denture design achievement detection method based on automatic verification described in the present invention, wherein: a data acquisition module collects denture achievement-related data and patient-related data, constructs a solution detection model, and automatically detects the denture design solution;

[0043] The detection module uses 3D printing technology to generate a denture solid model, and uses a solid model detection function to compare and detect the solid model with the denture design model;

[0044] ​​​The results evaluation module uploads the denture design results to the platform, and the platform evaluates the denture design results in real time.

[0045] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0046] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0047] Beneficial effects of the present invention: The online denture design results detection method based on automatic verification provided by the present invention improves the accuracy and consistency of denture design and reduces the subjective factors of manual inspection. Utilizing 3D printing technology and finite element analysis, multi-dimensional comprehensive evaluation is achieved, which improves design and manufacturing efficiency. The real-time feedback mechanism shortens the design cycle, enhances personalized customization capabilities, and improves product quality and reliability. The automated process reduces costs and resource waste, facilitates data management and traceability, and provides data support for continuous improvement. These advantages significantly improve the overall level of denture design and manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 An overall flow chart of an online denture design results detection method based on automatic verification provided by the first embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0051] Example 1

[0052] Reference Figure 1 , which is an embodiment of the present invention, provides an online denture design results detection method based on automatic verification, comprising:

[0053] S1: Collect data related to denture results and patients, build a plan detection model, and automatically detect denture design plans.

[0054] The collection of data related to denture results and patients includes obtaining three-dimensional images of the patient's internal oral structure through a handheld 3D oral scanner; obtaining the patient's occlusion data using a bite recorder; obtaining the patient's oral health data through medical records; obtaining historical patient denture design and use data through a database; and using CMM to perform height geometric measurements on solid models.

[0055] In order to automatically monitor and analyze whether the denture design scheme complies with industry regulations and simulate the mechanical properties of the denture design scheme in real time, a scheme detection model is constructed by combining denture design rules, FEA algorithm and machine learning. The formula is expressed as follows:

[0056]

[0057] Where D represents the result of the scheme detection, Φ(x, y, z) represents the displacement field function of the finite element analysis, α represents the attenuation coefficient, t represents the time variable, and V represents the volume of the denture design. represents the Laplace operator, w i represents the weight of the i-th rule, F i (x) represents the rule-based detection function, N represents the total number of rules, G j (y) represents the detection function of the machine learning model, y represents the input parameter set of the model, and M represents the total number of machine learning models;

[0058] In order to quantify the detection of denture design schemes, a scoring formula is designed, which is expressed as follows:

[0059]

[0060] Among them, S D Indicates the score of the design test result, H k (D) represents the kth detection index function, β k represents the weight coefficient of the indicator, P represents the total number of detection indicators, E(z) represents the normalized function based on the specific parameter set z, T represents the total time, Ψ(u,v) represents the two-dimensional variation function of the detection result, and u and υ are two variables of the function respectively;

[0061] The value range of D is from 0 to positive infinity. The larger the value of D is, the less the test results meet the design standards and requirements.

[0062] S D The value range of S is from 0 to positive infinity. The higher the value of S is, the higher the score of the detection result is.

[0063]

[0064] Among them, F i (x) is the i-th detection function based on the rule, x k is the kth input parameter, μ k is the mean of the kth parameter, σ k is the standard deviation of the kth parameter, and K is the total number of input parameters.

[0065]

[0066] Among them, G j (y) is the jth detection function based on the machine learning model, y m is the mth input parameter, γ m is the amplification factor of the mth parameter, and M is the total number of input parameters.

[0067]

[0068] Among them, H k (D) represents the kth detection index function, D represents the final score of the comprehensive detection model, α k represents the attenuation coefficient of the kth indicator, β kn It represents the weight coefficient of the kth indicator in the nth term, and N represents the highest order term of the polynomial;

[0069]

[0070] Among them, E(z) is the normalization function, z i is the i-th input parameter, μ i is the mean of the i-th parameter, σ i is the standard deviation of the i-th parameter, and L is the total number of input parameters.

[0071] Furthermore, the displacement field function of finite element analysis (FEA) is combined, the global deviation of the model is calculated by integration, and the Laplace operator is used for smoothing to ensure high-precision evaluation of the model. The FEA method can simulate complex mechanical behaviors and deformation conditions and provide high-precision numerical solutions. Through high-precision evaluation, small deviations in denture design can be accurately identified, improving the accuracy and consistency of design and manufacturing.

[0072] Furthermore, rule detection can ensure that the model meets the preset standards, while machine learning models can discover potential patterns and problems from big data. Multi-dimensional comprehensive evaluation ensures that the denture design not only meets the basic standards, but also meets the needs of personalized and complex application scenarios.

[0073] Furthermore, dynamic evaluation can timely capture changes and potential problems in the design process and provide real-time optimization suggestions. Real-time dynamic evaluation greatly shortens the design cycle, improves design and manufacturing efficiency, and meets the needs of rapid iteration and optimization. The innovative scoring mechanism provides a comprehensive and objective evaluation method that can better reflect the overall quality and performance of the design.

[0074] S2: Generate a denture solid model using 3D printing technology, and use the solid model detection function to compare and detect the solid model with the denture design model.

[0075] In order to reduce the error in denture production and solve the problem of whether the denture design model can be implemented, point cloud alignment and shape analysis are used to compare the 3D solid model measurement data with the original design model data, and a solid model detection function is constructed. The formula is expressed as:

[0076]

[0077] Where M(P,Q) represents the solid model detection function, P(x,y,z) represents the point cloud of the designed model, Q(x′,y′,z′) represents the point cloud of the actual 3D printed model, R represents the rigid body transformation matrix, ||·|| represents the Euclidean distance, and λ represents the regularization parameter. represents the Laplace operator, V p represents the volume integration area of ​​the denture design model, D i is the distance deviation of the i-th point, μ i is the expected distance deviation, α is the smoothing parameter, and N is the total number of points;

[0078] In order to quantify the detection results of the designed model, a scoring formula is designed, which is expressed as follows:

[0079]

[0080] Where S M represents the scoring function of the design model detection result, M j represents the model detection value of the jth detection point, β j represents the weight coefficient of the jth point, M represents the total number of detection points, Ψ(u,v) represents the two-dimensional change function of the detection result, u and v are the two variables of the function, and T represents the total time;

[0081] The value threshold of M(P,Q) ranges from 0 to positive infinity, and the lower the value, the smaller the deviation between the designed model and the actual model;

[0082] The value threshold of S(M) ranges from 0 to positive infinity. The higher the value, the higher the score of the test result, that is, the lower the quality of the denture design solution, indicating that the design needs further optimization and improvement.

[0083] Calculate the difference between the design model and the actual model, reduce noise interference, and ensure high accuracy of the test results. The integral calculation covers the entire volume area of ​​the design model to achieve a comprehensive evaluation of the model.

[0084] High-precision testing and evaluation methods can detect minor deviations in design and manufacturing, ensuring the precise fit and use of dentures. Comprehensively evaluate every detail of the model to ensure a high degree of consistency between the designed model and the actual model.

[0085] Combine multiple test results for comprehensive scoring to ensure the comprehensiveness of the evaluation results. The integral term combines the time variable TTT and the two-dimensional change function to achieve dynamic optimization and real-time evaluation of the design model.

[0086] The multi-dimensional scoring mechanism ensures that all aspects of the design model are fully evaluated, improving the scientificity and credibility of the evaluation. The real-time dynamic evaluation and optimization mechanism can timely discover and solve design problems, shorten the design cycle, and improve design efficiency. The evaluation parameters are automatically adjusted using big data analysis and machine learning models to improve the intelligence level of the evaluation. Through automated evaluation and optimization, human intervention is reduced. The data-driven intelligent evaluation method has promoted the development and progress of denture design and manufacturing technology, and has important academic and application value.

[0087] S3: Upload the denture design results to the platform, and the platform will evaluate the denture design results in real time.

[0088] In order to conduct a comprehensive visual score evaluation of the denture design results, the scoring function of the design model test results and the scoring of the design test results are combined, and the patient denture design and use data are considered to conduct a comprehensive scoring of the denture design results. The formula is expressed as:

[0089]

[0090] Among them, S total Indicates the comprehensive score, S M represents the score of the design model detection result, S D Indicates the design scheme test result score, S usage represents the patient's denture design and use data score, α, β, γ, δ represent the relative importance of different scores, V represents the volume integration area of ​​the model, T represents the total time, Represents the gradient of the design model detection result;

[0091] S total The value threshold is from 0 to positive infinity, S total The higher the value, the higher the overall score of the denture design outcome.

[0092] When S DWhen the score is >80, the denture design is excellent and the next step of evaluation will be entered directly;

[0093] When 60 D When <80, the denture design is medium, and the system will prompt the designer to check the specific inspection;

[0094] When S D <60, the system will mark the denture design as unqualified and redesign it;

[0095] S M When the score is >80, the model accuracy and consistency are good, and the next step of evaluation is directly entered;

[0096] When 50 M When <90, the system will prompt the designer to check the specific deviation points and perform local optimization;

[0097] When S M <50, the system will mark the design as unacceptable and require redesign or major revision.

[0098] 7. The method for detecting the online denture design results based on automatic verification according to claim 6, characterized in that: uploading the denture design results to the platform, and the platform evaluating the denture design results in real time further comprises: when S total When the score is >75, the functional test and performance of the denture design result meet the requirements and the design result passes the evaluation;

[0099] When 45 total When <75, there are some problems in the functional testing and performance of the denture design results. The following tests and optimizations are recommended;

[0100] When S total <45, the system will mark the denture design results as unqualified and redesign them.

[0101] The comprehensive consideration of multiple dimensions, including design model testing, design scheme testing, and usage data, ensures the comprehensiveness and objectivity of the evaluation results. The multi-dimensional evaluation method can more comprehensively reflect the overall quality and performance of the denture design. It improves the scientificity and credibility of the evaluation results, helps to discover potential problems in the design, and provides optimization suggestions.

[0102] All test and evaluation data are uploaded to the online platform for management, which allows designers to check and analyze historical data at any time. Platform management supports data traceability, ensuring the transparency and traceability of the design process. It provides data support for continuous improvement and quality management, and promotes continuous optimization of design and manufacturing.

[0103] ​​​On the other hand, this embodiment also provides an online denture design result detection system based on automatic verification, which includes:

[0104] The data acquisition module collects data related to denture results and patient data, builds a plan detection model, and automatically detects denture design plans.

[0105] The detection module uses 3D printing technology to generate a denture solid model, and uses the solid model detection function to compare and detect the solid model with the denture design model.

[0106] The results evaluation module uploads the denture design results to the platform, and the platform evaluates the denture design results in real time.

[0107] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0108] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0109] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0110] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0111] Example 2

[0112] Ten patients who needed custom dentures were selected as experimental subjects, namely A, B, C, D, E, F, and G. First, a 3D oral scanner was used to collect oral structure data for each patient, including detailed information such as the three-dimensional morphology of the teeth and the distribution of bite force. After the data collection was completed, the data was input into the computer-aided design (CAD) software to generate a personalized denture design model. Each model was customized according to the specific needs of the patient to ensure the accuracy and applicability of the model.

[0113] The physical model of the denture is printed using a high-precision 3D printer and biocompatible materials. During the printing process, the printing parameters (such as layer thickness, printing speed, temperature, etc.) are strictly controlled to ensure the accuracy and consistency of the physical model. After printing, the physical model is accurately measured using a coordinate measuring machine (CMM) to record the coordinate data of each key point.

[0114] The data of the solid model is compared and analyzed with the data of the design model. The point cloud alignment and shape analysis algorithm are used to calculate the deviation value of each model. The specific method is: use the rigid body transformation matrix to align the point cloud data of the solid model and the design model, calculate the Euclidean distance of all points, and smooth them through the Laplace operator to reduce the influence of noise. Through these calculations, the overall deviation value and local deviation distribution of each model are obtained.

[0115] Finally, all the data were uploaded to the online platform, which automatically evaluated the denture design results. The evaluation content included the accuracy, consistency, material properties, physical properties, manufacturing process and environmental impact of the model. The platform generated a detailed test report and optimization suggestions based on the preset evaluation criteria and comprehensive indicators. The experimental data are shown in Table 1.

[0116] Table 1 Experimental data table

[0117] Parameter name A B C D E F G Accuracy deviation(mm) 0.05 0.07 0.06 0.04 0.08 0.05 0.06 consistency(%) 98.5 97.2 97.8 98.9 96.5 98.4 97.6 Material hardness (MPa) 150 148 152 151 149 150 153 Elastic modulus(GPa) 3.2 3.1 3.3 3.2 3 3.2 3.3 Bite force distribution (N) 250 245 260 255 240 250 260 Abrasion resistance (g / 1000cycles) 0.02 0.03 0.02 0.02 0.04 0.02 0.03

[0118] From the data in the table, we can see that significant advantages and innovations have been demonstrated in all key parameters. First, in terms of accuracy deviation, the deviation of the denture models of all patients was between 0.04 and 0.08 mm, which is significantly better than the accuracy of traditional manual detection methods (usually more than 0.1 mm). This result shows that the accuracy of denture design can be effectively improved through the automated detection model, reducing errors caused by human factors.

[0119] In terms of consistency, the model consistency of all patients was between 96.5% and 98.9%, indicating high consistency between the physical model and the design model. This is mainly due to the application of high-precision 3D printing technology and point cloud alignment algorithm, which ensures high restoration and precise alignment during the printing process. Compared with traditional methods, the consistency of the denture model is significantly improved, avoiding errors caused by manual operation.

[0120] In terms of material properties, the hardness and elastic modulus data in the table are within the expected range, showing the reliability and stability of the material. Through precise material testing and evaluation, the present invention can ensure that the physical properties of the used materials meet the design requirements and avoid denture failure caused by insufficient material properties.

[0121] In terms of bite force distribution, the data is evenly distributed between 240 and 260 N, indicating that the designed denture can evenly distribute the bite force, improving the wearing comfort and functionality. In terms of wear resistance, the wear resistance of all samples is between 0.02 and 0.04 g / 1000 cycles, showing the excellent wear resistance of the material and ensuring the service life of the denture.

[0122] The comprehensive evaluation results show that the comprehensive scores of all samples are above 80 points, indicating that the present invention performs well in all evaluation dimensions. This not only reflects the advantages of automated detection and real-time evaluation, but also proves the innovation and practicality of the present invention in terms of accuracy, consistency, material properties and functionality.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting online denture design results based on automatic verification, characterized in that: include: Collect data related to denture results and patients, build a plan detection model, and automatically detect denture design plans; Generate a denture solid model using 3D printing technology, and use the solid model detection function to compare and detect the solid model with the denture design model; Upload the denture design results to the platform, and the platform will evaluate the denture design results in real time.

2. The method for detecting online denture design results based on automatic verification according to claim 1, characterized in that: The collection of data related to the denture results and the patient's relevant data includes obtaining a three-dimensional image of the patient's internal oral structure through a handheld 3D oral scanner; obtaining the patient's occlusal data using a bite recorder; Acquire patient oral health data through medical records; obtain historical patient denture design and use data through databases; use CMM to perform height geometry measurement on solid models.

3. The method for detecting online denture design results based on automatic verification according to claim 2, characterized in that: Collect data related to denture results and patients, build a solution detection model, and automatically detect the denture design solution. In order to automatically monitor and analyze whether the denture design solution complies with industry regulations, and simulate the mechanical properties of the denture design solution in real time, the solution detection model is built by combining denture design rules, FEA algorithms and machine learning. The formula is expressed as follows: Where D represents the result of the scheme detection, Φ(x, y, z) represents the displacement field function of the finite element analysis, α represents the attenuation coefficient, t represents the time variable, and V represents the volume of the denture design. represents the Laplace operator, w i represents the weight of the i-th rule, F i (x) represents the rule-based detection function, N represents the total number of rules, G j (y) represents the detection function of the machine learning model, y represents the input parameter set of the model, and M represents the total number of machine learning models; In order to quantify the detection of denture design schemes, a scoring formula is designed, which is expressed as follows: Among them, S D Indicates the score of the design test result, H k (D) represents the kth detection index function, β k represents the weight coefficient of the indicator, P represents the total number of detection indicators, E(z) represents the normalized function based on the specific parameter set z, T represents the total time, Ψ(u,v) represents the two-dimensional variation function of the detection result, and u and υ are two variables of the function respectively; The value range of D is from 0 to positive infinity. The larger the value of D is, the less the test results meet the design standards and requirements. S D The value range of S is from 0 to positive infinity. The higher the value of S is, the higher the score of the detection result is.

4. The method for detecting online denture design results based on automatic verification according to claim 3, characterized in that: The denture solid model is generated by 3D printing technology, and the solid model detection function is used to compare and detect the solid model with the denture design model. In order to reduce the error in denture production and solve the problem of whether the denture design model can be implemented, the 3D solid model measurement data is compared with the original design model data using point cloud alignment and shape analysis, and the solid model detection function is constructed. The formula is expressed as: Where M(P,Q) represents the solid model detection function, P(x,y,z) represents the point cloud of the designed model, Q(x,y,z′) represents the point cloud of the actual 3D printed model, R represents the rigid body transformation matrix, ||·|| represents the Euclidean distance, and λ represents the regularization parameter. represents the Laplace operator, V p represents the volume integration area of ​​the denture design model, D i is the distance deviation of the i-th point, μ i is the expected distance deviation, α is the smoothing parameter, and N is the total number of points; In order to quantify the detection results of the designed model, a scoring formula is designed, which is expressed as follows: Where S M represents the scoring function of the design model detection result, M j represents the model detection value of the jth detection point, β j represents the weight coefficient of the jth point, M represents the total number of detection points, Ψ(u,v) represents the two-dimensional change function of the detection result, u and v are the two variables of the function, and T represents the total time; The value threshold of M(P,Q) ranges from 0 to positive infinity, and the lower the value, the smaller the deviation between the designed model and the actual model; The value threshold of S(M) ranges from 0 to positive infinity. The higher the value, the higher the score of the test result, that is, the lower the quality of the denture design solution, indicating that the design needs further optimization and improvement.

5. The method for detecting online denture design results based on automatic verification according to claim 4, characterized in that: The denture design results are uploaded to the platform, and the platform evaluates the denture design results in real time. In order to conduct a comprehensive visual score evaluation of the denture design results, the denture design results are comprehensively scored by combining the design model test result scoring function and the design test result scoring, and considering the patient's denture design and use data. The formula is expressed as: Among them, S total Indicates the comprehensive score, S M represents the score of the design model detection result, S D Indicates the design scheme test result score, S usage represents the patient's denture design and use data score, α, β, γ, δ represent the relative importance of different scores, V represents the volume integration area of ​​the model, T represents the total time, Represents the gradient of the design model detection result; S total The value threshold is from 0 to positive infinity, S total The higher the value, the higher the overall score of the denture design outcome.

6. The method for detecting online denture design results based on automatic verification according to claim 5, characterized in that: The denture design results are uploaded to the platform, and the platform evaluates the denture design results in real time. D When the score is >80, the denture design is excellent and the next step of evaluation will be entered directly; When 60 D When <80, the denture design is medium, and the system will prompt the designer to check the specific inspection;​ When S D <60, the system will mark the denture design as unqualified and redesign it; S M When the score is >80, the model accuracy and consistency are good, and the next step of evaluation is directly entered; When 50 M When <90, the system will prompt the designer to check the specific deviation points and perform local optimization;​ When S M <50, the system will mark the design as unacceptable and require redesign or major revision.

7. The method for detecting online denture design results based on automatic verification according to claim 6, characterized in that: The denture design results are uploaded to the platform, and the platform evaluates the denture design results in real time. total When the score is >75, the functional test and performance of the denture design result meet the requirements and the design result passes the evaluation; When 45 total When <75, there are some problems in the functional testing and performance of the denture design results. The following tests and optimizations are recommended;​ When S total <45, the system will mark the denture design results as unqualified and redesign them.

8. An online denture design result detection system based on automatic verification using the method according to any one of claims 1 to 7, characterized in that: Data collection module, which collects data related to denture results and patient data, builds a scheme detection model, and automatically detects denture design schemes; The detection module uses 3D printing technology to generate a denture solid model, and uses a solid model detection function to compare and detect the solid model with the denture design model; The results evaluation module uploads the denture design results to the platform, and the platform evaluates the denture design results in real time.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the online denture design results detection method based on automatic verification are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of an online denture design results detection method based on automatic verification are implemented.

Images