Correction strategy generation method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of invisible orthodontics, and discloses a correction strategy generation method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a target form correction model for a target part, and initial point cloud data generated by a recycled invisible corrector at multiple angles; constructing an actual form correction model corresponding to the invisible corrector based on the initial point cloud data; generating a deformation prediction model of the invisible corrector based on the physical characteristics of the invisible corrector; comparing the deformation prediction model with the actual form correction model to obtain a first form comparison result, and comparing the target form correction model with the actual form correction model to obtain a second form comparison result; and updating a correction strategy for the target part according to the first form comparison result and the second form comparison result, and generating a target correction strategy. By implementing the technical scheme of the invention, a personalized invisible correction strategy can be accurately generated, so that the correction effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of invisible orthodontic technology, and in particular to a correction strategy generation method, device, computer equipment and storage medium. Background Art

[0002] During invisible orthodontic treatment, each set of invisible braces is designed and manufactured according to specific correction goals. However, many factors, such as the patient's wearing time, wearing method, and physical properties of the braces, can affect the actual correction effect, causing the correction process at certain stages to fail to achieve the expected goals, which in turn causes deviations and gradually accumulates. Summary of the invention

[0003] In view of this, the present invention provides a correction strategy generation method, apparatus, computer device and storage medium to solve the problem that the effect of the orthodontic appliance deviates from the expected due to wearing factors and physical factors of the orthodontic appliance during invisible orthodontic treatment.

[0004] In a first aspect, the present invention provides a correction strategy generating method, comprising: obtaining a target morphological correction model for a target part, and initial point cloud data generated at multiple angles of an invisible corrector recovered from the target part; constructing an actual morphological correction model corresponding to the invisible corrector based on the spatial relationship between the initial point cloud data at multiple angles; generating a deformation prediction model of the invisible corrector based on the physical properties of the invisible corrector; comparing the deformation prediction model with the actual morphological correction model to obtain a first morphological comparison result, and comparing the target morphological correction model with the actual morphological correction model to obtain a second morphological comparison result; updating the correction strategy for the target part according to the first morphological comparison result and the second morphological comparison result to generate a target correction strategy.

[0005] The correction strategy generation method provided in the embodiment of the present invention lays the foundation for accurate analysis and ensures the comprehensiveness of the data by acquiring the target morphological correction model and recovering the multi-angle initial point cloud data of the invisible corrector. The actual morphological correction model is constructed by using spatial relationships to truly reflect the actual state of the corrector. The deformation prediction model generated based on physical properties can effectively predict its changing trend during use. The deformation prediction model and the target morphological correction model are respectively compared with the actual morphological correction model, and the differences are accurately analyzed from different angles. The comparison results provide a key basis for updating the correction strategy, so that the generated target correction strategy is both scientific and targeted, which effectively improves the correction effect and efficiency.

[0006] In an alternative embodiment, a deformation prediction model of the invisible aligner is generated based on the physical characteristics of the invisible aligner: the force parameters of the target site and the material property parameters corresponding to the invisible aligner are obtained; deformation simulation is performed on the target shape correction model based on the force parameters and the material property parameters to obtain the deformation prediction model.

[0007] The correction strategy generation method provided by the embodiments of the present invention fully considers the key factors affecting the deformation of the aligner by obtaining the force parameters of the target site and the material property parameters of the invisible aligner, laying a foundation for subsequent accurate simulation. Deformation simulation is performed on the target shape correction model based on these parameters to generate a deformation prediction model, enabling the model to closely combine with the physical conditions in the actual use scenario and highly accurately predict the deformation of the invisible aligner under force, providing a very valuable reference basis for doctors or orthodontic professionals to pre-evaluate possible problems during the correction process and timely adjust the correction strategy, effectively improving the controllability and accuracy of the entire correction process.

[0008] In an alternative embodiment, the deformation prediction model and the actual shape correction model are compared to obtain a first shape comparison result, including: registering the deformation prediction model and the actual shape correction model to generate a registration result between the deformation prediction model and the actual shape correction model; performing data measurement on the registration result based on a preset distance measurement rule to determine first deviation data between the deformation prediction model and the actual shape correction model; wherein, the first shape comparison result includes the first deviation data.

[0009] The correction strategy generation method provided by the embodiments of the present invention can achieve precise correspondence in spatial position between the two by registering the deformation prediction model and the actual shape correction model and generating a registration result, creating good conditions for subsequent accurate comparison. Performing data measurement on the registration result based on a preset distance measurement rule to determine the first deviation data can accurately quantify the difference between the two, clearly presenting the deviation degree between the actual deformation and the predicted deformation of the invisible aligner, enabling doctors or orthodontic professionals to intuitively and accurately grasp the abnormal conditions during the correction process, providing a reliable quantitative basis for timely adjusting the correction strategy, and effectively ensuring the accuracy and effectiveness of orthodontic treatment.

[0010] In an alternative embodiment, the target form correction model and the actual form correction model are compared to obtain a second form comparison result, including preliminarily registering the target form correction model and the actual form correction model according to preset feature matching points to obtain a preliminary registration result; determining the closest points between the target form correction model and the actual form correction model based on the preliminary registration result; iteratively optimizing the preliminary registration result according to the closest points to obtain an optimized result; and performing data measurement on the optimized result based on a distance measurement rule to determine second deviation data between the target form correction model and the actual form correction model; wherein the second form comparison result includes the second deviation data.

[0011] The correction strategy generation method provided by the embodiments of the present invention performs preliminary registration according to preset feature matching points, building a basic framework for subsequent precise comparison and enabling the target form correction model and the actual form correction model to initially meet the comparable conditions. Then, the closest points are determined and the preliminary registration result is iteratively optimized based on them, greatly improving the accuracy and reliability of the registration and making the comparison between the models more in line with the actual situation. By using the distance measurement rule to measure the optimized result to obtain the second deviation data, the difference between the two can be accurately quantified, clearly presenting the deviation between the actual and target forms, thereby providing key data support for doctors or orthodontic professionals to comprehensively and deeply understand the deviation during the correction process, effectively assisting doctors or orthodontic professionals to accurately adjust the correction strategy, and effectively improving the quality and success rate of orthodontic treatment.

[0012] In an alternative embodiment, based on the value of the second deviation data, the display mode of the deviation area between the target form correction model and the actual form correction model is determined.

[0013] The correction strategy generation method provided by the embodiments of the present invention can convert abstract deviation data into an intuitive visual presentation, enabling doctors or orthodontic professionals to quickly and clearly identify the specific areas where there are differences between the target form correction model and the actual form correction model. This accurate and intuitive display method helps doctors or orthodontic professionals quickly focus on the problems in the complex correction process, thereby efficiently judging the severity and distribution range of the deviation.

[0014] In an alternative embodiment, the correction strategy for the target part is updated according to the first form comparison result and the second form comparison result to generate a target correction strategy, including: if the first deviation data and / or the second deviation data is greater than a preset threshold, a warning message is generated; in response to a strategy update operation generated according to the warning message, the correction strategy is updated according to the strategy update operation to generate a target correction strategy.

[0015] The correction strategy generation method provided by the embodiments of the present invention generates warning information by setting a preset threshold and comparing the first deviation data and / or the second deviation data with the threshold, realizing sensitive monitoring of abnormal situations during the correction process, and being able to promptly capture the significant deviation between the actual state and the expected state of the invisible aligner. The strategy update operation generated in response to the warning information enables the correction strategy to quickly make targeted adjustments according to the actual deviation situation, ensuring that the generated target correction strategy always meets the correction requirements of the patient's target part. This dynamic correction strategy update mechanism effectively avoids problems such as poor correction effects caused by deviation accumulation, and greatly improves the accuracy, reliability, and safety of orthodontic treatment.

[0016] In an alternative embodiment, based on the spatial relationship between the initial point cloud data from multiple angles, a correction model of the actual shape corresponding to the invisible aligner is constructed, including: denoising the initial point cloud data to obtain the denoised initial point cloud data; splicing the denoised initial point cloud data based on the spatial relationship between the initial point cloud data from multiple angles to obtain the spliced point cloud data; and performing meshing processing on the spliced point cloud data to generate a correction model of the actual shape corresponding to the invisible aligner.

[0017] The correction strategy generation method provided by the embodiments of the present invention effectively removes the interference factors in the data by denoising the initial point cloud data, ensuring that the data for subsequent operations is cleaner and more accurate, and laying a solid foundation for constructing an accurate correction model of the actual shape. Splicing the denoised initial point cloud data based on the spatial relationship can organically integrate the data from multiple angles, completely restore the shape information of the invisible aligner, and avoid data loss or incorrect splicing. Finally, meshing processing is performed to generate a correction model of the actual shape, enabling the model to have good topological structure and geometric characteristics while maintaining accuracy, thus greatly improving the construction quality of the correction model of the actual shape and providing a reliable guarantee for accurately evaluating the state of the invisible aligner and formulating effective correction strategies.

[0018] In a second aspect, the present invention provides a correction strategy generation device, including: an acquisition module, configured to acquire a target form correction model for a target part and initial point cloud data generated by a retrieved invisible aligner for the target part at multiple angles; a construction module, configured to construct an actual form correction model corresponding to the invisible aligner based on the spatial relationship between the initial point cloud data at multiple angles; a prediction module, configured to generate a deformation prediction model for the invisible aligner based on the physical characteristics of the invisible aligner; a comparison module, configured to compare the deformation prediction model with the actual form correction model to obtain a first form comparison result, and compare the target form correction model with the actual form correction model to obtain a second form comparison result; and a generation module, configured to update the correction strategy for the target part according to the first form comparison result and the second form comparison result to generate a target correction strategy.

[0019] In a third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the correction strategy generation method according to the first aspect or any corresponding embodiment thereof.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the correction strategy generation method according to the first aspect or any corresponding embodiment thereof.

[0021] In a fifth aspect, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the correction strategy generation method according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 is a flowchart of a correction strategy generation method according to an embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of a desktop three-dimensional scanner scanning an invisible tooth aligner according to an embodiment of the present invention;

[0025] Figure 3 is a flowchart of another correction strategy generation method according to an embodiment of the present invention;

[0026] Figure 4 It is a schematic diagram of the actual morphological correction model corresponding to the invisible tooth aligner according to an embodiment of the present invention;

[0027] Figure 5 It is a schematic flowchart of another method for generating a correction strategy according to an embodiment of the present invention;

[0028] Figure 6 It is a schematic diagram of the error heat map according to an embodiment of the present invention;

[0029] Figure 7 It is a structural block diagram of a correction strategy generation device according to an embodiment of the present invention;

[0030] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0032] During orthodontic treatment, each orthodontic appliance (such as an invisible dental aligner) is designed and manufactured according to specific treatment goals. However, during actual wearing, various factors such as the wearing duration, wearing method of the patient, and minor deformation of the material often result in the correction effect in some stages of the treatment not meeting the expectations, thus accumulating errors. Current monitoring methods, such as regular follow-up visits or using traditional scanning techniques, usually can only evaluate the correction situation when the patient visits the doctor, and cannot make full use of the important deformation carrier of the used orthodontic appliance. In fact, by performing high-precision three-dimensional scanning on the recycled orthodontic appliance and comparing it with the original design model, the actual deformation situation can be quantified, thereby inferring whether the treatment goal is achieved. However, invisible orthodontic appliances are generally made of transparent or semi-transparent polymer materials, and are easily affected by problems such as light penetration and refraction during optical scanning, which in turn affects the scanning accuracy, reconstruction quality, and registration reliability. Therefore, how to accurately obtain the external shape data of the orthodontic appliance and clearly display the error distribution through registration and deviation analysis has become an urgent technical problem in the current orthodontic field.

[0033] In view of this, the technical solution of the present invention obtains the initial point cloud data of the target form correction model and the recycled invisible aligner from multiple perspectives, constructs the actual form correction model based on the spatial relationship of these initial point cloud data, and generates a deformation prediction model by using the physical characteristics of the aligner. Subsequently, the deformation prediction model, the target form correction model and the actual form correction model are compared to obtain the comparison results of the two forms. According to these comparison results, the correction strategy is updated and the target correction strategy is generated, so as to comprehensively understand the differences among the actual state, the ideal state and the predicted state of the aligner, scientifically and effectively adjust the correction strategy, greatly improve the accuracy and success rate of correction, and effectively guarantee the orthodontic treatment effect.

[0034] According to an embodiment of the present invention, there is provided an embodiment of a correction strategy generation method. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0035] In this embodiment, a correction strategy generation method is provided, which can be used in computer devices such as laptop computers and desktop computers. Figure 1 It is a flowchart of the correction strategy generation method according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0036] Step S101, obtain a target form correction model for a target part, and initial point cloud data generated by the recycled invisible aligner for the target part from multiple angles.

[0037] The target part refers to a specific area of the human body that needs form correction, such as teeth, gums or other related oral structures that need to be corrected. The target form correction model is pre-designed and constructed according to factors such as the initial condition of the patient's target part, the orthodontic treatment goal, and the ideal path of adjustment of the target part, through professional orthodontic design software or with the help of previous clinical experience and orthodontic theory. Taking tooth correction as an example, the target form correction model represents the ideal position, arrangement state of the teeth and the ideal form of the corresponding invisible aligner at each treatment stage. Specifically, doctors or orthodontic professionals use a variety of diagnostic techniques (such as imaging examinations, functional tests, etc.) to comprehensively collect relevant information about the target part, including its anatomical structure, physiological movement pattern, etc., and establish three-dimensional model data of the target part. According to the standard process and expected goal of orthodontic treatment, use professional orthodontic design software for design and planning, set the ideal state of the target part in the software, and thus generate the target form correction model for each stage.

[0038] Taking orthodontics as an example, a doctor or orthodontic professional conducts an oral examination on the patient, including the arrangement of teeth, occlusion, etc., to obtain three-dimensional model data of the oral cavity. Then, according to the standard process and expected goals of orthodontic treatment, professional orthodontic design software (such as 3Shape, OrthoCAD, etc.) is used for design and planning. The ideal movement steps and final positions of the teeth are set in the software, so as to generate the target morphological correction model for each stage.

[0039] The recycled invisible aligner refers to the appliance that has been used by the patient for a period of time and then recycled. The initial point cloud data refers to the set of coordinate information of a large number of discrete points obtained by scanning the recycled invisible aligner from multiple directions. Specifically, the recycled invisible aligner is placed on a special scanning platform, and a three-dimensional scanner equipped with a high-precision rotating device and an advanced optical sensor is used for scanning. Driven by a computer device, the scanner performs non-contact optical measurements on the invisible aligner from multiple angles according to the preset scanning path and angle sequence. Before scanning, appropriate pretreatment measures (such as spraying special optical enhancers or performing surface cleaning) can be taken according to the material characteristics and surface optical properties of the invisible aligner to improve the quality and accuracy of the scanned data and ensure the acquisition of complete and accurate initial point cloud data from multiple angles.

[0040] Taking orthodontics as an example, as Figure 2 shown, a desktop three-dimensional scanner (such as a structured light scanner or a laser scanner) is used to collect high-precision point cloud data of the recycled invisible aligner (dental appliance). For transparent materials, matte powder can be sprayed or anti-reflection treatment can be carried out before scanning to reduce interference. In addition, a fixture or an automatic rotating table can be used to collect the recycled dental appliance from multiple angles.

[0041] Step S102, based on the spatial relationship between the initial point cloud data from multiple angles, construct the actual morphological correction model corresponding to the invisible aligner.

[0042] The spatial relationship refers to the relative position, angle, and topological connection between points in the three-dimensional space of the initial point cloud data of the invisible aligner obtained from different angles. The actual morphological correction model is a digital representation of the true shape of the recycled invisible aligner. Specifically, the initial point cloud data from different angles are aligned and registered, and the data from each perspective are aligned to a unified coordinate system using a preset algorithm. Then, through three-dimensional reconstruction technology, these aligned initial point cloud data are fused to generate a complete three-dimensional model, accurately reflecting the actual shape of the invisible aligner.

[0043] Step S103, based on the physical characteristics of the invisible aligner, generate a deformation prediction model of the invisible aligner.

[0044] Physical properties refer to factors such as the material, hardness, elasticity, plasticity, and deformation laws after force application of the invisible aligner. These properties determine how the invisible aligner deforms under different conditions (such as force application, heating, etc.). The deformation prediction model is a mathematical or computational model that, based on the physical properties of the invisible aligner, is used to predict how the aligner deforms when an external force is applied or during use. Specifically, the material properties of the invisible aligner (such as elasticity, hardness, plasticity, etc.) are analyzed, and then mechanical modeling is used to simulate the deformation behavior of the invisible aligner under different external forces. Using these physical properties and mechanical models, the deformation process of the invisible aligner when force or pressure is applied is calculated, thereby generating a deformation prediction model.

[0045] Step S104: Compare the deformation prediction model with the actual shape correction model to obtain a first shape comparison result, and compare the target shape correction model with the actual shape correction model to obtain a second shape comparison result.

[0046] The first shape comparison result refers to comparing the deformation prediction model of the invisible aligner with the actual shape correction model to evaluate the difference between the deformation generated after applying force to the target site of the invisible aligner and the actual correction model. The second shape comparison result refers to comparing the target shape correction model with the actual shape correction model, aiming to evaluate the difference between the expected shape (target shape) that the invisible aligner will finally adjust the target site to and the actual performance of the actual aligner. Specifically, a preset quantitative index can be used to calculate the difference between the deformation prediction model and the actual shape correction model to obtain the first shape comparison result; similarly, a similar measurement standard can be used to evaluate the difference between the target shape correction model and the actual shape correction model, thereby obtaining the second shape comparison result.

[0047] Step S105: Update the correction strategy for the target site according to the first shape comparison result and the second shape comparison result to generate a target correction strategy.

[0048] The target correction strategy refers to a new correction plan or method formulated for the target site. Specifically, by analyzing the first shape comparison result and the second shape comparison result, the difference between the predicted deformation of the invisible aligner and the actual effect is determined, and based on this, the usage method and parameter settings of the invisible aligner are further adjusted.

[0049] The correction strategy generation method provided by the embodiments of the present invention lays a foundation for accurate analysis by obtaining the target form correction model and the multi-angle initial point cloud data of the retrieved invisible aligner, ensuring the comprehensiveness of the data. The actual form correction model is constructed using spatial relationships, which can truly reflect the actual state of the aligner. The deformation prediction model generated based on physical properties effectively estimates its change trend during use. By comparing the deformation prediction model and the target form correction model with the actual form correction model respectively, the differences are accurately analyzed from different angles, and the obtained comparison results provide a key basis for updating the correction strategy, making the generated target correction strategy both scientific and targeted, and effectively improving the correction effect and efficiency.

[0050] In this embodiment, a correction strategy generation method is provided, which can be used in computer devices such as laptop computers and desktop computers. Figure 3 It is a flowchart of the correction strategy generation method according to the embodiments of the present invention, as Figure 3 shown, and this process includes the following steps:

[0051] Step S201, obtain the target form correction model for the target part, and the initial point cloud data generated by the retrieved invisible aligner for the target part at multiple angles. For details, please refer to Figure 1 Step S101 of the embodiment shown, which will not be elaborated here.

[0052] Step S202, based on the spatial relationship between the initial point cloud data at multiple angles, construct the actual form correction model corresponding to the invisible aligner.

[0053] Specifically, the above step S202 includes:

[0054] Step S2021, perform denoising processing on the initial point cloud data to obtain the denoised initial point cloud data.

[0055] During the acquisition process of the initial point cloud data, some scattered points and noises may be mixed in, which will affect the accuracy of subsequent model construction. Specifically, filtering algorithms such as Statistical Outlier Removal and Radius Outlier Removal can be used to screen the initial point cloud data, removing those scattered points and noises that significantly deviate from the normal data distribution, so as to obtain relatively pure denoised initial point cloud data.

[0056] Step S2022, based on the spatial relationship between the initial point cloud data at multiple angles, splice the denoised initial point cloud data to obtain the spliced point cloud data.

[0057] The initial point cloud data after denoising comes from multiple-angle scans of the invisible aligner, and they are in different relative positions in space. Using feature matching technology, similar feature points in the initial point cloud data from different angles are found, or a calibration target is used to determine the relative position relationship of the point clouds from different angles. According to these spatial relationships, the initial point cloud data from each angle is integrated so that they are stitched together under a unified coordinate system, and finally the stitched point cloud data is obtained to ensure that the point cloud data can completely reflect the overall shape of the invisible aligner.

[0058] Step S2023: Perform meshing on the stitched point cloud data to generate an actual shape correction model corresponding to the invisible aligner.

[0059] Convert the stitched point cloud data into a triangular mesh, which can be achieved through algorithms such as Poisson reconstruction or Marching Cubes. After conversion, if it is found that there are small holes or irregular edges in the generated mesh, it can be repaired in an automatic or manual manner to ensure the integrity and closure of the mesh. After these operations, an actual shape correction model corresponding to the invisible aligner is generated, and this model can accurately present the actual shape of the invisible aligner.

[0060] Taking tooth correction as an example, as Figure 4 shown, the multi-viewpoint cloud data of the collected invisible tooth aligner (dental brace) is stitched, denoised, and meshed to form a high-fidelity three-dimensional model of the dental brace surface. Post-processing such as smoothing and hole repair is performed on the generated three-dimensional model to enhance the model integrity and measurement stability. In addition, in order to optimize the model, it can be moderately simplified (reduce the number of redundant faces), while retaining the key features of the dental brace.

[0061] The correction strategy generation method provided by the embodiments of the present invention effectively removes the interference factors in the data through denoising the initial point cloud data, ensuring that the data on which subsequent operations are based is purer and more accurate, laying a solid foundation for constructing an accurate actual shape correction model. Stitching the denoised initial point cloud data based on spatial relationships can organically integrate the data from multiple angles, completely restoring the shape information of the invisible aligner, and avoiding data loss or incorrect stitching. Finally, meshing is performed to generate an actual shape correction model, enabling the model to have good topological structures and geometric characteristics while maintaining accuracy, thereby greatly improving the construction quality of the actual shape correction model and providing a reliable guarantee for accurately evaluating the state of the invisible aligner and formulating effective correction strategies.

[0062] Step S203: Generate a deformation prediction model of the invisible aligner based on the physical characteristics of the invisible aligner.

[0063] Specifically, the above step S203 includes:

[0064] Step S2031: Obtain the force parameters of the target part and the material property parameters corresponding to the invisible aligner.

[0065] The force parameters refer to the relevant parameters of the force exerted by the target part on the invisible aligner during normal physiological activities, functional movements, and the correction process. Taking tooth correction as an example, it includes the magnitude of the force, such as the pressure values generated by the teeth on the invisible aligner during actions like chewing, speaking, and swallowing; it includes the direction of the force, that is, the vector direction of the acting force, and different oral actions may cause the force to act on the aligner from different angles; there is also the point of application of the force, specifying which specific parts of the invisible aligner are subjected to the force from the target part. Specifically, high-precision sensors can be placed near the target part to monitor the magnitude and direction of the force exerted on the aligner during various daily activities and functional movements of the target part, and through long-term data collection and analysis, common force-bearing situations can be determined. Or, motion tracking technology can be used in combination with biomechanical models to simulate the movement process of the target part and calculate the force parameters generated on the invisible aligner under different actions. At the same time, referring to a large number of clinical case data of similar target parts and relevant biomechanical research results, the force-bearing situation of specific target parts can be estimated and adjusted.

[0066] Taking tooth correction as an example, high-precision pressure sensors can be placed in the patient's oral cavity to monitor the magnitude and direction of the pressure exerted by the teeth on the aligner under different oral activity states. After a period of data collection and analysis, typical force-bearing situations can be determined. Or, motion capture technology can be used in combination with biomechanical models to simulate the patient's oral movements and calculate the force parameters that the target part may generate on the aligner under various actions. At the same time, referring to a large number of clinical case data and relevant oral biomechanical research results, the force-bearing situation of specific types of correction cases can be estimated and corrected.

[0067] The material property parameters refer to the physical and mechanical performance indicators of the invisible aligner material itself. For example, it includes the elastic modulus of the material, which reflects the ability of the material to resist elastic deformation. The larger the elastic modulus, the smaller the deformation of the material under the same external force; there is also the deformation recovery coefficient, which determines the ability of the material to return to its original state after being deformed by force; in addition, it can also include parameters such as the Poisson's ratio and yield strength of the material, and these parameters together describe the behavioral characteristics of the material when subjected to force. Specifically, the detailed technical specification documents of the material can be requested from the material manufacturer of the invisible aligner, which will contain key parameters such as the elastic modulus and Poisson's ratio. For some special or new materials, special material testing experiments, such as tensile and compression tests, can be carried out, and the relevant material property parameters can be calculated based on the experimental data.

[0068] Step S2032: Perform deformation simulation on the target shape correction model based on the force parameters and material property parameters to obtain a deformation prediction model.

[0069] Specifically, a professional finite element analysis (FEA) software can be used to create a simulation environment. Import the target shape correction model into the software, and accurately set the material properties of the model in the software according to the material property parameters of the invisible aligner. For example, input parameters such as the elastic modulus, Poisson's ratio, and yield strength of the material, so that the model in the software has similar material mechanical properties to the actual invisible aligner. According to the obtained force parameters of the target part, apply corresponding forces to the target shape correction model in the software. This requires accurately determining the magnitude, direction, and application point of the force, and converting this information into loading conditions recognizable by the software. During the process of applying the force, the mechanical action mode of the target part in the actual movement and usage scenarios should be fully considered to ensure that the applied force conforms to the actual situation. Then, start the calculation program of the finite element analysis software. The software divides the target shape correction model into a large number of tiny elements according to the set material properties and force conditions, and gradually calculates the deformation of the entire model after being subjected to the force by solving the mechanical equilibrium equations of each element under the action of the force. During the calculation process, the software will continuously iterate and optimize the calculation results to improve the accuracy of the simulation. After a series of complex calculation and simulation processes, a deformation prediction model that can reflect the possible shape changes of the invisible aligner under the action of the force on the target part is finally obtained.

[0070] Step S204: Compare the deformation prediction model with the actual shape correction model to obtain a first shape comparison result, and compare the target shape correction model with the actual shape correction model to obtain a second shape comparison result. For details, please refer to Figure 1 Step S104 of the embodiment shown, which will not be elaborated here.

[0071] Step S205: Update the correction strategy for the target part according to the first shape comparison result and the second shape comparison result to generate a target correction strategy. For details, please refer to Figure 1 Step S105 of the embodiment shown, which will not be elaborated here.

[0072] The correction strategy generation method provided by the embodiments of the present invention takes into account the key factors affecting the deformation of the orthodontic appliance by obtaining the force parameters of the target part and the material characteristic parameters of the invisible orthodontic appliance, laying a foundation for subsequent accurate simulation. Based on these parameters, a deformation simulation is performed on the target shape correction model to generate a deformation prediction model, enabling the model to closely combine the physical conditions in the actual usage scenario and highly accurately predict the deformation of the invisible orthodontic appliance under force, providing a valuable reference basis for doctors or orthodontic professionals to pre-evaluate possible problems during the correction process and timely adjust the correction strategy, effectively improving the controllability and accuracy of the entire correction process.

[0073] In this embodiment, a correction strategy generation method is provided, which can be used in computer devices such as laptop computers and desktop computers. Figure 5 It is a flowchart of the correction strategy generation method according to the embodiments of the present invention, as Figure 5 shown, and the process includes the following steps:

[0074] Step S301, obtain a target shape correction model for the target part and the initial point cloud data generated by the recovered invisible orthodontic appliance for the target part at multiple angles. For details, please refer to Figure 3 Step S201 of the embodiment shown, which will not be elaborated here.

[0075] Step S302, construct an actual shape correction model corresponding to the invisible orthodontic appliance based on the spatial relationship between the initial point cloud data at multiple angles. For details, please refer to Figure 3 Step S202 of the embodiment shown, which will not be elaborated here.

[0076] Step S303, generate a deformation prediction model for the invisible orthodontic appliance based on the physical characteristics of the invisible orthodontic appliance. For details, please refer to Figure 3 Step S203 of the embodiment shown, which will not be elaborated here.

[0077] Step S304, compare the deformation prediction model with the actual shape correction model to obtain a first shape comparison result, and compare the target shape correction model with the actual shape correction model to obtain a second shape comparison result.

[0078] Specifically, the above step S304 includes:

[0079] Step S3041, register the deformation prediction model with the actual shape correction model to generate a registration result between the deformation prediction model and the actual shape correction model.

[0080] The registration result refers to a state description obtained after matching and aligning the deformation prediction model and the actual morphological correction model in terms of spatial position and geometric shape. Specifically, a feature-based registration method or an improved method based on the Iterative Closest Point (ICP) algorithm can be used to register the deformation prediction model and the actual morphological correction model. Feature-based registration first extracts key feature points on the deformation prediction model and the actual morphological correction model, such as the vertices of geometric shapes, edge turning points, etc., and then calculates a transformation matrix by finding the corresponding relationships of these feature points between the deformation prediction model and the actual morphological correction model, and uses mathematical methods such as the least squares method to perform transformations such as translation, rotation, and scaling on one of the models to make it coincide with the other model as much as possible in space, thereby obtaining the registration result. The improved method based on the ICP algorithm first roughly aligns the deformation prediction model and the actual morphological correction model initially, and then continuously iteratively finds the closest point pairs and calculates the transformation that minimizes the distance between these point pairs until a certain convergence condition is met, and finally obtains the registration result.

[0081] Step S3042, perform data measurement on the registration result based on a preset distance measurement rule to determine the first deviation data between the deformation prediction model and the actual morphological correction model; among them, the first morphological comparison result includes the first deviation data.

[0082] The distance measurement rule is a preset standard and method for measuring the spatial distance difference between two models, such as point-point distance, point-plane distance, etc. The first deviation data is obtained by performing data measurement on the registration result based on the preset distance measurement rule, and it reflects the local or overall spatial position difference value between the deformation prediction model and the actual morphological correction model after registration. Specifically, according to the selected distance measurement rule, corresponding points or regions are selected on the registered deformation prediction model and the actual morphological correction model. Calculate the distance values of all corresponding points, and perform statistical analysis on these distance values, such as calculating the average value, maximum value, root mean square value, etc. These statistical results are the first deviation data, which is used as an important part of the first morphological comparison result for subsequent judgment of the correction strategy update.

[0083] The correction strategy generation method provided by the embodiments of the present invention can achieve precise correspondence between the deformation prediction model and the actual shape correction model in terms of spatial position by registering them and generating a registration result, creating good conditions for subsequent precise comparison. Based on a preset distance measurement rule, data measurement is performed on the registration result to determine the first deviation data, which can accurately quantify the difference between the two, clearly presenting the deviation degree of the actual deformation of the invisible aligner from the predicted deformation, enabling doctors or orthodontic professionals to intuitively and accurately grasp the abnormal conditions during the correction process, providing a reliable quantitative basis for timely adjustment of the correction strategy, and strongly ensuring the accuracy and effectiveness of orthodontic treatment.

[0084] Step S3043: Perform preliminary registration on the target shape correction model and the actual shape correction model according to the preset feature matching points to obtain a preliminary registration result.

[0085] Feature matching points are representative and unique points selected in the target shape correction model and the actual shape correction model, which can reflect the key features and structural information of the models. For example, in scenarios related to tooth correction, they can be points at the cusp tips, incisal edges, etc.

[0086] The preliminary registration result refers to the relative position and attitude relationship and other information between the two models obtained after performing a preliminary alignment operation on the target shape correction model and the actual shape correction model by using the preset feature matching points. Specifically, on the target shape correction model and the actual shape correction model, according to the pre-determined rules and methods, accurately select and mark the feature matching points. For example, in a tooth correction model, determine the positions of the feature points based on obvious anatomical features such as cusp tips and incisal edges, and perform corresponding markings on the two models. Establish a one-to-one correspondence between the marked feature matching points on the target shape correction model and the actual shape correction model. By analyzing the geometric positions, local shapes and other feature information of the feature points, determine which points are corresponding in the two models. Based on the established correspondence of the feature points, use certain algorithms and mathematical models to calculate the initial transformation relationship between the two models, which may include transformation parameters such as translation and rotation. According to the calculated transformation parameters, perform corresponding translation and rotation operations on the actual shape correction model to align it with the target shape correction model to a certain extent, thereby obtaining the preliminary registration result.

[0087] Step S3044: Based on the preliminary registration result, determine the closest points between the target shape correction model and the actual shape correction model.

[0088] The closest points refer to the pair of points with the shortest distance between the target form correction model and the actual form correction model after preliminary registration based on preset feature matching points. Specifically, after preliminary registration, for each point on the target form correction model, by calculating its distance from all points on the actual form correction model (such as using metrics like Euclidean distance), the point on the actual form correction model that is closest to this point is found, thus forming a set of closest point pairs. This process can be accelerated by using efficient spatial search algorithms (such as KD-Tree, etc.) to calculate distances and find closest points, improving the calculation efficiency.

[0089] Step S3045: Perform iterative optimization according to the preliminary registration result of the closest point pairs to obtain the optimization result.

[0090] The optimization result refers to a more accurate registration state obtained after multiple adjustments based on the closest point pair model on the basis of the preliminary registration result. Specifically, the Iterative Closest Point (ICP) algorithm or its improved version can be used for iterative optimization. Taking the basic ICP algorithm as an example, first determine the closest point pairs according to the preliminary registration result. Based on these closest point pairs, calculate the transformation parameters that can make the target form correction model and the actual form correction model closer, including the translation vector and the rotation matrix. The calculation of these parameters aims to minimize the distance between the closest point pairs. Use the calculated transformation parameters to perform translation and rotation operations on the target form correction model (or the actual form correction model) to make it approach the actual form correction model (or the target form correction model). Repeat the processes of determining the closest point pairs, calculating the transformation parameters, and model transformation until the preset convergence condition is met (such as the distance change between the closest point pairs is less than a certain threshold, or the number of iterations reaches the set value). At this time, the model registration state obtained is the optimization result. During the iteration process, improved algorithms such as Enhanced ICP, Weighted ICP, Hierarchical ICP, and Local Deformation ICP can also be combined to further improve the optimization effect according to different model characteristics and requirements. For example, the Weighted ICP algorithm assigns higher weights to key regions, thus more accurately optimizing the registration accuracy of key parts.

[0091] Step S3046: Perform data measurement on the optimization result based on the distance measurement rule to determine the second deviation data between the target form correction model and the actual form correction model; among them, the second form comparison result includes the second deviation data.

[0092] The second deviation data is a value used to quantify the spatial position difference between the target shape correction model and the actual shape correction model after iterative optimization registration. Specifically, according to the specific application scenario and requirements, a suitable distance metric rule is selected. For example, the point-to-point distance can directly calculate the straight-line distance between the corresponding points of the two models; the point-to-plane distance calculates the perpendicular distance from the points on the target shape correction model to the corresponding surface of the actual shape correction model. According to the selected distance metric rule, the distances between the corresponding points or regions of the target shape correction model and the actual shape correction model in the optimization result are calculated. The distances of all corresponding points can be calculated, and further statistical indicators of these distances can be counted, such as the maximum deviation value (used to identify extreme deformation regions), the root mean square error (RMS, used to evaluate the overall deviation), etc. These statistical indicators are the second deviation data, and through these data, the deviation situation between the two models can be comprehensively and accurately reflected.

[0093] Taking tooth correction as an example, the target shape correction model generated in the invisible braces design software (such as a CAD platform) is imported into the system. Through methods such as key feature point matching or manual reference point matching, the recycled braces mesh is initially aligned with the target shape correction model in the general position. Further, through multiple rounds of iteration using the iterative closest point (ICP) algorithm or other improved algorithms, the global error is gradually reduced to achieve more accurate alignment. In response to the elastic deformation or local collapse that may occur during the actual use of the braces, the registration algorithm will perform adaptive weight setting to reduce the interference of these deformations on the registration result. In addition, in order to improve the registration accuracy of the key areas of the tooth crown, some areas (such as the edges of the braces) can be set as weakly registered areas during the registration process, or these areas with large deformations can be completely ignored to avoid their impact on the overall registration. After the registration is completed, it enters the deviation quantification and visualization stage. According to the point-to-plane or point-to-point distance principle, the distance between each vertex in the recycled braces mesh and the corresponding point on the surface of the reference model is calculated:

[0094]

[0095] where p is the point in the recycled braces model (actual shape correction model), and q is the set of points on the surface of the target shape correction model.

[0096] Subsequently, relevant statistical indicators are calculated, including: the maximum deviation value (Max Error), used to detect local severely deformed parts; the root mean square deviation (RMS Error), used to evaluate the overall registration accuracy; and the percentage over threshold (Percentage Over Threshold), used to measure the distribution ratio of the deviation.

[0097] The correction strategy generation method provided in the embodiment of the present invention performs preliminary alignment based on preset feature matching points, builds a basic framework for subsequent precise comparison, and makes the target morphology correction model and the actual morphology correction model initially comparable. Then, the nearest point is determined and the preliminary alignment result is iteratively optimized based on it, which greatly improves the accuracy and reliability of the alignment and makes the comparison between models more in line with the actual situation. The second deviation data is obtained by measuring the optimization result using the distance measurement rule, which can accurately quantify the difference between the two and clearly present the deviation between the actual and target morphologies, thereby providing key data support for doctors or orthodontic professionals to fully and deeply understand the deviations in the correction process, and effectively assist doctors or orthodontic professionals to accurately adjust the correction strategy and effectively improve the quality and success rate of orthodontic treatment.

[0098] Step S3047: Determine the display method of the deviation area between the target morphology correction model and the actual morphology correction model based on the value of the second deviation data.

[0099] The deviation area refers to the partial area where the target morphology correction model and the actual morphology correction model differ in spatial morphology. The display mode refers to the form in which the deviation area between the target morphology correction model and the actual morphology correction model is presented, so that the user can intuitively understand and analyze the deviation. For example, different colors can be used to distinguish different degrees of deviation, or the deviation area can be marked with specific graphics, or the deviation area can be highlighted by transparency changes, line outlines, etc. Specifically, different deviation threshold ranges are determined based on professional knowledge and practical experience in the correction field. For example, the second deviation data is divided into three intervals: a low deviation interval (such as 0-0.5mm), a medium deviation interval (0.5-1.5mm) and a high deviation interval (greater than 1.5mm). Set corresponding display modes for different deviation levels.

[0100] For example, a specific color can be assigned to each deviation interval. For example, the low deviation area is represented by green, which means that the actual shape of the area is close to the target shape and the correction effect is good; the medium deviation area is represented by yellow, indicating that attention should be paid to the correction of this area; the high deviation area is represented by red, indicating that the deviation of this area is large and the correction strategy may need to be adjusted. Through this color coding method, different color areas in the visualization model intuitively show the distribution of the degree of deviation.

[0101] For another example, the second deviation data is normalized so that its value range is mapped to the interval [0, 1] for unified color mapping on the heat map. Using a professional visualization tool or programming library (such as Matplotlib, Seaborn in Python), the normalized deviation data is converted into a heat map. In the heat map, warmer colors (such as red and orange) represent areas with larger deviations, and cooler colors (such as blue and green) represent areas with smaller deviations, as Figure 6 shown. This intuitive color gradient display enables the operator to clearly see the distribution of deviations across the entire model and quickly identify the areas where deviations are concentrated.

[0102] In addition, a report that can be automatically exported can be generated, including numerical statistics, screenshots and other information for doctors or orthodontic professionals to refer to.

[0103] The correction strategy generation method provided by the embodiments of the present invention can convert abstract deviation data into an intuitive visual presentation, enabling doctors or orthodontic professionals to quickly and clearly identify the specific areas where there are differences between the target form correction model and the actual form correction model. This accurate and intuitive display method helps doctors or orthodontic professionals quickly focus on the problems in the complex correction process, thereby efficiently judging the severity and distribution range of the deviations.

[0104] Step S305, update the correction strategy for the target part according to the first form comparison result and the second form comparison result to generate a target correction strategy.

[0105] Specifically, the above step S305 includes:

[0106] Step S3051, if the first deviation data and / or the second deviation data is greater than a preset threshold, generate a warning message.

[0107] The preset threshold is a reference value set in advance according to factors such as orthodontic treatment standards, experience, and specific correction goals. Specifically, continuously monitor the first deviation data and the second deviation data. When any one of the first deviation data or the second deviation data is greater than this preset threshold, it means that there is a large difference between the actual correction situation and the expected target form correction model or deformation prediction model. At this time, a warning message is generated. The warning message is used to prompt doctors or orthodontic professionals that there may be problems in the current correction process and attention needs to be paid.

[0108] Step S3052, in response to the strategy update operation generated according to the warning message, update the correction strategy according to the strategy update operation to generate a target correction strategy.

[0109] After receiving the warning information, the doctor or orthodontic professional conducts in-depth analysis based on the first deviation data and / or the second deviation data. By leveraging their professional knowledge and clinical experience, and considering the individual situation of the patient, the doctor or orthodontic professional determines a new correction plan. For example, the doctor or orthodontic professional refers to the deviation area, direction, and magnitude reflected in the deviation data to judge whether it is necessary to adjust the magnitude or direction of the corrective force, or change the shape of the orthodontic appliance, etc. Suppose the doctor or orthodontic professional discovers through analysis that the deviation in a certain area is too large, they may decide to increase the corrective force in that area, specifically by increasing a certain force value in a certain direction, or adjusting the thickness of the orthodontic appliance in that area, such as thickening it by 0.1 - 0.2 mm, etc., and input these adjusted values and directions into the computer device.

[0110] After receiving the adjustment information input by the doctor or orthodontic professional, the computer device generates a target correction strategy according to the internally preset algorithms and logics. In this process, the computer device will combine information such as the relevant data of the target site, the correction model, and the deviation analysis results obtained previously, and transform the doctor's adjustment intention into a specific and operable target correction strategy. For example, the computer device will accurately plan the force that the orthodontic appliance should exert in each subsequent correction process and when to replace the orthodontic appliance according to the corrective force adjustment value input by the doctor or orthodontic professional, etc., to ensure that the correction process can be advanced more precisely according to the new strategy to achieve the expected correction effect.

[0111] The correction strategy generation method provided by the embodiments of the present invention generates warning information by setting a preset threshold and comparing the first deviation data and / or the second deviation data with the threshold, realizing sensitive monitoring of abnormal situations during the correction process, and can promptly capture the significant deviation between the actual state and the expected state of the invisible orthodontic appliance. The strategy update operation generated in response to the warning information enables the correction strategy to quickly make targeted adjustments according to the actual deviation situation, ensuring that the generated target correction strategy always meets the correction requirements of the patient's target site. This dynamic correction strategy update mechanism effectively avoids problems such as poor correction effects caused by deviation accumulation, and greatly improves the accuracy, reliability, and safety of orthodontic treatment.

[0112] In this embodiment, a correction strategy generation device is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0113] This embodiment provides a correction strategy generation device, as Figure 7 shown, including:

[0114] An acquisition module 401, configured to acquire a target form correction model for a target part and initial point cloud data generated by an invisible aligner recovered for the target part at multiple angles;

[0115] A construction module 402, configured to construct an actual form correction model corresponding to the invisible aligner based on the spatial relationship between the initial point cloud data at multiple angles;

[0116] A prediction module 403, configured to generate a deformation prediction model for the invisible aligner based on the physical characteristics of the invisible aligner;

[0117] A comparison module 404, configured to compare the deformation prediction model with the actual form correction model to obtain a first form comparison result, and compare the target form correction model with the actual form correction model to obtain a second form comparison result;

[0118] A generation module 405, configured to update the correction strategy for the target part according to the first form comparison result and the second form comparison result, and generate a target correction strategy.

[0119] In some alternative embodiments, the prediction module 403 includes:

[0120] An acquisition sub-module, configured to acquire the force parameters of the target part and the material property parameters corresponding to the invisible aligner;

[0121] A simulation sub-module, configured to perform deformation simulation on the target form correction model based on the force parameters and the material property parameters to obtain a deformation prediction model.

[0122] In some alternative embodiments, the comparison module 404 includes:

[0123] A first registration unit, configured to register the deformation prediction model with the actual form correction model to generate a registration result between the deformation prediction model and the actual form correction model;

[0124] A first determination unit, configured to perform data measurement on the registration result based on a preset distance measurement rule to determine first deviation data between the deformation prediction model and the actual form correction model; wherein, the first form comparison result includes the first deviation data.

[0125] In some alternative embodiments, the comparison module 404 further includes:

[0126] A second registration unit, configured to perform preliminary registration on the target form correction model and the actual form correction model according to preset feature matching points to obtain a preliminary registration result;

[0127] A second determination unit, configured to determine the closest points between the target shape correction model and the actual shape correction model based on the preliminary registration result;

[0128] An optimization unit, configured to iteratively optimize the preliminary registration result according to the closest points to obtain an optimization result;

[0129] A third determination unit, configured to perform data measurement on the optimization result based on a distance measurement rule to determine the second deviation data between the target shape correction model and the actual shape correction model; wherein, the second shape comparison result includes the second deviation data.

[0130] In some alternative embodiments, the comparison module 404 further includes:

[0131] A fourth determination unit, configured to determine the display mode of the deviation area between the target shape correction model and the actual shape correction model based on the value of the second deviation data.

[0132] In some alternative embodiments, the generation module 405 includes:

[0133] A generation sub-module, configured to generate a warning message if the first deviation data and / or the second deviation data is greater than a preset threshold;

[0134] An update sub-module, configured to update the correction strategy according to the strategy update operation in response to the strategy update operation generated according to the warning message, and generate a target correction strategy.

[0135] In some alternative embodiments, the construction module 402 includes:

[0136] A denoising sub-module, configured to perform denoising processing on the initial point cloud data to obtain denoised initial point cloud data;

[0137] A splicing sub-module, configured to splice the denoised initial point cloud data based on the spatial relationship between the initial point cloud data at multiple angles to obtain spliced point cloud data;

[0138] A meshing sub-module, configured to perform meshing processing on the spliced point cloud data to generate an actual shape correction model corresponding to the invisible corrector.

[0139] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding above-mentioned embodiments, and will not be elaborated herein.

[0140] The correction strategy generation device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0141] The correction strategy generation device provided in the embodiment of the present invention lays a foundation for accurate analysis by obtaining a target morphology correction model and multi-angle initial point cloud data of a recycled invisible aligner, ensuring data comprehensiveness. The actual morphology correction model is constructed using spatial relationships, which can truly reflect the actual state of the aligner. The deformation prediction model generated based on physical characteristics effectively estimates its change trend during use. By comparing the deformation prediction model and the target morphology correction model with the actual morphology correction model respectively, the differences are accurately analyzed from different angles. The obtained comparison results provide a key basis for updating the correction strategy, making the generated target correction strategy both scientific and targeted, and effectively improving the correction effect and efficiency.

[0142] The embodiment of the present invention also provides a computer device having the above Figure 7 shown correction strategy generation device.

[0143] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As Figure 8 shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as a server array, a set of blade servers, or a multi-processor system). Figure 8 Taking one processor 10 as an example in

[0144] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.

[0145] Among them, the memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0146] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0147] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, a hard disk, or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0148] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means. Figure 8 Taking connection through a bus as an example.

[0149] The input device 30 can receive input digital or character information, and generate key signal inputs related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (such as an LED), and a tactile feedback device (such as a vibration motor), etc. The above display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touch screen.

[0150] The computer device further includes a communication interface for the computer device to communicate with other devices or communication networks.

[0151] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0152] A part of the present invention can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, the method and / or technical solution according to the present invention can be invoked or provided. Those skilled in the art should be able to understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.

[0153] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for generating a correction strategy, characterized in that, The method includes: Obtaining a target form correction model for a target part, and initial point cloud data generated by a retrieved invisible aligner for the target part at multiple angles; Constructing an actual form correction model corresponding to the invisible aligner based on the spatial relationship between the initial point cloud data at multiple angles; Generating a deformation prediction model for the invisible aligner based on the physical characteristics of the invisible aligner; Comparing the deformation prediction model with the actual form correction model to obtain a first form comparison result, and comparing the target form correction model with the actual form correction model to obtain a second form comparison result; Updating the correction strategy for the target part according to the first form comparison result and the second form comparison result to generate a target correction strategy.

2. The method according to claim 1, wherein The generating the deformation prediction model for the invisible aligner based on the physical characteristics of the invisible aligner: Obtaining the force parameters of the target part and the material property parameters corresponding to the invisible aligner; Performing deformation simulation on the target form correction model based on the force parameters and the material property parameters to obtain the deformation prediction model.

3. The method according to claim 1, characterized in that, Comparing the deformation prediction model with the actual form correction model to obtain a first form comparison result, including: Registering the deformation prediction model with the actual form correction model to generate a registration result between the deformation prediction model and the actual form correction model; Performing data measurement on the registration result based on a preset distance measurement rule to determine a first deviation data between the deformation prediction model and the actual form correction model; Wherein, the first form comparison result includes the first deviation data.

4. The method according to claim 3, wherein Comparing the target form correction model with the actual form correction model to obtain a second form comparison result, including Performing preliminary registration on the target form correction model and the actual form correction model according to preset feature matching points to obtain a preliminary registration result; Determining the closest points between the target form correction model and the actual form correction model based on the preliminary registration result; Performing iterative optimization on the preliminary registration result according to the closest points to obtain an optimized result; Performing data measurement on the optimized result based on the distance measurement rule to determine a second deviation data between the target form correction model and the actual form correction model; Wherein, the second form comparison result includes the second deviation data.

5. The method according to claim 4, wherein It further includes: Determining the display mode of the deviation area between the target form correction model and the actual form correction model based on the value of the second deviation data.

6. The method according to claim 3 or 4, characterized in that, Updating the correction strategy for the target part according to the first form comparison result and the second form comparison result to generate a target correction strategy, including: If the first deviation data and / or the second deviation data is greater than a preset threshold, generating a warning message; Responding to a strategy update operation generated according to the warning message, updating the correction strategy according to the strategy update operation to generate the target correction strategy.

7. The method according to claim 1, characterized in that Constructing the actual morphological correction model corresponding to the invisible corrector based on the spatial relationship between the initial point cloud data from multiple angles includes: Performing denoising processing on the initial point cloud data to obtain denoised initial point cloud data; Based on the spatial relationship between the initial point cloud data from multiple angles, splicing the denoised initial point cloud data to obtain spliced point cloud data; Performing meshing processing on the spliced point cloud data to generate the actual morphological correction model corresponding to the invisible corrector.

8. A correction strategy generation device, characterized in that, The device includes: An acquisition module for acquiring the target morphological correction model for the target part and the initial point cloud data generated at multiple angles of the invisible corrector recovered for the target part; A construction module for constructing the actual morphological correction model corresponding to the invisible corrector based on the spatial relationship between the initial point cloud data from multiple angles; A prediction module for generating a deformation prediction model of the invisible corrector based on the physical characteristics of the invisible corrector; A comparison module for comparing the deformation prediction model with the actual morphological correction model to obtain a first morphological comparison result, and comparing the target morphological correction model with the actual morphological correction model to obtain a second morphological comparison result; A generation module for updating the correction strategy for the target part according to the first morphological comparison result and the second morphological comparison result to generate a target correction strategy.

9. A computer device, characterized in that, Includes: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the correction strategy generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause the computer to execute the correction strategy generation method according to any one of claims 1 to 7.

Images