Adaptation judgment method and device of appliance and electronic equipment

Abstract

The invention discloses an adaptation judgment method and device of an appliance and electronic equipment. The method comprises the steps that an oral cavity model of a target object and an STL file of an appliance model are read; according to the STL file, generating point cloud data of the oral cavity model and point cloud data of the appliance model; under the condition that the length difference between the oral cavity model and the appliance model is greater than a preset threshold value, performing parallelism, alignment and overlapping rate calculation processing on the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model to obtain an overlapping rate; and according to the overlapping rate, calculating the adaptation degree of the to-be-matched appliance, and when the adaptation degree is greater than a preset threshold value, determining an adaptation target object of the to-be-matched appliance. Therefore, according to the embodiment of the invention, by carrying out parallelism, alignment and overlapping rate calculation processing on the oral cavity model and the appliance model, personalized appliance adaptation suggestions can be provided for each patient, and the wearing comfort and satisfaction of the patient are improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device and electronic equipment for determining the adaptation of an appliance. Background Art

[0002] In the field of oral orthodontics, traditional appliances usually adopt fixed specifications and sizes, aiming to improve the patency of the airway by adjusting the internal structure of the oral cavity, thereby reducing snoring. Due to the significant differences in the oral structure of each patient, these standardized appliances face major challenges in the actual fitting process.

[0003] With the advancement of 3D scanning technology, personalized medical products have gradually become possible, making it feasible to obtain high-precision patient oral models. However, existing technologies have obvious deficiencies in evaluating the compatibility of standardized braces with patient oral models. At present, the fitting of braces mainly relies on manual evaluation and subjective feedback from patients. This method is not only time-consuming, but also prone to poor fitting, resulting in a high return rate.

[0004] In actual operation, the adaptation of standardized braces needs to consider multiple factors, including but not limited to the complexity of the oral structure, the size and shape of the braces, etc. The existing methods are inefficient and inaccurate, and cannot fully meet market demand. In addition, due to the lack of an automated and precise evaluation system, patients often need to go through multiple trials and adjustments, which increases the patient's time cost. Summary of the invention

[0005] The embodiments of the present application provide a method, device and electronic device for determining the fit of an appliance. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0006] In a first aspect, an embodiment of the present application provides a method for determining the adaptation of an appliance, the method comprising:

[0007] Read the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user;

[0008] Generate point cloud data of the oral model and the appliance model according to the STL file;

[0009] When the length difference between the oral cavity model and the orthodontic appliance model is greater than a preset threshold, the oral cavity model and the orthodontic appliance model are parallelized, aligned, and overlapped based on the point cloud data of the oral cavity model and the point cloud data of the orthodontic appliance model to obtain the overlap rate;

[0010] The degree of fit of the appliance to be matched is calculated according to the overlap rate, and when the degree of fit is greater than a preset threshold, the target object for the appliance to be matched is determined.

[0011] Optionally, generate point cloud data of the oral model based on the STL file, including:

[0012] Analyze the STL file of the oral model to obtain all the triangular faces of the oral model;

[0013] Extract the vertex coordinates of each triangular facet of the oral model;

[0014] Merge the vertex coordinates of each triangular patch of the oral model into an array;

[0015] The duplicate vertex coordinates in the array are removed to obtain the point cloud data of the oral model. The point cloud data of the oral model is the three-dimensional coordinate points of the internal surface of the oral cavity of the target object.

[0016] Optionally, based on the point cloud data of the oral model and the point cloud data of the appliance model, the oral model and the appliance model are parallelized, aligned, and overlapped, to obtain an overlap rate, including:

[0017] Centralizing the point cloud data of the oral model and the point cloud data of the appliance model to obtain centralized point cloud data;

[0018] According to the centralized point cloud data, the oral model and the appliance model are processed in parallel to obtain the target point cloud data of the oral model and the target point cloud data of the appliance model;

[0019] Align the target point cloud data of the oral model with the target point cloud data of the appliance model to obtain the optimal position of the feature points of the oral model;

[0020] Based on the optimal position of the characteristic points of the oral model, the point cloud data of the occlusal surface is obtained;

[0021] According to the point cloud data of the occlusal surface, the area overlap ratio of the occlusal surface projected onto the preset plane is calculated.

[0022] Optionally, the oral cavity model and the appliance model are processed in parallel according to the centralized point cloud data to obtain target point cloud data of the oral cavity model and target point cloud data of the appliance model, including:

[0023] Calculate the first covariance matrix of the centralized point cloud data;

[0024] Perform eigenvalue decomposition on the first covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0025] Calculate the first rotation matrix according to the eigenvalues ​​and eigenvectors;

[0026] Based on the first rotation matrix, the point cloud data of the oral cavity model and the point cloud data of the appliance model are rotated respectively to obtain target point cloud data of the oral cavity model and the target point cloud data of the appliance model.

[0027] Optionally, the target point cloud data of the oral model is aligned with the target point cloud data of the appliance model to obtain the optimal position of the feature points of the oral model, including:

[0028] The vertices of the maxillary and mandibular middle incisors of the target object are used as the first feature points corresponding to the oral model;

[0029] The groove position corresponding to the middle tooth in the orthodontic appliance to be matched is used as the second feature point corresponding to the orthodontic appliance model;

[0030] Calculate an initial transformation matrix according to the position of the first feature point and the position of the second feature point;

[0031] The position of the first feature point corresponding to the oral cavity model is updated by using the initial transformation matrix to obtain the position of the feature point of the oral cavity model after update;

[0032] According to the target point cloud data of the oral model and the target point cloud data of the appliance model, the positions of the feature points of the updated oral model are iteratively optimized to obtain the optimal positions of the feature points of the oral model.

[0033] Optionally, according to the target point cloud data of the oral model and the target point cloud data of the appliance model, the positions of the updated oral model feature points are iteratively optimized to obtain the optimal positions of the oral model feature points, including:

[0034] The target point cloud data of the oral model and the target point cloud data of the appliance model are matched with each other at the closest point in the target point cloud data of the oral model, so as to determine the closest point that matches each target point cloud data in the target point cloud data of the appliance model, and obtain a plurality of closest point pairs;

[0035] Based on multiple closest point pairs, recalculate the target transformation matrix using the least squares method;

[0036] The positions of the updated oral model feature points are updated again by recalculating the target transformation matrix to obtain the latest positions of the oral model feature points;

[0037] According to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model, the square root of the average of the squares of the distances between the same feature points is calculated to obtain the root mean square deviation;

[0038] When the RMS deviation is less than the set tolerance or the number of update iterations reaches the maximum number of iterations, the optimal positions of the oral cavity model feature points are determined based on the latest positions of the oral cavity model feature points.

[0039] Optionally, based on the latest position of the oral model feature point, determining the optimal position of the oral model feature point includes:

[0040] Calculating a second covariance matrix according to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model;

[0041] Perform singular value decomposition on the second covariance matrix to obtain a decomposition matrix;

[0042] According to the decomposition matrix, calculate the target rotation matrix;

[0043] The target rotation matrix is ​​used to transform the latest positions of the feature points of the oral model to obtain the optimal positions of the feature points of the oral model.

[0044] In a second aspect, an embodiment of the present application provides a device for determining the fit of an appliance, the device comprising:

[0045] An STL file reading module is used to read the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user;

[0046] A point cloud data generation module is used to generate point cloud data of the oral model and point cloud data of the appliance model according to the STL file;

[0047] An overlap rate calculation module is used to parallelize, align and calculate the overlap rate of the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model to obtain the overlap rate when the length difference between the oral cavity model and the appliance model is greater than a preset threshold;

[0048] The adaptation judgment module is used to calculate the adaptation degree of the orthodontic appliance to be matched according to the overlap rate, and determine the adaptation target object of the orthodontic appliance to be matched when the adaptation degree is greater than a preset threshold.

[0049] In a third aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0050] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0051] In the embodiments of the present application, on the one hand, after reading the STL files of the oral model and the appliance model of the target object, it is possible to automatically determine whether the appliance to be matched is suitable for the target object, thereby realizing an automated appliance adaptation determination process, reducing the reliance on manual determination and subjective feedback from patients, and thus reducing the return rate due to improper adaptation. On the other hand, the present application can perform parallel, alignment, and overlap calculation processing on the oral model and the appliance model based on the point cloud data of the oral model and the point cloud data of the appliance model. The processing process uses computer vision technology, which can achieve high-precision model alignment, ensure accurate matching of the appliance with the patient's oral structure, and accurately determine whether the patient is suitable for an appliance of fixed specifications, thereby reducing the patient's time cost.

[0052] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0054] Figure 1 It is a flowchart of a method for determining the fit of an appliance provided in an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of a process of determining the adaptation of an appliance provided by the present application;

[0056] Figure 3 It is a structural schematic diagram of a device for determining the fit of an appliance provided by the present application;

[0057] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The following description and the accompanying drawings sufficiently illustrate specific embodiments of the present application to enable those skilled in the art to practice them.

[0059] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0060] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0061] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0062] The present application provides a method, device and electronic device for determining the adaptation of an appliance to solve the problems existing in the above-mentioned related technical issues. In an embodiment of the present application, on the one hand, after reading the STL files of the oral model and the appliance model of the target object, it can automatically determine whether the appliance to be matched is adapted to the target object, thereby realizing an automated appliance adaptation determination process, reducing the reliance on manual judgment and subjective feedback from patients, and thus reducing the return rate due to improper adaptation. On the other hand, the present application can perform parallel, alignment and overlap calculation processing on the oral model and the appliance model based on the point cloud data of the oral model and the point cloud data of the appliance model. The processing process uses computer vision technology, which can achieve high-precision model alignment, ensure accurate matching of the appliance with the patient's oral structure, and accurately determine whether the patient is suitable for an appliance of fixed specifications, thereby reducing the patient's time cost. The following is a detailed description using an exemplary embodiment.

[0063] The following will be combined with the attached Figure 1 -Attached Figure 2 , a method for determining the fit of an appliance provided in an embodiment of the present application is introduced in detail. The method can be implemented by a computer program and can be run on a device for determining the fit of an appliance based on a von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0064] See also Figure 1 , which is a flow chart of a method for determining the fit of an appliance provided in an embodiment of the present application. Figure 1 As shown, the method of the embodiment of the present application may include the following steps:

[0065] S101, reading the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user;

[0066] Among them, STL (Standard Triangle Language) file is a widely used 3D model file format, mainly used for 3D printing and computer-aided design. STL file approximates the surface of 3D model by defining triangular patches, each of which consists of three vertices (i.e. points with X, Y, and Z coordinates). This format facilitates the transmission and processing of 3D model data in different 3D printing and design software. The target object can be a patient who needs to make an appliance fitting judgment, and the entire fitting judgment process can be carried out around the oral structure of this patient. The oral model refers to a digital representation of the patient's oral structure obtained by 3D scanning technology, which can accurately reflect the patient's teeth, gums and other oral features. 3D scanning technology is a technology that can capture the shape and size of the surface of an object. The appliance model refers to the 3D model of the appliance to be matched selected by the user. The model represents the geometric shape and size of the appliance and is usually provided by the appliance manufacturer.

[0067] In some embodiments, a patient who needs to undergo an appliance fitting assessment can be selected as a target object, and the patient's oral cavity can be scanned using 3D scanning technology to obtain the geometric data of the oral cavity, and the geometric data of the oral cavity can be converted into an STL file, which describes in detail the surface of the patient's oral cavity, including features such as teeth and gums. The STL file of the appliance to be matched is obtained from the appliance manufacturer.

[0068] S102, generating point cloud data of the oral model and point cloud data of the appliance model according to the STL file;

[0069] In some embodiments of the present application, the specific process of generating point cloud data of the oral model based on the STL file includes: parsing the STL file of the oral model to obtain all the triangular facets of the oral model; extracting the vertex coordinates of each triangular facet of the oral model; merging the vertex coordinates of each triangular facet of the oral model into an array; removing the duplicate vertex coordinates in the array to obtain the point cloud data of the oral model, wherein the point cloud data of the oral model is the three-dimensional coordinate points of the internal surface of the oral cavity of the target object.

[0070] For example, all triangular patches of the oral model contain three vertices, denoted as v0, v1, and v2. The vertex coordinates of each triangular patch of the oral model are merged into an array Since the same vertex may appear in multiple triangles, it is necessary to remove duplicate points to obtain unique point cloud data. By removing duplicate points, point cloud data containing all unique vertices can be obtained. The final point cloud data format of the oral model is:

[0071] P={p1,p2,…,p n}, where each p i is a three-dimensional coordinate point (x i ,y i ,z i ).

[0072] It should be noted that the process of generating point cloud data of the orthodontic appliance model according to the STL file is the same as the logic of generating point cloud data of the oral model according to the STL file, which will not be repeated here.

[0073] In an embodiment of the present application, after obtaining the point cloud data of the oral model and the point cloud data of the orthodontic appliance model, it is also necessary to determine the length difference between the oral model and the orthodontic appliance model, specifically including: projecting the STL file of the oral model onto the plane formed by the XZ axes of the preset spatial coordinate system, and obtaining the outer contour area of ​​the tooth projection in combination with the Graham scanning algorithm; determining the average direction of all tangent vectors of the outer contour area to obtain the direction of the long axis of the oral cavity; calculating the first model length of the oral model in the direction of the long axis of the oral cavity according to the three-dimensional coordinate points of the internal surface of the oral cavity of the target object; reading the second model length preset for the orthodontic appliance model from the STL file of the orthodontic appliance model; calculating the absolute value of the difference between the first model length and the second model length to obtain the length difference between the oral model and the orthodontic appliance model.

[0074] It should be noted that since the oral scan data is parallel to the plane formed by the XZ axis, it is only necessary to analyze the angle between the long axis of the oral cavity and the Z axis, then rotate the model, and calculate the value difference of the Z axis to get the length. The length of the orthodontic appliance model is known, so no further calculation is required.

[0075] For example, project the read STL file header onto the xz plane, and then use the convex hull algorithm: Graham scanning algorithm to obtain the outer contour area of ​​the tooth projection, and calculate the average direction of all tangent vectors in the area, that is, the direction of the long axis of the oral cavity. Calculate the model length in this direction:

[0076] When a set of three-dimensional coordinate points on the inner surface of the oral cavity is P = {p1, p2, ..., p n}, where each point p i =(x i , z i ).

[0077] The length of the oral model is calculated as follows:

[0078]

[0079] Among them, v is the unit vector in the average direction. The maximum value of the projection length can be calculated by the above formula: d max and d min , L 口扫 =d max -d min . Perform a size comparison to evaluate the difference in length from front to back. Calculate the length difference by comparing the occlusal lengths of the two models:

[0080] ΔL=|L 口扫 -L 矫治器 |;

[0081] Among them, L 口扫 and L 矫治器 are the lengths of the oral model and the appliance model, respectively.

[0082] S103, when the length difference between the oral cavity model and the orthodontic appliance model is greater than a preset threshold, based on the point cloud data of the oral cavity model and the point cloud data of the orthodontic appliance model, parallelization, alignment and overlap rate calculation processing are performed on the oral cavity model and the orthodontic appliance model to obtain an overlap rate;

[0083] In some embodiments, a preset threshold ∈ can be set. If the length difference ΔL>∈, the appliance to be matched is determined to be incompatible. If it does not exceed the threshold, the oral model and the appliance model are parallelized, aligned, and overlapped based on the point cloud data of the oral model and the point cloud data of the appliance model to obtain the overlap rate.

[0084] In an embodiment of the present application, based on the point cloud data of the oral model and the point cloud data of the orthodontic appliance model, the oral model and the appliance model are parallelized, aligned and the overlap rate is calculated and processed, and the specific process of obtaining the overlap rate includes: centralizing the point cloud data of the oral model and the point cloud data of the orthodontic appliance model to obtain centralized point cloud data; based on the centralized point cloud data, parallel processing is performed on the oral model and the appliance model to obtain target point cloud data of the oral model and target point cloud data of the orthodontic appliance model; based on the target point cloud data of the oral model and the target point cloud data of the appliance model, alignment processing is performed to obtain the optimal position of the feature points of the oral model; based on the optimal position of the feature points of the oral model, the point cloud data of the occlusal surface is obtained; based on the point cloud data of the occlusal surface, the area overlap rate of the occlusal surface projected onto the preset plane is calculated.

[0085] Specifically, according to the centralized point cloud data, the oral cavity model and the orthodontic appliance model are processed in parallel to obtain the target point cloud data of the oral cavity model and the target point cloud data of the orthodontic appliance model. The specific process includes: calculating the first covariance matrix of the centralized point cloud data; performing eigenvalue decomposition on the first covariance matrix to obtain eigenvalues ​​and eigenvectors; calculating the first rotation matrix according to the eigenvalues ​​and eigenvectors; based on the first rotation matrix, rotating the point cloud data of the oral cavity model and the point cloud data of the orthodontic appliance model respectively to obtain the target point cloud data of the oral cavity model and the target point cloud data of the orthodontic appliance model.

[0086] For example, when the point cloud data of the oral model and the point cloud data of the orthodontic appliance model are centralized and the centralized point cloud data is obtained, the coordinates of each point are subtracted from the center point of the point cloud data. This can eliminate the translation effect of the model and only consider the rotation alignment.

[0087]

[0088] Among them, P and Q represent the point cloud data of the original oral model and the orthodontic appliance model respectively. and are the coordinates of the center point of each model, calculated as the average of all point coordinates. c and Q c It is the centralized point cloud data, which indicates the relative position of each point relative to the center of each model.

[0089] Then, calculate the first covariance matrix of the centralized point cloud data; perform eigenvalue decomposition on the first covariance matrix to obtain eigenvalues ​​and eigenvectors. The eigenvector represents the main direction of the data, that is, the direction of the principal component, and the eigenvalue represents the variance in these directions. The main direction of the orthodontic model is aligned to the main direction of the oral model through the first rotation matrix R:

[0090] R=V P V Q T ;

[0091] Among them, V P and V Q are the principal component direction matrices of the oral model and the appliance model, i.e., the eigenvector matrices obtained by PCA decomposition. R is the first rotation matrix required, which will ensure that the principal directions of the appliance model are aligned with the principal directions of the oral model.

[0092] Finally, the calculated first rotation matrix is ​​applied to the point cloud data of the oral model and the appliance model to complete the rotation alignment of the models and obtain the target point cloud data of the oral model and the appliance model after parallel processing. After this series of processing, the main directions of the oral model and the appliance model will be parallel, which is convenient for further processing and analysis.

[0093] P rotated =RP,Q rotated =RQ;

[0094] Among them, P rotated and Q rotated They represent the target point cloud data of the oral model and the appliance model after rotational alignment.

[0095] Specifically, the specific process of aligning the target point cloud data based on the oral model with the target point cloud data of the appliance model to obtain the optimal position of the feature points of the oral model includes: taking the vertices of the maxillary and mandibular middle incisors of the target object as the first feature points corresponding to the oral model; taking the groove positions corresponding to the middle teeth in the appliance to be matched as the second feature points corresponding to the appliance model; calculating the initial transformation matrix according to the positions of the first feature points and the second feature points; updating the positions of the first feature points corresponding to the oral model through the initial transformation matrix to obtain the updated positions of the feature points of the oral model; iteratively optimizing the updated positions of the feature points of the oral model according to the target point cloud data of the oral model and the target point cloud data of the appliance model to obtain the optimal positions of the feature points of the oral model.

[0096] For example, in order to achieve alignment between the appliance model and the oral model, first select points with obvious features on the model through feature point matching: the position of the middle teeth and the grooves in the appliance model to help achieve preliminary alignment. Specifically, for the oral model, the vertex of the middle teeth is selected as the first feature point. This position is the vertex of the maxillary and mandibular middle incisors, which can be determined by an automatic detection algorithm. For the appliance model, the position of the groove corresponding to the middle teeth is selected as the second feature point. After determining the position of the feature points, these feature points are matched between the two models. This can be achieved by directly comparing the coordinates of the feature points. Based on the position of the feature points, an initial transformation matrix T0 is calculated, which aligns the feature points of the oral model to the feature points of the appliance model.

[0097] The initial transformation matrix T0 can be calculated as follows. First, calculate the translation vector t:

[0098] t = qp;

[0099] Among them, the position of the feature point of the oral model is p = (x p ,y p ,zp ), the position of the feature point of the appliance model is q = (x q ,y q ,z q );

[0100] Then, construct the initial transformation matrix T0:

[0101]

[0102] Where I is the 3×3 identity matrix and 0 is the 1×3 zero vector.

[0103] Apply the initial transformation matrix T0 to the oral model and update the position and posture of the model:

[0104] p ′ =T0·p;

[0105] Among them, p ′ is the position of the updated oral model feature points.

[0106] Specifically, the process of iteratively optimizing the positions of the updated oral model feature points according to the target point cloud data of the oral model and the target point cloud data of the appliance model to obtain the optimal positions of the oral model feature points includes: performing nearest point pairing on the target point cloud data of the oral model and the target point cloud data of the appliance model to determine the nearest point in the target point cloud data of the oral model that matches each target point cloud data in the target point cloud data of the appliance model, and obtaining multiple nearest point pairs; recalculating the target transformation matrix based on the multiple nearest point pairs using the least squares method; updating the positions of the updated oral model feature points again through the recalculated target transformation matrix to obtain the latest positions of the oral model feature points; calculating the square root of the average of the squares of the distances between the same feature points according to the latest positions of the oral model feature points and the positions of the second feature points corresponding to the appliance model to obtain the root mean square deviation; when the root mean square deviation is less than the set tolerance or the number of update iterations reaches the maximum number of iterations, determining the optimal positions of the oral model feature points based on the latest positions of the oral model feature points.

[0107] For example, the target point cloud data of the oral model is paired with the target point cloud data of the appliance model at the closest point, and the closest point of each target point cloud data in the target point cloud data of the oral model in the target point cloud data of the appliance model is found to obtain the closest point pair. Based on the closest point pair, the target transformation matrix T is calculated using the least squares method. This matrix contains the rotation matrix R and the translation vector t. By minimizing the objective function:

[0108]

[0109] Among them, the target transformation matrix is ​​T, R is the rotation matrix, t is the translation vector, and p i and q i are the points in the oral model and the appliance model, respectively.

[0110] The calculated target transformation matrix T is applied to the oral model, and the positions of the updated oral model feature points are updated again to obtain the latest positions of the oral model feature points:

[0111] p i ′ =T·p i ;

[0112] Among them, p i ′ represents the latest position of the feature points of the oral model, and T is the target transformation matrix.

[0113] According to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model, the square root of the average value of the square of the distance between the same feature points is calculated to obtain the root mean square deviation. The root mean square deviation calculation formula is:

[0114]

[0115] Among them, p i and q i are the position vectors of the i-th feature point in the oral model and the appliance model, respectively.

[0116] When the RMS deviation is less than the set tolerance or the number of update iterations reaches the maximum number of iterations, the optimal position of the feature points of the oral model is determined based on the latest position of the feature points of the oral model. Otherwise, the nearest point pairing is performed again, a new transformation matrix is ​​calculated, and it is applied to the oral model again. This process is iterated continuously until the RMS deviation is less than the set tolerance or the predetermined maximum number of iterations is reached. Through such iterative optimization, the alignment accuracy between the models is continuously improved, thereby achieving the best match between the two models.

[0117] Specifically, the specific process of determining the optimal positions of the feature points of the oral model based on the latest positions of the feature points of the oral model includes: calculating the second covariance matrix according to the latest positions of the feature points of the oral model and the positions of the second feature points corresponding to the orthodontic model; performing singular value decomposition on the second covariance matrix to obtain a decomposition matrix; calculating the target rotation matrix based on the decomposition matrix; and using the target rotation matrix to transform the latest positions of the feature points of the oral model to obtain the optimal positions of the feature points of the oral model.

[0118] For example, the second covariance matrix is ​​calculated according to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model. The specific steps are:

[0119] Calculate the second covariance matrix H:

[0120]

[0121] in, and Respectively represent the coordinate vector of the i-th feature point in the appliance model and the oral model after the k-th iteration, and N is the number of feature points. The second covariance matrix H reflects the correlation of direction and amplitude between the entire point set. If the two point sets have a strong correlation in a certain direction, the value of the second covariance matrix H in the corresponding row and column will be larger.

[0122] Perform singular value decomposition (SVD) on the second covariance matrix H:

[0123] H=U·∑·V v ;

[0124] Among them, U and V are orthogonal matrices, ∑ is a diagonal matrix, and the elements on the diagonal are singular values ​​σ i , arranged in order from largest to smallest.

[0125] Calculate the target rotation matrix R:

[0126] Target rotation matrix R = VU r ;

[0127] Where R is the target rotation matrix. Check if the determinant of R is +1. If it is, no further correction is needed. But if it is -1, it indicates a mirror transformation and needs correction: multiply the last column of V by -1, because such a modification has the least effect on the rotation.

[0128] The column vectors in U and V represent the main directions of the original data space and the transformed data space, respectively. The singular values ​​σ in the diagonal matrix ∑ i Indicates the importance in the corresponding direction. Larger singular values ​​correspond to more significant directions in the data; suppose that in U, the first column vector points to the longest axis direction of the tooth distribution in the oral model, and in V, the first column vector also points to the longest extension direction in the orthodontic model. By rotating the matrix, the teeth of the oral model can be rotated along their longest axis to match the longest extension direction of the orthodontic model, thereby achieving alignment in these two main directions.

[0129] The target rotation matrix is ​​applied to the centralized feature point set of the oral model, that is, the latest position of the feature points of the oral model is transformed to update the position and posture of the oral model, and the optimal position of the feature points of the oral model is obtained.

[0130] Use the target rotation matrix R to change the latest position p′ of the feature points of the oral model i To transform:

[0131]

[0132] in, is the center of mass of the appliance model. Add back to the result to ensure that the transformed oral model feature point p″ i In the correct spatial position relative to the appliance model.

[0133] In some embodiments of the present application, the aligned occlusal surface is extracted, the point cloud data of the occlusal surface is obtained, and the area overlap ratio of the occlusal surface projected onto a certain plane is calculated to evaluate the alignment accuracy. The calculation formula for the projection area overlap ratio is:

[0134]

[0135] S104, calculating the degree of fitness of the appliance to be matched according to the overlap rate, and determining the target object to be matched with the appliance to be matched when the degree of fitness is greater than a preset threshold.

[0136] In some embodiments of the present application, after the overlap rate is obtained, the degree of fit is calculated based on the overlap rate and the length difference between the oral model and the appliance model. The degree of fit calculation comprehensively considers the overlap rate and the length difference, and linearly combines them through weight coefficients α and β:

[0137]

[0138] If the degree of fit is greater than the threshold, the appliance to be matched is determined to be suitable for the target object, otherwise it is determined to be unsuitable.

[0139] Finally, the system will display a comparison between the 3D scanned image of the patient's mouth and the appliance model. The page displays the 3D scanned model of the patient's mouth in open and closed states, and the appliance model is displayed for comparison, with a fit assessment provided through prompts or annotations next to it. Patients can clearly observe the differences and fit between the oral model and the appliance model, helping them make a more informed and confident choice.

[0140] For example Figure 2 As shown, Figure 2This is a schematic diagram of the process of determining the adaptation of an appliance provided by the present application. Files of an oral model and an appliance model are obtained. Based on the files, point cloud data of the two models are obtained. The length difference between the two models is calculated based on the point cloud data. If the length difference is greater than a preset threshold, it is determined that the appliance corresponding to the appliance model is not suitable for the patient corresponding to the oral model. If the length difference is less than or equal to the preset threshold, the two models are further parallelized, aligned, and the overlap rate is calculated. Finally, the degree of adaptation can be calculated based on the overlap rate. When the degree of adaptation is greater than the preset threshold, it is determined that the appliance corresponding to the appliance model is suitable for the patient corresponding to the oral model.

[0141] In the embodiments of the present application, on the one hand, after reading the STL files of the oral model and the appliance model of the target object, it is possible to automatically determine whether the appliance to be matched is suitable for the target object, thereby realizing an automated appliance adaptation determination process, reducing the reliance on manual determination and subjective feedback from patients, and thus reducing the return rate due to improper adaptation. On the other hand, the present application can perform parallel, alignment, and overlap calculation processing on the oral model and the appliance model based on the point cloud data of the oral model and the point cloud data of the appliance model. The processing process uses computer vision technology, which can achieve high-precision model alignment, ensure accurate matching of the appliance with the patient's oral structure, and accurately determine whether the patient is suitable for an appliance of fixed specifications, thereby reducing the patient's time cost.

[0142] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0143] See also Figure 3 , which shows a schematic diagram of the structure of a device for determining the fit of an appliance provided by an exemplary embodiment of the present application. The device for determining the fit of an appliance can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The device 1 includes an STL file reading module 10, a point cloud data generating module 20, an overlap rate calculating module 30, and a fit determining module 40.

[0144] An STL file reading module 10 is used to read the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user;

[0145] A point cloud data generating module 20 is used to generate point cloud data of the oral model and point cloud data of the appliance model according to the STL file;

[0146] The overlap rate calculation module 30 is used to perform parallelization, alignment and overlap rate calculation processing on the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model to obtain the overlap rate when the length difference between the oral cavity model and the appliance model is greater than a preset threshold;

[0147] The adaptation judgment module 40 is used to calculate the adaptation degree of the orthodontic appliance to be matched according to the overlap rate, and determine the adaptation target object of the orthodontic appliance to be matched when the adaptation degree is greater than a preset threshold.

[0148] It should be noted that the device for determining the fit of the appliance provided in the above embodiment only uses the division of the above functional modules as an example when executing the method for determining the fit of the appliance. In actual applications, the above functional distribution can be completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device for determining the fit of the appliance provided in the above embodiment and the method for determining the fit of the appliance embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0149] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0150] In the embodiments of the present application, on the one hand, after reading the STL files of the oral model and the appliance model of the target object, it is possible to automatically determine whether the appliance to be matched is suitable for the target object, thereby realizing an automated appliance adaptation determination process, reducing the reliance on manual determination and subjective feedback from patients, and thus reducing the return rate due to improper adaptation. On the other hand, the present application can perform parallel, alignment, and overlap calculation processing on the oral model and the appliance model based on the point cloud data of the oral model and the point cloud data of the appliance model. The processing process uses computer vision technology, which can achieve high-precision model alignment, ensure accurate matching of the appliance with the patient's oral structure, and accurately determine whether the patient is suitable for an appliance of fixed specifications, thereby reducing the patient's time cost.

[0151] The present application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the method for determining the adaptation of the orthodontic device provided by the above-mentioned various method embodiments.

[0152] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method for determining the fit of an orthodontic appliance in each of the above-mentioned method embodiments.

[0153] See also Figure 4 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0154] The communication bus 1002 is used to realize the connection and communication between these components.

[0155] The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

[0156] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0157] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts within the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes operating devices, user interfaces and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0158] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing the operating device, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage device located away from the aforementioned processor 1001. As Figure 4 As shown, the memory 1005 as a computer storage medium may include an operating device, a network communication module, a user interface module, and an appliance adaptation determination application.

[0159] exist Figure 4 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the adaptation determination application of the orthodontic device stored in the memory 1005, and specifically perform the following operations:

[0160] Read the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user;

[0161] Generate point cloud data of the oral model and the appliance model according to the STL file;

[0162] When the length difference between the oral cavity model and the orthodontic appliance model is greater than a preset threshold, the oral cavity model and the orthodontic appliance model are parallelized, aligned, and overlapped based on the point cloud data of the oral cavity model and the point cloud data of the orthodontic appliance model to obtain the overlap rate;

[0163] The degree of fit of the appliance to be matched is calculated according to the overlap rate, and when the degree of fit is greater than a preset threshold, the target object for the appliance to be matched is determined.

[0164] In one embodiment, when the processor 1001 generates point cloud data of the oral cavity model according to the STL file, the following operations are specifically performed:

[0165] Analyze the STL file of the oral model to obtain all the triangular faces of the oral model;

[0166] Extract the vertex coordinates of each triangular facet of the oral model;

[0167] Merge the vertex coordinates of each triangular patch of the oral model into an array;

[0168] The duplicate vertex coordinates in the array are removed to obtain the point cloud data of the oral model. The point cloud data of the oral model is the three-dimensional coordinate points of the internal surface of the oral cavity of the target object.

[0169] In one embodiment, before the processor 1001 performs parallelization, alignment, and overlap calculation processing on the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model, it further performs the following operations:

[0170] Project the STL file of the oral model onto the plane formed by the XZ axes of the preset spatial coordinate system, and use the Graham scanning algorithm to obtain the outer contour area of ​​the tooth projection;

[0171] Determine the average direction of all tangent vectors in the outer contour area to obtain the direction of the long axis of the oral cavity;

[0172] Calculating a first model length of the oral cavity model in the long axis direction of the oral cavity according to the three-dimensional coordinate points of the inner surface of the oral cavity of the target object;

[0173] Reading a second model length preset for the appliance model from the STL file of the appliance model;

[0174] The absolute value of the difference between the length of the first model and the length of the second model is calculated to obtain the length difference between the oral model and the orthodontic appliance model.

[0175] In one embodiment, the processor 1001 performs parallelization, alignment and overlap calculation processing on the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model. When the overlap rate is obtained, the following operations are specifically performed:

[0176] Centralizing the point cloud data of the oral model and the point cloud data of the appliance model to obtain centralized point cloud data;

[0177] According to the centralized point cloud data, the oral model and the appliance model are processed in parallel to obtain the target point cloud data of the oral model and the target point cloud data of the appliance model;

[0178] Align the target point cloud data of the oral model with the target point cloud data of the appliance model to obtain the optimal position of the feature points of the oral model;

[0179] Based on the optimal position of the characteristic points of the oral model, the point cloud data of the occlusal surface is obtained;

[0180] According to the point cloud data of the occlusal surface, the area overlap ratio of the occlusal surface projected onto the preset plane is calculated.

[0181] In one embodiment, the processor 1001 performs parallel processing on the oral cavity model and the appliance model according to the centralized point cloud data to obtain the target point cloud data of the oral cavity model and the target point cloud data of the appliance model, and specifically performs the following operations:

[0182] Calculate the first covariance matrix of the centralized point cloud data;

[0183] Perform eigenvalue decomposition on the first covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0184] Calculate the first rotation matrix according to the eigenvalues ​​and eigenvectors;

[0185] Based on the first rotation matrix, the point cloud data of the oral cavity model and the point cloud data of the appliance model are rotated respectively to obtain target point cloud data of the oral cavity model and the target point cloud data of the appliance model.

[0186] In one embodiment, the processor 1001 performs alignment processing based on the target point cloud data of the oral model and the target point cloud data of the appliance model to obtain the optimal position of the feature point of the oral model, and specifically performs the following operations:

[0187] The vertices of the maxillary and mandibular middle incisors of the target object are used as the first feature points corresponding to the oral model;

[0188] The groove position corresponding to the middle tooth in the orthodontic appliance to be matched is used as the second feature point corresponding to the orthodontic appliance model;

[0189] Calculate an initial transformation matrix according to the position of the first feature point and the position of the second feature point;

[0190] The position of the first feature point corresponding to the oral cavity model is updated by using the initial transformation matrix to obtain the position of the feature point of the oral cavity model after update;

[0191] According to the target point cloud data of the oral model and the target point cloud data of the appliance model, the positions of the feature points of the updated oral model are iteratively optimized to obtain the optimal positions of the feature points of the oral model.

[0192] In one embodiment, the processor 1001 performs iterative optimization of the positions of the updated oral model feature points according to the target point cloud data of the oral model and the target point cloud data of the appliance model, and when the optimal positions of the oral model feature points are obtained, the following operations are specifically performed:

[0193] The target point cloud data of the oral model and the target point cloud data of the appliance model are matched with each other at the closest point in the target point cloud data of the oral model, so as to determine the closest point that matches each target point cloud data in the target point cloud data of the appliance model, and obtain a plurality of closest point pairs;

[0194] Based on multiple closest point pairs, recalculate the target transformation matrix using the least squares method;

[0195] The positions of the updated oral model feature points are updated again by recalculating the target transformation matrix to obtain the latest positions of the oral model feature points;

[0196] According to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model, the square root of the average of the squares of the distances between the same feature points is calculated to obtain the root mean square deviation;

[0197] When the RMS deviation is less than the set tolerance or the number of update iterations reaches the maximum number of iterations, the optimal positions of the oral cavity model feature points are determined based on the latest positions of the oral cavity model feature points.

[0198] In one embodiment, when the processor 1001 determines the optimal position of the feature point of the oral model based on the latest position of the feature point of the oral model, the following operations are specifically performed:

[0199] Calculating a second covariance matrix according to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model;

[0200] Perform singular value decomposition on the second covariance matrix to obtain a decomposition matrix;

[0201] According to the decomposition matrix, calculate the target rotation matrix;

[0202] The target rotation matrix is ​​used to transform the latest positions of the feature points of the oral model to obtain the optimal positions of the feature points of the oral model.

[0203] In the embodiments of the present application, on the one hand, after reading the STL files of the oral model and the appliance model of the target object, it is possible to automatically determine whether the appliance to be matched is suitable for the target object, thereby realizing an automated appliance adaptation determination process, reducing the reliance on manual determination and subjective feedback from patients, and thus reducing the return rate due to improper adaptation. On the other hand, the present application can perform parallel, alignment, and overlap calculation processing on the oral model and the appliance model based on the point cloud data of the oral model and the point cloud data of the appliance model. The processing process uses computer vision technology, which can achieve high-precision model alignment, ensure accurate matching of the appliance with the patient's oral structure, and accurately determine whether the patient is suitable for an appliance of fixed specifications, thereby reducing the patient's time cost.

[0204] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program for determining the fit of the appliance can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium of the program for determining the fit of the appliance can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0205] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for determining the fit of an appliance, It is characterized in that The method comprises: Reading the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user; Generate point cloud data of the oral model and point cloud data of the appliance model according to the STL file; When the length difference between the oral cavity model and the orthodontic appliance model is greater than a preset threshold, the oral cavity model and the orthodontic appliance model are parallelized, aligned, and overlapped based on the point cloud data of the oral cavity model and the point cloud data of the orthodontic appliance model to obtain an overlap rate; The degree of fitness of the appliance to be matched is calculated according to the overlap rate, and when the degree of fitness is greater than a preset threshold, it is determined that the appliance to be matched is suitable for the target object.

2. The method according to claim 1, It is characterized in that Generating point cloud data of the oral model according to the STL file includes: Parsing the STL file of the oral cavity model to obtain all triangular facets of the oral cavity model; Extracting the vertex coordinates of each triangular facet of the oral model; Merging the vertex coordinates of each triangular facet of the oral model into an array; The repeated vertex coordinates in the array are removed to obtain the point cloud data of the oral model, where the point cloud data of the oral model are the three-dimensional coordinate points of the internal surface of the oral cavity of the target object.

3. The method according to claim 2, It is characterized in that Before performing parallelization, alignment and overlap rate calculation processing on the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model, the method further includes: Projecting the STL file of the oral model onto the plane formed by the XZ axes of a preset spatial coordinate system, and acquiring the outer contour area of ​​the tooth projection in combination with the Graham scanning algorithm; Determine the average direction of all tangent vectors of the outer contour area to obtain the direction of the long axis of the oral cavity; Calculating a first model length of the oral cavity model in the direction of the long axis of the oral cavity according to the three-dimensional coordinate points of the inner surface of the oral cavity of the target object; Reading a second model length preset for the appliance model from the STL file of the appliance model; The absolute value of the difference between the length of the first model and the length of the second model is calculated to obtain the length difference between the oral model and the orthodontic appliance model.

4. The method according to claim 1, It is characterized in that Based on the point cloud data of the oral model and the point cloud data of the appliance model, the oral model and the appliance model are parallelized, aligned, and overlapped, to obtain the overlapped rate, including: Centralizing the point cloud data of the oral model and the point cloud data of the appliance model to obtain centralized point cloud data; According to the centralized point cloud data, the oral cavity model and the appliance model are processed in parallel to obtain target point cloud data of the oral cavity model and target point cloud data of the appliance model; Performing alignment processing based on the target point cloud data of the oral model and the target point cloud data of the appliance model to obtain the optimal position of the feature points of the oral model; Based on the optimal positions of the characteristic points of the oral model, acquiring point cloud data of the occlusal surface; The area overlap ratio of the occlusal surface projected onto the preset plane is calculated based on the point cloud data of the occlusal surface.

5. The method according to claim 4, It is characterized in that The method of processing the oral cavity model and the appliance model in parallel according to the centralized point cloud data to obtain target point cloud data of the oral cavity model and target point cloud data of the appliance model includes: Calculate the first covariance matrix of the centralized point cloud data; Performing eigenvalue decomposition on the first covariance matrix to obtain eigenvalues ​​and eigenvectors; Calculate a first rotation matrix according to the eigenvalues ​​and eigenvectors; Based on the first rotation matrix, the point cloud data of the oral cavity model and the point cloud data of the appliance model are rotated respectively to obtain target point cloud data of the oral cavity model and the target point cloud data of the appliance model.

6. The method according to claim 4, It is characterized in that The aligning process based on the target point cloud data of the oral cavity model and the target point cloud data of the appliance model to obtain the optimal position of the feature points of the oral cavity model includes: Taking the vertices of the maxillary and mandibular middle incisors of the target object as the first feature points corresponding to the oral model; Using the groove position corresponding to the middle tooth in the orthodontic appliance to be matched as the second feature point corresponding to the orthodontic appliance model; Calculating an initial transformation matrix according to the position of the first feature point and the position of the second feature point; Update the position of the first feature point corresponding to the oral model by using the initial transformation matrix to obtain the updated position of the feature point of the oral model; According to the target point cloud data of the oral model and the target point cloud data of the appliance model, the positions of the updated feature points of the oral model are iteratively optimized to obtain the optimal positions of the feature points of the oral model.

7. The method according to claim 5, It is characterized in that The iterative optimization of the updated positions of the characteristic points of the oral model according to the target point cloud data of the oral model and the target point cloud data of the appliance model to obtain the optimal positions of the characteristic points of the oral model includes: Performing closest point pairing on the target point cloud data of the oral cavity model and the target point cloud data of the appliance model to determine the closest point in the target point cloud data of the oral cavity model that matches the target point cloud data of the appliance model, and obtaining a plurality of closest point pairs; Recalculating the target transformation matrix using a least squares method based on the multiple closest point pairs; The updated positions of the oral model feature points are updated again by recalculating the target transformation matrix to obtain the latest positions of the oral model feature points; According to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model, the square root of the average value of the square of the distance between the same feature points is calculated to obtain the root mean square deviation; When the RMS deviation is less than the set tolerance or the number of update iterations reaches the maximum number of iterations, the optimal position of the oral model feature point is determined based on the latest position of the oral model feature point.

8. The method according to claim 7, It is characterized in that The determining the optimal position of the feature point of the oral model based on the latest position of the feature point of the oral model comprises: Calculating a second covariance matrix according to the latest position of the feature point of the oral model and the position of the second feature point corresponding to the appliance model; Performing singular value decomposition on the second covariance matrix to obtain a decomposition matrix; Calculating a target rotation matrix according to the decomposition matrix; The target rotation matrix is ​​used to transform the latest positions of the feature points of the oral model to obtain the optimal positions of the feature points of the oral model.

9. A device for determining the fit of an appliance, It is characterized in that The device comprises: An STL file reading module, used to read the STL files of the oral cavity model and the appliance model of the target object; the oral cavity model is generated by scanning data obtained by scanning the oral cavity of the target object using 3D scanning technology, and the appliance model is a 3D model of the appliance to be matched selected by the user; A point cloud data generation module, used to generate point cloud data of the oral model and point cloud data of the appliance model according to the STL file; An overlap rate calculation module, used for performing parallelization, alignment and overlap rate calculation processing on the oral cavity model and the appliance model based on the point cloud data of the oral cavity model and the point cloud data of the appliance model to obtain the overlap rate when the length difference between the oral cavity model and the appliance model is greater than a preset threshold; The adaptation judgment module is used to calculate the adaptation degree of the orthodontic appliance to be matched according to the overlap rate, and determine that the orthodontic appliance to be matched is adapted to the target object when the adaptation degree is greater than a preset threshold.

10. An electronic device, It is characterized in that include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method according to any one of claims 1 to 8.

Images