Model occlusion optimization method and device, computer device and storage medium

Abstract

Embodiments of the present application disclose a model occlusion optimization method and device, computer equipment and a storage medium. The method comprises: obtaining a target object oral model, the oral model comprising a first single jaw model and a second single jaw model, the first single jaw model and the second single jaw model each comprising an occlusal contact area; generating a second target single jaw model of the second single jaw model in a current pose, the second target single jaw model simulating elastic deformation occurring when the second single jaw model is occluded in the current pose; determining vertex weights of each jaw vertex in the second single jaw model according to vertex collision relationships between the occlusal contact area, the first single jaw model and the second single jaw model; updating the pose of the second single jaw model according to the vertex weights and the second target single jaw model based on a preset occlusion optimization algorithm, until the occlusion optimization algorithm meets a preset convergence condition, and outputting an optimized oral model. By implementing the method of the embodiments of the present application, a real alignment result of the upper and lower jaws can be obtained.

Description

Technical Field

[0001] This application relates to the field of oral data processing technology, and in particular to a method, apparatus, computer equipment and storage medium for optimizing model occlusion. Background Technology

[0002] In digital dental care, accurate occlusal data is crucial for the fabrication of prostheses, the design of invisible aligners, and the planning of implant surgery.

[0003] After obtaining the upper and lower jaw models through scanning, the occlusal data collected from the patient's mouth is stitched together for alignment. However, because the collected occlusal data may not be the actual static occlusal state data of the patient's mouth (e.g., the patient's bite is not in place), or due to post-scraping errors, the occlusal relationship may not be accurate enough. In this case, an occlusal optimization algorithm is needed to fine-tune the occlusal relationship to get as close as possible to the patient's actual occlusal relationship.

[0004] However, current occlusion optimization algorithms only focus on the occlusion relationship of the oral model and do not consider the actual situation inside the patient's mouth. This can lead to the occlusion relationship on the optimized oral model not being the actual occlusion relationship inside the patient's mouth, making it difficult to obtain the true alignment results of the upper and lower jaws. Summary of the Invention

[0005] This application provides a model bite optimization method, apparatus, computer equipment, and storage medium, which can obtain the true alignment results of the upper and lower jaws.

[0006] In a first aspect, embodiments of this application provide a model bite optimization method, which includes:

[0007] Obtain an oral cavity model of the target object, the oral cavity model including a first single jaw model and a second single jaw model, both of which include an occlusal contact area;

[0008] Generate a second target single jaw model in the current pose of the second single jaw model. The second target single jaw model simulates the elastic deformation that occurs when the second single jaw model bites in the current pose.

[0009] Based on the occlusal contact area and the vertex collision relationship between the first and second single-jaw models, the vertex weights of each jaw vertex in the second single-jaw model are determined.

[0010] Based on the preset occlusion optimization algorithm, the pose of the second single jaw model is updated according to the weight of each vertex and the second target single jaw model;

[0011] The positional relationship between the first single jaw model and the second single jaw model after the updated pose is used to determine whether the occlusion optimization algorithm meets the preset convergence condition.

[0012] If the occlusion optimization algorithm does not meet the convergence condition, then return to the step of generating the second target single jaw model of the second single jaw model in the current pose, until the occlusion optimization algorithm meets the convergence condition and outputs the optimized oral cavity model.

[0013] In some embodiments, obtaining the oral cavity model of the target object includes:

[0014] Acquire an oral cavity texture image of the target object, the oral cavity texture image including test strip bite imprints;

[0015] Extract the occlusal contact area image from the oral cavity texture image;

[0016] The occlusal contact area image is mapped to the original oral cavity model corresponding to the target object through texture mapping to obtain the oral cavity model.

[0017] In some embodiments, extracting the occlusal contact area image from the oral cavity texture image includes:

[0018] The oral cavity texture image is subjected to image recognition processing to determine multiple test strip bite imprint images in the oral cavity texture image;

[0019] The bite imprint images of multiple test strips are filtered if the area of ​​the region is smaller than a preset area to obtain the bite contact area image.

[0020] In some embodiments, obtaining the oral cavity model of the target object includes:

[0021] Obtain the original oral cavity model of the target object;

[0022] Based on the curvature characteristics of each grid in the original oral cavity model, wear surface identification processing is performed on the original first single jaw model and the original second single jaw model in the original oral cavity model, and the identified wear surface is determined as the occlusal contact area to obtain the oral cavity model.

[0023] In some embodiments, determining the vertex weights of each jaw vertex in the second single-jaw model based on the occlusal contact area and the vertex collision relationship between the first and second single-jaw models includes:

[0024] For each of the jaw apexes, determine whether the jaw apex is located in the occlusal contact area of ​​the second single jaw model to obtain a first determination result, and determine whether the jaw apex collides with the occlusal contact area of ​​the first single jaw model to obtain a second determination result;

[0025] Based on the corresponding first judgment result and the corresponding second judgment result, the vertex weights of each jaw vertex are determined respectively.

[0026] In some embodiments, determining the vertex weights of each jaw vertex based on the corresponding first determination result and the corresponding second determination result includes:

[0027] Based on the corresponding first judgment result and the corresponding second judgment result, the first vertex weight of each jaw vertex is determined respectively;

[0028] The second vertex weight of each jaw vertex is determined based on the tooth priority corresponding to each jaw vertex.

[0029] The vertex weights of each jaw vertex are determined based on the first vertex weight and the second vertex weight.

[0030] In some embodiments, determining the first vertex weight of each jaw vertex based on the corresponding first judgment result and the corresponding second judgment result includes:

[0031] If the first judgment result indicates that the jaw vertex is located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex collides with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the first weight.

[0032] If the first judgment result indicates that the jaw vertex is located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex does not collide with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the second weight, and the second weight is less than the first weight.

[0033] If the first judgment result indicates that the jaw vertex is not located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex collides with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the third weight, and the third weight is less than the first weight.

[0034] If the first judgment result indicates that the jaw vertex is not located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex does not collide with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the fourth weight, and the fourth weight is less than the second weight and the third weight.

[0035] In some embodiments, updating the pose of the second single jaw model based on a preset occlusal optimization algorithm according to the vertex weights and the second target single jaw model includes:

[0036] The pose of the second single-jaw model is updated by minimizing the value of the objective function in the occlusion optimization algorithm, wherein the objective function is as follows:

[0037] ;

[0038] Where E is the function value, N is the total number of jaw vertices in the second single-jaw model, and i is the index of the jaw vertex. P i Let V be the current vertex position of the i-th jaw vertex, C be the current centroid displacement vector of the second single jaw model, R be the current rotation matrix of the second single jaw model, and V be the current centroid displacement vector of the second single jaw model. i Let V be the position of the i-th jaw vertex relative to the centroid in the second single-jaw model. i Q is a fixed value. i Let m be the target vertex position of the i-th jaw vertex in the second target single jaw model. i is the vertex weight of the i-th jaw vertex in the second single jaw model.

[0039] In some embodiments, the convergence condition is that the maximum occlusal depth between the first single jaw model and the second single jaw model is less than a preset maximum occlusal depth threshold, and the number of teeth in the second single jaw model that satisfy occlusal contact is greater than a tooth number threshold.

[0040] In some embodiments, before generating the second target single jaw model of the second single jaw model in the current pose, the method further includes:

[0041] The oral cavity model is subjected to miscellaneous data recognition processing to obtain miscellaneous data recognition results;

[0042] If the miscellaneous data identification result indicates the presence of miscellaneous data, then the oral cavity model is subjected to miscellaneous data deletion processing based on the miscellaneous data identification result.

[0043] In some embodiments, the step of performing noisy data deletion processing on the oral cavity model based on the noisy data identification result includes:

[0044] The user interface displays miscellaneous data prompts corresponding to the miscellaneous data identification results.

[0045] Receive a noisy data deletion operation triggered by the user based on the noisy data prompt information;

[0046] The oral cavity model is processed to remove miscellaneous data based on the aforementioned miscellaneous data removal operation;

[0047] Alternatively, based on a preset miscellaneous data deletion model, the miscellaneous data indicated by the miscellaneous data identification result can be processed to delete miscellaneous data.

[0048] Secondly, embodiments of this application also provide a model bite optimization device, which includes:

[0049] The transceiver unit is used to acquire the oral cavity model of the target object. The oral cavity model includes a first single jaw model and a second single jaw model. Both the first single jaw model and the second single jaw model include an occlusal contact area.

[0050] The processing unit is configured to generate a second target single jaw model of the second single jaw model in the current pose, the second target single jaw model simulating the elastic deformation of the second single jaw model during occlusion in the current pose; determine the vertex weights of each jaw vertex in the second single jaw model based on the occlusal contact area and the vertex collision relationship between the first and second single jaw models; update the pose of the second single jaw model based on a preset occlusal optimization algorithm, according to the vertex weights and the second target single jaw model; determine whether the occlusal optimization algorithm meets a preset convergence condition based on the positional relationship between the first single jaw model and the second single jaw model after the updated pose; if the occlusal optimization algorithm does not meet the convergence condition, return to the step of generating the second target single jaw model of the second single jaw model in the current pose until the occlusal optimization algorithm meets the convergence condition, and output the optimized oral cavity model.

[0051] Thirdly, embodiments of this application also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0052] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, can implement the above-described method.

[0053] This application provides a method, apparatus, computer device, and storage medium for optimizing model occlusion. The oral model obtained in this application includes the actual occlusal contact areas of the upper and lower jaws (two single jaws). The occlusion optimization algorithm is constrained by vertex weights generated from these actual occlusal contact areas. Therefore, when optimizing the occlusal relationship on the oral model (adjusting the pose of the second single jaw model) using the occlusion optimization algorithm provided in this application, the actual intraoral situation of the target object (such as a patient) is considered, thereby obtaining the actual alignment result of the upper and lower jaws of the target object. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 A schematic flowchart of the model bite optimization method provided in the embodiments of this application;

[0056] Figure 2 A schematic diagram of a sub-process of the model bite optimization method provided in the embodiments of this application;

[0057] Figure 3 A schematic diagram of an oral texture image for the model bite optimization method provided in the embodiments of this application;

[0058] Figure 4 A schematic diagram of a sub-process of the model bite optimization method provided in the embodiments of this application;

[0059] Figure 5 A schematic diagram of the wear surface region in the model bite optimization method provided in the embodiments of this application;

[0060] Figure 6 A schematic diagram of a sub-process of the model bite optimization method provided in the embodiments of this application;

[0061] Figure 7 A schematic diagram of a sub-process of the model bite optimization method provided in the embodiments of this application;

[0062] Figure 8 A schematic block diagram of the model bite optimization device provided in the embodiments of this application;

[0063] Figure 9 A schematic block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0064] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0066] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0067] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0068] This application provides a model bite optimization method, apparatus, computer equipment, and storage medium.

[0069] The execution subject of the model bite optimization method can be the model bite optimization device provided in the embodiments of this application, or a computer device that integrates the model bite optimization device. The model bite optimization device can be implemented in hardware or software, and the computer device can be a terminal or a server.

[0070] Figure 1 This is a schematic flowchart of the model bite optimization method provided in the embodiments of this application. Figure 1 As shown, the method includes the following steps S110-S160.

[0071] S110. Obtain the oral cavity model of the target object. The oral cavity model includes a first single jaw model and a second single jaw model. Both the first single jaw model and the second single jaw model include the occlusal contact area.

[0072] In this embodiment, the target object is the patient's oral cavity, or other user oral cavities that require alignment of the upper and lower jaw models. The oral cavity model in this embodiment can be obtained by real-time scanning with an oral scanner, or it can be imported from an external source, such as from a cloud database.

[0073] Specifically, the oral cavity model in this embodiment includes a first single jaw model and a second single jaw model, and both the first single jaw model and the second single jaw model include an occlusal contact area, which is a real occlusal contact area.

[0074] The first single jaw model can be a maxillary model or a mandibular model. When the first single jaw model is a maxillary model, the second single jaw model is a mandibular model. When the first single jaw model is a mandibular model, the second single jaw model is a maxillary model.

[0075] In some embodiments, please refer to Figure 2 The target subject's teeth have bite marks left by bite test strips. The target subject's oral cavity model is obtained through the following steps:

[0076] a1101. Obtain the oral cavity texture image of the target object, which includes the bite imprint of the test strip;

[0077] a1102. Extract the occlusal contact area image from the oral cavity texture image;

[0078] a1103. The image of the occlusal contact area is mapped to the original oral cavity model corresponding to the target object through texture mapping relationship to obtain the oral cavity model.

[0079] Specifically, after leaving static occlusal impressions on the patient's teeth using occlusal strips, an oral scan is performed to obtain images of the patient's oral cavity texture (e.g., ...). Figure 3 As shown, Figure 3 This is a schematic diagram of the maxillary and mandibular models in the oral cavity texture image of this embodiment, where the red parts on the teeth represent the test strip occlusal imprints. Then, occlusal contact point identification (i.e., extracting the occlusal contact area image, such as extracting the red parts on the teeth) is performed: Specifically, image recognition processing is performed on the oral cavity texture image to determine multiple test strip occlusal imprint images in the oral cavity texture image; test strip occlusal imprint images with an area smaller than a preset area are filtered to obtain occlusal contact area images. Finally, the identified occlusal contact area images are mapped onto the grid points of the original oral cavity model through texture mapping relationships to obtain an oral cavity model containing the occlusal contact areas.

[0080] The original oral model is obtained by scanning the target object whose teeth do not have test strip occlusal imprints, either through scanning or external retrieval. The occlusal contact area is fused to the original oral model using a mapping method, resulting in an oral model containing the occlusal contact area, rather than directly obtaining an oral model containing the occlusal contact area. This avoids interference from test strip occlusal imprints in model construction and improves the model construction effect.

[0081] Furthermore, in some embodiments, the original oral cavity model and the oral cavity texture image may be obtained from the same scan, and AI is used to automatically identify the bite marks on the test strips on the model during model construction. In some embodiments, the original oral cavity model and the oral cavity texture image may be obtained from different scans, or from different time periods.

[0082] In some embodiments, the original oral cavity model and the oral cavity texture image are obtained using the same device, such as a camera or scanner, which is either an intraoral or extraoral scanner. This setup ensures data consistency and improves occlusion optimization.

[0083] If the original oral cavity model and the oral cavity texture image are obtained from the same scanner and the same patient scan, then the original oral cavity model is reconstructed from the black and white image captured by the scanner's black and white camera; the oral cavity texture image is captured by the scanner's texture camera. Since the two cameras are integrated into the same device, their relative poses are fixed and known. Therefore, there is a definite correspondence between the black and white image and the texture image. A texture mapping relationship can be established based on this. Finally, based on this texture mapping relationship, the oral cavity texture image is mapped onto the original oral cavity model to generate a textured oral cavity model.

[0084] In some embodiments, the original oral cavity model and the oral cavity texture image are obtained by different devices, such as by different scanners, or, for example, the original oral cavity model is obtained by a scanner and the oral cavity texture image is obtained by a camera, wherein the scanner is an intraoral scanner or an extraoral scanner.

[0085] It should be noted that if the original oral cavity model and the oral cavity texture image are acquired by different devices or at different times, spatial alignment needs to be completed through common feature matching before texture mapping (generating a textured oral cavity model) to establish an accurate texture mapping relationship.

[0086] If the original oral cavity model and oral cavity texture image are obtained through different scanners, there is no need to restrict the region or device, making it convenient for users to obtain models and images in different regions or with different devices.

[0087] If the original oral cavity model is obtained through a scanner and the oral cavity texture image is obtained through a camera, then a higher resolution camera can be used to obtain a more accurate oral cavity texture image. This results in more precise texture data, more accurate bite optimization, and no restrictions on the location of oral cavity texture image acquisition, making it convenient for users to obtain oral cavity texture images at home.

[0088] In other embodiments, please refer to Figure 4 The oral cavity model of the target object is obtained through the following steps:

[0089] b1101. Obtain the original oral cavity model of the target object;

[0090] b1102. Based on the curvature characteristics of each grid in the original oral model, wear surface identification processing is performed on the original first single jaw model and the original second single jaw model in the original oral model, and the identified wear surface is determined as the occlusal contact area to obtain the oral model.

[0091] Specifically, the original oral cavity model of the target object is scanned or externally retrieved, including the original first single jaw model and the original second single jaw model. Then, wear surfaces are identified for both the original first and second single jaw models. Since wear surfaces are typically relatively flat areas on the tooth mesh, they can be identified using the curvature features of the mesh in the oral cavity model. Furthermore, smaller wear surface areas need to be filtered out. Finally, the filtered wear surface areas are mapped onto the mesh points of the oral cavity model (e.g., ...). Figure 5 As shown, Figure 5 The area inside the red circle is the identified wear surface area, which gives us an oral cavity model that includes the occlusal contact area.

[0092] In addition, the wear surface in the model can be identified by training an AI model.

[0093] In some embodiments, to more comprehensively identify the occlusal contact area, the occlusal contact area can be determined by combining the occlusal imprint of the test strip with the automatic identification of the wear surface. In this case, such as... Figure 6 As shown, the oral cavity model of the target object is obtained through the following steps:

[0094] c1101. Obtain the oral cavity texture image of the target object, which includes the bite imprint of the test strip;

[0095] c1102. Extract the occlusal contact area image from the oral cavity texture image;

[0096] c1103. Map the occlusal contact area image to the original oral cavity model corresponding to the target object through texture mapping relationship to obtain the first candidate model. The occlusal contact area image in the second candidate model is the first candidate occlusal contact area.

[0097] The steps c1101-c1103 for determining the first candidate model are similar to the steps a1101-a1103 for determining the oral cavity model, and will not be elaborated here.

[0098] c1104. Obtain the original oral cavity model of the target object;

[0099] c1105. Based on the curvature characteristics of each grid in the original oral model, wear surface identification processing is performed on the original first single jaw model and the original second single jaw model in the original oral model, and the identified wear surface is determined as the second candidate occlusal contact area to obtain the second candidate model.

[0100] The steps c1104-c1105 for determining the first candidate model are similar to the steps b1101-b1102 for determining the oral cavity model, and will not be elaborated here.

[0101] c1106. Align the first candidate model and the second candidate model to obtain the aligned model. Determine the first candidate occlusal contact area and the second candidate occlusal contact area in the aligned model as the occlusal contact area in the oral cavity model to obtain the oral cavity model.

[0102] In this embodiment, by combining the bite imprint of the test strip with the automatic recognition of the worn surface to determine the bite contact area, the identified bite contact area can be more comprehensive.

[0103] Furthermore, for some data that only scanned one side (one of the front, left, and right sides) of the bite, the bite contact area obtained by traditional bite optimization algorithms often deviates from the actual bite. The above embodiments of this application automatically identify and determine the bite contact area by using bite imprints and / or wear surfaces on test strips, making the calculated bite contact area closer to the actual bite state. Based on this, subsequent orthodontic plans, crown designs, or restoration designs can be made, resulting in orthodontic plans, crowns, or restorations that are more suitable for the patient's oral cavity.

[0104] S120. Generate a second target single jaw model in the current pose of the second single jaw model. The second target single jaw model simulates the elastic deformation that occurs when the second single jaw model bites in the current pose.

[0105] In this embodiment, after each iteration, a second target single jaw model needs to be regenerated in the current pose (the current pose is updated after each iteration). This second target single jaw model is intermediate data generated during the execution of the occlusion optimization algorithm. It is an ideal occlusion state model generated internally by the algorithm and deformed. It simulates the morphological changes that teeth should have in real occlusion through non-rigid deformation technology, thereby guiding the optimization algorithm to gradually adjust the second single jaw model (since the second single jaw model is a movable jaw, mandibular adjustment is performed) to make it closer to the real occlusion relationship in the patient's mouth.

[0106] In some embodiments, to avoid interference from miscellaneous data on the dental and maxillofacial surfaces of the oral model in optimizing the occlusal state and to obtain a more accurate occlusal state, the following steps are also included before performing occlusal optimization and during the occlusal optimization process (such as after entering the occlusal optimization step and before formally generating the second target single jaw model in the current pose): performing miscellaneous data identification processing on the oral model to obtain miscellaneous data identification results; if the miscellaneous data identification results indicate the presence of miscellaneous data, then performing miscellaneous data deletion processing on the oral model based on the miscellaneous data identification results.

[0107] The aforementioned miscellaneous data includes food residue and / or saliva bubbles, etc. The results of miscellaneous data identification can be obtained through a trained miscellaneous data identification model for intelligent deletion of miscellaneous data identification results, or through an identification algorithm. Miscellaneous data identification processing can be performed directly on the oral cavity model, or it can be done by projecting the oral cavity model to obtain multiple two-dimensional images, performing miscellaneous data identification processing on these multiple two-dimensional images, and then back-projecting the processing results back onto the oral cavity model.

[0108] Furthermore, based on the miscellaneous data identification results, the oral model is processed to remove miscellaneous data, including: displaying miscellaneous data prompt information corresponding to the miscellaneous data identification results through the user interface; receiving the miscellaneous data deletion operation triggered by the user based on the miscellaneous data prompt information; performing miscellaneous data deletion processing on the oral model based on the miscellaneous data deletion operation (manual deletion); or, directly deleting the miscellaneous data indicated by the miscellaneous data identification results (automatic deletion).

[0109] Among them, deleting the miscellaneous data indicated by the miscellaneous data identification result can be done by deleting the source data of the miscellaneous data, or by deleting the miscellaneous data from the intermediate product or the reconstructed model so that the display interface does not show the miscellaneous data, or by separating the first target area and hiding it from the interactive interface, or by only displaying it semi-transparently and not participating in the bite optimization process, etc.

[0110] S130. Based on the occlusal contact area and the vertex collision relationship between the first and second single-jaw models, determine the vertex weights of each jaw vertex in the second single-jaw model.

[0111] In this embodiment, each iteration of the calculation requires updating the vertex weight of each jaw vertex. The vertex weight is related to whether the vertex is located in the occlusal contact area and whether it collides with the first single jaw model.

[0112] Specifically, in some embodiments, such as Figure 7 As shown, the vertex weights of each jaw vertex are determined according to the following steps:

[0113] S1301. For each jaw vertex, determine whether the jaw vertex is located in the occlusal contact area of ​​the second single jaw model to obtain the first judgment result, and determine whether the jaw vertex collides with the occlusal contact area of ​​the first single jaw model to obtain the second judgment result.

[0114] In some embodiments, the first and second single-jaw models are the maxillary and mandibular models, respectively, which can be acquired in two separate scans and stored independently. In some embodiments, the oral cavity model may also include one or more static occlusal relationships of the maxillary and mandibular models. The mandibular and maxillary models are controlled to be in a specified occlusal state based on the static occlusal relationship, and collision detection is performed to obtain a second judgment result. The static occlusal relationship can be obtained by scanning the patient's oral cavity from multiple sides (e.g., anterior, left, and right sides) using an oral scanner, or by simulation using an AI model, or by acquisition from the cloud or local storage.

[0115] In some embodiments, the motion trajectory of a mandibular model (such as a second single-jaw model) is acquired, and then the mandibular model is moved based on the motion trajectory to perform collision detection with the maxillary model to obtain a second judgment result. The motion trajectory of the mandibular model can be obtained by scanning and processing the oral cavity simulating biting movements using an oral scanner and / or CBCT and / or facial scanner, or it can be simulated using an AI model, or it can be obtained from the cloud or locally.

[0116] S1302. Based on the corresponding first judgment result and the corresponding second judgment result, determine the vertex weight of each jaw vertex respectively.

[0117] Furthermore, step S1302 specifically includes:

[0118] Based on the corresponding first judgment result and the corresponding second judgment result, determine the first vertex weight of each mandibular vertex; determine the second vertex weight of each mandibular vertex based on the tooth priority corresponding to each mandibular vertex; determine the vertex weight of each mandibular vertex based on the first vertex weight and the second vertex weight.

[0119] In this embodiment, different tooth priorities are pre-set for teeth in different positions.

[0120] Furthermore, based on the corresponding first judgment result and the corresponding second judgment result, the first vertex weight of each jaw vertex is determined, including:

[0121] If the first judgment result indicates that the jaw vertex is located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex collides with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined as the first weight.

[0122] If the first judgment result indicates that the jaw vertex is located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex does not collide with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the second weight, and the second weight is less than the first weight.

[0123] If the first judgment result indicates that the jaw vertex is not located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex collides with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the third weight, and the third weight is less than the first weight.

[0124] If the first judgment result indicates that the jaw vertex is not located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex does not collide with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the fourth weight, and the fourth weight is less than the second weight and the third weight.

[0125] The higher the weight, the greater the influence of the vertex on the posture of the mandibular dental model.

[0126] As can be seen, the weight of each jaw vertex can be dynamically determined through this embodiment. This weight is obtained by constraining the actual occlusal contact area, so that the subsequent occlusal optimization algorithm can optimize the occlusal relationship based on the actual occlusal contact area.

[0127] S140. Based on the preset occlusal optimization algorithm, update the pose of the second single jaw model according to the weight of each vertex and the second target single jaw model.

[0128] In this embodiment, the preset bite optimization algorithm can be either the Shape Matching algorithm or the Iterative Closest Point Algorithm (ICP) algorithm.

[0129] Specifically, the pose of the second single-jaw model is updated by minimizing the function value of the objective function in the occlusion optimization algorithm. The objective function is as follows:

[0130] ;

[0131] Where E is the function value, N is the total number of jaw vertices in the second single-jaw model, and i is the index of the jaw vertex. P i Let V be the current vertex position of the i-th jaw vertex, C be the current centroid displacement vector of the second single jaw model, R be the current rotation matrix of the second single jaw model, and V be the current position of the i-th jaw vertex. i Let V be the position of the i-th jaw vertex relative to the centroid in the second single-jaw model. iThis is a fixed value (which can be obtained from the coordinates and centroid position of the vertex in the initial state (without meshing adjustment), i.e. ), Q i Let m be the target vertex position of the i-th jaw vertex in the second target single jaw model. i represents the vertex weight of the i-th jaw vertex in the second single jaw model.

[0132] The posture of the second single-jaw model is controlled by the position (C) and rotation (R) of the center of gravity. Here, C is a three-dimensional vector [X, Y, Z], and R is the function value of the objective function in the three-dimensional matrix minimization occlusal optimization algorithm, which aims to make the position of the mandible as close as possible to the positions of each vertex of the second target single-jaw model (non-rigid oral cavity model).

[0133] S150. Determine whether the occlusion optimization algorithm meets the preset convergence conditions based on the positional relationship between the first single jaw model and the second single jaw model after the updated pose. If not, return to step S120; if yes, proceed to step S160.

[0134] Specifically, the convergence condition is that the maximum occlusal depth between the first and second single-jaw models is less than a preset maximum occlusal depth threshold, and the number of teeth satisfying occlusal contact in the second single-jaw model is greater than a tooth number threshold. Due to scanning requirements, a certain amount of occlusal penetration is allowed in both the upper and lower jaws, typically within 0.3 (i.e., the maximum occlusal depth threshold is set within 0.3).

[0135] This embodiment determines the maximum occlusal depth and the number of teeth in occlusal contact between the first and second single-jaw models by the positional relationship between the first single-jaw model and the second single-jaw model after the pose is updated.

[0136] In this context, teeth that satisfy occlusal contact are defined as those whose overlapping area in the intersecting region of the corresponding teeth in the second maxillary single jaw model has an overlap rate greater than a preset overlap threshold. The tooth number threshold can be preset or dynamically calculated based on the actual number of teeth in the target object, for example, calculated according to a certain proportion of the actual number of teeth.

[0137] S160, Output the optimized oral cavity model.

[0138] In this embodiment, when the occlusion optimization algorithm meets the convergence condition, it outputs an optimized oral cavity model, which can reflect the true alignment result of the upper and lower jaws of the target object.

[0139] Specifically, the optimized oral model can be output to an interactive interface for display, sent to a dental laboratory, or uploaded to the cloud.

[0140] In summary, the oral model obtained in this application includes the actual occlusal contact area of ​​the upper and lower jaws, and the occlusal optimization algorithm is constrained by the vertex weights generated by the actual occlusal contact area. It can be seen that when optimizing the occlusal relationship on the oral model (adjusting the pose of the second single jaw model) by the occlusal optimization algorithm provided in this application, the actual situation inside the mouth of the target object (such as a patient) is taken into consideration, thereby obtaining the actual alignment result of the upper and lower jaws of the target object.

[0141] Figure 8 This is a schematic block diagram of a model bite optimization device provided in an embodiment of this application. Figure 8 As shown, corresponding to the above-described model bite optimization method, this application also provides a model bite optimization device 500. This model bite optimization device 500 includes a unit for performing the above-described model bite optimization method, and can be configured in an electronic device. Specifically, please refer to... Figure 8 The model bite optimization device 500 includes a transceiver unit 501 and a processing unit 502.

[0142] Specifically, the transceiver unit 501 can be an oral scanner or a computer connected to the oral scanner via wired or wireless means, and the processing unit 502 can be a computer connected to the oral scanner via wired or wireless means, a terminal, a server, or a cloud. The method corresponding to this device is applicable to 3D scanners such as oral scanners (intraoral scanners or extraoral scanners). This device can be understood, for example, as a 3D scanner, mobile phone, tablet computer, laptop computer, desktop computer, smart TV, cloud server, VR / AR device, or cloud device.

[0143] in:

[0144] The transceiver unit 501 is used to acquire the oral cavity model of the target object. The oral cavity model includes a first single jaw model and a second single jaw model. Both the first single jaw model and the second single jaw model include an occlusal contact area.

[0145] Processing unit 502 is used to generate a second target single jaw model of the second single jaw model in the current pose. The second target single jaw model simulates the elastic deformation of the second single jaw model during occlusion in the current pose. Based on the occlusal contact area and the vertex collision relationship between the first and second single jaw models, the vertex weights of each jaw vertex in the second single jaw model are determined. Based on a preset occlusal optimization algorithm, the pose of the second single jaw model is updated according to the vertex weights and the second target single jaw model. The positional relationship between the first single jaw model and the second single jaw model after the updated pose is used to determine whether the occlusal optimization algorithm meets the preset convergence conditions. If the occlusal optimization algorithm does not meet the convergence conditions, the process returns to the step of generating the second target single jaw model of the second single jaw model in the current pose until the occlusal optimization algorithm meets the convergence conditions, and the optimized oral model is output.

[0146] In some embodiments, when performing the step of acquiring the oral cavity model of the target object, the transceiver unit 501 is specifically used for:

[0147] The oral cavity texture image of the target object is obtained, the oral cavity texture image including the bite imprint of the test strip; the bite contact area image in the oral cavity texture image is extracted by the processing unit 502; the bite contact area image is mapped to the original oral cavity model corresponding to the target object by the processing unit 502 through the texture mapping relationship to obtain the oral cavity model.

[0148] In some embodiments, when performing the step of extracting the occlusal contact region image from the oral cavity texture image, the processing unit 502 is specifically used for:

[0149] Image recognition processing is performed on the oral cavity texture image to identify multiple test strip bite imprint images in the oral cavity texture image; test strip bite imprint images with a region area smaller than a preset area are filtered to obtain bite contact area images.

[0150] In some embodiments, when performing the step of acquiring the oral cavity model of the target object, the transceiver unit 501 is specifically used for:

[0151] Obtain the original oral cavity model of the target object;

[0152] The processing unit 502 uses the curvature characteristics of each grid in the original oral model to perform wear surface identification processing on the original first single jaw model and the original second single jaw model in the original oral model, and determines the identified wear surface as the occlusal contact area to obtain the oral model.

[0153] In some embodiments, when the processing unit 502 performs the step of determining the vertex weights of each jaw vertex in the second single jaw model based on the occlusal contact area and the vertex collision relationship between the first and second single jaw models, it is specifically used for:

[0154] For each jaw vertex, determine whether the jaw vertex is located in the occlusal contact area of ​​the second single jaw model to obtain the first judgment result, and determine whether the jaw vertex collides with the occlusal contact area of ​​the first single jaw model to obtain the second judgment result;

[0155] Based on the corresponding first judgment result and the corresponding second judgment result, the vertex weights of each jaw vertex are determined respectively.

[0156] In some embodiments, when the processing unit 502 performs the step of determining the vertex weights of each jaw vertex based on the corresponding first judgment result and the corresponding second judgment result, it is specifically used for:

[0157] Based on the corresponding first judgment result and the corresponding second judgment result, the first vertex weight of each jaw vertex is determined respectively;

[0158] The weight of the second vertex of each jaw vertex is determined based on the tooth priority corresponding to each jaw vertex.

[0159] The vertex weights of each jaw vertex are determined based on the weights of the first and second vertices.

[0160] In some embodiments, when the processing unit 502 performs the step of determining the first vertex weight of each jaw vertex based on the corresponding first judgment result and the corresponding second judgment result, it is specifically used for:

[0161] If the first judgment result indicates that the jaw vertex is located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex collides with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined as the first weight.

[0162] If the first judgment result indicates that the jaw vertex is located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex does not collide with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the second weight, and the second weight is less than the first weight.

[0163] If the first judgment result indicates that the jaw vertex is not located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex collides with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the third weight, and the third weight is less than the first weight.

[0164] If the first judgment result indicates that the jaw vertex is not located in the occlusal contact area of ​​the second single jaw model, and the second judgment result indicates that the jaw vertex does not collide with the occlusal contact area of ​​the first single jaw model, then the first vertex weight of the jaw vertex is determined to be the fourth weight, and the fourth weight is less than the second weight and the third weight.

[0165] In some embodiments, when the processing unit 502 executes the step of updating the pose of the second single jaw model based on the weights of each vertex and the second target single jaw model using a preset occlusion optimization algorithm, it is specifically used for:

[0166] The pose of the second single-jaw model is updated by minimizing the function value of the objective function in the occlusion optimization algorithm. The objective function is as follows:

[0167] ;

[0168] Where E is the function value, N is the total number of jaw vertices in the second single-jaw model, and i is the index of the jaw vertex. P i Let V be the current vertex position of the i-th jaw vertex, C be the current centroid displacement vector of the second single jaw model, R be the current rotation matrix of the second single jaw model, and V be the current position of the i-th jaw vertex. i Let V be the position of the i-th jaw vertex relative to the centroid in the second single-jaw model. i Q is a fixed value. i Let m be the target vertex position of the i-th jaw vertex in the second target single jaw model. i represents the vertex weight of the i-th jaw vertex in the second single jaw model.

[0169] In some embodiments, the convergence condition is that the maximum occlusal depth between the first single jaw model and the second single jaw model is less than a preset maximum occlusal depth threshold, and the number of teeth in the second single jaw model that satisfy occlusal contact is greater than a tooth number threshold.

[0170] In summary, the oral model obtained in this application includes the actual occlusal contact area of ​​the upper and lower jaws, and the occlusal optimization algorithm is constrained by the vertex weights generated by the actual occlusal contact area. It can be seen that when optimizing the occlusal relationship on the oral model (adjusting the pose of the second single jaw model) by the occlusal optimization algorithm provided in this application, the actual situation inside the mouth of the target object (such as a patient) is taken into consideration, thereby obtaining the actual alignment result of the upper and lower jaws of the target object.

[0171] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned model bite optimization device and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0172] The aforementioned model bite optimization device can be implemented as a computer program, which can, for example... Figure 9 It runs on the computer device shown.

[0173] Please see Figure 9 , Figure 9This is a schematic block diagram of a computer device 600 provided in an embodiment of this application. The computer device 600 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0174] See Figure 9 The computer device 600 includes a processor 602, a memory, and a network interface 605 connected via a system bus 601. The memory may include a non-volatile storage medium 603 and internal memory 604.

[0175] The non-volatile storage medium 603 may store an operating system 6031 and a computer program 6032. The computer program 6032 includes program instructions that, when executed, cause the processor 602 to perform a model meshing optimization method.

[0176] The processor 602 provides computing and control capabilities to support the operation of the entire computer device 600.

[0177] The internal memory 604 provides an environment for the execution of the computer program 6032 in the non-volatile storage medium 603. When the computer program 6032 is executed by the processor 602, the processor 602 can execute a model bite optimization method.

[0178] This network interface 605 is used for network communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 600 to which the present application is applied. The specific computer device 600 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0179] The processor 602 is used to run the computer program 6032 stored in the memory to perform the following steps:

[0180] Obtain the oral cavity model of the target object. The oral cavity model includes a first single jaw model and a second single jaw model. Both the first and second single jaw models include the occlusal contact area.

[0181] Generate a second target single jaw model in the current pose of the second single jaw model. The second target single jaw model simulates the elastic deformation that occurs when the second single jaw model bites in the current pose.

[0182] Based on the occlusal contact area and the vertex collision relationship between the first and second single jaw models, the vertex weights of each jaw vertex in the second single jaw model are determined.

[0183] Based on the preset occlusion optimization algorithm, the pose of the second single jaw model is updated according to the weight of each vertex and the second target single jaw model.

[0184] The positional relationship between the first single jaw model and the second single jaw model after the updated pose is used to determine whether the occlusion optimization algorithm meets the preset convergence conditions.

[0185] If the occlusion optimization algorithm does not meet the convergence condition, return to the step of generating the second target single jaw model in the current pose, until the occlusion optimization algorithm meets the convergence condition and outputs the optimized oral model.

[0186] It should be understood that, in the embodiments of this application, the processor 602 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0187] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0188] Therefore, this application also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the following steps:

[0189] Obtain the oral cavity model of the target object. The oral cavity model includes a first single jaw model and a second single jaw model. Both the first and second single jaw models include the occlusal contact area.

[0190] Generate a second target single jaw model in the current pose of the second single jaw model. The second target single jaw model simulates the elastic deformation that occurs when the second single jaw model bites in the current pose.

[0191] Based on the occlusal contact area and the vertex collision relationship between the first and second single jaw models, the vertex weights of each jaw vertex in the second single jaw model are determined.

[0192] Based on the preset occlusion optimization algorithm, the pose of the second single jaw model is updated according to the weight of each vertex and the second target single jaw model.

[0193] The positional relationship between the first single jaw model and the second single jaw model after the updated pose is used to determine whether the occlusion optimization algorithm meets the preset convergence conditions.

[0194] If the occlusion optimization algorithm does not meet the convergence condition, return to the step of generating the second target single jaw model in the current pose, until the occlusion optimization algorithm meets the convergence condition and outputs the optimized oral model.

[0195] The storage medium can be any computer-readable storage medium that can store program code, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0196] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0197] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0198] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0199] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0200] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of model occlusion optimization, characterized by, The method comprises the following steps: obtaining a dental model of a target object, the dental model comprising a first single jaw model and a second single jaw model, the first single jaw model and the second single jaw model each comprising a real occlusal contact area; generating a second target single jaw model of the second single jaw model in a current pose, the second target single jaw model simulating elastic deformation occurring when the second single jaw model is occluded in the current pose; determining vertex weights of each jaw vertex in the second single jaw model according to the occlusal contact area and a vertex collision relationship between the first single jaw model and the second single jaw model; updating the pose of the second single jaw model according to the vertex weights and the second target single jaw model based on a preset occlusal optimization algorithm; determining whether the occlusal optimization algorithm meets a preset convergence condition according to a positional relationship between the first single jaw model and the second single jaw model after the pose is updated; if the occlusal optimization algorithm does not meet the convergence condition, returning to the step of generating the second target single jaw model of the second single jaw model in the current pose until the occlusal optimization algorithm meets the convergence condition, and outputting an optimized dental model; the step of determining the vertex weights of each jaw vertex in the second single jaw model according to the occlusal contact area and the vertex collision relationship between the first single jaw model and the second single jaw model comprises: for each jaw vertex, determining whether the jaw vertex is located in the occlusal contact area of the second single jaw model to obtain a first determination result, and determining whether the jaw vertex collides with the occlusal contact area of the first single jaw model to obtain a second determination result; determining the vertex weight of each jaw vertex according to the corresponding first determination result and the corresponding second determination result.

2. The method of claim 1, wherein, The method comprises the following steps: obtaining a dental model of a target object, the dental model comprising a first single jaw model and a second single jaw model, the first single jaw model and the second single jaw model each comprising a real occlusal contact area; generating a second target single jaw model of the second single jaw model in a current pose, the second target single jaw model simulating elastic deformation occurring when the second single jaw model is occluded in the current pose; determining vertex weights of each jaw vertex in the second single jaw model according to the occlusal contact area and a vertex collision relationship between the first single jaw model and the second single jaw model; 3. The method of claim 2, wherein, updating the pose of the second single jaw model according to the vertex weights and the second target single jaw model based on a preset occlusal optimization algorithm; determining whether the occlusal optimization algorithm meets a preset convergence condition according to a positional relationship between the first single jaw model and the second single jaw model after the pose is updated; if the occlusal optimization algorithm does not meet the convergence condition, returning to the step of generating the second target single jaw model of the second single jaw model in the current pose until the occlusal optimization algorithm meets the convergence condition, and outputting an optimized dental model; 4. The method of claim 1, wherein, the step of determining the vertex weights of each jaw vertex in the second single jaw model according to the occlusal contact area and the vertex collision relationship between the first single jaw model and the second single jaw model comprises: for each jaw vertex, determining whether the jaw vertex is located in the occlusal contact area of the second single jaw model to obtain a first determination result, and determining whether the jaw vertex collides with the occlusal contact area of the first single jaw model to obtain a second determination result; determining the vertex weight of each jaw vertex according to the corresponding first determination result and the corresponding second determination result.

5. The method of claim 1, wherein, The method comprises the following steps: obtaining a dental model of a target object, the dental model comprising a first single jaw model and a second single jaw model, the first single jaw model and the second single jaw model each comprising a real occlusal contact area; generating a second target single jaw model of the second single jaw model in a current pose, the second target single jaw model simulating elastic deformation occurring when the second single jaw model is occluded in the current pose; determining vertex weights of each jaw vertex in the second single jaw model according to the occlusal contact area and a vertex collision relationship between the first single jaw model and the second single jaw model; updating the pose of the second single jaw model according to the vertex weights and the second target single jaw model based on a preset occlusal optimization algorithm; determining whether the occlusal optimization algorithm meets a preset convergence condition according to a positional relationship between the first single jaw model and the second single jaw model after the pose is updated; if the occlusal optimization algorithm does not meet the convergence condition, returning to the step of generating the second target single jaw model of the second single jaw model in the current pose until the occlusal optimization algorithm meets the convergence condition, and outputting an optimized dental model; the step of determining the vertex weights of each jaw vertex in the second single jaw model according to the occlusal contact area and the vertex collision relationship between the first single jaw model and the second single jaw model comprises: determine a first vertex weight of each of the jaw vertexes according to the corresponding first determination result and the corresponding second determination result; determine a second vertex weight of each of the jaw vertexes according to the tooth priority of the corresponding jaw vertex; determine the vertex weight of each of the jaw vertexes according to the first vertex weight and the second vertex weight.

6. The method of claim 5, wherein, The method further comprises: if the first determination result indicates that the jaw vertex is located in the occlusal contact region of the second single-jaw model, and the second determination result indicates that the jaw vertex collides with the occlusal contact region of the first single-jaw model, determining the first vertex weight of the jaw vertex as a first weight; if the first determination result indicates that the jaw vertex is not located in the occlusal contact region of the second single-jaw model, and the second determination result indicates that the jaw vertex collides with the occlusal contact region of the first single-jaw model, determining the first vertex weight of the jaw vertex as a third weight, the third weight being smaller than the first weight; if the first determination result indicates that the jaw vertex is not located in the occlusal contact region of the second single-jaw model, and the second determination result indicates that the jaw vertex does not collide with the occlusal contact region of the first single-jaw model, determining the first vertex weight of the jaw vertex as a fourth weight, the fourth weight being smaller than the second weight and the third weight. The method further comprises:

7. The method of claim 1, wherein, updating the pose of the second single-jaw model according to the vertex weight and the second target single-jaw model based on a preset occlusal optimization algorithm, wherein the updating comprises: updating the pose of the second single-jaw model by minimizing the function value of an objective function in the occlusal optimization algorithm, the objective function being as follows: ； wherein E is the function value, N is the total number of jaw vertices of the second single jaw model, i is the serial number of the jaw vertex, , P i is the current vertex position of the i-th jaw vertex, C is the current center of gravity displacement vector of the second single jaw model, R is the current rotation matrix of the second single jaw model, V i is the position of the i-th jaw vertex relative to the center of gravity in the second single jaw model, and V i is a fixed value, Q i is the target vertex position of the i-th jaw vertex in the second target single jaw model, m i is the vertex weight of the i-th jaw vertex in the second single jaw model.

8. The method of claim 1, wherein, The convergence condition is that the maximum bite penetration depth between the first single-jaw model and the second single-jaw model is smaller than a preset maximum bite penetration depth threshold, and the number of teeth satisfying occlusal contact in the second single-jaw model is greater than a tooth number threshold.

9. The method of claim 1, wherein, The method further comprises: performing a junk data identification process on the oral cavity model to obtain a junk data identification result; if the junk data identification result indicates that there is junk data, performing a junk data deletion process on the oral cavity model according to the junk data identification result.

10. The method of claim 9, wherein, The method further comprises: displaying junk data prompt information corresponding to the junk data identification result through a user interaction interface; receiving a junk data deletion operation triggered by a user based on the junk data prompt information; performing a junk data deletion process on the oral cavity model based on the junk data deletion operation; Or, directly to the mixed data indicated by the mixed data recognition result is carried out mixed data deletion processing.

11. A model occlusion optimization apparatus, characterized by, Comprise: The transceiver unit is configured to obtain a target object's oral model, the oral model comprises a first single jaw model and a second single jaw model, the first single jaw model and the second single jaw model both include a real occlusal contact area; The processing unit is configured to generate a second target single jaw model of the second single jaw model in a current pose, the second target single jaw model simulates the elastic deformation of the second single jaw model when occluding in the current pose; according to the occlusal contact area and the vertex collision relationship between the first single jaw model and the second single jaw model, determine the vertex weight of each jaw vertex in the second single jaw model; Based on the preset occlusion optimization algorithm, according to each vertex weight and the second target single jaw model, update the pose of the second single jaw model; according to the position relationship between the first single jaw model and the second single jaw model after updating the pose, determine whether the occlusion optimization algorithm meets the preset convergence condition; if the occlusion optimization algorithm does not meet the convergence condition, return to execute the step of generating the second target single jaw model of the second single jaw model in the current pose, until the occlusion optimization algorithm meets the convergence condition, output the optimized oral model; The processing unit is configured to: For each jaw vertex, determine whether the jaw vertex is located in the occlusal contact area of the second single jaw model to obtain a first determination result, and determine whether the jaw vertex collides with the occlusal contact area of the first single jaw model to obtain a second determination result; According to the corresponding first determination result and the corresponding second determination result, the vertex weight of each jaw vertex is determined respectively.

12. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the model occlusion optimization method of any one of claims 1-10.

13. A storage medium, characterized by The storage medium stores a computer program, the computer program comprises program instructions, the program instructions are executed by the processor to make the processor execute the model occlusion optimization method of any one of claims 1-10.

Images