Orthodontic monitoring method, device and system and storage medium

Abstract

The embodiment of the invention provides an orthodontic monitoring method. The method comprises the following steps: acquiring a first surface layer structure and a first surface layer appearance of teeth of a patient based on scanning; acquiring a current brace model input by a user, a historical surface structure at the end of the historical orthodontic period and a historical surface appearance; determining structure matching features based on the first surface structure and the current brace model; determining structure change features based on the historical surface structure; determining appearance change characteristics based on the historical surface appearance; determining an estimated surface structure based on the first surface structure, the structure matching feature and the structure change feature; determining an estimated surface appearance based on the first surface appearance and the appearance change feature; and based on the estimated surface layer structure, the estimated surface layer appearance and the current tooth socket model, determining a target surface layer structure, the end time of the current orthodontic period and tooth socket parameters of the next orthodontic period.

Description

Technical Field

[0001] The present invention relates to the technical field of orthodontic treatment, and in particular to an orthodontic monitoring method, device, system and storage medium. Background Art

[0002] Both doctors and patients need to pay close attention to the progress of orthodontic treatment. For doctors, due to the large number of patients, some details may be overlooked through manual examination, resulting in misdiagnosis and failure to correct the orthodontic plan in time. For patients, due to lack of professionalism, they cannot correctly express oral problems and thus cannot convey effective information to doctors in a timely manner.

[0003] Therefore, it is desirable to provide an orthodontic monitoring method and device so that doctors can promptly intervene in problems that arise after patients receive orthodontic treatment, thereby ensuring that the orthodontic effect develops as expected. Summary of the invention

[0004] One or more embodiments of the present specification provide an orthodontic monitoring method, the method comprising: acquiring a first surface structure and a first surface appearance of a patient's teeth based on scanning; acquiring a current braces model input by a user, and a historical surface structure and a historical surface appearance at the end of a historical orthodontic cycle; determining a structure matching feature based on the first surface structure and the current braces model; determining a structure change feature based on the historical surface structure; determining an appearance change feature based on the historical surface appearance; determining an estimated surface structure based on the first surface structure, the structure matching feature and the structure change feature; determining an estimated surface appearance based on the first surface appearance and the appearance change feature; determining a target surface structure, an end time of a current orthodontic cycle, and braces parameters for the next orthodontic cycle based on the estimated surface structure, the estimated surface appearance and the current braces model.

[0005] One or more embodiments of the present specification provide an orthodontic monitoring device, the device comprising: a scanning module, including a first scanning module, a second scanning module and a third scanning module, wherein: the first scanning module is configured to perform a first scan to obtain a first surface structure; the second scanning module is configured to perform a second scan to obtain a first surface appearance; the third scanning module is configured to perform a third scan to obtain a first deep structure; an input module is configured to obtain a braces model input by a user, a historical surface structure and a historical surface appearance at the end of a historical orthodontic cycle; a processing module is configured to: determine based on the first surface structure and the current braces model, Structural matching features; determining structural change features based on historical surface structures; determining appearance change features based on historical surface appearances; determining an estimated surface structure based on the first surface structure, structural matching features and structural change features; determining an estimated surface appearance based on the first surface appearance and appearance change features; determining a target surface structure, an end time of a current orthodontic cycle and braces parameters for a next orthodontic cycle based on the estimated surface structure, the estimated surface appearance and the current braces model; a display module configured to display the braces model, target surface structure, an end time of a current orthodontic cycle and braces parameters for a next orthodontic cycle input by a user.

[0006] One or more embodiments of the present specification provide an orthodontic monitoring system, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to implement the above-mentioned orthodontic monitoring method.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned orthodontic monitoring method. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is an exemplary structural diagram of an orthodontic monitoring device according to some embodiments of the present specification;

[0010] Figure 2 is an exemplary flow chart of an orthodontic monitoring method according to some embodiments of the present specification;

[0011] Figure 3 is an exemplary schematic diagram of determining an estimated surface structure according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart of correcting a target surface structure according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 is an exemplary structural diagram of an orthodontic monitoring device 100 according to some embodiments of the present specification.

[0018] like Figure 1 As shown, the orthodontic monitoring device 100 may include a scanning module 110, an input module 120, a processing module 130, and a display module 140. In some embodiments, the scanning module 110 may include a first scanning module 111, a second scanning module 112, and a third scanning module 113.

[0019] The scanning module 110 is a device for performing three-dimensional scanning and imaging of teeth and their surrounding structures.

[0020] In some embodiments, the first scanning module 111 is configured to perform a first scan to obtain a first surface structure. In some embodiments, the first scanning module 111 may include an optical scanner, an intraoral scanner, and the like.

[0021] In some embodiments, the second scanning module 112 is configured to perform a second scan to obtain the first surface appearance. In some embodiments, the second scanning module 112 may include color scanning, multi-spectral imaging, high-definition photography, etc.

[0022] In some embodiments, the third scanning module 113 is configured to perform a third scan to acquire the first deep structure. In some embodiments, the third scanning module 113 may include cone beam computed tomography (CBCT), ultrasound imaging, and the like.

[0023] The input module 120 is a device for receiving various information and data provided by the user. In some embodiments, the input module 120 is configured to obtain the braces model input by the user, the historical surface structure at the end of the historical orthodontic cycle, and the historical surface appearance. In some embodiments, the input module may include components such as a graphical user interface, a physical input device, and automatic data import. In some embodiments, the input module 120 can be directly connected to the scanning module 110 to automatically obtain the latest scan data.

[0024] The processing module 130 is a device for analyzing and processing the acquired data. In some embodiments, the processing module 130 can be connected to the scanning module 110 or the input module 120 .

[0025] In some embodiments, the processing module 130 is configured to: determine the structural matching features by comparing the first surface structure obtained by scanning and the current braces model input by the user; determine the structural change features based on the historical surface structure; determine the appearance change features based on the historical surface appearance; determine the estimated surface structure based on the first surface structure, the structural matching features and the structural change features; determine the estimated surface appearance based on the first surface appearance and the appearance change features; determine the target surface structure, the end time of the current orthodontic cycle and the braces parameters of the next orthodontic cycle based on the estimated surface structure, the estimated surface appearance and the current braces model.

[0026] In some embodiments, the processing module 130 may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), and the like.

[0027] The display module 140 is a device for presenting information and data related to orthodontic treatment to the user or doctor in an intuitive manner. In some embodiments, the display module 140 can be connected to the processing module 130. In some embodiments, the display module 140 is configured to display the current braces model input by the user, and can also display the target surface structure predicted by the processing module 130, the end time of the current orthodontic cycle, and the braces parameters of the next orthodontic cycle generated by the processing module 130. In some embodiments, the display module 140 can be implemented based on a display device such as a display screen.

[0028] In some embodiments of the present specification, a high-precision three-dimensional model can be generated through a multi-dimensional scanning module. The user's historical data and current braces model are obtained through the input module to ensure personalized customization of the treatment plan to meet the specific needs of different patients. Through the comprehensive analysis and prediction of the processing module, the efficiency and accuracy of the treatment process are ensured, and the braces parameters for the next orthodontic cycle are automatically generated. Through the display module, patients can clearly understand the progress and expected results of the treatment, and enhance their trust and sense of participation in the treatment process.

[0029] Figure 2 is an exemplary flow chart of an orthodontic monitoring method according to some embodiments of the present specification.

[0030] In some embodiments, the orthodontic monitoring method includes: obtaining a first surface structure and a first surface appearance of the patient's teeth based on scanning; obtaining a current braces model input by a user, a historical surface structure at the end of a historical orthodontic cycle, and a historical surface appearance; determining a structural matching feature based on the first surface structure and the current braces model; determining a structural change feature based on the historical surface structure; determining an appearance change feature based on the historical surface appearance; determining an estimated surface structure based on the first surface structure, the structural matching feature, and the structural change feature; determining an estimated surface appearance based on the first surface appearance and the appearance change feature; determining a target surface structure, an end time of the current orthodontic cycle, and braces parameters for the next orthodontic cycle based on the estimated surface structure, the estimated surface appearance, and the current braces model.

[0031] like Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by a processing module.

[0032] Step 210: Acquire a first surface structure and a first surface appearance of the patient's teeth based on the scan.

[0033] The first surface structure may reflect the current surface structure of the tooth. The surface structure refers to a structure that reflects the surface condition of the tooth. For example, the surface structure of the tooth may include the arrangement, size, shape, position, angle, etc. of the tooth.

[0034] In some embodiments, the first surface structure can be represented in a variety of forms, such as a 3D model, a digital sequence, etc. The 3D model can represent the first surface structure in the form of a 3D model diagram. The digital sequence can represent the conditions of each structure in the form of specific numerical values.

[0035] In some embodiments, the first surface structure can be obtained based on 3D scanning, for example, by scanning the oral cavity using an intraoral laser scanner (iTero scanner).

[0036] The first surface appearance may reflect the current surface appearance of the tooth. The surface appearance refers to the appearance reflecting the health status of the tooth. For example, the surface appearance may include the number, area or size of caries, black triangles, tartar, etc.

[0037] The first surface appearance may adopt the same representation form as the first surface structure.

[0038] In some embodiments, the first surface appearance can be obtained by image capture, for example, by ordinary capture using a micro camera.

[0039] Step 220, obtaining the current braces model, the historical surface structure at the end of the historical orthodontic cycle, and the historical surface appearance input by the user.

[0040] In some embodiments, the user may be a doctor or other person performing orthodontic operations. The user may input corresponding data to the processing module through the input module.

[0041] The current braces model refers to the 3D model of the braces currently worn by the patient.

[0042] The orthodontic process can generally be divided into multiple stages. Different stages can correspond to orthodontic cycles of different lengths. The braces models corresponding to different orthodontic cycles or different stages can be different to achieve the desired orthodontic effect. The historical orthodontic cycle refers to the orthodontic cycle that the patient has currently experienced.

[0043] The orthodontic process generally includes the alignment and leveling stage, the gap closing stage, the fine adjustment stage and the maintenance stage. The alignment and leveling stage is used to align the teeth. During this stage, the tooth structure changes greatly, and the adjustment cycle of braces is shorter. For example, half a month is an orthodontic cycle. The gap closing stage mainly adjusts the molar relationship, the inward retraction of the front teeth, and the front and back position relationship of the gap teeth. The orthodontic cycle of this stage can be three weeks. The fine adjustment stage is used to finely adjust the tooth cusp relationship in a small range to make the tooth occlusion relationship tighter and improve the chewing efficiency. The orthodontic cycle of this stage can be one or two months. The maintenance stage is used to stabilize the teeth after the braces are removed to prevent rebound. This stage generally lasts 2-3 years.

[0044] The historical surface structure includes surface structures corresponding to the end of multiple historical orthodontic cycles.

[0045] The historical surface appearance includes surface appearances corresponding to the end of multiple historical orthodontic cycles.

[0046] The historical surface structure and the historical surface appearance can be represented in a sequence form, where one element corresponds to the surface structure and the surface appearance at the end of a historical orthodontic cycle, and adjacent elements represent the corresponding surface structure and the surface appearance at the end of adjacent cycles; each element can be represented in a 3D model or a digital sequence. The historical surface structure and the historical surface appearance can be obtained by the input module by searching the historical data from the storage module.

[0047] Step 230 : determining a structural matching feature based on the first surface structure and the current braces model.

[0048] The structural matching feature refers to the feature of the structural matching between the tooth and the brace. In some embodiments, the structural matching feature can be characterized based on a sequence or matrix form.

[0049] In some embodiments, the processing module can obtain the actual position, actual size, actual angle of each tooth and the difference between the braces position, braces size, and braces angle of the corresponding tooth in the current braces model by comparing the first surface structure with the current braces model, and integrate the differences of all teeth (such as position differences, size differences, angle differences, etc.), for example, representing them in the form of a sequence or matrix to obtain structural matching features.

[0050] There may be some differences between the shape settings of the corresponding teeth in the current braces model and the actual teeth. This is to apply appropriate force so that the teeth can gradually move to the target position under the action of the braces to achieve the purpose of orthodontics.

[0051] The position difference can be expressed as a coordinate difference in a 3D virtual coordinate system.

[0052] Size differences include width differences, length differences, height differences, tooth external surface area differences, and tooth volume differences.

[0053] The angle difference may be an angle difference value in a normal direction of the outer surface of the tooth.

[0054] Step 240, determining structural change characteristics based on the historical surface structure.

[0055] The structural change feature refers to the feature of the tooth structure change in the adjacent orthodontic cycle. The structural change feature may include the historical structural change feature and / or the current structural change feature. The current structural change feature may characterize the morphological change rate of each tooth corresponding to the current orthodontic cycle, wherein the morphological change rate includes the average change rate of the tooth position, the average change rate of the size, and the average change rate of the direction.

[0056] In some embodiments, the processing module can compare the differences in the actual position, actual size and actual direction of each tooth at the end of adjacent historical orthodontic cycles in the historical surface structure, and combine the duration corresponding to the latter orthodontic cycle in the adjacent historical orthodontic cycle to determine the morphological change rate of each tooth in each historical orthodontic cycle as a historical structural change feature.

[0057] In some embodiments, the processing module performs fitting regression based on the historical structural change characteristics corresponding to multiple historical orthodontic cycles to determine the current structural change characteristics corresponding to the current orthodontic cycle. In some embodiments, the fitting regression includes least squares method, gradient descent method, etc.

[0058] Step 250 , based on the historical surface appearance, determine the appearance change characteristics.

[0059] Appearance change characteristics refer to the characteristics of the appearance changes of teeth in adjacent orthodontic cycles. Appearance change characteristics may include historical appearance change characteristics and / or current appearance change characteristics. Current appearance change characteristics may characterize the appearance change rate of each tooth corresponding to the current orthodontic cycle, wherein the appearance change rate includes the average change rate of caries, the average change rate of black triangles, and the average change rate of tartar.

[0060] The average rate of change of dental caries may include the average rate of change of the number of dental caries, the average rate of change of the number of dental caries black spots, and the average rate of change of the area of ​​dental caries black spots. In some embodiments, the average rate of change of dental caries may be determined by comparing the changes in the number of dental caries, the number of dental caries black spots, and the area of ​​dental caries black spots in adjacent orthodontic cycles, combined with the duration corresponding to the next orthodontic cycle in adjacent historical orthodontic cycles.

[0061] The average change rate of black triangles may include the average change rate of the number of black triangles and the average change rate of the area; the average change rate of dental calculus may include the average change rate of the number of dental calculus and the average change rate of the area. The determination method of the average change rate of black triangles and the average change rate of dental calculus is the same as the average change rate of caries.

[0062] In some embodiments, the processing module may determine the current appearance change feature based on the fitting of multiple historical appearance change features. The principle thereof is described in the determination of the current structure change feature.

[0063] Step 260, determining an estimated surface structure based on the first surface structure, the structure matching feature and the structure change feature.

[0064] The estimated surface structure refers to the surface structure of the tooth at an estimated future time point. The future time point can be preset.

[0065] In some embodiments, the estimated surface structures at multiple future time points may be constructed into an estimated surface structure sequence.

[0066] In some embodiments, the processing module can determine the estimated surface structure corresponding to the first surface structure, structural matching characteristics and structural change characteristics based on a query comparison table. The comparison table is tabular data prepared in advance based on historical orthodontic data, including estimated surface structures corresponding to different first surface structures, structural matching characteristics and structural change characteristics in different orthodontic cycles.

[0067] Step 270 , determining an estimated surface appearance based on the first surface appearance and the appearance change characteristics.

[0068] The estimated surface appearance refers to the surface appearance of the tooth at an estimated future point in time.

[0069] In some embodiments, the estimated surface appearances at multiple future time points may be constructed into an estimated surface appearance sequence.

[0070] In some embodiments, the processing module may determine the estimated surface appearance based on the first surface appearance and the appearance change characteristics in a variety of ways. For example, the processing module may first determine the time interval (such as the number of days) from the current time to the future time point, and then determine the estimated surface appearance based on the time interval, the appearance change characteristics and the first surface appearance.

[0071] For example, the estimated surface appearance = the first surface appearance + the number of days between intervals * the current appearance change feature. For example, the estimated number of caries in the surface appearance = the number of caries in the first surface appearance + the number of days between intervals * the average change rate of the number of caries in the current appearance change feature.

[0072] Step 280, based on the estimated surface structure, the estimated surface appearance and the current brace model, determine the target surface structure, the end time of the current orthodontic cycle and the brace parameters of the next orthodontic cycle.

[0073] The target surface structure refers to the expected surface structure that the tooth can achieve during the current orthodontic cycle.

[0074] In some embodiments, the processing module may determine a target surface structure based on the estimated surface structure, the estimated surface appearance, and the current brace model.

[0075] The end time of the current orthodontic cycle refers to the earliest time when the surface structure of the teeth in the current orthodontic cycle reaches or is closest to the target surface structure.

[0076] In some embodiments, the processing module compares each estimated surface structure in the estimated surface structure sequence with the current braces model, determines the estimated matching features between the two, compares the estimated matching features with the preset matching features, determines one or more estimated matching features whose difference with the preset matching features is less than a first threshold, and obtains the corresponding one or more time points as candidate time points.

[0077] The estimated matching feature refers to the structural matching feature obtained by comparing the estimated surface structure with the current braces model.

[0078] The preset matching feature refers to the ideal structural matching feature between the surface structure of the tooth and the current brace model at the end of the preset current orthodontic cycle. In some embodiments, the preset matching feature can be preset by the doctor based on the orthodontic goal.

[0079] The first threshold refers to the difference between the estimated matching feature and the preset matching feature, such as a maximum value. In some embodiments, the first threshold can be set by a doctor based on experience.

[0080] In some embodiments, the processing module obtains the estimated surface appearance corresponding to the candidate time point from the estimated surface appearance sequence, compares the retrieved estimated surface appearance with the preset surface appearance, determines multiple estimated surface appearances whose differences are less than a second threshold, obtains the corresponding multiple time points, and selects the time point closest to the current time as the end time of the current orthodontic cycle.

[0081] The preset surface appearance refers to the surface appearance that the teeth are expected to achieve at the end of the current orthodontic cycle.

[0082] The second threshold refers to the maximum difference between the estimated surface appearance and the preset surface appearance. In some embodiments, the second threshold can be set by a doctor based on experience.

[0083] In some embodiments, the processing module may use the estimated surface structure corresponding to the end time of the current orthodontic cycle as the target surface structure.

[0084] The braces parameters for the next orthodontic cycle refer to the parameters of the braces model that need to be set for the next orthodontic cycle, for example, the position, size, angle, etc. of each tooth in the braces model. The braces parameters for the next orthodontic cycle can be represented in the form of a 3D model or a digital sequence.

[0085] In some embodiments, the processing module can determine the braces parameters for the next orthodontic cycle according to a preset database based on the estimated surface structure, the estimated surface appearance and the current braces model.

[0086] The preset database refers to a preset database that records the surface structure and surface appearance of teeth and the corresponding relationship between the current braces model and braces parameters. In some embodiments, the preset database can be constructed based on historical orthodontic data with good orthodontic effects. The historical orthodontic data includes the surface structure of teeth that have undergone orthodontics at the second time point of the first orthodontic cycle, the surface appearance at the second time point, and the braces model at the first time point and the braces parameters corresponding to the second orthodontic cycle. The first orthodontic cycle is before the second orthodontic cycle, and the first time point is before the second time point.

[0087] According to some embodiments of the present specification, the orthodontic effect that can be achieved during an orthodontic cycle, the end time of the current orthodontic cycle, and the braces parameters that need to be set for the next orthodontic cycle can be determined according to the changes in tooth structure and appearance during the wearing of braces. The braces parameters can be adaptively adjusted according to the orthodontic situation during the orthodontic process, making the orthodontic process more efficient and the estimated orthodontic effect more accurate.

[0088] Figure 3 is an exemplary schematic diagram of determining an estimated surface structure according to some embodiments of this specification. Figure 3 As shown, the process of determining the estimated surface structure includes the following: In some embodiments, the process of determining the estimated surface structure can be performed by a scanning module and a processing module.

[0089] In some embodiments, the processing module determines the estimated surface structure may include: obtaining a first deep structure of the patient's teeth based on a scan; determining the patient's occlusal features based on the first surface structure and the first deep structure; and determining the estimated surface structure based on the first surface structure, structure matching features, structure change features, and the patient's occlusal features.

[0090] In some embodiments, the processing module may obtain the first deep structure 311 of the patient's tooth through a scanning module such as an X-ray scanner.

[0091] In some embodiments, the first deep structure 311 may include the position, shape, etc. of structures such as tooth roots, alveolar bones, and periodontal membranes.

[0092] For a description of the first surface structure 312, see Figure 2 and its related description.

[0093] The patient's occlusal features 313 refer to features related to the contact relationship between the upper and lower teeth when they are closed. In some embodiments, the patient's occlusal features 313 may include an occlusal plane, an occlusal point, an occlusal force distribution, an occlusal type, etc. Among them, the occlusal plane refers to the plane formed by the upper and lower teeth when they are closed; the occlusal point refers to the specific contact point between the upper and lower teeth when they are closed; the occlusal force distribution refers to the distribution of pressure on each tooth when biting; the occlusal type may include an overbite, an open bite, an underbite (i.e., an overbite), a locked bite, etc.

[0094] In some embodiments, the processing module may determine the patient's occlusal features 313 in a variety of ways based on the first surface structure 312 and the first deep structure 311 .

[0095] In some embodiments, the processing module may load the first surface structure 312 and the first deep structure 311 into a virtual 3D human head model, perform a bite action, and automatically identify the trained system to determine the corresponding patient bite feature 313. The trained system refers to an intelligent system trained by machine learning or deep learning algorithms. In some embodiments, the trained system may include a bite feature recognition system based on a convolutional neural network (CNN), a bite action simulation system based on a recurrent neural network (RNN), a bite feature classification system based on a support vector machine (SVM), etc.

[0096] In some embodiments, the processing module can establish a three-dimensional model of the patient's teeth and jaws through the three-dimensional data obtained by the scanning module, and simulate the patient's bite process through computer simulation technology to determine the patient's bite characteristics 313. In some embodiments, the doctor can use a special bite force sensor to directly measure the patient's bite force distribution, record the patient's bite contact points, generate a detailed bite map, and determine the patient's bite characteristics 313.

[0097] In some embodiments, the processing module may determine the estimated surface structure 330 in a variety of ways based on the first surface structure 312 , the structure matching feature 314 , the structure change feature 315 , and the patient's occlusal feature 313 .

[0098] In some embodiments, the processing module can determine the estimated surface structure 330 based on the first surface structure 312, the structure matching feature 314, the structure change feature 315 and the patient's occlusal feature 313 through the first estimated model 320. For a description of the structure matching feature 314, the structure change feature 315 and the estimated surface structure 330, see Figure 2 and its related description.

[0099] The first estimation model 320 is a model for predicting the estimated surface structure of the patient's teeth. In some embodiments, the first estimation model 320 can be a machine learning model, such as a three-dimensional convolutional neural network (3D Convolutional Neural Networks, 3D-CNN) and the like.

[0100] In some embodiments, the input of the first estimated model 320 may include a first surface structure 312 , a structure matching feature 314 , a structure change feature 315 , and a patient occlusal feature 313 , and the output may be an estimated surface structure 330 of the patient's teeth.

[0101] In some embodiments, the input of the first estimation model may further include a tooth loosening feature. The processing module may determine the tooth loosening feature based on the first surface structure and the first surface appearance.

[0102] In some embodiments, the tooth looseness feature may include the degree of looseness of each tooth. In some embodiments, the processing module may determine the degree of looseness of each tooth in a variety of ways based on the first surface structure and the first surface appearance.

[0103] Taking the tooth whose looseness needs to be determined as the target tooth as an example, the processing module can determine the looseness of the target tooth based on the following method.

[0104] The processing module can determine the deviation of the central axis of the target tooth from the standard direction based on the first surface structure; determine the interval distance between the target tooth and the adjacent teeth based on the first surface structure, and if the target tooth has two adjacent teeth on the left and right, take the average of the interval distances on the left and right sides as the interval distance; determine the tartar degree of the target tooth and the black triangle degree between the adjacent teeth based on the first surface appearance; then, the processing module can perform weighted averaging based on the above-mentioned deviation, interval distance, tartar degree and black triangle degree to obtain the looseness degree of the target tooth.

[0105] The central axis refers to the connecting line between the midpoints of the horizontal line above the tooth and the horizontal line below the tooth. The standard direction can be preset by the doctor, and each tooth in each position has its own corresponding standard direction. The degree of tartar can be determined based on the area and size of the tartar by searching the first preset table for degree judgment. The first preset table pre-sets the tartar degree corresponding to different tartar areas and sizes.

[0106] The method for determining the black triangle degree is similar to the method for determining the tartar degree, which will not be repeated here. If the target tooth has two adjacent teeth on the left and right, the processing module can average the tartar degree and the black triangle degree of the teeth on the left and right sides respectively as the tartar degree of the target tooth and the black triangle degree between the adjacent teeth.

[0107] In some embodiments, the looseness of the target tooth can be determined based on the above-mentioned deviation, spacing distance, tartar degree and black triangle degree by formula (1):

[0108] Among them, T is the looseness of the target tooth, A is the deviation of the central axis of the target tooth from the standard direction, B is the distance between the target tooth and the adjacent tooth, C is the tartar degree of the target tooth, D is the black triangle degree between the target tooth and the adjacent tooth, and k1, k2, k3, and k4 are all weight coefficients. The weight coefficient can be set according to experience.

[0109] The processing module can determine the degree of looseness of each tooth based on the above method, and then obtain the tooth looseness feature. For example, the tooth looseness feature can be represented based on a sequence, with one element corresponding to the degree of looseness of one tooth. The processing module can use the tooth looseness feature as the input of the first estimation model.

[0110] In some embodiments of the present specification, by determining the loose tooth characteristics, more information about tooth stability is provided to the doctor, and potential problems can be discovered in advance before or during treatment, such as the possibility of loosening or shifting of certain teeth, helping the doctor to better evaluate the safety and effectiveness of orthodontic treatment plans. At the same time, using the loose tooth characteristics as the input of the first prediction model also improves the accuracy of predicting the surface structure of the patient's teeth.

[0111] In some embodiments, the input of the first prediction model may further include a tooth usage feature. The processing module may determine the tooth usage feature based on the first surface structure, the first surface appearance, and the patient information.

[0112] Patient information refers to relevant information provided by the patient. In some embodiments, the patient information may include basic patient information, medical history, oral health status, lifestyle, etc. Among them, the basic patient information may include gender, age, etc. Medical history may include previous medical history, allergy history, orthodontic treatment history, etc. Oral health status may include periodontal health, caries status, oral hygiene habits, etc. Lifestyle may include eating habits, whether smoking or drinking, oral cleaning habits, etc., such as the patient's brushing frequency and single brushing duration.

[0113] In some embodiments, patient information may be determined via patient input.

[0114] The tooth usage characteristics refer to the specific usage of the patient's teeth in daily life. In some embodiments, the tooth usage characteristics may include the frequency of tooth usage, dietary characteristics, and cleaning characteristics. Among them, the tooth usage frequency may include the frequency of use of each tooth. Dietary characteristics may include the patient's preference for hard food, corrosive food (cola, candy, etc.). Cleaning characteristics may include the degree of cleaning effectiveness, the degree of cleaning negativity, etc. Among them, the degree of cleaning negativity may include the degree to which the patient's habit of brushing horizontally causes wedge-shaped defects, etc.

[0115] In some embodiments, the processing module can determine the tooth usage characteristics in a variety of ways based on the first surface structure, the first surface appearance, and the patient information.

[0116] In some embodiments, for each tooth, the processing module can determine the degree of tooth wear based on the first surface structure through an image recognition algorithm; and determine the frequency of tooth use based on the degree of tooth wear. The degree of tooth wear can be determined by identifying pits, debris, etc. on the enamel surface. The frequency of tooth use is positively correlated with the degree of tooth wear.

[0117] In some embodiments, the processing module can determine an average wear degree based on the average wear degree of all teeth; determine a first hard food preference based on the average wear degree; determine a second hard food preference based on the frequency of hard food consumption in the patient information; and determine a hard food preference based on the average of the first hard food preference and the second hard food preference.

[0118] In some embodiments, the processing module can determine the number of caries based on the first surface appearance; determine the first corrosive food preference based on the number of caries; determine the second corrosive food preference based on the frequency of consumption of corrosive foods in the patient information; and determine the corrosive food preference based on the average of the first corrosive food preference and the second corrosive food preference. The number of caries is positively correlated with the first corrosive food preference.

[0119] In some embodiments, the processing module can determine the number of wedge-shaped defects based on the first surface structure; determine the negative degree of cleaning based on the number of wedge-shaped defects. In some embodiments, the processing module can determine the number of black triangles and the number of dental calculus based on the first surface appearance; determine the first cleaning effectiveness based on the number of black triangles and the number of dental calculus; determine the second cleaning effectiveness based on the brushing frequency and the single brushing time; and determine the cleaning effectiveness by weighted average based on the first cleaning effectiveness and the second cleaning effectiveness. Among them, the number of black triangles and the number of dental calculus are negatively correlated with the first cleaning effectiveness.

[0120] In some embodiments, when determining the cleaning effectiveness, the weight coefficient of the first cleaning effectiveness is greater than the weight coefficient of the second cleaning effectiveness. In some embodiments, the second cleaning effectiveness can be determined based on the brushing frequency and the single brushing duration by looking up a second preset table. The second preset table pre-sets the second cleaning effectiveness corresponding to different brushing frequencies and single brushing durations.

[0121] In some embodiments of the present specification, by determining tooth usage characteristics, doctors are provided with more information about the patient's daily tooth usage, so that doctors can better assess the risks of the patient's daily tooth usage and take preventive measures to ensure that the teeth can maintain good function and aesthetics during orthodontic treatment.

[0122] In some embodiments, the first estimation model 320 can be obtained through training based on a first training sample with a first label. In some embodiments, the first training sample can include a sample first surface structure of a sample patient at a first historical time point, a sample structure matching feature, a sample structure change feature, and a sample patient occlusal feature. The first label can be the actual surface structure of the sample patient corresponding to the first training sample at a second historical time point. In some embodiments, the first training sample can also include a sample tooth loosening feature and a sample tooth use feature of the sample patient at the first historical time point.

[0123] In some embodiments, the first training sample and the first label may be obtained based on historical orthodontic data.

[0124] In some embodiments, the processing module can be trained by various methods based on the first training sample and the first label. For example, the processing module can be trained based on the gradient descent method. As an example only, the processing module can input multiple first training samples with first labels into the initial first estimation model, construct a loss function through the first label and the result of the initial first estimation model, and iteratively update the parameters of the initial first estimation model based on the loss function. When the loss function of the initial first estimation model meets the preset conditions, the model training is completed and the trained first estimation model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0125] In some embodiments of the present specification, accurate predictions can be obtained through the first estimation model, which reduces unnecessary adjustments and follow-up visits, shortens the treatment cycle, and reduces the economic and time costs of patients. At the same time, it reduces the discomfort that patients may experience during the treatment process and improves patient satisfaction.

[0126] In some embodiments of the present specification, by acquiring the first deep structure, determining the patient's occlusal characteristics, and combining the first surface structure, structure matching characteristics, and structure change characteristics, the model can more accurately simulate the three-dimensional morphology and internal structure of the teeth, predict the patient's future surface structure of the teeth, and ensure the reliability of the prediction results.

[0127] Figure 4 is an exemplary flow chart of correcting the target surface structure according to some embodiments of this specification. Figure 4 As shown, the process of correcting the target surface structure includes the following contents: In some embodiments, the process of correcting the target surface structure can be executed by an input module and a processing module.

[0128] In some embodiments, the input module can obtain the second surface structure 410 of the patient's teeth before the start of the last orthodontic cycle, the third surface structure after the end of the last orthodontic cycle, and the historical estimated surface structure corresponding to the last orthodontic cycle; the processing module can determine the historical effect distribution 440 based on the second surface structure 410, the third surface structure 420 and the historical estimated surface structure 430, and the historical effect distribution includes the historical orthodontic effects of one or more teeth; and correct the target surface structure based on the historical effect distribution 440, determine the corrected target surface structure 450, and send it to the doctor.

[0129] The second surface structure refers to the surface structure of the patient's teeth before the last orthodontic cycle began. For an explanation of the surface structure, see Figure 2 The corresponding content in step 210.

[0130] The third surface structure refers to the surface structure of the patient's teeth after the previous orthodontic cycle is completed.

[0131] In some embodiments, the second surface structure and the third surface structure can be obtained based on historical orthodontic data or determined by an input module obtaining user input.

[0132] Historical estimated surface structure refers to the estimated surface structure determined during the previous orthodontic cycle. For more information on estimated surface structure, see Figure 2 The relevant description of step 260 in FIG.

[0133] In some embodiments, in response to the processing module performing multiple determinations of the estimated surface structure in the previous orthodontic cycle, the input module can select, from the multiple historical estimated surface structures obtained, the estimated surface structure determined at the time point in the previous orthodontic cycle that belongs to the same process as the current time point in the current orthodontic stage, or the time point closest to the current process. The process of a time point in the orthodontic stage in which it is located can be represented based on the difference between the time point and the start time point of the orthodontic stage in which it is located, such as the current process is the difference between the current time point and the start time point of the current orthodontic stage.

[0134] In some embodiments, the historical effect distribution may include the historical orthodontic effects of each tooth in each historical orthodontic cycle.

[0135] The historical orthodontic effect refers to the orthodontic effect corresponding to each tooth when the historical orthodontic cycle is completed.

[0136] In some embodiments, taking the tooth for which the orthodontic effect needs to be determined as the target tooth as an example, the historical orthodontic effect of a target tooth in a historical orthodontic cycle can be calculated based on the following equation (2):

[0137] Among them, n represents the total number of items of data types contained in the surface structure of the tooth. For example, when the surface structure of the tooth includes the arrangement, size, shape, position, and angle of the tooth, the value of n is 5. i represents the i-th surface structure of the target tooth. Ai represents the corresponding data of the i-th surface structure of the target tooth in the second surface structure. Bi represents the corresponding data of the i-th surface structure of the target tooth in the third surface structure. Ci represents the corresponding data of the i-th surface structure of the target tooth in the historical estimated surface structure. h represents the historical orthodontic effect of the target tooth. Ai, Bi, and Ci can be obtained by the input module.

[0138] In some embodiments, the processing module may correct the target surface structure based on the historical effect distribution.

[0139] In some embodiments, the processing module may determine the product of the historical orthodontic effect of each tooth and the corresponding target surface structure as the corrected target surface structure of each tooth.

[0140] In some embodiments, the processing module may determine the corrected target surface structure through the first estimation model.

[0141] In some embodiments, the processing module can input the historical effect distribution as one of the model inputs into the first estimation model to obtain the estimated surface structure, and use the estimated surface structure closest to the current time point as the corrected target surface structure.

[0142] For more information on the first estimation model, see Figure 3 Related description.

[0143] In some embodiments, the processing module determines the orthodontic difficulty distribution based on the first surface structure and the first deep structure; corrects the target surface structure based on the historical effect distribution and the orthodontic difficulty distribution, and determines the corrected target surface structure.

[0144] The orthodontic difficulty distribution may include the current orthodontic difficulty of each tooth.

[0145] In some embodiments, the processing module may determine the orthodontic difficulty distribution through a second estimation model based on the first surface structure and the first deep structure.

[0146] For more information on the first surface structure and the first deep structure, see Figure 2 and Figure 3 Related description.

[0147] The second estimation model refers to the model used to determine the orthodontic difficulty distribution.

[0148] In some embodiments, the second estimation model may be a three-dimensional machine learning model, such as a three-dimensional convolutional neural network model (3D-CNN) or other trained machine learning models.

[0149] In some embodiments, the input of the second estimation model is the first surface structure and the first deep structure, and the output is the orthodontic difficulty distribution.

[0150] In some embodiments, the second estimation model can be obtained by training a large number of labeled training samples. The training samples include the sample first surface structure and the sample first deep structure of the teeth of the sample patient in a certain orthodontic cycle. The label is the orthodontic difficulty corresponding to the sample first surface structure and the sample first deep structure of the sample patient. The orthodontic difficulty can be determined based on the remaining orthodontic time of the sample patient. For example, the longer the remaining orthodontic time is determined, the greater the orthodontic difficulty.

[0151] In some embodiments, the training samples may be obtained from historical orthodontic data corresponding to historical patients who have completed orthodontic treatment.

[0152] In some embodiments, for more information about the training process of the second estimation model, see Figure 3 Description of the first estimation model in .

[0153] In some embodiments, the processing module may correct the target surface structure based on the historical effect distribution and the orthodontic difficulty distribution.

[0154] In some embodiments, the processing module may sort the plurality of teeth in order of difficulty from low to high based on the orthodontic difficulty distribution determined at the current time point to obtain a first sort.

[0155] In some embodiments, the processing module may sort the plurality of teeth in descending order of effect based on the historical effect distribution determined according to the last orthodontic cycle to obtain a second sorting.

[0156] In some embodiments, the processing module determines a sequence of adjustment coefficients based on the first ranking and the second ranking.

[0157] The adjustment coefficient sequence refers to a sequence of adjustment coefficients used when adjusting the target orthodontic effect to be achieved for each tooth in the current orthodontic cycle. For example, the adjustment coefficient sequence includes the adjustment coefficient of tooth 1, the adjustment coefficient of tooth 2, ..., the adjustment coefficient of tooth n.

[0158] In some embodiments, the adjustment coefficient of each tooth is related to the position relationship of the tooth in the first ranking and the second ranking. For example, if the ranking position of the target tooth in the first ranking is the same as the ranking position in the second ranking, the adjustment coefficient of the target tooth is 1.

[0159] If the target tooth's ranking position in the first sorting is before its ranking position in the second sorting, the adjustment coefficient of the target tooth is greater than 1, and the greater the difference in the ranking positions, the greater the adjustment coefficient, but the adjustment coefficient does not exceed the maximum coefficient value, such as the maximum coefficient value can be 1.5.

[0160] If the target tooth's ranking position in the first sorting is behind its ranking position in the second sorting, the adjustment coefficient of the target tooth is less than 1, and the greater the difference in the ranking positions, the smaller the adjustment coefficient, but the adjustment coefficient is not less than the minimum coefficient value, such as the minimum coefficient value can be 0.5.

[0161] In some embodiments, the processing module can correct the target surface structure based on the adjustment coefficient sequence composed of the adjustment coefficients of each tooth and the historical effect distribution. For example, the processing module can use the product of the historical orthodontic effect of each tooth (such as the historical orthodontic effect closest to the current time point) and its corresponding adjustment coefficient as the adjustment factor, and then determine the product of the adjustment factor and the target surface structure of the corresponding tooth as the corrected target surface structure of each tooth.

[0162] In some embodiments, the processing module may determine the corrected target surface structure through the first estimation model.

[0163] In some embodiments, the processing module may input the adjustment coefficient sequence and the historical effect distribution as part of the model input into the first estimation model to obtain the estimated surface structure and use it as the corrected target surface structure.

[0164] According to some embodiments of the present specification, the target surface structure is adjusted according to data such as the orthodontic difficulty of each tooth and the historical orthodontic effect, so that the determined target surface structure can be made more reasonable to improve the accuracy of the orthodontic plan.

[0165] In some embodiments, the input module corrects the target surface structure based on the historical effect distribution and the orthodontic difficulty distribution, and determines the corrected target surface structure, including: obtaining the second deep structure; the processing module determines the historical difficulty distribution based on the second surface structure and the second deep structure; determines the orthodontic matching degree distribution based on the historical effect distribution and the historical difficulty distribution; corrects the target surface structure based on the orthodontic matching degree distribution, the historical effect distribution and the orthodontic difficulty distribution, and determines the corrected target surface structure.

[0166] For more information on the second surface structure, see Figure 4 Related description.

[0167] The second deep structure refers to the deep structure of the teeth obtained before the start of the previous orthodontic cycle.

[0168] In some embodiments, the second deep structure can be acquired by the input module based on historical orthodontic data.

[0169] The historical difficulty distribution refers to the orthodontic difficulty distribution determined in the previous orthodontic cycle.

[0170] In some embodiments, the processing module may determine the historical difficulty distribution based on the second surface structure and the second deep structure, which is similar to determining the orthodontic difficulty distribution based on the first surface structure and the first deep structure. For details, see the corresponding content above.

[0171] The orthodontic matching distribution refers to the matching degree between the historical orthodontic effect and the historical orthodontic difficulty of each tooth.

[0172] In some embodiments, the orthodontic matching degree distribution of each tooth is related to the position relationship of the tooth in the first sorting and the second sorting. For example, if the sorting position of the target tooth in the first sorting is the same as the sorting position in the second sorting, the orthodontic matching degree distribution of the target tooth is 1.

[0173] If the target tooth's ranking position in the first sorting is before its ranking position in the second sorting, the orthodontic matching degree distribution of the target tooth is greater than 1, and the greater the difference in the ranking positions, the greater the orthodontic matching degree distribution, but the orthodontic matching degree distribution does not exceed the maximum distribution value, such as the maximum distribution value can be 1.5.

[0174] If the target tooth's ranking position in the first sorting is behind its ranking position in the second sorting, the orthodontic matching degree distribution of the target tooth is less than 1, and the greater the difference in the ranking positions, the smaller the orthodontic matching degree distribution, but the orthodontic matching degree distribution is not less than the minimum distribution value, such as the minimum distribution value can be 0.5.

[0175] In some embodiments, the processing module may perform weighted averaging of the orthodontic matching degree distribution and the adjustment coefficient sequence to obtain an updated adjustment coefficient sequence. For example, the weighted sum of the orthodontic matching degree and the adjustment coefficient of each tooth is used as the updated adjustment coefficient of the tooth, and the sequence formed by the updated adjustment coefficients of all teeth is the updated adjustment coefficient sequence.

[0176] In some embodiments, when the orthodontic matching degree and the adjustment coefficient of each tooth are weighted and summed, the weights of the orthodontic matching degree and the adjustment coefficient can be determined based on a preset.

[0177] In some embodiments, the processing module can correct the target surface structure based on the updated adjustment coefficient sequence to obtain a corrected target surface structure. The specific correction method refers to the corresponding content in the previous text. The difference is that in all applications involving adjustment coefficients, the corresponding adjustment coefficients in the updated adjustment coefficient sequence are used.

[0178] According to some embodiments of the present specification, the historical difficulty distribution is determined based on the second surface structure and the second deep structure, and the orthodontic matching degree distribution is determined based on the historical difficulty distribution and the historical effect distribution. The orthodontic matching degree distribution is used to update the adjustment coefficient to make the correction of the target surface structure more accurate.

[0179] In some embodiments, the input module corrects the target surface structure based on the historical effect distribution, and determining the corrected target surface structure includes: obtaining a historical braces model corresponding to the previous orthodontic cycle; determining the historical matching features based on the second surface structure and the historical braces model; determining the estimated effect distribution based on the historical matching features, the historical effect distribution, and the structural matching features; correcting the target surface structure based on the estimated effect distribution to determine the corrected target surface structure.

[0180] Historical braces models refer to the braces models used in the previous orthodontic cycle.

[0181] The historical matching feature refers to the structural matching feature determined at the end of the previous orthodontic cycle. The method of determining the historical matching feature based on the second surface structure and the historical brace model is similar to the method of determining the structural matching feature based on the first surface structure and the current brace model. For details, see Figure 2 Description of step 230 in FIG.

[0182] The estimated effect distribution may include the estimated orthodontic effect achieved by each tooth at the end of the current orthodontic cycle.

[0183] In some embodiments, the processing module may determine an estimated effect distribution through a regression model based on historical matching features, historical effect distribution, and structural matching features.

[0184] A regression model is a model used to fit the data. A regression model can be linear regression, random forest regression, etc.

[0185] In some embodiments, the processing module uses a regression model to determine the mathematical relationship between each item in the historical matching feature (e.g., position, size, angle) and the historical orthodontic effect, and then based on this mathematical relationship and combined with the currently acquired structural matching features, calculates the estimated effect distribution corresponding to the structural matching features.

[0186] In some embodiments, the processing module may correct the target surface structure based on the estimated effect distribution.

[0187] In some embodiments, the processing module may determine the product of the estimated effect distribution of each tooth and the corresponding target surface structure as the corrected target surface structure of each tooth.

[0188] In some embodiments, the processing module may determine the corrected target surface structure through the first estimation model.

[0189] In some embodiments, the processing module can use the estimated effect distribution as one of the model inputs, input it into the first estimation model, obtain the estimated surface structure, and use the estimated surface structure closest to the current time point as the corrected target surface structure.

[0190] For more information on the first estimation model, see Figure 3 Related description.

[0191] According to some embodiments of the present specification, when correcting the target surface structure, the historical matching features of the previous orthodontic cycle are taken into account, that is, the structural matching of the teeth and the braces model of the previous orthodontic cycle is used to determine the estimated effect distribution of the current orthodontic cycle, and then the target surface structure is corrected based on the estimated effect distribution. This can make the updated target surface structure more in line with the changing trend of the tooth structure, and obtain a target surface structure that is more in line with expectations.

[0192] According to some embodiments of the present specification, based on the surface structure before and after the start of the previous orthodontic cycle and the historical estimated surface structure corresponding to a cycle, the historical estimated effect is determined, and then the obtained target surface structure is updated and adjusted based on the historical effect distribution. This can obtain a more accurate target surface structure, and thus more accurately determine the braces parameters for the next cycle.

[0193] It should be noted that the above description of process 400 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 400 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0194] One or more embodiments of the present specification provide an orthodontic monitoring system, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to implement the above-mentioned orthodontic monitoring method.

[0195] One or more embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned orthodontic monitoring method.

[0196] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0197] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0198] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0199] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0200] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0201] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0202] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An orthodontic monitoring method, the method comprising: Acquire a first surface structure and a first surface appearance of the patient's teeth based on the scan; Obtaining the current braces model, the historical surface structure at the end of the historical orthodontic cycle, and the historical surface appearance input by the user; Determining a structural matching feature based on the first surface structure and the current braces model; Based on the historical surface structure, determining structural change characteristics; Based on the historical surface appearance, determining appearance change characteristics; Determining an estimated surface structure based on the first surface structure, the structure matching feature, and the structure change feature; Determining an estimated surface appearance based on the first surface appearance and the appearance change characteristic; Based on the estimated surface structure, the estimated surface appearance and the current braces model, a target surface structure, an end time of a current orthodontic cycle and braces parameters for a next orthodontic cycle are determined.

2. The method according to claim 1, characterized in that: The determining the estimated surface structure based on the first surface structure, the structure matching feature and the structure change feature comprises: Acquire a first deep structure of the patient's tooth based on the scan; determining a patient's occlusal characteristics based on the first surface structure and the first deep structure; The estimated surface structure is determined based on the first surface structure, the structure matching feature, the structure change feature and the patient's occlusal feature.

3. The method according to claim 1, characterized in that The method further comprises: Acquire the second surface structure of the patient's teeth before the start of the last orthodontic cycle, the third surface structure after the end of the last orthodontic cycle, and the historical estimated surface structure corresponding to the last orthodontic cycle; Determine a historical effect distribution based on the second surface structure, the third surface structure and the historical estimated surface structure, wherein the historical effect distribution includes historical orthodontic effects of one or more teeth; The target surface structure is corrected based on the historical effect distribution, and the corrected target surface structure is determined and sent to the doctor.

4. The method according to claim 3, characterized in that The correcting the target surface structure based on the historical effect distribution and determining the corrected target surface structure comprises: Obtain the historical braces model corresponding to the previous orthodontic cycle; determining a historical matching feature based on the second surface structure and the historical braces model; Determining an estimated effect distribution based on the historical matching feature, the historical effect distribution, and the structural matching feature; The target surface structure is corrected based on the estimated effect distribution to determine the corrected target surface structure.

5. An orthodontic monitoring device, comprising: The scanning module includes a first scanning module, a second scanning module and a third scanning module, wherein: A first scanning module is configured to perform a first scan to obtain a first surface structure; A second scanning module is configured to perform a second scan to obtain the first surface appearance; A third scanning module is configured to perform a third scan to obtain the first deep structure; An input module configured to obtain a current brace model, a historical surface structure at the end of a historical orthodontic cycle, and a historical surface appearance input by a user; The processing module is configured as follows: Determining a structural matching feature based on the first surface structure and the current braces model; Based on the historical surface structure, determining structural change characteristics; Based on the historical surface appearance, determining appearance change characteristics; Determining an estimated surface structure based on the first surface structure, the structure matching feature, and the structure change feature; Determining an estimated surface appearance based on the first surface appearance and the appearance change characteristic; Determining a target surface structure, an end time of a current orthodontic cycle, and braces parameters for a next orthodontic cycle based on the estimated surface structure, the estimated surface appearance, and the current braces model; The display module is configured to display the current braces model, the target surface structure, the end time of the current orthodontic cycle, and the braces parameters of the next orthodontic cycle input by the user.

6. The device according to claim 5, characterized in that The processing module is further configured to: determining a patient's occlusal characteristics based on the first surface structure and the first deep structure; The estimated surface structure is determined based on the first surface structure, the structure matching feature, the structure change feature and the patient's occlusal feature.

7. The device according to claim 5, characterized in that The input module is further configured to: Acquire the second surface structure of the patient's teeth before the start of the last orthodontic cycle, the third surface structure after the end of the last orthodontic cycle, and the historical estimated surface structure corresponding to the last orthodontic cycle; The processing module is further configured to: Determine a historical effect distribution based on the second surface structure, the third surface structure and the historical estimated surface structure, wherein the historical effect distribution includes historical orthodontic effects of one or more teeth; The target surface structure is corrected based on the historical effect distribution, and the corrected target surface structure is determined and sent to the doctor.

8. The device according to claim 7, characterized in that The input module is further configured to obtain a historical brace model corresponding to a previous orthodontic cycle; The processing module is further configured to: determining a historical matching feature based on the second surface structure and the historical braces model; Determining an estimated effect distribution based on the historical matching feature, the historical effect distribution, and the structural matching feature; The target surface structure is corrected based on the estimated effect distribution to determine the corrected target surface structure.

9. An orthodontic monitoring system, characterized in that: The system includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least part of the computer instructions to implement the orthodontic monitoring method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the orthodontic monitoring method according to any one of claims 1 to 4.

Images