Method for generating dental crown model and system for generating dental crown model

Abstract

Provided are a method for generating a dental crown model and a system for generating a dental crown model. The method for generating a dental crown model comprises: retrieving preset tooth model data according to a target position of a tooth to be treated, wherein the preset tooth model data comprises a plurality of geometrical features; adjusting a preset tooth model by using a plurality of tooth model parameters to obtain adjusted geometrical features; give scores of the matching degree between the adjusted feature points and a plurality of conditional operations; performing weighted operation on the scores to obtain a false tooth score; if the false tooth score is less than a threshold score, inputting the false tooth score into an artificial intelligence unit for parameter correction to obtain a plurality of new tooth model parameters, and continuing adjustment until the false tooth score is greater than the threshold score; and using a tooth model corresponding to final parameters as a dental crown model of a patient.

Description

Dental crown model generation method and dental crown model generation system Technical Field

[0001] The present invention relates to a technology for generating a dental crown model. More specifically, the present invention relates to an automatic dental crown model generation method using artificial intelligence technology and a dental crown model generation system using the same. Background Art

[0002] Previously, when a dentist performed dental treatment on a patient and discovered a tooth in poor condition, the patient might require root canal therapy. Once these treatments were completed, the next step was typically to create a crown. Traditionally, crown fabrication was a complex and tedious process, often requiring the dentist to take an impression of the patient's tooth and then fabricate the crown based on the impression.

[0003] First, the dentist will conduct a detailed oral examination of the patient's missing teeth. They will then use specialized materials to create a mold of the missing teeth, which will be used to create a crown model. However, during this process, the patient will often need to wear temporary braces for an extended period of time. These temporary braces are usually handcrafted by the dentist and often require considerable time and effort, as the dentist must individually adjust and meticulously carve them according to the patient's specific oral conditions.

[0004] After taking the impression, the dentist will send the model to an external dental laboratory, where a dental technician will create a cast of the crown. This process also takes time, and in some cases, the dentist will need to perform additional subtle sculpting and adjustments based on the model to ensure that the size, shape, and function of the crown perfectly meet the patient's oral anatomy. This is not only a test of skill, but also places high demands on the dental technician's patience and manual dexterity. Furthermore, the patient must wear a temporary denture while the dental technician is working on the crown.

[0005] Furthermore, although crown fabrication technology is relatively mature, the traditional manual fabrication and adjustment process still has certain limitations, such as manual errors during the fabrication process, high time costs, and various inconveniences for patients while waiting. These factors make the crown fabrication process both cumbersome and challenging, and require patients to return for multiple visits, increasing the complexity of the entire treatment process. Therefore, traditional crown fabrication methods are not only time-consuming, but also require high professional skills from dental technicians and require multiple communications and collaborations with external manufacturers, making the entire process extremely cumbersome and inefficient. Summary of the Invention

[0006] An object of a preferred embodiment of the present invention is to provide a method and a system for generating a dental crown model, which can automatically generate a dental crown model after scanning a tooth model of a patient.

[0007] Another object of a preferred embodiment of the present invention is to provide a method and system for generating a dental crown model, for generating a temporary dental crown during dental treatment.

[0008] In view of this, a preferred embodiment of the present invention provides a method for generating a crown model, which includes: providing multiple geometric features based on a three-dimensional tooth image model; retrieving preset tooth model data based on a target position of a tooth to be treated; step A: adjusting the preset tooth model using multiple tooth model parameters to generate a test tooth model, thereby obtaining multiple preset geometric features; step B: generating multiple conditional operations based on a tooth shape curve and the above-mentioned multiple geometric features; step C: performing multiple scores based on the degree of feature matching between the above-mentioned multiple preset geometric features and the above-mentioned multiple conditional operations; step D: performing a weighted operation on the above-mentioned multiple scores with multiple weights to obtain a denture score; if the denture score is less than a threshold score, inputting the denture score into a parameter correction artificial intelligence unit, updating the multiple tooth model parameters, and continuing steps A to D until the denture score is greater than the threshold score; and using the test tooth model corresponding to the final multiple tooth model parameters as a final crown model.

[0009] Another preferred embodiment of the present invention provides a dental crown model generation system comprising a 3D image input device, a conditional operation generation module, a denture artificial intelligence analysis model, a parameter correction artificial intelligence unit, a judgment module, and a model generation unit. The 3D image input device is used to scan a patient's teeth to obtain a 3D dental image model. Based on a target position of a tooth to be treated, the device retrieves preset dental model data and provides multiple geometric features based on the 3D dental image model. The conditional operation generation module generates multiple conditional operations based on a tooth shape curve and the aforementioned multiple geometric features.

[0010] The artificial intelligence analysis model for dentures is configured to perform the following steps: Step A: Using multiple dental model parameters to adjust the preset dental model to generate a test dental model, thereby obtaining multiple preset feature points; Step B: Using the multiple geometric features to generate multiple conditional operations; Step C: Performing multiple scores based on the degree of matching between the multiple preset geometric features and the multiple conditional operations; and Step D: Performing a weighted operation on the multiple scores using multiple weights to obtain a denture score. The parameter correction artificial intelligence unit updates the multiple dental model parameters based on the denture score and feeds the results back to the artificial intelligence analysis model for dentures. The judgment module compares the denture score with a threshold score and, when the denture score is less than the threshold score, outputs the denture score to the parameter correction artificial intelligence unit. The model generation unit is coupled to the judgment module, wherein, when the denture score is greater than the threshold score, a final crown model is generated for the test dental model corresponding to the multiple dental model parameters corresponding to the denture score.

[0011] A preferred embodiment of the present invention proposes a method for generating a crown model. This method utilizes regression analysis and artificial intelligence to automatically adjust parameters, significantly shortening production time and reducing errors and instabilities associated with manual operation. Secondly, the method accurately calculates and automatically optimizes the crown model based on the patient's three-dimensional imaging data and tooth shape curves, eliminating the need for manual carving or multiple adjustments. This ensures the accuracy of the crown model and meets the patient's individual needs. Finally, through weighted calculations and artificial intelligence-based corrections, the optimal crown model is automatically achieved, avoiding oversights in manual operation and improving treatment effectiveness and patient comfort.

[0012] In order to make the above and other objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are provided to enable those skilled in the art to further understand the present invention and are incorporated into and constitute part of the specification of the present invention. The accompanying drawings illustrate exemplary embodiments of the present invention and are used together with the specification to explain the principles of the present invention.

[0014] FIG1 shows a system block diagram of a dental crown model generating system according to a preferred embodiment of the present invention.

[0015] FIG. 2A is a schematic diagram showing a preset tooth model of the upper jaw of a dental crown model generation system according to a preferred embodiment of the present invention.

[0016] FIG. 2B is a schematic diagram showing a preset tooth model of the mandibular tooth of the dental crown model generation system according to a preferred embodiment of the present invention.

[0017] FIG3 is a schematic diagram showing a tooth three-dimensional image model scanned by the three-dimensional image input device 101 in a tooth crown model generation system according to a preferred embodiment of the present invention.

[0018] FIG4 is a schematic diagram showing a preset tooth model 11 extracted by a tooth crown model generation system according to the three-dimensional tooth image model of FIG3 according to a preferred embodiment of the present invention.

[0019] FIG5 is a schematic diagram showing a dental crown model of a patient generated by combining a three-dimensional tooth image model scanned by a three-dimensional image input device 101 with a dental crown model generation system according to a preferred embodiment of the present invention.

[0020] FIG6 is a schematic diagram showing a tooth three-dimensional image model scanned by the three-dimensional image input device 101 in a tooth crown model generation system according to a preferred embodiment of the present invention.

[0021] FIG. 7 is a schematic diagram showing a preset tooth model 46 extracted by a tooth crown model generation system according to the three-dimensional tooth image model of FIG. 6 , according to a preferred embodiment of the present invention.

[0022] FIG8 is a schematic diagram showing a top-view regression curve calculated by the conditional calculation generation module 103 of the dental crown model generation system according to a preferred embodiment of the present invention based on buccal biting feature points of adjacent teeth.

[0023] FIG9 is a schematic diagram showing a top-view regression curve calculated by the conditional calculation generation module 103 of the dental crown model generation system according to the lingual biting feature points of the adjacent teeth in accordance with a preferred embodiment of the present invention.

[0024] FIG. 10 is a schematic diagram showing a top-view regression curve calculated by the conditional calculation generation module 103 of the crown model generation system according to groove feature points of adjacent teeth in accordance with a preferred embodiment of the present invention.

[0025] FIG. 11 is a schematic diagram showing a lateral view regression curve calculated by the conditional calculation generation module 103 of the dental crown model generation system according to buccal biting feature points of adjacent teeth in accordance with a preferred embodiment of the present invention.

[0026] FIG. 12 is a schematic diagram showing a medial view regression curve calculated by the conditional calculation generation module 103 of the dental crown model generation system according to buccal biting feature points of adjacent teeth in accordance with a preferred embodiment of the present invention.

[0027] FIG. 13 is a schematic diagram showing a medial view regression curve calculated by the conditional calculation generation module 103 of the crown model generation system according to the groove feature points of adjacent teeth in a preferred embodiment of the present invention.

[0028] FIG. 14 is a schematic diagram showing a vector inner product calculated by the conditional calculation generation module 103 of the crown model generation system according to the conditions of the anchor tooth in a preferred embodiment of the present invention.

[0029] FIG. 15 is a schematic diagram showing a vector inner product calculated by the conditional calculation generation module 103 of the crown model generation system according to a preferred embodiment of the present invention based on the conditions of the crown position and the adjacent teeth.

[0030] FIG. 16 is a schematic diagram showing operation conditions calculated by the conditional operation generation module 103 of the dental crown model generation system according to the conditions of the dental crown model in a preferred embodiment of the present invention.

[0031] 17 to 20 are schematic diagrams showing patient crown models generated by a crown model generation system according to a preferred embodiment of the present invention.

[0032] FIG21 shows a flowchart of a method for generating a dental crown model according to a preferred embodiment of the present invention.

[0033] Explanation of Symbols: 101: 3D image input device 102: Feature coordinate generation module 103: Conditional operation generation module 104: Denture artificial intelligence analysis model 105: Parameter correction artificial intelligence unit 106: Judgment module 107: Model generation unit 108: 3D printer 11-17, 21-27, 41-47, 31-37: Preset tooth models MIA, DIA: Feature points of the preset tooth model 11 301, 801, 901, 1001, 1101, 1201, 1301: Feature coordinates 501: Parabolic regression equation MBC: Near Buccal bite feature point LBC: Distal buccal bite feature point MLC: Mesial lingual bite feature point DLC: Distal lingual bite feature point MG: Mesial central groove feature point DG: Distal central groove feature point 802: Parabolic regression equation for outer edge in top view 902: Linear regression equation for inner edge in top view 1002: Linear regression equation for inner edge in top view 1102: Parabolic regression equation for upper edge in lateral view 1202: Linear regression equation for upper edge in medial view 1302: Linear regression equation for inner edge in medial view 1402: Abutment Point 1401 on the surface of the tooth: The closest point 1401 to the initial position of the abutment tooth surface point 1402 and the preset tooth model 46 1501: A coordinate of the crown model 46 at the initial position 1502: The coordinate of the point closest to coordinate 1501 1601: The widest coordinate point of the tooth 1602: The longest coordinate point of the tooth S2101-S2112: The process steps of the crown model generation method of a preferred embodiment of the present invention DETAILED DESCRIPTION

[0034] Reference will now be made in detail to exemplary embodiments of the present invention, which are illustrated in the accompanying drawings. Wherever possible, the same reference numerals will be used in the drawings and the description to refer to the same or similar parts. The exemplary embodiments are merely one way to implement the design concepts of the present invention, and the following examples are not intended to limit the present invention.

[0035] Figure 1 illustrates a system block diagram of a dental crown model generation system according to a preferred embodiment of the present invention. Referring to Figure 1 , in this embodiment, the dental crown model generation system includes a 3D image input device 101, a conditional operation generation module—a denture artificial intelligence analysis model 104, a parameter correction artificial intelligence unit 105, a judgment module 106, a model generation unit 107, and a 3D printer 108. In this embodiment, the 3D image input device 101 includes a geometric feature generation module 102, which includes an image judgment artificial intelligence model. Furthermore, the denture artificial intelligence analysis model 104 includes a conditional operation generation module 103.

[0036] Specifically, when a dentist determines that a patient needs denture treatment, generally after completing root canal treatment, tooth extraction treatment, or implantation of tooth roots, the dentist can use the three-dimensional image input device 101 to scan the patient's teeth to obtain a three-dimensional tooth image model, which includes a target position of the tooth to be treated.

[0037] FIG2A is a schematic diagram of a preset tooth model of the upper jaw of a crown model generation system according to a preferred embodiment of the present invention. FIG2B is a schematic diagram of a preset tooth model of the lower jaw of a crown model generation system according to a preferred embodiment of the present invention. Referring to FIG2A and FIG2B , in this embodiment, the seven teeth on the right side of the upper jaw are labeled 11 to 17; the seven teeth on the left side of the upper jaw are labeled 21 to 27; the seven teeth on the right side of the lower jaw are labeled 41 to 47; and the seven teeth on the left side of the upper jaw are labeled 31 to 37. These preset tooth models 11 to 17, 21 to 27, 41 to 47, and 31 to 37 are based on the Dental Demonstration Teeth Model commonly used by dentists as initial models. Furthermore, the tooth numbers are labeled according to the tooth numbering system of the International Dental Federation.

[0038] Figure 3 illustrates a schematic diagram of a three-dimensional tooth image model scanned by a three-dimensional image input device 101 in a dental crown model generation system according to a preferred embodiment of the present invention. Referring to Figure 3 , assume that the patient's three-dimensional tooth image model lacks the tooth labeled 11. In this case, the image judgment artificial intelligence model within the feature coordinate generation module 102 locates the target position 11 of the tooth to be treated from the three-dimensional tooth image model and retrieves the preset tooth model data labeled 11. Figure 4 illustrates a schematic diagram of the preset tooth model 11 retrieved by the dental crown model generation system according to a preferred embodiment of the present invention based on the three-dimensional tooth image model in Figure 3 . Referring to Figure 4 , the left side shows a side view of the preset tooth model 11, and the right side shows a top view of the preset tooth model 11. The labels MIA and DIA indicate the feature points of the preset tooth model 11. Since this location is an incisor, in this embodiment, only two feature points are present: the mesiolabial incisal angle and the distiolabial incisal angle.

[0039] Referring back to Figure 3 , the geometric feature generation module 102 then provides multiple geometric features based on the three-dimensional tooth image model. In this embodiment, feature coordinates 301 are used as an example. In actual implementation, these features may also include edge lines or other geometric features, but the present invention is not limited thereto. These feature coordinates 301 can be automatically searched using an image-based artificial intelligence model. In this embodiment, due to the top view, the feature coordinates 301 are based on, for example, the occlusal protrusions of the teeth. Based on clinical data and experience, these feature coordinates 301 tend to exhibit an arrangement that approximates a parabola. Therefore, in this embodiment, the conditional operation generation module 103 is an automatic analysis model constructed through training and parameter adjustment based on the clinical experience of multiple dentists. This conditional operation generation module 103 performs, for example, a regression analysis based on the feature coordinates 301 in Figure 3 , the preset feature points MIA and DIA of the preset tooth model 11 at the initial position, and the tooth shape curve (a parabola in this embodiment), thereby determining the parabolic regression equation that best corresponds to the feature coordinates.

[0040] After the parabolic regression equation is determined, the denture artificial intelligence analysis model 104 begins operation. Multiple dental model parameters corresponding to the initial preset dental model data, such as rotation parameters, stretching parameters, and translation parameters, are input into the denture artificial intelligence analysis model 104. The denture artificial intelligence analysis model 104 then scores the degree of match between the generated model and the parabolic regression equation based on the input rotation parameters, stretching parameters, translation parameters, and other important dental parameters. In the above embodiment, although only the top view is used to find the parabolic regression equation corresponding to the top view, in actual applications, the corresponding regression equations generated by the characteristic coordinates of the lateral and medial views may also be included. This exemplary example simplifies the above description.

[0041] After the scoring is completed, all scores will be weighted and added to obtain a denture score. This denture score will be sent to the judgment module 106. The judgment module 106 will compare the denture score with the threshold score. When the denture score is less than the threshold score, the denture score will be output to the parameter correction artificial intelligence unit 105. The parameter correction artificial intelligence unit 105 will correct and update multiple dental model parameters based on the input denture score and feed them back to the denture artificial intelligence analysis model. The conditional operation generation module 103 will then find another crown position based on the dental model parameters and generate another parabolic regression equation based on the preset feature points generated again. Through the cyclic operation of the conditional operation generation module 103, the denture artificial intelligence analysis model 104, the judgment module 106 and the parameter correction artificial intelligence unit 105, until the denture score is greater than the threshold score, the judgment module 106 will send the final multiple dental model parameters to the model generation unit 107. The model generation unit 107 will generate a patient crown model based on the test tooth model corresponding to these multiple dental model parameters.

[0042] Figure 5 illustrates a schematic diagram of a patient's crown model generated using a 3D dental image model scanned by a 3D imaging input device 101, in a preferred embodiment of the present invention. Referring to Figure 5 , the tooth model at position 11 shows that the crown size, position, and angle are almost perfectly matched, and the feature points of the patient's crown model generated by the model generation unit 107 nearly overlap with the parabolic regression equation 501. Subsequently, 3D printing is performed with the 3D printer 108, allowing for the timely production of a temporary dental crown suitable for the patient. This allows the patient to complete the temporary dental crown production on the same day.

[0043] The above embodiment takes the incisors as an example, and the incisors have only two feature points, and only one parabolic regression equation is calculated as an example. However, in actual application, only a single condition will not be used. In order to allow those with general knowledge in the relevant technical field to understand the present invention, a more complex example is given below. Figure 6 shows a schematic diagram of a tooth three-dimensional image model scanned by a three-dimensional image input device 101 in a crown model generation system of a preferred embodiment of the present invention. Please refer to Figure 6. In this embodiment, the molar numbered 46 is used as an example. At this time, an image judgment artificial intelligence model inside the feature coordinate generation module 102 locates the target position 46 of the tooth to be treated from the tooth three-dimensional image model, and takes out the preset tooth model data numbered 46.

[0044] FIG7 illustrates a schematic diagram of a preset tooth model 46 extracted from the three-dimensional tooth image model of FIG6 by a dental crown model generation system according to a preferred embodiment of the present invention. Referring to FIG7 , this figure shows a top view of the preset tooth model 46. The top view of the preset tooth model 46 includes six geometric feature points: the mesio-buccal cusp (MBC), the distal-buccal cusp (DBC), the mesio-lingual cusp (MLC), the distal-lingual cusp (DLC), the mesial groove (MG), and the distal groove (DG). These geometric feature points are used to accurately locate the position and shape of each tooth in the tooth model, particularly when creating a digital tooth model, to ensure that the tooth shape is consistent with the patient's occlusion.

[0045] By inputting multiple corresponding dental model parameters, such as rotation parameters, stretch parameters, and translation parameters, from the initial preset dental model data into the artificial intelligence analysis model 104, the conditional calculation generation module 103 within the artificial intelligence analysis model 104 begins operation. Figure 8 illustrates a schematic diagram of a top-view regression curve calculated by the conditional calculation generation module 103 of the dental crown model generation system according to a preferred embodiment of the present invention, based on the buccal bite feature points of adjacent teeth. Referring to Figure 8 , in this embodiment, the feature coordinate generation module 102 determines multiple geometric features based on the three-dimensional dental image model. Feature coordinates 801 are used as an example here. In actual applications, geometric feature parameters such as edge points, edge lines, and crown base coordinates may also be included, as will be explained later. These feature coordinates 801 in this embodiment are automatically searched by the artificial intelligence model for image judgment and are divided into three groups. The first group of feature coordinates 801 is the buccal bite feature points (Buccal cusp). This first group of feature coordinates 801 represents the raised portion of the tooth bite near the cheek. These two remaining premolars and the rear molars have a total of four buccal cusp feature points. Based on clinical data and experience, these buccal cusp feature points tend to follow a parabolic arrangement. Therefore, in this embodiment, the conditional operation generation module 103 performs a regression analysis based on the feature coordinates 801 in FIG8 , the preset feature points MBC and DBC at the initial position of the preset tooth model 46, and the tooth shape curve, to obtain a top-view outer edge parabolic regression equation 802.

[0046] FIG9 illustrates a schematic diagram of a top-view regression curve calculated by the conditional calculation generation module 103 of the crown model generation system according to a preferred embodiment of the present invention based on the lingual cusp feature points of adjacent teeth. Referring to FIG9 , similarly, the second set of feature coordinates 901, namely the lingual cusp feature points, are the raised portion of the tooth cusp near the tongue. These two remaining premolars and the rear molars together comprise four lingual cusp feature points. Based on clinical data and experience, these lingual cusp feature points tend to be arranged in a nearly straight line. Therefore, in this embodiment, the conditional calculation generation module 103 performs a regression analysis based on the feature coordinates 901 in FIG9 , the preset feature points MLC and DLC of the preset tooth model 46 at the initial position, and the tooth shape curve to obtain a top-view inner edge linear regression equation 902.

[0047] FIG10 illustrates a schematic diagram of a top-view regression curve calculated by the conditional calculation generation module 103 of the crown model generation system according to a preferred embodiment of the present invention based on the groove feature points of adjacent teeth. Referring to FIG10 , similarly, the third set of characteristic coordinates 1001 is the groove feature point. This third set of characteristic coordinates 1001 is the groove connection portion near the center of the tooth. These groove feature points, which are formed by the two remaining premolars and the rear molar, total six. Based on clinical data and experience, these groove feature points tend to be arranged in a nearly straight line. Therefore, in this embodiment, the conditional calculation generation module 103 performs a regression analysis based on the characteristic coordinates 1001 in FIG10 , the preset characteristic points MG and DG of the preset tooth model 46 at the initial position, and the tooth shape curve to obtain a top-view internal linear regression equation 1002.

[0048] FIG11 illustrates a schematic diagram of a lateral view regression curve calculated by the conditional calculation generation module 103 of a dental crown model generation system according to a preferred embodiment of the present invention based on the buccal cusp feature points of adjacent teeth. Referring to FIG11 , in this embodiment, the feature coordinates are similarly divided into three groups, as in the aforementioned embodiment. In this embodiment, feature coordinates 1101 are the aforementioned buccal cusp feature points (Buccal cusps). These four buccal cusp feature points are present, consisting of the two remaining premolars and the posterior molars. Based on clinical data and experience, these buccal cusp feature points also tend to approximate a parabola on the lateral side. Therefore, in this embodiment, the conditional calculation generation module 103 performs a regression analysis based on the feature coordinates 1101 in FIG11 , the preset feature points MBC and DBC of the preset tooth model 46 at the initial position, and the tooth shape curve, to obtain a parabolic regression equation 1102 for the upper edge of the lateral view.

[0049] FIG12 is a schematic diagram of a medial view regression curve calculated by the conditional calculation generation module 103 of the crown model generation system according to a preferred embodiment of the present invention based on the lingual cusp feature points of the adjacent teeth. Referring to FIG12 , in this embodiment, the characteristic coordinates 1201 are the aforementioned lingual cusp feature points (i.e., the second set of characteristic coordinates). These four lingual cusp feature points (i.e., the remaining two premolars and the posterior molars) are present. Based on clinical data and experience, the aforementioned lingual cusp feature points (i.e., the lingual cusp) tend to be arranged in a nearly straight line. Therefore, in this embodiment, the conditional calculation generation module 103 performs a regression analysis based on the characteristic coordinates 1201 in FIG12 , the preset feature points MLC and DLC of the preset tooth model 46 at the initial position, and the tooth shape curve to obtain a linear regression equation 1202 for the upper edge of the medial view.

[0050] FIG13 is a schematic diagram showing a medial view regression curve calculated by the conditional operation generation module 103 of the crown model generation system according to a preferred embodiment of the present invention based on the groove feature points of the adjacent teeth. Referring to FIG13 , in this embodiment, the characteristic coordinates 1301 are the aforementioned groove feature points (groove), i.e., the third set of characteristic coordinates. There are a total of 6 groove feature points (groove) from the two remaining premolars and the rear molars. Based on clinical data and experience, the aforementioned groove feature points (groove) tend to be arranged in a nearly straight line. Therefore, in this embodiment, the conditional operation generation module 103 performs a regression analysis operation based on the characteristic coordinates 1301 of FIG13 , the preset feature points MG and DG of the preset tooth model 46 at the initial position, and the tooth shape curve to obtain a medial view internal linear regression equation 1302.

[0051] The above embodiment is mainly for implementing anatomical alignment and axial positioning control. It is mainly to control the shape of the crown so that it conforms to the arrangement rules of natural teeth, including the frontal view (Facial View): ensuring the alignment of the incisaledge and the smoothness of the curve; the occlusal view (Occlusal View): ensuring that the groove and the cusp are in a reasonable position; the lateral profile (Lateral View): ensuring that the overall shape of the crown meets the biomechanical requirements; axial control (Axial Positioning): ensuring that the implantation direction of the crown is correct and does not affect the occlusion of the adjacent teeth and the abutment teeth. Therefore, regression calculation is used to make the characteristic points of the preset tooth model 46 as close to the characteristic curve as possible. However, in addition to the above regression equation, there are many important conditional calculations for the crown that need to be met. For example, abutment coverage and manufacturing compliance are very important conditions. To ensure that the crown can completely cover the abutment tooth, such as a tooth that has been ground down for a crown or an abutment made for an implant, and fit the tooth margin to prevent defects (such as holes or thin areas), the goal is to have the tooth model completely cover the abutment tooth.

[0052] Figure 14 illustrates a schematic diagram of the vector inner product calculated by the conditional calculation generation module 103 of the crown model generation system according to the conditions of the abutment tooth in a preferred embodiment of the present invention. Referring to Figure 14 , in this embodiment, a point 1402 on the surface of the abutment tooth is used as the normal vector N, and a vector D is used as the closest point 1401 between the abutment tooth surface 1402 and the initial position of the preset tooth model 46. The inner product of these two vectors N and D is then performed. As one skilled in the art will appreciate, a positive inner product indicates that vectors N and D are in the same direction; a negative inner product indicates that vectors N and D are in opposite directions. A larger and more positive inner product value indicates a higher similarity between vectors N and D; a smaller and more negative inner product value indicates a lower similarity between vectors N and vector X. Therefore, simply summing up all inner products will yield the anchor tooth coverage and manufacturing suitability scores. As shown in FIG14 , since the initial position of the preset tooth model 46 is not configured on the anchor tooth, the coordinates of the initial position of the preset tooth model 46 will inevitably overlap with the anchor tooth, resulting in negative inner products of the N vector and the D vector for many coordinates. This will have a significant negative impact on the anchor tooth coverage and manufacturing fit scores.

[0053] Next, proximal contact and occlusal thickness regulation are also crucial considerations. This primarily addresses the relationship between the crown and adjacent and opposing teeth, controlling the crown's contact points to meet clinical standards and avoid excessive or inadequate contact gaps. Furthermore, ensuring the crown's occlusal thickness meets structural strength requirements is crucial to avoid excessive weakness or compromised occlusal function.

[0054] Figure 15 illustrates a schematic diagram of the vector inner product calculated by the conditional calculation generation module 103 of the crown model generation system according to a preferred embodiment of the present invention, based on the crown position and adjacent teeth. Referring to Figure 15 , in this embodiment, the goal is to ensure that the crown model is in perfect contact with the adjacent teeth, avoiding excessive distances that create gaps or overlaps with adjacent teeth that could cause collisions. Therefore, this embodiment uses the normal vector N of coordinate 1502, the point closest to coordinate 1501 among all adjacent teeth, to calculate the inner product of the difference vector D between coordinate 1501 and coordinate 1502 and the normal vector N of coordinate 1502. Similarly, because the inner product can be considered the similarity between two vectors, and the two vectors are in opposite directions, the inner product should originally be negative. However, considering the case of overlapping adjacent teeth, proximity without contact should be considered. Therefore, the higher the calculated score, the better (the less negative, the better). Similarly, by summing up the final inner product results, a contiguity and occlusal thickness control score can be obtained.

[0055] Furthermore, symmetry and morphological constraints are also crucial. These ensure that the crown is similar in shape to the contralateral or adjacent teeth, maintaining both aesthetics and functionality. They also limit the deformation of the crown model to meet anatomical, aesthetic, and biomechanical requirements. Maintaining bilateral symmetry of the crown ensures it conforms to the patient's dental arch. This is particularly important for teeth such as incisors, which are particularly important for appearance.

[0056] FIG16 is a schematic diagram showing the calculation conditions calculated by the conditional calculation generation module 103 of the crown model generation system according to the conditions of the crown model in a preferred embodiment of the present invention. Referring to FIG16 , the goal is to limit the width-to-length ratio of the crown model of the maxillary central incisor to greater than 70%. Taking FIG16 as an example, the widest (with the largest X value) and longest (with the largest Y value) coordinate points 1601 and 1602 of the tooth are obtained, and the X value of the coordinate point 1601 and the Y value of the coordinate point 1602 are inserted into the fractional calculation formula. The "symmetry and morphology constraint score" can be obtained. In this embodiment, the larger the symmetry and morphology constraint score, the better.

[0057] After determining the six regression equations 802, 902, 1002, 1102, 1202, and 1302, as well as the other dental model-related conditional operations, the artificial intelligence analysis model 104 will score and weight the model based on the degree of fit between the input rotation parameters, stretch parameters, translation parameters, and other important dental parameters, and the generated regression equations 802, 902, 1002, 1102, 1202, and 1302, to obtain a denture score. This score is then sent to the judgment module 106. The judgment module 106 compares the denture score with a threshold score. If the score is less than the threshold score, the module outputs the score to the parameter correction artificial intelligence unit 105. The parameter correction artificial intelligence unit 105 corrects and updates the various dental model parameters based on the input denture score and feeds this back to the artificial intelligence analysis model. The artificial intelligence analysis model 104, the judgment module 106, and the parameter correction artificial intelligence unit 105 operate in a loop until the denture score exceeds the threshold score. The judgment module 106 then sends the final multiple dental model parameters to the model generation unit 107. The model generation unit 107 then generates a patient crown model based on the test tooth model corresponding to these multiple dental model parameters.

[0058] Figures 17-20 illustrate schematic diagrams of a patient crown model generated by a crown model generation system according to a preferred embodiment of the present invention. Referring to Figure 17 , those skilled in the art will appreciate that, after n cycles of optimization through the artificial intelligence analysis model 104, the judgment module 106, and the parameter correction artificial intelligence unit 105, the feature points MBC and DBC are very close to the aforementioned top-view outer edge parabolic regression equation 802. Similarly, the feature points MLC and DLC, as well as the feature points MG and DG, are also very close to the aforementioned top-view inner edge linear regression equation 902 and top-view inner edge linear regression equation 1002, respectively. Furthermore, Figures 18-20 also show that the feature points of the resulting patient crown model are also very close to the corresponding aforementioned outer view upper edge parabolic regression equation 1102, inner view upper edge linear regression equation 1202, and inner view inner edge linear regression equation 1302.

[0059] Although the regression equations in the above embodiments include a quadratic parabola and a straight line, in actual system operation, a unified quadratic curve is often used for regression approximation to facilitate adjustment. However, as long as the coefficients of the quadratic terms or corresponding terms are sufficiently small, a substantial approximation to a straight line can be achieved. Therefore, the present invention is not limited to the use of quadratic, linear, or higher-order polynomial approximation methods.

[0060] Although the above embodiment uses the feature coordinate generation module 102 and the internal image judgment artificial intelligence model to perform feature point judgment. However, those with ordinary knowledge in the relevant technical field should know that if there is no feature coordinate generation module 102, the dentist can also mark the feature points on the three-dimensional image model of the teeth after scanning. Furthermore, if the feature points judged by the image judgment artificial intelligence model are found to be incorrect after manual inspection, the dentist can also make manual corrections. Therefore, the present invention is not limited to this. Furthermore, although the above embodiment only describes conditional operations such as characteristic curves, inner product operations, and appearance ratio operations, those with ordinary knowledge in the relevant technical field should know that in the field of dentistry and dental crowns, there are still many conditions that can optimize the dental crown model of this case. Even if the above embodiment does not disclose them, in fact, these undisclosed conditional operations can be selectively added or not added to the image judgment artificial intelligence model according to different situations. Therefore, the present invention is not limited to the above embodiment.

[0061] In addition, although the above embodiment takes into account the geometric characteristic coordinates of the patient's crown model when entering the regression operation to generate the regression curve, those with ordinary knowledge in the relevant technical field should know that it is still possible to selectively not include the geometric characteristic coordinates of the crown model, and only rely on the characteristic coordinates of the remaining teeth to generate the regression curve. However, considering that there are two or more teeth that need to be made into crowns, using the geometric characteristic coordinates of two crown models at the same time will produce a dental model that is more in line with the patient. Therefore, the above situation is only a better exemplary example. In actual operation, according to different situations, for example, when there are many remaining teeth and only one tooth needs to be treated, only the geometric characteristic coordinates of the remaining teeth can be used for the regression operation, and the preset geometric characteristic coordinates of the input crown model can be ignored. Therefore, the present invention is not limited to this.

[0062] The above embodiments can be summarized into a method for generating a crown model. FIG21 shows a flow chart of a method for generating a crown model according to a preferred embodiment of the present invention. Referring to FIG21 , the steps of the method for generating a crown model include:

[0063] Step S2101: Start.

[0064] Step S2102: Providing a 3D dental image model, including multiple feature coordinates. As described in the above embodiment, after the patient completes the 3D dental image model scan, a 3D dental image model is obtained. At this point, the target position of the tooth to be treated is located, for example, by an image judgment artificial intelligence unit. Multiple feature coordinates are provided based on the morphology of the surrounding teeth (incisors, canines, premolars, and molars).

[0065] Step S2103: Retrieving a preset tooth model data according to a target position of a tooth to be treated, for example, by using an image judgment artificial intelligence unit to retrieve a preset tooth model corresponding to the position of the tooth to be treated from a built-in tooth model.

[0066] Step S2104: Utilizing multiple dental model parameters, the preset dental model is adjusted to generate a test dental model, thereby obtaining multiple preset geometric features. As in the aforementioned embodiment related to the regression calculation, if the tooth to be treated is an incisor, two feature points will be generated; if the tooth to be treated is a molar, six feature points will be generated. Furthermore, depending on the conditional calculation employed, the extracted geometric features may also vary, such as the use of the nearest point in the aforementioned inner product calculation. Therefore, the present invention is not limited to the aforementioned embodiment.

[0067] Step S2105: Based on a tooth shape curve and the above-mentioned multiple geometric features, multiple conditional operations are obtained. As described in the above embodiment, the operation of the regression equation generally includes the inner side, the outer side, and the top view. Depending on the complexity of the teeth being treated, there will be different numbers of regression equations. For example, there will be two to three regression equations for incisors, and up to six regression equations for molars. Furthermore, the inner product of the vectors calculated by the conditions of the above-mentioned support teeth, the inner product of the vectors calculated by the conditions of the crown position and the adjacent teeth, and the width-to-length ratio of the incisor crown model, etc., all belong to conditional operations.

[0068] Step S2106: The matching degree between the preset geometric features and the conditional operation is evaluated in multiple scores. As in the above embodiment, the evaluation is performed using the artificial intelligence analysis model for the denture.

[0069] Step S2107: The multiple scores are weighted by multiple weights to obtain a denture score. As in the above embodiment, the scores are weighted by the denture artificial intelligence analysis model.

[0070] Step S2108: Determine whether the score reaches a threshold. If the denture score is less than the threshold, proceed to step S2109. If the denture score is greater than the threshold, proceed to step S2110.

[0071] Step S2109: Input the denture score into the parameter correction artificial intelligence unit and update multiple dental model parameters. And return to step S1805 to continue the operation until step S2108 determines that the denture score is greater than the threshold score. Generally speaking, the above-mentioned weighted operation will be given different weights according to the importance of these conditional operations to the dentist or dental technician. For example, if it does not match the support teeth, even if the occlusion-related regression operation score is very high, the final weighted total score will be very low due to the mismatch of the support teeth (because the crown cannot be installed). In this part, after several cycles, the parameter correction artificial intelligence unit can find which dental model parameters can make the score grow significantly and which dental model parameters have less influence. Therefore, in the above-mentioned loop operation, the score will gradually converge.

[0072] Step S2110: Use the test tooth model corresponding to the final multiple dental model parameters as a final crown model. This final crown model is the patient's crown model.

[0073] Step S2111: Use the final crown model to perform a 3D print to produce a temporary crown. This allows the patient to complete the temporary crown production on the same day, further improving treatment efficiency. However, this step can be modified or omitted depending on the situation. For example, if there is a partner manufacturer, the final crown model can be provided to the manufacturer for custom crown production. If an engraving machine is available, customization can be performed immediately after the patient selects the material, directly producing a permanent crown. Therefore, the present invention is not limited to this.

[0074] Step S2112: End.

[0075] In summary, the preferred embodiment of the present invention provides a method for generating a crown model based on a 3D image model, which offers significant advantages over prior art. First, traditional methods require dentists to manually create crown models and rely on individual adjustments to temporary crowns, a tedious and time-consuming process. However, the preferred embodiment of the present invention utilizes regression analysis and artificial intelligence to automatically adjust parameters, significantly shortening production time and reducing errors and instability in manual operation. Second, the preferred embodiment of the present invention accurately calculates and automatically optimizes the crown model based on the patient's 3D image data and tooth shape curves, eliminating the need for manual engraving or multiple adjustments. This ensures the accuracy of the crown model and meets the patient's individual needs. Compared to the tedious process of repeated model adjustments required by traditional methods, this significantly reduces the dentist's burden and the potential for error. Finally, because the generated crown model can be directly printed using a 3D printer, patients can complete temporary crown production on the same day, further improving treatment efficiency. Even with access to an engraving machine, permanent crowns can be directly produced, eliminating the long waiting time and multiple adjustments associated with traditional methods, significantly improving patient comfort and treatment experience. Therefore, the preferred embodiment of the present invention provides a more efficient and precise dental treatment plan.

[0076] The specific embodiments described in the detailed description of the preferred embodiments are merely for the purpose of illustrating the technical content of the present invention and are not intended to limit the present invention to these embodiments. Any modifications and variations made without departing from the spirit of the present invention and the following claims are intended to fall within the scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for generating a dental crown model, comprising: Providing a three-dimensional tooth image model including multiple geometric features; Retrieving a preset tooth model data according to a target position of a tooth to be treated; Step A: Using a plurality of dental model parameters, adjusting the preset dental model to generate a test dental model, thereby obtaining a plurality of preset geometric features; Step B: generating multiple conditional operations based on the multiple geometric features; Step C: performing multiple scoring based on the matching degree between the plurality of preset geometric features and a feature of the plurality of conditional operations; Step D: performing a weighted calculation on the above multiple scores using multiple weights to obtain a denture score; If the denture score is less than a threshold score, input the denture score into a parameter modification artificial intelligence unit to update the plurality of dental model parameters, and continue steps A to D until the denture score is greater than the threshold score; as well as The test tooth model corresponding to the final plurality of dental model parameters is used as a final crown model.

2. The method for generating a dental crown model according to claim 1, wherein: Providing the three-dimensional tooth image model, including the plurality of geometric features, including: Input the three-dimensional tooth image model; Utilizing an image judgment artificial intelligence unit to locate the target position of the tooth to be treated from the three-dimensional tooth image model; and The image judgment artificial intelligence unit is used to determine a plurality of feature coordinates based on at least one remaining tooth adjacent to the target position.

3. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: The plurality of raised positions in the three-dimensional tooth image model are set as a plurality of outer edge feature coordinates; The multiple conditional operations are generated by the multiple geometric features, including: A regression analysis operation is performed on the plurality of outer edge feature coordinates to obtain a plurality of parabola coefficients to generate a top-view outer edge parabola regression equation.

4. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: A plurality of raised positions in the three-dimensional tooth image model are set as a plurality of inner edge feature coordinates; The multiple conditional operations are generated by the multiple geometric features, including: A regression analysis operation is performed on the plurality of inner edge feature coordinates to obtain a plurality of linear coefficients to generate a top-view inner edge linear regression equation.

5. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: A plurality of recessed positions in the three-dimensional tooth image model are set as a plurality of internal feature coordinates; The multiple conditional operations are generated by the multiple geometric features, including: A regression analysis operation is performed on the plurality of internal feature coordinates to obtain a plurality of linear coefficients to generate a top-view internal linear regression equation.

6. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: The plurality of raised positions in the three-dimensional tooth image model are set as a plurality of upper edge feature coordinates; The multiple conditional operations are generated by the multiple geometric features, including: A regression analysis operation is performed on the plurality of upper edge feature coordinates to obtain a plurality of parabolic coefficients to generate a parabolic regression equation of the upper edge of the outer view.

7. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: The plurality of raised positions in the three-dimensional tooth image model are set as a plurality of upper edge feature coordinates; The multiple conditional operations are generated by the multiple geometric features, including: A regression analysis operation is performed on the plurality of upper edge feature coordinates to obtain a plurality of linear coefficients to generate a linear regression equation for the upper edge of the inner view.

8. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: A plurality of recessed positions in the three-dimensional tooth image model are set as a plurality of internal feature coordinates; The multiple conditional operations are generated by the multiple geometric features, including: A regression analysis operation is performed on the plurality of internal feature coordinates to obtain a plurality of linear coefficients to generate an internal linear regression equation of the inner view.

9. The method for generating a dental crown model according to claim 1, wherein: Using the final tooth model corresponding to the multiple dental model parameters as the final crown model further includes: The final crown model is used to generate a temporary crown using a 3D printer.

10. The method for generating a dental crown model according to claim 1, wherein: The multiple dental model parameters include at least: a rotation parameter for determining the angle of the test tooth model relative to a fixed point; a stretching parameter for determining a stretching length of at least one axis of the test tooth model; and A translation parameter is used to determine the position of the test tooth model relative to the fixed point.

11. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: Setting a plurality of characteristic coordinates at a plurality of positions of a tooth in the three-dimensional tooth image model; The multiple conditional operations are generated by the multiple geometric features, including: A plurality of inner product operations are performed on the normal vectors of the plurality of feature coordinates and the vector of the closest point corresponding to the test tooth model.

12. The method for generating a dental crown model according to claim 11, wherein: The matching degree between the plurality of preset geometric features and the features of the plurality of conditional operations is evaluated in a plurality of scores, including: The results of the multiple inner product operations are summed up to serve as a score of the coverage and manufacturing suitability of a table gear.

13. The method for generating a dental crown model according to claim 1, wherein: Provides a 3D tooth image model, including multiple geometric features, including: Setting a plurality of characteristic coordinates at edge positions of adjacent teeth of a tooth in the three-dimensional tooth image model; The multiple conditional operations are generated by the multiple geometric features, including: An inner product operation is performed on the normal vectors of the plurality of feature coordinates and the vector of the closest point corresponding to the test tooth model.

14. The method for generating a dental crown model according to claim 13, wherein: The matching degree between the plurality of preset geometric features and the features of the plurality of conditional operations is evaluated in a plurality of scores, including: The results of the multiple inner product operations are summed up to form an adjacency relationship and occlusal thickness control score.

15. The method for generating a dental crown model according to claim 1, wherein: The multiple conditional operations are generated through the multiple geometric features, including: A ratio operation is performed on the ratio of the height to the width of the test tooth model.

16. The method for generating a dental crown model according to claim 15, wherein: The matching degree between the plurality of preset geometric features and the features of the plurality of conditional operations is evaluated in a plurality of scores, including: The height and width of the test tooth model were deducted by a proportionality constant to obtain a symmetry and morphological constraint score.

17. A tooth crown model generation system comprising: a three-dimensional image input device for scanning teeth to obtain a three-dimensional tooth image model, extracting preset tooth model data according to a target position of the three-dimensional tooth image model, and providing a plurality of geometric features based on the three-dimensional tooth image model; The conditional operation generates a module - a denture artificial intelligence analysis model, which is used to perform: Step A: Using a plurality of dental model parameters, adjusting the preset dental model to generate a test dental model, thereby obtaining a plurality of preset geometric features; Step B: generating multiple conditional operations based on the multiple geometric features; Step C: performing multiple scoring based on the matching degree between the plurality of preset geometric features and a feature of the plurality of conditional operations; Step D: performing a weighted calculation on the above multiple scores using multiple weights to obtain a denture score; a parameter correction artificial intelligence unit, which updates the plurality of dental model parameters according to the denture score and feeds back to the denture artificial intelligence analysis model; a judgment module that compares the denture score with a threshold score and outputs the denture score to the parameter correction artificial intelligence unit when the denture score is less than the threshold score; as well as A model generating unit is coupled to the judgment module, wherein when the denture score is greater than the threshold score, a crown model is generated from the test tooth model corresponding to the plurality of dental model parameters corresponding to the denture score.

18. The dental crown model generation system according to claim 17, wherein: The three-dimensional image input device comprises: A feature coordinate generation module includes an image judgment artificial intelligence model for locating the target position of the tooth to be treated from the three-dimensional tooth image model and determining the multiple feature coordinates based on at least one remaining tooth adjacent to the target position.

19. The dental crown model generation system according to claim 17, wherein: When the artificial intelligence analysis model for dentures sets multiple protrusion positions in the three-dimensional image model of the teeth as multiple outer edge feature coordinates, the conditional operation generation module is used to perform the regression analysis operation on the multiple outer edge feature coordinates to obtain multiple parabolic coefficients to generate a top-view outer edge parabolic regression equation.

20. The dental crown model generation system according to claim 17, wherein: When the image judgment artificial intelligence model sets multiple protrusion positions in the three-dimensional image model of the tooth as multiple inner edge feature coordinates, the conditional operation generation module is used to perform the regression analysis operation on the multiple inner edge feature coordinates to obtain multiple straight line coefficients to generate a top-down view inner edge straight line regression equation.

21. The dental crown model generation system according to claim 17, wherein: When the image judgment artificial intelligence model sets multiple recessed positions in the three-dimensional image model of the tooth as multiple internal feature coordinates, the conditional operation generation module is used to perform the regression analysis operation on the multiple internal feature coordinates to obtain multiple linear coefficients to generate a top-down internal linear regression equation.

22. The dental crown model generation system according to claim 17, wherein: When the image judgment artificial intelligence model sets multiple protrusion positions in the three-dimensional image model of the tooth as multiple upper edge feature coordinates, the conditional operation generation module is used to perform the regression analysis operation on the multiple upper edge feature coordinates to obtain multiple parabolic coefficients to generate a parabolic regression equation for the upper edge of the lateral view.

23. The dental crown model generation system according to claim 17, wherein: When the image judgment artificial intelligence model sets the multiple protrusion positions in the three-dimensional image model of the tooth as multiple upper edge feature coordinates, the conditional operation generation module is used to perform the regression analysis operation on the multiple upper edge feature coordinates to obtain multiple straight line coefficients to generate an upper edge straight line regression equation for the inner view.

24. The dental crown model generation system according to claim 17, wherein: When the image judgment artificial intelligence model sets multiple recessed positions in the three-dimensional image model of the tooth as multiple internal feature coordinates, the conditional operation generation module is used to perform the regression analysis operation on the multiple internal feature coordinates to obtain multiple linear coefficients to generate an internal linear regression equation for the medial view.

25. The dental crown model generation system according to claim 17, wherein: Also includes: A three-dimensional printer is coupled to the model generating unit and generates a temporary crown according to the final crown model.

26. The dental crown model generation system according to claim 17, wherein: The multiple dental model parameters include at least: a rotation parameter for determining the angle of the test tooth model relative to a fixed point; a stretching parameter for determining a stretching length of at least one axis of the test tooth model; and A translation parameter is used to determine the position of the test tooth model relative to the fixed point.

27. The dental crown model generation system according to claim 17, wherein: When the artificial intelligence analysis model of the denture sets multiple feature coordinates for multiple positions of a tooth in the three-dimensional image model of the tooth, The conditional operation generation module is used to generate multiple conditional operations, including: A plurality of inner product operations are performed on the normal vectors of the plurality of feature coordinates and the vector of the closest point corresponding to the test tooth model.

28. The dental crown model generation system according to claim 27, wherein: The artificial intelligence analysis model executes step C, further comprising: The results of the multiple inner product operations are summed up to serve as a score of the coverage and manufacturing suitability of a table gear.

29. The dental crown model generation system according to claim 17, wherein: When the artificial intelligence analysis model of the denture sets multiple feature coordinates for the edge position of the adjacent teeth of a tooth in the three-dimensional image model of the tooth, The conditional operation generation module is used to generate multiple conditional operations, including: A plurality of inner product operations are performed on the normal vectors of the plurality of feature coordinates and the vector of the closest point corresponding to the test tooth model.

30. The dental crown model generation system according to claim 29, wherein: The artificial intelligence analysis model executes step C, further comprising: The results of the multiple inner product operations are summed up to form an adjacency relationship and occlusal thickness control score.

31. The dental crown model generation system according to claim 17, wherein: The conditional operation generation module is used to generate multiple conditional operations, including: A ratio operation is performed on the ratio of the height to the width of the test tooth model.

32. The dental crown model generation system according to claim 31, wherein: The artificial intelligence analysis model executes step C, further comprising: The height and width of the test tooth model were deducted by a proportionality constant to obtain a symmetry and morphological constraint score.

Images