Method for optimizing three-dimensional modeling of oral abutment by using machine learning algorithm

Abstract

The invention relates to the technical field of oral abutment three-dimensional modeling, and discloses a method for optimizing oral abutment three-dimensional modeling by utilizing a machine learning algorithm, which comprises the following steps of: 1, acquiring detection data of an oral cavity of a patient and a three-dimensional size of an implant, and classifying to form a data set; 2, analyzing the crowding degree and occlusal force distribution state of the teeth of the patient, and generating a crowding ratio and a distribution index; 3, analyzing the inclination of anterior teeth of the patient, evaluating the occlusion relationship of the teeth of the patient, and setting a conversion coefficient for converting the three-dimensional size of the implant into the three-dimensional size of the oral abutment; 4, the three-dimensional size of the oral cavity abutment is simulated, an abutment data set is generated, and the personalized adaptation capacity is high; and step 5, constructing an oral cavity three-dimensional model, an implant three-dimensional model and an oral cavity abutment three-dimensional model of the patient, setting a fixed threshold value, evaluating the fitness of the oral cavity abutment three-dimensional model, and outputting optimization suggestions, and the comfort level of optimization modeling is high.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of three-dimensional modeling, in particular to a method for optimizing three-dimensional modeling of an oral abutment by using a machine learning algorithm. BACKGROUND

[0002] An oral abutment is a key component in dental implant restoration that connects the implant and the upper restoration. Its core function is to provide stable support and retention for the restoration, while also restoring the function and aesthetics of the teeth. With the development of digital technology, three-dimensional modeling of oral abutments has gradually become an important tool in the field of implant restoration. This technology is based on patient oral data for accurate design, enabling personalized customization. By CT scanning to obtain a three-dimensional model of the patient's oral cavity, combined with the position, angle and occlusion relationship of the implant, a highly adaptable abutment is designed for the patient's oral structure. This personalized design not only improves the accuracy of the abutment, but also effectively avoids errors caused by reliance on the experience of doctors in traditional methods, helping doctors to make virtual planning and simulation before surgery, by evaluating the adaptability of the abutment, occlusal force distribution and potential complication risks, to optimize the design scheme and reduce the number of intraoperative adjustments and tryouts. This not only shortens the implant restoration period and reduces patient discomfort, but also significantly improves treatment efficiency and ensures that the restoration effect better meets the physiological needs of the patient.

[0003] Currently, traditional three-dimensional modeling optimization methods for oral abutments usually rely on the experience of doctors, are highly subjective, difficult to ensure accuracy, lack personalized adaptation ability, have high customized production costs, and in addition, patients need to try on and repeatedly adjust the shape of the abutment multiple times, resulting in low patient comfort and long implant restoration period. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a method for optimizing three-dimensional modeling of an oral abutment by using a machine learning algorithm, which has the advantages of strong personalized adaptation ability, high optimization modeling comfort, etc., and solves the problems of insufficient personalized adaptation ability of traditional three-dimensional modeling optimization methods for oral abutments and low patient comfort.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a method for optimizing three-dimensional modeling of an oral abutment by using a machine learning algorithm, comprising the following steps:

[0006] Step 1: Connect the CT scanner through the network, obtain the detection data of the patient's oral cavity and the three-dimensional size of the implant, and classify them into an oral data set and an implant data set;

[0007] Step 2: According to the oral data set, analyze the crowding degree and occlusal force distribution state of the patient's teeth, and generate the corresponding crowding ratio Yjb and distribution index Fbz;

[0008] Step three: According to the oral data set, the inclination of the patient's anterior teeth is analyzed, and the occlusal relationship of the patient's teeth is evaluated by combining the crowding ratio Yjb and the distribution index Fbz, and the corresponding conversion coefficient is set to convert the three-dimensional size of the implant into the three-dimensional size of the oral abutment;

[0009] Step four: According to the implant data set and the conversion coefficient, the three-dimensional size of the oral abutment is simulated to generate the corresponding abutment data set Jtsj;

[0010] Step five: According to the oral data set, the implant data set and the abutment data set Jtsj, the three-dimensional model KX of the patient's oral cavity, the three-dimensional model ZX of the implant and the three-dimensional model TX of the oral abutment are constructed, the fixed numerical fitting threshold THY is set, the fitting degree of the three-dimensional model TX of the oral abutment is evaluated, and the corresponding optimization suggestion is output.

[0011] Preferably, in step one, the oral data set includes the dental arch length, the crown width, the anterior tooth angle and the occlusal paper mark area of the patient, wherein the anterior tooth angle includes the angle between the maxillary anterior teeth and the maxillary bone and the angle between the mandibular anterior teeth and the mandibular bone, and the occlusal paper mark contains several contact points, and the mark area is the contact point area.

[0012] Preferably, in step one, the implant data set includes the height, diameter, taper and surface curvature of the implant.

[0013] Preferably, in step two, the calculation process of the crowding ratio Yjb is as follows:

[0014] According to the oral data set, the dental arch length of the patient is marked as gc, and the crown width of all teeth of the patient is marked as {u1, u2, u3,..., un}, u1 to un representing the crown width of the first tooth to the nth tooth;

[0015] ZU=u1+u2+u3+...+un

[0016]

[0017] In the formula, ZU represents the sum of the crown widths of all teeth of the patient.

[0018] Preferably, in step two, the calculation process of the distribution index Fbz is as follows:

[0019] According to the oral data set, the occlusal paper mark area is marked as {y1, y2, y3,..., ym}, y1 to ym representing the area of the first to mth contact points on the occlusal paper;

[0020]

[0021] In the formula, represents the average area of all contact points on the occlusion paper, ye represents the area of the e-th contact point on the occlusion paper, e∈m, represents the distribution index Fbz of the patient's teeth calculated according to the standard deviation formula.

[0022] Preferably, in the third step, the anterior tooth inclination evaluation process is as follows:

[0023] According to the oral data set, the angle between the patient's upper anterior teeth and the maxilla is marked as sj, and the angle between the patient's lower anterior teeth and the mandible is marked as xj.

[0024] If 22°≤ the angle sj between the patient's upper anterior teeth and the maxilla ≤ 28°, it indicates that the inclination of the patient's upper anterior teeth is normal, the conversion coefficient k3 for the implant taper is ≤ 1, and the conversion coefficient k4 for the implant surface curvature is ≤ 1.

[0025] If the angle sj between the patient's upper anterior teeth and the maxilla is < 22°, or the angle sj between the patient's upper anterior teeth and the maxilla is > 28°, it indicates that the inclination of the patient's upper anterior teeth is abnormal, the conversion coefficient k3 for the implant taper is > 1, and the conversion coefficient k4 for the implant surface curvature is > 1.

[0026] If 25°≤ the angle xj between the patient's lower anterior teeth and the mandible ≤ 35°, it indicates that the inclination of the patient's lower anterior teeth is normal, the conversion coefficient k3 for the implant taper is ≤ 1, and the conversion coefficient k4 for the implant surface curvature is ≤ 1.

[0027] If the angle xj between the patient's lower anterior teeth and the mandible is < 25°, or the angle xj between the patient's lower anterior teeth and the mandible is > 35°, it indicates that the inclination of the patient's upper anterior teeth is abnormal, the conversion coefficient k3 for the implant taper is > 1, and the conversion coefficient k4 for the implant surface curvature is > 1.

[0028] Preferably, in the third step, the occlusion relationship evaluation process is as follows:

[0029] If the crowding ratio Yjb > 1, it indicates that the patient has a tooth crowding problem, the occlusion relationship is abnormal, and the conversion coefficient k2 for the implant diameter is < 1.

[0030] If the crowding ratio Yjb ≤ 1, it indicates that the patient does not have a tooth crowding problem, the occlusion relationship is normal, and the conversion coefficient k2 for the implant diameter is ≥ 1.

[0031] If the distribution index Fbz ≥ the distribution threshold FBY, it indicates that the patient's upper and lower teeth have uneven pressure distribution, the occlusion relationship is abnormal, and the conversion coefficient k1 for the implant height is ≥ 1.

[0032] If the distribution index Fbz is less than the distribution threshold FBY, it indicates that the upper and lower teeth pressure distribution of the patient is uniform, the occlusal relationship is normal, and the conversion coefficient k1 of the implant height is less than 1.

[0033] Preferably, in step four, the base data set Jtsj calculation process is as follows:

[0034] According to the implant data set, the height of the implant is marked as gd, the diameter of the implant is marked as zj, the taper of the implant is marked as zd, and the surface curvature of the implant is marked as ql.

[0035]

[0036] In the formula, gd x k1 represents the oral abutment height obtained according to the implant height, zj x k2 represents the oral abutment diameter obtained according to the implant diameter, zd x k3 represents the oral abutment taper obtained according to the implant taper, and ql x k4 represents the oral abutment surface curvature obtained according to the implant surface curvature.

[0037] Preferably, in step five, the oral abutment three-dimensional model TX construction process is as follows:

[0038] S1, according to the occlusal paper mark in the oral data set, the central axis of all contact points is fitted by using image processing software, and the dental centerline L is marked;

[0039] S2, according to the oral data set and the dental centerline L, the oral three-dimensional model KX is constructed by using CAD software;

[0040] S3, according to the implant data set, the implant three-dimensional model ZX is constructed by using CAD software;

[0041] S4, the implant three-dimensional model ZX is valued into the oral three-dimensional model KX, which is used to simulate the fitting state of the implant in the oral cavity;

[0042] S5, according to the base data set Jtsj, the oral abutment three-dimensional model TX is constructed by using CAD software;

[0043] S6, the oral abutment three-dimensional model TX is valued into the oral three-dimensional model KX, which is used to simulate the fitting state of the oral abutment in the oral cavity with the implant.

[0044] Preferably, in step five, the fitting degree evaluation process is as follows:

[0045] If the gap between the oral abutment three-dimensional model TX and the implant three-dimensional model ZX is greater than or equal to the fitting threshold THY in the patient's oral three-dimensional model KX, it indicates that the fitting degree of the oral abutment three-dimensional model TX is low, and the three-dimensional size of the oral abutment should be simulated again, and if the gap between the oral abutment three-dimensional model TX and the implant three-dimensional model ZX is less than the fitting threshold THY, it indicates that the fitting degree of the oral abutment three-dimensional model TX is high, and optimization is not needed.

[0046] Compared with the prior art, the present application provides a method for optimizing oral abutment three-dimensional modeling using a machine learning algorithm, which has the following beneficial effects:

[0047] 1、The present application connects the CT scanner through the network, obtains the detection data of the patient's oral cavity and the three-dimensional size of the implant, and classifies and forms the oral data set and the implant data set, analyzes the crowding degree and the occlusal force distribution state of the patient's teeth according to the oral data set, generates the corresponding crowding ratio Yjb and distribution index Fbz, analyzes the anterior tooth inclination of the patient according to the oral data set, and combines the crowding ratio Yjb and the distribution index Fbz to evaluate the occlusal relationship of the patient's teeth, and sets the corresponding conversion coefficient for converting the three-dimensional size of the implant into the three-dimensional size of the oral abutment, automatically enhances the abutment form adaptability for abnormal inclined teeth, reduces the risk of stress concentration, and automatically optimizes the abutment size to match the unique occlusal biomechanical environment of the patient, simulates the three-dimensional size of the oral abutment according to the implant data set and the conversion coefficient, generates the corresponding abutment data group Jtsj, and associates the implant parameters with the oral characteristics to realize rapid modeling and strong individual adaptation capability.

[0048] 2、The present application constructs the patient's oral three-dimensional model KX, implant three-dimensional model ZX and oral abutment three-dimensional model TX through the oral data set, implant data set and abutment data group Jtsj, sets a fixed numerical fitting threshold THY, evaluates the fitting degree of the oral abutment three-dimensional model TX, and outputs the corresponding optimization suggestion to form a modeling-verification-optimization closed loop, ensure the precise matching of the abutment and the implant, and optimize the modeling comfort. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 The method steps of the present application are shown in the figure. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0051] Since the traditional optimization method of three-dimensional modeling of oral abutment usually relies on the experience of doctors, the subjectivity is strong, it is difficult to ensure the accuracy, the individual adaptation ability is insufficient, the customized production cost is high, in addition, the patient needs to try on multiple times and repeatedly adjust the shape of the abutment, the patient's comfort is low, the implant restoration cycle is long, therefore, please refer to Figure 1 The application provides a method for optimizing three-dimensional modeling of oral abutment by using a machine learning algorithm, which comprises the following steps:

[0052] Step one: connect the CT scanner through the network, obtain the detection data of the patient's oral cavity and the three-dimensional size of the implant, and classify and form an oral data set and an implant data set;

[0053] The oral data set comprises the dental arch length, the crown width, the front tooth angle and the occlusal paper mark area of the patient, wherein the front tooth angle comprises the angle between the maxillary anterior teeth and the maxillary bone and the angle between the mandibular anterior teeth and the mandibular bone, the occlusal paper mark comprises a plurality of contact points, and the mark area is the contact point area;

[0054] The implant data set comprises the height, diameter, taper and surface curvature of the implant;

[0055] Specifically, by classifying the data set, the algorithm obtains a structured input, avoids the error introduced due to the dependence on subjective experience in the traditional modeling, and ensures the traceability and reusability of the data;

[0056] Step two: according to the oral data set, analyze the crowdedness of the patient's teeth and the distribution state of the occlusal force, and generate the corresponding crowdedness ratio Yjb and distribution index Fbz;

[0057] The crowdedness ratio Yjb calculation process is as follows:

[0058] According to the oral data set, the dental arch length of the patient is marked as gc, and the crown width of all the teeth of the patient is marked as {u1, u2, u3,..., un}, wherein u1 to un represent the crown width of the first tooth to the nth tooth;

[0059] ZU=u1+u2+u3+...+un

[0060]

[0061] In the formula, ZU represents the total crown width of all the teeth of the patient, and the crowdedness ratio Yjb is used to objectively judge the degree of tooth crowding;

[0062] The distribution index Fbz calculation process is as follows:

[0063] According to the oral data set, the occlusal paper mark area is marked as {y1, y2, y3,..., ym}, wherein y1 to ym represent the area of the first contact point to the mth contact point on the occlusal paper;

[0064]

[0065] In the formula, represents the average area of all contact points on the occlusion paper, ye represents the area of the e-th contact point on the occlusion paper, e∈m, represents the distribution index Fbz of the patient's teeth calculated according to the standard deviation formula, and the lower the value, the more uniform the patient's occlusal force distribution;

[0066] Step three: according to the oral data set, the inclination of the patient's anterior teeth is analyzed, and the occlusal relationship of the patient's teeth is evaluated in combination with the crowding ratio Yjb and the distribution index Fbz, and a corresponding conversion coefficient is set for converting the three-dimensional size of the implant into the three-dimensional size of the oral abutment, automatically enhancing the form adaptability of the abutment for the abnormally inclined teeth, reducing the risk of stress concentration, and automatically optimizing the size of the abutment to match the unique occlusal biomechanical environment of the patient;

[0067] The anterior tooth inclination evaluation process is as follows:

[0068] According to the oral data set, the angle between the patient's maxillary anterior teeth and the maxillary bone is marked as sj, and the angle between the patient's mandibular anterior teeth and the mandibular bone is marked as xj;

[0069] If 22°≤ the angle sj between the patient's maxillary anterior teeth and the maxillary bone ≤28°, it indicates that the inclination of the patient's maxillary anterior teeth is normal, the conversion coefficient k3 for the implant taper is ≤1, and the conversion coefficient k4 for the implant surface curvature is ≤1;

[0070] If the angle sj between the patient's maxillary anterior teeth and the maxillary bone is less than 22°, or the angle sj between the patient's maxillary anterior teeth and the maxillary bone is greater than 28°, it indicates that the inclination of the patient's maxillary anterior teeth is abnormal, the conversion coefficient k3 for the implant taper is greater than 1, and the conversion coefficient k4 for the implant surface curvature is greater than 1;

[0071] If 25°≤ the angle xj between the patient's mandibular anterior teeth and the mandibular bone ≤35°, it indicates that the inclination of the patient's mandibular anterior teeth is normal, the conversion coefficient k3 for the implant taper is ≤1, and the conversion coefficient k4 for the implant surface curvature is ≤1;

[0072] If the angle xj between the patient's mandibular anterior teeth and the mandibular bone is less than 25°, or the angle xj between the patient's mandibular anterior teeth and the mandibular bone is greater than 35°, it indicates that the inclination of the patient's maxillary anterior teeth is abnormal, the conversion coefficient k3 for the implant taper is greater than 1, and the conversion coefficient k4 for the implant surface curvature is greater than 1;

[0073] Specifically, the inclination angle of the front teeth is important for evaluating the occlusal relationship, and can directly determine whether the tooth inclination is normal. When the angle of the front teeth is abnormal, it may cause deep overbite, malocclusion and other problems. Therefore, it is recommended to choose a high taper or high curvature abutment to better adapt to the inclination angle of the implant. Such abutments can provide a larger adjustment range to help the restoration restore the correct tooth long axis, thereby optimizing the occlusal function and aesthetic effect.

[0074] The occlusal relationship evaluation process is as follows:

[0075] If the crowding ratio Yjb>1, it indicates that the patient has a tooth crowding problem and an abnormal occlusal relationship, and the conversion coefficient k2<1 for the implant diameter;

[0076] If the crowding ratio Yjb≤1, it indicates that the patient does not have a tooth crowding problem and has a normal occlusal relationship, and the conversion coefficient k2≥1 for the implant diameter;

[0077] Specifically, when the tooth crowding ratio Yjb is high, it may cause tooth misalignment and twisting, which can affect the normal contact of teeth during occlusion. It may also cause insufficient space around the implant, especially when the adjacent teeth are inclined or misaligned. If the abutment diameter is too large, it may conflict with the adjacent teeth or surrounding tissues, causing restoration difficulties or pressure on the gums.

[0078] If the distribution index Fbz≥distribution threshold FBY, it indicates that the patient's upper and lower teeth pressure distribution is uneven, and the occlusal relationship is abnormal, and the conversion coefficient k1≥1 for the implant height;

[0079] If the distribution index Fbz< distribution threshold FBY, it indicates that the patient's upper and lower teeth pressure distribution is uniform, and the occlusal relationship is normal, and the conversion coefficient k1<1 for the implant height;

[0080] Specifically, in a normal occlusion state, the occlusion mark should be evenly distributed on the functional cusp and sulcus area of the upper and lower teeth. If local premature contact or non-contact area is found during examination, it indicates that there is a problem of occlusal interference or incomplete occlusion, which can easily cause abnormal wear of teeth, and even may cause complications such as temporomandibular joint dysfunction. Therefore, the vertical distance needs to be compensated by adjusting the abutment height to restore the occlusal plane.

[0081] Step four: simulate the three-dimensional size of the oral abutment according to the implant data set and the conversion coefficient, and generate the corresponding abutment data set Jtsj;

[0082] The abutment data set Jtsj calculation process is as follows:

[0083] According to the implant data set, the height of the implant is marked as gd, the diameter of the implant is marked as zj, the taper of the implant is marked as zd, and the surface curvature of the implant is marked as ql.

[0084]

[0085] gd x k1 represents the height of the abutment obtained according to the height of the implant, zj x k2 represents the diameter of the abutment obtained according to the diameter of the implant, zd x k3 represents the taper of the abutment obtained according to the taper of the implant, and ql x k4 represents the surface curvature of the abutment obtained according to the surface curvature of the implant, which associates the implant parameters with the oral characteristics, realizes rapid modeling, and has strong individual adaptation capability;

[0086] Step five: according to the oral data set, the implant data set and the abutment data set Jtsj, the three-dimensional model KX of the patient's oral cavity, the three-dimensional model ZX of the implant and the three-dimensional model TX of the oral abutment are constructed, a fixed value of the fitting threshold THY is set, the adaptation degree of the three-dimensional model TX of the oral abutment is evaluated, and the corresponding optimization suggestion is output;

[0087] The construction process of the three-dimensional model TX of the oral abutment is as follows:

[0088] S1, according to the bite paper mark in the oral data set, the central axis of all contact points is fitted by using image processing software, and the dental center line L is marked;

[0089] S2, according to the oral data set and the dental center line L, the three-dimensional model KX of the oral cavity is constructed by using CAD software;

[0090] S3, according to the implant data set, the three-dimensional model ZX of the implant is constructed by using CAD software;

[0091] S4, the three-dimensional model ZX of the implant is valued into the three-dimensional model KX of the oral cavity, which is used to simulate the fitting state of the implant in the oral cavity;

[0092] S5, according to the abutment data set Jtsj, the three-dimensional model TX of the oral abutment is constructed by using CAD software;

[0093] S6, the three-dimensional model TX of the oral abutment is valued into the three-dimensional model KX of the oral cavity, which is used to simulate the fitting state of the oral abutment in the oral cavity with the implant;

[0094] The adaptation degree evaluation process is as follows:

[0095] In the three-dimensional model KX of the patient's oral cavity, if the gap between the three-dimensional model TX of the oral abutment and the three-dimensional model ZX of the implant is greater than or equal to the fitting threshold THY, it indicates that the adaptation degree of the three-dimensional model TX of the oral abutment is low, and the three-dimensional size of the oral abutment should be simulated again, if the gap between the three-dimensional model TX of the oral abutment and the three-dimensional model ZX of the implant is less than the fitting threshold THY, it indicates that the adaptation degree of the three-dimensional model TX of the oral abutment is high, and optimization is not needed, forming a modeling-verification-optimization closed loop to ensure the precise matching of the abutment and the implant, and the optimization modeling has high comfort.

[0096] Example 1

[0097] In this experiment, a 35-year-old patient was selected as the subject. Measurements showed that the patient's dental arch length was 50mm, and the crown widths of the 32 teeth were: 8mm, 7mm, 6mm, 7mm, 8mm, 9mm, 7mm, 8mm, 6mm, 7mm, 8mm, 7mm, 6mm, 7mm, 8mm, 7mm, 6mm, 7mm, 8mm, 7mm, 6mm, 7mm, 8mm, 7mm, 6mm, 7mm, 8mm, 7mm, 8mm, 7mm, 8mm, and 7mm. The crowding ratio of this patient's teeth was calculated using the Yjb algorithm as follows:

[0098] ZU=8+7+6+7+8+9+7+8+6+7+8+7+6+7+8+7+6+7+8+7+6+7+8+7+6+7+8+7+6+7+8+7=224

[0099]

[0100] In the formula, ZU = 224 represents the total crown width of all the patient's teeth. The crowding ratio Yjb of the patient's teeth is 4.48. It is determined that the crowding ratio Yjb of the patient's teeth is greater than 1, indicating that the patient has a problem with tooth crowding and abnormal occlusion. The conversion coefficient k2 for implant diameter is less than 1.

[0101] Example 2

[0102] In this experiment, a 60-year-old patient was selected as the subject. The patient's occlusal paper imprint area was measured to be 2.0 mm². 2 3.5mm 2 4.0mm 2 2.5mm 2 and 3.0mm 2 The distribution index Fbz for this patient is calculated as follows:

[0103]

[0104] In the formula, The average area of ​​all contact points on the occlusal paper is represented by the standard deviation formula. The distribution index Fbz of the patient's teeth is calculated to be approximately 0.71. The distribution threshold FBY is set to 1. It is determined that the distribution index Fbz of the patient's teeth is less than the distribution threshold FBY, indicating that the pressure distribution of the patient's upper and lower teeth is uniform and the occlusal relationship is normal. The conversion coefficient k1 for implant height is less than 1.

[0105] The setting of the size of the threshold is to facilitate comparison, and the size of the threshold depends on how much sample data and the base number set by the person skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantized values.

[0106] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formula are set by the person skilled in the art according to the actual situation. The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical range disclosed by the present application, according to the technical solution and the inventive concept of the present application, should be covered within the protection scope of the present application.

Claims

1. A method for optimizing 3D modeling of dental abutments using machine learning algorithms, characterized in that, Includes the following steps: Step 1: Connect to a CT scanner via the network to acquire the patient's oral cavity examination data and the three-dimensional dimensions of the implants, and classify them into oral cavity datasets and implant datasets; Step 2: Based on the oral dataset, analyze the crowding degree and occlusal force distribution of the patient's teeth, and generate the corresponding crowding ratio Yjb and distribution index Fbz; Step 3: Based on the oral dataset, analyze the patient's anterior tooth inclination, and then combine the crowding ratio Yjb and distribution index Fbz to assess the occlusal relationship of the patient's teeth, and set the corresponding conversion coefficient to convert the implant three-dimensional dimensions into the oral abutment three-dimensional dimensions. Step 4: Based on the implant dataset and conversion coefficients, simulate the three-dimensional dimensions of the dental abutment and generate the corresponding abutment dataset Jtsj; Step 5: Based on the oral dataset, implant dataset, and abutment dataset Jtsj, construct the patient's oral 3D model KX, implant 3D model ZX, and oral abutment 3D model TX. Set a fixed fitting threshold THY, evaluate the fit of the oral abutment 3D model TX, and output corresponding optimization suggestions.

2. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 1, characterized in that: In step one, the oral dataset includes the patient's dental arch length, crown width, anterior tooth angle, and occlusal paper imprint area. The anterior tooth angle includes the angle between the maxillary anterior teeth and the maxilla and the mandibular anterior teeth and the mandible. The occlusal paper imprint contains several contact points, and the imprint area is the contact point area.

3. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 2, characterized in that: In step one, the planting dataset includes the height, diameter, taper, and surface curvature of the implant.

4. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 3, characterized in that: In step two, the calculation process for the congestion ratio Yjb is as follows: Based on the oral dataset, the patient's dental arch length is labeled as gc, and the crown width of all the patient's teeth is labeled as {u1, u2, u3, ..., un}, where u1 to un represent the crown width of the first to the nth teeth; ZU=u1+u2+u3+...+un In the formula, ZU represents the sum of the crown widths of all the patient's teeth.

5. The method for optimizing three-dimensional modeling of the oral abutment using machine learning algorithms according to claim 4, characterized in that: In step two, the calculation process for the distribution index Fbz is as follows: Based on the oral cavity dataset, the areas of the occlusal paper imprints are labeled as {y1, y2, y3, ..., ym}, where y1 to ym represent the areas of the first to the mth contact points on the occlusal paper; In the formula, Let y represent the average area of ​​all contact points on the interlocking paper, and ye represent the area of ​​the e-th contact point on the interlocking paper, where e ∈ m. This indicates that the distribution index Fbz of the patient's teeth is calculated according to the standard deviation formula.

6. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 5, characterized in that: In step three, the anterior tooth inclination assessment process is as follows: Based on the oral dataset, the angle between the patient's maxillary anterior teeth and the maxilla is labeled as sj, and the angle between the patient's mandibular anterior teeth and the mandible is labeled as xj. If 22°≤ the angle sj between the patient's maxillary anterior teeth and the maxilla≤28°, it indicates that the patient's maxillary anterior teeth inclination is normal, the conversion coefficient k3≤1 for implant taper, and the conversion coefficient k4≤1 for implant surface curvature. If the angle sj between the patient's maxillary anterior teeth and the maxilla is <22°, or the angle sj between the patient's maxillary anterior teeth and the maxilla is >28°, it indicates that the patient's maxillary anterior teeth have an abnormal inclination. The conversion coefficient k3 for implant taper is >1, and the conversion coefficient k4 for implant surface curvature is >1. If 25°≤ the angle xj between the patient's mandibular anterior teeth and the mandible≤35°, it means that the patient's mandibular anterior teeth inclination is normal. The conversion coefficient k3≤1 for implant taper and the conversion coefficient k4≤1 for implant surface curvature. If the angle xj between the patient's mandibular anterior teeth and the mandible is less than 25°, or the angle xj between the patient's mandibular anterior teeth and the mandible is greater than 35°, it indicates that the patient's maxillary anterior teeth have an abnormal inclination. The conversion coefficient k3 for implant taper is greater than 1, and the conversion coefficient k4 for implant surface curvature is greater than 1.

7. The method for optimizing three-dimensional modeling of the oral abutment using machine learning algorithms according to claim 6, characterized in that: In step three, the occlusal relationship assessment process is as follows: If the crowding ratio Yjb > 1, it indicates that the patient has a problem with tooth crowding and abnormal occlusion, and the conversion coefficient k2 for the implant diameter is < 1. If the crowding ratio Yjb≤1, it means that the patient does not have a problem with tooth crowding, the occlusion is normal, and the conversion coefficient k2 for the implant diameter is ≥1. If the distribution index Fbz ≥ the distribution threshold FBY, it indicates that the pressure distribution of the patient's upper and lower teeth is uneven and the occlusal relationship is abnormal. The conversion coefficient k1 for implant height is ≥ 1. If the distribution index Fbz < the distribution threshold FBY, it indicates that the pressure distribution of the patient's upper and lower teeth is uniform, the occlusal relationship is normal, and the conversion coefficient k1 for implant height is < 1.

8. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 7, characterized in that: In step four, the calculation process for the base station data group Jtsj is as follows: Based on the implant dataset, the height of the implant is labeled as gd, the diameter of the implant is labeled as zj, the taper of the implant is labeled as zd, and the surface curvature of the implant is labeled as ql. In the formula, gd×k1 represents the abutment height obtained based on the implant height, zj×k2 represents the abutment diameter obtained based on the implant diameter, zd×k3 represents the abutment taper obtained based on the implant taper, and ql×k4 represents the abutment surface curvature obtained based on the implant surface curvature.

9. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 8, characterized in that: In step five, the process for constructing the 3D model (TX) of the oral abutment is as follows: S1. Based on the occlusal paper imprints in the oral cavity dataset, use image processing software to fit the midline of all contact points and mark the tooth midline L; S2. Based on the oral cavity dataset and the dental midline L, construct a three-dimensional oral cavity model KX using CAD software; S3. Based on the planting dataset, construct a three-dimensional model ZX of the implant using CAD software; S4. Input the ZX value of the implant 3D model into the oral cavity 3D model KX to simulate the fit of the implant in the oral cavity. S5. Based on the abutment data set Jtsj, construct a three-dimensional model TX of the dental abutment using CAD software; S6. Input the TX value of the three-dimensional model of the oral abutment into the three-dimensional model of the oral cavity KX to simulate the fit between the oral abutment and the implant in the oral cavity.

10. The method for optimizing three-dimensional modeling of the oral cavity abutment using machine learning algorithms according to claim 9, characterized in that: In step five, the fit evaluation process is as follows: In the patient's oral cavity 3D model KX, if the gap between the oral abutment 3D model TX and the implant 3D model ZX is greater than or equal to the fitting threshold THY, it indicates that the fit of the oral abutment 3D model TX is low and the 3D dimensions of the oral abutment should be re-simulated. If the gap between the oral abutment 3D model TX and the implant 3D model ZX is less than the fitting threshold THY, it indicates that the fit of the oral abutment 3D model TX is high and no optimization is required.

Images