Method for automatically aligning dentures in three-dimensional oral cavity data and computer-readable recording medium in which program for executing same on computer is recorded

Abstract

A method for automatically aligning dentures in three-dimensional oral cavity data comprises the steps of: receiving three-dimensional oral cavity data; determining features of the three-dimensional oral cavity data; determining features of three-dimensional tooth data; transforming the three-dimensional tooth data into a transformed state by using the features and constraints; determining a state change of the transformed state; and generating transformed tooth data by considering the state change and a reference value.

Description

A computer-readable recording medium having recorded thereon a method for automatically aligning dentures to three-dimensional oral data and a program for executing the method on a computer.

[0001] The present invention relates to a method for automatically aligning dentures to three-dimensional oral data, and more particularly, to a method for automatically aligning dentures to three-dimensional oral data, which can shorten the time and process for manufacturing dentures and improve their quality.

[0002] 3D oral model data refers to 3D scanned models of an oral cavity with significant or complete tooth loss, or a model or reconstruction of such a case. Dentures must be individually designed to fit each patient's oral structure, so they must be manufactured individually.

[0003] The method of making dentures is gradually changing from the method of making a mold of the oral cavity using alginate and then making the prosthesis manually to the digital method of obtaining data of the edentulous oral cavity using a 3D scanner, designing the prosthesis using a computer, and then 3D printing it.

[0004] The purpose of the present invention is to provide a method for automatically arranging dental data in a three-dimensional oral scan model, which can shorten the time and process for manufacturing dentures and improve quality.

[0005] However, the problem to be solved by the present invention is not limited to the problem mentioned above, and may be expanded in various ways without departing from the spirit and scope of the present invention.

[0006] A method for automatically aligning dentures to three-dimensional oral data according to embodiments of the present invention includes the steps of receiving three-dimensional oral data, determining features of the three-dimensional oral data, determining features of the three-dimensional tooth data, converting the three-dimensional tooth data into a transformed state using the features and restrictions, determining a state change of the transformed state, and generating transformed tooth data by considering the state change and a reference value.

[0007] In one embodiment, the step of converting to the transformation state may include the step of determining an initial state of the 3D dental data, the step of converting the initial state to a first transformation state based on the feature of the 3D oral data, and the step of determining a compensation value using the first transformation state and the constraints.

[0008] In one embodiment, the step of converting to the conversion state may further include a step of determining whether the state change of the first conversion state is greater than or equal to the reference value.

[0009] In one embodiment, the step of converting to the transformation state may further include a step of converting the first transformation state to a second transformation state based on the feature of the three-dimensional oral data when the state change of the first transformation state is lower than the reference value.

[0010] In one embodiment, the step of converting to the conversion state may be such that, if the state change of the first conversion state is greater than or equal to the reference value, the first conversion state may be the converted tooth data.

[0011] In one embodiment, the state change may be a change in the reward value.

[0012] In one embodiment, the state change may be the difference between the initial state and the first transformed state.

[0013] In one embodiment, the reward value may be a value based on a weight and a satisfaction value, and the satisfaction value may be a value based on the first transformation state and the constraints.

[0014] In one embodiment, if the first transformation state is outside the constraints, the satisfaction value may be 0.

[0015] In one embodiment, the satisfaction value may be changed based on a satisfaction degree which is a difference between the first transformation state and the constraint.

[0016] In one embodiment, the method may further include a step of terminating learning when the change in the reward value is greater than or equal to a reference change.

[0017] In one embodiment, the three-dimensional tooth data may include three-dimensional single tooth data. The three-dimensional single tooth data may be converted into transformed single tooth data based on the feature.

[0018] In one embodiment, the compensation value may be determined based on whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data. Whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data may be determined based on an angular difference between a normal vector of the median plane of the first transformation state and a normal vector of the median plane of the three-dimensional oral data.

[0019] In one embodiment, the reward value may be a product of a weight and a satisfaction value. The satisfaction value may be calculated using the second formula.

[0020] [Second Formula]

[0021]

[0022] Here, means the above satisfaction value, refers to the normal vector of the median plane of the above 3D oral data, may be the normal vector of the median plane of the first transformation state.

[0023] In one embodiment, the compensation value may be determined based on whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data. Whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data may be determined based on a distance from a point on the median plane of the first transformation state to the median plane of the three-dimensional oral data.

[0024] In one embodiment, the compensation value may be determined based on whether the occlusal plane of the first transformation state is similar to the occlusal plane of the three-dimensional oral data. Whether the occlusal plane of the first transformation state is similar to the occlusal plane of the three-dimensional oral data may be determined based on the angular difference between the normal vector of the occlusal plane of the first transformation state and the normal vector of the occlusal plane of the three-dimensional oral data.

[0025] In one embodiment, the reward value may be a product of a weight and a satisfaction value. The satisfaction value may be calculated using the fourth formula.

[0026] [Formula 4]

[0027]

[0028] Here, means the above satisfaction value, refers to the normal vector of the occlusal plane of the above 3D oral data, may be the normal vector of the occlusal plane of the first transformation state.

[0029] In one embodiment, the compensation value may be determined based on whether the first transformation state is located within the borderline. Whether the first transformation state is located within the borderline may be determined based on whether the first transformation state is located around the borderline of the three-dimensional oral data.

[0030] In one embodiment, the compensation value may be determined based on whether the first transformation state is similar to the shape of the wax rim. Whether the first transformation state is similar to the shape of the wax rim may be determined using the average distance between the position data of the first transformation state and the shape data of the wax rim.

[0031] A computer-readable recording medium having recorded thereon a program according to embodiments of the present invention causes a computer to execute a method for automatically aligning dentures to three-dimensional oral data. The method includes the steps of receiving three-dimensional oral data, determining features of the three-dimensional oral data and three-dimensional tooth data, converting the three-dimensional tooth data into a transformed state using the features and constraints, determining a state change of the transformed state, and generating transformed tooth data by considering the state change and a reference value.

[0032] According to a method for automatically aligning dentures to three-dimensional oral data, dentures are automatically generated from the three-dimensional oral data, thereby shortening the denture manufacturing time and process and improving the quality of the dentures.

[0033] In addition, the step of converting 3D dental data using features includes at least one of the steps of determining an initial state of the 3D dental data, determining a behavior of the initial state, converting the initial state into a transformed state based on the behavior, determining a compensation value based on the transformed state and restrictions, and determining whether the state change of the transformed state is greater than or equal to a reference value, which is performed using an artificial intelligence neural network, so that the time and process for manufacturing dentures can be shortened and the quality of dentures can be improved. In addition, dentures more suitable for the 3D oral data can be created.

[0034] However, the effects of the present invention are not limited to the above-mentioned effects, and may be expanded in various ways without departing from the spirit and scope of the present invention.

[0035] FIG. 1 is a flowchart illustrating an example of a method for automatically aligning dentures to three-dimensional oral data according to one embodiment of the present invention.

[0036] Figure 2 is a flowchart showing an example of converting the 3D tooth data of Figure 1.

[0037] Fig. 3 is a drawing showing an example of the three-dimensional tooth data of Fig. 1.

[0038] Figure 4 is a drawing showing an example of the three-dimensional oral data of Figure 1.

[0039] Figure 5 is a drawing showing the median plane and occlusal plane of the three-dimensional oral data of Figure 4.

[0040] Figure 6 is a drawing showing the median plane and occlusal plane of the three-dimensional tooth data of Figure 3.

[0041] Figure 7 is a drawing showing the maxillary tubercle, incisal papilla, and border line of the 3D maxillary data included in the 3D oral data of Figure 4.

[0042] Figure 8 is a drawing showing the posterior prominence and border line of the 3D mandibular data included in the 3D oral data of Figure 4.

[0043] Fig. 9 is a drawing showing an example of the three-dimensional oral data of Fig. 1.

[0044] Fig. 10 is a drawing showing transformed tooth data generated according to a method for automatically aligning dentures to the three-dimensional oral data of Fig. 1.

[0045] Fig. 11 is a flowchart showing an example of converting the 3D tooth data of Fig. 1.

[0046] FIG. 12 is a flowchart illustrating an example of a method for automatically aligning dentures to three-dimensional oral data according to one embodiment of the present invention.

[0047] Figure 13 is a drawing showing the deleted data of Figure 12.

[0048] With respect to the embodiments of the present invention disclosed in the text, specific structural and functional descriptions are merely illustrative for the purpose of explaining the embodiments of the present invention, and the embodiments of the present invention may be implemented in various forms and should not be construed as being limited to the embodiments described in the text.

[0049] The present invention is susceptible to various modifications and takes various forms. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present invention to specific disclosed forms, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention.

[0050] While terms like "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms may be used to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0051] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0052] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0053] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be construed in an idealized or overly formal sense unless explicitly defined herein.

[0054] Meanwhile, if a particular embodiment can be implemented differently, the functions or operations specified within a particular block may occur in a different order than specified in the flowchart. For example, two consecutive blocks may actually be executed substantially simultaneously, or, depending on the related functions or operations, the blocks may be executed in reverse order.

[0055] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. Identical components in the drawings are designated by the same reference numerals, and redundant descriptions of identical components are omitted.

[0056] FIG. 1 is a flowchart showing an example of a method for automatically aligning dentures to three-dimensional oral data according to an embodiment of the present invention. FIG. 2 is a flowchart showing an example of converting three-dimensional dental data (DD) of FIG. 1. FIG. 3 is a diagram showing an example of the three-dimensional dental data (DD) of FIG. 1. FIG. 4 is a diagram showing an example of the three-dimensional oral data (EAD) of FIG. 1. FIG. 5 is a diagram showing a midline plane (MSP) and an occlusal plane (OSP) of the three-dimensional oral data (EAD) of FIG. 4. FIG. 6 is a diagram showing a midline plane (MSP) and an occlusal plane (OSP) of the three-dimensional dental data (DD) of FIG. 3. FIG. 7 is a diagram showing a maxillary tubercle (HN), an incisal papilla (IP), and a border line (BL) of three-dimensional maxillary data (MAXD) included in the three-dimensional oral data (EAD) of FIG. 4. Figure 8 is a drawing showing the posterior prominence (RP) and border line (BL) of the three-dimensional mandibular data (MAND) included in the three-dimensional oral data (EAD) of Figure 4.

[0057] Referring to FIGS. 1 to 8, a method for automatically aligning dentures to three-dimensional oral data according to the present embodiment may include a step of receiving three-dimensional oral data (EAD) (S100-1), a step of receiving three-dimensional dental data (DD) (S100-2), a step of determining a feature of the three-dimensional oral data (EAD) (S300), a step of determining a feature of the three-dimensional dental data (DD) (S400), and a step of converting the three-dimensional dental data (DD) using the feature (S500). The method for automatically aligning dentures to three-dimensional oral data may be performed by a computing device.

[0058] In one embodiment, a method for automatically aligning dentures to the three-dimensional oral data can be performed using deep reinforcement learning.

[0059] For example, reinforcement learning can mean learning to perform an action in the current state and derive an optimal policy through the reward obtained through said action. The deep reinforcement learning can be a model that considers deep learning techniques in the reinforcement learning. The reinforcement learning can store both states and actions in the form of a lookup table, which can result in large capacity. In contrast, deep reinforcement learning can reduce capacity by functionalizing the states and actions through neural network learning. Furthermore, since reward design is simpler than rule-based techniques that design rewards for all cases, it can enable setting desired restrictions on the actions.

[0060] The above 3D oral data refers to data scanned using a 3D scanner of teeth and the oral cavity, or an object modeled or reconstructed therefrom. For example, the 3D oral data may be mesh data including 3D points (vertexes) and triangular or rectangular faces (rectangles) created by connecting the points. There is no restriction on the file extension of the 3D oral data, and may be, for example, one of ply, obj, and stl.

[0061] The above 3D oral data (EAD) may include 3D maxillary data (MAXD) and 3D mandibular data (MAND). In one embodiment, the 3D tooth data (DD) may be stored data. In one embodiment, the 3D tooth data (DD) may be selected by a user. For example, the 3D tooth data (DD) may be a 3D tooth library model. The 3D tooth library model is a type of sample tooth (standard tooth) used to manufacture prosthetics, implants, braces, etc., and may have a typical tooth shape. The tooth library model may have one sample tooth (standard tooth) for each tooth number. The 3D tooth library model may be a tooth model with a high degree of mesh completion. Therefore, when manufacturing prosthetics, dentures, implants, braces, etc. by modifying the 3D tooth library model, it may be very suitable for using a 3D printing method. Therefore, when the above 3D dental library model is aligned with the patient's oral scan data, it can become an appropriate intermediate model for digitally manufacturing prosthetics, dentures, implants, braces, etc.

[0062] The step (S500) of converting the 3D tooth data (DD) using the above features may include a step (S510) of determining an initial state of the 3D tooth data (DD), a step (S530) of determining a behavior of the initial state, a step (S550) of converting the initial state into a conversion state based on the behavior, a step (S570-1) of determining a compensation value based on the conversion state and restrictions, and a step (S590A) of determining whether the state change of the conversion state is greater than or equal to a reference value. If the state change of the conversion state is lower than the reference value, the step (S500) of converting the 3D tooth data (DD) using the features may include a step (S570-2) of determining a behavior of the first conversion state. For example, if the state change of the conversion state is lower than the reference value, the step of converting the 3D tooth data (DD) may further include a step of converting the first conversion state into a second conversion state based on the feature. For example, the step (S500) of converting the 3D dental data (DD) using the above features can be performed by an artificial intelligence neural network.

[0063] In one embodiment, the three-dimensional tooth data (DD) may include three-dimensional single tooth data (ODD). The three-dimensional single tooth data (ODD) may be converted into transformed single tooth data based on the feature.

[0064] The initial state may refer to the state of the three-dimensional dental data (DD). For example, the initial state may represent information such as the position, rotation state, size, and inclination of the three-dimensional dental data. For example, the initial state may be defined by a first coordinate.

[0065] [1st coordinate]

[0066]

[0067] Here, means the initial state, refers to the x-coordinate of the 3D tooth data (DD), refers to the y-coordinate of the 3D tooth data (DD), refers to the z-coordinate of the 3D tooth data (DD), represents the rotation state in the x-axis direction of the 3D tooth data (DD), represents the rotation state in the y-axis direction of the 3D tooth data (DD), represents the rotation state in the z-axis direction of the 3D tooth data (DD), represents the size of the 3D tooth data (DD) in the x-axis direction, represents the size of the 3D tooth data (DD) in the y-axis direction, represents the size of the 3D tooth data (DD) in the z-axis direction, may refer to the slope of the 3D dental data (DD).

[0068] However, the present invention is not limited to the number of pieces of information contained in the initial state. For example, the initial state may only contain information about position and rotation.

[0069] The above action may refer to an operation of converting the initial state into a first transformation state. For example, if the initial state has a first position and a first rotation state, the first position may be changed to a second position and the first rotation state may be changed to a second rotation state through the action. Accordingly, the first transformation state may have the second position and the second rotation state. For example, if the initial state has a first size, the first size may be changed to a second size through the action. For example, if the initial state has a first slope, the first slope may be changed to a second slope through the action. In one embodiment, the action may vary based on the reward value.

[0070] The above compensation value may be determined based on the first transformation state and restrictions. The restrictions may be data based on the features. For example, the restrictions may be data that considers whether the first transformation state is located within a border line (BL), whether it is similar to a shape of a wax-rim (WXR), whether the occlusal plane (OSP) of the first transformation state is similar to the occlusal plane (OSP) of the three-dimensional oral data (EAD), and whether the midline (MSP) of the first transformation state is similar to the midline (MSP) of the three-dimensional oral data (EAD). The compensation value may be a value based on a weight and a satisfaction value. For example, the compensation value may be a value obtained by multiplying the weight and the satisfaction value.

[0071] In general, the median plane may refer to the exact center plane dividing the right and left sides of the body. In the present embodiment, the median plane (MSP) may refer to the exact center plane of the three-dimensional oral data (EAD). Additionally, the median plane (MSP) may refer to the exact center plane of the three-dimensional dental data (DD).

[0072] In general, the occlusal plane may refer to a plane on which the occlusal surfaces of teeth are located. In one embodiment, the occlusal plane (OSP) may be set by the user.

[0073] In general, the incisal papilla may refer to a raised portion near the anterior end of the median plane of the maxillary arch. The incisal papilla may be located between the central incisors. In the present embodiment, the incisal papilla (IP) may refer to a raised portion near the anterior end of the median plane (MSP) of the three-dimensional oral data (EAD).

[0074] In general, a retrooral prominence can refer to a raised area behind a mandibular molar. A maxillary tubercle can refer to a raised area behind a maxillary molar. A border can refer to the boundary between the gums anteriorly and the hard and soft palates posteriorly. A wax rim can be created during the denture fabrication process. For example, a wax rim can refer to a wax model created by the user based on their prediction of the size and shape. For example, the shape can refer to a model used in dentistry to aid in the fabrication of removable prosthetics, such as complete and partial dentures.

[0075] In one embodiment, an integrated compensation value may be determined based on the compensation value. For example, the integrated compensation value may be a value obtained by adding a first compensation value and a second compensation value. For example, the first compensation value may be a compensation value determined based on whether the median plane (MSP) of the first transformed state is similar to the median plane (MSP) of the three-dimensional oral data (EAD). For example, the second compensation value may be a compensation value determined based on whether the occlusal plane (OSP) of the first transformed state is similar to the occlusal plane (OSP) of the three-dimensional oral data (EAD). However, the present invention is not limited to the number of compensation values ​​on which the integrated compensation value is based.

[0076] In one embodiment, the weight may be set by the user. For example, the weight may vary depending on the constraints. For example, if the user considers whether the first transformation state is located within the borderline (BL) important among the constraints, the weight for whether the first transformation state is located within the borderline (BL) may be set high.

[0077] In one embodiment, the weights can be learned using the artificial intelligence neural network.

[0078] In one embodiment, the satisfaction value may have a fixed value based on whether the first transformation state satisfies the constraint. For example, if the first transformation state satisfies the constraint, the satisfaction value may have an ON value. For example, the ON value may mean 1. For example, if the first transformation state does not satisfy the constraint, the satisfaction value may have an OFF value. For example, the OFF value may mean 0.

[0079] In one embodiment, the satisfaction value may be defined by the user. For example, the satisfaction value may vary based on the degree of satisfaction, which is the difference between the first transition state and the constraint. For example, the satisfaction value may have a linear function based on the degree of satisfaction, which is the degree to which the first transition state satisfies the constraint. For example, the satisfaction value may have a non-linear function based on the degree of satisfaction.

[0080] In one embodiment, the compensation values ​​and the satisfaction values ​​can be calculated using a formula.

[0081] For example, the first compensation value can be calculated based on the first formula.

[0082] [Formula 1]

[0083]

[0084] Here, means the above first compensation value, means the first weight, may mean the first satisfaction value. The first satisfaction value may be a value indicating whether the median plane (MSP) of the first transformation state is similar to the median plane (MSP) of the three-dimensional oral data (EAD). For example, whether the median plane (MSP) of the first transformation state is similar to the median plane (MSP) of the three-dimensional oral data (EAD) may be determined based on an angular difference between a normal vector of the median plane (MSP) of the first transformation state and a normal vector of the median plane (MSP) of the three-dimensional oral data (EAD). For example, whether the median plane (MSP) of the first transformation state is similar to the median plane (MSP) of the three-dimensional oral data (EAD) may be determined based on a distance from a point of the median plane (MSP) of the first transformation state to the median plane (MSP) of the three-dimensional oral data (EAD). The higher the similarity between the median plane (MSP) of the first transformation state and the median plane (MSP) of the three-dimensional oral data (EAD), the higher the first compensation value may be.

[0085] For example, the first satisfaction value can be calculated based on the second formula.

[0086] [Second Formula]

[0087]

[0088] Here, means the first satisfying value, refers to the normal vector of the median plane (MSP) of the three-dimensional oral data (EAD), may refer to the normal vector of the median plane (MSP) of the first transformation state. The similarity between the median plane (MSP) of the first transformation state and the median plane (MSP) of the 3D oral data (EAD) may be determined using the second formula. For example, the first satisfaction value may be calculated by utilizing the inner product of the normal vector of the median plane (MSP) and the normal vector of the median plane (MSP) of the first transformation state. For example, the first satisfaction value may be calculated by utilizing the outer product of the normal vector of the median plane (MSP) and the normal vector of the median plane (MSP) of the first transformation state. However, the present invention is not limited to the formula for calculating the first satisfaction value.

[0089] For example, the second compensation value can be calculated based on the third formula.

[0090] [Formula 3]

[0091]

[0092] Here, means the second compensation value, means the second weight, may refer to the second satisfaction value. The second satisfaction value may be a value indicating whether the occlusal plane (OSP) of the first transformation state is similar to the occlusal plane (OSP) of the three-dimensional oral data (EAD). For example, whether the occlusal plane (OSP) of the first transformation state is similar to the occlusal plane (OSP) of the three-dimensional oral data (EAD) may be determined based on an angular difference between a normal vector of the occlusal plane (OSP) of the first transformation state and a normal vector of the occlusal plane (OSP) of the three-dimensional oral data (EAD). For example, whether the occlusal plane (OSP) of the first transformation state is similar to the occlusal plane (OSP) of the three-dimensional oral data (EAD) may be determined based on a distance from a point of the occlusal plane (OSP) of the first transformation state to the occlusal plane (OSP) of the three-dimensional oral data (EAD). The higher the similarity between the occlusal plane (OSP) of the first transformation state and the occlusal plane (OSP) of the three-dimensional oral data (EAD), the higher the second compensation value may be.

[0093] For example, the second satisfaction value can be calculated based on the fourth formula.

[0094] [Formula 4]

[0095]

[0096] Here, means the second satisfying value, refers to the normal vector of the occlusal plane (OSP) of the above 3D oral data (EAD), may refer to the normal vector of the occlusal plane (OSP) of the first transformation state. The similarity between the occlusal plane (OSP) of the first transformation state and the occlusal plane (OSP) of the three-dimensional oral data (EAD) may be determined using the second formula. For example, the second satisfaction value may be calculated by utilizing the inner product of the normal vector of the occlusal plane (OSP) of the three-dimensional oral data (EAD) and the normal vector of the occlusal plane (OSP) of the first transformation state. For example, the second satisfaction value may be calculated by utilizing the outer product of the normal vector of the occlusal plane (OSP) of the three-dimensional oral data (EAD) and the normal vector of the occlusal plane (OSP) of the first transformation state. However, the present invention is not limited to the formula for calculating the second satisfaction value.

[0097] For example, the third compensation value can be calculated based on the fifth formula.

[0098] [Formula 5]

[0099]

[0100] Here, means the third compensation value, means the third weight, may mean a third satisfaction value. For example, the third satisfaction value may be a value indicating whether the first conversion state is located within the border line (BL). For example, whether the first conversion state is located within the border line (BL) may be determined based on whether the first conversion state is located around the border line (BL) of the three-dimensional oral data (EAD). For example, whether the first conversion state is located within the border line (BL) may be determined using an average distance between the position data of the first conversion state and the position data of the border line (BL). However, the present invention is not limited to a method for determining whether the first conversion state is located within the border line (BL). For example, when the first conversion state is located outside the border line (BL), the third compensation value may decrease.

[0101] For example, the fourth compensation value can be calculated based on the sixth formula.

[0102] [Formula 6]

[0103]

[0104] Here, means the fourth compensation value, means the fourth weight, may mean a fourth satisfaction value. The fourth satisfaction value may be a value indicating whether the first conversion state is similar to the shape of the wax rim (WXR). For example, whether the first conversion state is similar to the shape of the wax rim (WXR) may be determined using the average distance between the position data of the first conversion state and the shape data of the wax rim (WXR). However, the present invention is not limited to a method for determining whether the first conversion state is similar to the shape of the wax rim (WXR).

[0105] For example, the fifth reward value can be calculated based on the seventh formula.

[0106] [7th Formula]

[0107]

[0108] Here, means the fifth compensation value, means the fifth weight, may mean a fifth satisfaction value. The fifth satisfaction value may be a value indicating whether the first transformation state is located close to the retrooral prominence (RP) of the three-dimensional oral data (EAD). For example, when the first transformation state is located close to the retrooral prominence (RP), the fifth satisfaction value may increase. For example, when the first transformation state is located far from the retrooral prominence (RP), the fifth satisfaction value may decrease. For example, when the first transformation state overlaps with an area of ​​the retrooral prominence (RP), the fifth satisfaction value may decrease.

[0109] For example, the sixth reward value can be calculated based on the eighth formula.

[0110] [Eighth Formula]

[0111]

[0112] Here, means the above 6th compensation value, means the 6th weight, may mean a sixth satisfaction value. The sixth satisfaction value may be a value indicating whether the first transformation state is located close to the maxillary tubercle (HN) of the three-dimensional oral data (EAD). For example, when the first transformation state is located close to the maxillary tubercle (HN), the sixth satisfaction value may increase. For example, when the first transformation state is located far from the maxillary tubercle (HN), the sixth satisfaction value may decrease. For example, when the first transformation state overlaps with an area of ​​the maxillary tubercle (HN), the sixth satisfaction value may decrease.

[0113] For example, the seventh reward value can be calculated based on the ninth formula.

[0114] [9th Formula]

[0115]

[0116] Here, means the above 7th compensation value, means the 7th weight, may mean a seventh satisfaction value. The seventh satisfaction value may mean a value indicating whether the first transformation state is located close to the incisal papilla (IP) of the three-dimensional oral data (EAD). For example, the seventh satisfaction value may be a value indicating whether the central incisor (MT) of the first transformation state is spaced apart from the incisal papilla (IP) by a first distance in the first direction (D1). For example, the seventh satisfaction value may be determined based on the position data of the first distance and the distance of the central incisor (MT). For example, the seventh satisfaction value may be determined based on the distance between the position data of the first distance and the midpoint of the central incisor (MT). For example, the first distance may be set based on anatomy. For example, the first distance may be set by the user.

[0117] The above state change may refer to the difference between a previous state and a current state. For example, the state change may refer to the difference between a first coordinate corresponding to the previous state and a first coordinate corresponding to the current state. For example, the state change may refer to the difference between the initial state and the first transformed state. For example, the state change may refer to the difference between a second transformed state and the first transformed state.

[0118] For example, the method for determining the difference may utilize the compensation value. For example, the method for determining the difference may utilize a change in the compensation value.

[0119] If the compensation value corresponding to the second conversion state becomes greater than the compensation value corresponding to the first conversion state, the state change may increase. If the compensation value corresponding to the second conversion state becomes smaller than the compensation value corresponding to the first conversion state, the state change may decrease.

[0120] If the state change is lower than the reference value, the second transformation state may be converted to a third transformation state based on the feature. If the state change is lower than the reference value, the transformation process of converting to a transformation state based on the feature may be repeated. For example, the transformation process may be repeated approximately N times. For example, based on the transformation process, the initial state may be converted to an Nth transformation state.

[0121] If the state change is greater than or equal to a reference value, the transformed tooth data may be generated. For example, if the state change is greater than or equal to a reference value in the Nth transformed state, the transformed tooth data may be generated based on the Nth transformed state. The reference value may be set by the user.

[0122] For example, the method for determining the difference can utilize the behavior. For example, the method for determining the difference can utilize a change in the behavior. For example, if the change in the behavior decreases, the state change can decrease. If the change in the behavior increases, the state change can increase.

[0123] The above features may be points, lines, surfaces, planes, regions, or solids representing the characteristics of the three-dimensional oral cavity data (EAD). For example, the features may be set by the user. For example, the features may be set using anatomical features of the oral cavity.

[0124] For example, the feature may be the occlusal plane (OSP). The occlusal plane (OSP) may refer to a plane on which the occlusal surface of a tooth is located. For example, the occlusal plane (OSP) may be a curved surface for satisfying the occlusion of teeth. The occlusal plane (OSP) may be set by a user based on the three-dimensional oral data (EAD). For example, when the three-dimensional oral data (EAD) includes individual tooth data and / or abutment tooth data, the occlusal plane (OSP) may be determined based on the individual tooth data and / or abutment tooth data.

[0125] For example, the feature may be the median plane (MSP). The median plane (MSP) may refer to the center plane of the three-dimensional oral data (EAD). For example, the median plane (MSP) may refer to the exact center plane of the three-dimensional oral data (EAD). The median plane (MSP) may refer to the center plane of the three-dimensional tooth data (DD) and the transformed state. For example, the median plane may refer to the exact center plane of the three-dimensional tooth data (DD) and the transformed state.

[0126] For example, the feature may be the incisal papilla (IP). The incisal papilla (IP) may refer to a protruding point located at the periphery of the median plane (MSP) in the three-dimensional maxillary data (MAXD).

[0127] For example, the feature may be the maxillary tubercle (HN). The maxillary tubercle (HN) may refer to an area located in the three-dimensional maxillary data (MAXD). For example, the maxillary tubercle (HN) may refer to an area protruding behind the maxillary molars in terms of dental anatomy.

[0128] For example, the feature may be the retrooral prominence (RP). The retrooral prominence (RP) may refer to an area located in the three-dimensional mandibular data (MAND). For example, the retrooral prominence (RP) may refer to an area protruding behind the mandibular molars in terms of dental anatomy.

[0129] For example, the feature may be the border line (BL). The border line (BL) may refer to an area in the 3D oral cavity data (EAD) where the transformed tooth data should be aligned. For example, the border line (BL) may be a closed line that represents the boundary between the gums in front and the hard palate and soft palate in back in terms of dental anatomy.

[0130] For example, the feature may be shape data of the wax-rim (WXR). The shape data of the wax-rim (WXR) may be scan data of a shape for tooth placement.

[0131] FIG. 10 is a diagram showing transformed tooth data (CTD) generated according to a method for automatically aligning dentures from the three-dimensional oral data (EAD) of FIG. 1.

[0132] Referring to FIGS. 1, 2, and 10, in the present embodiment, a transformed tooth data (CTD) can be generated based on a method for automatically aligning dentures from the three-dimensional oral cavity data (EAD) of FIGS. 1 and 2. In addition, a denture can be generated based on the transformed tooth data (CTD).

[0133] In this way, dentures can be automatically aligned from the three-dimensional oral data (EAD), thereby shortening the denture manufacturing time and process and improving the quality of the dentures.

[0134] In addition, since at least one of the step (S510) of determining the initial state of the 3D dental data (DD) in the step (S500) of converting the 3D dental data (DD) using the feature, the step (S530) of determining the behavior of the initial state, the step (S550) of converting the initial state into a converted state based on the behavior, the step (S570-1) of determining a compensation value based on the converted state and restrictions, and the step (S590A) of determining whether the state change of the converted state is greater than or equal to a reference value is performed using an artificial intelligence neural network, the denture manufacturing time and process can be shortened, and the quality of the denture can be improved. In addition, a denture more suitable for the 3D oral data (EAD) can be created.

[0135] Fig. 11 is a flowchart showing an example of converting the 3D tooth data of Fig. 1.

[0136] The method for automatically aligning dentures from three-dimensional oral data (EAD) according to the present embodiment is substantially the same as the method for automatically aligning dentures from three-dimensional oral data (EAD) of FIGS. 1 to 10, except that the step (S500) of converting the three-dimensional dental data (DD) using the feature further includes the step (S580) of updating an artificial neural network and the step (S590B) of determining whether a change in the artificial neural network is greater than a reference change. Therefore, the same reference numbers are used for the same or similar components, and redundant descriptions are omitted.

[0137] In this embodiment, the artificial intelligence neural network can be updated based on the reward value and the action. For example, the artificial intelligence neural network can learn using the reward value and the action. The reward value can change based on the learning of the artificial intelligence neural network. The weights can change based on the learning of the artificial intelligence neural network. Since the artificial intelligence neural network can learn, a denture more suitable for the 3D oral cavity data (EAD) can be created. In addition, the denture manufacturing time and process can be further shortened.

[0138] According to the learning of the artificial intelligence neural network, the artificial intelligence neural network may change. If the change of the artificial intelligence neural network is greater than or equal to a reference change, the artificial intelligence neural network may terminate learning. If the change of the artificial intelligence neural network is lower than the reference change, the action of the first transformation state may be determined. For example, the reference change may be set by a user. For example, the change of the artificial intelligence neural network may be determined based on a reward value corresponding to the first transformation state or a sum of reward values ​​corresponding to the Nth transformation state.

[0139] Fig. 12 is a flowchart illustrating an example of a method for automatically aligning dentures from three-dimensional oral data (EAD) according to one embodiment of the present invention. Fig. 13 is a diagram illustrating the deletion data (DL) of Fig. 12.

[0140] The method for automatically aligning dentures from three-dimensional oral data (EAD) according to the present embodiment is substantially the same as the method for automatically aligning dentures from three-dimensional oral data (EAD) of FIGS. 1 to 10, except that it further includes a step (S200) of deleting the individual tooth data and the abutment tooth data of the three-dimensional oral data (EAD), and therefore, the same reference numbers are used for the same or similar components, and redundant descriptions are omitted.

[0141] In this embodiment, the individual tooth data and the abutment data of the three-dimensional oral cavity data (EAD) can be deleted. For example, the individual tooth data and the abutment data can be referred to as deleted data (DL). Since the individual tooth data and the abutment data can be deleted, the accuracy of the three-dimensional oral cavity data (EAD) can be further improved. Accordingly, the quality of the denture can be further improved. In addition, the denture manufacturing time and process can be shortened.

[0142] In one embodiment, the feature may be the location of the deleted data (DL).

[0143] In one embodiment, a computer-readable recording medium having recorded thereon a program for executing a method for automatically aligning dentures from three-dimensional oral data (EAD) according to the above embodiments on a computer may be provided. The above-described method can be written as a computer-executable program and implemented in a general-purpose digital computer that executes the program using the computer-readable medium. In addition, the structure of data used in the above-described method can be recorded on a computer-readable medium through various means. The computer-readable medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the medium may be those specially designed and configured for the present invention or may be known and usable by those skilled in the art in the field of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program instructions include not only machine language codes, such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention.

[0144] Additionally, the method for automatically aligning dentures from the aforementioned three-dimensional oral data (EAD) can also be implemented in the form of a computer program or application executed by a computer and stored in a recording medium.

[0145] The present invention relates to a method for automatically aligning dentures to three-dimensional oral data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, which can reduce the effort and time required for manufacturing dentures and improve the accuracy and productivity of dentures.

[0146] Although the present invention has been described with reference to the above embodiments, it will be understood by those skilled in the art that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A step of receiving 3D oral data; A step of determining features of the above 3D oral data; Step of determining features of 3D tooth data; A step of converting the 3D dental data into a transformed state using the features and limitations of the 3D oral data; A step of determining a state change of the above conversion state; and A method for automatically aligning dentures to three-dimensional oral data, comprising the step of generating transformed tooth data by considering the above state change and reference value.

2. In the first paragraph, the step of converting to the conversion state is: A step of determining the initial state of the above 3D tooth data; A step of converting the initial state into a first transformed state based on the feature of the three-dimensional oral data; and A method for automatically aligning dentures to three-dimensional oral data, characterized by comprising a step of determining a compensation value using the first transformation state and the restrictions.

3. In the second paragraph, the step of converting to the conversion state is: A method for automatically aligning dentures to three-dimensional oral data, characterized in that it further includes a step of determining whether the state change of the first conversion state is greater than or equal to the reference value.

4. In the third paragraph, the step of converting to the conversion state is: A method for automatically aligning dentures to three-dimensional oral data, characterized in that it further comprises a step of converting the first conversion state into a second conversion state based on the feature of the three-dimensional oral data when the state change of the first conversion state is lower than the reference value.

5. In the third paragraph, the step of converting to the conversion state is: A method for automatically aligning dentures to three-dimensional oral data, characterized in that when the state change of the first conversion state is greater than or equal to the reference value, the first conversion state is the converted tooth data.

6. A method for automatically aligning dentures to three-dimensional oral data, characterized in that the change in state is a change in the compensation value in the third paragraph.

7. A method for automatically aligning dentures to three-dimensional oral data, characterized in that the state change in the third paragraph is a difference between the initial state and the first transformed state.

8. In the second paragraph, the compensation value is a value based on the weight and the satisfaction value, A method for automatically aligning dentures to three-dimensional oral data, wherein the above-mentioned satisfaction value is a value based on the first transformation state and the above-mentioned constraints.

9. A method for automatically aligning dentures to three-dimensional oral data, characterized in that, in the 8th paragraph, if the first transformation state is outside the constraints, the satisfaction value is 0.

10. A method for automatically aligning dentures to three-dimensional oral data, characterized in that in the 8th paragraph, the satisfaction value is changed based on the degree of satisfaction, which is the difference between the first transformation state and the constraints.

11. In paragraph 2, A method for automatically aligning dentures to three-dimensional oral data, characterized in that it further includes a step of terminating learning when the change in the above compensation value is greater than or equal to the reference change.

12. In the second paragraph, the compensation value is determined based on whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data, A method for automatically aligning dentures to three-dimensional oral data, characterized in that whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data is determined based on the angular difference between the normal vector of the median plane of the first transformation state and the normal vector of the median plane of the three-dimensional oral data.

13. In the 12th paragraph, the compensation value is a value obtained by multiplying the weight and the satisfaction value, The above satisfaction value is [Second Formula] (Here, means the above satisfaction value, refers to the normal vector of the median plane of the above 3D oral data, A method for automatically aligning dentures to three-dimensional oral data, characterized in that the method is calculated using the normal vector of the median plane of the first transformation state.

14. In the second paragraph, the compensation value is determined based on whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data, A method for automatically aligning dentures to three-dimensional oral data, characterized in that whether the median plane of the first transformation state is similar to the median plane of the three-dimensional oral data is determined based on a distance from a point of the median plane of the first transformation state to the median plane of the three-dimensional oral data.

15. In the second paragraph, the compensation value is determined based on whether the occlusal plane of the first transformation state is similar to the occlusal plane of the three-dimensional oral data, A method for automatically aligning dentures to three-dimensional oral data, characterized in that whether the occlusal plane of the first transformation state is similar to the occlusal plane of the three-dimensional oral data is determined based on the angular difference between the normal vector of the occlusal plane of the first transformation state and the normal vector of the occlusal plane of the three-dimensional oral data.

16. In paragraph 15, the compensation value is a value obtained by multiplying the weight and the satisfaction value, The above satisfaction value is [Formula 4] (Here, means the above satisfaction value, refers to the normal vector of the occlusal plane of the above 3D oral data, A method for automatically aligning dentures to three-dimensional oral data, characterized in that the method is calculated using the normal vector of the occlusal plane of the first transformation state.

17. In the second paragraph, the compensation value is determined based on whether the first conversion state is located within the border line, A method for automatically aligning dentures to three-dimensional oral data, characterized in that whether the first transformation state is located within the border line is determined based on whether the first transformation state is located around the border line of the three-dimensional oral data.

18. In the second paragraph, the compensation value is determined based on whether the first conversion state is similar to the shape of the wax-rim, A method for automatically aligning dentures to three-dimensional oral data, characterized in that whether the first transformation state is similar to the shape of the wax-rim is determined using the average distance between the position data of the first transformation state and the shape data of the wax-rim.

19. In the first paragraph, the three-dimensional tooth data includes three-dimensional single tooth data, A method for automatically aligning dentures to 3D oral data, characterized in that the 3D single tooth data is converted into transformed single tooth data based on the feature.

20. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 19 on a computer.

Images