Method, apparatus, system, and computer program for manufacturing customized oral appliance for improving sleep disorders through 3D modeling

Abstract

Disclosed is a method for 3D modeling a customized oral appliance for improving sleep disorders according to various embodiments of the present invention. The method comprises the steps of: generating a dental model including an upper jaw model and a lower jaw model; generating contour information on the basis of the dental model; generating a plurality of part models on the basis of the contour information; and generating an oral device model by integrating the plurality of part models.

Description

Method, device, system, and computer program for manufacturing a customized oral device for improving sleep disorders through 3D modeling

[0001] Various embodiments of the present invention relate to a method for providing a user-customized oral device, and more specifically, to a method for 3D modeling and manufacturing a customized oral device for improving sleep disorders.

[0002] Sleep is an essential element of human health and well-being, and deep sleep, in particular, is a crucial time for physical recovery and mental stability. However, sleep disorders are becoming increasingly common in modern society, and among them, snoring and sleep apnea are having a serious impact on many people. These sleep disorders not only degrade the quality of sleep but can also lead to various health problems in the long term, such as cardiovascular disease, hypertension, and diabetes.

[0003] Snoring and sleep apnea primarily occur due to the narrowing of the airway. When airflow is obstructed by airway stenosis, recurrent hypoxia occurs during sleep. This condition reduces sleep depth, which can lead to persistent fatigue and daytime drowsiness. Furthermore, if hypoxia persists for a long period, it can lead to serious complications.

[0004] There are two main conventional methods for treating sleep disorders. The first method involves using a CPAP machine to forcibly push air into a narrowed airway. This method is effective in preventing sleep apnea by maintaining a continuous air supply to prevent airway obstruction. However, this method requires users to wear the device continuously, and many users find it uncomfortable to use for extended periods. Furthermore, the need for equipment maintenance and repeated hospital visits places a financial and time burden on patients.

[0005] The second method involves utilizing oral devices that users can wear while sleeping. This is a non-invasive approach that secures the airway and facilitates smooth breathing by wearing the device during sleep. Oral devices are widely used as a relatively simple and safe method that can be used without surgery. However, since existing oral devices are generally manufactured in standardized forms, there are concerns that they may not perfectly fit individual users' oral structures or dental conditions, potentially causing discomfort or limiting treatment effectiveness.

[0006] Accordingly, efforts to provide customized oral appliances are ongoing; however, the production of such devices requires advanced technical expertise, leading to increased costs. In other words, the high cost and complex manufacturing processes make it difficult for many users to easily access these devices. Consequently, there is a continuing need for technology capable of efficiently designing and manufacturing customized appliances suitable for each user.

[0007] (Prior Art Literature)

[0008] (Patent Literature)

[0009] Republic of Korea Published Patent Application No. 10-2019-0065793 (June 12, 2019)

[0010] The problem that the present invention aims to solve is to provide a 3D modeling method that can efficiently and economically design and manufacture a user-customized oral device, which has been devised in response to the aforementioned background technology.

[0011] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below.

[0012] A 3D modeling method for a customized oral device for improving sleep disorders according to an embodiment of the present invention for solving the above-mentioned problem is disclosed. The method may include the steps of generating a tooth model including an upper jaw model and a lower jaw model, generating contour information based on the tooth model, generating a plurality of part models based on the contour information, and integrating the plurality of part models to generate an oral device model.

[0013] In an alternative embodiment, the step of generating the contour information may include the step of generating a master model by applying a clearance distance corresponding to each of a plurality of regions of the tooth model, the step of generating basic contour information based on the master model, and the step of generating the contour information by correcting the master model based on the basic contour information.

[0014] In an alternative embodiment, the clearance distance is set to allow for pressure dispersion and a predetermined movement, and is characterized by being determined differently for each region based on the anatomical characteristics of the tooth, interaction with surrounding structures, and physical characteristics of the individual tooth, and the step of generating the basic contour information may include the step of identifying a plurality of predefined regions in the tooth model, the step of calculating a clearance distance for each region corresponding to each of the plurality of regions, the step of applying the calculated clearance distance for each region to each of the plurality of regions, and the step of performing surface treatment corresponding to the region to which the clearance distance is applied.

[0015] In an alternative embodiment, the step of generating the contour information comprises generating mandibular advancement amount information based on oral data and generating the contour information by adjusting the relative position between the maxilla and mandible of the master model based on the generated mandibular advancement amount information, wherein the oral data is information regarding the user's oral condition and may include impression result data and jaw movement video data.

[0016] In an alternative embodiment, the step of generating the plurality of part models may include generating a first part model corresponding to the maxillary model based on the contour information and generating a second part model corresponding to the mandibular model based on the contour information.

[0017] In an alternative embodiment, the first part model and the second part model may be characterized by including at least one of a lingual space for securing an airway, a wing portion provided through a shape covering a tooth, and an open hole formed through a hole shape in one area for pressure dispersion.

[0018] In an alternative embodiment, the step of generating the oral device model may include the step of connecting the plurality of part models into one to generate an integrated model, the step of performing surface treatment on the integrated model, and the step of generating the oral device model by performing inner surface processing based on the contour information corresponding to the integrated model with the completed surface treatment.

[0019] In an alternative embodiment, the method further comprises the step of generating the oral device model by processing the tooth model as input to a deep learning model, wherein the deep learning model may be characterized as a neural network model pre-trained through a learning dataset composed of tooth models and oral device models of a plurality of users.

[0020] In an alternative embodiment, the method may further include the step of manufacturing an oral device model by outputting the generated oral device model.

[0021] According to another embodiment of the present invention, an apparatus for performing a 3D modeling method for a customized oral device for improving sleep disorders is disclosed. The apparatus includes a memory for storing one or more instructions and a processor for executing one or more instructions stored in the memory, and the processor can perform the 3D modeling method for a customized oral device for improving sleep disorders described above by executing one or more instructions.

[0022] According to another embodiment of the present invention, a computer program stored on a computer-readable recording medium is disclosed. The computer program is combined with a computer, which is hardware, to perform a 3D modeling method for a customized oral device for improving sleep disorders.

[0023] According to another embodiment of the present invention, a manufacturing system for a customized oral device for improving sleep disorders is disclosed through 3D modeling. The system includes a computing device for generating an oral device model and an output device for manufacturing by outputting the oral device model. The computing device may generate a tooth model including an upper jaw model and a lower jaw model, generate contour information based on the tooth model, generate a plurality of part models based on the contour information, and generate the oral device model based on the plurality of part models.

[0024] Other specific details of the present invention are included in the detailed description and drawings.

[0025] By accurately reflecting the individual user's oral structure and dental condition, the discomfort and limitations of effectiveness associated with existing standardized devices can be overcome. This allows for the provision of customized devices suitable for a diverse range of users, thereby increasing accessibility to sleep disorder treatment.

[0026] Additionally, the present invention can reduce manufacturing costs and time by automating the process of generating oral device models using deep learning models, and enables more efficient design and production. This can popularize user-customized devices and provide more people with the opportunity to be free from sleep disorders.

[0027] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0028] FIG. 1 is an exemplary diagram schematically illustrating a system for implementing a 3D modeling method for a customized oral device for improving sleep disorders related to one embodiment of the present invention.

[0029] FIG. 2 is an exemplary diagram showing a user wearing a customized oral device related to one embodiment of the present invention.

[0030] FIG. 3 is a hardware configuration diagram of a computing device that performs a 3D modeling method for a customized oral device for improving sleep disorders related to one embodiment of the present invention.

[0031] FIG. 4 illustrates a flowchart exemplarily showing a 3D modeling method for a customized oral device for improving sleep disorders related to one embodiment of the present invention.

[0032] FIG. 5 is an illustrative diagram for explaining a tooth model related to one embodiment of the present invention.

[0033] FIG. 6 is an illustrative diagram for explaining a master model generated in correspondence with a tooth model related to one embodiment of the present invention.

[0034] FIGS. 7 and FIGS. 8 are illustrative diagrams for explaining the process of setting a clearance distance corresponding to each region of a tooth related to an embodiment of the present invention.

[0035] FIG. 9 is an illustrative diagram for explaining the process of generating contour information related to one embodiment of the present invention.

[0036] FIG. 10 is an illustrative diagram for explaining the wing portion and lingual space related to one embodiment of the present invention.

[0037] FIG. 11 is an exemplary diagram of a customized oral device related to one embodiment of the present invention, viewed from various directions.

[0038] FIG. 12 is an exemplary diagram showing the process of generating an oral device model through a plurality of parts models related to one embodiment of the present invention.

[0039] FIG. 13 is an exemplary diagram showing the process of performing corrections on an integrated model related to one embodiment of the present invention.

[0040] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate an understanding of the invention. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0041] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0042] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0043] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0044] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be interpreted as moving out of the scope of the invention.

[0045] The description of the presented embodiments is provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Thus, the present invention is not limited to the embodiments presented herein. The present invention should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0046] In this specification, the term "computer" refers to any type of hardware device comprising at least one processor, and may be understood to include software configurations operating on said hardware device according to the embodiments. For example, the term "computer" may be understood to include smartphones, tablet PCs, desktops, laptops, and user clients and applications running on each of these devices, but is not limited thereto.

[0047] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0048] Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least some of each step may be performed on different devices.

[0049]

[0050] Figure 1 is an example diagram schematically illustrating a system for implementing a 3D modeling method for a customized oral device for improving sleep disorders.

[0051] As illustrated in FIG. 1, a system according to embodiments of the present invention may include a computing device (100), a user terminal (200), an external server (300), and a network (400). The components illustrated in FIG. 1 are exemplary, and additional components may exist or some of the components illustrated in FIG. 1 may be omitted. The computing device (100), the external server (300), and the user terminal (200) according to embodiments of the present invention may mutually transmit and receive data for a system according to embodiments of the present invention through the network (400).

[0052] A network (400) according to embodiments of the present invention can use various wired communication systems such as a Public Switched Telephone Network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a Local Area Network (LAN).

[0053] In addition, the network (400) presented here may use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0054] A network (400) according to embodiments of the present invention may be configured regardless of the mode of communication, such as wired or wireless, and may be configured as various communication networks, such as a Personal Area Network (PAN) or a Wide Area Network (WAN). Additionally, the network (400) may be a known World Wide Web (WWW) and may utilize wireless transmission technologies used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth. The technologies described in this specification may be used in other networks as well as the networks mentioned above.

[0055] According to an embodiment of the present invention, a computing device (100) (hereinafter referred to as 'computing device (100)') that performs a 3D modeling method for a customized oral device for improving sleep disorders can generate a customized oral device model based on the individual user's oral structure and tooth condition.

[0056] In an embodiment, the computing device (100) can acquire oral data related to the user's oral structure and tooth condition and can generate an oral device model based on the acquired oral data. For example, the computing device (100) can generate an oral device model optimized for the user's oral structure and tooth alignment based on 3D digital data (e.g., a tooth model) generated from the scan results of the user's impression result data. For another example, the computing device (100) may generate a tooth model using captured data of the user's teeth. The captured data may be acquired using an oral scanner or a camera of a user terminal (e.g., a smartphone), but is not limited thereto.

[0057] In the present invention, the oral device model may refer to a 3D model optimized for the user's oral structure and dental condition. Based on the oral device model, a customized oral device optimized for the user can be manufactured, and the device can be utilized to effectively improve the user's sleep disorder. Furthermore, the oral device model can be finely adjusted according to the user's oral condition, thereby improving the comfort of wearing the device and maximizing the therapeutic effect related to the sleep disorder.

[0058] According to an embodiment, the device may be physically fabricated through 3D printing based on an oral device model, and then the surface of the device may be smoothed through a polishing process. Subsequently, a customized oral device may be provided to the user after undergoing cleaning and inspection processes. This series of processes maximizes the precision and effectiveness of the customized oral device and can contribute to effectively improving the user's sleep disorders.

[0059] Referring to Fig. 2, the custom oral device can function by physically widening the narrowed airway by advancing the mandible. The finally produced custom oral device is worn by the user in the mouth while sleeping, thereby enabling smooth breathing by securing the airway and effectively improving disorders such as snoring or sleep apnea during sleep.

[0060] According to one embodiment of the present invention, a computing device (100) may be characterized by generating individual part models corresponding to the upper jaw and the lower jaw, respectively, and then integrating them to generate an integrated oral device model. Specifically, the computing device (100) first analyzes the user's oral structure to generate individual part models corresponding to the upper jaw and the lower jaw, respectively, and then combines these two part models to form a single integrated oral device model. Since the oral device model is generated as an integrated unit without separate parts for assembly, it has the advantage of high structural integrity, a low risk of damage or deformation during use, and easy maintenance.

[0061] In an embodiment, the computing device (100) of the present invention can adjust the placement distance between the upper and lower jaws based on the user's oral data, and can generate an optimized oral device model by precisely adjusting the positions of individual part models to correspond thereto.

[0062] Oral data may include various data related to the user's oral condition, such as data on the user's impression results, multiple oral image data captured from various angles of the oral structure, and video data of jaw movements. These data play a crucial role in designing customized oral appliance models for each user, thereby enabling the provision of a device optimized for each user's oral structure.

[0063] That is, the computing device (100) can design and generate an integrated oral device model by comprehensively analyzing the user's oral data and through precise placement of the upper and lower jaws and optimized positional adjustment between the part models. This improves the fit and durability of the customized oral device and allows for a higher effect in improving sleep disorders.

[0064] In addition, according to an embodiment of the present invention, in the process of generating an oral device model, by applying a clearance distance related to each user's oral structure and tooth alignment, pressure can be evenly distributed rather than concentrated on a specific area when worn. In particular, this clearance design is customized by taking into account the different oral structures and tooth alignments of each user, thereby optimizing the pressure applied to each tooth. As a result, there is less fatigue or discomfort even when wearing the device for a long period, and a natural and stable wearing state can be maintained even during sleep. Consequently, long-term therapeutic effects can be maintained while using the device, and a higher effect in improving sleep disorders can be expected. A detailed description regarding the 3D modeling method of a customized oral device for improving sleep disorders related to the present invention will be provided later with reference to FIGS. 4 to 13.

[0065] In the embodiment, only one computing device (100) in FIG. 1 is illustrated, but it will be obvious to those skilled in the art that more servers may also be included within the scope of the invention and that the computing device (100) may include additional components. That is, the computing device (100) may be composed of multiple computing devices. In other words, a set of multiple nodes may constitute the computing device (100).

[0066] According to one embodiment of the present invention, the computing device (100) may be a server that provides cloud computing services. More specifically, the computing device (100) may be a server that provides cloud computing services, which are a type of internet-based computing, where information is processed by another computer connected to the internet rather than the user's computer. The cloud computing service may be a service that stores data on the internet and allows users to access necessary data or programs anytime and anywhere via internet access without installing them on their own computers, and allows data stored on the internet to be easily shared and transmitted through simple operations and clicks. Furthermore, the cloud computing service may not only simply store data on a server on the internet but also allow users to perform desired tasks using the functions of applications provided on the web without installing separate programs, and may be a service that allows multiple people to work while sharing documents simultaneously. Additionally, the cloud computing service may be implemented in at least one form among IaaS (Infrastructure as a Service), PaaS (Platform as a Service), SaaS (Software as a Service), a virtual machine-based cloud server, and a container-based cloud server. That is, the computing device (100) of the present invention may be implemented in at least one form among the cloud computing services described above. The specific description of the aforementioned cloud computing service is merely an example and may include any platform for establishing the cloud computing environment of the present invention.

[0067] According to one embodiment of the present invention, a user terminal (200) may be a terminal associated with a user who wishes to access a computing device (100) to obtain analysis information regarding 3D modeling data (e.g., data regarding the oral structure of an individual user), such as a customized oral device model or an optimized device design plan. As an example, the user terminal (200) may be a terminal associated with a user (e.g., a dentist) who provides the design results of a customized oral device to a user (e.g., a patient). If the user terminal (200) is a terminal associated with a dentist who provides the design results of a customized oral device to a patient, the 3D modeling analysis information provided from the computing device (100) may be utilized as a medical assistance terminal for diagnosis and device design establishment. The user terminal (200) is equipped with a display so as to receive input from the user and provide output of any form to the user.

[0068] The user terminal (200) can transmit the stored patient's oral data to the computing device (100), and the computing device (100) can generate an analysis result or a customized oral device design based on the data and provide it to the user terminal (200).

[0069] In an embodiment, a user terminal (200) may refer to any form of entity(s) in a system having a mechanism for communicating with a computing device (100). For example, such a user terminal (200) may include a personal computer (PC), a notebook, a mobile terminal, a smartphone, a tablet PC, and a wearable device, and may include any type of terminal capable of connecting to a wired or wireless network. Additionally, the user terminal (200) may include any server implemented by at least one of an agent, an API (Application Programming Interface), and a plug-in. Additionally, the user terminal (200) may include an application source and / or a client application.

[0070] In one embodiment, an external server (300) may be connected to a computing device (100) via a network (400) and may provide various information and data necessary for the computing device (100) to perform a 3D modeling method of a user-customized oral device, or receive, store, and manage optimized oral device design data derived during the 3D modeling process. For example, the external server (300) may be a storage server separately provided outside the computing device (100), but is not limited thereto.

[0071] According to one embodiment of the present invention, an external server (300) may be a server that stores oral scan data, tooth alignment data, and related treatment plan data corresponding to a plurality of users. Specifically, the external server (300) may store and manage 3D scan data of the user's oral structure, orthodontic modeling data, and dental diagnostic findings or customized oral device design data regarding the same. As another example, the external server (300) may store the manufacturing history of oral devices and device usage progress data for each user, and may store treatment results linked thereto based on this. This information can be utilized to comprehensively review the user's entire treatment process and to continuously improve the design of an optimized customized oral device.

[0072] For example, the external server (300) may be at least one of a dental hospital server and an oral device manufacturer's server, and may be a server that stores information regarding the user's oral diagnostic data and the design of a customized oral device. Additionally, the external server (300) may be a server of an oral device-related research institution or a medical data management institution, and may play a role in managing and storing research results or device effect analysis data related to the user's oral data at such an institution.

[0073] The information stored in the external server (300) can be used as training data, verification data, and test data for training the artificial intelligence-based 3D modeling system of the present invention. That is, the external server (300) stores a data set for training the neural network model of the present invention, thereby improving the accuracy of oral device modeling and design. The computing device (100) of the present invention can acquire various oral data (or tooth data) from the external server (300), and build a training data set based thereon to develop an artificial intelligence model capable of generating a more precise customized oral device model.

[0074] The information stored in the external server (300) can be utilized as training data, verification data, and test data for training the neural network in the present invention. That is, the external server (300) may be a server that stores information regarding a data set for training the neural network model of the present invention. The external server (300) may store data for training the artificial intelligence model of the present invention. The computing device (100) of the present invention can acquire a plurality of medical data from the external server (300) and can construct a plurality of training data sets based on the acquired medical data. The computing device (100) can generate an artificial intelligence model by performing training using the data included in the training data sets.

[0075] The external server (300) is a digital device and may be a digital device equipped with a processor and memory, such as a laptop computer, notebook computer, desktop computer, web pad, or mobile phone. The external server (300) may be a web server that processes services. The types of servers described above are merely examples and the present invention is not limited thereto. Hereinafter, with reference to FIG. 3, the hardware configuration of a computing device (100) that performs a 3D modeling method for a customized oral device for improving sleep disorders will be described.

[0076] FIG. 3 is a hardware configuration diagram of a computing device that performs a 3D modeling method for a customized oral device for improving sleep disorders related to one embodiment of the present invention.

[0077] Referring to FIG. 3, a computing device (100) for performing a 3D modeling method for a customized oral device for improving sleep disorders related to one embodiment of the present invention may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, FIG. 2 only shows components related to the embodiment of the present invention. Therefore, a person skilled in the art to which the present invention pertains will understand that other general-purpose components may be included in addition to the components shown in FIG. 3.

[0078] According to one embodiment of the present invention, the processor (110) can typically handle the overall operation of the computing device (100). The processor (110) can provide or process appropriate information or functions to a user or user terminal by processing signals, data, information, etc. that are input or output through the components described above, or by running an application program stored in memory (120).

[0079] Additionally, the processor (110) can perform operations for at least one application or program for executing the method according to embodiments of the present invention, and the computing device (100) may have one or more processors.

[0080] According to one embodiment of the present invention, the processor (110) may be composed of one or more cores and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device.

[0081] A processor (110) can read a computer program stored in memory (120) and perform data processing for an artificial intelligence model according to one embodiment of the present invention. According to one embodiment of the present invention, the processor (110) can perform calculations for learning a neural network. The processor (110) can perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation.

[0082] Additionally, the processor (110) may be capable of processing the learning of a network function using at least one of a CPU, a GPGPU, and a TPU. For example, a CPU and a GPGPU may work together to process the learning of a network function and data classification using the network function. Additionally, in one embodiment of the present invention, processors of a plurality of computing devices may be used together to process the learning of a network function and data classification using the network function. Furthermore, a computer program executed in a computing device according to one embodiment of the present invention may be a CPU, GPGPU, or TPU executable program.

[0083] In this specification, the network function may be used interchangeably with artificial neural networks and neural networks. In this specification, the network function may include one or more neural networks, and in this case, the output of the network function may be an ensemble of the outputs of one or more neural networks.

[0084] The processor (110) can read a computer program stored in memory (120) and provide a deep learning model according to one embodiment of the present invention. According to one embodiment of the present invention, the processor (110) can perform calculations to train the deep learning model.

[0085] According to one embodiment of the present invention, the processor (110) can typically handle the overall operation of the computing device (100). The processor (110) can provide or process appropriate information or functions to a user or user terminal by processing signals, data, information, etc. that are input or output through the components described above, or by running an application program stored in memory (120).

[0086] Additionally, the processor (110) can perform operations for at least one application or program for executing the method according to embodiments of the present invention, and the computing device (100) may have one or more processors.

[0087] In various embodiments, the processor (110) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (110). Additionally, the processor (110) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0088] Memory (120) stores various data, instructions and / or information. Memory (120) may load a computer program (151) from storage (150) to execute a method / operation according to various embodiments of the present invention. When the computer program (151) is loaded into memory (120), the processor (110) may perform the method / operation by executing one or more instructions constituting the computer program (151). Memory (120) may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0089] The bus (130) provides communication functions between components of the computing device (100). The bus (130) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0090] The communication interface (140) supports wired and wireless internet communication of the computing device (100). Additionally, the communication interface (140) may support various communication methods other than internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the art of the present invention. In some embodiments, the communication interface (140) may be omitted.

[0091] Storage (150) can store computer programs (151) non-temporarily. When performing a process for 3D modeling of a customized oral device for sleep disorder personality through a computing device (100), storage (150) can store various information necessary to provide a process for 3D modeling of a customized oral device for sleep disorder personality.

[0092] The storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0093] A computer program (151) may include one or more instructions that cause a processor (110) to perform a method / operation according to various embodiments of the present invention when loaded into memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0094] In one embodiment, the computer program (151) may include one or more instructions for performing a 3D modeling method for a customized oral device for improving sleep disorders, the steps of generating a tooth model including an upper jaw model and a lower jaw model, generating contour information based on the tooth model, generating a plurality of part models based on the contour information, and generating an oral device model based on the plurality of part models.

[0095] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0096] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present invention may be executed as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as a combination of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors. Hereinafter, with reference to FIGS. 4 through 13, a method for 3D modeling of a customized oral device for improving sleep disorders performed by a computing device (100) will be described in detail.

[0097]

[0098] FIG. 4 illustrates a flowchart exemplifying a 3D modeling method for a customized oral device for improving sleep disorders related to an embodiment of the present invention. The steps illustrated in FIG. 4 may be changed in order as necessary, and at least one step may be omitted or added. That is, the following steps are merely an embodiment of the present invention, and the scope of the present invention is not limited thereto.

[0099] According to one embodiment of the present invention, a 3D modeling method for a customized oral device for improving sleep disorders may include the step of acquiring oral data for generating a tooth model.

[0100] In the embodiments, oral data may include various data related to the user's oral structure and tooth condition. For example, oral data may include the user's impression result data, 3D scan data, tooth alignment information, and jaw movement video data, but is not limited thereto.

[0101] Specifically, the impression result data is a digital conversion of physical impression data that accurately replicates the user's oral structure, and provides basic data for 3D modeling by accurately reflecting the shape, size, and arrangement of the teeth.

[0102] 3D scan data is a three-dimensional digital image generated by scanning a user's oral structure from various angles. It provides more precise structural information than impression data and can include the detailed shapes of teeth and gums. This allows for the accurate modeling of the interrelationship between teeth and surrounding tissues.

[0103] Tooth alignment information is data indicating the position and arrangement status of each tooth; it plays a crucial role in analyzing the occlusal state and interactions between teeth, and helps oral appliances be designed to fit the tooth alignment so that they can perform effective functions.

[0104] Jaw movement video data is footage recording the motion of a user's jaw as it moves, and it can be utilized to analyze the dynamic relationship between the mandible and the maxilla. Jaw movement video data plays a crucial role in improving the stability and comfort of oral appliances by considering jaw movements during design to ensure natural operation while worn, and by accurately reflecting the user's occlusal force and range of motion.

[0105] These oral data provide essential information for the computing device (100) to precisely design a user-customized oral device model and contribute to creating a device optimized for improving sleep disorders.

[0106] In one embodiment, the acquisition of oral data may involve receiving or loading data stored in memory (120). The acquisition of oral data may involve receiving or loading oral data from another storage medium, another computing device, or a separate processing module within the same computing device based on wired or wireless communication means. For example, a user may connect to a computing device (100) through a user terminal (200) and receive a user interface related to the acquisition of oral data from the computing device (100), and may transfer oral data to the computing device (100) by dragging and dropping oral data onto the provided user interface. As another example, the computing device (100) may be linked with an external server (300) to automatically retrieve oral data stored in the external server (300), or allow the user to transmit specific oral data to the external server (300) for storage. Through this, the acquisition of oral data can be made more efficient and automated, and the user can easily manage and utilize the data.

[0107] According to one embodiment of the present invention, a 3D modeling method for a customized oral device for improving sleep disorders may include the step (S100) of generating a tooth model including an upper jaw model and a lower jaw model.

[0108] In the embodiment, the tooth model is a 3D model that accurately reflects the user's oral structure and tooth arrangement, and can accurately represent the entire oral structure by including individual models corresponding to the upper and lower jaws, respectively.

[0109] In one embodiment, a computing device (100) can generate a tooth model based on impression result data. Impression result data refers to physical impression data that accurately replicates the user's oral structure and is converted into digital form, which can accurately reflect the shape, size, and position of the teeth. For example, plaster is poured into the impression result corresponding to the user to create a plaster stone, and by digitizing it and converting it into a 3D model, the user's oral structure can be precisely reproduced. In an embodiment, high-resolution digital data, i.e., impression result data, can be obtained from the impression result through a process of performing scanning or image processing. In this process, the physical impression result is converted into a highly precise 3D shape, and data including the fine structure and surface details of the teeth is generated. Through this, a digitized 3D model is generated and can subsequently be used as basic data for designing a customized oral device model.

[0110] Additionally, in an embodiment, the computing device (100) can generate a tooth model based on a plurality of oral images taken from multiple angles. For example, a user utilizes a user terminal to go through a procedure of taking pictures of their oral condition from various angles through a user interface provided by the computing device (100), thereby obtaining a plurality of oral images. These oral images are used as data to precisely determine the arrangement of teeth and the relationship between the upper and lower jaws.

[0111] According to one embodiment, if there is a lack of necessary data or if the image of a specific part is insufficient during the process of acquiring oral images, the computing device (100) may guide the user to take steps to acquire additional images. By doing so, additional oral images that are needed can be supplemented to generate a more accurate and complete tooth model.

[0112] More specifically, the computing device (100) can analyze multiple acquired oral image data to evaluate the quality and completeness of the images. The computing device (100) can check whether each image was captured clearly, whether all teeth and oral structures are clearly identifiable, and whether important information regarding specific parts of the oral cavity or tooth arrangement is missing. If the image of a specific part is unclear or if part of an important oral structure is not captured, the computing device (100) can automatically identify the area and determine that additional image capture is necessary.

[0113] Additionally, the computing device (100) provides a user interface that includes information clearly explaining to the user the area requiring additional imaging and the reason for such imaging. The user interface provides the user with specific imaging instructions, such as the imaging angle and specific locations inside the oral cavity. The user can additionally image the insufficient area according to the instructions provided through the user interface and transmit the images to the computing device (100).

[0114] Through this process, the computing device (100) can fully obtain all necessary oral images and, based on this, generate a more accurate and precise tooth model. This precise tooth model is used as basic data for designing oral devices and plays an important role in providing a customized oral device optimized for the user.

[0115] The computing device (100) can accurately reproduce the fine structure and arrangement state of the teeth by acquiring a plurality of oral images in this manner and converting them into a 3D model based on the acquired plurality of oral images.

[0116] In an embodiment, the tooth model (10) may include an upper jaw model (11) and a lower jaw model (12), as shown in FIG. 5. FIG. 5 is an illustrative diagram for explaining a tooth model related to an embodiment of the present invention.

[0117] The tooth model (10) can accurately reflect the user's oral structure and represent the accurate occlusal relationship between the upper and lower jaws. In addition, the tooth model (10) can reproduce the position, size, and relationship of each tooth with the surrounding periodontal tissues.

[0118] In various embodiments, the computing device (100) may generate a tooth model (10) in which the positional relationship between the upper and lower jaws is adjusted by reflecting the amount of lower jaw advancement for the user, but is not limited thereto.

[0119] According to one embodiment of the present invention, a 3D modeling method for a customized oral device for improving sleep disorders may include a step (S200) of generating contour information based on a tooth model.

[0120] In one embodiment, the step of generating contour information may include the step of generating a master model by applying a clearance distance corresponding to each of a plurality of regions of the tooth model (10), the step of generating basic contour information based on the master model, and the step of generating contour information by correcting the master model based on the basic contour information. According to one embodiment, the master model (20) is generated corresponding to the tooth model (10), and as shown in FIG. 6, it may include a first master sub-model (21) corresponding to the maxillary model (11) and a second master sub-model (22) corresponding to the mandibular model (12).

[0121] In the embodiment, the clearance distance is set to allow for pressure dispersion and a predetermined movement, and may be characterized by being determined differently by region based on the anatomical characteristics of the tooth, interaction with surrounding structures, and physical characteristics of individual teeth.

[0122] In the embodiment, the basic contour information is generated based on the contour of the master model created by applying a clearance distance to the tooth model corresponding to the user.

[0123] Contour information is generated by adjusting the placement distance between the maxilla (i.e., the first master sub-model) and mandible (i.e., the second master sub-model) of the master model based on basic contour information, and is utilized to design an oral device that enables smooth breathing during the user's sleep by focusing particularly on advancing the mandible to secure the airway.

[0124] In one embodiment, the contour information (or basic contour information) does not directly represent the physical thickness or volume of the oral device and may consist of linear data defined along the outline of the master model. That is, rather than representing the structural elements of the actual oral device, the contour information is a virtual contour used to define the shape of the device and can serve as a basic baseline for the optimal placement of the maxilla and mandible during the design phase.

[0125] More specifically, the computing device (100) analyzes the characteristics of each tooth and surrounding tissue to identify areas where clearance is required or appropriate. This prevents excessive pressure from being concentrated on specific teeth, thereby minimizing discomfort when wearing the device and allowing for natural movement of the teeth and gums. Based on these analysis results, the computing device (100) can generate a master model and, based on this, optimize the positions of the upper and lower jaws to generate contour information.

[0126] In a specific embodiment, the step of generating basic contour information may include identifying a plurality of predefined regions in a tooth model, calculating a region-specific clearance distance corresponding to each of the plurality of regions, applying the calculated region-specific clearance distance to each of the plurality of regions, and performing surface treatment corresponding to the regions to which the clearance distance is applied.

[0127] The computing device (100) can first form a gap (e.g., a basic gap) in the basic tooth and gum structure to facilitate the removal of the oral device, then identify a predefined area, and provide an appropriate gap to each identified area.

[0128] In the embodiment, the predefined area may be set as a plurality of areas for each of the upper and lower jaws, and may be an area defined to maximize comfort and functionality when wearing the oral device.

[0129] In one embodiment, for the mandible, the predefined area may include a first area corresponding to the contact surface of the mandibular anterior teeth and a second area corresponding to the contact surface of the mandibular molars. The first area is a region where pain is likely to occur when wearing the device, and a relatively large clearance is provided to distribute pressure. The second area is the contact surface of the mandibular molars, and a clearance is applied to allow for a small range of movement.

[0130] In one embodiment, for the maxilla, the predefined areas may include a third area corresponding to the maxillary anterior teeth, a fourth area corresponding to the maxillary molar contact surface, a fifth area corresponding to the maxillary outer side, and a sixth area corresponding to the outer surface of the anterior teeth. For a specific example, referring to FIG. 7, the third area (10a) related to the maxillary anterior teeth is the area most likely to cause pain, and a clearance is provided to minimize discomfort when worn. The fourth area (10b) related to the maxillary molar contact surface is an area where strong bite force is applied and there is a high possibility of damage to the oral device, and a clearance is set to prevent damage. Referring to FIG. 8, the fifth area (10c) and the sixth area related to the maxillary outer side and the outer surface of the anterior teeth are areas that may get caught when removing the oral device, and an appropriate clearance is provided to facilitate removal.

[0131] According to the embodiment, the clearance distance is set to different sizes depending on the predefined area, which is intended to maximize comfort and functionality when wearing the oral device.

[0132] For a specific example, the area designated as the first zone in the mandible is the region where it meets the mandibular anterior teeth, an area highly likely to cause pain when wearing the device. A first clearance, which is the largest clearance, is applied to this area to prevent pressure from concentrating there and to minimize discomfort during wear. The second zone of the mandible corresponds to the interface of the mandibular molars; as this area requires a small range of movement, a second clearance, which is of medium size, is applied. Since inter-tooth interaction is important in this region, providing an appropriate clearance allows for movement while maintaining the stability of the device.

[0133] In the case of the maxilla, the maxillary anterior region, designated as the third zone, is an area with a very high potential for pain; therefore, the first clearance distance—the largest among all regions—is applied. This ensures that pressure is evenly distributed, improving comfort and minimizing discomfort even during prolonged use. The maxillary molar interface, designated as the fourth zone, is the area subjected to the strongest bite force and is highly susceptible to breakage of the oral appliance. A second clearance distance, of medium size, is applied to this area to prevent breakage and enhance the durability of the appliance.

[0134] In addition, the outer side of the maxilla (region 5) and the outer surface of the anterior teeth (region 6) are areas that may get caught when removing the oral appliance, and a relatively small clearance, known as a third clearance, may be provided to these areas. This small clearance reduces friction that may occur during the process of putting on and taking off the appliance, thereby helping the appliance to be easily removed.

[0135] In this way, by setting the clearance distance for each area by relatively comparing them, the computing device (100) can design the oral device in a form optimized for the user. By providing a larger clearance in areas requiring a large clearance, a medium clearance in areas where stability and durability are important, and a small clearance in areas where easy removal is required, it is possible to provide a stable fit with minimal discomfort even during long-term wear. This clearance setting also increases the durability of the device, minimizes damage that may occur during use, and maximizes the therapeutic effect by ensuring that the device adheres properly to the teeth and gums.

[0136] In various embodiments, the computing device (100) may acquire various oral data from a user terminal and apply additional corrections to the clearance distance corresponding to each area based thereon. These additional corrections are made to provide an optimal fit by reflecting the user's oral characteristics and individual requirements.

[0137] First, the computing device (100) collects various oral data, such as the user's impression results, tooth sensitivity, occlusal force, gum condition, and jaw movement video information. The impression results provide information that allows for precise identification of the user's tooth structure and alignment status, while tooth sensitivity and gum condition can be obtained through survey data or clinical records. Occlusal force and jaw movement video information are collected by analyzing the force and pattern when the user bites or moves their teeth.

[0138] Based on this data, the computing device (100) sets the clearance distance of each area initially, and then analyzes the collected data to calculate the degree of correction. Specifically, the computing device (100) can generate tooth sensitivity information, gum condition information, occlusal force information, and tooth structure information based on the acquired oral data, and can calculate an optimal correction value by analyzing the correlation between each piece of information.

[0139] In an embodiment, the computing device (100) can generate tooth sensitivity information and gum condition information based on clinical records and survey data obtained from a user. The tooth sensitivity information reflects the areas the user feels sensitive to and indicates how sensitive a specific tooth or gum is to pressure, and the gum condition information includes data that predicts how the gum will respond to pressure or device wearing, including gum thickness, health status, and the presence of inflammation.

[0140] Additionally, the computing device (100) can generate occlusal force information through a process of analyzing video information of the user's jaw movement and the occlusal state. The occlusal force information is data that measures the magnitude and direction of the force generated when the user bites the teeth, and evaluates the contact area between the upper and lower jaws, the balance of biting forces, and the interaction between teeth, and reflects this in the design of the oral device.

[0141] Additionally, the computing device (100) can generate tooth structure information through 3D scan data. The tooth structure information is information indicating the shape, size, and arrangement of each tooth, as well as the surface area of ​​the tooth and its relationship with surrounding tissues, and through this data, the oral device is designed to fit each tooth accurately.

[0142] According to one embodiment, the first clearance distance corresponding to the joint surface of the mandibular anterior teeth and the maxillary anterior teeth can be corrected based on the results of analyzing the user's tooth sensitivity information and gum condition information. The computing device (100) may apply additional correction to increase the determined clearance distance so that, in the case of a user with high tooth sensitivity, the pressure applied to the gums does not cause discomfort.

[0143] Additionally, in the embodiment, the second clearance distance corresponding to the maxillary molar contact surface can be corrected based on the user's occlusal force information and tooth structure information. The computing device (100) may apply additional correction to widen the clearance distance to mitigate impact between the teeth and the oral device in the case of a user with strong occlusal force. This contributes to reducing wear or damage that may occur when wearing the device and maintaining stable interaction between the user's teeth and the device. On the other hand, in the case of a user with weak occlusal force, the clearance distance is reduced to increase the degree of contact between the teeth and the device, thereby improving the wearing comfort and increasing the stability of the device.

[0144] Additionally, a third clearance distance corresponding to the outer side of the maxilla and the outer surface of the anterior teeth can be adjusted to facilitate the wearing and removal of the device. The computing device (100) analyzes jaw movement video information and adjusts the clearance distance to reduce friction that may occur when wearing and removing the oral device. In areas where excessive friction occurs, a small clearance distance is applied to alleviate friction and allow the device to be easily removed.

[0145] In this way, the computing device (100) can generate basic contour information by analyzing various oral data and performing additional corrections on the clearance distance determined corresponding to each area. The basic contour information is the result of applying additional corrections on customized clearances to each area by reflecting the user's tooth and gum structure, sensitivity, occlusal force, jaw movement, etc., thereby enabling the oral device to be designed in a state optimized for the user.

[0146] Additionally, in the embodiment, the computing device (100) may perform surface treatment corresponding to the area where the gap distance is applied. Surface treatment of the gap portion plays an important role in maximizing the wearing comfort of the oral device and preventing pressure from being concentrated on specific areas. In this process, the computing device (100) may smooth the surface of the gap portion or remove unnecessary protrusions so that the device is designed to adhere softly to the teeth and gums.

[0147] For example, the area with the gap needs to make softer contact with the teeth to distribute pressure. To this end, the computing device (100) applies a surface treatment technique, such as wrapping, to remove roughness or sharp edges from the surface of the device and to allow the device to be worn comfortably in the user's oral cavity. In particular, since the gap area must be designed to distribute pressure evenly when the device is worn, the surface treatment is corrected to improve the finish quality of the device and minimize discomfort even during long-term wear.

[0148] This surface treatment process ensures that the device adheres properly to the teeth and gums, reducing friction and irritation and contributing to the minimization of user discomfort. Consequently, the surface treatment can improve the overall fit of the oral device, increase its durability, and contribute to protecting the user's oral health.

[0149] Additionally, in an embodiment, the step of generating contour information may include the step of generating mandibular advancement amount information based on oral data and the step of generating the contour information by adjusting the relative position between the maxilla and mandible of a master model based on the generated mandibular advancement amount information. In an embodiment, the oral data may include impression result data and jaw movement video data, as information regarding the user's oral condition.

[0150] More specifically, the computing device (100) analyzes the impression result data to accurately determine the user's oral structure and tooth alignment status. In this process, the computing device (100) comprehensively analyzes the size, shape, and alignment status of each tooth, as well as the height and thickness of the gums and the relationship between the teeth and the gums, to precisely reproduce the user's oral structure as a 3D model.

[0151] Additionally, jaw movement video data provides important data for analyzing how the user's mandible moves. A computing device (100) precisely analyzes the range and pattern of the anterior-posterior, up-down, and left-right movements of the mandible through these videos. For example, when the user opens and closes their mouth, it is possible to determine how far the mandible moves forward, at what angle it moves, and how this movement interacts with the maxilla. These analysis results are used to accurately calculate the amount of mandibular advancement, which is an important factor in optimizing the user's airway.

[0152] The calculated mandibular advancement information plays a key role in adjusting the relative positions between the maxilla (i.e., the first master sub-model) and the mandible (i.e., the second master sub-model) of the master model. Based on the mandibular advancement information, the computing device (100) adjusts the positions of the maxilla and mandible so that they interlock with each other and maintain an optimal occlusal state while ensuring a smooth airway. Through this, the oral device is designed to sufficiently open the user's airway during sleep.

[0153] In an embodiment, the computing device (100) can generate contour information by reflecting mandibular advancement information in the basic contour information. That is, by determining the optimal arrangement between the maxilla and mandible of the master model by reflecting mandibular advancement information, the oral device can help provide appropriate space by moving the mandible forward to secure the airway.

[0154] Specifically, the computing device (100) analyzes jaw movement video data to calculate the amount of advancement of the mandible. In this process, the computing device (100) precisely tracks the movement pattern of the mandible when the user opens and closes the mouth. It analyzes how the mandible moves in the forward, backward, up and down, and left and right directions when the user moves the mandible, and specifically measures the distance of advancement of the mandible, which is important for securing the airway.

[0155] First, the computing device (100) calculates the maximum distance the mandible moves forward and measures the angle when the mandible is moved the farthest forward. To analyze how the user's mandible affects the airway at this position, the size and degree of change of the airway space are evaluated. For example, the airway is expanded when the mandible is advanced by 2 mm, and the effect of this expansion on the occlusal state of the maxilla and mandible is analyzed together.

[0156] Additionally, the computing device (100) analyzes through simulation how the efficiency of airway securing changes when the advancement of the mandible is excessively large or insufficient. By comparing the case where the mandible advances 1 mm and the case where it advances 3 mm, the degree of airway securing, the user's occlusal state, and the stress applied to the jaw joint are calculated in each situation. Through this, the computing device (100) calculates the optimal amount of mandibular advancement, and the calculated amount of mandibular advancement is adjusted to enable airway securing suitable for the user while minimizing discomfort during long-term wear.

[0157] For example, the computing device (100) analyzes the user's jaw movement video and confirms that the airway is maximized when the mandible advances by an average of 2.5 mm, and that the occlusion between the upper and lower jaws remains stable. On the other hand, it is also analyzed that if the mandible advances by more than 3 mm, excessive load may be placed on the jaw joint. Based on this, the computing device (100) sets the amount of mandible advance to 2.5 mm and incorporates this into the design of the oral device to maximize the user's airway and maintain the stability of the occlusion.

[0158] In this way, the computing device (100) accurately calculates the amount of advancement of the mandible based on the jaw movement video, thereby ensuring optimal airway security and comfort during wear.

[0159] In addition, in the embodiment, the computing device (100) is designed to prevent excessive advancement of the mandible so as not to strain the jaw joint. For example, if the amount of advancement of the mandible is too large, unnecessary stress may be applied to the jaw joint. Therefore, the computing device (100) can calculate the optimal amount of advancement by considering the user's jaw joint condition and muscle strength based on the analysis results of the jaw movement video data, and generate contour information based on this.

[0160] The computing device (100) analyzes data regarding the user's jaw joint and corrects the amount of mandibular advancement so that it does not exceed an appropriate range. At this time, the computing device (100) considers the muscle tension and joint movement patterns that occur when the user moves the jaw, and applies a design that minimizes unnecessary stress caused by mandibular advancement. For example, if advancement of more than 2.5 mm may strain the jaw joint, the computing device (100) takes this into account and sets an optimal value that limits the amount of mandibular advancement to 2.0 to 2.5 mm. Through this, the oral device is designed to maintain an appropriate amount of advancement for securing the airway, while ensuring that no unnecessary burden is placed on the jaw joint even during long-term wear. The specific numerical description of the mandibular advancement amount described above is merely an example, and the present invention is not limited thereto.

[0161] To summarize with reference to FIG. 9, the computing device (100) generates a master model (20) including a first master sub-model (21) and a second master sub-model (22) by applying a clearance distance corresponding to a plurality of regions corresponding to a tooth model (10) including an upper jaw model (11) and a lower jaw model (12), and can generate basic contour information based on the generated master model (20). Additionally, the computing device (100) can generate final contour information (30) by adjusting the relative position between the first master sub-model (21) and the second master sub-model (22) based on the basic contour information (i.e., adjusting by reflecting the lower jaw advancement amount information). In this process, the computing device (100) is designed so that the oral device is accurately fitted to each part by reflecting the user's individual oral structure and lower jaw advancement amount information. The final generated contour information is utilized as important basic data for the design of the oral device, thereby maximizing the user's airway and ensuring comfort when wearing the device.

[0162] In one embodiment, the computing device (100) can generate a master model (20) by combining the first master sub-model (21) and the second master sub-model (22) by reflecting mandibular advancement amount information during the process of combining the first master sub-model (21) and the second master sub-model (22).

[0163] In another embodiment, the computing device (100) can generate a tooth model (10) with positional relationships between the upper and lower jaws applied by reflecting information on the amount of lower jaw advancement in the user's tooth model (10), and then generate and combine a first master sub-model (21) and a second master sub-model (22) based on the tooth model (10) to generate a master model (20) with information on the amount of lower jaw advancement reflected.

[0164] According to one embodiment of the present invention, a 3D modeling method for a customized oral device for improving sleep disorders may include the step (S300) of generating a plurality of part models based on contour information.

[0165] The step of generating a plurality of part models may include the step of generating a first part model corresponding to an upper jaw model based on contour information and the step of generating a second part model corresponding to an lower jaw model based on contour information.

[0166] The contour information (or basic contour information) generated by the computing device (100) does not directly represent the physical thickness or volume of the oral device and may consist of linear data defined along the outer edge of the master model. That is, rather than representing the structural elements of the actual oral device, the contour information is a virtual contour used to define the shape of the device and can serve as a basic baseline for the optimal placement of the upper and lower jaws during the design phase.

[0167] According to an embodiment, the computing device (100) generates a first part model and a second part model based on generated contour information. In this process, the contour information acts as a virtual contour line applied to each region of the upper jaw model and the lower jaw model, thereby allowing the part models of the upper jaw and the lower jaw to be accurately defined.

[0168] In an embodiment, the computing device (100) can generate a first part model corresponding to the maxillary model based on contour information. In this step, an appropriate clearance is applied according to the tooth and gum structure of the maxilla, and this clearance plays an important role in determining the shape of the part model. The computing device (100) sets a virtual boundary along the outer edge of the maxillary model based on the contour information and defines the structure of the first part model along this boundary. At this time, each part of the part model is adjusted to match the anatomical characteristics of the maxilla and is designed to have an optimal thickness and volume by considering airway securing and occlusal conditions.

[0169] Additionally, the computing device (100) generates a second part model corresponding to the mandibular model. The process of generating the second part model is also performed based on contour information. The computing device (100) analyzes the tooth arrangement and gum condition of the mandibular model and generates a second part model corresponding to the mandibular model based on contour information generated along the outer edge of the mandibular model. In the case of the mandibular model, information on the amount of advancement is included, so the shape of the second part model can be adjusted in specific parts to maximize the airway securing effect due to the advancement of the mandibular model. For example, to minimize discomfort that may occur as the anterior teeth of the mandibular model move forward, the thickness and clearance of the corresponding area are adjusted, and the device is designed to be worn stably as a result.

[0170] In the embodiment, during the process in which the first part model and the second part model are each generated based on contour information, the thickness may be applied only outwardly to the outlines of the upper and lower jaws. The computing device (100) adjusts the process to enable actual production by applying an appropriate thickness to each part model based on contour information corresponding to the tooth model.

[0171] Specifically, the outlines of the upper and lower jaws are theoretically defined as surfaces with zero thickness, but thickness must be applied to the outlines for the actual fabrication of the oral device. At this time, the thickness is applied only to the outer side. This is to ensure that the oral device is designed to fit the teeth and gums accurately. If thickness is applied inwardly, that is, based on the contour information, the teeth may not be able to properly fit inside the device, making it impossible to wear the device. Therefore, to prevent this problem, the computing device (100) generates each part model by applying thickness only to the outer side of the outline.

[0172] The first part model and the second part model generated by the computing device (100) are digital models that reflect the structures of the upper and lower jaws, respectively, and are subsequently integrated to form a single integrated oral device model.

[0173] According to one embodiment, the first part model and the second part model may be characterized by including at least one of a lingual space for securing an airway, a wing portion provided through a shape covering a tooth, and an open hole formed through a hole shape in one area for pressure dispersion.

[0174] More specifically, referring to FIG. 10 (a), the wing portion (1200) may be provided in a shape that wraps around the teeth on the side of the oral device. The wing portion (1200) provides stability so that the oral device does not come off the teeth during sleep, and at the same time facilitates the attachment and detachment of the device. In particular, the wing portion serves to widen the contact area between the upper and lower jaws and increase the fixation force of the device.

[0175] The computing device (100) can determine the optimal location and size for the wing portion by analyzing the user's oral structure and tooth arrangement data. For example, the computing device (100) designs the wing portion by considering the area where the user's teeth are distributed and the angles and heights of these teeth. Near the maxillary anterior teeth, the height of the wing portion may be designed to be relatively low to facilitate easy removal, and near the mandibular molars, the height of the wing portion may be designed to be larger to increase stability.

[0176] Additionally, the computing device (100) may form wing portions on both the outer and inner sides of the teeth, which is designed to further increase the fixation force of the oral device and prevent the device from coming off the teeth. The design of these wing portions can be adjusted to suit the individual user's tooth structure and oral condition, minimizing discomfort that may occur during the process of the user wearing and removing the device, and allowing the device to maintain a stable position even when worn for a long period of time.

[0177] In the embodiments, the wing portion is provided in the section extending from the maxillary and mandibular anterior teeth to the molars, and the height and shape of the wing portion may be designed differently for each region. The wing portion may be formed on the inner and outer sides relative to the teeth, respectively, a design that simultaneously considers the stability and comfort of the device. For example, the inner wing portion near the maxillary anterior teeth may be designed with a relatively low height to facilitate easy attachment and detachment of the device, thereby helping the user easily put on and take off the device. On the other hand, the outer wing portion may be designed with a slightly higher height to compensate for instability that may occur during attachment and detachment in the anterior teeth.

[0178] In the vicinity of the molars, the heights of both the inner and outer wings may be designed to be relatively high to enhance the stability of the device. In the embodiment, the molars may be considered to include premolars and molars. Premolars are generally anterior molars that perform the function of chewing, and may be areas where relatively little pressure is generated during occlusion. Molars are posterior molars that primarily function to grind food, and may be areas where significant pressure is applied during occlusion.

[0179] The inner wing firmly grips the side of the tooth to secure the device and prevent it from moving during sleep, while the outer wing provides robust support to prevent the device from slipping sideways. This design ensures the device remains stably fixed to the teeth even during sleep, while simultaneously facilitating easy removal.

[0180] Additionally, in an embodiment, referring to FIG. 10(b), the lingual space (1100) may be an empty space formed on the inner side of the oral device, particularly in the part where the tongue is located. FIG. 10(b) is an example view taken from the lower direction when the oral device is worn. For example, when the device is worn, if the user's tongue is pushed by the device due to the thickness of the device, the airway may not be sufficiently secured, and breathing may not be smooth. To prevent this, the lingual space is formed on the inner side of the device so that the tongue can be positioned comfortably. The lingual space is particularly important for securing the airway and is designed to maintain the natural position of the tongue while the device is worn, thereby facilitating breathing during sleep.

[0181] According to an embodiment, the lingual space (1100) may be formed in the posterior region of the maxillary anterior region. A computing device (100) may analyze the user's oral structure and the position of the tongue to identify the posterior region of the maxillary anterior region and generate a first part model so that the lingual space is formed on the identified region. Through this, the position of the tongue is maintained and the airway is not blocked even when the device is worn, thereby allowing the user to breathe smoothly.

[0182] In addition, in an embodiment, the computing device (100) may analyze oral data to determine the location and number of open holes to effectively distribute pressure that may occur when wearing the device. The open holes are intended to alleviate excessive pressure concentrated on specific areas when the oral device is worn, thereby minimizing discomfort felt by the user and increasing the durability of the device. Excessive pressure can overload the teeth and gums in specific areas, potentially causing pain or discomfort in the long term, which may hinder the effective use of the device. Therefore, the computing device (100) may include open holes during the individual part creation process to prevent such problems in advance.

[0183] Specifically, the computing device (100) analyzes the user's tooth structure and pressure distribution and identifies an area where excessive pressure is likely to be applied to a specific part. For example, since the area near the lower molars is an area where large pressure can be concentrated during tooth occlusion, the computing device (100) can be designed to effectively disperse pressure by forming an open hole in this area. In this process, the computing device (100) calculates the optimal size so that the open hole is neither too large nor too small, thereby maximizing the pressure dispersion effect while maintaining the functionality of the device.

[0184] Additionally, some users may have anterior crowns that are relatively long or protruding. In such cases, pressure is likely to be concentrated near the anterior teeth, so additional opening holes may be required. A computing device (100) can analyze the user's anterior tooth structure and optimize the size and number of opening holes according to the length and shape of the anterior teeth. For example, in the case of a user with long anterior crowns, multiple opening holes are formed on the lingual or mesiodistal surface of the anterior teeth to disperse excessive pressure applied to that area. This reduces the burden on the anterior teeth and improves the comfort of wearing the device, even when the device is worn for a long time.

[0185] When determining the location of the open holes, the computing device (100) considers the interaction between the area where pressure is concentrated and the surrounding structure. For example, if strong contact with the upper jaw occurs near the lower molars, multiple open holes can be placed in this area to evenly distribute the pressure. At this time, the computing device (100) can also optimize the size and shape of the open holes to design them so as to minimize discomfort that may occur during long-term wear.

[0186] In addition, the open holes can be appropriately designed for users with long or protruding anterior teeth. The computing device (100) arranges multiple open holes of appropriate size to match the length of the anterior teeth, thereby effectively dispersing pressure that may be concentrated on the anterior teeth. This allows the oral device to fit smoothly to the user's anterior teeth, thereby minimizing discomfort even when worn for a long time.

[0187] Additionally, the computing device (100) can adjust the size and number of each opening hole to suit the user's oral structure. For example, larger opening holes are designed for areas where more pressure is applied, and smaller opening holes are designed for areas where relatively less pressure is applied, so that pressure distribution can be optimized. This increases the durability of the device and allows the user to wear the device more comfortably.

[0188] The computing device (100) generates a first part model and a second part model based on these analysis results, and the generated models include open holes optimized for pressure distribution. Open holes designed near the anterior region are also designed based on the aforementioned analysis and are particularly useful for users with relatively long anterior regions or those expected to experience pressure concentration. These open holes are designed to reduce discomfort that may occur while wearing the device and to ensure the device fits stably to the user's oral structure, thereby maximizing long-term treatment effects.

[0189] The design of such open holes not only enhances the functionality of the device but also plays an important role in helping the user maintain oral health in the long term. Therefore, the computing device (100) provides an optimal design that considers both user comfort and the effectiveness of the device by precisely adjusting the location, size, and number of the open holes.

[0190] According to various embodiments, the computing device (100) can design an oral device model that prevents teeth grinding and clenching by identifying molar areas based on the user's oral data. Specifically, the computing device (100) analyzes various oral data, such as the user's occlusal force, tooth structure, and jaw movement, to precisely determine the distribution of force occurring in the molar areas and the occlusal state. Based on this data, the computing device (100) can design an empty space so that the molar areas do not come into contact, thereby making adjustments so that no force is applied to the molars during occlusion.

[0191] Referring to FIG. 11 (a) and (b), the molar region (1000a) is the area where teeth grinding and clenching mainly occur, and the computing device (100) forms this area as an empty space so that the molars do not come into direct contact during occlusion. This design plays an important role in preventing the user from unintentionally clenching or grinding their teeth by effectively blocking the pressure applied to the molars.

[0192] According to an embodiment, the molar region (1000a) in the present invention may refer to an area primarily related to molars. Molars are teeth located at the posterior end of the upper and lower jaws; they are larger than premolars and are subject to stronger pressure during occlusion. While molars play an important role in grinding food, they are also an area where unnecessary pressure, such as from teeth grinding or clenching, is primarily concentrated. In the present invention, this molar region is treated as an empty space so that the molars do not come into direct contact while the device is worn, thereby providing a function to effectively prevent excessive pressure that may occur during occlusion.

[0193] According to one embodiment, the oral device model of the present invention may be manufactured in a form that covers up to the premolar portion among the molars, as shown in FIG. 11, and does not cover the molar portion, or covers only a portion of the front of the molar. This may be a design method that maintains the stability of the device while blocking strong pressure that may occur in the molar portion. Therefore, by maintaining proper occlusion in the premolar portion while preventing interlocking of the molar portion, it is possible to prevent teeth grinding or clenching while wearing the device and provide the effect of protecting the user's oral health.

[0194] The computing device (100) first identifies the position of the molars and the contact pattern between the teeth based on the user's oral data to design a void space in the molar area. In this process, the computing device (100) precisely analyzes the area where occlusal force is concentrated, disperses the force that may occur during occlusion, and adjusts the molar area so that it does not interlock. Through this, the oral device is designed so that unnecessary pressure is not applied to the molars even during sleep, and can prevent tooth damage caused by teeth grinding or clenching.

[0195] In addition, this empty space design is not limited to a simple asymmetrical structure but is precisely executed by taking into account the user's jaw movement data and the occlusal state of the upper and lower jaws. The computing device (100) analyzes the user's jaw movement video data to determine the optimal size and location of the empty space to minimize the possibility of contact in the molar area. This ensures that the user does not feel discomfort when wearing the device even if an empty space is formed, and maintains comfort even when worn for a long period.

[0196] As a result, the computing device (100) provides a customized oral device that prevents teeth grinding and clenching through this design process, and helps the user wear the device stably even while sleeping. This maximizes the comfort and functionality of the oral device, and can provide the user with a more comfortable and effective sleep environment.

[0197] According to one embodiment of the present invention, a 3D modeling method for a customized oral device for improving sleep disorders may include the step (S400) of generating an oral device model based on a plurality of part models.

[0198] In a specific embodiment, the step of generating an oral device model may include the step of generating an integrated model by connecting a plurality of part models into one, the step of performing surface treatment on the integrated model, and the step of generating an oral device model by performing inner surface processing based on contour information corresponding to the integrated model with completed surface treatment.

[0199] Specifically, the step of creating an oral appliance model begins by first connecting multiple part models into one to create an integrated model. At this time, each part model is designed to be optimized for the user's oral structure, corresponding to the upper and lower jaws as shown in FIG. 12 (a). During the process of merging the part models, the space between each part model is filled, as shown in FIG. 12 (b). Specifically, during the merging process between the part models, a new material is added to the boundary portions of each model or existing models are closely fitted together, so that the space is filled so that the seams are invisible, and the structure transforms into a single integrated structure.

[0200] Afterward, as shown in (c) of FIG. 12, surface treatment is performed so that the shapes of each model are naturally connected. This surface treatment process can be achieved using wrapping or smoothing techniques.

[0201] The computing device (100) may apply surface treatment techniques, such as wrapping or smoothing, to make the appearance of the integrated model more natural and smooth. These techniques smoothly connect the boundaries between the parts models, ensuring that the appearance of the integrated model is seamlessly connected, while simultaneously improving the wearing comfort of the device. For example, as shown in FIG. 13, the computing device (100) smooths the surface of the integrated model by applying a wrapping technique to each corner and curved part of the integrated model to naturally connect the boundaries. Through this, the foreign body sensation is minimized when wearing the oral device, and it can be worn smoothly inside the oral cavity.

[0202] That is, the computing device (100) can perform surface treatment to generate an integrated model in which the boundaries between individual part models are smoothly connected (i.e., an integrated model with completed surface treatment).

[0203] Meanwhile, during the process of combining part models and applying surface treatments (e.g., lapping and smoothing), the shape of the integrated model becomes slightly thicker than the original model. This is because the overall volume increases as the outer edges of the individual part models are smoothly connected. Consequently, a problem may arise where the internal space of the integrated model, particularly the area where teeth are inserted, becomes narrower.

[0204] To solve this, the computing device (100) creates an oral device model by performing inner surface processing based on contour information (i.e., contour information generated based on the master model) after surface processing for the integrated model is completed.

[0205] Specifically, the computing device (100) performs a calculation to reconstruct the inner surface of the oral device by precisely subtracting it from the 3D model using contour information. In this process, the computing device (100) reclaims the internal space that has been narrowed due to surface treatment, thereby forming an optimal space where the tooth can be accurately inserted. The contour information generated based on the master model accurately reflects the anatomical structure of the tooth and serves as a guide to precisely subtract the inner surface of the device based on the detailed contours of the tooth and gum.

[0206] Through this process, the computing device (100) removes unnecessary protrusions or excessively narrowed spaces within the oral device and optimizes the internal structure so that the device fits precisely into the user's teeth and gums. Contour information reflecting clearance distance and mandibular advancement amount ensures that pressure applied to the teeth and gums is properly distributed when the device is worn, thereby allowing the oral device to maintain optimal fit and functionality.

[0207] As a result, the precise inner surface processing performed by the computing device (100) ensures that the oral device adheres precisely to the user's teeth and gums while being worn without discomfort, thereby maximizing the wearability and functionality of the device. The resulting oral device model can maintain comfort even when worn by the user for a long period, effectively secure the airway during sleep, and provide a stable occlusal state.

[0208] Since the oral device model of the present invention is implemented as a single integrated unit, separate accessories are not required to connect the upper and lower jaw portions. Consequently, the structure of the device is simplified, making hygiene management easier and reducing the burden on the user in maintaining the device's cleanliness. Furthermore, thanks to the integrated structure, the possibility of device breakage is reduced, and stability can be guaranteed even with long-term use.

[0209] In particular, the oral device model of the present invention includes a clearance designed to reflect the anatomical characteristics of each tooth and gum, which can effectively distribute pressure generated during wear. This prevents pressure from concentrating on specific areas and minimizes discomfort even when the device is worn for a long period. Furthermore, the clearance design allows the device to permit a small range of movement with the user's teeth and gums, helping to maintain a natural occlusal state while preventing strain on the temporomandibular joint. As a result, it prevents injuries that may occur during device use and further enhances overall comfort.

[0210] Consequently, the oral device model of the present invention is hygienic and easy to maintain thanks to its integrated structure without connecting parts between the upper and lower jaws, and is a device that maintains comfort and safety even during long-term use by providing pressure distribution and freedom of movement through a clearance design, and can effectively provide airway security and a stable occlusal state during sleep.

[0211] According to one embodiment of the present invention, a 3D modeling method for a customized oral device for improving sleep disorders may include the step of generating an oral device model by processing a tooth model as input to a deep learning model.

[0212] The deep learning model may be characterized as a neural network model that has been pre-trained through a training dataset consisting of multiple users' tooth models and oral device models.

[0213] Specifically, the computing device (100) can build a learning data set including upper and lower jaw tooth models collected from multiple users and oral device models made to fit each user.

[0214] The training data set may include a training input data set related to multiple users' tooth models and a training output data set related to oral device models corresponding to each tooth model.

[0215] The training input data includes data related to a tooth model generated based on oral data such as the user's tooth structure, alignment, gum condition, and jaw movement, and this is provided as input to the deep learning model. The training output data includes data for an oral appliance model designed custom for each user, and this is used as ground truth data to be compared with the oral appliance model predicted by the deep learning model.

[0216] For example, a computing device (100) provides a specific user's upper and lower jaw tooth model as input data, and a deep learning model predicts an oral appliance model suitable for the user based on this. The predicted oral appliance model is compared with the actual correct oral appliance model used, and in this process, an error between the prediction result and the correct data is derived. The derived error is used to adjust the connection weights within the deep learning model through backpropagation. The deep learning model learns iteratively to minimize this error, thereby improving its ability to generate an optimal oral appliance model corresponding to each tooth model. Through this learning process, the deep learning model receives a new user's tooth model as input and evolves into a neural network model capable of automatically generating a customized oral appliance model that optimizes airway patency and comfort.

[0217] That is, the computing device (100) can automatically generate a customized oral device model for a user by utilizing a deep learning model learned through tooth models and oral device models collected from multiple users, and receiving a new user's tooth model as input. In this process, the computing device (100) predicts an oral device model based on the input tooth model, and the deep learning model performs a device design that can optimize airway securing and wearing comfort based on the learned data. The oral device model predicted by the deep learning model is generated by reflecting the optimal thickness, clearance distance, mandibular advancement amount, etc., tailored to each user's oral structure and characteristics, thereby helping the device to effectively improve sleep disorders.

[0218] In this way, by creating a deep learning model and utilizing the generated deep learning model to automatically generate a customized oral appliance model based on a new user's dental model, a device optimized for the user's oral structure and characteristics can be provided quickly and efficiently. This reduces the time that may occur during the process of designing a customized oral appliance, while simultaneously maximizing accuracy and comfort to provide a device that is more effective in improving sleep disorders.

[0219] In various embodiments, the computing device (100) can further improve the accuracy of the output of the final deep learning model by including not only the tooth model but also jaw movement video data in the training input data and proceeding with training. Specifically, the jaw movement video data provides important information that can comprehensively analyze patterns such as how the user's jaw moves during sleep, forward and backward movement, left and right rotation, and up and down movement. By including this jaw movement data in the training input data, the deep learning model can learn more precisely how the user's lower jaw contributes to widening the airway and how stably the contact between the upper and lower jaws is formed during occlusion, along with the tooth model.

[0220] The computing device (100) utilizes jaw movement video data and tooth model data collected from multiple users as training input data for a neural network model, thereby enabling the prediction of various movements that may occur for each user while the oral device is worn. For example, if a specific user has a tendency for the mandible to retract or advance during sleep, the deep learning model can learn this and optimize the amount of mandibular advancement so that the airway can be stably secured while the user is wearing the oral device. This learning process enables the creation of a more accurate and personalized oral device model by reflecting dynamic data, which cannot be obtained solely from static tooth alignment information, into the deep learning model.

[0221] As video data of jaw movement is included in the training input data in this manner, the deep learning model designs an optimal oral appliance model by considering the user's oral structure and mandibular movement patterns from a more comprehensive perspective. The output of the deep learning model predicts not only the interaction between the tooth model and the oral appliance model but also the fit of the appliance based on changes in jaw movement and occlusion, thereby improving the accuracy of the output of the user-customized oral appliance model. Through this, the finally generated oral appliance model provides a more precise fit and is designed to allow the user to comfortably and effectively secure the airway even during sleep.

[0222] Additionally, according to an embodiment, the computing device (100) may include a function to simulate the performance of an oral device model. Through a deep learning model, the computing device model can predict, through virtual simulation, how much it contributes to securing the airway when actually worn, and whether it does not burden the user's jaw joint. The computing device (100) performs a simulation based on the user's oral structure, tooth arrangement, and jaw movement data, and can predict how the optimized oral device widens the airway and disperses pressure when worn.

[0223] These simulation results are fed back as training data for a deep learning model, contributing to the creation of a more accurate and precise model when designing the next oral device model. Consequently, the computing device (100) provides an optimized oral device model that reflects the user's individual oral characteristics and movements during sleep, and is designed so that the user can wear the device comfortably for a long period of time.

[0224] In various embodiments, the computing device (100) can perform an oral device design process using a previously learned artificial intelligence model.

[0225] In one embodiment, the computing device (100) inputs the user's tooth model (10) into a pre-trained artificial intelligence model and obtains a user-customized oral device model from the output of the artificial intelligence model.

[0226] In various embodiments, the user's tooth model (10) may reflect information on the user's mandibular advancement amount and may apply a positional relationship between the upper and lower jaws, but is not limited thereto.

[0227] For example, the computing device (100) can convert a 3D mesh of a user tooth model into voxels of a preset size. The preset size may be set to an appropriate size considering the amount of computation when used as training data for an AI model, but the specific size is not limited.

[0228] For example, a computing device (100) can input tooth voxels into a pre-trained artificial intelligence model (e.g., UNet-based architecture) and obtain oral device voxels as the output of the artificial intelligence model.

[0229] The computing device (100) can convert the output oral device voxels into a 3D mesh of the oral device using a marching cube algorithm, but the specific algorithm is not limited to this.

[0230] In one embodiment, the computing device (100) can obtain a master model (20) generated in correspondence with the user's tooth model (10).

[0231] In various embodiments, the master model (20) may be generated using the method described above in this specification, but is not limited thereto. As another example, the computing device (100) may obtain information about a pre-designated vertex group for the upper and lower jaws, which is designated for the user's tooth model (10).

[0232] Information regarding vertex groups may be specified manually by the user (e.g., mouse drag input), but may also be specified automatically using a pre-trained segmentation artificial intelligence model according to the embodiment.

[0233] The computing device (100) can generate a master model by applying a gap to a specified group of vertices.

[0234] For example, the computing device (100) can add thickness according to a pre-set rule to the entire mesh of the tooth model (10) and add thickness according to a pre-set rule to each vertex group set for each tooth part.

[0235] Subsequently, the computing device (100) can perform processing to convert the surface of the mesh with added thickness into a smooth form. For example, the computing device (100) can duplicate the original mesh and perform processing (e.g., remesh, fatten, subdivision) to convert the surface of the duplicated mesh into a smooth form. The computing device (100) can attach the duplicated mesh, after processing is complete, to the original mesh (e.g., naturally attached to the original mesh via shrinkwrap). According to an embodiment, the computing device (100) can further perform the same process to generate a master model (20) with a smooth and natural form.

[0236] In one embodiment, the computing device (100) can generate a first master sub-model (21) and a second master sub-model (22) for each of the upper and lower jaws using the above process.

[0237] In various embodiments, the computing device (100) may duplicate a mesh for the mandible multiple times during the process of creating a second master sub-model (22) for the mandible, and then merge the duplicated n meshes at different intervals (e.g., -1 to -n) in the z-axis direction to secure an undercut space necessary for the removal of an oral device, but is not limited thereto.

[0238] The computing device (100) can create a master model (20) by combining the first master sub-model (21) and the second master sub-model (22).

[0239] In various embodiments, the computing device (100) may input the user's tooth model (10) into a pre-trained artificial intelligence model and obtain a master model (20) from the output of the artificial intelligence model.

[0240] In one embodiment, the computing device (100) can generate a final oral device model by subtracting the master model (20) from the oral device model generated using an artificial intelligence model.

[0241] Through this, the computing device (100) can generate a user-customized oral device by correcting the oral device model generated using an artificial intelligence model using the master model (20). Depending on the embodiment, additional correction may be performed on the generated customized oral device, but is not limited thereto.

[0242] According to one embodiment of the present invention, a manufacturing system for a customized oral device for improving sleep disorders through 3D modeling may include an output device that manufactures by outputting an oral device model. The output device may be a high-precision output device such as a 3D printer and serves to physically produce an oral device model designed to be customized for the user. For example, the output device may include various 3D printing methods such as SLA (Stereolithography), SLS (Selective Laser Sintering), and FDM (Fused Deposition Modeling), but is not limited thereto. The output device can precisely output the complex shape and fine structure of the oral device model, so that the digital oral device model created during the design stage can be realized as a physical product.

[0243] In one embodiment, the output device may be used as equipment for outputting an integrated oral device model including parts models of the upper and lower jaws. More specifically, when a 3D oral device model generated by a computing device (100) is transmitted to the output device, the output device outputs the oral device model layer by layer using high-resolution 3D printing technology. The output oral device is precisely manufactured to match the tooth structure and anatomical characteristics of the gums, taking into account the interlocking of the upper and lower jaws.

[0244] That is, a customized oral device is output through an output device in a form optimized for the individual user's teeth and gum structure, and this can be used for therapeutic purposes to improve sleep disorders as a completed oral device after subsequent processing. In the embodiment, subsequent processing may include a process of smoothing the surface of the device through a polishing process after physical fabrication. Additionally, subsequent processing may include a cleaning and inspection process after the polishing process. This series of processes maximizes the precision and effectiveness of the customized oral device and can contribute to effectively improving the user's sleep disorders.

[0245] Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. (Hereafter, they will be described uniformly as neural network.) A data structure may include a neural network. A data structure including a neural network may be stored on a computer-readable medium. A data structure including a neural network may also include data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for training the neural network. A data structure including a neural network may include any of the components disclosed above. That is, a data structure including a neural network may be configured to include all or any combination thereof, such as data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for training the neural network. In addition to the aforementioned components, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all forms of data used or generated during the computational process of the neural network, and is not limited to the foregoing. The computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. The neural network may be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. The neural network is composed of at least one node.

[0246] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0247] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors.

[0248] Those skilled in the art will understand that the various exemplary logic blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented by electronic hardware, various forms of programs or design code (referred to herein as “software”), or a combination of all such. To clearly illustrate this interoperability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been generally described above in relation to their functions. Whether such functions are implemented as hardware or software depends on the design constraints imposed on the specific application and the overall system. Those skilled in the art may implement the functions described in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of the invention.

[0249] The various embodiments presented herein may be implemented as methods, devices, or articles of manufacture using standard programming and / or engineering techniques. The term “article of manufacture” includes a computer program, carrier, or medium accessible from any computer-readable device. For example, computer-readable media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical discs (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and / or other machine-readable media for storing information. The term “machine-readable media” includes, but is not limited to, wireless channels and various other media capable of storing, holding, and / or transmitting command(s) and / or data.

[0250] It should be understood that the specific order or hierarchy of steps in the presented processes is merely an example of exemplary approaches. It should be understood that, based on design priorities, the specific order or hierarchy of steps in the processes may be rearranged within the scope of the invention. The appended method claims provide various step elements in a sample order, but do not imply limitation to the specific order or hierarchy presented.

[0251] The description of the presented embodiments is provided so that any person skilled in the art may use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Thus, the present invention is not limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0252] The relevant details have been described in the best mode for carrying out the invention as described above.

Claims

1. A method performed on one or more processors of a computing device, A step of generating a tooth model including an upper jaw model and a lower jaw model; A step of generating contour information based on the above tooth model; A step of generating a plurality of part models based on the above contour information; and The step of generating an oral device model by integrating the above plurality of part models; comprising Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

2. In Paragraph 1, The step of generating the above contour information is, A step of generating a master model by applying a clearance distance corresponding to each of the plurality of regions of the above tooth model; A step of generating basic contour information based on the above master model; and A step of generating the contour information by correcting the master model based on the basic contour information; comprising Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

3. In Paragraph 2, The above clearance distance is set to allow for pressure dispersion and a predetermined movement, and is characterized by being determined differently by region based on the anatomical characteristics of the tooth, interaction with surrounding structures, and physical characteristics of individual teeth. The step of generating the above basic contour information is, A step of identifying a plurality of predefined regions in the above tooth model; A step of calculating a clearance distance for each region corresponding to each of the plurality of regions above; A step of applying the calculated clearance distance for each of the above regions to each of the plurality of regions; and A step of performing surface treatment corresponding to an area to which a clearance distance is applied; comprising Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

4. In Paragraph 2, The step of generating the above contour information is, A step of generating mandibular advancement amount information based on oral data; and The method includes the step of generating the contour information by adjusting the relative position between the maxilla and mandible of the master model based on the generated mandibular advancement amount information; The above oral data is information regarding the user's oral condition, including impression result data and jaw movement video data, Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

5. In Paragraph 1, The step of generating the above multiple parts models is, A step of generating a first part model corresponding to the maxillary model based on the above contour information; and The step of generating a second part model corresponding to the mandibular model based on the above contour information; comprising Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

6. In Paragraph 5, The above-mentioned first part model and the above-mentioned second part model are, Characterized by including at least one of a lingual space for securing an airway, a wing portion provided through a shape covering the tooth, and an open hole formed through a hole shape in one area for pressure dispersion. Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

7. In Paragraph 1, The step of generating the above oral device model is, A step of creating an integrated model by connecting the above-mentioned plurality of part models into one; A step of performing surface treatment on the above integrated model; and The step of generating the oral device model by performing inner surface processing based on the contour information in correspondence with the integrated model having completed surface treatment; Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

8. In Paragraph 1, The above method is, The method further includes the step of generating the oral device model by processing the tooth model as input to a deep learning model; The deep learning model described above is characterized as being a neural network model pre-trained through a training dataset composed of multiple users' tooth models and oral device models. Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

9. In Paragraph 1, The step of manufacturing an oral device model by outputting the generated oral device model above; further comprising Manufacturing method of a customized oral device for improving sleep disorders through 3D modeling.

10. Memory for storing one or more instructions; and It includes a processor that executes one or more instructions stored in the memory, A device that performs the method of claim 1 by executing one or more of the above-mentioned instructions.

11. A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of claim 1.

12. A computing device for generating an oral appliance model; and An output device for manufacturing by outputting the above oral device model; comprising, The above computing device is, Create a tooth model including a maxillary model and a mandibular model, and Generate contour information based on the above tooth model, and Based on the above contour information, generate multiple part models, and Generating the oral device model based on the above plurality of parts models, Manufacturing system for customized oral devices for improving sleep disorders through 3D modeling.

Images