WO2023211025A1

WO2023211025A1 - Orthodontic recommendation system and method using artificial intelligence

Info

Publication number: WO2023211025A1
Application number: PCT/KR2023/005053
Authority: WO
Inventors: 김신엽
Original assignee: 김신엽; 김호정; 김아정
Priority date: 2022-04-28
Filing date: 2023-04-14
Publication date: 2023-11-02
Also published as: KR102464472B1

Abstract

The present invention relates to an orthodontic recommendation system and method using artificial intelligence and, more specifically, to an orthodontic recommendation system and method using artificial intelligence, wherein a database is built by collecting big data including oral data and medical data (charts) of patients for whom treatment has been completed, an orthodontic diagnosis of an arbitrary patient and a correction method at each treatment stage are derived and recommended on the basis of a treatment model generated by analyzing and learning the data, thereby allowing the optimal correction method to be recommended on the basis of the oral data and the medical records of a plurality of patients.

Description

Orthodontic treatment recommendation system and method using artificial intelligence

The present invention relates to an orthodontic method recommendation system and method using artificial intelligence, and more specifically, to build a database by collecting big data including oral data and medical data (charts) of patients who have completed treatment, and to collect the data. Based on the treatment model created through analysis and learning, orthodontic diagnosis for any patient and derivation and recommendation of orthodontic methods at each treatment stage, artificial intelligence recommends the optimal orthodontic method based on the oral data and medical records of multiple patients. This relates to an orthodontic recommendation system and method using intelligence.

In general, a condition in which the dentition is not straight and the occlusion of the upper and lower teeth is abnormal is called malocclusion. Such malocclusion not only causes functional problems such as chewing and pronunciation problems and aesthetic problems for the face, but also causes cavities and gum disease. The same health problems can also occur.

Therefore, orthodontic treatment must be performed to change this malocclusion into normal occlusion.

Before performing such orthodontic treatment, in order to determine an appropriate treatment method, it is desirable to conduct a simulation of the patient's current dental condition as well as the expected shape of the teeth during orthodontic treatment.

However, when straightening teeth in such a tooth simulation device, the operator, the doctor, must move the position and rotation of each tooth, which causes a problem in that the work is less efficient.

Korean registered patent [10-2121963] discloses a transparent orthodontic model setting device, method, and program using orthodontic clinical big data.

Korean registered patent [10-2227460] discloses a method of aligning teeth for orthodontic treatment and an orthodontic CAD system that performs the same.

Therefore, the present invention was created to solve the problems described above, and the purpose of the present invention is to collect big data including oral data and medical data (charts) of patients who have completed treatment, build a database, and collect data Based on the treatment model created by analyzing and learning, orthodontic diagnosis for any patient and orthodontic method at each treatment stage are derived and recommended, the optimal orthodontic method is recommended based on the oral data and medical records of multiple patients. The goal is to provide an orthodontic method recommendation system and method using artificial intelligence.

The purposes of the embodiments of the present invention are not limited to the purposes mentioned above, and other purposes not mentioned will be clearly understood by those skilled in the art from the description below. .

In order to achieve the above-described object, an orthodontic method recommendation system using artificial intelligence according to an embodiment of the present invention constructs a database by analyzing image data and medical treatment data of patients who have completed treatment, and images of random patients. An orthodontic method recommendation server 100 for diagnosing the patient's dentition according to data and questionnaires and recommending orthodontic methods for prescriptions at each treatment stage; A plurality of dental terminals (110, 120) for connecting to the orthodontic method recommendation server and transmitting and receiving data necessary to provide diagnosis and orthodontic method recommendation services for the patient's dentition; And a plurality of data acquisition devices (130, 140, 150, 160) for collecting data necessary for diagnosis and recommendation of correction method for the patient's dentition, wherein the plurality of data acquisition devices include an X-ray, a 3D scanner, It is characterized in that it includes a camera and a computed tomography device, and the orthodontic method recommendation server 100 includes a transceiver unit 101 that provides an interface for providing orthodontic diagnosis and orthodontic method recommendation services to the plurality of user terminals; a data collection unit 103 for collecting and processing the image data to extract first tooth characteristic elements and extracting treatment characteristic elements from the treatment data; A data processing unit 104 for extracting second tooth characteristic elements and patient characteristic elements by performing data processing necessary for diagnosing the dentition of an arbitrary patient based on the data transmitted and received through the transmitting and receiving unit and the data collected through the data collection unit. ; Prescribing treatment according to the current weight according to the treatment data and the second tooth characteristic elements and patient characteristic elements extracted from the data processing unit, evaluating the feasibility of the prescribed treatment, storing the prediction results, and calculating the treatment achievement level, Artificial intelligence analysis unit (105) to update the care model; A correction method recommendation unit 108 for recommending a correction method according to the prescribed treatment; a database management unit 106 that stores data necessary to provide the orthodontic diagnosis and orthodontic treatment recommendation service; A chart preparation unit 107 for outputting the patient's 3D tooth image and treatment information through the dental terminal and recording the information received through the dental terminal in the medical chart database; And a control unit 102 for controlling each component including the transmitting and receiving unit, data collection unit, data processing unit, artificial intelligence analysis unit, correction method recommendation unit, database management unit, and chart preparation unit.

The data collection unit 103 includes an image collection unit 301 for forming 3D tooth data using image data collected through the plurality of data acquisition devices; a first tooth arrangement unit 302 for generating a first tooth arrangement according to the arch shape of the user from the collected image data; a first tooth characteristic extraction unit 303 for extracting the first tooth characteristic element by comparing each arranged tooth with a standard tooth shape; a first data conversion unit 305 for receiving and converting the medical treatment data of the patient; a medical treatment characteristic extraction unit 306 for extracting medical treatment characteristic elements from the converted medical treatment data; and a treatment history review unit 304 for reviewing treatment details according to the extracted tooth characteristics and storing the treatment details in the database management unit in consideration of the treatment characteristic elements.

The data processing unit 104 includes a data input unit 401 for receiving image data acquired through the plurality of data acquisition devices; a second tooth arrangement unit 402 for generating a second tooth arrangement according to the arch shape of the user from the image data; a second tooth characteristic extraction unit 403 for extracting the second tooth characteristic element by comparing each arranged tooth with a standard tooth shape; a second data conversion unit 404 for receiving and converting the questionnaire answers input from the patient through the dental terminal; and a patient characteristic extraction unit 405 for extracting the patient characteristic elements from the converted questionnaire answers.

The artificial intelligence analysis unit 105 includes an artificial intelligence treatment prescription unit 501 for deriving prescription details by searching a database based on second tooth characteristic elements and patient characteristic elements for a patient during arbitrary treatment; a treatment feasibility evaluation unit 502 for evaluating the treatment feasibility of the derived prescription details and storing the predicted results; a medical treatment achievement level calculation unit 503 for calculating a medical treatment achievement level according to previously stored prediction results; a learning unit 504 for learning the calculated treatment achievement level; an inference unit 505 for inferring treatment consideration factors for the patient according to the learning content; a treatment process modeling unit 506 for updating the treatment model for each tooth according to the inference results; And it is characterized by including a patient weight adjustment unit 507 for correcting the progress weight of each tooth of the patient.

The orthodontic method recommendation unit 108 includes a target tooth determination unit 601 for determining a target tooth according to the prescription details for which the feasibility of treatment has been evaluated; a material type determination unit 602 for determining the type of material to be used for the determined target tooth; a material size selection unit 603 for selecting the size of the material to be used for the determined target tooth; an attachment position determination unit 604 for determining an attachment position of a material to be used for the determined target tooth; and a control strength determination unit 605 for determining the control strength of a material requiring control strength in the determined type of material.

The first tooth characteristic element and the second tooth characteristic element are characterized in that they include the position, length, degree of rotation, and degree of inclination of each tooth, and the treatment characteristic elements include type of device, type of wire, type of setup, It is characterized by including the type of bracket used according to the setup, the bonding method, and whether or not a rubber band is used, and the patient characteristic elements include the patient's view of beauty, gender, age, and eating habits.

In addition, the orthodontic method recommendation method using artificial intelligence according to an embodiment of the present invention to achieve the above-mentioned purpose includes a data collection step (S910) of collecting image data and treatment data of a patient who has completed treatment; A database construction step (S920) of constructing a database by extracting the patient's dentition, first tooth characteristic elements, and treatment characteristic elements for each stage of treatment from the collected data; A data processing step (S930) of acquiring image data for a patient during a random treatment and extracting second tooth characteristic elements and patient characteristic elements; A prescription history deriving step (S940) of deriving prescription (treatment) details by searching a database based on the second tooth characteristic elements and the patient characteristic elements for the patient during the arbitrary medical treatment; A treatment feasibility evaluation step (S950) of evaluating the treatment feasibility of the derived prescription details and storing the predicted results; A learning and inference step (S960) in which the treatment achievement level is calculated according to the pre-stored prediction results, and the treatment process for the patient is learned and inferred according to the calculated treatment achievement level; A weight correction step (S970) of correcting the treatment model and the progress weight of each tooth of the patient according to learning and reasoning, and determining the corrected progress weight of each tooth as the weight of the patient during treatment; A correction method recommendation step (S980) in which a correction method is recommended according to the prescription details for which the feasibility of treatment has been evaluated; And an artificial intelligence analysis step ( S990).

The database building step (S920) includes a data transfer step (S1010) of receiving pre-stored patient image data and medical treatment data; A first tooth array generation step (S1020) of generating a first tooth array by integrating and mapping the plurality of image data; A first tooth characteristic element extraction step (S1030) of extracting a first tooth characteristic element for each tooth from the arranged teeth; A first data conversion step (S1040) of converting the medical treatment data; A treatment characteristic element extraction step (S1050) of extracting treatment characteristic elements from the converted medical treatment data; And a step (S1060) of constructing a database using the first tooth characteristic element and the treatment characteristic element, and the data processing step (S930) acquires image data of the patient during any treatment. Data acquisition step (S1110); A second tooth array generation step (S1120) of processing the image data to create a second tooth array; A second tooth characteristic element extraction step (S1130) of extracting a second tooth characteristic element for each tooth from the arranged teeth; A second data conversion step (S1140) in which survey answers are input and converted through a dental terminal; And a patient characteristic element extraction step (S1150) of extracting patient characteristic elements of a patient undergoing arbitrary treatment from the converted questionnaire answers.

The orthodontic method recommendation step (S980) includes a target tooth determination step (S1210) of determining a target tooth according to the prescription details for which the feasibility of treatment has been evaluated; A material type determination step (S1220) of determining the type of material to be used for the determined target tooth; A material size selection step (S1230) of selecting the size of the material to be used for the determined target tooth; An attachment position determination step (S1240) of determining the attachment position of the material to be used on the determined target tooth; And a control strength determination step (S1250) of determining the control strength of a material requiring control strength in the determined type of material.

In addition, according to one embodiment of the present invention, a computer-readable recording medium storing a program for implementing the orthodontic method recommendation method using artificial intelligence is provided.

In addition, according to one embodiment of the present invention, in order to implement the orthodontic method recommendation method using artificial intelligence, a program stored in a computer-readable recording medium is provided.

According to an orthodontic method recommendation system and method using artificial intelligence according to an embodiment of the present invention, big data including oral data and medical data (charts) of patients who have completed treatment are collected to build a database, and the data Based on the treatment model created through analysis and learning, orthodontic diagnosis for any patient and orthodontic treatment at each treatment stage are derived and recommended, the optimal orthodontic treatment is recommended based on the oral data and medical records of multiple patients to provide necessary treatment. It has the effect of allowing the process to proceed.

In addition, according to the orthodontic method recommendation system and method using artificial intelligence according to an embodiment of the present invention, rather than receiving a recommendation based on one piece of similar clinical data, the orthodontic method necessary for the patient is derived based on the history of each treatment step. Therefore, it is effective in proposing an efficient correction method.

In addition, according to the orthodontic treatment recommendation system and method using artificial intelligence according to an embodiment of the present invention, the treatment achievement rate is calculated according to the previous treatment history at each treatment and the weight is corrected if necessary, so the orthodontic treatment method customized to the patient There is an effect that can be recommended.

In addition, according to the orthodontic method recommendation system and method using artificial intelligence according to an embodiment of the present invention, in the treatment history, incorrect prescription methods or prescription methods that do not work properly can be excluded through prescription feasibility evaluation. There is a high level of reliability in treatment.

1 is a configuration diagram of an orthodontic method recommendation system using artificial intelligence according to an embodiment of the present invention.

Figure 2 is a detailed configuration diagram of the correction method recommendation server of Figure 1.

Figure 3 is a detailed configuration diagram of the data collection unit of Figure 2.

Figure 4 is a detailed configuration diagram of the data processing unit of Figure 2.

Figure 5 is a detailed configuration diagram of the artificial intelligence analysis unit of Figure 2.

Figure 6 is a detailed configuration diagram of the correction method recommendation unit of Figure 2.

7A to 7E are diagrams for explaining image data used in an orthodontic recommendation system using artificial intelligence according to an embodiment of the present invention.

Figure 8a is a general structure of the upper and lower jaw, and Figure 8b is a diagram to explain the arrangement of the patient's teeth.

Figure 9 is a flowchart of an embodiment of an orthodontic method recommendation method using artificial intelligence according to the present invention.

Figure 10 is a detailed flowchart of one embodiment of the database construction step of Figure 9.

Figure 11 is a detailed flow chart of one embodiment of the data processing step of Figure 9.

Figure 12 is a detailed flow chart of one embodiment of the correction method recommendation step of Figure 9.

*Detailed explanation of main symbols in the drawing*

100: Diagnostic server 110, 120: Dental terminal

130: X-ray 140: 3D scanner

150: Camera 160: CT

101: Transmitter and receiver 102: Control unit

103: data collection unit 104: data processing unit

105: Artificial intelligence analysis department 106: Database management department

107: Chart preparation section 108: Correction method recommendation section

301: image collection unit 302: first tooth array unit

303: First tooth characteristic extraction unit 304: Treatment history review unit

305: first data conversion unit 306: treatment characteristics extraction unit

401: data input unit 402: second tooth array unit

403: Second tooth characteristic extraction unit 404: Second data conversion unit

405: Patient characteristic extraction unit

501: Artificial intelligence treatment prescription department 502: Treatment feasibility evaluation department

503: Treatment achievement calculation unit 504: Learning unit

505: Inference unit 506: Medical process modeling unit

507: patient weight adjustment unit 508: initial weight determination unit

601: Target tooth determination unit 602: Material type selection unit

603: Material size selection unit 604: Attachment position determination unit

605: Control strength determination unit

S910: Data collection step

S920: Database construction stage

S930: Data processing step

S940: Prescription details derivation step

S950: Treatment feasibility evaluation stage

S960: Learning and inference phase

S970: Weight correction step

S980: Correction method recommendation step

S990: Artificial intelligence analysis stage

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be.

On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used herein are merely used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, processes, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, processes, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application. No.

Hereinafter, the present invention will be described in more detail with reference to the attached drawings. Prior to this, the terms or words used in this specification and claims should not be construed as limited to their usual or dictionary meanings, and the inventor should appropriately define the concept of terms in order to explain his or her invention in the best way. Based on the principle of definability, it must be interpreted with meaning and concept consistent with the technical idea of the present invention. In addition, if there is no other definition in the technical and scientific terms used, they have meanings commonly understood by those skilled in the art to which this invention pertains, and the gist of the present invention is summarized in the following description and accompanying drawings. Descriptions of known functions and configurations that may be unnecessarily obscure are omitted. The drawings introduced below are provided as examples so that the idea of the present invention can be sufficiently conveyed to those skilled in the art. Accordingly, the present invention is not limited to the drawings presented below and may be embodied in other forms. Additionally, like reference numerals refer to like elements throughout the specification. It should be noted that like elements in the drawings are represented by like symbols wherever possible.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which machines learn and make decisions on their own and become smarter. As artificial intelligence systems are used, the recognition rate improves and users' preferences can be more accurately understood, and existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning (deep learning) and element technologies using machine learning.

Machine learning is an algorithmic technology that classifies/learns the characteristics of input data on its own, and elemental technology is a technology that uses machine learning algorithms such as deep learning to mimic the functions of the human brain such as cognition and judgment, including linguistic understanding and visual It consists of technical areas such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies/processes human language/characters and includes natural language processing, machine translation, conversation systems, question and answer, and voice recognition/synthesis. Visual understanding is a technology that recognizes and processes objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image improvement. Inferential prediction is a technology that judges information to make logical inferences and predictions, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendations. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology that controls the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.

Meanwhile, data collection and processing used in the present invention can be performed using robotic process automation (RPA) technology. Robotic Process Automation (RPA) technology is a technology that formalizes data generated in the business process and performs it logically and automatically. It is used for data collection, input, and comparison in corporate finance, accounting, manufacturing, purchasing, and customer management. Simple, repetitive tasks are automated and performed quickly and precisely. In other words, overall work time can be shortened and costs can be reduced.

By applying cognitive technologies such as machine learning, voice recognition, and natural language processing, it can be used for diagnosis and prescription in the medical field that requires human cognitive ability, customer asset management in the financial industry, and analysis of legal precedents.

Big data refers to a data set that exceeds the capabilities of existing data collection, storage, management, and analysis. Big data can be classified into structured data, semi-structured data, and unstructured data depending on the degree of formalization.

Structured data refers to data stored in fixed fields. In other words, it refers to data that is stored in a certain format. Semi-structured data refers to data that is not stored in fixed fields but includes metadata or schema. Examples of semi-structured data include Extensible Mark-up Language (XML) and Hypertext Mark-up Language (HTML). Unstructured data refers to data that is not stored in fixed fields. Examples of unstructured data include text documents, image data, video data, and voice data.

Figure 1 is a configuration diagram of an orthodontic method recommendation system using artificial intelligence according to an embodiment of the present invention, and Figure 2 is a configuration diagram of an orthodontic method recommendation server of Figure 1.

Referring to FIG. 1, the orthodontic method recommendation system using artificial intelligence according to an embodiment of the present invention includes an orthodontic method recommendation server 100, a plurality of

dental terminals

110 and 120, and a plurality of

data acquisition devices

130 and 140. , 150, 160).

The orthodontic method recommendation server 100 is a computing system equipped with software and/or hardware components to provide services for diagnosing the patient's dentition and recommending orthodontic methods using artificial intelligence, and is connected to a plurality of dental terminals (110) through a communication network. , 120) and a plurality of data acquisition devices (130, 140, 150, 160) to provide diagnostic information to the dental terminal (110, 120).

The orthodontic method recommendation server 100 adjusts the progress weight for each patient's tooth through learning diagnosis, treatment feasibility assessment, and treatment achievement level according to the patient's individual tooth characteristics, and prescribes treatment applying the adjusted weight, according to the prescription history. Recommended correction methods are provided to the

dental terminals

110 and 120.

The

dental terminals

110 and 120 connect to the orthodontic method recommendation server 100 and transmit and receive data necessary to provide diagnosis and orthodontic method recommendation services for the patient's dentition.

The plurality of

data acquisition devices

130, 140, 150, and 160 acquire the patient's X-rays, 3D scanning images, facial photos, CT, etc. for diagnosis of dentition and transmit them to the orthodontic method recommendation server 100.

The X-ray 130 takes radiographs and transmits them to the correction method recommendation server 100.

The 3D scanner 140 acquires image data of the patient's tooth structure. The 3D scanner 140 is a component for optically acquiring tooth structure image data, such as a CT device or an oral scanner.

A photo of the patient's face and oral cavity is taken through the camera 150 and transmitted to the orthodontic method recommendation server 100.

The CT 160 is a computed tomography device that acquires cross-sectional images of the human body using X-rays and transmits them to the correction method recommendation server 100.

Additionally, the orthodontic method recommendation system using artificial intelligence according to an embodiment of the present invention may further include an oral scanner (not shown). When scanning the inside of the mouth with an oral scanner, the scan data is uploaded to a separate cloud server (not shown), and to use the scan data, it must be downloaded from the cloud server.

Referring to Figure 2, the correction method recommendation server 100 includes a transceiver unit 101, a control unit 102, a data collection unit 103, a data processing unit 104, an artificial intelligence analysis unit 105, and a correction method recommendation unit ( 108), a database management unit 106, and a chart creation unit 107. The transceiver unit 101, the control unit 102, the data collection unit 103, the data processing unit 104, the artificial intelligence analysis unit 105, the correction method recommendation unit 108, and the database management unit 106. ) and the chart creation unit 107, at least some of which may be program modules that communicate with the correction method recommendation server 100. These program modules may be included in the correction method recommendation server 100 in the form of operating systems, application program modules, and other program modules, and may be physically stored on various known storage devices. Additionally, these program modules may be stored in a remote memory device capable of communicating with the correction method recommendation server 100. Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.

Here, the communication network can be configured regardless of the communication mode, such as wired or wireless, and includes a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN). It can be composed of various communication networks. Preferably, the communication network referred to in the present invention may be the known World Wide Web (WWW).

The transceiver 101 interfaces so that the orthodontic method recommendation server 100 can communicate with the plurality of

dental terminals

110 and 120, and transmits and receives data related to the provision of artificial intelligence orthodontic diagnosis and orthodontic method recommendation services. The necessary graphical user interface can be provided to the plurality of

dental terminals

110 and 120.

The control unit 102 includes the transmitting and receiving unit 101 as described above, a data collection unit 103, a data processing unit 104, an artificial intelligence analysis unit 105, a correction method recommendation unit 108, and a database management unit ( 106) and performs a function of controlling the flow of data between the chart preparation unit 107.

The data collection unit 103 builds a database for data of patients who have completed orthodontic treatment. That is, the data collection unit 103 collects and processes image data acquired through the plurality of

data acquisition devices

130, 140, 150, and 160, extracts the characteristics of each tooth, reviews the treatment history, and stores it in the database. Enter and extract treatment characteristics from treatment data.

Data collected includes facial photos, X-rays, intraoral scans, medical charts, etc.

The data processing unit 104 provides tooth characteristic elements and patient characteristic elements for diagnosing the dentition of an arbitrary patient based on data transmitted and received through the transmitting and receiving unit 101 and data collected through the data collection unit 103. Perform data processing necessary to extract.

The artificial intelligence analysis unit 105 prescribes treatment according to the current weight according to the medical records (charts) of the

dental terminals

110 and 120 and the second tooth characteristic elements and patient characteristic elements extracted from the data processing unit 104. evaluates the feasibility of prescribed treatment, stores predicted results, calculates treatment achievement, and updates the treatment model.

The correction method recommendation unit 108 recommends a correction method according to the prescribed treatment (prescription history).

The database management unit 106 includes a patient database 106a for managing patient information, an image record database 106b for storing and managing the patient's image records, and input data through the

dental terminals

110 and 120. A medical chart database 106c that stores the treatment details received, a characteristic extraction database 106d that extracts and stores characteristics of each tooth from the image data collected through the data collection unit 103, and the patient's dentition information (tooth characteristics) ), a treatment model database (106e) that stores the treatment model for the treatment prescription according to the treatment prescription, a prediction result database (106f) that stores the prediction result according to the treatment prescription, and a prediction result database (106f) that stores information on the materials used for correction. It may include an orthodontic material database (106g) and an orthodontic method database (106h) that stores details of orthodontic methods recommended to the patient.

In the above embodiment, the database storing information for implementing the present invention is a patient database 106a, an image record database 106b, a medical chart database 106c, a feature extraction database 106d, and a medical model database 106e. , it was classified into eight databases: the prediction result model database 106f, the correction material database 106g, and the correction method database 106h, but the composition of the database including these classifications may be changed according to the needs of those skilled in the art.

For example, information about wires may be stored in the correction material database 106g. The wires are gold (heat-treated) wire, stainless steel (SS) wire, Australian wire, cobalt-chromium wire, Elgiloy wire, beta-titanium wire, TMA wire, NiTi wire, Nitinol wire, triple wire. Includes triple strand wire, coaxial wire, response wire, braided rectangular wire, etc.

Meanwhile, in the present invention, a database is a concept that includes not only a database in the narrow sense, but also a database in a broad sense including data records based on a computer file system, and even a set of simple operation processing logs can be searched for It should be understood that if data of can be extracted, it can be included in the database referred to in the present invention.

The chart preparation unit 107 outputs the patient's 3D tooth image and treatment details through the

dental terminals

110 and 120, and determines the prescription details (treatment details) at the treatment stage to be sent to the dental terminals 110 and 120. ) so that the information entered is recorded in the medical chart database 106c.

Meanwhile, numbering and landmark expression in 3D tooth images are implemented automatically.

The plurality of

dental terminals

110 and 120 are digital devices that include a function that allows the dental office to access and communicate with the orthodontic method recommendation server 100 through a communication network in order to provide artificial intelligence orthodontic diagnosis and orthodontic method recommendation services. As such, the present invention can be applied to any digital device equipped with a memory means and equipped with a microprocessor, such as a personal computer (e.g., a desktop computer, a laptop computer, etc.), a workstation, a PDA, a web pad, a mobile phone, etc., and has computational capabilities. It can be adopted as a number of

dental terminals

110 and 120 according to.

Meanwhile, the plurality of

dental terminals

110 and 120 may be formed integrally with a chair for treating a patient.

Meanwhile, the plurality of

dental terminals

110 and 120 may have a dedicated application installed for providing artificial intelligence orthodontic diagnosis and orthodontic method recommendation services.

The plurality of

dental terminals

110, 120 request artificial intelligence orthodontic diagnosis and orthodontic method recommendation services from the orthodontic method recommendation server 100, and provide AI orthodontic diagnosis and orthodontic method recommendation services according to the artificial intelligence orthodontic diagnosis and orthodontic method recommendations received from the orthodontic method recommendation server 100. Contents (target tooth information, material type, material size, attachment position, control strength, etc.) are displayed.

Referring to FIG. 3, the data collection unit 103 includes an image collection unit 301, a first tooth arrangement unit 302, a first tooth characteristic extraction unit 303, a treatment history review unit 304, and a first tooth arrangement unit 302. It includes a data conversion unit 305 and a medical treatment characteristic extraction unit 306.

The image collection unit 301 forms 3D tooth data using image data collected through the plurality of

data acquisition devices

130, 140, 150, and 160.

In detail, a 3D tooth model can be formed by matching image data collected by collection date, and for patients who have completed treatment, multiple models can be formed from start to completion, and changes in dentition can be clearly confirmed.

The first tooth arrangement unit 302 generates a first tooth arrangement according to the user's arch shape from the collected image data.

The first tooth characteristic extraction unit 303 extracts a first tooth characteristic element for each tooth arranged by comparing it with a standard tooth shape. The first tooth characteristic element includes the position, length, rotation degree, and inclination degree of each tooth.

The first data conversion unit 305 receives and converts the medical treatment data of the patient.

The medical treatment characteristic extraction unit 306 extracts medical treatment characteristic elements from the converted medical treatment data.

The above medical treatment characteristics include device type, wire type, loss setup, and MBT (Richard McLaughlin, John Bennett, Hugo Trevisi) setup. Includes Damon setup, type of bracket used depending on the setup, bonding method, and whether or not a rubber band is used.

The medical treatment history review unit 304 reviews medical treatment history according to the extracted tooth characteristics, and stores the medical treatment history in the database management unit considering the medical treatment characteristic elements.

In detail, in the treatment history, check the tooth extraction, whether surgery, type of treatment by date of treatment, type of attachment, degree of movement (displacement) of each tooth compared to the previous treatment, and rate of change including rotation rate.

FIG. 4 is a detailed configuration diagram of the data processing unit of FIG. 2.

Referring to FIG. 4, the data processing unit 104 performs data processing on patient data currently in treatment, including a data input unit 401, a second tooth arrangement unit 402, a second tooth characteristic extraction unit 403, It includes a second data conversion unit 404 and a patient characteristic extraction unit 405.

The data input unit 401 receives image data acquired through the plurality of

data acquisition devices

130, 140, 150, and 160.

The second tooth arrangement unit 402 generates a second tooth arrangement according to the shape of the user's arch from the image data.

The second tooth characteristic extraction unit 403 extracts a second tooth characteristic element for each tooth arranged by comparing it with a standard tooth shape. The second tooth characteristic element includes the position, length, rotation degree, and inclination degree of each tooth.

The second data conversion unit 404 receives and converts the questionnaire answers input from the patient through the

dental terminals

110 and 120.

The patient characteristic extraction unit 405 extracts patient characteristic elements (patient's preferences) from the converted questionnaire answers.

For example, the patient characteristic elements (patient's preferences) may include aesthetics, gender, age, eating habits, etc.

As shown in Figure 5, the artificial intelligence analysis unit 105 includes an artificial intelligence treatment prescription unit 501, a treatment feasibility evaluation unit 502, a treatment achievement calculation unit 503, a learning unit 504, and an inference unit. (505), a medical process modeling unit 506, a patient weight adjustment unit 507, and an initial weight determination unit 508.

The artificial intelligence treatment prescription unit 501 searches the database based on the second tooth characteristic and patient characteristic elements for the patient during arbitrary treatment to derive prescription (treatment) details.

The treatment feasibility evaluation unit 502 evaluates the treatment feasibility of the derived prescription details and stores the prediction results. Depending on the existence of previous treatment history, the feasibility of the prescribed treatment is evaluated, and if there is no previous treatment history, the predicted results are stored in the database.

The treatment achievement level calculation unit 503 calculates the treatment achievement level according to the previously stored prediction results.

The learning unit 504 learns the calculated treatment achievement level.

The inference unit 505 infers factors to consider for treatment of the patient according to the learning contents.

The treatment process modeling unit 506 updates the treatment model for each tooth according to the inference results.

The patient's weight adjustment unit 507 corrects the progression weight for each patient's tooth.

The artificial intelligence analysis unit 105 further includes an initial weight determination unit 508 for determining the initial weight of the patient based on the patient's individual characteristics.

As shown in FIG. 6, the orthodontic method recommendation unit 108 includes a target tooth determination unit 601, a material type determination unit 602, a material size selection unit 603, an attachment position determination unit 604, and Includes a control strength determination unit 605.

The target tooth determination unit 601 determines the target tooth according to the prescription details for which the feasibility of treatment has been evaluated.

The material type determination unit 602 determines the type of material to be used for the determined target tooth.

The material size selection unit 603 selects the size of the material to be used for the determined target tooth.

The material type determination unit 602 and the material size selection unit 603 may determine the type of correction material and select the size based on information about the correction material stored in the correction material database 106g.

The attachment position determination unit 604 determines the attachment position of the material to be used for the determined target tooth.

The control strength determination unit 605 determines the control strength of the material requiring control strength in the determined type of material.

Although not shown in the drawings, in the determined type of material, a component that determines the control position or control direction of the material for which the control position or control direction is required may be further included.

For example, in terms of types of materials, wires include gold (heat-treated) wire, stainless steel (SS) wire, Australian wire, cobalt-chromium wire, Elgiloy wire, beta-titanium wire, Includes TMA wire, NiTi wire, Nitinol wire, triple strand wire, coaxial wire, response wire, braided rectangular wire, etc.

Figures 7a to 7e are diagrams for explaining image data used in an orthodontic method recommendation system using artificial intelligence according to an embodiment of the present invention.

Figure 7a is a lateral head standard radiograph, Figure 7b is a frontal head standard radiograph, Figure 7c is a panoramic radiograph, Figure 7d is a temporomandibular joint radiograph, and Figure 7e is a 3D scanned tooth data image.

A tooth arrangement is created by integrating and mapping the patient's tooth data (image data) shown in FIGS. 7A to 7E.

We will now explain how teeth are individually arranged in the first tooth arrangement unit and the second tooth arrangement unit.

Basically, teeth are divided into the upper and lower jaws, so it is necessary to distinguish between the upper and lower jaws in order to move individual teeth, and the upper and lower jaws are distinguished through detection or selection of boundary images of the upper and lower jaw.

Then, the teeth of the upper and lower jaws are arranged (positioning).

In the case of the current scanned tooth data, since it is scanned tilted at a specific angle, positioning is performed to accurately align the teeth.

Then, distinguish between teeth and gum areas.

In the 3D scanned patient's tooth data shown in FIG. 7E, the teeth and gum areas can be clearly distinguished, so the teeth and gum areas can be distinguished through image boundary detection or selection designation.

And once the teeth and gum areas are differentiated, the teeth that need correction are separated.

In the case of teeth that require correction, the position of the tooth must be displaced through processes such as enlarging, rotating, and returning the tooth, so space is needed for the tooth that needs to be moved for correction to move. Since it is difficult to distinguish between teeth based on their shape, distinguish between teeth that need correction in the area that needs correction.

When teeth are distinguished as shown in Figure 8b, reference information for each individual tooth is specified.

In addition, axis information specified by setting the axis for all teeth is also included. Standard information is set, and the standard information is set for each tooth and mapped to each tooth.

Once the reference information for the teeth is set as described above, displacements such as expansion, rotation, and return can be individually controlled.

In the orthodontic method recommendation system using artificial intelligence according to the present invention, the second tooth characteristic element and the patient characteristic element are extracted, and when standard information for the tooth is specified, the post-correction data such as expansion, rotation, and return of the tooth requiring correction is provided. You can create and derive prescription details step by step accordingly.

The post-correction data is generated by expanding, rotating, and returning the teeth that need correction based on the virtual arch line created when setting the reference information, and correcting the teeth so that they are aligned with the virtual arch line.

The orthodontic tooth data is data generated by moving teeth to a set position through the process of expanding, rotating, and returning teeth that require correction. Final correction is performed through multiple stages due to constraints on the tooth movement distance that can move the teeth. Dental data may be formed.

Here, the steps for extending, rotating, and returning teeth may be subdivided depending on the condition of the teeth and the number and position of teeth to be corrected. In the case of minor orthodontic treatment, it may be comprised of fewer steps, so that final orthodontic tooth data is not formed. The steps required may vary from patient to patient.

Therefore, in the orthodontic method recommendation system using artificial intelligence according to the present invention, the patient's current condition is analyzed at each treatment, prescription details are derived, an orthodontic method is recommended according to the prescription details, and the extent to which the previously predicted results are correct is checked. and perform the adjustment process.

Expansion of the teeth means protruding the teeth to secure space to rotate the teeth, rotation of the teeth means moving the teeth up and down, left and right in 4 axes to the position requiring correction, and return of the teeth means expansion. This means correcting the damaged teeth by rotation and then moving them to their original position.

Here, the expansion of the teeth is a necessary process when the space for moving the teeth is not secured. If the space for moving the teeth cannot be secured only by expanding the teeth, a stripping process of reducing the width of the teeth by grinding the teeth is further performed. may be included.

First, image data and treatment data of patients who have completed treatment are collected (S910).

Afterwards, a database is constructed by extracting the patient's dentition, first tooth characteristic elements, and treatment characteristic elements at each stage of treatment from the collected data (S920).

The first tooth characteristic element includes the position, length, rotation degree, and inclination degree of each tooth.

Thereafter, image data for the patient is acquired during any medical treatment, and the second tooth characteristic element and the patient characteristic element are extracted (S930).

Thereafter, during any treatment, a database is searched based on the second tooth characteristic element and the patient characteristic element for the patient to derive prescription (treatment) details (S940).

The second tooth characteristic element includes the position, length, rotation degree, and inclination degree of each tooth.

The patient characteristic elements (patient's preferences) may include beauty views, gender, age, eating habits, etc.

Afterwards, the treatment feasibility of the derived prescription details is evaluated and the prediction results are stored (S950).

Afterwards, the treatment achievement level is calculated based on the previously predicted result, and the treatment process for the patient is learned and inferred according to the calculated treatment achievement level (S960).

Thereafter, the treatment model and the progress weight of each tooth of the patient are corrected according to learning and reasoning, and the corrected progress weight of each tooth is determined as the weight of the patient during treatment (S970).

Afterwards, a correction method is recommended according to the prescription details for which the feasibility of treatment has been evaluated (S980)

During any treatment, the prescription details derivation step (S940), the treatment feasibility evaluation step (S950), the learning and reasoning step (S960), the weight correction step (S970), and the correction method recommendation step (S980) are performed for each patient during treatment. Using artificial intelligence, it provides dentition diagnosis and correction method recommendation services (S990).

Figure 10 is a detailed flowchart of one embodiment of the database building step (S920) of Figure 9.

In the database construction step (S920), pre-stored patient image data and medical treatment data are received (S1010).

Thereafter, the plurality of image data are integrated and mapped to generate a first tooth array (S1020).

Afterwards, the first tooth characteristic element for each tooth is extracted from the arranged teeth (S1030).

Afterwards, the medical treatment data is converted (S1040).

Afterwards, treatment characteristic elements are extracted from the converted treatment data (S1050).

Afterwards, a database is constructed using the first tooth characteristic element and the medical treatment characteristic element (S1060).

The patient's image data and medical treatment data may be stored in multiple external data servers (not shown).

Figure 11 is a detailed flowchart of one embodiment of the data processing step (S930) of Figure 9.

In the data processing step (S930), first, image data of the patient is acquired during any medical treatment (S1110).

Afterwards, the image data is processed to generate a second tooth array (S1120).

Afterwards, a second tooth characteristic element for each tooth is extracted from the arranged teeth (S1130).

Afterwards, the survey answers are input and converted through the dental terminal (S1140).

Patient characteristic elements of a patient during random treatment are extracted from the converted questionnaire answers (S1150).

Figure 12 is a detailed flowchart of one embodiment of the correction method recommendation step (S980) of Figure 9.

In the orthodontic method recommendation step (S980), the target tooth is first determined according to the prescription details for which the feasibility of treatment has been evaluated (S1210).

Afterwards, the type of material to be used for the determined target tooth is determined (S1220).

In terms of types of materials, wires include gold (heat-treated) wire, stainless steel (SS) wire, Australian wire, cobalt-chrome wire, Elgiloy wire, beta-titanium wire, TMA wire, and NiTi. Wire, Nitinol wire, triple strand wire, coaxial wire, respond wire, braided rectangular wire, etc.

Afterwards, the size of the material to be used for the determined target tooth is selected (S1230).

Based on the information about the correction material stored in the correction material database 106g, the type of correction material can be determined and the size can be selected.

Afterwards, the attachment position of the material to be used for the determined target tooth is determined (S1240).

Thereafter, in the determined type of material, the control strength of the material requiring control strength is determined (S1250).

Additionally, for the type of material determined above, the control position or control direction of the material for which the control position or control direction is required may be determined.

In the above, the orthodontic method recommendation method using artificial intelligence according to an embodiment of the present invention has been described. However, a computer-readable recording medium storing a program for implementing the orthodontic method recommendation method using artificial intelligence and the orthodontic method using artificial intelligence are described above. Of course, a program stored in a computer-readable recording medium for implementing the recommended method can also be implemented.

In other words, those skilled in the art will be able to easily understand that the method of recommending orthodontic treatment using artificial intelligence described above may be included and provided in a recording medium that can be read by a computer by tangibly implementing a program of commands for implementing it. . In other words, it can be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable by those skilled in the computer software art. Examples of the computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and floptical disks. Included are magneto-optical media, and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, USB memory, and the like. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

The present invention is not limited to the above-described embodiments, and the scope of application is diverse. Of course, various modifications and implementations are possible without departing from the gist of the present invention as claimed in the claims.

Claims

In an orthodontic method recommendation system using artificial intelligence,

Build a database by analyzing the image data and treatment data of patients who have completed treatment, diagnose the patient's dentition according to the image data and questionnaires of random patients, and recommend orthodontic methods to recommend correction methods for prescriptions at each treatment stage. server(100);

A plurality of dental terminals (110, 120) for connecting to the orthodontic method recommendation server and transmitting and receiving data necessary to provide diagnosis and orthodontic method recommendation services for the patient's dentition; and

A plurality of data acquisition devices (130, 140, 150, 160) for collecting data necessary for diagnosis and recommendation of correction method for the patient's dentition.

Including,

The plurality of data acquisition devices include X-rays, 3D scanners, cameras, and computed tomography devices,

The correction method recommendation server 100,

A transceiver unit 101 that provides an interface for providing orthodontic diagnosis and orthodontic treatment recommendation services to the plurality of user terminals;

a data collection unit 103 for collecting and processing the image data to extract first tooth characteristic elements and extracting treatment characteristic elements from the treatment data;

A data processing unit 104 for extracting second tooth characteristic elements and patient characteristic elements by performing data processing necessary for diagnosing the dentition of an arbitrary patient based on the data transmitted and received through the transmitting and receiving unit and the data collected through the data collection unit. ;

Prescribing treatment according to the current weight according to the treatment data and the second tooth characteristic elements and patient characteristic elements extracted from the data processing unit, evaluating the feasibility of the prescribed treatment, storing the prediction results, and calculating the treatment achievement level, Artificial intelligence analysis unit (105) to update the care model;

A correction method recommendation unit 108 for recommending a correction method according to the prescribed treatment;

a database management unit 106 that stores data necessary to provide the orthodontic diagnosis and orthodontic treatment recommendation service;

A chart preparation unit 107 for outputting the patient's 3D tooth image and treatment information through the dental terminal and recording the information received through the dental terminal in the medical chart database; and

A control unit 102 for controlling each component including the transmitting and receiving unit, data collection unit, data processing unit, artificial intelligence analysis unit, correction method recommendation unit, database management unit, and chart preparation unit.

An orthodontic method recommendation system using artificial intelligence, characterized in that it includes.
According to paragraph 1,

The data collection unit 103,

An image collection unit 301 for forming 3D tooth data using image data collected through the plurality of data acquisition devices;

a first tooth arrangement unit 302 for generating a first tooth arrangement according to the arch shape of the user from the collected image data;

a first tooth characteristic extraction unit 303 for extracting the first tooth characteristic element by comparing each arranged tooth with a standard tooth shape;

a first data conversion unit 305 for receiving and converting the medical treatment data of the patient;

a medical treatment characteristic extraction unit 306 for extracting medical treatment characteristic elements from the converted medical treatment data; and

A medical history review unit 304 for reviewing medical treatment details according to the extracted tooth characteristics and storing the medical treatment details in the database management unit in consideration of the medical treatment characteristic elements.

An orthodontic method recommendation system using artificial intelligence, characterized in that it includes.
According to paragraph 2,

The data processing unit 104,

a data input unit 401 for receiving image data acquired through the plurality of data acquisition devices;

a second tooth arrangement unit 402 for generating a second tooth arrangement according to the arch shape of the user from the image data;

a second tooth characteristic extraction unit 403 for extracting the second tooth characteristic element by comparing each arranged tooth with a standard tooth shape;

a second data conversion unit 404 for receiving and converting the questionnaire answers input from the patient through the dental terminal; and

Patient characteristic extraction unit 405 for extracting the patient characteristic elements from the converted questionnaire answers.

An orthodontic method recommendation system using artificial intelligence, characterized in that it includes.
According to paragraph 3,

The artificial intelligence analysis unit 105,

An artificial intelligence treatment prescription unit 501 for deriving prescription details by searching a database based on the second tooth characteristic element and the patient characteristic element for the patient during random treatment;

a treatment feasibility evaluation unit 502 for evaluating the treatment feasibility of the derived prescription details and storing the predicted results;

a medical treatment achievement level calculation unit 503 for calculating a medical treatment achievement level according to previously stored prediction results;

a learning unit 504 for learning the calculated treatment achievement level;

an inference unit 505 for inferring treatment consideration factors for the patient according to the learning content;

a treatment process modeling unit 506 for updating the treatment model for each tooth according to the inference results; and

Patient weight adjustment unit 507 for correcting the progression weight for each patient's tooth

An orthodontic method recommendation system using artificial intelligence, characterized in that it includes.
According to clause 4,

The correction method recommendation unit 108,

a target tooth determination unit 601 for determining a target tooth according to the prescription details for which the feasibility of treatment has been evaluated;

a material type determination unit 602 for determining the type of material to be used for the determined target tooth;

a material size selection unit 603 for selecting the size of the material to be used for the determined target tooth;

an attachment position determination unit 604 for determining an attachment position of a material to be used for the determined target tooth; and

In the determined type of material, a control strength determination unit 605 for determining the control strength of the material requiring control strength.

An orthodontic method recommendation system using artificial intelligence, characterized in that it includes.
According to paragraph 1,

The first tooth characteristic element and the second tooth characteristic element are,

Characterized by including the position, length, degree of rotation, and degree of inclination of each tooth,

The above medical treatment characteristics are:

Characterized by including the type of device, type of wire, type of setup, type of bracket used according to the setup, bonding method, and whether or not a rubber band is used,

The patient characteristic elements are,

An orthodontic method recommendation system using artificial intelligence that includes the patient's aesthetic view, gender, age, and eating habits.
In the method of recommending orthodontic treatment using artificial intelligence,

A data collection step (S910) of collecting image data and treatment data of patients who have completed treatment;

A database construction step (S920) of constructing a database by extracting the patient's dentition, first tooth characteristic elements, and treatment characteristic elements for each stage of treatment from the collected data;

A data processing step (S930) of acquiring image data for a patient during a random treatment and extracting second tooth characteristic elements and patient characteristic elements;

A prescription history deriving step (S940) of deriving prescription (treatment) details by searching a database based on the second tooth characteristic elements and the patient characteristic elements for the patient during the arbitrary medical treatment;

A treatment feasibility evaluation step (S950) of evaluating the treatment feasibility of the derived prescription details and storing the predicted results;

A learning and inference step (S960) in which the treatment achievement level is calculated according to the pre-stored prediction results, and the treatment process for the patient is learned and inferred according to the calculated treatment achievement level;

A weight correction step (S970) of correcting the treatment model and the progress weight of each tooth of the patient according to learning and reasoning, and determining the corrected progress weight of each tooth as the weight of the patient during treatment;

A correction method recommendation step (S980) in which a correction method is recommended according to the prescription details for which the feasibility of treatment has been evaluated; and

An artificial intelligence analysis step (S990) that provides orthodontic diagnosis and orthodontic method recommendation services by repeating the prescription history derivation step, the treatment feasibility evaluation step, the learning and reasoning step, the weight correction step, and the orthodontic method recommendation step at each treatment. )

Orthodontic method recommendation method using artificial intelligence, including.
In clause 7,

In the database construction step (S920),

A data transfer step (S1010) of receiving pre-stored patient image data and medical treatment data;

A first tooth array generation step (S1020) of generating a first tooth array by integrating and mapping the plurality of image data;

A first tooth characteristic element extraction step (S1030) of extracting a first tooth characteristic element for each tooth from the arranged teeth;

A first data conversion step (S1040) of converting the medical treatment data;

A treatment characteristic element extraction step (S1050) of extracting treatment characteristic elements from the converted medical treatment data; and

Building a database using the first tooth characteristic element and the medical treatment characteristic element (S1060)

Characterized by including,

The data processing step (S930) is,

A data acquisition step (S1110) of acquiring patient image data during any medical treatment;

A second tooth array generation step (S1120) of processing the image data to create a second tooth array;

A second tooth characteristic element extraction step (S1130) of extracting a second tooth characteristic element for each tooth from the arranged teeth;

A second data conversion step (S1140) in which survey answers are input and converted through a dental terminal; and

Patient characteristic element extraction step (S1150) of extracting patient characteristic elements of a patient during random treatment from the converted questionnaire answers.

A method of recommending orthodontic treatment using artificial intelligence, comprising:
According to clause 8,

In the correction method recommendation step (S980),

A target tooth determination step (S1210) of determining a target tooth according to the prescription details for which the feasibility of the treatment has been evaluated;

A material type determination step (S1220) of determining the type of material to be used for the determined target tooth;

A material size selection step (S1230) of selecting the size of the material to be used for the determined target tooth;

An attachment position determination step (S1240) of determining the attachment position of the material to be used on the determined target tooth; and

In the determined type of material, a control strength determination step (S1250) of determining the control strength of the material requiring control strength.

A method of recommending orthodontic treatment using artificial intelligence, comprising:
In clause 7,

The first tooth characteristic element and the second tooth characteristic element are,

Characterized by including the position, length, degree of rotation, and degree of inclination of each tooth,

The above medical treatment characteristics are:

Characterized by including the type of device, type of wire, type of setup, type of bracket used according to the setup, bonding method, and whether or not a rubber band is used,

The patient characteristic elements are,

Orthodontic method recommendation method using artificial intelligence, which includes the patient's aesthetic view, gender, age, and eating habits.