KR102392912B1 - Booth based self-oral examination device - Google Patents

Abstract

It relates to a booth-based self-examination device that enables anyone to easily self-examine themselves through a non-face-to-face oral examination booth to optimally manage their oral cavity, thereby promoting oral health. After taking a picture of the oral cavity, correcting the oral image of the user, mapping the corrected oral image and diagnosis request information to generate oral examination diagnosis request information, and sending the generated oral examination diagnosis request information to the oral care service server Oral examination booth, oral examination diagnosis request information provided from oral examination booth is transmitted to oral health management server to request oral examination diagnosis, and oral examination diagnosis result is transmitted to oral care service server and oral examination diagnosis request information A booth-based self-examination device, including an oral health management server that diagnoses the included oral image to generate oral health information, encrypts the generated oral health information, and transmits the result of oral examination to the oral care service server implement

Description

Booth based self-oral examination device

The present invention relates to a booth-based self-oral examination device, and more particularly, through a non-face-to-face oral examination booth (Booth), anyone can easily self-examine the oral cavity to optimally manage the oral cavity, and through this, oral health It relates to a booth-based self-examination device designed to promote promotion.

Although oral diseases can be highly preventable through proper preventive treatment and continuous management, many patients with oral diseases are still aware of oral prevention, such as not receiving a diagnosis or requesting treatment from a doctor unless there is a problem with oral health. This is insufficient.

Unlike other diseases, prevention of oral disease is very important, and even simple procedures such as scaling can prevent periodontal disease. It can be seen that not only oral health care but also cost and benefit are great.

In predicting the patient's current oral condition, accurate examination and diagnosis results and objective numerical information are required, not the subjective opinion of a dentist or dental hygienist, but there is no system for objectively calculating the oral health condition.

The two major diseases of the oral cavity are tooth decay (dental caries) and periodontal disease. In particular, periodontal disease, which means periodontitis and gingivitis, is difficult to prevent in advance because the detection is delayed because there is no pain in the beginning and it progresses chronically.

Therefore, various methods for diagnosing such oral disease states in advance, and based on this, various methods for improving oral health and preventing oral diseases have been studied and proposed. to <Patent Document 3> are disclosed.

<Patent Document 1> receives user condition information including information on at least one of a user's gender, age, periodontal disease, and goal setting information from a user terminal and treatment information at a user's affiliated medical institution. In addition, information on oral care products is received from an oral care product store. Thereafter, information on a specific oral care product included in a specific category corresponding to the user's condition information and treatment information is provided to the user terminal to provide a user-customized oral care service.

In addition, <Patent Document 2> examines the patient's oral condition, converts the oral examination index calculation standard data including the patient's oral examination data, residential area and age information into big data, and then analyzes this to analyze the patient's The influence of the oral examination index calculation standard data on oral health is determined according to the region of residence and age. Then, by giving weight to the oral examination index calculation standard data, the oral health is managed by digitizing the reference data for the oral examination index calculation.

In addition, <Patent Document 3> collects the user's personal information, the user's oral hygiene behavior data and oral questionnaire data, and oral examination data generated by the user visiting a specialized medical institution. By integrating and analyzing each piece of information collected in this way, the user's risk of oral disease is evaluated and personalized service is provided.

However, the conventional oral disease management systems as described above are a method of generating oral disease management information by analyzing the user's personal information, oral data and questionnaire data, and oral examination data generated through a specialized medical institution, and have poor real-time performance and current users Since it is not a method of analyzing oral images of

In addition, conventional techniques have a disadvantage in that it is difficult for a user to recognize his or her periodontal disease state in real time.

In addition, the prior art also has a disadvantage in that it is not possible to accurately check the state of his or her periodontal disease in a non-face-to-face manner.

Republic of Korea Patent Publication 10-2017-0050467 (published on May 11, 2017) (User-customized oral care service providing method and oral care service providing server) Republic of Korea Patent Registration 10-1868979 (registered on June 12, 2018) (Oral health management system and method using deep learning algorithm) Republic of Korea Patent Registration 10-1788030 (Registered on October 13, 2017) (Oral disease risk diagnosis and oral care system and method)

Therefore, the present invention has been proposed to solve all the problems that occur in the prior art as described above, and anyone can easily self-examine themselves through a non-face-to-face oral examination booth (Booth) to optimally manage the oral cavity. The purpose of this is to provide a booth-based self-examination device designed to promote oral health through this.

In order to achieve the above object, "booth-based self-oral examination device" according to the present invention,

After taking a picture of the user's oral cavity, correcting the captured user's oral image, mapping the corrected oral image and diagnosis request information to generate oral examination diagnosis request information, and sending the generated oral examination diagnosis request information to the oral care service server Transmitting oral examination booth;

an oral care service server that transmits the oral examination diagnosis request information provided from the oral examination booth to an oral health management server to request an oral examination diagnosis, and transmits an oral examination diagnosis result to a user; and

The oral health information is generated by diagnosing the oral image included in the oral examination diagnosis request information transmitted from the oral care service server, and the generated oral health information is encrypted and transmitted to the oral care service server as an oral examination diagnosis result. It is characterized in that it includes a health management server.

In the above, the oral examination booth, the oral care service server, and the oral health management server improve security even in case of data leakage due to hacking through the transmission and reception of the encrypted oral examination diagnosis result.

In the above, the user sets the transmission location to transmit the oral examination diagnosis result to the user terminal or sets the transmission location by paper printing.

In the above, the oral examination booth is,

body;

a camera built into the body and photographing the user's oral cavity;

a controller built into the body, controlling the correction and transmission of the user's oral image taken by the camera, and controlling the output of the oral examination diagnosis result;

It is installed on the body, characterized in that it comprises a printer for printing the oral examination diagnosis results on paper under the control of the controller.

In the above controller,

a manipulation unit including a plurality of function buttons for a user to manipulate for oral examination, and outputting a function input signal corresponding to the manipulation of the function buttons;

Recognizing the input function according to the function input signal output from the operation unit, controlling correction and transmission of the user's oral image photographed by the camera, and comprising a control unit for controlling the output of the oral examination diagnosis result do.

In the above controller,

Oral image correction unit to increase the sharpness by correcting the user's oral image taken through the camera under the control of the control unit;

Under the control of the control unit, oral examination diagnosis request information including the oral image corrected by the oral image correction unit and diagnosis request information is transmitted to the oral care service server to request an oral examination diagnosis, and the received oral examination diagnosis result It characterized in that it comprises a communication unit for transmitting the to the control unit.

In the above, the controller acquires the user's answer information to the oral examination questionnaire through the operation unit, and generates the questionnaire response information using the obtained user's answer information, characterized in that it comprises a questionnaire response unit for transmitting to the control unit.

In the above, the oral health management server is characterized in that when transmitting the oral examination diagnosis result, the oral examination booth ID and the access token using the user information are used to limit the authority of the access target to improve security.

In the above, the oral health management server learns the received oral image with a CNN (Convolutional Neural Network) algorithm, which is an artificial intelligence algorithm, determines whether a photo can be analyzed, whether or not to correct, and whether to extract, and uses the determined result information to detect an object (Object Detection). ) to obtain dental caries state information and prosthesis state information, and an oral health calculation unit for learning the obtained dental caries state information and prosthesis state information with an Artificial Neural Network (ANN) algorithm to determine the oral health state; It is characterized in that it comprises an oral health information providing unit that generates the oral health information determined by the oral health calculation unit as an oral examination diagnosis result, and encrypts the generated oral examination diagnosis result and transmits it to the oral care service server.

In the oral health calculation unit, an image registration unit for registering the oral image transmitted from the oral examination booth as an oral health prediction target; By learning the image registered in the image registration unit with a CNN (Convolutional Neural Network) algorithm, it is determined whether the image can be analyzed, whether it is corrected, and whether or not tooth extraction is performed, and the result information is analyzed by object detection to obtain dental caries status information. and an oral diagnostic unit that acquires the prosthesis status information and determines the oral health status by learning the acquired orthodontic status information, tooth extraction status information, dental caries status information, and prosthesis status information with an Artificial Neural Network (ANN) algorithm. do it with

According to the present invention, there is an effect of promoting oral health by allowing anyone to easily self-examine the oral cavity through an oral examination booth (Booth) to check the oral condition.

In addition, according to the present invention, it is possible to analyze the user's oral health in real time, and by analyzing the oral health with the oral image, there is an effect of promoting accuracy in the analysis of oral diseases.

In addition, according to the present invention, there is an effect that can improve the convenience of the user by promoting preventive oral care through the oral examination booth.

1 is an overall configuration diagram of a booth-based self-examination device according to the present invention;
Figure 2 is a configuration diagram of an embodiment of the examination booth of Figure 1;
3 is a block diagram of an embodiment of the oral health calculation unit of FIG. 1;
4 to 7 are diagrams illustrating an artificial intelligence algorithm for analyzing an oral image in the present invention.

Hereinafter, a booth-based self-oral examination device according to a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

The terms or words used in the present invention described below should not be construed as being limited to conventional or dictionary meanings, and the inventor may appropriately define the concept of terms to describe his invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention based on the principle that it can be.

Accordingly, the embodiments described in this specification and the configurations shown in the drawings are only preferred embodiments of the present invention, and do not represent all of the technical spirit of the present invention, so various equivalents and It should be understood that there may be variations.

1 is an overall configuration diagram of a booth-based self-examination apparatus according to a preferred embodiment of the present invention, and may include an oral examination booth 100 , an oral care service server 200 and an oral health management server 300 . .

The oral examination booth 100 captures the user's oral cavity, corrects the captured user's oral image, maps the corrected oral image and the diagnosis request information to generate the oral examination diagnosis request information, and the generated oral examination diagnosis It serves to transmit the request information to the oral care service server (200).

Here, the user may use the oral examination booth 100 to provide user personal information (user smartphone information, e-mail information, etc.) and general data such as questionnaire data. There are two types of oral examinations: simple examination and general examination. In the case of simple examination, it is only necessary to provide the user's personal information (device ID, user information) and oral image. Just provide an image.

The user receives the oral examination diagnosis result using the oral examination booth 100 or the user terminal, recognizes his or her oral health condition through this, and visits a dental hospital to take follow-up measures if the oral health condition is predicted to be poor It is desirable to take care of oral health by taking Here, the user terminal may be implemented as a mobile device such as a smart phone and a smart pad, a personal computer or a notebook computer capable of the Internet, and the like.

The oral examination booth 100 is a hardware form installed in public places and institutions (eg, schools, government offices, public health centers, companies, industrial complexes, etc.), so that oral diseases can be easily inspected in various places such as public places and institutions. It is a booth type inspection equipment.

Here, the user requests an oral examination through the oral examination booth 100, and sets the transmission location to transmit the oral examination diagnosis result to the user terminal (eg, user's smartphone), or transmits it by paper printing (print output) You can set the location.

That is, the user can receive the oral examination diagnosis result directly from the user's smartphone by selecting the user's smartphone as a means to receive the oral examination diagnosis result, and select a printout to be placed in a predetermined position of the oral examination booth 100 Through the provided print, the oral examination results can be checked in print in real time at the site.

This oral examination booth 100 is provided with a body 101 that is built-in or installed with various equipment that allows a user to enter, photograph an oral cavity, request an oral examination, and to check the oral examination result in real time in the field as a printout. This body 101 is provided with sufficient space so that there is no discomfort when one user enters and takes an oral cavity.

A camera 102 for photographing the user's oral cavity is installed at a predetermined position of the body 101 . By photographing the oral cavity through the camera 102, the user does not need to prepare a separate oral imaging equipment.

The body 101 is provided with a controller 110, which is a control device for controlling the correction and transmission of the user's oral image photographed by the camera 102, and for controlling the output of the oral examination diagnosis result at a predetermined position. In the controller 110 , a user may select a function through a touch or select a transmission location of an oral examination diagnosis result.

In addition, a printer 120 is installed at an arbitrary position of the body 101 to print the oral examination diagnosis result on paper under the control of the controller 110 . Through the printer 120, the user can check the oral examination diagnosis result in print in real time in the field.

Meanwhile, as shown in FIG. 2 , the controller 110 includes a plurality of function buttons for the user to operate for oral examination, and the operation unit 111 for outputting a function input signal corresponding to the operation of the function button. ) is included. Here, when the input device is a touch panel, the manipulation unit 111 may select or set various functions by touching a function button displayed as an icon on the touch panel. When the operation unit 111 is not a touch panel, a display device for checking functions or displaying information for checking other information or using diagnostic equipment and a plurality of buttons for inputting functions must be separately provided. In the present invention, it is assumed that the manipulation unit 111 is implemented as a touch panel, so that information input and information display are possible.

The controller 110 recognizes an input function according to the function input signal output from the operation unit 111, controls correction and transmission of the user's oral image captured by the camera 102, and results of oral examination diagnosis and a control unit 113 for controlling the output of

The control unit 113 requests an oral examination using only the oral image corrected by the oral image correcting unit 115 and the user's personal information when the user selects a simple examination among examination modes. When the user selects a general checkup in the checkup mode, the oral examination is requested using the oral image corrected by the oral image correction unit 115, the questionnaire response information generated by the questionnaire response unit 116, and the user's personal information. . Here, the user personal information may include user information and device ID information (oral examination booth ID information). This user's personal information can be used as the issuance information of a web token (access token) for security when the oral examination result information is transmitted later.

In addition, the controller 110 is an oral image correction unit 115 that enhances sharpness by correcting the user's oral image taken through the camera 102 under the control of the control unit 113, the control of the control unit 113 The oral examination diagnosis request information including the oral image corrected by the oral image correction unit 115 and the diagnosis request information is transmitted to the oral care service server 200 to request the oral examination diagnosis, and the received oral examination and a communication unit 112 that transmits the diagnosis result to the control unit 113 . Here, the communication unit 112 is connected to the oral care service server 200 through a network.

The oral examination booth 100 and the oral health service server 200 may be connected to various wired and wireless networks, and a communication interface may be formed with real-time properties.

The reason for implementing a plurality of servers as the oral care service server 200 and the oral health management server 300 is to increase the security of the diagnosis result to prevent leakage of personal information. Actual health care and personal information are all managed by the oral health management server 300, but the security is improved by transmitting information through a web token, and the oral care service server 200 is simply an interface of information and simple procedures such as hospital reservations. By processing only the service, prompt service was made.

In addition, the controller 110 acquires the user's answer information to the memory 114 for storing various information and the oral examination questionnaire through the operation unit 111, and uses the obtained user's answer information to display the questionnaire response information. It includes a questionnaire response unit 116 that is generated and transmitted to the control unit 113 , and a print output unit 117 that transmits the oral examination diagnosis result to the printer 120 under the control of the control unit 113 .

The oral care service server 200 transmits the oral examination diagnosis request information provided from the oral examination booth 100 to the oral health management server 300 to request an oral examination diagnosis, and transmits the oral examination diagnosis result to the user. plays a role

This oral care service server 200 confirms the transmission location of the oral examination diagnosis result included in the oral examination diagnosis request information transmitted from the oral examination booth 100, and oral examination according to the transmission position of the oral examination diagnosis result The diagnosis result is transmitted to the oral examination booth 100 or transmitted to the user terminal registered by the user.

The oral health management server 300 generates oral health information by diagnosing the oral image included in the oral examination diagnosis request information transmitted from the oral care service server 200, and encrypts the generated oral health information to diagnose the oral examination As a result, it serves to transmit to the oral care service server (200).

Here, it is preferable that the oral examination booth 100, the oral care service server 200, and the oral health management server 300 improve security even in case of data leakage due to hacking through the transmission and reception of the encrypted oral examination diagnosis result.

It is preferable that the oral health management server 300 improves security by limiting the authority of an access target using an access token using an oral examination booth ID and user information when transmitting an oral examination diagnosis result.

The oral health management server 300 learns the received oral image with a CNN (Convolutional Neural Network) algorithm, which is an artificial intelligence algorithm, determines whether the photo can be analyzed, whether or not to correct it, and whether or not to extract, and detects the determined result information ( Object Detection) to obtain dental caries status information and prosthesis status information, and learn the acquired dental caries status information and prosthesis status information with ANN (Artificial Neural Network) algorithm to determine oral health status oral health calculation unit 310 ), an oral health information providing unit ( 320), and a database 330 in which big data for oral diagnosis, personal information, encryption algorithm, and the like are stored.

The oral health information providing unit 320 serves to transmit the oral examination diagnosis result to the oral care service server 200 .

As shown in FIG. 3 , the oral health calculation unit 310 registers the oral image transmitted from the oral examination booth 100 as an oral health prediction target image registration unit 311, the image registration unit 311 registration By learning the image from the CNN (Convolutional Neural Network) algorithm, it determines whether the image can be analyzed, whether it is corrected or not, and whether or not the tooth is extracted. It may include an oral diagnosis unit 312 for determining oral health status by learning the acquired information on whether or not orthodontics and whether or not tooth extraction has been obtained, dental caries status information and prosthesis status information using an artificial neural network (ANN) algorithm.

The operation of the booth-based self-examination apparatus according to the present invention configured as described above will be described in detail as follows.

First, an oral examination booth 100 for self-diagnosis of oral examination is installed in public places and institutions such as schools, government offices, public health centers, companies, and industrial complexes.

A user using the facility visits the oral examination booth 100 installed in the facility to self-examine and manage their oral health condition.

Thereafter, the user makes a request for oral examination through the operation unit 111 provided in the controller 110 in order to check the oral health state.

When an oral examination request is generated through the manipulation unit 111 , the control unit 113 in the controller 110 guides the oral examination method through the screen of the manipulation unit 111 made of a touch panel.

Here, as a guide to the oral examination method, the user's personal information is requested and the location to transmit the information of the oral examination diagnosis result is selected. The user inputs simple personal information (name, date of birth, phone number, etc.) in response to such a request.

Here, the user enters basic user personal information as personal information, and for more accurate oral examination, the user registers his/her medical history, medications or body specific information (high blood pressure, low blood pressure, diabetes, heart disease, constipation, pregnancy, etc.) You may.

Thereafter, the user selects a location to transmit the information of the oral examination diagnosis result, that is, a location to receive the oral examination diagnosis result. For example, an oral examination diagnosis result may be directly received in printed form at the oral examination booth 100 on site, or a user terminal such as a smartphone carried by the user may be selected as the oral examination diagnosis result receiving location.

When the selection of the personal information input and oral examination diagnosis result transmission location is finished, the control unit 113 guides the camera 102 to photograph the oral cavity through the screen of the operation unit 111 . That is, the mouth is opened at the center of the camera 102 to guide oral photography.

Here, since the oral examination booth 100 is a facility used by a large number of public, contamination can be easily made, and in particular, since it is an oral diagnosis device, contamination can be further aggravated by bacteria in the mouth. Due to the contamination problem of the camera 102, users may be hesitant to use it.

Therefore, in order to solve the contamination problem of the camera 102, a camera sterilization device 103 capable of removing the contamination of the camera 102 is provided at a predetermined position of the body 101 of the oral examination booth 100. Here, the camera sterilization apparatus 103 may use a chemical sterilization method of spraying a sterilizing solution to the camera 102 and sterilizing through a drying function, or a physical sterilization method of sterilizing using a wavelength such as ultraviolet rays.

By sterilizing the camera 102 using this sterilization method, the camera 102 is prevented from being contaminated and at the same time, the user can always use the camera 102 in a clean state.

The user photographs the oral cavity on the camera 102 according to the guide information guided through the operation unit 111 .

When oral imaging is performed, the control unit 113 transmits the oral image obtained through the camera 102 to the oral image correcting unit 115 .

The oral image correction unit 115 improves the sharpness by correcting the input oral image. That is, the input oral image is an atypical image, and the image quality or the photographing position may be changed by a camera or a photographer, so that the examination result may be different.

Therefore, correction is required for atypical photos.

For the correction of the atypical picture, the input oral image is divided into preset sizes, and the direction is adjusted to become a frontal image. Directional control is recognized as a method of recognizing the position through the oral structure and can be adjusted in the front. Then, the image sharpen filter (Image Sharpen Filter) to filter the direction-adjusted segmented image to increase the sharpness. Here, since the technique of increasing the sharpness of a picture with the image chaffine filter is a known technique in the image processing field, a detailed description thereof will be omitted.

Here, the user selects the examination mode in a state in which oral photographing is finished.

That is, when oral imaging is finished, a checkup list is displayed on the screen, and the user selects a checkup mode on this screen. Here, the checkup list includes a simple checkup and a general checkup mode.

The simple check-up is a mode that requests a self-examination using only the user's personal information and oral image, and the general check-up is a mode that requests the self-examination by providing the user's personal information, oral image and questionnaire information.

In the general examination mode, the questionnaire response unit 116 displays the questionnaire on the operation unit 111 and allows the user to select a response. The user responds to the questionnaire response request displayed on the operation unit 111 . The response can be performed simply with a touch to select an answer. Complete the response according to the questionnaire response request and request an oral examination diagnosis.

When the simple checkup is selected or the questionnaire response of the general checkup ends, the control unit 113 determines that the user's action has been completed.

Thereafter, the control unit 113 generates oral examination diagnosis request information including user personal information, oral examination diagnosis result transmission location information, corrected oral image information, and medical history or medication information in the simple diagnosis mode. In addition, in the general examination mode, oral examination diagnosis request information is generated including user personal information, oral examination diagnosis result transmission location information, corrected oral image information, questionnaire response information, and medical history information, such as medication information.

Thereafter, the generated oral examination diagnosis request information is transmitted to the oral care service server 200 through the communication unit 112 .

The oral care service server 200 transmits the oral examination diagnosis request information to the oral health management server 300 when the oral examination diagnosis request information is received from the oral examination booth 100 connected through the network.

The image registration unit 311 of the oral health calculation unit 310 of the oral health management server 300 extracts only the oral image included in the transmitted oral examination diagnosis request information and registers it in the internal database as an oral health examination target image. Here, since the oral image is taken by an individual, the shooting environment is different, so there is no standard for the color of the actual shot image. Therefore, after setting the reference point, color correction is automatically performed so that all photos are identical to the reference point, and then saved.

Next, the oral diagnosis unit 312 learns the oral image with a CNN (Convolutional Neural Network) algorithm to determine whether the picture can be analyzed, whether or not to correct, and whether to extract. Next, the determined result information is analyzed by object detection to obtain dental caries status information, periodontitis status information, and prosthesis status information, and the obtained dental caries status information and prosthesis status information are analyzed using an Artificial Neural Network (ANN) algorithm. learning to determine the state of oral health.

For example, the presence of an oral image is determined by learning an oral image with a Convolutional Neural Network (CNN) algorithm. The process of determining the presence or absence of an oral image by learning an oral image with a CNN algorithm is shown in FIG. For this purpose, it is assumed that a CNN model that determines whether an image photographed and requested to be registered is an oral image is built. It is preferable to use the pre-trained CNN model by adding the oral image category to the already known CNN models such as VGG16 (https://neurohive.io/en/popular-networks/vgg16/) and ResNet50. The training data may be oral image data or image data of a category to be added.

Using these oral image data, the CNN model is trained to determine the presence or absence of an oral image. Here, the learning time may vary depending on the amount of learning data to be added.

As a result of checking the presence or absence of an oral image, if it is determined as an oral image, the oral image is learned by a CNN (Convolutional Neural Network) algorithm shown in FIG. 5 to determine whether or not correction is made. Here, Figure 5 is an example of a CNN model that determines whether or not correction from the input oral image. These CNN models can be built using AutoKeras. Transfer learning using pre-trained VGG16, ResNet50, etc. can also be used. Required data is oral photo data with/without braces, and by adding two categories of oral photos (with/without braces) to the CNN model, it is possible to simply determine whether or not to correct.

Correction can be determined using this CNN model, but this also requires sufficient learning time and data, and an increase in the training data results in an increase in the amount of computation. Therefore, it is possible to omit the learning process of the CNN (Convolutional Neural Network) algorithm for determining whether or not to calibrate by inducing the user to select whether to calibrate by creating a questionnaire.

When the questionnaire information is provided through the questionnaire preparation, the questionnaire information is classified by the FFNN (Feed Forward Neural Network) algorithm. Here, the FFNN algorithm is a machine learning algorithm in which a questionnaire response (user information) is an input and a diagnosis result is an output. It is desirable to design and use an FFNN suitable for the input/output structure using a Python-based library such as Tensorflow or Keras. For activation functions, loss functions, optimization methods, parallel computing structures, and overfitting problems, FFNN algorithms that have been recently studied and analyzed can be used. The input data (survey response) is preprocessed, and the preprocessed data is divided into training data and verification data. Then, learning data is learned through neural network learning, and the validation data and learning result data are verified and supplemented through a newly designed neural network. And when verification and supplementation are completed, the final model is output as a questionnaire diagnosis result.

It is also possible to determine whether or not correction is made using the CNN model constructed here, but it is also possible to additionally determine whether tooth extraction is performed using the same CNN model. By adding the tooth extraction mouth image category to the CNN model, it is possible to simply determine whether or not tooth extraction has occurred.

Next, the determined orthodontic information and tooth extraction information are analyzed by object detection to obtain dental caries status information and prosthesis status information. To this end, an object detection algorithm for determining detection of oral diseases (dental caries) and prostheses from the input oral image as shown in FIG. 6 is constructed. The object detection algorithm for determining oral disease and prosthesis detection uses the previously developed Faster R-CNN, SSD, YOLO (W.Liu et al., 2015, arXiv (http://arxiv.org/abs/1512.02325)), etc. Available. As data required for obtaining dental caries status information and prosthesis status information with the object detection algorithm, oral image data in which oral diseases and prostheses are displayed may be used. Accuracy can be improved by classifying whether or not to wear braces and learning. It has the advantage of being able to detect both dental caries and prostheses with one algorithm. Here, the dental caries status information may include information on the presence or absence of dental caries and information on the number of dental caries when dental caries exists, and the prosthesis status information includes information on the presence or absence of a prosthesis and information on the number of prostheses when there is a prosthesis. . Dental caries image learning checks which part of the entire oral region the oral image provided by the user is, and performs image learning after confirming the location of the oral region image, and through this, the presence or absence of dental caries and the number of dental caries are extracted. . In the same way, the presence or absence of the prosthesis and the number of prostheses are also extracted.

Then, the oral health status by learning the orthodontic information, tooth extraction information, dental caries status information, and prosthesis status information with the ANN (Artificial Neural Network) algorithm (2019 NIMS industrial math problem solving workshop proposal model) as shown in FIG. judge Here, the ANN algorithm, which is an artificial intelligence algorithm, determines an oral health state (oral health) by inputting the information on whether or not to orthodontic, information on whether or not to extract teeth, dental caries state information, and prosthetic state information as inputs. For this purpose, the oral health level judgment data of the patient corresponding to the reliable oral image data obtained from the specialist or the specialist may be used. In order to promote the accuracy of oral diagnosis, the acquired oral image data may be used as oral image data in which a professor-level specialist marks the affected area. The marking also marks the number of most cases related to teeth and gums, such as prostheses, resins, and low mineralization, as well as the degree of disease (in the case of caries, ICDAS grade, a system for discriminating dental caries), not the presence or absence of a simple disease.

When the oral health state determination is completed, oral health prediction information is generated and stored in an internal database.

Next, the oral health information providing unit 320 transmits the oral examination diagnosis result obtained through the determination to the oral care service server 200 .

At this time, in order to prevent unauthorized leakage of the oral examination diagnosis result, the oral examination diagnosis result is encrypted using an encryption module. Encryption uses a method of generating a 256-bit web access token using the device ID and user information of the received or pre-registered user terminal.

The encrypted oral examination diagnosis result is transmitted to the oral care service server 200 .

The oral care service server 200 checks the oral examination diagnosis result transmission location information included in the oral examination diagnosis request information, and transmits the oral examination diagnosis result to the oral examination booth 100 if it is received as a printed matter directly at the site. Contrary to this, when the oral examination diagnosis result transmission location is the user's terminal, the oral examination diagnosis result is converted into MMS data and transmitted to the user terminal registered by the user. Here, the oral examination diagnosis result may be in the form of an oral examination report.

Even if the oral health management server 300 is leaked to unauthorized persons by means such as hacking before the oral examination diagnosis result is transmitted to the user terminal or oral examination booth 100, the user device ID (oral examination booth 100) ID) and user information are encrypted web tokens, so others who do not know the user device ID and user information cannot check the oral examination result information, so security can be improved.

The communication unit 112 of the oral examination booth 100 transmits the received oral examination diagnosis result to the control unit 113 .

The control unit 113 decrypts the web access token using the registered user device ID (oral examination booth ID) and user information using the decoding module for the received oral examination diagnosis result. Decryption is the reverse of encryption. If the user device ID and user information match, the encrypted oral examination result can be checked. By using encrypted information when issuing web tokens in this way, it is possible to fundamentally prevent unauthorized users from accessing the oral examination diagnosis results.

The control unit 113 transmits the decoded oral examination diagnosis result to the print output unit 117 to be printed. The print output unit 117 converts the received oral examination diagnosis result into a data format suitable for the format of the printer 120 and transmits it to the printer 120 . The printer 120 prints the delivered oral examination diagnosis result on paper and then outputs it.

As a result, the user can check the oral examination result in real time as a printed product through the oral examination booth 100 at the site.

If the user selects the transmission location of the oral examination diagnosis result with the user terminal, the user receives the oral examination diagnosis result using the user terminal carried by the user. Thereafter, the web access token is decrypted using the registered user device ID and user information using the previously registered decryption module. Decryption is the reverse of encryption.

If the user device ID and user information match, the encrypted oral examination result can be opened.

By using encryption information when issuing web tokens in this way, it is possible to fundamentally prevent unauthorized users from accessing the oral examination diagnosis results.

The user judges the oral condition based on the oral diagnosis result.

Here, the oral diagnosis result is in the form of a report, and it is not information that a specialist diagnoses that there is a certain oral disease, but there may be a problem in a certain part, and if this state continues, the next problem will occur in the future.

For example, the oral diagnosis result can be divided into 10 steps.

Levels 1 to 3 are indicated as good, levels 4 to 7 are moderate, and levels 8 to 10 are marked as dangerous. Therefore, the user sees the oral diagnosis result, checks the stage, and manages the oral cavity through this.

In particular, if the user determines that there is a problem with the oral condition through the oral diagnosis result report (in the range of 8 to 10 stages of the oral diagnosis result), the user immediately visits the dentist to manage his or her oral health and prevent deterioration of oral health in advance. it will be preventable.

Although the invention made by the present inventor has been described in detail according to the above embodiment, the present invention is not limited to the above embodiment and it is common knowledge in the art that various changes can be made without departing from the gist of the present invention. It is self-evident to those who have

100: oral examination booth
101: body
102: camera
110: controller
111: control panel
112: communication department
113: control unit
114: memory
115: oral image correction unit
116: Questionnaire response unit
117: print output unit
120: printer
200: oral health service server
300: oral health management server
310: oral health calculation unit
311: image register
312: oral diagnostic unit
320: oral health information provider
330: database

Claims (10)

After taking a picture of the user's oral cavity, correcting the captured user's oral image, mapping the corrected oral image and diagnosis request information to generate oral examination diagnosis request information, and sending the generated oral examination diagnosis request information to the oral care service server Transmitting oral examination booth;
an oral care service server that transmits the oral examination diagnosis request information provided from the oral examination booth to an oral health management server to request an oral examination diagnosis, and transmits an oral examination diagnosis result to a user; and
The oral health information is generated by diagnosing the oral image included in the oral examination diagnosis request information transmitted from the oral care service server, and the generated oral health information is encrypted and transmitted to the oral care service server as an oral examination diagnosis result. including a health management server;
The oral examination booth is built into the body, a camera for photographing the user's oral cavity;
It is built into the body, and includes a controller that controls the correction and transmission of the user's oral image photographed by the camera, and controls the output of the oral examination diagnosis result,
The controller includes an oral image correction unit that enhances sharpness by correcting the user's oral image taken through the camera,
The oral image correction unit divides the input oral image into preset sizes, recognizes the oral image by a method of recognizing the position through the oral structure, and adjusts the direction so that the oral image becomes a frontal image,
The oral examination booth is equipped with a camera sterilization device at a predetermined position of the body in order to solve the contamination problem of the camera, and booth-based self-oral examination, characterized in that the camera sterilizer is used to remove the contamination of the camera Device.
The method according to claim 1, The oral examination booth, oral care service server, and oral health management server through the transmission and reception of the encrypted oral examination diagnosis result to improve security even in case of data leakage due to hacking, booth-based self-oral examination Device.
delete The method according to claim 1, The oral examination booth,
Booth-based self-examination device, characterized in that it is installed on the body, comprising a printer for printing the oral examination diagnosis results on paper under the control of the controller.
The method according to claim 4, The controller,
a manipulation unit including a plurality of function buttons for a user to manipulate for oral examination, and outputting a function input signal corresponding to the manipulation of the function buttons;
Recognizing the input function according to the function input signal output from the operation unit, controlling correction and transmission of the user's oral image photographed by the camera, and comprising a control unit for controlling the output of the oral examination diagnosis result booth-based self-examination device.
The method according to claim 5, The controller,
Under the control of the control unit, oral examination diagnosis request information including the oral image corrected by the oral image correction unit and diagnosis request information is transmitted to the oral care service server to request an oral examination diagnosis, and the received oral examination diagnosis result Booth-based self-oral examination device, characterized in that it comprises a communication unit for transmitting the to the control unit.
The method of claim 5, wherein the controller includes a questionnaire response unit that obtains the user's answer information to the oral examination questionnaire through the operation unit, generates the questionnaire response information using the obtained user's response information, and transmits it to the control unit booth-based self-examination device.
The method according to claim 1, wherein the oral health management server improves security by limiting the authority of the access target by using an access token using the oral examination booth ID and user information when transmitting the oral examination diagnosis result. Booth-based self-examination device.
The method according to claim 1, The oral health management server is an artificial intelligence algorithm CNN (Convolutional Neural Network) algorithm by learning the received oral image to determine whether the picture can be analyzed, whether or not correction and tooth extraction, and detects the determined result information as an object An oral health calculation unit that obtains dental caries status information and prosthesis status information by analyzing (Object Detection), and determines oral health status by learning the acquired dental caries status information and prosthesis status information with an Artificial Neural Network (ANN) algorithm; Booth-based self comprising an oral health information providing unit that generates the oral health information determined by the oral health calculation unit as an oral examination diagnosis result, and encrypts the generated oral examination diagnosis result and transmits it to the oral care service server oral examination device.
The method according to claim 9, wherein the oral health calculation unit image registration unit for registering the oral image transmitted from the oral examination booth as an oral health prediction target; By learning the image registered in the image registration unit with a CNN (Convolutional Neural Network) algorithm, it is determined whether the image can be analyzed, whether it is corrected, and whether or not tooth extraction is performed, and the determined result information is analyzed by object detection to obtain dental caries status information. and an oral diagnostic unit that acquires the prosthesis status information and determines the oral health status by learning the acquired orthodontic status information, tooth extraction status information, dental caries status information, and prosthesis status information with an Artificial Neural Network (ANN) algorithm. booth-based self-examination device.

Images