Method and system for diagnosing oral diseases in companion animals

Abstract

The present invention provides a method and system for diagnosing oral diseases in companion animals, the method being performed by a health management server and including the steps of: generating health standard data by matching basic condition information and basic result data; receiving condition measurement information of a test subject from a user terminal; and generating health result data by comparing and analyzing the condition measurement information based on the health standard data, wherein the generating health standard data can include the steps of preprocessing images included in basic radiography information included in the basic condition information; extracting analyzable analysis images from the preprocessed images; extracting region-specific analysis images for a plurality of disease analyses from the analysis images and diagnosing the presence or absence of oral diseases for the region-specific analysis images to generate basic diagnosis data; determining disease progression stages for the region-specific analysis images based on the basic diagnosis data to generate basic assessment data; and generating basic result data including the basic diagnosis data and the basic assessment data corresponding to the basic diagnosis data.

Description

[Technical Field]

[0001] The present invention relates to a method and system for diagnosing oral diseases in companion animals, and to a diagnostic method and system that can quickly determine the presence or absence of a disease in the early stages when a disease occurs in the oral cavity of a companion animal, thereby enabling prompt medical treatment and preventing misdiagnosis. [Background technology]

[0002] As the population ages and single-person households increase, people are becoming increasingly self-centered and emotionally desolate. As a result, an increasing number of people view pets as family members or companions, and the companion animal market is growing steadily.

[0003] When companion animals start to show unusual symptoms, most people take them to a veterinary hospital for treatment or solve the symptoms based on information they receive from people around them or via the internet or telephone.

[0004] However, much of the information obtained from people around them or through the internet or telephone is incorrect, which can make treatment difficult. Even if patients visit the hospital in person, they often have to wait long periods of time, and due to the hospital's heavy workload, customers often do not receive proper service (see Korean Patent Publication No. 10-2021-0108686 (published on September 3, 2021)).

[0005] The matters described above as background art are merely intended to enhance understanding of the background of the present invention and should not be construed as acknowledging that they constitute prior art already known to those skilled in the art. Summary of the Invention [Problem to be solved by the invention]

[0006] The problem to be solved by the present invention is to provide a method and system for diagnosing oral diseases in companion animals.

[0007] The problems to be solved by the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0008] To solve the above-mentioned problems, a companion animal oral disease diagnosis method according to one embodiment of the present invention includes the steps of: matching basic condition information and basic result data to generate health standard data; receiving condition measurement information of the test subject from a user terminal; and comparing and analyzing the condition measurement information based on the health standard data to generate health result data; wherein the step of generating the health standard data may include the steps of preprocessing images included in basic imaging information included in the basic condition information; extracting analyzable analysis images from the preprocessed images; extracting site-specific analysis images for multiple disease analyses from the analysis images and diagnosing the presence or absence of oral diseases for the site-specific analysis images to generate basic diagnostic data; determining the disease progression stage for the site-specific analysis images based on the basic diagnostic data to generate basic judgment data; and generating basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

[0009] In one embodiment of the present invention, the generating of the health result data may include extracting actual analysis images from actual photographing information included in the status measurement information of the test subject; extracting region-specific actual analysis images from the actual analysis images and diagnosing the presence or absence of oral diseases for the region-specific actual analysis images to generate actual diagnosis data; determining disease progression stages for the region-specific actual analysis images based on the actual diagnosis data to generate actual judgment data; and generating the health result data including the actual diagnosis data and the actual judgment data corresponding to the actual diagnosis data.

[0010] In one embodiment of the present invention, the step of extracting the actual analysis image may include a step of analyzing the degree of shaking of the first image when the actual photographing information includes a first image; a step of determining whether the degree of shaking of the first image is lower than a first reference value when the degree of shaking of the first image is analyzed as a first numerical value; a step of determining whether the first numerical value is lower than the first reference value when the first numerical value is determined to be lower than the first reference value; a step of determining whether the clarity of the first image is higher than a second reference value when the clarity of the first image is analyzed as a second numerical value; a step of determining whether the second numerical value is higher than the second reference value when the second numerical value is determined to be higher than the second reference value when the first image is analyzed as an image of which part of a companion animal the first image is an image of; and a step of classifying the first image as an analyzable image and extracting the first image as the actual analysis image when the first image is analyzed as an image of an oral cavity region.

[0011] In one embodiment of the present invention, the step of generating the actual diagnostic data may include a step of analyzing the brightness of the first image when the first image is extracted as the actual analysis image; a step of checking whether the third value is within a reference range when the brightness of the first image is analyzed as a third value; a step of determining that correction of the first image is unnecessary when it is confirmed that the third value is within the reference range; a step of setting a correction value for the first image based on the third value when it is confirmed that the third value is outside the reference range; and a step of performing brightness correction on the first image using the correction value.

[0012] In one embodiment of the present invention, the step of generating the actual diagnostic data may further include the steps of: cropping an area occupied by teeth on the first image and extracting it as a second image; analyzing whether there are symptoms of at least one of tooth decay, tartar, dental fracture, tooth discoloration, remaining baby teeth, and tooth loss based on the second image, and diagnosing the presence or absence of oral disease for the tooth area, and generating the actual diagnostic data; cropping an area occupied by gums on the first image and extracting it as a third image; and analyzing whether there are symptoms of at least one of gum inflammation and gum tumor based on the third image, and diagnosing the presence or absence of oral disease for the gum area, and generating the actual diagnostic data.

[0013] In one embodiment of the present invention, the step of generating the basic result data may include a step of visually analyzing the analysis image by region based on the basic information of the test subject included in the basic condition information, and classifying the oral disease as "present" and labeling the basic diagnosis data if tartar is present on the teeth of the test subject or inflammation is present in the gums of the test subject.

[0014] In addition, a companion animal oral disease diagnosis system according to another embodiment of the present invention for solving the above-mentioned problems includes a user terminal that generates status measurement information including actual photographed information obtained from a test subject; and a health management server that iteratively learns health standard data generated by matching basic status information with basic result data, analyzes the status measurement information, and generates health result data for the test subject; wherein the health management server extracts actual analysis images from the actual photographed information, simultaneously analyzes actual analysis images for each region extracted from the actual analysis images, diagnoses the presence or absence of oral diseases for the test subject, and generates actual diagnosis data, and based on the actual diagnosis data The health result data includes actual judgment data generated by determining the disease progression stage of the oral disease based on the basic condition information, preprocessing images included in the basic imaging information included in the basic condition information, extracting analyzable analysis images from the images, extracting site-specific analysis images for multiple disease analyses from the analysis images, diagnosing the presence or absence of oral disease for the site-specific analysis images, and generating basic diagnostic data, determining the disease progression stage for the site-specific analysis images based on the basic diagnostic data, and generating basic judgment data, and generating basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

[0015] A program according to an embodiment of the present invention is stored in a computer-readable recording medium so that the program can be combined with a computer, which is hardware, to perform the companion animal oral disease diagnosis method.

[0016] Other details of the invention are included in the detailed description and drawings. [Effects of the Invention]

[0017] According to the present invention, when an abnormality occurs in the subject of examination, particularly in the oral cavity of a companion animal, the oral condition of the companion animal can be diagnosed using a portable terminal device to quickly and accurately determine the current condition of the companion animal, thereby providing confidence to the caregiver of the companion animal.

[0018] According to the present invention, the current condition of a companion animal can be accurately diagnosed in real time using a portable terminal, thereby increasing the convenience and reliability of the user.

[0019] According to the present invention, by receiving hospital information on the current condition of a companion animal, the companion animal's illness can be treated early at a hospital that can treat the illness, thereby protecting the health of the companion animal.

[0020] According to the present invention, notification information about companion animals is continuously provided to pet owners, thereby encouraging them to return to the veterinary clinic and preventing them from abandoning the pet.

[0021] According to the present invention, by sharing the result data of companion animals with the linked service, the condition of companion animals can be more accurately understood and responded to, thereby giving confidence to the guardians of companion animals.

[0022] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram for explaining a companion animal oral disease diagnostic system according to one embodiment of the present invention. [Figure 2] 2 is a diagram for explaining a detailed configuration of the companion animal oral disease diagnostic system shown in FIG. 1. [Figure 3] 10 is a diagram illustrating basic result data labeled in accordance with basic condition information; [Figure 4] 10 is a diagram for explaining a method for verifying basic result data. [Figure 5] 1 is a diagram illustrating a method for diagnosing oral diseases in companion animals according to one embodiment of the present invention. [Figure 6] 6 is a detailed diagram illustrating a method for generating the health standard data shown in FIG. 5. [Figure 7] 7 is a detailed diagram illustrating a method for generating basic result data shown in FIG. 6. [Figure 8] 1 is a diagram illustrating a process of extracting an actual analysis image according to an embodiment of the present invention; [Figure 9] 10 is a diagram showing the results of extracting an actual analysis image. [Figure 10] 1 is a diagram illustrating a process of performing brightness correction on an image according to an embodiment of the present invention. [Figure 11] 10 is a diagram showing a result of performing brightness correction on an image. [Figure 12] 1 is a diagram illustrating a process of diagnosing the presence or absence of oral diseases and generating actual diagnostic data according to an embodiment of the present invention. [Figure 13] 10 is a diagram showing the results of extracting an analysis image by region. DETAILED DESCRIPTION OF THE INVENTION

[0024] The advantages and features of the present invention, as well as methods for achieving them, will become more apparent from the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and may be embodied in various different forms. However, the present invention is defined only by the scope of the claims, and the present invention is not limited to the embodiments disclosed below.

[0025] The terms used in this specification are for the purpose of describing the embodiments and are not intended to limit the present invention. In this specification, the singular includes the plural unless otherwise specified in the context. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other elements in addition to the elements referenced. The same reference numerals refer to the same elements throughout this specification, and "and / or" includes each and every combination of one or more of the referenced elements. Although terms such as "first," "second," etc. are used to describe various elements, these elements are not limited by these terms. These terms are used merely to distinguish one element from another. Therefore, a first element referred to below may of course be a second element within the technical spirit of the present invention.

[0026] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in the sense that they can be commonly understood by a person of ordinary skill in the art to which the present invention belongs. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless they are clearly and specifically defined.

[0027] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0028] Figure 1 is a conceptual diagram for explaining a companion animal oral disease diagnostic system according to one embodiment of the present invention, Figure 2 is a diagram for explaining the detailed configuration of the companion animal oral disease diagnostic system shown in Figure 1, Figure 3 is a diagram for explaining basic result data labeled according to basic condition information, and Figure 4 is a diagram for explaining a method for verifying basic result data.

[0029] 1 and 2, a companion animal oral disease diagnosis system 1000 according to an embodiment of the present invention may include a user terminal 10, a health management server 20, a service link terminal 30, and an administrator terminal 40. In this case, the administrator terminal 40 may be omitted.

[0030] Here, the user terminal 10, the health management server 20, the service link terminal 30, and the manager terminal 40 can transmit and receive data in real time in synchronization using a wireless communication network. The wireless communication network may support various long-distance communication methods, such as Wireless LAN (WLAN), Digital Living Network Alliance (DLNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Code Division Multi Access 2000 (CDMA2000), Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (EV-DO), Wideband CDMA (WCDMA), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTEA), Wireless Mobile Broadband Service (WMBS), Bluetooth Low Energy (BLE), Zigbee, and Radio Frequency (RF). Various communication methods such as, but not limited to, IEEE 802.11a (IEEE 802.11b) and LoRa (Long Range) may be applied. However, the present invention is not limited to these, and various widely known wireless or mobile communication methods may be applied.

[0031] First, in this embodiment, the companion animal oral disease diagnosis system 1000 is used to photograph the oral region of companion animals, particularly puppies, and determine whether or not there is an oral disease and, if so, the stage of progression of the disease, but this is not limited thereto. For example, oral diseases of various animals, including vertebrates such as mammals, birds, reptiles, amphibians, and fish, and invertebrates such as arthropods and mollusks, living with a guardian, companion, or owner (hereinafter referred to as guardian), as well as oral diseases of humans can be measured.

[0032] The user terminal 10 is a portable terminal carried by the caretaker of the companion animal 1, and can operate using an application program (or application) in the present disclosure, and such application can be downloaded from an external server or the health management server 20 via wireless communication. For example, the user terminal 10 can include various terminals such as, but not limited to, a smartphone, a PDA (Personal Digital Assistant), a tablet, a wearable device (including, for example, a smartwatch, a smart glass, a head mounted display (HMD), etc.), and various Internet of Things (IoT) terminals.

[0033] As shown in FIG. 2, the user terminal 10 may include a photographing unit 100, a transceiver unit 110, a memory unit 120, a display unit 130, and a terminal control unit 140.

[0034] The photographing unit 100 can use a camera (not shown) provided in the user terminal 10 to recognize the oral cavity of the companion animal 1 and acquire actual photographic information photographed around the oral cavity. Here, the actual photographic information is information generated by actually photographing the oral cavity of the companion animal 1, and can include information on photos and / or videos of the condition of the companion animal 1 that requires care. For example, the actual photographic information can include, but is not limited to, photos or videos of the condition of the oral cavity of the companion animal 1.

[0035] The transceiver 110 transmits the status measurement information to the health management server 20 and receives health management data generated based on the health standard data from the health management server 20. At this time, the health standard data is data indicating standards for the oral health of the companion animal 1 and can be updated in real time according to the health result data.

[0036] Here, the condition measurement information is information used to measure the oral cavity condition of the companion animal 1, and may include photos and videos whose brightness, clarity, etc. have been automatically adjusted based on the actual shooting information, taking into account the surrounding environment, shaking, clarity, whether or not the oral cavity has been photographed, etc.

[0037] Furthermore, the health standard data may be data generated by matching the basic condition information of the companion animal 1 with the basic result data.

[0038] The basic condition information indicates the basic condition of the companion animal 1 and may include basic information and basic photography information. The basic information may include various information related to the companion animal 1, such as guardian information, abandonment information, hospital record information, unique identification number, breed, sex, age, weight, whether neutered, and whether the animal has given birth, etc. The guardian information may include contact information, etc., and the hospital record information may include vaccination information, medical information, and whether the animal has any allergies, etc. In this case, depending on the embodiment, cosmetic information may be included in the hospital record information. The basic photography information may include information generated by photographing the companion animal 1, and may include general photography information photographed in a general photography mode.

[0039] The basic result data may include basic diagnosis data and basic judgment data. The basic diagnosis data may be data diagnosing the presence or absence of oral diseases using basic imaging information, and the basic judgment data may be data determining the progression stage of oral diseases based on the basic diagnosis data. In this case, the basic diagnosis data may be determined by the naked eye, but is not limited to this.

[0040] The health result data may include actual diagnosis data and actual judgment data. The actual diagnosis data may be data obtained by diagnosing the presence or absence of oral diseases in the companion animal 1 using condition measurement information based on the health standard data, and the actual judgment data may be data obtained by determining the progression stage of a disease corresponding to the actual diagnosis data based on the health standard data. In this case, the actual diagnosis data may be judged by the naked eye, but is not limited to this.

[0041] Here, the names of oral diseases may include, but are not limited to, tooth decay, tartar, dental fracture, tooth discoloration, retained immature teeth, tooth loss, gum inflammation, gum tumor, and the like.

[0042] According to an embodiment, the transceiver 110 can receive health standard data from the health management server 20 and transmit health result data to the health management server 20 .

[0043] According to an embodiment, when the user terminal 10 transmits the status measurement information to the health management server 20 , the transceiver 110 can receive the health result data from the health management server 20 .

[0044] The transceiver 110 can transmit and receive medical care management data, which may include, but is not limited to, recommendation information that can be recommended depending on the current state or disease state of the companion animal 1, reservation management information, veterinary clinic link information, and clinic record information.

[0045] The memory unit 120 can store data transmitted and received through the transceiver unit 110 and data supporting various functions of the user terminal 10 .

[0046] The memory unit 120 can store a number of application programs (or applications) operated by the user terminal 10, as well as data and commands for the operation of the user terminal 10. At least some of these application programs can be downloaded from an external server via wireless communication.

[0047] The display unit 130 is a means for visually and audibly displaying the current operating status of the user terminal 10, and may include a display unit that can output symbols, letters, numbers, etc. on the screen depending on the operating status, a lamp that outputs by changing colors or flashing, or a speaker that outputs audio.

[0048] For example, when outputting health result data after completing measurements on companion animal 1, display unit 130 may display actual diagnosis data in O / X, flash the screen in red or green, display guidance such as "Normal" or "Recommended to visit a doctor," or display actual judgment data together with dictionary information. At this time, display unit 130 may provide a voice message to guide the guardian to accurately check the results of companion animal 1.

[0049] In addition, when outputting medical treatment management data, hospital information such as the location, contact information, and available appointment dates of the hospital corresponding to the recommended information generated based on the veterinary hospital link information can be displayed along with a road view, map, or calendar, hospital record information including medical treatment details and preventive information can be displayed, and reservation management information including a reservation completion signal received in response to the reservation request signal from the user terminal device 10 can be displayed on the screen.

[0050] The terminal control unit 140 can operate the photographing unit 100 according to the manual operation of the guardian to generate the condition measurement information of the companion animal 1, and can receive and output the health result data for the condition measurement information.

[0051] Specifically, the terminal control unit 140 can recognize the oral cavity of the companion animal 1 and automatically correct the actual photographed information acquired mainly from the oral cavity to generate condition measurement information. At this time, the condition measurement information can include actual basic information and actual photographed information. Here, the actual basic information includes guardian information, hospital record information, unique identification number, breed, sex, age, weight, whether neutered or not, whether or not the dog has given birth, etc., the guardian information includes contact information, etc., and the hospital record information includes vaccination information, medical information, whether or not the dog has allergies, etc. At this time, depending on the embodiment, cosmetic information may be included in the hospital record information.

[0052] The status measurement information may include photos and videos generated by automatically adjusting brightness and clarity from actual photograph information, taking into account the surrounding environment, shaking, clarity, and whether or not oral cavity is photographed. Here, the photos may be at least one and the videos may be at least 10 seconds long, but are not limited thereto.

[0053] In other words, the terminal control unit 140 can receive health result data for the condition measurement information regardless of time and place using the portable user terminal 10, and can accurately check whether or not the companion animal 1 has an oral disease and the progression stage of each oral disease. As a result, oral diseases of the companion animal 1 can be treated early to protect the health of the companion animal 1, thereby respecting the diversity of caregivers and increasing convenience and reliability.

[0054] According to an embodiment, when the terminal control unit 140 receives the health standard data from the health management server 20, the terminal control unit 140 can compare and analyze the status measurement information based on the health standard data to generate health result data.

[0055] Furthermore, the terminal control unit 140 can transmit and receive medical management data corresponding to the current state or disease state of the companion animal 1 based on the health result data.

[0056] Specifically, the terminal control unit 140 generates a reservation request signal including a hospital selection and a hospital reservation request according to the recommendation information recommended in accordance with the health result data based on the veterinary hospital linkage information, and transmits the signal to the health management server 20 or the service linkage terminal 30, and receives a reservation completion signal corresponding to the reservation request signal from the health management server 20 or the service linkage terminal 30. In addition, the terminal control unit 140 can receive hospital record information of the companion animal 1 from the health management server 20 or the service linkage terminal 30.

[0057] The health management server 20 can include a communication unit 200 , a database unit 210 , a monitoring unit 220 , a disease data management unit 230 , a medical data management unit 240 , and a management control unit 250 .

[0058] When the communication unit 200 receives the status measurement information from the user terminal 10, it can transmit the health result data to the user terminal 10.

[0059] According to the embodiment, when the communication unit 200 transmits the health standard data to the user terminal 10, the communication unit 200 can receive the health result data from the user terminal 10.

[0060] In addition, the communication unit 200 can transmit and receive medical management data between the user terminal 10 and the health management server 20 .

[0061] According to the embodiment, the communication unit 200 can transmit and receive medical management data between the user terminal 10 and the service link terminal 30 .

[0062] The database unit 210 can store data transmitted and received through a wireless communication network to and from the user terminal 10 and the service link terminal 30. At this time, the health standard data can be updated in real time in response to the health result data and stored.

[0063] The database unit 210 can store data supporting various functions of the health management server 20. The database unit 210 can store a number of application programs (or applications) operated by the health management server 20, and data and commands for the operation of the health management server 20. At least some of these application programs can be downloaded from an external server via wireless communication.

[0064] Meanwhile, the basic condition information, condition measurement information, health result data, and health standard data used in this embodiment stored in the database unit 210 may be embodied in the form of a corresponding mapping table, but is not limited to this.

[0065] The monitoring unit 220 can monitor the operating status of the user terminal 10, the operating status of the health management server 20, and data transmitted and received between the user terminal 10 and the health management server 20 through a screen. That is, by checking the usage status of the user terminal 10 in real time, it is possible to make parental use more convenient and to give parents more confidence.

[0066] The disease data management unit 230 can acquire basic condition information for a plurality of companion animals 1 and generate basic result data by analyzing the acquired basic condition information. In this case, the basic condition information can be information acquired through puppies in facilities such as abandoned dog centers and shelters, but is not limited to this.

[0067] The disease data management unit 230 can input basic information for multiple companion animals 1 using a mobile terminal, set the photography area of ​​the companion animal 1, and then obtain basic photography information consisting of general photography information taken in general photography mode.

[0068] In this embodiment, the basic condition information is disclosed as including basic photographing information for the oral cavity of the companion animal 1 based on basic information for a plurality of companion animals 1, but is not limited thereto and may include basic photographing information for various parts such as the face, eyes, head, abdomen, legs, chest, etc. In this case, the basic photographing information may include photographs or videos.

[0069] For example, in order to collect basic imaging information for the oral cavity region, the disease data management unit 230 can enable the tongue of the companion animal 1 to be accurately imaged in a general imaging mode.

[0070] In addition, the disease data management unit 230 can determine the presence or absence of oral disease using the basic imaging information included in the basic condition information, and if it is determined that an oral disease is present, generate basic result data including the progression stage of the oral disease. For example, referring to Fig. 3, the disease data management unit 230 can analyze the presence or absence of oral disease using the basic imaging information, and if the basic imaging information is information taken to diagnose dental symptoms, classify and label the information into Level 1 (normal), Level 2 (tartar), etc., and if the basic imaging information is information taken to diagnose gum symptoms, classify and label the information into Level 1 (normal), Level 2 (gum inflammation), etc., and convert the information into data.

[0071] Specifically, the disease data management unit 230 preprocesses the basic photograph information based on the basic information of the companion animal 1 to extract and correct analyzable images, extracts site-specific analysis images from the extracted analysis images, diagnoses the presence or absence of oral diseases that can be diagnosed with the naked eye, and generates basic diagnostic data. The site-specific analysis images are simultaneously analyzed based on the basic diagnostic data to determine the progression stage of each disease, thereby generating basic judgment data analyzing the progression stage of multiple diseases. Here, the basic diagnostic data is data that can diagnose abnormal signs inside the oral cavity with the naked eye, and the basic judgment data may be data generated by extracting site-specific analysis images for analyzing multiple diseases from the analysis images extracted based on the basic diagnostic data. For example, the disease data management unit 230 may determine tartar or gum inflammation using site-specific analysis images extracted from the teeth and gums, diagnose the presence of an oral disease based on the determination result, and generate basic diagnostic data regarding the presence or absence of the oral disease. The disease data management unit 230 may simultaneously evaluate the site-specific analysis images by site using a DCIN (Densely Connected Inception Network) algorithm based on the basic diagnostic data to generate more precise basic judgment data including the progression stage of each disease.

[0072] According to one embodiment, the DCIN algorithm has the advantages of reducing the amount of calculation using a 1x1 convolutional layer, extracting feature values ​​through parallel calculation of convolutional layers of different sizes, reusing feature values ​​to strengthen feature propagation, and reducing overfitting through the regularizing effect of dense connection in situations where the case-specific dataset is small in the early stages of development due to the characteristics of standard photographic images.

[0073] As described above, the health management server 20 visually analyzes the analysis image by region based on the basic information of the subject included in the basic condition information, and if the subject has tartar on the teeth or inflammation in the gums, it can classify the oral disease as "present" and label the basic diagnosis data.

[0074] The health management server 20 can perform learning and verification through a DCIN-based oral symptom diagnosis model, which is a deep learning algorithm.

[0075] Specifically, the health management server 20 generates a training dataset and a validation dataset using labeling data collected using a research system, performs data learning based on DCIN to extract optimal image features related to oral diseases, and then verifies the suitability of the model by checking whether there is overfitting in the learning data for each area that shows the characteristics of oral diseases. At this time, the health management server 20 can perform verification by comparing the extraction success rates of the training dataset and the test dataset, and if overfitting occurs, can normalize the image extraction area (teeth, gums) and perform iterative learning to collect additional learning datasets.

[0076] If the basic imaging information is information on an oral region, the disease data management unit 230 extracts an analyzable analysis image from the photo or video included in the basic imaging information, taking into consideration the surrounding environment, shaking, clarity, whether the oral region is photographed, etc., automatically corrects the brightness, clarity, etc. of the extracted analysis image, extracts analysis images by region for analyzing multiple diseases such as teeth and gums from the corrected analysis image, analyzes them simultaneously to determine the progression stage of each disease, and labels them by level to generate basic result data.

[0077] Meanwhile, when the basic photographing information is a photograph, the disease data management unit 230 can generate basic diagnosis data and basic judgment data for one photograph. Alternatively, when the basic photographing information is a video, the disease data management unit 230 can determine normal images from the video through a filtering step and extract at least 10 images to generate basic diagnosis data and basic judgment data. In this case, the filtering can be performed using a Laplace filter, and when the area occupied by the oral cavity in the total area is greater than a certain amount, the degree of shaking of the image included in the video can be filtered to obtain a normal image, but the filtering is not limited to this.

[0078] The medical data management unit 240 can manage medical management data transmitted and received between the user terminal 10 and the service link terminal 30 based on the health result data. Here, the medical management data can include recommendation information that can be recommended depending on the current state or disease state of the companion animal 1, reservation management information, veterinary clinic link information, and clinic record information.

[0079] For example, if medical treatment is required based on the actual diagnosis data, the medical data management unit 240 may provide recommendation information generated based on hospital information to the user terminal 10. At this time, the recommendation information may be information recommending hospital information corresponding to the health result data using veterinary clinic link information generated based on the hospital information provided from the service link terminal 30.

[0080] In addition, the medical data management unit 240 can transmit and receive reservation management information between the user terminal 10 and the service link terminal 30 .

[0081] For example, the medical data management unit 240 can transmit a reservation request signal received from the user terminal 10 to the service linking terminal 30, and can transmit a reservation completion signal generated in response to the reservation request signal from the service linking terminal 30 to the user terminal 10.

[0082] In addition, the medical data management unit 240 can transmit the hospital record information to the user terminal 10. At this time, the medical data management unit 240 can receive the hospital record information from the service link terminal 30.

[0083] For example, after the medical treatment of the companion animal 1 is completed, the medical data management unit 240 may transmit hospital record information including medical treatment details information to the user terminal 10, and in general, may transmit hospital record information including preventive information or cosmetic treatment information to the user terminal 10. In addition, the medical data management unit 240 may transmit notification information regarding the companion animal 1 to the user terminal 10. At this time, the notification information is information generated by the service link terminal 30, and may be, but is not limited to, notification information regarding the medical treatment or cosmetic treatment of the companion animal 1.

[0084] Depending on the embodiment, the medical data manager 240 may share hospital record information with other servers.

[0085] The management control unit 250 can generate health standard data by matching the basic condition information with the basic result data using deep learning. While this embodiment describes the use of deep learning, the present invention is not limited to this, and machine learning techniques such as random forest and support vector machine can also be used. In this case, the management control unit 250 can update the health standard data in real time in response to the health result data.

[0086] Specifically, the management control unit 250 can generate health standard data by iteratively learning the basic condition information and the basic result data based on a convolutional neural network (CNN) algorithm and verifying the suitability. In this case, the process of verifying the health standard data can be cross-verified by veterinarians and researchers at the contracted research institution, for example, at least three specialists, as shown in FIG. 4, but is not limited thereto.

[0087] In addition, when the management control unit 250 receives the status measurement information from the user terminal 10, it can generate health result data based on the health standard data.

[0088] Specifically, the management control unit 250 can generate health result data including actual diagnosis data that can diagnose the presence or absence of oral diseases with the naked eye by extracting actual analysis images by image from actual analysis images extracted by preprocessing the photos and / or videos included in the status measurement information, and actual judgment data that is generated by simultaneously analyzing multiple disease analyses from the actual analysis images by part based on the actual diagnosis data and determining the progression stage of each disease corresponding to the actual diagnosis data.

[0089] For example, if the actual photographed information is information of an oral region, the management control unit 250 may extract an analyzable actual analysis image from a photo or video included in the actual photographed information, taking into consideration the surrounding environment, shaking, clarity, whether the oral cavity was photographed, etc., automatically correct the brightness and clarity of the extracted actual analysis image, extract actual analysis images for each region for analyzing multiple diseases such as teeth and gums from the corrected actual analysis image, diagnose the presence or absence of oral diseases that can be diagnosed with the naked eye, analyze the actual diagnosis data based on the actual diagnosis data, determine the progression stage of each disease, and generate actual diagnosis information. That is, the management control unit 250 may analyze the region occupied by the teeth in the actual analysis image to check for color changes, the presence or absence of scratches, etc., analyze the region occupied by the gums in the actual analysis image to check for color changes, the presence or absence of inflammation, etc., and simultaneously analyze diseases for multiple regions, thereby analyzing the progression stage of multiple diseases through the analysis images for each region.

[0090] Meanwhile, when the actual photographed information is a photograph, the management and control unit 250 can generate actual diagnosis data and actual judgment data for one photograph. Alternatively, when the actual photographed information is a video, the management and control unit 250 can determine normal images from the video through a filtering step, extract at least 10 images, and generate actual diagnosis data and actual judgment data. In this case, the filtering can be performed using a Laplace filter to filter the degree of shaking of the image included in the video when the area occupied by the oral cavity in the total area is greater than a certain amount, thereby obtaining a normal image, but is not limited to this.

[0091] According to an embodiment, when the management control unit 250 transmits the health standard data to the user terminal 10, the management control unit 250 can receive the health result data corresponding to the condition measurement information of the companion animal 1.

[0092] According to an embodiment, the management control unit 250 can insert and transmit advertising information together with data transmitted and received between the user terminal 10, the service link terminal 30, and / or the administrator terminal 40. Accordingly, separate advertising revenue can be generated to support facilities such as abandoned dog centers and shelters.

[0093] The health management server 20 with this structure can automatically extract diagnostic areas from status measurement information acquired through the user terminal 10 based on verified health standard data that has been repeatedly learned from basic result data labeled in accordance with basic status information acquired from multiple companion animals 1, compare and analyze the extracted images, analyze multiple diseases, and generate health result data including the presence or absence of oral diseases and the progression stage of each disease. This can solve problems such as unnecessary hospital visits and neglect that can occur when the status of companion animals 1 is assessed solely by the naked eye.

[0094] In addition, the health management server 20 provides recommended information to the user terminal 10 according to the current state or disease state of the companion animal 1, thereby enabling the companion animal 1 to be managed quickly and accurately.

[0095] The health management server 20 may be implemented using hardware circuits (e.g., CMOS-based logic circuits), firmware, software, or a combination thereof. For example, it may be implemented using transistors, logic gates, and electronic circuits in the form of various electrical structures.

[0096] The service link terminal 30 can use the health result data received from a plurality of veterinary clinics that manage and treat the health of the companion animal 1 to more quickly proceed with the treatment of the companion animal 1.

[0097] The service link terminal 30 can share hospital record information with the user terminal 10, the health management server 20, and a separate server.

[0098] The service link terminal 30 can provide hospital information and notification information to the user terminal 10 and / or the health management server 20 .

[0099] According to an embodiment, the service link terminal 30 may include a separate facility such as an abandoned dog center or a shelter.

[0100] The administrator terminal 40 is a terminal owned by a separate administrator, and can transmit and receive data in real time by synchronizing with the user terminal 10, the health management server 20, and the service link terminal 30 through a wireless communication network. At this time, the administrator terminal 40 can transmit and receive data using an application program.

[0101] The administrator terminal 40 can learn the health standard data received from the health management server 20 and analyze the status measurement information received from the user terminal 10 to generate health result data including actual diagnosis data and actual judgment data.

[0102] According to an embodiment, when the administrator terminal 40 receives the status measurement information from the user terminal 10, the administrator terminal 40 can compare and analyze the status measurement information based on the health standard data to generate health result data.

[0103] According to the embodiment, when health result data is generated in the user terminal 10, the administrator terminal 40 can receive the health result data from the user terminal 10 and transmit it to the health management server 20. Also, when health result data is generated in the health management server 20, the administrator terminal 40 can receive the health result data from the health management server 20 and transmit it to the user terminal 10.

[0104] According to an embodiment, the administrator terminal 40 can transmit and receive medical management data corresponding to the current state or disease state of the companion animal 1 based on the health result data with at least one of the user terminal 10, the health management server 20, and the service link terminal 30.

[0105] The administrator terminal 40 may include various portable electronic communication devices that support communication with the user terminal 10, the health management server 20, and the service linking terminal 30. For example, the separate smart devices may include various terminals such as, but not limited to, a smartphone, a PDA (Personal Digital Assistant), a tablet, a wearable device (including, for example, a smartwatch, a smart glass, and an HMD (Head Mounted Display)), and various Internet of Things (IoT) terminals.

[0106] The operation of the companion animal oral disease diagnostic system according to one embodiment of the present invention having the above structure is as follows.

[0107] Figure 5 is a diagram for explaining a method for diagnosing oral diseases in companion animals according to one embodiment of the present invention, Figure 6 is a detailed diagram for explaining a method for generating health standard data shown in Figure 5, and Figure 7 is a detailed diagram for explaining a method for generating basic result data shown in Figure 6.

[0108] First, although the companion animal 1 is disclosed as being limited to a puppy in the examples of the present invention, it is not limited to this.

[0109] As shown in FIG. 5, the health management server 20 can generate health standard data (S10).

[0110] 6, the health management server 20 can acquire basic information about a plurality of companion animals 1 (S100). Here, the basic information may include, but is not limited to, guardian information, abandonment information, hospital record information, unique identification number, breed, sex, age, weight, whether the animal has been neutered, and whether the animal has given birth.

[0111] For example, the disease data management unit 230 can acquire basic information of the companion animal 1 inputted using a separate mobile terminal.

[0112] Next, the health management server 20 can select the region of the companion animal 1 to be photographed based on the basic information (S110).

[0113] For example, the disease data management unit 230 can check the photographed body part of the companion animal 1 set through a separate mobile terminal. That is, the disease data management unit 230 can select various body parts of the companion animal 1, such as the mouth, face, ears, abdomen, legs, chest, and back.

[0114] Next, when photographing the oral cavity region, the health management server 20 can first photograph the oral cavity region of the companion animal 1 in a general photographing mode and acquire general photographing information (S120).

[0115] For example, when a separate mobile terminal is used to photograph the oral cavity of the companion animal 1 in a general photography mode, the disease data management unit 230 can obtain general photography information from the mobile terminal.

[0116] Next, the health management server 20 generates basic condition information using the basic information and the basic imaging information including the corresponding general imaging information (S130). At this time, the general imaging information may include at least one photo and at least 10 seconds of video.

[0117] Next, the health management server 20 can extract analyzable analysis images from the basic imaging information to generate basic result data (S140).

[0118] Specifically, as shown in FIG. 7, if the information included in the basic photography information is a photograph (S200), the health management server 20 can verify whether the photograph is an analyzable image and extract an analysis image (S210).

[0119] For example, the disease data management unit 230 may extract an analyzable analysis image by taking into consideration the surrounding environment, shaking, clarity, whether the oral cavity is photographed, etc. At this time, the extracted analysis image may be corrected. That is, the disease data management unit 230 may extract the oral cavity area from the analysis image and correct the white balance and brightness.

[0120] Next, the health management server 20 can extract analysis images for each region for analyzing a plurality of diseases from the extracted analysis images (S220).

[0121] For example, the disease data management unit 230 can extract an analysis image for each tooth region from the analysis image, and an analysis image for each gum region, and simultaneously analyze a plurality of diseases for each region.

[0122] Next, basic diagnostic data for diagnosing the presence or absence of oral diseases can be generated using the site-specific analysis images (S230).

[0123] For example, the disease data management unit 230 can determine whether there is tartar or gum inflammation using the analysis images extracted from the teeth and gums, and based on the determination result, diagnose whether there is an oral disease and generate basic diagnostic data regarding the presence or absence of the oral disease.

[0124] Next, the health management server 20 can generate basic judgment data by determining analysis images for each part for analyzing a plurality of diseases based on the basic diagnosis data (S240).

[0125] Specifically, the disease data management unit 230 determines color changes, the presence or absence of scratches, etc. from the image of the tooth area, and determines color changes, the presence or absence of inflammation, etc. from the image of the gum area, and can analyze multiple diseases by area simultaneously, thereby analyzing multiple diseases through the analysis image by area.

[0126] At this time, the disease data management unit 230 can use the DCIN algorithm based on the basic diagnosis data to simultaneously judge the analysis image by region and generate more clearly basic judgment data in which multiple diseases are analyzed, but is not limited to this.

[0127] Meanwhile, if the information included in the basic photographing information is a moving image (S250), a normal image can be extracted by filtering the opening and closing of the mouth on the moving image.

[0128] For example, the disease data management unit 230 can extract at least 10 images by determining normal images from the video through a filtering step. At this time, the filtering uses a Laplace filter to filter the degree of shaking of the images included in the video if the area occupied by the oral cavity in the total area is greater than a certain amount, thereby obtaining normal images.

[0129] In this way, the health care server 20 can generate baseline result data corresponding to the baseline condition information.

[0130] Next, the health management server 20 matches the basic condition information with the basic result data (S150), and performs iterative learning based on the CNN algorithm to verify compatibility and generate health standard data (S160, S170).

[0131] Next, if the caregiver requests a diagnosis of the current state or disease state of the companion animal 1, the user terminal 10 can take a photograph of the oral cavity of the companion animal 1 and generate actual photograph information (S12).

[0132] Next, when the actual basic information is input, the user terminal 10 can generate state measurement information using the actual basic information and the actual photograph information (S14).

[0133] Next, the health management server 20 can generate health result data corresponding to the condition measurement information based on the health standard data (S16).

[0134] Specifically, the management control unit 250 preprocesses the photos and / or videos included in the status measurement information to extract and correct actual analysis images, extracts actual analysis images by region from the corrected actual analysis images, and generates health result data including actual diagnosis data that can be used to diagnose the presence or absence of oral diseases in the actual analysis images by region with the naked eye, and actual judgment data generated by judging the progression stage of each disease corresponding to the actual diagnosis data.

[0135] Next, the user terminal 10 can receive health result data corresponding to the status measurement information from the health management server 20 (S18).

[0136] For example, when outputting health result data after completing measurements of oral diseases on the companion animal 1, the display unit 130 can output the measurement results for oral diseases on the screen.

[0137] Next, the service link terminal 30 can provide hospital information based on the health standard data (S20).

[0138] Here, the step of providing hospital information may be performed in advance, but is not limited thereto.

[0139] Next, the health management server 20 can generate veterinary clinic linkage information based on the hospital information (S22).

[0140] Here, the step of generating the veterinary clinic linkage information may be performed in advance, but is not limited thereto.

[0141] Next, the health management server 20 can generate recommendation information corresponding to the health result data based on the veterinary clinic link information and transmit the recommendation information to the user terminal 10 (S24).

[0142] Next, the health management server 20 can generate reservation management information (S26).

[0143] For example, the health management server 20 can receive a reservation request signal generated based on custom-made information from the user terminal 10, and can receive reservation management information corresponding to the reservation request signal from the service link terminal 30 and transmit it to the user terminal 10.

[0144] Next, the service link terminal 30 can generate and share hospital record information including details of medical treatment for the companion animal 1 (S28).

[0145] At this time, the hospital record information can be transmitted to the user terminal 10 and the health management server 20 .

[0146] Finally, the health management server 20 can update the health standard data in real time in response to the health result data (S30).

[0147] As described above, the companion animal oral disease diagnosis system 1000 may include a user terminal 10 and a health management server 20. The user terminal 10 may generate condition measurement information including actual photographic information acquired from the subject of examination, and the health management server 20 may generate health result data for the subject of examination by repeatedly learning the health standard data generated by matching the basic condition information with the basic result data and analyzing the condition measurement information.

[0148] The health management server 20 extracts actual analysis images from the actual photographing information, simultaneously analyzes the actual analysis images for each region extracted from the actual analysis images, diagnoses the presence or absence of oral diseases for the subject, and generates actual diagnosis data. It can also generate health result data including actual judgment data generated by judging the progression stage of each oral disease based on the actual diagnosis data.

[0149] The health management server 20 preprocesses images included in the basic radiography information included in the basic condition information, extracts analyzable analysis images from the images, extracts site-specific analysis images for multiple disease analysis from the analysis images, diagnoses the presence or absence of oral diseases for the site-specific analysis images, and generates basic diagnostic data, determines the progression stage of diseases for the site-specific analysis images based on the basic diagnostic data, and generates basic judgment data, and generates basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

[0150] That is, the health management server 20 can generate health standard data by matching the basic condition information and the basic result data, receive the condition measurement information of the subject to be examined from the user terminal 10, and compare and analyze the condition measurement information based on the health standard data to generate health result data.

[0151] When generating the health standard data, the health management server 20 preprocesses the images included in the basic radiography information included in the basic condition information, extracts analyzable analysis images from the preprocessed images, extracts site-specific analysis images for analyzing multiple diseases from the analysis images, diagnoses the presence or absence of oral diseases for the site-specific analysis images, and generates basic diagnostic data, determines the progression stage of the disease for the site-specific analysis images based on the basic diagnostic data, and generates basic judgment data, and generates basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

[0152] When generating health result data, the health management server 20 extracts actual analysis images from actual photographing information included in the condition measurement information of the subject, extracts actual analysis images by region from the actual analysis images, diagnoses the presence or absence of oral diseases for the actual analysis images by region, generates actual diagnosis data, determines the progression stage of the disease for the actual analysis images by region based on the actual diagnosis data, generates actual judgment data, and generates health result data including the actual diagnosis data and the actual judgment data corresponding to the actual diagnosis data.

[0153] Hereinafter, the process of extracting the actual analysis image will be described in detail with reference to FIGS.

[0154] FIG. 8 is a diagram illustrating a process of extracting an actual analysis image according to an embodiment of the present invention, and FIG. 9 is a diagram illustrating the result of extracting an actual analysis image.

[0155] As shown in FIG. 8, when the first image is included in the actual photographing information, the health management server 20 can analyze the degree of shaking of the first image (S900).

[0156] Specifically, the user terminal 10 can take a picture of the companion animal 1 to generate actual photographic information including the first image, generate status measurement information using the actual photographic information, and transmit the status measurement information to the health management server 20. At this time, the health management server 20 can receive the status measurement information from the user terminal 10, and based on the status measurement information, can confirm that the first image is included in the actual photographic information and analyze the degree of shaking of the confirmed first image.

[0157] When analyzing the degree of shaking of the first image, the health management server 20 may analyze it using a shaking value that indicates how much the first image has shaken within a certain range, and a higher shaking value may indicate more shaking, and a lower shaking value may indicate less shaking.

[0158] For example, if the degree of fluctuation is set within a range of 1 to 10, the health management server 20 may analyze the degree of fluctuation of the first image as a value between 8 and 10 if the state of fluctuation of the first image is analyzed to be highly volatile; if the state of fluctuation of the first image is analyzed to be moderately volatile, the degree of fluctuation of the first image may be analyzed to be a value between 4 and 7; and if the state of fluctuation of the first image is analyzed to be almost negligible, the degree of fluctuation of the first image may be analyzed to be a value between 1 and 3.

[0159] The health management server 20 can compare the image learned for each shake value with the first image to analyze which value the degree of shake of the first image corresponds to, and for this purpose, the image learned for each shake value can be stored and managed in the database unit 210.

[0160] That is, the health management server 20 analyzes the degree of shaking of the first image and may analyze the degree of shaking of the first image as a first numerical value according to the shaking state of the first image.

[0161] When the degree of shaking of the first image is analyzed as a first numerical value, the health management server 20 may check whether the first numerical value is lower than a first reference value (S910). Here, the first reference value may be set differently depending on the embodiment.

[0162] If the health management server 20 determines that the first numerical value is lower than the first reference value, it may analyze the clarity of the first image (S920).

[0163] When analyzing the clarity of the first image, the health management server 20 may analyze it using a clarity value that indicates how clear the first image is within a certain range, and a higher clarity value indicates more clarity, and a lower clarity value indicates less clarity.

[0164] For example, if the clarity is set within the range of 1 to 10, the health management server 20 may analyze the clarity of the first image and, if the first image is analyzed to be very clear, the clarity of the first image may be analyzed as any one of 8 to 10; if the first image is analyzed to be somewhat clear, the clarity of the first image may be analyzed as any one of 4 to 7; and if the first image is analyzed to be not clear, the clarity of the first image may be analyzed as any one of 1 to 3.

[0165] The health management server 20 can compare the image learned by the clarity value with the first image to analyze whether the clarity of the first image corresponds to a certain value, and for this purpose, the image learned by the clarity value can be stored and managed in the database unit 210.

[0166] That is, the health management server 20 may analyze the clarity of the first image and analyze the clarity of the first image as a second numerical value depending on the clarity of the first image.

[0167] When the clarity of the first image is analyzed as the second value, the health management server 20 may determine whether the second value is higher than a second reference value (S930). Here, the second reference value may be set differently depending on the embodiment.

[0168] If the health management server 20 determines that the second numerical value is higher than the second reference value, it can analyze which part of the companion animal the first image is taken of (S940).

[0169] Specifically, if the area occupied by a specific part in the first image is greater than a certain amount, the health management server 20 can analyze the image as an image of the corresponding part. For example, if, after analyzing whether the first image is an image of a certain part, the area occupied by the oral cavity in the first image is 70% or more, the health management server 20 can analyze the first image as an image of the oral cavity.

[0170] The health management server 20 may check whether the first image is an image of the oral cavity (S950).

[0171] If the first image is analyzed as an image of an oral cavity region, the health management server 20 may classify the first image as an analyzable image (S960).

[0172] If the health management server 20 determines that the first numerical value is not lower than the first reference value, or the second numerical value is not higher than the second reference value, or if the first image is analyzed as an image of another part of the body rather than an image of the oral cavity, the health management server 20 can classify the first image as an unanalyzable image (S970).

[0173] As described above, photographs generated by photographing companion animal 1 can be classified into non-analyzable data and analyzable data based on shake, clarity, whether teeth or gums are included, etc., and the process of determining whether an image is analyzable based on shake, clarity, whether teeth or gums are included, etc. can be trained through machine learning, and analyzable images can be extracted as actual analysis images after being cropped around the teeth and gums.

[0174] For example, referring to (a) of FIG. 9, the health management server 20 can classify the first image shown in (a) of FIG. 9 as an analyzable image based on the shake, clarity, whether or not the oral cavity is photographed, etc., of the first image. If the first image is classified as an analyzable image, the first image can be extracted as an actual analysis image after being cropped around the oral cavity area.

[0175] For example, referring to (b) of FIG. 9, the health management server 20 can classify the first image as an unanalyzable image based on the shake, clarity, presence or absence of oral cavity images, etc. of the first image shown in (b) of FIG. 9, and if the first image is classified as an unanalyzable image, the health management server 20 can delete the first image and then transmit a re-photograph request notification message to the user terminal 10.

[0176] The health management server 20 may extract the first image as an actual analysis image and then correct the white balance and brightness of the first image.

[0177] The process of performing brightness correction on an image will be described in detail below with reference to FIGS.

[0178] FIG. 10 is a diagram illustrating a process of performing brightness correction on an image according to an embodiment of the present invention, and FIG. 11 is a diagram illustrating a result of performing brightness correction on an image.

[0179] As shown in FIG. 10, when the first image is extracted as the actual analysis image, the health management server 20 may analyze the brightness of the first image (S1100).

[0180] When analyzing the brightness of the first image, the health management server 20 can analyze it using a brightness value that indicates how bright the first image is within a certain range, with a higher brightness value indicating more brightness and a lower brightness value indicating darker.

[0181] For example, if brightness is set within the range of 1 to 10, the health management server 20 may analyze the brightness of the first image and, if the first image is analyzed to be very bright, analyze the brightness of the first image as any one of 8 to 10; if the first image is analyzed to be somewhat bright, analyze the brightness of the first image as any one of 4 to 7; and if the first image is analyzed to be dark, analyze the brightness of the first image as any one of 1 to 3.

[0182] The health management server 20 can compare the image learned by brightness value with the first image to analyze which value the brightness of the first image corresponds to, and for this purpose, the image learned by brightness value can be stored and managed in the database unit 210.

[0183] That is, the health management server 20 may analyze the brightness of the first image and analyze the brightness of the first image as a third value depending on the brightness state of the first image.

[0184] When the brightness of the first image is analyzed as a third value, the health management server 20 may check whether the third value is within a reference range (S1110). Here, the reference range may be set differently depending on the embodiment.

[0185] If the health management server 20 determines that the third value is within the reference range, it may determine that correction of the first image is not necessary (S1120).

[0186] For example, if the reference range is set to a range from 4 to 7, when the health management server 20 confirms that the third numerical value is 5, it can confirm that the third numerical value is within the reference range and determine that correction of the first image is not necessary.

[0187] If the health management server 20 determines that the third value is outside the reference range, it may set a correction value for the first image based on the third value (S1130).

[0188] When the health management server 20 determines that the third numerical value is greater than the maximum value of the reference range when setting the compensation value for the first image, the health management server 20 may set the compensation value to a lower value as the third numerical value increases. In this case, the compensation value may be set to a value less than 0 to darken the image.

[0189] For example, if the reference range is set to a range from 4 to 7, the health management server 20 can set the correction value for the first image to -1 if the third numerical value is confirmed to be 8, and can set the correction value for the first image to -2 if the third numerical value is confirmed to be 9.

[0190] When the health management server 20 sets the correction value for the first image, if it determines that the third numerical value is smaller than the minimum value of the reference range, it may set the correction value to a higher value as the third numerical value becomes lower. In this case, the correction value may be set to a value greater than 0 to brighten the image.

[0191] For example, if the reference range is set to a range from 4 to 7, the health management server 20 can set the correction value for the first image to 1 if the third numerical value is confirmed to be 3, and can set the correction value for the first image to 2 if the third numerical value is confirmed to be 2.

[0192] Once the correction value for the first image is set, the health management server 20 can perform brightness correction for the first image using the correction value (S1140).

[0193] If the correction value for the first image is a negative number, the health management server 20 may perform brightness correction using the correction value so that the first image is darkened.

[0194] For example, if the health management server 20 determines that the correction value for the first image is -1, it can perform brightness correction so that the first image is changed to one level darker, and if the correction value for the first image is determined to be -2, it can perform brightness correction so that the first image is changed to two levels darker.

[0195] If the correction value for the first image is a positive number, the health management server 20 can perform brightness correction using the correction value so that the first image is changed to be brighter.

[0196] For example, if the health management server 20 determines that the correction value for the first image is 1, it can perform brightness correction so that the first image is changed to be one level brighter, and if the correction value for the first image is determined to be 2, it can perform brightness correction so that the first image is changed to be two levels brighter.

[0197] As mentioned above, the first image can be corrected with an image suitable for analysis by processing corrections to white balance and brightness for the first image according to the brightness conditions of the first image.

[0198] For example, referring to FIG. 11, if the brightness state of the first image is dark as shown on the left side, brightness correction is performed on the first image, and the first image can be changed to an image suitable for analysis in diagnosing oral diseases as shown on the right side.

[0199] The health management server 20 can correct the brightness of the first image, diagnose the presence or absence of oral diseases, and generate actual diagnosis data.

[0200] Hereinafter, the process of diagnosing the presence or absence of oral diseases and generating actual diagnostic data will be described in detail with reference to FIGS.

[0201] FIG. 12 is a diagram illustrating a process of diagnosing the presence or absence of oral diseases and generating actual diagnostic data according to one embodiment of the present invention, and FIG. 13 is a diagram illustrating the results of extracting an analysis image by region.

[0202] 12, the health management server 20 may crop the area occupied by the teeth on the first image and extract it as a second image (S1300). In the process of extracting the second image, the CNN landmark algorithm may be applied.

[0203] 13(a), if the health management server 20 analyzes the first image by region and determines that the area occupied by teeth in a specific region is equal to or greater than a certain amount, it may crop the region as a region occupied by teeth and extract the cropped portion as the second image. In this case, if there are multiple regions occupied by teeth, the multiple regions may be cropped and extracted as the second image.

[0204] The health management server 20 may analyze whether there are any symptoms of a disease in the tooth region based on the second image (S1310). At this time, the health management server 20 may analyze whether there are any symptoms of at least one of tooth decay, tartar, dental fracture, tooth discoloration, remaining baby teeth, and tooth loss based on the second image.

[0205] The health management server 20 can compare the image learned for each disease symptom for the tooth region with the second image to analyze whether there is a disease symptom in the tooth region of the companion animal 1, and for this purpose, the image learned for each disease symptom for the tooth region can be stored and managed in the database unit 210.

[0206] The health management server 20 analyzes the second image to determine whether there is at least one symptom of tooth decay, tartar, dental fracture, tooth discoloration, remaining baby teeth, or tooth loss, and diagnoses the presence or absence of oral diseases in the tooth area (S1320).

[0207] If the health management server 20 analyzes that there is at least one symptom of tooth decay, tartar, dental fracture, tooth discoloration, remaining baby teeth, and tooth loss, it can diagnose the presence or absence of oral disease for the tooth area as "yes," and if it analyzes that there is no symptom of tooth decay, tartar, dental fracture, tooth discoloration, remaining baby teeth, or tooth loss, it can diagnose the presence or absence of oral disease for the tooth area as "no."

[0208] Meanwhile, the health management server 20 may crop the area occupied by the gums on the first image and extract it as a third image (S1330). In the process of extracting the third image, a CNN landmark algorithm may be applied.

[0209] 13(b), if the health management server 20 analyzes the first image by region and determines that the area occupied by the gums in a specific region is equal to or greater than a certain amount, it may crop the region as the gum region and extract the cropped portion as the third image. In this case, if there are multiple regions occupied by the gums, the multiple regions may be cropped and extracted as the third image.

[0210] The health management server 20 may analyze whether there are any symptoms of a disease in the gum area based on the third image (S1340). At this time, the health management server 20 may analyze whether there are any symptoms of at least one of gum inflammation and gum tumor based on the third image.

[0211] The health management server 20 can compare the image learned for each disease symptom in the gum area with the third image to analyze whether there is a disease symptom in the gum area of ​​the companion animal 1, and for this purpose, the image learned for each disease symptom in the gum area can be stored and managed in the database unit 210.

[0212] The health management server 20 analyzes whether there is a symptom of at least one of gum inflammation and gum tumor based on the third image, and can diagnose whether there is an oral disease in the gum area (S1350).

[0213] If the health management server 20 analyzes that there is at least one symptom of gum inflammation and gum tumor, it can diagnose the presence or absence of oral disease in the gum area as "yes," and if it analyzes that there is no symptom of gum inflammation or gum tumor, it can diagnose the presence or absence of oral disease in the gum area as "no."

[0214] When the health management server 20 diagnoses the presence or absence of oral diseases for each of the tooth region and the gum region, it can generate actual diagnosis data including each diagnosis result (S1360).

[0215] The steps of a method or algorithm described in connection with the embodiments of the present invention may be embodied directly in hardware, in a software module executed by hardware, or in a combination thereof. The software module may reside in Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable storage medium commonly known in the art to which the present invention pertains.

[0216] Although the embodiments of the present invention have been described above with reference to the accompanying drawings, those skilled in the art will understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential characteristics thereof. Therefore, the above-described embodiments should be understood to be illustrative in all respects and not restrictive.

Claims

1. 1. A method for diagnosing oral diseases in companion animals, the method being performed by a health care server, comprising: matching the baseline condition information and baseline outcome data to generate health standard data; receiving state measurement information of the object to be inspected from a user terminal; and comparing and analyzing the status measurement information based on the health standard data to generate health outcome data; The step of generating the health standard data includes: preprocessing an image included in the basic imaging information included in the basic state information; extracting an analyzable analysis image from the preprocessed image; extracting region-specific analysis images for a plurality of disease analyses from the analysis images, diagnosing the presence or absence of oral diseases for the region-specific analysis images, and generating basic diagnostic data; generating basic judgment data by determining a disease progression stage for the site-specific analysis image based on the basic diagnosis data; and A method for diagnosing oral diseases in companion animals, comprising: a step of generating basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

2. generating the health outcome data includes: extracting an actual analysis image from actual photographing information included in the state measurement information of the object to be inspected; extracting actual analysis images by region from the actual analysis images, diagnosing the presence or absence of oral diseases for the actual analysis images by region, and generating actual diagnosis data; generating actual determination data by determining a disease progression stage for the actual analysis image for each region based on the actual diagnosis data; and The method of claim 1 , further comprising: generating the health result data including the actual diagnosis data and the actual judgment data corresponding to the actual diagnosis data.

3. The step of extracting the actual analysis image includes: analyzing a degree of shaking of the first image when the actual photographing information includes the first image; when the degree of shaking of the first image is analyzed as a first numerical value, determining whether the first numerical value is lower than a first reference value; analyzing the clarity of the first image when the first numerical value is determined to be lower than the first reference value; when the clarity of the first image is analyzed as a second value, determining whether the second value is higher than a second reference value; If the second numerical value is determined to be higher than the second reference value, analyzing which part of the companion animal the first image is an image of; and 3. The method for diagnosing oral diseases in companion animals according to claim 2, further comprising: when the first image is analyzed as an image of an oral cavity region, classifying the first image as an analyzable image and extracting the first image as the actual analysis image.

4. The step of generating actual diagnostic data comprises: analyzing brightness of the first image when the first image is extracted as the actual analysis image; when the brightness of the first image is analyzed as a third value, determining whether the third value is included in a reference range; determining that correction of the first image is not necessary when it is determined that the third value is within the reference range; If the third value is determined to be outside the reference range, setting a correction value for the first image based on the third value; and The method of claim 3, further comprising: performing brightness correction on the first image using the correction value.

5. The step of generating actual diagnostic data comprises: cropping the area occupied by the teeth on the first image and extracting it as a second image; analyzing whether or not there is at least one symptom of tooth decay, tartar, dental fracture, tooth discoloration, remaining baby teeth, and tooth loss based on the second image, and diagnosing the presence or absence of the oral disease for the tooth region, thereby generating the actual diagnosis data; cropping the area occupied by the gums on the first image and extracting it as a third image; and The method for diagnosing oral diseases in companion animals as described in claim 4, further comprising a step of analyzing whether there are symptoms of at least one of gum inflammation and gum tumors based on the third image, diagnosing the presence or absence of the oral disease in the gum area, and generating the actual diagnostic data.

6. The step of generating the baseline result data comprises:

2. The method for diagnosing oral diseases in companion animals according to claim 1, further comprising: analyzing the analysis images by region with the naked eye based on the basic information of the subject of examination included in the basic condition information; and classifying the oral disease as "present" and labeling the basic diagnostic data if tartar is present on the teeth of the subject of examination or inflammation is present in the gums of the subject of examination.

7. a user terminal that generates status measurement information including actual photographic information acquired from an object to be inspected; and a health management server that iteratively learns health standard data generated by matching basic condition information with basic result data, analyzes the condition measurement information, and generates health result data for the test subject; The health management server extracting actual analysis images from the actual photographing information, simultaneously analyzing the actual analysis images for each region extracted from the actual analysis images to diagnose the presence or absence of oral diseases for the test subject and generating actual diagnosis data; and generating the health result data including actual judgment data generated by judging the progression stage of each oral disease based on the actual diagnosis data; A companion animal oral disease diagnostic system that preprocesses images included in basic imaging information included in the basic condition information, extracts analyzable analysis images from the images, extracts site-specific analysis images for multiple disease analyses from the analysis images, diagnoses the presence or absence of oral disease for the site-specific analysis images, generates basic diagnostic data, determines the disease progression stage for the site-specific analysis images based on the basic diagnostic data, generates basic judgment data, and generates basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

8. A computer program stored on a computer-readable recording medium that, when combined with a computer as hardware, enables the method for diagnosing oral diseases in companion animals according to any one of claims 1 to 6 to be carried out.

Images