Method and system for diagnosing oral disease of companion animal

Abstract

The invention provides a method and a system for diagnosing oral diseases of companion animals. The method for diagnosing an oral disease of a companion animal, which is executed by a health management server, comprises the steps of: generating health standard data by matching basic state information and basic result data; receiving state detection information of the inspection object from the user terminal; and comparing and analyzing the state detection information on the basis of the health standard data to generate health result data, the step of generating the health standard data may include: pre-processing an image included in basic imaging information included in the basic state information; extracting an analyzable analysis image from the pre-processed image; a diagnosis unit that extracts analysis images for analyzing respective parts of a plurality of diseases from the analysis images, diagnoses whether or not an oral disease is present in the analysis images of the respective parts, and generates basic diagnosis data; determining the progress stage of each disease in the analysis image of each part according to the basic diagnosis data, and generating basic determination data; and generating the basic result data including the basic diagnostic data and the basic determination data corresponding to the basic diagnostic data.

Description

Technical Field

[0001] The present invention relates to a method and system for diagnosing oral diseases of companion animals, and specifically to the following diagnostic method and system, which can quickly determine whether a companion animal has a disease in its oral cavity in the early stage, thereby achieving rapid diagnosis and preventing misdiagnosis. Background Art

[0002] With the aging population and the increase in single-person households, people are becoming increasingly self-centered and overwhelmed. As a result, the number of people who consider pets as family members or companions is increasing, and the companion animal market is steadily growing.

[0003] When these companion animals show abnormal symptoms that are not usually seen, most people will take the companion animals to the pet hospital for treatment, or solve the abnormal symptoms of the companion animals based on information obtained from people around them or through the Internet, telephone, etc.

[0004] However, there is a lot of erroneous information obtained from people around or through the Internet, telephone, etc., so treatment may be difficult. If you go to the hospital in person, the waiting time at the hospital is long, the hospital's business volume is large, and there are many cases of inadequate customer service (see Korean Patent Publication No. 10-2021-0108686 (published on September 3, 2021)).

[0005] The matters described as the background technology are only for enhancing the understanding of the background of the present invention and should not be considered as belonging to the prior art known to ordinary technicians in this technical field. Summary of the Invention

[0006] Technical issues

[0007] The problem to be solved by the present invention is to provide a method and system for diagnosing oral diseases of companion animals.

[0008] The problems to be solved by the present invention are not limited to the problems mentioned above, and ordinary technicians can clearly understand other problems not mentioned through the following description.

[0009] Technical Solution

[0010] A method for diagnosing oral diseases of companion animals according to an embodiment of the present invention for solving the above-mentioned problems may include the following steps: generating health standard data by matching basic status information and basic result data; receiving status detection information of the inspection object from a user terminal; and generating health result data by comparing and analyzing the status detection information based on the above-mentioned health standard data. The steps of generating the above-mentioned health standard data may include the following steps: preprocessing the image contained in the basic shooting information, the above-mentioned basic shooting information is contained in the above-mentioned basic status information; extracting an analyzable analysis image from the above-mentioned preprocessed image; extracting analysis images of various parts for analyzing multiple diseases from the above-mentioned analysis images, diagnosing whether there is oral disease in the analysis images of the above-mentioned various parts, and generating basic diagnostic data; judging the progression stage of each disease in the analysis images of the above-mentioned various parts based on the above-mentioned basic diagnostic data, and generating basic judgment data; and generating the above-mentioned basic result data including the above-mentioned basic diagnostic data and the above-mentioned basic judgment data corresponding to the above-mentioned basic diagnostic data.

[0011] In one embodiment of the present invention, the step of generating the above-mentioned health result data may include the following steps: extracting the actual analysis image from the actual shooting information contained in the above-mentioned status detection information of the above-mentioned inspection object; extracting the actual analysis image of each part from the above-mentioned actual analysis image, diagnosing whether the above-mentioned oral disease exists in the actual analysis image of the above-mentioned each part, and generating actual diagnosis data; judging the progression stage of each disease in the actual analysis image of the above-mentioned each part based on the above-mentioned actual diagnosis data, and generating actual judgment data; and generating the above-mentioned health result data including the above-mentioned actual diagnosis data and the above-mentioned actual judgment data corresponding to the above-mentioned actual diagnosis data.

[0012] In one embodiment of the present invention, the step of extracting the above-mentioned actual analysis image may include the following steps: in a case where the above-mentioned actual shooting information includes a first image, analyzing the degree of shaking of the above-mentioned first image; if the degree of shaking of the above-mentioned first image is analyzed as a first numerical value, confirming whether the above-mentioned first numerical value is lower than the first standard value; if it is confirmed that the above-mentioned first numerical value is lower than the above-mentioned first standard value, analyzing the clarity of the above-mentioned first image; if the clarity of the above-mentioned first image is analyzed as a second numerical value, confirming whether the above-mentioned second numerical value is higher than the second standard value; if it is confirmed that the above-mentioned second numerical value is higher than the above-mentioned second standard value, analyzing which part of the companion animal the above-mentioned first image is; and if the above-mentioned first image is analyzed as an image of the oral part, classifying the above-mentioned first image as an analyzable image, and extracting the above-mentioned first image as the above-mentioned actual analysis image.

[0013] In one embodiment of the present invention, the step of generating the above-mentioned actual diagnostic data may include the following steps: if the above-mentioned first image is extracted as the above-mentioned actual analysis image, analyzing the brightness of the above-mentioned first image; if the brightness of the above-mentioned first image is analyzed as a third value, confirming whether the above-mentioned third value is included in the standard range; if it is confirmed that the above-mentioned third value is included in the above-mentioned standard range, determining that the above-mentioned first image does not need to be corrected; if it is confirmed that the above-mentioned third value exceeds the above-mentioned standard range, setting the correction value of the above-mentioned first image according to the above-mentioned third value; and using the above-mentioned correction value to perform brightness correction of the above-mentioned first image.

[0014] In one embodiment of the present invention, the step of generating the above-mentioned actual diagnostic data may also include the following steps: cutting out the area occupied by the teeth in the above-mentioned first image and extracting it as a second image; analyzing whether there is at least one symptom of tooth decay, tartar, tooth fracture, tooth discoloration, residual deciduous teeth and tooth loss based on the above-mentioned second image, diagnosing whether the above-mentioned oral disease exists in the above-mentioned tooth area, and generating the above-mentioned actual diagnostic data; cutting out the area occupied by the gums on the above-mentioned first image and extracting it as a third image; and analyzing whether there is at least one symptom of gingival inflammation and gingival tumor based on the above-mentioned third image, diagnosing whether the above-mentioned oral disease exists in the above-mentioned gum area, and generating the above-mentioned actual diagnostic data.

[0015] In one embodiment of the present invention, the step of generating the above-mentioned basic result data may include the following steps: visually analyzing the analysis images of the above-mentioned various parts based on the basic information of the above-mentioned inspection object contained in the above-mentioned basic status information, and classifying the oral disease as present when there is tartar in the teeth of the above-mentioned inspection object or there is inflammation in the gums of the above-mentioned inspection object, and marking the above-mentioned basic diagnostic data.

[0016] In addition, a diagnostic system for oral diseases of companion animals in another embodiment of the present invention for solving the above-mentioned problems includes: a user terminal, which generates status detection information, and the above-mentioned status detection information includes actual shooting information obtained from the inspection object; and a health management server, which repeatedly learns health standard data generated by matching basic status information and basic result data, analyzes the above-mentioned status detection information, and generates health result data of the above-mentioned inspection object, in which the above-mentioned health management server extracts actual analysis images from the above-mentioned actual shooting information, and simultaneously analyzes the actual analysis images of various parts extracted from the above-mentioned actual analysis images, diagnoses whether the above-mentioned inspection object suffers from oral diseases to generate actual diagnosis data, and generates the above-mentioned health result data, and the above-mentioned health result The result data includes actual judgment data generated by judging the progression stage of each of the above-mentioned oral diseases based on the above-mentioned actual diagnosis data, preprocessing the image contained in the basic shooting information, the above-mentioned basic shooting information is included in the above-mentioned basic status information, extracting an analyzable analysis image from the above-mentioned image, extracting analysis images of each part for analyzing multiple diseases from the above-mentioned analysis image, diagnosing whether there is oral disease in the analysis image of the above-mentioned each part, and generating basic diagnosis data, judging the progression stage of each disease in the analysis image of the above-mentioned each part based on the above-mentioned basic diagnosis data, and generating basic judgment data, and generating the above-mentioned basic result data including the above-mentioned basic diagnosis data and the above-mentioned basic judgment data corresponding to the above-mentioned basic diagnosis data.

[0017] The program of one embodiment of the present invention is incorporated into a computer as hardware and stored in a computer-readable recording medium in a manner that executes the above-mentioned method for diagnosing oral diseases of companion animals.

[0018] Other specific matters of the present invention are included in the detailed description and drawings.

[0019] Effects of the Invention

[0020] According to the present invention, when an abnormality occurs in the oral cavity of an inspection object, especially a companion animal, the oral condition of the companion animal can be diagnosed using a portable terminal, and the current condition of the companion animal can be judged quickly and accurately, thereby providing a sense of trust to the guardian of the companion animal.

[0021] According to the present invention, the current condition of a companion animal can be accurately diagnosed in real time using a portable terminal, thereby improving user convenience and reliability.

[0022] According to the present invention, hospital information about the current condition of a companion animal is received together, and the companion animal's disease is treated early at a hospital capable of treating the companion animal's disease, thereby maintaining the companion animal's health.

[0023] According to the present invention, notification information about companion animals is continuously provided to caregivers, thereby preventing the animals from being induced to revisit or leaving the animal hospital.

[0024] According to the present invention, the companion animal's result data is shared with the connection service, and the companion animal's condition is more accurately grasped and dealt with, thereby providing a sense of trust to the companion animal's caregiver.

[0025] The effects of the present invention are not limited to the effects mentioned above, and those skilled in the art can clearly understand other effects not mentioned through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 FIG. 1 is a schematic diagram illustrating a diagnostic system for oral diseases of companion animals according to an embodiment of the present invention.

[0027] Figure 2 For illustration purposes Figure 1 The detailed structure of the companion animal oral disease diagnosis system is shown in the figure.

[0028] Figure 3 This figure is used to explain the basic result data marked in correspondence with the basic status information.

[0029] Figure 4 A diagram illustrating a method for verifying basic result data.

[0030] Figure 5 FIG. 1 is a diagram for explaining a method for diagnosing oral diseases of companion animals according to an embodiment of the present invention.

[0031] Figure 6 To illustrate the generation Figure 5 Detailed diagram of the method for health standard data shown in .

[0032] Figure 7 To illustrate the generation Figure 6 Detailed diagram of the method underlying the resulting data shown in .

[0033] Figure 8 FIG. 1 is a diagram for explaining a process of extracting an actual analysis image according to an embodiment of the present invention.

[0034] Figure 9 FIG. 1 is a diagram showing the result of extracting an actual analysis image.

[0035] Figure 10 FIG. 1 is a diagram for explaining a process of performing brightness correction on an image according to an embodiment of the present invention.

[0036] Figure 11 is a diagram showing the result of performing brightness correction on an image.

[0037] Figure 12 FIG. 1 is a diagram for explaining a process of generating actual diagnosis data by diagnosing whether an oral disease exists according to an embodiment of the present invention.

[0038] Figure 13 Graphs showing the results of extracting analysis images for various regions. DETAILED DESCRIPTION

[0039] The advantages, features, and methods for achieving these advantages and features of the present invention will become apparent with reference to the accompanying drawings and the embodiments described in detail below. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in a variety of different forms. These embodiments are provided only to make the disclosure of the present invention more complete and to fully inform those skilled in the art of the present invention of the scope of the present invention. The present invention is defined solely by the scope of the claims.

[0040] The terms used in this specification are used to illustrate the embodiments and do not limit the present invention. In this specification, unless otherwise mentioned, the singular may also include the plural in a sentence. "Comprises" and / or "comprising" used in the specification does not exclude the existence or addition of one or more other structural elements other than the mentioned structural elements. Throughout the specification, the same figure marks refer to the same structural elements, and "and / or" includes each and all combinations of more than one of the mentioned structural elements. Although "first", "second" and the like are used to describe various structural elements, these structural elements are not limited to these terms. These terms are only used to distinguish one structural element from another structural element. Therefore, the first structural element mentioned below can also be a second structural element within the technical idea of ​​the present invention.

[0041] Unless otherwise defined, all terms (including technical and scientific terms) used in this specification are used with the meanings commonly understood by those skilled in the art. Furthermore, unless explicitly defined otherwise, terms defined in commonly used dictionaries should not be interpreted in an unusual or excessive manner.

[0042] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0043] Figure 1 FIG. 1 is a schematic diagram illustrating a diagnostic system for oral diseases of companion animals according to an embodiment of the present invention. Figure 2 For illustration purposes Figure 1 The detailed structure of the companion animal oral disease diagnosis system is shown in FIG. Figure 3 is a diagram for explaining basic result data marked in correspondence with basic status information. Figure 4 A diagram illustrating a method for verifying basic result data.

[0044] like Figure 1 and Figure 2 As shown, a diagnostic system 1000 for oral diseases of companion animals according to an embodiment of the present invention may include a user terminal 10, a health management server 20, a service contact terminal 30, and an administrator terminal 40. In this case, the administrator terminal 40 may be omitted.

[0045] The user terminal 10 , the health management server 20 , the service contact terminal 30 and the administrator terminal 40 may utilize a wireless communication network to synchronously send and receive data in real time. Wireless communication networks can support various long-distance communication methods, such as wireless local area networks (WLAN), Digital Living Network Alliance (DLNA), wireless broadband (Wibro), World Interoperability for Microwave Access (WiMAX), Global System for Mobile communications (GSM), Code Division Multiple Access (CDMA), Code Division Multiple Access 2000 (CDMA2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), Wideband CDMA (WCDMA), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), and Long Term Evolution Plus (LTE-AD). The present invention relates to various communication methods such as LTE-Term Evolution-Advanced (LTEA), Wireless Mobile Broadband Service (WMBS), Bluetooth Low Energy (BLE), Zigbee, Radio Frequency (RF), and Long Range (LoRa), but is not limited to these. It can also be applied to various widely known wireless communication or mobile communication methods.

[0046] First, in this embodiment, a companion animal oral disease diagnosis system 1000 is disclosed for imaging the oral area of ​​a companion animal, particularly a puppy, to determine whether the companion animal has an oral disease and, if so, the stage of progression of the disease. However, this is not limiting. For example, oral diseases can be detected not only in various animals living with a caregiver, companion, or dog owner (hereinafter referred to as the caregiver), including vertebrates such as mammals, birds, reptiles, amphibians, and fish, arthropods, and invertebrates such as mollusks, but also in humans.

[0047] The user terminal 10 is a portable terminal carried by a person caring for the companion animal 1. In the present disclosure, the user terminal 10 can be operated using an application program (or application), which can be downloaded from an external server or health management server 20 via wireless communication. For example, the user terminal 10 may include various terminals such as a smartphone, a personal digital assistant (PDA), a tablet, a wearable device (e.g., a smartwatch, a smart glass, a head-mounted display (HMD)), and various Internet of Things (IoT) terminals, but is not limited thereto.

[0048] like Figure 2 As shown, the user terminal 10 described above may include a photographing unit 100 , a transceiver unit 110 , a storage unit 120 , a display unit 130 and a terminal control unit 140 .

[0049] The imaging unit 100 can use a camera (not shown) installed on the user terminal 10 to identify the oral cavity of the companion animal 1 and obtain actual image information captured centered on the oral cavity. The actual image information is information generated by actually capturing the oral cavity of the companion animal 1 and may include images and / or videos of the condition of the companion animal 1 requiring management. For example, the actual image information may include images or videos of the oral cavity of the companion animal 1, but is not limited thereto.

[0050] The transceiver 110 transmits the status detection 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. The health standard data is data indicating the standard of the oral health of the companion animal 1 and can be updated in real time in correspondence with the health result data.

[0051] Among them, the status detection information is information used to detect the oral status of the companion animal 1. It can automatically adjust the brightness and clarity of pictures and videos based on actual shooting information and taking into account the surrounding environment, shaking, clarity, whether to shoot the mouth, etc.

[0052] Furthermore, the health standard data may be data generated by matching basic status information of the companion animal 1 with basic result data.

[0053] Basic status information represents the basic status of companion animal 1 and may include basic information and basic photography information. Basic information includes various information related to companion animal 1, such as guardian information, abandonment information, hospital records, unique identification number, breed, gender, age, weight, sterilization status, and fertility status. Guardian information includes contact information, while hospital records may include vaccination information, medical treatment information, and allergy status. Depending on the embodiment, hospital records may also include beauty information. Basic photography information may include information generated by photographing companion animal 1, including standard photography information captured using standard photography mode.

[0054] Basic result data may include basic diagnostic data and basic judgment data. Basic diagnostic data is data used to diagnose whether an oral disease exists using basic imaging information. Basic judgment data may be data used to determine the progression stage of an oral disease based on the basic diagnostic data. In this case, basic diagnostic data may be visually determined, but is not limited to this.

[0055] Health result data may include actual diagnosis data and actual judgment data. Actual diagnosis data is data that diagnoses whether companion animal 1 has an oral disease based on health standard data and status detection information. Actual judgment data is data that determines the progression stage of each disease corresponding to the actual diagnosis data based on the health standard data. In this case, actual diagnosis data may be visually judged, but is not limited to this.

[0056] Among them, the names of diseases related to oral diseases include tooth decay, tartar, tooth fracture, tooth discoloration, retained deciduous teeth, missing teeth, gingivitis, gingival tumors, etc., but are not limited to these.

[0057] According to an embodiment, the transceiver 110 may receive health standard data from the health management server 20 and may transmit health result data to the health management server 20 .

[0058] According to an embodiment, when the transceiver 110 transmits the status detection information from the user terminal 10 to the health management server 20 , the health result data may be received from the health management server 20 .

[0059] The transceiver 110 can transmit and receive medical management data, which may include, but is not limited to, recommendation information based on the current condition or disease state of the companion animal 1 , appointment management information, animal hospital contact information, and hospital record information.

[0060] The storage unit 120 may store data transmitted and received by the transceiver unit 110 and data supporting various functions of the user terminal 10 .

[0061] The storage unit 120 may store a plurality of application programs (or applications) driven by the user terminal 10, data for operating the user terminal 10, and instructions. At least a portion of such applications may be downloaded from an external server via wireless communication.

[0062] 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 that outputs symbols, letters, numbers, etc. on the screen according to the operating status, a light that outputs by color changes or flashing, or a speaker that outputs by audio.

[0063] For example, after the examination of companion animal 1 is completed and health result data is output, display unit 130 may display the actual diagnostic data through the O / X, flash the screen in red or green, display a message such as "Normal" or "Recommendation to the Hospital," or display the actual diagnosis data and dictionary information together. At this time, display unit 130 may provide voice guidance prompts to enable the caregiver to accurately confirm the results of companion animal 1.

[0064] In addition, when outputting diagnosis and treatment management data, hospital information such as the location, contact information, available reservation dates, etc. of the hospital corresponding to the recommendation information generated based on the contact information of the animal hospital, as well as a panoramic map or map or a calendar can be displayed on the screen, or hospital record information containing diagnosis and treatment history information, prevention information, etc. can be displayed on the screen, or appointment management information containing an appointment completion signal received in response to the appointment request signal of the user terminal 10 can be displayed on the screen.

[0065] The terminal control unit 140 operates the imaging unit 100 through manual operation by the caregiver to generate status detection information of the companion animal 1 , and can receive and output health result data related to the status detection information.

[0066] Specifically, the terminal control unit 140 identifies the oral cavity of the companion animal 1 and automatically corrects the actual photographic information obtained with the oral cavity as the center to generate status detection information. In this case, the status detection information may include actual basic information and actual photographic information. The actual basic information includes guardian information, hospital records, unique identification number, dog breed, gender, age, weight, sterilization status, and fertility status. The guardian information includes contact information, and hospital records may include vaccination information, medical treatment information, and allergy status. Depending on the embodiment, the hospital records may also include cosmetic information.

[0067] The status detection information may include images and videos generated using actual shooting information, automatically adjusting brightness and clarity based on the surrounding environment, shake, clarity, and whether the oral cavity is being photographed. The images must be at least one and the videos must be at least 10 seconds long, but are not limited to these.

[0068] In other words, the terminal control unit 140 receives health result data related to status monitoring information using the portable user terminal 10, regardless of time and location, and can accurately confirm whether the companion animal 1 has an oral disease and the progression stage of each oral disease. This allows the oral disease of the companion animal 1 to be treated at an early stage, thereby maintaining the health of the companion animal 1, thereby improving convenience and reliability while respecting the diversity of caregivers.

[0069] According to an embodiment, in the case of receiving health standard data from the health management server 20 , the terminal control part 140 may compare and analyze the status detection information according to the health standard data, and may generate health result data.

[0070] Furthermore, the terminal control unit 140 may transmit and receive diagnosis and treatment management data corresponding to the current condition or disease state of the companion animal 1 based on the health result data.

[0071] Specifically, the terminal control unit 140 generates a reservation request signal including hospital selection and hospital reservation request based on the animal hospital contact information and recommendation information based on the health result data, and transmits the signal to the health management server 20 or the service contact terminal 30. The terminal control unit 140 may also receive a reservation completion signal corresponding to the reservation request signal from the health management server 20 or the service contact terminal 30. Furthermore, the terminal control unit 140 may receive hospital record information for the companion animal 1 from the health management server 20 or the service contact terminal 30.

[0072] The health management server 20 may include a communication unit 200 , a database unit 210 , a monitoring unit 220 , a disease data management unit 230 , a diagnosis and treatment data management unit 240 , and a management control unit 250 .

[0073] In the case of receiving the status detection information from the user terminal 10 , the communication part 200 may transmit the health result data to the user terminal 10 .

[0074] According to an embodiment, in the case of transmitting the health standard data to the user terminal 10 , the communication part 200 may receive the health result data from the user terminal 10 .

[0075] In addition, the communication unit 200 can transmit and receive medical treatment management data between the user terminal 10 and the health management server 20 .

[0076] According to an embodiment, the communication unit 200 may transmit and receive medical treatment management data between the user terminal 10 and the service contact terminal 30 .

[0077] The database unit 210 can store data transmitted and received via the wireless communication network with the user terminal 10 and the service contact terminal 30. In this case, the health standard data can be updated and stored in real time in correspondence with the health result data.

[0078] The database unit 210 may store data supporting various functions of the health management server 20. The database unit 210 may store a plurality of application programs (or applications) driven by the health management server 20, as well as data and instructions for operating the health management server 20. At least some of these applications may be downloaded from an external server via wireless communication.

[0079] In addition, the basic status information, status detection information, health result data, and health standard data used in this embodiment stored in the database unit 210 can be implemented in the form of mutually corresponding mapping tables, but is not limited to this.

[0080] The monitoring unit 220 can monitor the operating status of the user terminal 10, the working status of the health management server 20, and the data sent and received between the user terminal 10 and the health management server 20 through the screen. In other words, the usage status of the user terminal 10 can be confirmed in real time, thereby facilitating use by the caregiver and providing the caregiver with a sense of trust.

[0081] The disease data management unit 230 obtains basic status information of multiple companion animals 1, analyzes the obtained basic status information and generates basic result data. In this case, the basic status information can be information obtained from puppies in facilities such as stray dog ​​centers and protection centers, but is not limited to these.

[0082] The disease data management unit 230 uses a mobile terminal to input basic information of a plurality of companion animals 1 , and after setting the photographing part of the companion animals 1 , basic photographing information consisting of ordinary photographing information photographed in an ordinary photographing mode can be obtained.

[0083] In this embodiment, the basic status information disclosed includes basic photographic information of the oral cavity of the companion animal 1 based on the basic information of the plurality of companion animals 1. However, the basic status information is not limited thereto and may include basic photographic information of various parts of the body, such as the face, eyes, head, abdomen, feet, and chest. In this case, the basic photographic information may include images or videos.

[0084] For example, in order to collect basic photographic information about the oral cavity, the disease data management unit 230 may accurately photograph the tongue of the companion animal 1 in a normal photographing mode.

[0085] In addition, the disease data management unit 230 uses the basic imaging information included in the basic status information to determine whether the patient has an oral disease. If the patient is determined to have an oral disease, basic result data including the progression stages of the oral disease can be generated. Figure 3 The disease data management unit 230 uses the basic shooting information to analyze whether there is an oral disease. When the basic shooting information is information shot for the purpose of diagnosing dental symptoms, it is classified into Level 1 (normal) and Level 2 (tartar) and marked. When the basic shooting information is information shot for the purpose of diagnosing gum symptoms, it is classified into Level 1 (normal) and Level 2 (gingivitis) and marked so that it can be digitized.

[0086] Specifically, the disease data management unit 230 pre-processes the basic captured information based on the basic information of the companion animal 1, extracts and corrects analyzable images, extracts analysis images of various parts from the extracted analysis images, and diagnoses whether the animal has an oral disease that can be diagnosed visually to generate basic diagnostic data. Based on the basic diagnostic data, the analysis images of various parts are simultaneously analyzed to determine the progression stage of each disease. This generates basic judgment data that analyzes the progression stages of multiple diseases. The basic diagnostic data is data that can visually diagnose abnormal signs within the oral cavity. The basic judgment data can be generated by extracting analysis images of various parts used to analyze multiple diseases from the analysis images extracted based on the basic diagnostic data. For example, the disease data management unit 230 uses analysis images of various parts extracted from the teeth and gums to determine whether the animal has tartar or gingival inflammation. Based on the judgment result, the disease data management unit 230 diagnoses the animal as having an oral disease and generates basic diagnostic data on whether the animal has an oral disease. Based on the basic diagnostic data and using the densely connected inception network (DCIN) algorithm, the analysis images of various parts are simultaneously analyzed by part, thereby more clearly generating basic judgment data that includes the progression stages of each disease.

[0087] According to one embodiment, as a feature of the DCIN algorithm, a 1x1 convolutional layer is used to reduce the amount of computation, feature values ​​can be extracted from convolutional layers of different sizes through parallel computing, and feature propagation can be enhanced through the reuse of feature values. In terms of the characteristics of standard captured images, when the data set for each case is small in the early stages of development, overmatching can be reduced through the regularizing effect of dense connections.

[0088] As described above, the health management server 20 visually analyzes the analysis images of various parts based on the basic information of the inspection object contained in the basic status information, and classifies the inspection object as having oral disease if there is tartar in the teeth or inflammation in the gums of the inspection object, and marks the basic diagnostic data.

[0089] The health management server 20 can perform learning and verification using an oral symptom diagnosis model based on DCIN, which is a deep learning algorithm.

[0090] Specifically, the health management server 20 uses the research system to generate a learning dataset and a validation dataset from the collected labeled data. To extract optimal image features related to oral diseases, the server then verifies the model's adaptability by checking whether the learning data is overfitting, based on the areas indicated by the oral disease features, based on the DCIN learning data. The server then compares the extraction success rates of the training and test datasets for verification. If overfitting occurs, the server normalizes the image extraction areas (teeth, gums) and performs repeated learning to further collect learning datasets.

[0091] In the case where the basic shooting information is information of shooting the oral cavity, the disease data management unit 230 extracts analyzable analysis images from the pictures or videos contained in the basic shooting information, taking into account the surrounding environment, shaking, clarity, whether the oral cavity is shot, etc., automatically corrects the brightness, clarity, etc. of the extracted analysis images, extracts analysis images of various parts for analyzing multiple diseases such as teeth and gums from the corrected analysis images, and analyzes them at the same time to determine the progression stage of each disease, and can generate basic result data according to level labels.

[0092] Furthermore, if the basic imaging information is an image, the disease data management unit 230 can generate basic diagnostic data and basic judgment data for a single image. Alternatively, if the basic imaging information is a video, a filtering step is performed to determine a normal image from the video, and at least ten images can be extracted to generate the basic diagnostic data and basic judgment data. In this case, filtering utilizes a Laplace filter to filter the degree of motion in the video when the area of ​​the oral cavity relative to the total area is greater than a specified value, thereby obtaining a normal image. However, this is not limiting.

[0093] The medical data management unit 240 can manage medical management data sent and received between the user terminal 10 and the service contact terminal 30 based on the health result data. The medical management data can include recommendation information based on the current condition or disease state of the companion animal 1, appointment management information, animal hospital contact information, and hospital record information.

[0094] For example, if treatment is required based on actual diagnostic data, the treatment data management unit 240 may provide recommendation information generated based on hospital information to the user terminal 10. In this case, the recommendation information may be information that recommends hospital information corresponding to the health result data using the animal hospital contact information generated based on the hospital information received from the service contact terminal 30.

[0095] In addition, the medical data management unit 240 may transmit and receive reservation management information between the user terminal 10 and the service contact terminal 30 .

[0096] For example, the medical data management unit 240 transmits a reservation request signal received from the user terminal 10 to the service contact terminal 30 , and may also transmit a reservation completion signal generated by the service contact terminal 30 in response to the reservation request signal to the user terminal 10 .

[0097] In addition, the medical data management unit 240 may transmit the hospital record information to the user terminal 10. At this time, the medical data management unit 240 may receive the hospital record information from the service contact terminal 30.

[0098] For example, when companion animal 1's medical treatment is completed, medical data management unit 240 transmits hospital records containing medical history information to user terminal 10. Typically, hospital records containing preventive or cosmetic information may be transmitted to user terminal 10. Furthermore, medical data management unit 240 may transmit notification information regarding companion animal 1 to user terminal 10. In this case, notification information is generated by service contact terminal 30 and may be, but is not limited to, notification information regarding companion animal 1's medical treatment or cosmetic procedures.

[0099] According to an embodiment, the medical data management unit 240 may share hospital record information with other servers.

[0100] The management and control unit 250 can use deep learning to match basic status information and basic result data to generate health standard data. In this embodiment, the use of deep learning is described, but it is not limited to this. Machine learning technologies such as random forests and support vector machines can also be used. In this case, the management and control unit 250 can update the health standard data in real time in accordance with the health result data.

[0101] Specifically, the management control unit 250 repeatedly learns the basic status information and basic result data according to the Convolutional Neural Network (CNN) algorithm and verifies the adaptability, thereby generating health standard data. Figure 4 As shown, the process of verifying the health standard data can be performed by entrusting a veterinarian and a research team of a research institution, for example, at least three specialists to cross-verify the suitability, but is not limited thereto.

[0102] In addition, in the case of receiving the status detection information from the user terminal 10 , the management control part 250 may generate health result data based on the health standard data.

[0103] Specifically, the management control unit 250 generates health result data by extracting actual analysis images of each image from the actual analysis images extracted by preprocessing the pictures and / or videos contained in the status detection information. The above health result data includes actual diagnosis data and actual judgment data. The above actual diagnosis data can diagnose whether oral diseases are present with the naked eye. The above actual judgment data is generated by simultaneously performing multiple disease analyses on the actual analysis images of various parts based on the actual diagnosis data, and judging the progression stage of each disease corresponding to the actual diagnosis data.

[0104] For example, if the actual photographic information is information about an oral cavity, the management control unit 250 extracts analyzable actual analysis images from the image or video included in the actual photographic information, taking into account the surrounding environment, shake, clarity, and whether the oral cavity is captured. The extracted actual analysis images are automatically corrected for brightness, clarity, and other factors. From the corrected actual analysis images, actual analysis images for each region, such as teeth and gums, are extracted for analyzing multiple diseases. The presence of oral diseases that can be visually diagnosed is diagnosed, and the progression stage of each disease is determined based on the actual diagnosis data and the actual diagnosis data, thereby generating actual diagnosis information. Specifically, the management control unit 250 analyzes the area occupied by the teeth in the actual analysis images to determine color changes and the presence of wounds, and analyzes the area occupied by the gums in the actual analysis images to determine color changes and the presence of inflammation, thereby simultaneously analyzing diseases in multiple regions and analyzing the progression stages of multiple diseases using the analysis images for each region.

[0105] Furthermore, if the actual captured information is an image, the management control unit 250 can generate actual diagnosis data and actual judgment data for a single image. Alternatively, if the actual captured information is a video, a filtering step is performed to determine a normal image from the video, and at least ten images can be extracted to generate the actual diagnosis data and actual judgment data. In this case, filtering utilizes a Laplace filter to filter the degree of motion in the video when the area of ​​the oral cavity relative to the total area is greater than a specified value, thereby obtaining a normal image. However, this is not limiting.

[0106] According to an embodiment, in the case of transmitting the health standard data to the user terminal 10 , the management control portion 250 may receive health result data corresponding to the status detection information of the companion animal 1 .

[0107] According to an embodiment, the management control unit 250 can transmit and receive data with the user terminal 10, the service contact terminal 30, and / or the administrator terminal 40, and can also insert and transmit advertising information. This generates additional advertising revenue, which can be used to sponsor facilities such as stray dog ​​centers and protection centers.

[0108] The health management server 20, with the aforementioned structure, automatically extracts diagnostic sites from the condition detection information obtained by the user terminal 10 by repeatedly learning and verifying health standard data based on labeled basic result data corresponding to basic condition information obtained from multiple companion animals 1. The server then compares and analyzes the extracted images to analyze multiple diseases. This generates health result data that includes the presence or absence of oral diseases and the progression stage of each disease. This solves the problem of unnecessary hospital visits and untreated treatment that occurs when the condition of companion animals 1 is determined solely by visual inspection.

[0109] Furthermore, the health management server 20 provides recommendation information to the user terminal 10 according to the current state or disease state of the companion animal 1 , thereby enabling quick and accurate management of the companion animal 1 .

[0110] The health management server 20 described above may be implemented by hardware circuits (eg, CMOS-based logic circuits), firmware, software, or a combination thereof. For example, it may be implemented using transistors, logic gates, and electronic circuits as various electrical structures.

[0111] The service contact terminal 30 can diagnose the companion animal 1 more quickly using the health result data received from a plurality of animal hospitals that manage and diagnose the health of the companion animal 1 .

[0112] The service contact terminal 30 may share hospital record information with the user terminal 10 , the health management server 20 , and a separate server.

[0113] The service contact terminal 30 may provide hospital information and notification information to the user terminal 10 and / or the health management server 20 .

[0114] According to an embodiment, the service contact terminal 30 may include facilities such as a stray dog ​​center, a protection center, etc.

[0115] The administrator terminal 40 is a terminal carried by an independent administrator, and uses a wireless communication network to synchronize with the user terminal 10, the health management server 20, and the service contact terminal 30 in real time to send and receive data. At this time, the administrator terminal 40 can use an application program (or application) to send and receive data.

[0116] The manager terminal 40 learns the health standard data received from the health management server 20 , analyzes the status detection information received from the user terminal 10 , and can generate health result data including actual diagnosis data and actual judgment data.

[0117] According to an embodiment, in the case of receiving the status detection information from the user terminal 10 , the manager terminal 40 may compare and analyze the status detection information with the health standard data to generate health result data.

[0118] According to an embodiment, when health result data is generated from the user terminal 10, the administrator terminal 40 may receive the health result data from the user terminal 10 and transmit it to the health management server 20. In addition, when health result data is generated from the health management server 20, the administrator terminal 40 may receive the health result data from the health management server 20 and transmit it to the user terminal 10.

[0119] According to an embodiment, the manager terminal 40 may transmit and receive diagnosis and treatment management data corresponding to the current state or disease state of the companion animal 1 with at least one of the user terminal 10 , the health management server 20 , and the service contact terminal 30 based on the health result data.

[0120] The user terminal 40 described above may include various portable electronic communication devices that support communication with the user terminal 10, the health management server 20, and the service contact terminal 30. For example, individual smart devices may include, but are not limited to, various terminals such as smartphones, personal digital assistants, tablet computers, wearable devices (e.g., including watch-type terminals, glasses-type terminals, head-mounted displays, etc.), and various IoT terminals.

[0121] The operation of the oral disease diagnosis system for companion animals according to one embodiment of the present invention having the above-described structure is as follows.

[0122] Figure 5 FIG. 1 is a diagram for explaining a method for diagnosing oral diseases of companion animals according to an embodiment of the present invention. Figure 6 To illustrate the generation Figure 5 A detailed diagram of the method for health standard data is shown in Figure 7 To illustrate the generation Figure 6 Detailed diagram of the method underlying the resulting data shown in .

[0123] First, in the embodiments of the present invention, the companion animal 1 is disclosed as being limited to a puppy, but the present invention is not limited thereto.

[0124] like Figure 5 As shown, the health management server 20 may generate health standard data ( S10 ).

[0125] Specifically, refer to Figure 6 The health management server 20 can obtain basic information of multiple companion animals 1 (S10). The basic information may include guardian information, abandonment information, hospital record information, inherent identification number, dog breed, gender, age, weight, whether it is sterilized, whether it has given birth, etc., but is not limited to this.

[0126] For example, the disease data management unit 230 may obtain basic information of the companion animal 1 input using a separate mobile terminal.

[0127] Next, the health management server 20 may select an imaging part of the companion animal 1 based on the basic information ( S110 ).

[0128] For example, the disease data management unit 230 can confirm the imaging part of the companion animal 1 set by a separate mobile terminal. In other words, the disease data management unit 230 can select various parts of the companion animal 1 such as the mouth, face, ears, abdomen, feet, chest, back, etc.

[0129] Thereafter, in the case of photographing the oral cavity, the health management server 20 may photograph the oral cavity of the companion animal 1 once in a normal photographing mode to obtain normal photographing information ( S120 ).

[0130] For example, in the case where the oral region of the companion animal 1 is photographed in a normal photographing mode using a separate mobile terminal, the disease data management unit 230 may obtain normal photographing information from the mobile terminal.

[0131] Next, the health management server 20 may generate basic status information using the basic information and the basic shooting information including the corresponding general shooting information (S130). At this time, the general shooting information may include at least one picture and at least 10 seconds of video.

[0132] Thereafter, the health management server 20 may extract an analyzable analysis image from the basic photographing information to generate basic result data ( S140 ).

[0133] Specifically, if Figure 7 As shown, in a case where the information included in the basic photographing information is a picture ( S200 ), the health management server 20 verifies whether the picture is an analyzable image and may extract an analysis image ( S210 ).

[0134] For example, the disease data management unit 230 can extract analyzable analysis images by taking into account the surrounding environment, shake, clarity, and whether the oral cavity is captured. In this case, correction processing can be performed on the extracted analysis images. Specifically, the disease data management unit 230 can extract the oral cavity from the analysis image and perform white balance and brightness correction processing.

[0135] Next, the health management server 20 may extract analysis images for analyzing respective parts of a plurality of diseases from the extracted analysis images ( S220 ).

[0136] For example, the disease data management unit 230 extracts analysis images of each tooth portion and analysis images of each gum portion from the analysis image, and can analyze a plurality of diseases by portion at the same time.

[0137] Afterwards, basic diagnostic data for diagnosing whether an oral disease exists may be generated using the analyzed images of each part ( S230 ).

[0138] For example, the disease data management unit 230 uses analysis images of various parts extracted from teeth and gums to determine tartar or gum inflammation, diagnoses oral diseases based on the determination results, and generates basic diagnostic data on whether the patient has an oral disease.

[0139] Next, the health management server 20 may determine analysis images for analyzing respective parts of a plurality of diseases based on the basic diagnosis data, and may generate basic determination data ( S240 ).

[0140] Specifically, the disease data management unit 230 determines color changes, whether there are wounds, etc. in the image of the tooth part, and determines color changes, whether there is inflammation, etc. in the image of the gum part, and simultaneously analyzes multiple diseases in each part, so that multiple diseases can be analyzed through the analysis images of each part.

[0141] At this time, the disease data management unit 230 uses the DCIN algorithm to simultaneously judge the analysis images of each part according to the basic diagnosis data, and can more clearly generate basic judgment data for analyzing multiple diseases, but is not limited to this.

[0142] In addition, when the information included in the basic shooting information is a video ( S250 ), the opening and closing of the mouth in the video is filtered, and a normal image can be extracted.

[0143] For example, the disease data management unit 230 may determine normal images from the video through a filtering step and extract at least ten images. In this case, the filtering may utilize a Laplace filter to filter the degree of shaking in the video when the area of ​​the oral cavity relative to the total area is greater than a specified value, thereby obtaining a normal image.

[0144] As described above, the health management server 20 may generate basic result data corresponding to the basic status information.

[0145] Afterwards, the health management server 20 matches the basic status information and the basic result data ( S150 ), and can repeatedly learn according to the CNN algorithm and verify the adaptability to generate health standard data ( S160 , S170 ).

[0146] Next, when the caregiver requests diagnosis of the current condition or disease state of the companion animal 1 , the user terminal 10 may photograph the oral cavity of the companion animal 1 to generate actual photographic information ( S12 ).

[0147] Afterwards, if actual basic information is input, the user terminal 10 may generate state detection information using the actual basic information and the actual shooting information ( S14 ).

[0148] Next, the health management server 20 may generate health result data corresponding to the status detection information based on the health standard data ( S16 ).

[0149] Specifically, the management control unit 250 can extract and correct the actual analysis image by pre-processing the pictures and / or videos contained in the status detection information, and extract the actual analysis image of each part from the corrected actual analysis image to generate health result data. The above health result data includes actual diagnosis data and actual judgment data. The above actual diagnosis data can be diagnosed by the naked eye to see whether there is oral disease in the actual analysis image of each part, and the above actual judgment data is generated by judging the progression stage of each disease corresponding to the actual diagnosis data.

[0150] Thereafter, the user terminal 10 may receive health result data corresponding to the status detection information from the health management server 20 ( S18 ).

[0151] For example, when the health result data is output after the oral disease detection of the companion animal 1 is completed, the display unit 130 may output the oral disease detection result on the screen.

[0152] Next, the service contact terminal 30 may provide hospital information based on the health standard data ( S20 ).

[0153] The step of providing hospital information may be performed before, but is not limited thereto.

[0154] Thereafter, the health management server 20 may generate animal hospital contact information based on the hospital information ( S22 ).

[0155] The step of generating the contact information of the animal hospital may be performed before, but is not limited thereto.

[0156] Next, the health management server 20 may generate recommendation information corresponding to the health result data based on the animal hospital contact information and transmit the recommendation information to the user terminal 10 ( S24 ).

[0157] Thereafter, the health management server 20 may generate reservation management information ( S26 ).

[0158] For example, the health management server 20 receives a reservation request signal generated according to the customized information from the user terminal 10 , receives reservation management information corresponding to the reservation request signal from the service contact terminal 30 , and transmits the information to the user terminal 10 .

[0159] Next, the service contact terminal 30 may generate and share hospital record information including the medical history information of the companion animal 1 ( S28 ).

[0160] At this time, the hospital record information can be transmitted to the user terminal 10 and the health management server 20 .

[0161] Finally, the health management server 20 may update the health standard data in real time in correspondence with the health result data ( S30 ).

[0162] As described above, the diagnostic system 1000 for oral diseases of companion animals may include a user terminal 10 and a health management server 20. The user terminal 10 may generate status detection information including actual photographed information obtained from the inspection object, and the health management server 20 may analyze the status detection information by repeatedly learning and matching basic status information and basic result data to generate health standard data, and may generate health result data of the inspection object.

[0163] The health management server 20 extracts actual analysis images from the actual shooting information, and analyzes the actual analysis images of various parts extracted from the actual analysis images, diagnoses whether the examination object suffers from oral diseases to generate actual diagnosis data, and generates health result data. The above health result data includes actual judgment data generated by judging the progression stages of various oral diseases based on the actual diagnosis data.

[0164] The health management server 20 pre-processes the images contained in the basic shooting information, which is contained in the basic status information, extracts analyzable analysis images from the images, extracts analysis images of various parts used to analyze multiple diseases from the analysis images, diagnoses whether oral diseases exist in the analysis images of various parts, and generates basic diagnostic data. Based on the basic diagnostic data, the progression stage of each disease in the analysis images of various parts is judged, and basic judgment data is generated, generating basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

[0165] That is, the health management server 20 generates health standard data by matching basic status information and basic result data, receives status detection information of the inspection object from the user terminal 10, and can generate health result data by comparing and analyzing the status detection information with the health standard data.

[0166] When generating health standard data, the health management server 20 preprocesses the images contained in the basic shooting information, the above-mentioned basic shooting information is contained in the basic status information, extracts analyzable analysis images from the preprocessed images, extracts analysis images of various parts for analyzing multiple diseases from the analysis images, diagnoses whether oral diseases exist in the analysis images of various parts, and generates basic diagnostic data. According to the basic diagnostic data, the progression stage of each disease in the analysis images of various parts is judged, and basic judgment data is generated, and basic result data including basic diagnostic data and basic judgment data corresponding to the basic diagnostic data is generated.

[0167] When generating health result data, the health management server 20 extracts actual analysis images from the actual shooting information, which is included in the status detection information of the inspection object, extracts actual analysis images of various parts from the actual analysis images to diagnose whether there are oral diseases in the actual analysis images of various parts, and generates actual diagnosis data. According to the actual diagnosis data, the progression stage of each disease in the actual analysis images of various parts is judged to generate actual judgment data, and health result data containing actual diagnosis data and actual judgment data corresponding to the actual diagnosis data can be generated.

[0168] Below, refer to Figure 8 and Figure 9 , the process of extracting the actual analysis image is explained in detail.

[0169] Figure 8 FIG. 1 is a diagram for explaining a process of extracting an actual analysis image according to an embodiment of the present invention. Figure 9 FIG. 1 is a diagram showing the result of extracting an actual analysis image.

[0170] like Figure 8 As shown, when the actual photographing information includes the first image, the health management server 20 may analyze the degree of shaking of the first image ( S900 ).

[0171] Specifically, the user terminal 10 generates actual photographic information including a first image by photographing the companion animal 1, generates status detection information using the actual photographic information, and transmits the status detection information to the health management server 20. Upon receiving the status detection information from the user terminal 10, the health management server 20 may confirm, based on the status detection information, that the actual photographic information contains the first image, and may analyze the degree of shaking of the confirmed first image.

[0172] When analyzing the degree of shaking of the first image, the health management server 20 may analyze the shaking value indicating the degree of shaking of the first image within a specified range, wherein a higher value indicates more shaking and a lower value indicates less shaking.

[0173] For example, when the degree of shake is set to a range of 1 to 10, the health management server 20 analyzes the result of the degree of shake of the first image. If the shake state of the first image is analyzed to be a state of excessive shake, the degree of shake of the first image can be analyzed as a value between 8 and 10. If the shake state of the first image is analyzed to be a state of appropriate shake, the degree of shake of the first image can be analyzed as a value between 4 and 7. If the shake state of the first image is analyzed to be a state of almost no shake, the degree of shake of the first image can be analyzed as a value between 1 and 3.

[0174] The health management server 20 may analyze the value of the shake degree of the first image by comparing the image learned based on the shake value with the first image. To this end, the database unit 210 may store and manage the image learned based on the shake value.

[0175] That is, the health management server 20 may analyze the degree of shaking of the first image and convert the degree of shaking of the first image into a first value according to the shaking state of the first image.

[0176] If the shaking degree of the first image is analyzed as a first value, the health management server 20 may confirm whether the first value is lower than a first standard value (S910). The first standard value may be set differently according to the embodiment.

[0177] If it is determined that the first value is lower than the first standard value, the health management server 20 may analyze the clarity of the first image ( S920 ).

[0178] When analyzing the clarity of the first image, the health management server 20 may analyze the clarity of the first image within a specified range using a clarity value indicating how clear the first image is, wherein a higher clarity value indicates greater clarity and a lower clarity value indicates less clarity.

[0179] For example, when the clarity is set to a range of 1 to 10, the health management server 20 analyzes the clarity of the first image. If the first image is analyzed to be in a very clear state, the clarity of the first image can be analyzed as a value between 8 and 10. If the first image is analyzed to be in a clear state, the clarity of the first image can be analyzed as a value between 4 and 7. If the first image is analyzed to be in an unclear state, the clarity of the first image can be analyzed as a value between 1 and 3.

[0180] The health management server 20 may analyze the clarity value of the first image by comparing the image learned based on the clarity value with the first image. To this end, the database unit 210 may store and manage the image learned based on the clarity value.

[0181] That is, the health management server 20 may analyze the clarity of the first image and convert the clarity of the first image into a second value according to the clarity state of the first image by analyzing the clarity of the first image.

[0182] If the definition analysis of the first image is a second value, the health management server 20 may confirm whether the second value is higher than a second standard value (S930). The second standard value may be set differently according to the embodiment.

[0183] If it is confirmed that the second value is higher than the second standard value, the health management server 20 may analyze which part of the companion animal is imaged by the first image ( S940 ).

[0184] Specifically, when the area occupied by a specific part in the first image is above a specified area, the health management server 20 can analyze it as an image of the corresponding part. For example, the first image can be analyzed as an image of which part the first image is taken. When the area occupied by the oral part in the first image is above 70%, the first image can be analyzed as an image of the oral part.

[0185] The health management server 20 may confirm whether the first image is an image of the oral cavity ( S950 ).

[0186] If the first image is analyzed as an image capturing the oral cavity, the health management server 20 may classify the first image as an analyzable image ( S960 ).

[0187] If it is confirmed that the first value is not lower than the first standard value, or the second value is confirmed to be not higher than the second standard value, or the first image is analyzed as not an image of the oral area but an image of other areas, the health management server 20 may classify the first image as an unanalyzable image (S970).

[0188] As described above, pictures generated by photographing the companion animal 1 can be classified into unanalyzable data and analyzable data based on shaking, clarity, whether the teeth or gums are photographed, etc., and the process of confirming whether an image is analyzable based on shaking, clarity, whether the teeth or gums are photographed, etc. can be learned through machine learning. For analyzable images, they can be cropped with the teeth and gums as the center and extracted as actual analysis images.

[0189] For example, refer to Figure 9 (a), the health management server 20 can Figure 9 The first image shown in (a) is classified as an analyzable image based on its shaking, clarity, whether the oral cavity is photographed, etc. If the first image is classified as an analyzable image, the first image is cropped with the oral cavity as the center and extracted as the actual analysis image.

[0190] For example, refer to Figure 9 (b), the health management server 20 can Figure 9 The shaking, clarity, whether the oral cavity is photographed, etc. of the first image shown in (b) are used to classify the first image as an unanalyzable image. If the first image is classified as an unanalyzable image, after deleting the first image, a reshooting request notification message can be transmitted to the user terminal 10.

[0191] After extracting the first image as the actual analysis image, the health management server 20 may perform white balance and brightness correction processing on the first image.

[0192] Below, refer to Figure 10 and Figure 11 , details the process of performing brightness correction on an image.

[0193] Figure 10 FIG. 1 is a diagram for illustrating a process of performing brightness correction processing on an image according to an embodiment of the present invention. Figure 11 is a diagram showing the result of performing brightness correction on an image.

[0194] like Figure 10 As shown, if the first image is extracted as the actual analysis image, the health management server 20 may analyze the brightness of the first image ( S1100 ).

[0195] When analyzing the brightness of the first image, the health management server 20 may analyze the brightness of the first image within a specified range using a brightness value indicating how bright the first image is, where a higher value indicates brighter and a lower value indicates darker.

[0196] For example, when the brightness is set to a range of 1 to 10, the health management server 20 analyzes the brightness of the first image. If the first image is analyzed to be in a very bright state, the brightness of the first image can be analyzed as a value between 8 and 10. If the first image is analyzed to be in a bright state, the brightness of the first image can be analyzed as a value between 4 and 7. If the first image is analyzed to be in a dark state, the brightness of the first image can be analyzed as a value between 1 and 3.

[0197] The health management server 20 compares the image learned based on the brightness value with the first image to analyze which value the brightness of the first image belongs to. To this end, the database unit 210 may store and manage the image learned based on the brightness value.

[0198] That is, the health management server 20 may analyze the brightness of the first image to obtain the third value according to the brightness state of the first image by analyzing the brightness of the first image.

[0199] If the brightness analysis of the first image is a third value, the health management server 20 may confirm whether the third value is within a standard range (S1110). The standard range may be set differently according to the embodiment.

[0200] If it is confirmed that the third value is within the standard range, the health management server 20 may determine that the first image does not need to be corrected ( S1120 ).

[0201] For example, when the standard range is set to 4 to 7, if the health management server 20 confirms that the third value is 5, it is determined that the third value is within the standard range, and thus it can be determined that the first image does not need correction.

[0202] If it is confirmed that the third value is out of the standard range, the health management server 20 may set a correction value for the first image according to the third value ( S1130 ).

[0203] When the health management server 20 sets the correction value of the first image, if it is determined that the third value is greater than the maximum value of the standard range, the correction value can be set to a lower value as the third value is higher. In this case, the correction value can be set to a value less than 0 to darken the image.

[0204] For example, when the standard range is set to 4 to 7, if the health management server 20 confirms that the third value is 8, the correction value of the first image can be set to -1; if the third value is confirmed to be 9, the correction value of the first image can be set to -2.

[0205] When setting the correction value of the first image, if the health management server 20 confirms that the third value is less than the minimum value of the standard range, the lower the third value, the higher the correction value can be set. In this case, the correction value can be set to a value greater than 0 to brighten the image.

[0206] For example, when the standard range is set to 4 to 7, if the health management server 20 confirms that the third value is 3, the correction value of the first image can be set to 1; if the third value is confirmed to be 2, the correction value of the first image can be set to 2.

[0207] If the correction value of the first image is set, the health management server 20 may perform brightness correction of the first image using the correction value ( S1140 ).

[0208] In a case where the correction value of the first image is a negative number, the health management server 20 may perform brightness correction using the correction value to darken the first image.

[0209] For example, in the health management server 20, if the correction value of the first image is confirmed to be -1, brightness correction is performed by darkening the first image by 1 level. If the correction value of the first image is confirmed to be -2, brightness correction is performed by darkening the first image by 2 levels.

[0210] In a case where the correction value of the first image is a positive number, the health management server 20 may perform brightness correction using the correction value to brighten the first image.

[0211] For example, in the health management server 20, if the correction value of the first image is confirmed to be 1, brightness correction is performed by brightening the first image by 1 level. If the correction value of the first image is confirmed to be 2, brightness correction is performed by brightening the first image by 2 levels.

[0212] As described above, the white balance and brightness correction processes are performed on the first image according to the brightness state of the first image, thereby correcting the first image to an image suitable for analysis.

[0213] For example, refer to Figure 11 As shown in the left figure, when the brightness state of the first image is in a dark state, brightness correction is performed on the first image. As shown in the right figure, the first image can be changed into an image suitable for analysis when diagnosing oral diseases.

[0214] The health management server 20 performs brightness correction on the first image and then diagnoses whether the patient has an oral disease, thereby generating actual diagnosis data.

[0215] Below, refer to Figure 12 and Figure 13 , which explains in detail the process of generating actual diagnostic data by diagnosing whether an oral disease is present.

[0216] Figure 12 FIG. 1 is a diagram for explaining a process of generating actual diagnosis data by diagnosing whether an oral disease exists according to an embodiment of the present invention. Figure 13 Graphs showing the results of extracting analysis images for various regions.

[0217] like Figure 12 As shown, the health management server 20 cuts out the area occupied by the teeth in the first image and extracts it as a second image (S1300). In the process of extracting the second image, the CNN landmark algorithm can be applied.

[0218] For example, refer to Figure 13 In step (a), if the area occupied by the teeth in a specific region of the first image is determined to be greater than a predetermined area, the health management server 20 may crop the corresponding region to the area occupied by the teeth and extract the cropped portion as the second image. In this case, if there are multiple areas occupied by the teeth, multiple areas may be cropped and extracted as the second image.

[0219] The health management server 20 may analyze whether the tooth part has disease symptoms based on the second image (S1310). At this time, the health management server 20 may analyze whether there is at least one symptom of tooth decay, tartar, tooth fracture, tooth discoloration, residual deciduous teeth, and tooth loss based on the second image.

[0220] The health management server 20 can analyze whether the companion animal 1 has disease symptoms in the teeth by comparing the image learned according to the disease symptoms of the teeth with the second image. To this end, the database unit 210 can store and manage the image learned according to the disease symptoms of the teeth.

[0221] The health management server 20 can diagnose whether there is an oral disease in the tooth area based on the second image analysis to determine whether there is at least one symptom of tooth decay, tartar, tooth fracture, tooth discoloration, residual deciduous teeth and tooth loss (S1320).

[0222] If the health management server 20 analyzes that there is at least one symptom of tooth decay, tartar, tooth fracture, tooth discoloration, remaining deciduous teeth and missing teeth, the oral disease of the dental part can be diagnosed as yes. If the analysis shows that there is no symptom of tooth decay, tartar, tooth fracture, tooth discoloration, remaining deciduous teeth and missing teeth, the oral disease of the dental part can be diagnosed as no.

[0223] In addition, the health management server 20 cuts out the area occupied by the gums in the first image and extracts it as a third image (S1330). In the process of extracting the third image, a CNN landmark algorithm can be applied.

[0224] For example, refer to Figure 13 In step (b), if the results of the region-by-region analysis of the first image confirm that the area occupied by the gum portion in a specific region is greater than a specified area, the health management server 20 may crop the corresponding region to the area occupied by the gum portion and extract the cropped portion as a third image. In this case, if there are multiple areas occupied by the gum portion, multiple areas may be cropped and extracted as the third image.

[0225] The health management server 20 may analyze whether the gum area has disease symptoms based on the third image (S1340). At this time, the health management server 20 may analyze whether at least one of gum inflammation and gum tumor exists based on the third image.

[0226] The health management server 20 can analyze whether the gum area of ​​the companion animal 1 has disease symptoms by comparing the image learned based on the disease symptoms of the gum area with the third image. To this end, the database unit 210 can store and manage the image learned based on the disease symptoms of the gum area.

[0227] The health management server 20 may analyze whether at least one symptom of gum inflammation and gum tumor exists based on the third image, and diagnose whether there is an oral disease in the gum area ( S1350 ).

[0228] If the analysis shows that there is at least one symptom of gingivitis and gingival tumor, the health management server 20 can diagnose whether there is oral disease in the gum area as yes; if the analysis shows that there is no symptom of gingivitis and gingival tumor, the health management server 20 can diagnose whether there is oral disease in the gum area as no.

[0229] If the presence of oral diseases in the teeth and gums is diagnosed, the health management server 20 may generate actual diagnosis data including each diagnosis result ( S1360 ).

[0230] The steps of the methods or algorithms described in the embodiments of the present invention may be implemented directly by hardware, or by a software module executed by hardware, or by a combination thereof. The software module may reside in a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium known in the art to which the present invention belongs.

[0231] While the embodiments of the present invention have been described above with reference to the accompanying drawings, those skilled in the art will appreciate that the present invention can be implemented in other specific forms without changing the technical concept or essential features of the present invention. Therefore, it should be understood that the embodiments described above are merely illustrative in all respects and are not restrictive.

Claims

1. A method for diagnosing oral diseases of companion animals, which is performed by a health management server, comprising the following steps: Generate health standard data by matching basic status information and basic result data; receiving status detection information of the inspection object from the user terminal; and Based on the above health standard data, the above status detection information is compared and analyzed to generate health result data. The steps for generating the above health standard data include the following steps: Preprocessing an image included in basic shooting information, wherein the basic shooting information is included in the basic state information; extracting an analyzable analysis image from the pre-processed image; Extracting analysis images of various parts for analyzing a plurality of diseases from the analysis images, diagnosing whether oral diseases exist in the analysis images of the various parts, and generating basic diagnostic data; Determining the progression stage of each disease in the analysis images of each of the above-mentioned parts based on the above-mentioned basic diagnostic data, and generating basic judgment data; and The basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data is generated.

2. The method for diagnosing oral diseases of companion animals according to claim 1, wherein: The steps for generating the above health outcome data include the following steps: extracting an actual analysis image from actual photographed information included in the state detection information of the inspection object; Extracting actual analysis images of various parts from the actual analysis images, diagnosing whether the oral disease exists in the actual analysis images of the various parts, and generating actual diagnosis data; Based on the actual diagnosis data, the progression stage of each disease in the actual analysis images of each part is judged, and actual judgment data is generated; as well as The health result data including the actual diagnosis data and the actual judgment data corresponding to the actual diagnosis data is generated.

3. The method for diagnosing oral diseases of companion animals according to claim 2, wherein: The steps of extracting the above-mentioned actual analysis image include the following steps: When the actual shooting information includes a first image, analyzing the shaking degree of the first image; If the shaking degree of the first image is analyzed as a first value, determining whether the first value is lower than a first standard value; If it is confirmed that the first value is lower than the first standard value, analyzing the clarity of the first image; If the clarity of the first image is analyzed as a second value, determining whether the second value is higher than a second standard value; If it is confirmed that the second value is higher than the second standard value, analyzing which part of the companion animal is captured in the first image; as well as If the first image is analyzed as an image of the oral cavity, the first image is classified as an image that can be analyzed, and the first image is extracted as the actual analysis image.

4. The method for diagnosing oral diseases of companion animals according to claim 3, wherein: The steps to generate the above actual diagnostic data include the following steps: If the first image is extracted as the actual analysis image, analyzing the brightness of the first image; If the brightness of the first image is analyzed as a third value, determining whether the third value is within a standard range; If it is confirmed that the third value is within the standard range, it is determined that the first image does not need to be corrected; If it is confirmed that the third value exceeds the standard range, setting a correction value of the first image according to the third value; and The brightness correction of the first image is performed using the correction value.

5. The method for diagnosing oral diseases of companion animals according to claim 4, wherein: The steps of generating the above-mentioned actual diagnostic data also include the following steps: Cutting out the area occupied by the teeth in the first image and extracting it as the second image; analyzing, based on the second image, whether at least one of the following symptoms is present: tooth decay, tartar, tooth fracture, tooth discoloration, retained deciduous teeth, and tooth loss; diagnosing whether the aforementioned oral disease exists in the aforementioned tooth area; and generating the aforementioned actual diagnosis data; Cutting out the area occupied by the gums from the first image and extracting it as a third image; and Based on the third image, it is analyzed whether at least one symptom of gingival inflammation and gingival tumor exists, and it is diagnosed whether the gingival area has the oral disease, and the actual diagnosis data is generated.

6. The method for diagnosing oral diseases of companion animals according to claim 1, wherein: The steps for generating the above basic result data include the following steps: Based on the basic information of the inspection object contained in the above-mentioned basic status information, the analysis images of the above-mentioned various parts are analyzed with the naked eye. When there is tartar in the teeth of the above-mentioned inspection object or there is inflammation in the gums of the above-mentioned inspection object, the oral disease is classified as present and the above-mentioned basic diagnostic data is marked.

7. A diagnostic system for oral diseases of companion animals, comprising: A user terminal generates status detection information, wherein the status detection information includes actual photographic information obtained from the inspection object; as well as A health management server that repeatedly learns health standard data generated by matching basic status information and basic result data, analyzes the above status detection information, and generates health result data of the above inspection object, In the above health management server, Extracting an actual analysis image from the actual photographing information, analyzing the actual analysis images of various parts extracted from the actual analysis image, diagnosing whether the inspection object suffers from an oral disease to generate actual diagnosis data, and generating the health result data, the health result data including actual judgment data generated by judging the progression stage of each oral disease based on the actual diagnosis data, Preprocess the images contained in the basic shooting information contained in the basic status information, extract analyzable analysis images from the images, extract analysis images of various parts for analyzing multiple diseases from the analysis images, diagnose whether oral diseases exist in the analysis images of the various parts, and generate basic diagnostic data, judge the progression stage of each disease in the analysis images of the various parts based on the basic diagnostic data, and generate basic judgment data, and generate the basic result data including the basic diagnostic data and the basic judgment data corresponding to the basic diagnostic data.

8. A computer program incorporated in a computer as hardware and stored in a computer-readable recording medium in a manner that executes the method according to any one of claims 1 to 6.

Images