KR102534158B1 - Method and system for providing artificial intelligence diagnosis information for companion animals - Google Patents

Abstract

A method and system for providing artificial intelligence diagnostic information for companion animals are disclosed. A method of providing artificial intelligence diagnosis information for companion animals performed in a server device according to an aspect of the present invention includes receiving companion animal information for diagnosis from a guardian terminal; For companion animal information, performing artificial intelligence diagnosis by deep learning on diagnosis information big data; Storing artificial intelligence diagnosis information according to artificial intelligence diagnosis and generating access information for accessing artificial intelligence diagnosis information; and providing artificial intelligence diagnosis information to any veterinarian terminal that has made a request using the access information.

Description

Method and system for providing artificial intelligence diagnosis information for companion animals

The present invention relates to a method and system for providing artificial intelligence diagnostic information for companion animals.

In recent years, more and more people live alone beyond nuclear families, and the number of people with companion animals such as dogs and cats is increasing day by day. However, since companion animals cannot speak, veterinarians often misdiagnose, and medical accidents and medical disputes are increasing. As a result, there is a high interest in artificial intelligence diagnosis services that analyze the opinions of guardians, as well as analyze and advise veterinary images such as X-ray images and CT images of animals.

Artificial intelligence diagnosis service will be provided not only as a means for veterinarians' diagnosis assistance, but also for companion animal guardians' direct self-diagnosis, and for this reason, a more effective and accurate diagnosis method is required. In addition, it is necessary to effectively deliver AI diagnosis information for self-diagnosis to veterinarians at veterinary hospitals.

Republic of Korea Patent Publication No. 10-2019-0077636 (published on July 4, 2019) Companion animal healthcare artificial intelligence system

Therefore, the present invention has been made to solve the above-mentioned problems, and allows the guardian to perform self-diagnosis for companion animals using artificial intelligence, and furthermore, provides convenience by allowing expert opinions to be checked online. It is to provide a method and system for providing artificial intelligence diagnostic information for animals.

In addition, the present invention is to provide a method and system for providing artificial intelligence diagnosis information for companion animals, which can more easily and safely deliver diagnosis information by artificial intelligence when receiving a detailed diagnosis from a veterinarian.

Other objects of the present invention will become clearer through preferred embodiments described below.

According to one aspect of the present invention, in a method of providing artificial intelligence diagnostic information for companion animals performed in a server device, the step of receiving companion animal information for diagnosis from a guardian terminal; Performing artificial intelligence diagnosis by deep learning on the diagnostic information big data for the companion animal information; storing artificial intelligence diagnosis information according to the artificial intelligence diagnosis and generating access information for accessing the artificial intelligence diagnosis information; and providing the artificial intelligence diagnostic information to any veterinarian terminal that made a request using the access information, including a method for providing artificial intelligence diagnostic information for companion animals and a record in which a program executing the method is recorded. medium is provided.

Here, exposing the companion animal information and the artificial intelligence diagnosis information to a plurality of expert terminals during a waiting time; and processing information on expert opinions collected during the waiting time, storing the information together with the artificial intelligence diagnosis information, and providing the information to the guardian terminal.

In addition, the expert opinion is analyzed to calculate an accuracy value for the artificial intelligence diagnosis result, and among the information on the expert opinion, information on the expert opinion most similar to and most different from the artificial intelligence diagnosis is obtained along with the accuracy value. First of all, it is exposed to the guardian terminal.

In addition, the expert terminal is selected based on the location of the guardian terminal and the companion animal information.

In addition, the service cost for the artificial intelligence diagnosis is determined using the waiting time and the number of expert terminals.

In addition, a reservation is made with an expert presenting an opinion selected from the guardian terminal among the expert opinions, and the access information is provided to the reserved expert terminal.

In addition, when access to the AI diagnosis information using the access information is requested from the veterinarian terminal, whether to provide the AI diagnosis information to the veterinarian terminal is determined according to an authentication result using the location of the guardian terminal. .

According to another aspect of the present invention, a guardian terminal providing companion animal information for diagnosis; For the companion animal information, artificial intelligence diagnosis is performed by deep learning on the diagnosis information big data, artificial intelligence diagnosis information according to the artificial intelligence diagnosis is stored, and access information for accessing the artificial intelligence diagnosis information is provided. Artificial intelligence diagnosis server to generate; and a veterinarian terminal acquiring the artificial intelligence diagnosis information by making a request to the artificial intelligence diagnosis server using the access information.

Here, the artificial intelligence diagnosis server exposes the companion animal information and the artificial intelligence diagnosis information to a plurality of expert terminals during a waiting time, and processes information on expert opinions collected during the waiting time to process the artificial intelligence diagnosis information. It is stored together and provided to the guardian terminal.

According to the present invention, self-diagnosis can be performed on companion animals using artificial intelligence, and even expert opinions can be checked online, providing convenience to guardians.

In addition, according to the present invention, diagnosis information by artificial intelligence can be delivered more easily and safely when receiving a detailed diagnosis from a veterinarian.

1 is a configuration diagram schematically showing an entire system for providing artificial intelligence diagnosis information for companion animals according to an embodiment of the present invention.
2 is a block diagram showing the configuration of a diagnostic information providing server according to an embodiment of the present invention.
3 is a flowchart schematically illustrating a process of providing artificial intelligence diagnosis information for companion animals according to an embodiment of the present invention.
4 is a flowchart illustrating a process of providing a diagnosis opinion using collective intelligence of experts according to an embodiment of the present invention. .
5 is an exemplary diagram illustrating diagnosis information for a veterinary image according to an embodiment of the present invention;
6 is a flowchart illustrating a process of providing access information to an expert according to an embodiment of the present invention.
7 is a flowchart illustrating a process of providing access information according to location-based authentication of a guardian terminal according to an embodiment of the present invention.

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

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, terms such as a first threshold value and a second threshold value, which will be described later, may be substantially different from each other or partially identical to each other. Since there is room, terms such as first and second are written together for convenience of classification.

Terms used in this specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

In addition, the components of the embodiments described with reference to each drawing are not limitedly applied only to the corresponding embodiment, and may be implemented to be included in other embodiments within the scope of maintaining the technical spirit of the present invention, and also separate Even if the description is omitted, it is natural that a plurality of embodiments may be re-implemented as an integrated embodiment.

In addition, in the description with reference to the accompanying drawings, the same or related reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the present invention, if it is determined that a detailed description of related known technologies may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted.

FIG. 1 is a configuration diagram schematically showing an entire system for providing artificial intelligence diagnosis information for companion animals according to an embodiment of the present invention.

Referring to FIG. 1 , the entire system includes a guardian terminal 10, a veterinarian terminal (30-1, ..., 30-n, hereinafter collectively referred to as 30) and a diagnostic information providing server 50.

The guardian terminal 10 is a terminal device owned by a guardian of a companion animal, and may be, for example, a PC or a mobile device. The diagnostic information providing server 50 provides an interface for AI self-diagnosis to the guardian terminal 10 . That is, the companion animal guardian performs self-diagnosis on the companion animal using artificial intelligence using the interface provided by the diagnosis information providing server 50 in an application program or web method using the guardian terminal 10. . For example, artificial intelligence diagnosis is performed by the diagnosis information providing server 50 using companion animal information such as images such as X-ray images and CT images of companion animals, videos of companion animals, and texts about symptoms. .

The veterinarian terminal 30 is a terminal device possessed by a veterinarian and is a computing device equipped with a communication means for communicating with the diagnostic information providing server 50 through a communication network, and diagnostic information by artificial intelligence diagnosis from the diagnostic information providing server 50. is acquired and displayed. For example, the veterinarian terminal 30 may display a display means (eg, an x-ray image or a CT image) for displaying an image for medical purposes (hereinafter referred to as a veterinary image) for an animal. For example, a display such as a touch screen, etc.) is provided.

In addition, the veterinarian terminal 30 can also use the artificial intelligence diagnosis service provided by the diagnosis information providing server 50 like the guardian terminal 10 . That is, the veterinarian performs diagnosis using companion animal information such as a veterinary image displayed on the veterinarian terminal 30, and can also check information on AI diagnosis received from the diagnosis information providing server 50. In other words, the diagnostic information providing server 50 receives and analyzes companion animal information, performs artificial intelligence diagnosis, and provides it to the veterinarian terminal 30 . Therefore, veterinarians can reduce the probability of misdiagnosis by referring to the diagnosis information by artificial intelligence when diagnosing themselves.

The diagnostic information providing server 50 performs artificial intelligence diagnosis based on companion animal information including veterinary images and symptom information acquired from the guardian terminal 10 or the veterinarian terminal 30. Perform deep learning using diagnostic information big data. For example, diagnosis information by experts along with information on various veterinary images and symptoms is stored as big data as diagnosis history information, and is used as data for learning artificial intelligence. For example, if companion animal information is an X-ray image of a dog's hind legs, artificial intelligence diagnosis that determines whether a disease such as fracture or inflammation exists based on what has been learned from other images having the most similar shape is performed. is to carry out Since services are operated and attempted in various medical fields with the concept of performing medical diagnosis by artificial intelligence based on images, etc., it will be obvious to those skilled in the art, so a more detailed description will be omitted. In addition, since artificial intelligence learning using big data is widely used in other fields recently, it will be obvious to those skilled in the art, so a more detailed description will be omitted.

In addition, the diagnosis information providing server 50 may provide such artificial intelligence diagnosis service to the guardian terminal 10 or the veterinarian terminal 30 in the form of a cloud service in the form of SaaS (Software as a Service). According to this, it is possible to upgrade the examination service, and also, due to the acquisition of various diagnostic information, the learning of the image reading function of artificial intelligence (AI) can be strengthened. In addition, due to the expansion of AI diagnosis, cheaper medical expenses can be induced, thereby guaranteeing the right to health of companion animals. In addition, since medical data is managed in the form of a cloud service, it is possible to establish a legal basis for companion animal medical insurance laws.

2 is a block diagram showing the configuration of a diagnostic information providing server according to an embodiment of the present invention, and FIG. 3 schematically illustrates a process of providing artificial intelligence diagnostic information for companion animals according to an embodiment of the present invention. It is a flow chart.

Referring to FIG. 2, the diagnostic information providing server 30 includes a communication unit 210, a storage unit 220, and a control unit 230, and the control unit 230 includes an artificial intelligence diagnosis unit 231 and an access information generation unit. (232) and a diagnostic information providing unit (233).

The communication unit 210 is for communicating with the guardian terminal 10 and the veterinarian terminal 30 through a communication network, and since this will be obvious to those skilled in the art, a detailed description thereof will be omitted.

In the storage unit 220, data for driving the communication unit 210 and the control unit 230 is stored, in particular, learning data for deep learning of artificial intelligence is stored, and knowledge information for diagnosis of artificial intelligence is stored. Learning data and/or knowledge information may be stored and managed in the form of a DB (database) as a separate storage medium. In addition, the storage unit 220 stores diagnosis information by artificial intelligence diagnosis and access information (eg, serial number or URL) for accessing the diagnosis information.

The artificial intelligence diagnosis unit 231 of the control unit 230 performs AI diagnosis on the companion animal based on the input companion animal information. For example, when a number image is received from the guardian terminal 10, the artificial intelligence diagnosis unit 231 analyzes the number image to diagnose whether there is a disease based on knowledge information learned by deep learning, Diagnosis result information is output.

The access information generation unit 232 of the control unit 230 generates access information (eg, serial number, URL, etc.) that can access diagnosis information according to AI diagnosis results. That is, the control unit 230 stores artificial intelligence diagnosis information, which is information obtained by processing the diagnosis results performed by the artificial intelligence diagnosis unit 231, in the storage unit 220, and generates access information for accessing the information. is to do

The diagnostic information providing unit 233 provides corresponding artificial intelligence diagnostic information to any veterinarian terminal that has made a request using the access information.

That is, referring to FIG. 3 showing the processing procedure, the diagnostic information providing server 50 receives companion animal information (veterinary image, symptom information (text), companion animal activity video, crying) received from the guardian terminal 10. When a recorded sound source, etc.) is received (S310), diagnosis by artificial intelligence learned by big data is performed (S320).

The provision server 50 can provide the result of AI diagnosis to the guardian terminal 10, and also stores AI diagnosis information including AI diagnosis results and companion animal information, and converts AI diagnosis information to AI diagnosis information. Generates access information for access (S330). The connection information generated in this way may be provided to the guardian terminal 10 or may be provided to the veterinarian terminal 30 designated by the guardian terminal 10 . For example, when a reservation service for a specialized animal hospital is provided to the guardian terminal 10 and the reservation is performed, access information may be provided to the veterinarian terminal of the reserved specialized hospital together with the reservation information.

Subsequently, when a request using the corresponding access information is received from any veterinarian terminal, the stored artificial intelligence diagnosis information is provided (S340). At this time, as will be described later, an authentication procedure may be performed to enhance security, and diagnostic information may be provided only when authentication is successful. For example, authentication may be performed using the location of the guardian terminal 10, or authentication may be performed using reservation information (eg, reservation time) when a reservation is made with a guardian in advance. This will be described in detail later.

Until now, the diagnosis information providing server 50 has been mainly described to provide only diagnosis services using artificial intelligence. According to another example, a service using collective intelligence of a group of experts may be provided.

4 is a flowchart illustrating a service process for providing a diagnosis opinion using expert collective intelligence according to an embodiment of the present invention, and FIG. 5 is an example showing diagnosis information on a veterinary image according to an embodiment of the present invention. It is also

Referring to FIG. 4 , in providing an artificial intelligence diagnosis service, first, a service charge is settled with the guardian terminal 10 (S410). That is, a free diagnosis service may be provided, but this is an example of providing a paid service.

Here, the service fee may be set in various ways, but in the present embodiment, the service fee varies according to the number of experts to be used and waiting time.

That is, when the service charge is settled, the diagnostic information providing server 50 determines the waiting time and the number of experts corresponding to the service charge (the waiting time and the number of experts for each charge may be set in advance) (S420), and the determined standby time Artificial intelligence diagnostic information is exposed to the corresponding number of expert terminals during the time (S430). That is, AI diagnosis information including AI diagnosis results is exposed to experts. For example, AI diagnosis information corresponding to the guardian terminal for which fee A is paid is exposed to 10 experts for one hour.

When the waiting time elapses, the collected expert opinions and artificial intelligence diagnosis information are provided to the guardian terminal 10 (S440).

Referring to FIG. 5 showing the interface screen provided to the guardian terminal, along with an X-ray image of companion animal information, artificial intelligence diagnosis results 510 and expert opinions 520 are displayed on one side of the screen.

Here, according to an example, the expert opinion is analyzed to calculate the accuracy value for the artificial intelligence diagnosis result, and among the information on the expert opinion, information on the expert opinion most similar to and most different from the artificial intelligence diagnosis is prioritized along with the accuracy value. and exposed to the guardian terminal. For example, if 8 out of 10 experts disclosed the same opinion as the artificial intelligence diagnosis result, the accuracy value may be calculated as 80%, which is, of course, only one example.

And according to an example, the display method of expert opinions may vary depending on the accuracy value. For example, the lower the accuracy value (eg, below the first threshold value), the more expert opinions that differ from the artificial intelligence diagnosis. Conversely, if the accuracy value is high (eg, greater than or equal to a second threshold value greater than the first threshold value), the most similar expert opinion is displayed preferentially.

According to this example, the guardian can immediately recognize the difference between the artificial intelligence diagnosis and the opinions of experts through the accuracy of the artificial intelligence diagnosis, and also, by first checking the different opinions among the experts' opinions and encountering various opinions, they can be more cautious. Diagnosis can reduce the probability of misdiagnosis.

And, the diagnosis information providing server 50 selects an expert terminal based on the location of the guardian terminal 10 and companion animal information. For example, an expert who operates a veterinary hospital near the location of the guardian terminal 10 may be prioritized, and a specialist according to the type of companion animal is prioritized.

According to an example, a reservation may be made with an expert who presents an opinion selected from the guardian terminal 10 among expert opinions, and access information may be provided through the reserved expert terminal.

6 is a flowchart illustrating a process of providing access information to an expert according to an embodiment of the present invention.

Referring to FIG. 6 , the diagnostic information providing server 50 provides expert opinions to the guardian terminal 10 (S610), and determines whether one of the expert opinions is selected by the guardian (S620).

If selected, information on the specialist (e.g., veterinary hospital information, specialty, etc.) is provided to the guardian's terminal, a visit diagnosis reservation service is provided, and when the reservation is successful, access to AI diagnosis information is provided. The information is provided to the expert's terminal device (for example, a veterinary hospital PC or a corresponding veterinarian terminal) (S630). Hereinafter, for convenience of description, the corresponding specialist is a veterinarian, and accordingly, the provision of access information and reservation information to the veterinarian terminal 30 will be mainly described. According to an example, the diagnostic information providing server 50 performs a security policy that allows access to artificial intelligence diagnostic information using access information on the reservation date and reservation time according to the reservation information. In other words, the veterinarian terminal 30 that has acquired the access information can check the artificial intelligence diagnosis information stored in the diagnosis information providing server 50 using the access information only at the reserved time (30 minutes before or after the reservation time, etc.).

Unlike this, if the expert opinion is not selected, the next access information is set in a form provided by authentication based on the location of the guardian terminal (S640). According to this example, when access to artificial intelligence diagnosis information using access information is requested from any veterinarian terminal 30, the diagnostic information providing server 50 provides information to the veterinarian terminal according to the authentication result using the location of the guardian terminal. Determine whether to provide artificial intelligence diagnostic information. For example, by allowing access using the access information only when it is determined that the location of the veterinarian terminal 30 requesting access using the access information and the current location of the guardian terminal 10 are the same or similar to each other, Only veterinarians at veterinary hospitals are provided with artificial intelligence diagnosis information.

7 is a flowchart illustrating a process of providing access information according to location-based authentication of a guardian terminal according to an embodiment of the present invention.

Referring to FIG. 7 , when a request for AI diagnosis information using access information is received from any veterinarian terminal 30 (S710), AI diagnosis corresponding to the AI diagnosis information corresponding to the access information is performed. The guardian terminal is identified, location information is acquired from the corresponding guardian terminal 10, and authentication is performed (S720). For example, authentication is performed by checking whether the guardian terminal 10 is currently located at a random animal hospital or located at the same location as the veterinarian terminal 30 that performed the request.

It determines whether the location authentication is successful (S730), and if successful, artificial intelligence diagnosis information corresponding to the access information is provided to the veterinarian terminal (30) (S740).

Unlike this, if authentication fails, the failure is processed and connection failure is notified to the veterinarian terminal 30 (S750). At this time, according to an example, the diagnostic information providing server 50 guides the newly generated password to the guardian terminal 10, performs secondary authentication on whether the password is input from the veterinarian terminal 30, and if successful, artificial intelligence Intelligence diagnosis information can also be provided.

In addition, as described above, when a medical appointment is set in advance between the guardian and the veterinarian, diagnosis information is provided using only access information without location-based authentication in the time zone corresponding to the reservation time according to the reservation information, and the guardian is provided at times other than the reservation time. Location-based authentication of the terminal 10 may be performed. Alternatively, authentication may be performed using both the reservation time and the location of the guardian terminal 10 .

The above-described method for providing artificial intelligence diagnosis information for companion animals according to the present invention can be implemented as computer readable code on a computer readable recording medium. Computer-readable recording media includes all types of recording media in which data that can be decoded by a computer system is stored. For example, there may be read only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed to computer systems connected through a computer communication network, and stored and executed as readable codes in a distributed manner.

In addition, although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can make the present invention within the scope not departing from the spirit and scope of the present invention described in the claims below. It will be appreciated that various modifications and variations may be made.

10: Guardian terminal
30: veterinarian terminal
50: Diagnostic information providing server

Claims (10)

In the method of providing artificial intelligence diagnostic information for companion animals performed in a server device,
Receiving companion animal information for diagnosis from a guardian terminal;
Performing artificial intelligence diagnosis by deep learning on the diagnostic information big data for the companion animal information;
storing artificial intelligence diagnosis information according to the artificial intelligence diagnosis and generating access information for accessing the artificial intelligence diagnosis information; and
Providing the artificial intelligence diagnosis information to any veterinarian terminal that has made a request using the access information,
The companion animal information and the artificial intelligence diagnosis information are exposed to a plurality of expert terminals during the waiting time, and the information on expert opinions collected during the waiting time is processed, stored together with the artificial intelligence diagnosis information, and provided to the guardian terminal. but
The expert opinion is analyzed to calculate an accuracy value for the artificial intelligence diagnosis result, and among the information on the expert opinion, information on the expert opinion most similar to and most different from the artificial intelligence diagnosis is prioritized along with the accuracy value. A method of providing artificial intelligence diagnostic information for companion animals that is exposed to the guardian terminal.
delete delete The method of claim 1,
A method of providing artificial intelligence diagnosis information for a companion animal, wherein the expert terminal is selected based on the location of the guardian terminal and the companion animal information.
The method of claim 1,
A method for providing artificial intelligence diagnosis information for companion animals, wherein a service cost for the artificial intelligence diagnosis is determined using the waiting time and the number of expert terminals.
The method of claim 1,
A method of providing artificial intelligence diagnosis information for companion animals, wherein a reservation is made with an expert who has presented an opinion selected from the guardian terminal among the expert opinions, and the access information is provided to the reserved expert terminal.
The method of claim 1,
When access to the artificial intelligence diagnosis information using the access information is requested from the veterinarian terminal, whether to provide the artificial intelligence diagnosis information to the veterinarian terminal is determined according to the authentication result using the location of the guardian terminal. A method for providing artificial intelligence diagnostic information for animals.
A recording medium containing instructions executable by a computer such as an application or program module to be executed by a computer for performing the method of claim 1.
A guardian terminal providing companion animal information for diagnosis;
For the companion animal information, artificial intelligence diagnosis is performed by deep learning on the diagnosis information big data, artificial intelligence diagnosis information according to the artificial intelligence diagnosis is stored, and access information for accessing the artificial intelligence diagnosis information is provided. Artificial intelligence diagnosis server to generate; and
Including a veterinarian terminal for acquiring the artificial intelligence diagnosis information by performing a request to the artificial intelligence diagnosis server using the access information,
The artificial intelligence diagnosis server exposes the companion animal information and the artificial intelligence diagnosis information to a plurality of expert terminals during a waiting time, and processes information on expert opinions collected during the waiting time, together with the artificial intelligence diagnosis information. Save and provide to the guardian terminal,
The expert opinion is analyzed to calculate an accuracy value for the artificial intelligence diagnosis result, and among the information on the expert opinion, information on the expert opinion most similar to and most different from the artificial intelligence diagnosis is prioritized along with the accuracy value. An artificial intelligence diagnosis information providing system for companion animals that is exposed to the guardian terminal.
The method of claim 9,
The artificial intelligence diagnosis server,
The companion animal information and the artificial intelligence diagnosis information are exposed to a plurality of expert terminals during the waiting time, and the information on expert opinions collected during the waiting time is processed, stored together with the artificial intelligence diagnosis information, and provided to the guardian terminal. AI diagnostic information providing system for companion animals.

Images