KR102472583B1 - Artificial intelligence based electronic apparatus for providing diagnosis information on abrasion, control method, and computer program - Google Patents

Abstract

An electronic device is disclosed. The electronic device includes a memory storing an artificial intelligence model trained to provide diagnostic information on abrasion, and a processor connected to the memory. The processor inputs the image to the artificial intelligence model, obtains diagnostic information about the abrasion included in the image, and provides the acquired diagnostic information.

Description

Artificial intelligence model-based electronic device, control method, and computer program that provide diagnostic information on abrasions

The present disclosure relates to an electronic device, and more particularly, to an electronic device that acquires diagnostic information by inputting an image including an abrasion to an artificial intelligence model.

For rapid healing of acute wounds such as abrasions, it is necessary to use suitable dressing formulations required according to the nature of the wound.

However, most of the medical staff in the emergency room do not provide optimized professional treatment for dressing preparations, etc., and in the case of the general public, applying the wrong folk remedy before visiting the emergency room may adversely affect wound healing.

Publication No. 10-2020-0042509 (System and method for skin condition analysis)

The present disclosure provides an electronic device and control method for providing appropriate medical information on abrasions using an artificial intelligence model specially trained for abrasions.

The objects of the present disclosure are not limited to the above-mentioned objects, and other objects and advantages of the present disclosure not mentioned above can be understood by the following description and will be more clearly understood by the embodiments of the present disclosure. Further, it will be readily apparent that the objects and advantages of the present disclosure may be realized by means of the instrumentalities and combinations indicated in the claims.

An electronic device according to an embodiment of the present disclosure includes a memory storing an artificial intelligence model trained to provide diagnosis information on an abrasion, and a processor connected to the memory. The processor inputs an image to the artificial intelligence model, obtains diagnostic information about the abrasion included in the image, and provides the obtained diagnostic information.

The diagnostic information may include information on at least one of abrasion occurrence time, abrasion condition, disinfection method, dressing method, dressing formulation, and prognosis of the abrasion.

The processor obtains environmental information including at least one of temperature, humidity, and weather, inputs the image and the obtained environmental information to the artificial intelligence model, and information about the prognosis of the abrasion included in the image can also be obtained.

The processor, based on the information on the dressing method included in the provided diagnostic information, may identify a replacement cycle of the dressing formulation, and provide at least one notification according to the identified replacement cycle.

Meanwhile, the memory may include a first artificial intelligence model trained to output diagnostic information on the abrasion, and a second artificial intelligence model trained to generate a predictive image related to the prognosis of the abrasion. In this case, the processor inputs the image to the second artificial intelligence model, obtains at least one predicted image for each period related to the prognosis of the abrasion, and transmits the obtained predicted image to the first artificial intelligence model By inputting, it is possible to obtain diagnosis information for each period of the abrasion.

The processor may generate an order form including information on types and quantities of medical items related to medical treatment for abrasions based on a history of providing diagnosis information.

Meanwhile, the processor transmits the input image and the acquired diagnostic information to a plurality of specialist terminals, and receives feedback on the obtained diagnostic information from at least one specialist terminal among the plurality of specialist terminals. In this case, information on the received feedback may be transmitted to the plurality of specialist terminals, an agreement on the feedback may be derived, and the artificial intelligence model may be updated according to the derived agreement.

According to an embodiment of the present disclosure, a control method of an electronic device including an artificial intelligence model trained to provide diagnosis information on abrasions includes inputting an image including an abrasion to the artificial intelligence model, and including the abrasion in the image obtaining diagnostic information about the abrasion, and providing the obtained diagnostic information.

The electronic device and control method according to the present disclosure have an effect of providing precise information on medical treatment and prognosis for abrasions using at least an artificial intelligence model intensively trained for abrasions.

1 is a diagram for schematically explaining input and output of an artificial intelligence model used by an electronic device according to an embodiment of the present disclosure;
2 is a block diagram for explaining the configuration of an electronic device according to an embodiment of the present disclosure;
3 is a flowchart for explaining a control method of an electronic device according to an embodiment of the present disclosure;
4 is a diagram for explaining an operation of using artificial intelligence models trained to output diagnostic information and predictive images, respectively, by an electronic device according to an embodiment of the present disclosure;
5 is a flowchart for explaining an operation of updating an artificial intelligence model by an electronic device according to an embodiment of the present disclosure; and
6 is a block diagram for explaining the configuration of an electronic device according to various embodiments of the present disclosure.

Prior to a detailed description of the present disclosure, the method of describing the present specification and drawings will be described.

First, terms used in the present specification and claims are general terms in consideration of functions in various embodiments of the present disclosure. However, these terms may vary depending on the intention of a technician working in the art, legal or technical interpretation, and the emergence of new technologies. In addition, some terms are arbitrarily selected by the applicant. These terms may be interpreted as the meanings defined in this specification, and if there is no specific term definition, they may be interpreted based on the overall content of this specification and common technical knowledge in the art.

In addition, the same reference numerals or numerals in each drawing attached to this specification indicate parts or components that perform substantially the same function. For convenience of description and understanding, the same reference numerals or symbols are used in different embodiments. That is, even if all components having the same reference numerals are shown in a plurality of drawings, the plurality of drawings do not mean one embodiment.

Also, in the present specification and claims, terms including ordinal numbers such as “first” and “second” may be used to distinguish between elements. These ordinal numbers are used to distinguish the same or similar components from each other, and the meaning of the term should not be construed as being limited due to the use of these ordinal numbers. For example, the order of use or arrangement of elements associated with such ordinal numbers should not be limited by the number. If necessary, each ordinal number may be used interchangeably.

In this specification, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "comprise" or "consist of" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other It should be understood that the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

In the embodiments of the present disclosure, terms such as “module,” “unit,” and “part” are terms used to refer to components that perform at least one function or operation, and these components are hardware or software. It may be implemented or implemented as a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc. are integrated into at least one module or chip, except for cases where each of them needs to be implemented with separate specific hardware, so that at least one processor can be implemented as

Also, in an embodiment of the present disclosure, when a part is said to be connected to another part, this includes not only a direct connection but also an indirect connection through another medium. In addition, the meaning that a certain part includes a certain component means that it may further include other components without excluding other components unless otherwise stated.

1 is a diagram schematically illustrating input and output of an artificial intelligence model used by an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 1 , the electronic device may input an image 1 of a scratch to an artificial intelligence model 10 .

In this case, the artificial intelligence model 10 may output diagnosis information 2 about the abrasion included in the image 1 . The artificial intelligence model 10 may be a model trained using images of abrasions on various body parts as training data.

Referring to FIG. 1 , the diagnostic information 2 may include information about a dressing method and a dressing formulation for the abrasion included in the image 1 .

As such, the electronic device according to the present disclosure can use an artificial intelligence model trained to output diagnostic information when an image of a scratch is input, and the outputted information is useful for medical practice or medical education/training of ordinary people or specialists. can be used

In particular, the accuracy and reliability of the provided information can be guaranteed by using an intensively trained artificial intelligence model specialized only for a relatively limited range of injuries, such as 'abrasion'.

The configuration and operation of the electronic device will be described in more detail through the following drawings.

2 is a block diagram for explaining the configuration of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 2 , the electronic device 100 includes a memory 110 and a processor 120 .

The electronic device 100 may be various terminal devices such as smart phones, desktop PCs, tablet PCs, notebook PCs, wearable devices, VR/AR devices, and PDAs.

Also, the electronic device 100 may be implemented as a server including one or more computers that communicate with at least one terminal device.

The memory 110 is a component for storing an operating system (OS) for controlling overall operations of elements in the electronic device 100, at least one instruction, and data.

The memory 110 may include non-volatile memory such as ROM and flash memory, and may include volatile memory such as DRAM. Also, the memory 110 may include a hard disk, a solid state drive (SSD), and the like.

Referring to FIG. 2 , the memory 110 may include at least one artificial intelligence model 111 trained to provide diagnostic information on abrasions.

The artificial intelligence model 111 may correspond to a network model based on a neural network.

The network model may include a plurality of network nodes having weights. A plurality of network nodes may form a connection relationship based on weights between nodes of different layers.

The artificial intelligence model 111 may be learned through a Deep Neural Network (DNN) method, and may use a Convolutional Neural Network (CNN), a Regional Convolutional Neural Network (RCNN), a Generative Adversarial Network (GAN), etc., but are limited thereto. It is not.

For example, the artificial intelligence model 111 may include at least one convolutional layer for extracting feature information from an image and a plurality of (independent) fully-connected layers for deriving various diagnostic information from the extracted feature information. However, it is not limited thereto.

When at least one image including a scratch is input, the artificial intelligence model 111 may be implemented to recognize a scratch included in the image and output diagnostic information on the recognized scratch. To this end, the artificial intelligence model 111 may include at least one object recognition part for recognizing the abrasion and an extraction part for extracting various diagnostic information from the abrasion, but is not limited thereto.

Diagnosis information on the abrasion may include information on at least one of an abrasion occurrence time, an abrasion state, a disinfection method, a dressing method, a dressing formulation, and a prognosis of the abrasion.

Specifically, the diagnosis information may include information about time that has elapsed since the occurrence of the abrasion.

In addition, the diagnosis information may include information about the area, depth, and severity of the abrasion.

In addition, the diagnosis information may include information on whether or not disinfection of the abrasion is necessary, the type and quantity of disinfectant, disinfection time, and disinfection frequency.

In addition, the diagnostic information may include information on whether a dressing is necessary, a dressing process, a dressing formulation, a dressing cycle, and the like.

In addition, diagnostic information is information about the expected course of the abrasion over time, information on the expected course of the abrasion over time if appropriate medical measures (disinfection, dressing, etc.) are taken, and recovery of the abrasion. It may include information on how long it takes.

The artificial intelligence model 111 may include a classifier model for each item trained to extract appropriate information for each item (time of occurrence of abrasion, condition of abrasion, disinfection method, dressing method, dressing formulation, prognosis of abrasion, etc.) However, it is not limited thereto.

The artificial intelligence model 111 may be a model trained based on diagnostic information matched to at least one image including an abrasion.

Specifically, the artificial intelligence model 111 may be trained by using the abrasion image as training data for input and diagnostic information on the abrasion as training data for output.

The artificial intelligence model 111 may be trained based on a plurality of training data sets each composed of input data including one or more images and output data including diagnostic information.

Here, the diagnostic information used as training data may be various medical data and data obtained from various specialists (ex. specialists).

Training of the artificial intelligence model 111 may be performed through the processor 120 of the electronic device 100 or may be performed in at least one external device.

The processor 120 is a component for overall controlling each component included in the electronic device 100, and various units such as a central processing unit (CPU), an application processor (AP), a graphic processing unit (GPU), a VPU, and an NPU. may consist of

The processor 120 may control the electronic device 100 by executing instructions stored in the memory 110 .

In addition, the processor 120 may provide appropriate diagnosis information on at least one abrasion using the artificial intelligence model 111 stored in the memory 110 .

3 is a flowchart illustrating a control method of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 3 , the processor 120 may obtain diagnosis information on the abrasion included in the image by inputting the image including the abrasion to the artificial intelligence model 111 (S310).

The processor 120 may obtain an image by photographing the abrasion through the camera of the electronic device 100 .

Alternatively, the processor 120 may communicate with at least one external device to receive a scratch image captured through a camera of the at least one external device.

Then, the processor 120 may provide the acquired diagnostic information (S320).

Specifically, the processor 120 may provide diagnostic information through a display or a speaker of the electronic device 100 .

Alternatively, when the electronic device 100 is a server, the processor 120 may communicate with at least one terminal device and provide diagnostic information through a display or speaker of the terminal device.

Meanwhile, the artificial intelligence model 111 may be trained based on at least one image including abrasion and environment information.

That is, the artificial intelligence model 111 may be trained to output diagnostic information (eg, prognosis) differently according to environmental information even when the same abrasion is input. As a result, the abrasion recovery variation according to weather, temperature, humidity, etc. may be reflected in the output.

The environmental information may include information about temperature, humidity, weather, and the like during the abrasion recovery period.

The processor 120 may obtain environmental information from databases of various servers such as the Korea Meteorological Administration or forecast service providers. Alternatively, the processor 120 may obtain environment information by performing a period-by-period search through at least one search engine.

In addition, the processor 120 may obtain information about the prognosis of the abrasion included in the image by inputting the image including the abrasion and environment information to the artificial intelligence model 111 .

Here, the processor 120 converts environmental information including information about temperature, humidity, weather, etc. for each period after the abrasion occurs or when the image including the abrasion is input to the artificial intelligence model (: present) to the artificial intelligence model (111) can be entered.

On the other hand, according to one embodiment, the processor 120 based on the information on the dressing method included in the diagnostic information provided through the artificial intelligence model 111, it is possible to identify the replacement cycle of the dressing formulation.

And, the processor 120 may provide at least one notification according to the identified replacement period. Specifically, the processor 120 may provide a notification every time a replacement period passes from the time point at which diagnosis information is first provided.

As an example, it is assumed that an image including an abrasion is input at 2:00 PM on January 15th. In this case, the processor 120 inputs the image including the abrasion into the artificial intelligence model 111, and diagnostic information including the dressing cycle (ex. Form dressing is required, and gauze is replaced every day for 5 days) required) can be obtained.

And, the processor 120 may provide the acquired diagnostic information.

Here, if the time at which the diagnostic information is provided is 2:01 pm on January 15, the processor 120 will provide a notification requesting replacement of the gauze at 2:01 pm every day from January 16 to 20 can

In this case, the processor 120 may provide a notification through a display and/or a speaker included in the electronic device 100 . Alternatively, the processor 120 may provide a notification through the user terminal by performing communication with at least one user terminal.

On the other hand, the electronic device 100 according to an embodiment of the present disclosure, based on the history of providing diagnosis information as the process of FIG. 3 is performed one or more times, medical items related to medical treatment for abrasions (eg, antiseptic solution) , dressing formulations, etc.) can create an order form containing information on the type and quantity.

Specifically, whenever diagnosis information on abrasions is provided as shown in FIG. 3 , the electronic device 100 provides a medical item (ex. dressing preparation) matched with a medical measure (ex. dressing with form preparation) according to the provided diagnosis information. can identify the type and quantity of Also, the electronic device 100 may create/update an order form based on the type and quantity of the identified medical articles.

For example, when a medical measure such as 'dressing through hydrogel gauze' is suggested according to the diagnosis information, the electronic device 100 may create an order form including hydrogel gauze in an order list.

In this case, the number or quantity of gauze included in the order list may be calculated based on the area of the abrasion included in the abrasion images provided with diagnostic information.

As such, the electronic device 100 according to the present disclosure can automatically build/update an order form to additionally receive medical supplies of the type and quantity used for the medical treatment whenever medical treatment for abrasions is performed, It can contribute to inventory management of medical supplies in hospitals/health institutions.

Meanwhile, according to an embodiment, the memory 110 may each include an artificial intelligence model trained to output diagnostic information on the abrasion and an artificial intelligence model trained to generate a predictive image related to the prognosis of the abrasion.

In this case, the processor 120 may obtain diagnostic information and predictive images, respectively, by inputting an image including the abrasion to each artificial intelligence model.

In this regard, FIG. 4 is a diagram for explaining an operation of using artificial intelligence models trained to output diagnostic information and predictive images, respectively, by an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 4 , model 1 410 may correspond to a Convolutional Neural Network (CNN) model for outputting diagnostic information. Model 1 410 may be a model trained based on a plurality of scratch images and diagnostic information matched to each scratch image.

The electronic device 100 may obtain diagnosis information 402 by inputting the image 401 including the abrasion to the model 1 410 . And, the electronic device 100 may provide diagnostic information 402 .

Here, the diagnosis information 402 is information on medical measures (ex. dressing formulation, dressing method, etc.) for the abrasion included in the image 402 and/or prediction information about the prognosis of the abrasion included in the image 401. can include

Meanwhile, referring to FIG. 4 , model 2 420 corresponds to a generative adversarial network (GAN) for generating at least one predictive image in which the prognosis of an abrasion is reflected.

Model 2 420 can be trained to generate predictive images for the prognosis of future abrasions, whether or not a particular medical action is taken for the abrasion.

To this end, the model 2 420 includes a plurality of images of abrasions on which no medical treatment has been performed for each period (according to the passage of time), and a plurality of images of abrasions on which at least one medical treatment has been performed for each period of time (according to the passage of time). It can be trained based on multiple images.

Model 2 520 may be trained based on feedback between a generator and a discriminator, and may be trained to generate predictive images over time for a specific abrasion image.

As a specific example, weights between nodes in the generator may be updated in a direction of reducing a difference between the predicted image generated through the generator and the actual elapsed image (ex. reading of the discriminator).

However, the model 2 520 generating the predicted image does not necessarily have to be based on GAN, and any type of neural network model configured to output a predicted image when an image of the abrasion is input is of course possible.

Referring to FIG. 4 , the electronic device 100 inputs an image 401 including an abrasion to a model 2 420 and predicts images 401-1, 2, 3) can be obtained. For example, each of the prediction images 401-1, 2, and 3 may indicate a prognosis of a daily interval, but is not limited thereto.

Here, the electronic device 100 may input the prediction images 401-1, 2, and 3 to the model 1 410 to obtain diagnosis information 402-1, 2, and 3 for each period.

That is, the electronic device 100 may provide diagnostic information predicted in the future according to the prognosis of the abrasion together with diagnostic information of the current condition 401 .

In this case, there is an effect that information on the overall treatment expectation process can be comprehensively provided.

Meanwhile, according to an embodiment, the electronic device 100 may provide diagnostic information through a plurality of artificial intelligence models trained for each body part.

In this case, the memory 110 may include a plurality of artificial intelligence models trained for each body part on abrasions. For example, one AI model can be trained to provide diagnostic information for abrasions on the hand, and another AI model can be trained to provide diagnostic information for abrasions on the face.

Here, when an image of an abrasion is input, the electronic device 100 may identify a body part included in the image.

In this case, the electronic device 100 may identify the body part according to at least one user command for selecting the body part.

Alternatively, the electronic device 100 may identify the body part by using at least one artificial intelligence model for object recognition trained to identify the body part included in the image.

In addition, the electronic device 100 may input an image (photographed of the abrasion) to at least one artificial intelligence model matched to the identified body part.

As a specific example, when a body part is identified as a hand, the electronic device 100 may input an image to an artificial intelligence model trained to provide diagnosis information on abrasion on the hand. This artificial intelligence model may be a trained model based on images of abrasions on the hand and diagnosis information on the images.

As such, when separately trained artificial intelligence models for each body part are used, the accuracy of the output of each artificial intelligence model can be further improved. This is because skin characteristics (thickness, moisture, oil, sensitivity, resilience, skin texture, etc.) may differ for each body part, and diagnosis information on abrasions may vary as skin characteristics change.

Meanwhile, according to an embodiment, the processor 120 may update the artificial intelligence model through feedback on diagnostic information (and/or predicted image) output from at least one artificial intelligence model.

5 is a flowchart illustrating an operation of updating an artificial intelligence model by an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 5 , the processor 120 may transmit (abrasion) images input to the artificial intelligence models 111 and 410 and diagnostic information output from the artificial intelligence models to a plurality of specialist terminals (S510). .

Alternatively, the processor 120 may transmit an image input to the artificial intelligence model 420 and a predicted image output from the artificial intelligence model 420 to a plurality of specialized terminals.

Here, the specialist may mean a surgeon, and more specifically, may correspond to a person with extensive experience in treating abrasions, a professor, a researcher, and the like.

The specialist's terminal corresponds to various terminal devices such as a specialist's smart phone and desktop PC.

That is, the judgment result (diagnosis information, predicted image) of the artificial intelligence model may be transmitted to a plurality of specialists.

If feedback is received from at least one specialist (terminal), the processor 120 may transmit information on the received feedback to a plurality of specialist terminals to derive an agreement (S520).

Here, the feedback may include an additional opinion and/or other opinion of the specialist about the judgment result of the artificial intelligence model.

In this case, the feedback may be received separately for each of a plurality of items (eg, timing of occurrence of the abrasion, condition of the abrasion, disinfection method, dressing method, dressing formulation, prognosis of the abrasion, etc.). Also, the feedback may include at least one image of the abrasion (a more suitable predictive image depending on the prognosis of the abrasion).

When information about the feedback is transmitted to a plurality of specialist terminals, the plurality of specialist terminals may transmit information about whether to agree to the feedback to the electronic device 100 .

In this case, the processor 120 may determine whether to accept the feedback based on the number of specialists who agree with the corresponding feedback.

For example, when the number of specialists who agree with the corresponding feedback exceeds a threshold or the ratio of specialists who agree exceeds a threshold ratio, the processor 120 may determine to accept the corresponding feedback.

Alternatively, if there are a certain number (eg, one) or more specialists who do not agree with the corresponding feedback, the processor 120 may determine not to accept the corresponding feedback.

In this case, the processor 120 may transmit information on whether or not the corresponding feedback is accepted to a plurality of specialist terminals.

Then, the processor 120 may update the artificial intelligence models 111, 410, and 420 according to the agreement derived as described above (S530).

Specifically, when it is determined that the feedback is accepted, the processor 120 changes the artificial intelligence model 111, 410 so that the judgment result of the artificial intelligence model 111, 410, 420 (for the same image) is changed according to the feedback. , 420) can be trained.

Here, the processor 120 may change a weight between at least one node of the artificial intelligence models 111, 410, and 420 according to the feedback.

Meanwhile, according to an embodiment, after the diagnostic information is provided, the processor 120 may identify whether the diagnostic information is accepted or not according to a user input. That is, the electronic device 100 may receive input as to whether or not the user (eg, surgeon) has accepted (agreed) the diagnostic information provided by the artificial intelligence model.

Also, the processor 120 may identify the trust scores of the artificial intelligence models 111 and 410 according to the acceptance history of the diagnostic information.

The diagnostic information acceptance history refers to the ratio/frequency/number of times that users who received the diagnostic information output from the artificial intelligence models 111 and 410 accepted or did not accept the diagnostic information.

Here, the acceptance history of diagnosis information may be classified for each body part and stored in the memory 110, but is not limited thereto.

The processor 120 may update the trust scores of the artificial intelligence models 111 and 410 in real time according to the acceptance history (diagnostic information) updated in real time.

In this case, the trust score of the artificial intelligence model 111 or 410 may increase whenever the diagnostic information is accepted, and the trust score of the artificial intelligence model 111 or 410 may decrease whenever the diagnostic information is not accepted. In addition, the higher the acceptance rate of the diagnosis information, the higher the confidence score of the artificial intelligence models 111 and 410 may be. However, it is not limited thereto.

If the confidence score is less than the threshold value, the processor 120 may perform additional training on the artificial intelligence models 111 and 410 .

Specifically, the electronic device 100 may identify the abrasion image input to the artificial intelligence model when diagnostic information that was not accepted is output.

Also, the processor 120 may additionally train the artificial intelligence model 111 based on the identified abrasion image and diagnosis information (feedback) of the specialist on the abrasion.

Here, the processor 120 may obtain feedback by transmitting the diagnostic information that is not accepted to a plurality of specialist terminals (see FIG. 5 ).

Meanwhile, according to an embodiment, the processor 120 may identify the type of wound included in the image, and perform the process according to the embodiment of FIG. 3 only when the identified type of wound is an abrasion. .

Types of wounds may further include lacerations, burns, and the like, in addition to abrasions.

Here, the processor 120 may select a type of wound according to a user input, or may use at least one artificial intelligence model trained to identify the type of wound.

The artificial intelligence model may be at least one classifier model trained to select one of lacerations, burns, and abrasions when an image including a wound is input.

If the type of wound included in the image is a laceration or burn, the processor 120 may provide treatment-related information using at least one other artificial intelligence model trained through the laceration or burn image.

In this way, by using a separate artificial intelligence model or software module for each wound, an artificial intelligence-based medical guide system reflecting the expertise and individuality of medical knowledge can be established.

Meanwhile, FIG. 6 is a block diagram illustrating a configuration of an electronic device according to various embodiments of the present disclosure.

Referring to FIG. 6 , the electronic device 100 includes at least a camera 130, a display 140, a speaker 150, a user input unit 160, and a communication unit 170 in addition to the memory 110 and the processor 120. may contain one more.

The camera 130 is configured to photograph an external environment and may be implemented with various cameras such as an RGB camera, a depth camera, a Time of Flight (TOF) camera, and a stereo camera.

For example, the processor 120 may acquire an image by controlling the camera 130 according to a user command for photographing the abrasion.

The display 140 is a component for displaying various contents or various user interfaces provided through the electronic device 100 .

The display 140 may be implemented as an LED, a liquid crystal display (LCD), a plasma display panel (PDP), an organic light emitting diode (OLED), a transparent OLED (TOLED), a micro LED, or the like, but is not limited thereto. Also, the display 140 may be implemented as a flat panel display, a curved display, a foldable display, a rollable display, and the like.

For example, the processor 120 may control the display 140 to display an image (abrasion) captured through the camera 130, and visually provide diagnostic information obtained according to the image through the display 140. can do.

The speaker 150 is a component for aurally providing various contents or UI provided through the electronic device 100 . However, the electronic device 100 may include a terminal connected to at least one speaker device other than the speaker 150 .

For example, the processor 120 may output a guide voice explaining diagnosis information on the abrasion through the speaker 150 .

The user input unit 160 is a component for receiving a user command or user information. The user input unit 160 may be implemented as a touch sensor, a button, a camera, a microphone, and the like.

A user command for capturing at least one image including the abrasion, a user command for requesting diagnosis information on the abrasion, and the like may be input through the user input unit 160 .

The communication unit 170 is a configuration for the electronic device 100 to communicate with at least one external device and may include a circuit.

The communication unit 170 is TCP/IP (Transmission Control Protocol/Internet Protocol), UDP (User Datagram Protocol), HTTP (Hyper Text Transfer Protocol), HTTPS (Secure Hyper Text Transfer Protocol), FTP (File Transfer Protocol), SFTP ( Various types of information may be transmitted and received with one or more external electronic devices using communication protocols such as Secure File Transfer Protocol (MQTT) and Message Queuing Telemetry Transport (MQTT).

To this end, the communication unit 170 may be connected to an external device based on a network implemented through wired communication and/or wireless communication. In this case, the communication unit 170 may be directly connected to an external device, but may also be connected to an external electronic device through one or more external servers (eg, Internet Service Provider (ISP)) providing a network.

The network may be a Personal Area Network (PAN), a Local Area Network (LAN), a Wide Area Network (WAN), etc., depending on the area or size, and an intranet, It may be an extranet or the Internet.

Wireless communication includes LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), Zigbee, etc. can include

Wired communication may include at least one of communication methods such as Ethernet, optical network, Universal Serial Bus (USB), and Thunderbolt.

Here, the communication unit 170 may include a network interface or network chip according to the wired/wireless communication method described above. On the other hand, the communication method is not limited to the above-described example, and may include a newly appearing communication method according to the development of technology.

For example, when the electronic device 100 is implemented as a server, the electronic device 100 may communicate with at least one user terminal (eg, a smartphone) through the communication unit 170 . Specifically, the electronic device 100 serving as a server may interwork with a user terminal through at least one web page or application.

In this case, the electronic device 100 may receive an image of the abrasion photographed through a camera of the user terminal from the user terminal.

And, the electronic device 100 may acquire diagnostic information by inputting the corresponding image to at least one artificial intelligence model.

At this time, the electronic device 100 may transmit the acquired diagnostic information to the user terminal, and the user terminal may provide the diagnostic information to the user.

Meanwhile, the various embodiments described above may be implemented by combining a plurality of embodiments as long as they do not conflict with each other.

Meanwhile, various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

According to the hardware implementation, the embodiments described in this disclosure are application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable gate arrays (FPGAs). ), processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions.

In some cases, the embodiments described herein may be implemented by a processor itself. According to software implementation, embodiments such as procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules described above may perform one or more functions and operations described herein.

On the other hand, computer instructions or computer programs for performing processing operations in each device in the system according to various embodiments of the present disclosure described above are stored in a non-transitory computer-readable medium. can be stored Computer instructions or computer programs stored in such a non-transitory computer readable medium, when executed by a processor of a specific device, cause the above-described specific device to perform processing operations in the electronic device according to various embodiments described above.

A non-transitory computer readable medium is a medium that stores data semi-permanently and is readable by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. Specific examples of the non-transitory computer readable media may include CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

Although the preferred embodiments of the present disclosure have been shown and described above, the present disclosure is not limited to the specific embodiments described above, and is common in the technical field belonging to the present disclosure without departing from the gist of the present disclosure claimed in the claims. Of course, various modifications and implementations are possible by those with knowledge of, and these modifications should not be individually understood from the technical spirit or perspective of the present disclosure.

Meanwhile, the various embodiments described above may be implemented by combining a plurality of embodiments as long as they do not conflict with each other.

Meanwhile, various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

According to the hardware implementation, the embodiments described in this disclosure are application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable gate arrays (FPGAs). ), processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions.

In some cases, the embodiments described herein may be implemented by a processor itself. According to software implementation, embodiments such as procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules described above may perform one or more functions and operations described herein.

On the other hand, computer instructions or computer programs for performing processing operations in each device in the system according to various embodiments of the present disclosure described above are stored in a non-transitory computer-readable medium. can be stored Computer instructions or computer programs stored in such a non-transitory computer readable medium, when executed by a processor of a specific device, cause the above-described specific device to perform processing operations in the electronic device according to various embodiments described above.

A non-transitory computer readable medium is a medium that stores data semi-permanently and is readable by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. Specific examples of the non-transitory computer readable media may include CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

Although the preferred embodiments of the present disclosure have been shown and described above, the present disclosure is not limited to the specific embodiments described above, and is common in the technical field belonging to the present disclosure without departing from the gist of the present disclosure claimed in the claims. Of course, various modifications and implementations are possible by those with knowledge of, and these modifications should not be individually understood from the technical spirit or perspective of the present disclosure.

100: electronic device 110: memory
120: processor

Claims (9)

In electronic devices,
a memory storing artificial intelligence models trained to provide diagnostic information about abrasions; and
Including; a processor connected to the memory;
the processor,
Inputting an image to the artificial intelligence model to obtain diagnosis information on abrasions included in the image;
providing the obtained diagnostic information;
Identify whether or not the diagnostic information is accepted according to a user input;
Transmitting the input image and the acquired diagnostic information to a plurality of specialist terminals;
When feedback on the obtained diagnostic information is received from at least one specialist terminal among the plurality of specialist terminals, information on the received feedback is transmitted to the plurality of specialist terminals to determine whether or not to agree with the feedback. receive information about
Based on information on whether or not to agree with the feedback, if the number of specialists agreeing with the feedback exceeds a threshold, or the ratio of specialists agreeing with the feedback exceeds a threshold ratio, the artificial intelligence based on the feedback Updating an intelligence model, changing a weight between at least one node of the artificial intelligence model according to the feedback;
Identifying the trust score of the artificial intelligence model according to the acceptance history of the diagnostic information,
If the confidence score is less than the threshold, the image input to the artificial intelligence model at the time the unaccepted diagnostic information was output is identified, and the image input to the artificial intelligence model at the time the unaccepted diagnostic information was output and the acceptance Further training of the artificial intelligence model based on feedback on the image input to the artificial intelligence model at the time when the diagnostic information that was not performed was output,
acceptance history,
The electronic device, characterized in that the ratio, frequency, or number of users who received the diagnostic information output from the artificial intelligence model accepting or not accepting the diagnostic information. According to claim 1,
The diagnostic information,
An electronic device comprising information on at least one of an abrasion occurrence time, an abrasion condition, a disinfection method, a dressing method, a dressing formulation, and a prognosis of the abrasion. According to claim 2,
the processor,
Obtain environmental information including at least one of temperature, humidity, and weather;
The electronic device, wherein information about a prognosis of an abrasion included in the image is obtained by inputting the image and the acquired environment information to the artificial intelligence model. According to claim 1,
the processor,
Based on the information on the dressing method included in the diagnostic information provided above, identifying the replacement cycle of the dressing formulation,
An electronic device that provides at least one notification according to the identified replacement cycle. According to claim 1,
the memory,
a first artificial intelligence model trained to output diagnostic information about abrasions; and
A second artificial intelligence model trained to generate predictive images related to the prognosis of abrasions;
the processor,
Inputting the image to the second artificial intelligence model to obtain at least one predictive image for each period related to the prognosis of the abrasion;
The electronic device that obtains diagnosis information for each time of the abrasion by inputting the obtained predictive image to the first artificial intelligence model. According to claim 1,
the processor,
An electronic device that generates an order form containing information about types and quantities of medical items related to medical treatment for abrasions based on a history of providing diagnostic information. delete delete delete

Images