KR20210122034A - A system for treating skin damage based on artificial intelligence and providing remote medical service - Google Patents

Abstract

The present invention relates to a method for operating a skin damage treatment system, which comprises the steps of: allowing a user terminal to receive an image related to the skin damage to a user; allowing the user terminal to receive information related to the skin damage from the user; allowing the user terminal to transmit the image related to the skin damage and the information related to the skin damage to a service server; allowing the service server to determine a risk level based on the image related to the skin damage and the information related to the skin damage; when the risk level indicates a mild case, allowing the service server to transmit information related to the treatment method to the user terminal; when the risk level indicates the mild case, allowing the service server to transmit the image related to the skin damage, the information related to the skin damage, and the information related to the treatment method to a medical personnel terminal; when the risk level indicates a severe case, allowing the service server to transmit at least one hospital information, selected based on a location of the user included in the information related to skin damage, to the user terminal. The present invention can prevent skin damage from becoming worse.

Description

{A SYSTEM FOR TREATING SKIN DAMAGE BASED ON ARTIFICIAL INTELLIGENCE AND PROVIDING REMOTE MEDICAL SERVICE}

The present disclosure relates to a system for providing skin injury treatment and telemedicine services.

Skin damage may include wounding, dermatitis or dryness. Wound means that the continuity of the skin is broken or a structural defect has occurred due to external or internal factors. Wounds can also include burns in which the skin is damaged by heat. Wounds may also include wounds caused by bedsores. For rapid healing of skin damage, a treatment method according to skin damage should be applied. However, there are cases in which the healing of skin damage is delayed or scars are left because the patient lacks knowledge about skin damage treatment. For example, tincture of iodine or Mercurochrome, which are called red pills, are commonly used to heal skin damage. Tincture of iodine or Mercurochrome is an antibacterial agent that kills bacteria. However, these drugs have a sterilizing effect, but in the process of actually healing any skin damage, they interfere with the epithelial cells or fibroblasts in the regeneration process, thereby slowing the healing process.

In addition, in the case of skin damage, the evaluation method of the depth of damage caused by the skin damage has not been studied much compared to its importance. In addition, the judgment is highly dependent on the subjective judgment by experts. In addition, there is a shortage of skin damage experts worldwide. If the general public underestimates the depth of the initial damage caused by skin damage, without consulting a skin damage expert, the skin damage may worsen, and if the depth of the initial damage is overestimated, it may cause cost increases.

Recently, deep learning has been showing good performance in the image field. A model can be created that can determine the severity of skin damage through machine learning using images related to skin damage and information related to skin damage. Such a machine learning model can determine the severity of skin damage relatively accurately at an early stage. In addition, it is possible to prevent a situation in which the patient spends unnecessary costs or the patient's skin damage is aggravated. In particular, early judgment on the severity of skin damage in medically vulnerable areas such as islands and mountains, schools, and military bases can prevent deterioration of skin damage and prevent unnecessary medical expenses.

The operating method of the skin damage treatment system of the present disclosure includes the steps of: a user terminal receiving an image related to a user's skin damage; a user terminal receiving information related to skin damage from a user; Transmitting the image and skin damage related information to the service server, the service server determining the risk level based on the skin damage related image and skin damage related information, if the risk indicates mild, the service server provides a treatment method Transmitting information related to the user terminal to the user terminal, if the risk is mild, the service server 'transmits the image related to the skin damage, information related to the skin damage, and information related to the treatment method to the medical personnel terminal and the risk is severe indicates, the service server is characterized in that it comprises the step of transmitting at least one hospital information selected based on the user's location included in the information related to the skin damage to the user terminal.

The operating method of the skin damage treatment system of the present disclosure includes the steps of: the service server collects skin damage related information from a plurality of user terminals to generate skin damage occurrence status information; the service server stores skin damage occurrence status information in advance Comprising the step of comparing with the existing skin damage statistical data and the service server generating difference information by comparing the skin damage occurrence status information and skin damage statistical data, the skin damage occurrence status information includes the cause of skin damage over time, It includes at least one of skin damage occurrence site, skin damage occurrence age, skin damage occurrence gender, or skin damage location information, and the pre-stored skin damage statistical data is information on the skin damage occurrence status in the past.

The operating method of the skin damage treatment system of the present disclosure includes the steps of: a service server transmitting skin damage occurrence status information to a pharmacy terminal; is characterized in that it comprises the step of outputting information on the shortage of medicines by comparing the drug demand forecast information and the drug inventory of the pharmacy.

The operating method of the skin damage treatment system of the present disclosure includes the steps of: receiving, by a user terminal, at least one piece of hospital information when the degree of risk indicates severe; transmitting the user's information to the , the hospital server selected based on the user's information transmits prescription information and diagnostic information to the service server, the service server includes images related to skin damage, information related to skin damage, prescription information, and It characterized in that it comprises the step of transmitting the diagnosis information to a plurality of medical care provider terminals, and the service server receiving the prescription information and evaluation information on the diagnosis information from the plurality of medical care person terminals.

The operating method of the skin damage treatment system of the present disclosure includes the steps of: a user terminal periodically acquiring an image of a user's skin damaged area to obtain a plurality of treatment progress images; Transmitting method-related information to a service server, the service server transmitting a plurality of treatment progress images and treatment method-related information to a plurality of medical care personnel terminals, and the service server transmitting the treatment period and treatment method from the plurality of medical personnel terminals It characterized in that it comprises the step of receiving the evaluation information for the related information.

The step of determining the degree of risk of the operating method of the skin damage treatment system of the present disclosure includes, by the service server, determining whether the skin damage cause information included in the skin damage related information is an electric image or an inhalation image, skin damage cause information is an electric burn or inhalation burn, the service server determining the risk to be severe, the service server acquiring the area of the skin damaged area based on the image and skin damage related information, and and when the ratio of the area of the skin damaged area to the reference body surface area corresponding to the age of the patient included in the related information is equal to or greater than a threshold value, the service server determining the risk to be severe.

The operating method of the skin damage treatment system of the present disclosure includes the steps of receiving, by a health care provider terminal receiving an image related to skin damage, information related to skin damage, and information related to a treatment method, evaluation information on information related to a treatment method from a medical person , a step in which the health care provider terminal transmits evaluation information to the service server, the service server calculates a score that is inversely proportional to the time from the time the treatment method-related information is sent to the health care provider terminal to the time it receives the evaluation information from the health care provider terminal. It characterized in that it comprises the step of allocating to.

The operating method of the skin damage treatment system of the present disclosure includes, by a service server, obtaining first difference information between the first evaluation information received from the first medical care provider terminal and the second evaluation information received from the second medical care provider terminal; When the first difference information is greater than a predetermined threshold, the service server transmits, by the service server, an image related to skin damage, information related to skin damage, and information related to a treatment method to a third healthcare provider terminal, and the third healthcare provider terminal receives treatment from the healthcare provider receiving and transmitting third evaluation information about the method-related information to a service server, by the service server, a third of the first evaluation information and the second difference information of the third evaluation information, the second evaluation information, and the third evaluation information obtaining difference information, when the second difference information and the third difference information are less than a threshold value, determining, by the service server, an average of the first evaluation information, the second evaluation information, and the third evaluation information as the final evaluation information , when the second difference information is smaller than the threshold value, and the third difference information is greater than the threshold value, determining, by the service server, an average of the first evaluation information and the third evaluation information as the final evaluation information, and the second difference information greater than the threshold value and when the third difference information is less than the threshold value, the service server determining an average of the second evaluation information and the third evaluation information as the final evaluation information.

The operating method of the skin damage treatment system of the present disclosure includes the steps of, by a user terminal, transmitting drug information and user information included in information related to a treatment method to a service server based on a user's input, wherein the service server includes user information and drug information generating an encrypted authentication code based on the step, the service server transmitting the drug information, the user's information and the authentication code to the pharmacy terminal, the pharmacy terminal sending the authentication code to the delivery man terminal, the delivery man terminal of the medicine Recognizing the drug identifier displayed on the package, the delivery man terminal transmitting the authentication code, the drug identifier, and the delivery person's identifier to the service server, the user terminal recognizing the drug identifier displayed on the package of the drug, the authentication displayed on the delivery man terminal Recognizing the code by the user terminal, and transmitting the recognized authentication code and the recognized drug identifier to the service server by the user terminal.

The step of recognizing the authentication code of the operating method of the skin damage treatment system of the present disclosure by the user terminal includes the steps of: the image acquisition unit of the user terminal photographing the QR code corresponding to the authentication code displayed on the display unit of the delivery man terminal, and the user terminal Comprising the step of obtaining an authentication code based on the photographed image of the QR code, when the service server receives the authentication code and drug identifier from the delivery man terminal, and receives the recognized authentication code and the recognized drug identifier from the user terminal , the service server is characterized in that it generates a signal indicating the termination of the service.

In addition, a program for implementing the operating method of the skin damage treatment system as described above may be recorded in a computer-readable recording medium.

1 is a block diagram illustrating a skin damage treatment system 100 according to an embodiment of the present disclosure.
2 is a block diagram of a service server 210 according to an embodiment of the present disclosure.
3 is a flowchart of a method of operating a skin damage treatment system according to an embodiment of the present disclosure.
4 is a flowchart illustrating an operation of a pharmacy terminal according to an embodiment of the present disclosure.
5 is a flowchart illustrating a process for evaluating a treatment result in a hospital by a skin damage treatment system according to an embodiment of the present disclosure.
6 is a flowchart illustrating an operation of a medical care provider terminal according to an embodiment of the present disclosure.
7 is a flowchart illustrating an operation of a service server according to an embodiment of the present disclosure.
8 is a flowchart illustrating a method of operating a skin damage treatment system according to an embodiment of the present disclosure.
9 illustrates a data learning unit included in a service server according to an embodiment of the present disclosure.
10 illustrates a machine learning model included in a service server according to an embodiment of the present disclosure.

Advantages and features of the disclosed embodiments, and methods of achieving them, will become apparent with reference to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the present disclosure to be complete, and those of ordinary skill in the art to which the present disclosure pertains. It is only provided to fully inform the person of the scope of the invention.

Terms used in this specification will be briefly described, and the disclosed embodiments will be described in detail.

The terms used in this specification are selected as currently widely used general terms as possible while considering the functions in the present disclosure, but may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the terms used in the present disclosure should be defined based on the meaning of the term and the contents of the present disclosure, rather than the name of a simple term.

References in the singular herein include plural expressions unless the context clearly dictates that the singular is singular. Also, the plural expression includes the singular expression unless the context clearly dictates the plural.

When a part "includes" a certain element throughout the specification, this means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

Also, as used herein, the term “unit” refers to a software or hardware component, and “unit” performs certain roles. However, "part" is not meant to be limited to software or hardware. A “unit” may be configured to reside on an addressable storage medium and may be configured to refresh one or more processors. Thus, by way of example, “part” includes components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functionality provided within components and “parts” may be combined into a smaller number of components and “parts” or further divided into additional components and “parts”.

According to an embodiment of the present disclosure, “unit” may be implemented with a processor and a memory. The term “processor” should be interpreted broadly to include general purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, and the like. In some circumstances, a “processor” may refer to an application specific semiconductor (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), or the like. The term "processor" refers to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such configurations. may refer to.

The term “memory” should be interpreted broadly to include any electronic component capable of storing electronic information. The term memory includes random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erase-programmable read-only memory (EPROM), electrical may refer to various types of processor-readable media, such as erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, and the like. A memory is said to be in electronic communication with the processor if the processor is capable of reading information from and/or writing information to the memory. A memory integrated in the processor is in electronic communication with the processor.

Hereinafter, with reference to the accompanying drawings, embodiments will be described in detail so that those of ordinary skill in the art to which the present disclosure pertains can easily implement them. And in order to clearly describe the present disclosure in the drawings, parts irrelevant to the description will be omitted.

1 is a block diagram illustrating a skin damage treatment system 100 according to an embodiment of the present disclosure.

The skin damage treatment system 100 may include a service server 210 , a user terminal 220 , a medical personnel terminal 230 , a pharmacy terminal 240 , a hospital server 250 or a delivery person terminal 260 .

The service server 210 and the hospital server 250 may be cloud servers. The cloud server refers to a server used for cloud computing. Cloud computing is the provision of system resources for virtualized computers over the Internet. Cloud computing is a type of Internet-based computing and refers to a technology that processes information through a server connected to the Internet rather than a user's terminal.

The service server 210 , the user terminal 220 , the medical personnel terminal 230 , the pharmacy terminal 240 , the hospital server 250 or the delivery man terminal 260 may include a processor and a memory. The processor may execute instructions stored in memory.

The service server 210 , the user terminal 220 , the medical personnel terminal 230 , the pharmacy terminal 240 , the hospital server 250 or the delivery person terminal 260 may include a communication unit. The service server 210 , the user terminal 220 , the medical personnel terminal 230 , the pharmacy terminal 240 , the hospital server 250 or the delivery person terminal 260 may communicate with each other through wired/wireless communication to send and receive data.

The service server 210 , the user terminal 220 , the medical personnel terminal 230 , the pharmacy terminal 240 , the hospital server 250 or the delivery man terminal 260 may include an input unit or an output unit. The input unit may receive a user's input. The input unit may include a keyboard, a microphone, a camera, a touchpad, a touch screen, and the like. The service server 210 , the user terminal 220 , the medical personnel terminal 230 , the pharmacy terminal 240 , the hospital server 250 or the delivery man terminal 260 may operate in response to a user's input. In addition, the output unit may include a speaker and a display. The output unit may output the processing result of the processor as an image or sound.

The input unit may receive a user's input. The input unit of the service server 210, the user terminal 220, the medical personnel terminal 230, the pharmacy terminal 240, the hospital server 250, or the delivery person terminal 260 receives an image related to skin damage or information related to skin damage. can be obtained The image related to the skin damage may be an image of the skin damage taken directly by the user using a camera. For example, the image related to skin damage may be an image of at least one of an image, a wound, or a pressure sore taken by a user using a patient application included in the user terminal. In addition, the image related to the skin damage may be image data received by the user by wire or wirelessly from another user terminal. In addition, the image related to the skin damage may be image data already stored in the user terminal.

Information related to skin damage may largely include personal information and medical information. The personal information may include at least one of the patient's age, the patient's skin color, the patient's gender, or the patient's identification information. The patient's identification information may include a name or resident registration number. Personal information may include information of not only the patient but also the patient's guardian. Medical information includes the body part with skin damage corresponding to the image data of the skin damage, the cause of the skin damage, the date of occurrence of the skin damage, the location of the skin damage, the size of the skin damage, the depth of the skin damage, or the It may include at least one of temperature.

The input unit transmits images related to skin damage or information related to skin damage to the service server 210 , the user terminal 220 , the medical personnel terminal 230 , the pharmacy terminal 240 , the hospital server 250 or the delivery person terminal 260 . can send The input unit may compress an image related to skin damage or information related to skin damage based on a predetermined algorithm in order to reduce the amount of data.

The service server 210 may perform machine learning based on data received from the input unit, or may output predictive data based on a machine learning model already machine-learned. The service server 210 may output a machine learning model based on the received skin damage image data or skin damage related information. Also, the service server 210 may apply an image related to skin damage or information related to skin damage to the machine learning model to output predicted information related to skin damage.

The service server 210, the user terminal 220, the medical personnel terminal 230, the pharmacy terminal 240, the hospital server 250, or the delivery person terminal 260 outputs the expected information related to skin damage through a wired or wireless output unit. can be sent to The service server 210, the user terminal 220, the medical personnel terminal 230, the pharmacy terminal 240, the hospital server 250, or the delivery man terminal 260 is a predetermined machine learning model or skin damage treatment prediction information. Compression using an algorithm can reduce the amount of data required for data transmission and increase the speed of transmission.

2 is a block diagram of a service server 210 according to an embodiment of the present disclosure.

Referring to FIG. 2 , the service server 210 according to an embodiment may include a data learning unit 110 and a data recognition unit 120 . The service server 210 as described above may include a processor and a memory.

The data learning unit 110 may receive the first data and the second data to obtain a machine learning model for the relationship between the first data and the second data. The machine learning model obtained by the data learning unit 110 may be a model for generating second data using the first data. For example, the data learning unit 110 may learn a relationship between image data of a plurality of existing skin damage and treatment information on the existing skin damage. When an image of skin damage or basic information about skin damage is given, the data learning unit 110 may generate a machine learning model for predicting treatment information according to skin damage.

The data recognition unit 120 may apply the image data of the current patient's skin damage or information related to the skin damage to the machine learning model to output skin damage treatment prediction information. The machine learning model may be information about the criteria for which treatment should be performed according to the image of the skin damage. In addition, the data recognition unit 120 may use the image data of the skin damage or information related to the skin damage and the result output by the machine learning model to update the machine learning model.

At least one of the data learning unit 110 and the data recognition unit 120 may be manufactured in the form of at least one hardware chip and mounted in an electronic device. For example, at least one of the data learning unit 110 and the data recognition unit 120 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or an existing general-purpose processor (eg, CPU). Alternatively, it may be manufactured as a part of an application processor) or a graphics-only processor (eg, GPU) and mounted on various electronic devices described above.

Also, the data learning unit 110 and the data recognition unit 120 may be respectively mounted in separate electronic devices. For example, one of the data learning unit 110 and the data recognition unit 120 may be included in the electronic device, and the other one may be included in the server. In addition, the data learning unit 110 and the data recognition unit 120 may provide the machine learning model information built by the data learning unit 110 to the data recognition unit 120 through wire or wireless, and recognize data. Data input to the unit 120 may be provided to the data learning unit 110 as additional learning data.

Meanwhile, at least one of the data learning unit 110 and the data recognition unit 120 may be implemented as a software module. When at least one of the data learning unit 110 and the data recognition unit 120 is implemented as a software module (or a program module including instructions), the software module is a memory or computer-readable ratio It may be stored in a non-transitory computer readable media. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

The data learning unit 110 according to an embodiment of the present disclosure includes a data acquisition unit 111 , a preprocessing unit 112 , a training data selection unit 113 , a model learning unit 114 , and a model evaluation unit 115 . may include

The data acquisition unit 111 may acquire data necessary for machine learning. Since a lot of data is required for learning, the data acquisition unit 111 may receive image data of a plurality of existing skin damage or information on skin damage and treatment information on existing skin damage.

The preprocessor 112 may preprocess the obtained data so that the received data can be used for machine learning. The preprocessor 112 may process the acquired data into a preset format so that the model learning unit 114 to be described later can use it. The preprocessor 112 may process the skin damage image data with a filter, so that the outline of the skin damage is clearly revealed. In addition, the preprocessor 112 may adjust at least one of the size, white balance, color, contrast, and saturation of the image data so that the skin damage characteristics are clearly revealed.

The learning data selection unit 113 may select data necessary for learning from the pre-processed data. The selected data may be provided to the model learning unit 114 . The learning data selection unit 113 may select data required for learning from among preprocessed data according to a preset criterion. In addition, the training data selection unit 113 may select data according to a preset criterion by learning by the model learning unit 114 to be described later.

The training data selection unit 113 may pre-classify the image data based on the skin damage information or the pre-trained machine learning model in order to relieve the processing burden of the model learning unit 114 . The learning data selection unit 113 may classify the image data of the existing skin damage according to at least one of a type and a size of the skin damage based on the information on the skin damage. Different treatment methods will be used depending on whether the skin damage is a burn, a cut, or a pressure sore, and the preprocessor 112 may separately classify only the image of the skin damage. Since the model learning unit 114 performs machine learning specialized for skin damage, the processing burden can be reduced.

The model learning unit 114 may learn a criterion regarding which skin damage treatment expected information to be output according to the image data of the existing skin damage. Also, the model learning unit 114 may learn by using a data learning model that outputs treatment prediction information of skin damage according to image data of existing skin damage and information on skin damage as learning data. In this case, the data learning model may be a pre-built model. For example, the data learning model may be a model built in advance by receiving basic learning data (eg, a skin damage image, information on skin damage, or treatment information on skin damage).

The data learning model may be constructed in consideration of the field of application of the learning model, the purpose of learning, or the computer performance of the device. The data learning model may be, for example, a model based on a neural network. For example, models such as Deep Neural Network (DNN), Recurrent Neural Network (RNN), Long Short-Term Memory models (LSTM), BRDNN (Bidirectional Recurrent Deep Neural Network), Convolutional Neural Networks (CNN) will be used as data learning models. However, the present invention is not limited thereto.

According to various embodiments, when there are a plurality of data learning models built in advance, the model learning unit 114 may determine a data learning model having a high correlation between the input learning data and the basic learning data as the data learning model to be learned. have. In this case, the basic learning data may be pre-classified for each type of data, and the data learning model may be previously built for each type of data. For example, the basic training data may be pre-classified according to various criteria such as a place where the training data is generated, a time when the training data is generated, the size of the training data, a generator of the training data, and the type of object in the training data.

Also, the model learning unit 114 may train the data learning model using, for example, a learning algorithm including error back-propagation or gradient descent.

Also, the model learning unit 114 may learn the data learning model through supervised learning using, for example, learning data as an input value. In addition, the model learning unit 114 learns data through unsupervised learning, for example, discovering a criterion for situation determination by self-learning the type of data required for situation determination without any guidance. model can be trained. Also, the model learning unit 114 may learn the data learning model through, for example, reinforcement learning using feedback on whether a result of situation determination according to learning is correct.

In addition, when the data learning model is learned, the model learning unit 114 may store the learned data learning model. In this case, the model learning unit 114 may store the learned data learning model in the memory of the electronic device including the data recognition unit 120 . Alternatively, the model learning unit 114 may store the learned data learning model in a memory of a server connected to the electronic device through a wired or wireless network.

The memory in which the learned data learning model is stored may also store, for example, commands or data related to at least one other component of the electronic device. The memory may also store software and/or programs. Software and/or programs may include, for example, a kernel, middleware, application programming interfaces (APIs) and/or application programs (or “applications”), and the like.

The model evaluation unit 115 inputs evaluation data to the data learning model, and when a result output from the evaluation data does not satisfy a predetermined criterion, the model evaluation unit 114 may allow the model learning unit 114 to learn again. In this case, the evaluation data may be preset data for evaluating the data learning model.

For example, the model evaluation unit 115, among the results of the learned data learning model for the evaluation data, does not satisfy a predetermined criterion when the number or ratio of evaluation data for which the recognition result is not accurate exceeds a preset threshold. can be evaluated as For example, when the predetermined criterion is defined as a ratio of 2%, when the learned data learning model outputs an erroneous recognition result for more than 20 evaluation data out of a total of 1000 evaluation data, the model evaluation unit 115 learns It can be evaluated that the data learning model is not suitable.

On the other hand, when there are a plurality of learned data learning models, the model evaluation unit 115 evaluates whether a predetermined criterion is satisfied for each learned machine learning model, and uses the model that satisfies the predetermined criterion as a final data learning model. can decide In this case, when there are a plurality of models satisfying the predetermined criteria, the model evaluator 115 may determine any one or a predetermined number of models preset in the order of the highest evaluation score as the final data learning model.

Meanwhile, at least one of the data acquisition unit 111 , the preprocessor 112 , the training data selection unit 113 , the model learning unit 114 , and the model evaluation unit 115 in the data learning unit 110 is at least one may be manufactured in the form of a hardware chip of For example, at least one of the data acquisition unit 111 , the preprocessor 112 , the training data selection unit 113 , the model learning unit 114 , and the model evaluation unit 115 is artificial intelligence (AI). It may be manufactured in the form of a dedicated hardware chip for this purpose, or it may be manufactured as a part of an existing general-purpose processor (eg, CPU or application processor) or graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

In addition, the data acquisition unit 111 , the preprocessor 112 , the training data selection unit 113 , the model learning unit 114 , and the model evaluation unit 115 may be mounted in one electronic device, or separate Each of the electronic devices may be mounted. For example, some of the data acquisition unit 111 , the preprocessor 112 , the training data selection unit 113 , the model learning unit 114 , and the model evaluation unit 115 are included in the electronic device, and the rest are It can be included in the server.

In addition, at least one of the data acquisition unit 111 , the preprocessor 112 , the training data selection unit 113 , the model learning unit 114 , and the model evaluation unit 115 may be implemented as a software module. A program in which at least one of the data acquisition unit 111, the preprocessor 112, the learning data selection unit 113, the model learning unit 114, and the model evaluation unit 115 includes a software module (or instructions) module), the software module may be stored in a computer-readable non-transitory computer readable medium. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

The data recognition unit 120 according to an embodiment of the present disclosure includes a data acquisition unit 121 , a preprocessing unit 122 , a recognition data selection unit 123 , a recognition result providing unit 124 , and a model update unit 125 . may include.

The data acquisition unit 121 may acquire skin damage image data of the current patient or information related to the skin damage of the current patient. The preprocessor 122 may preprocess the acquired data so that the acquired skin damage image data of the current patient and information related to the skin damage of the current patient can be used. For example, the preprocessor 122 may process the skin damage image data with a filter to make the outline of the skin damage clearly visible. Also, the preprocessor 122 may adjust at least one of white balance, color, contrast, or saturation of the skin damage image data.

The recognition data selection unit 123 may select necessary data from the pre-processed data. The selected data may be provided to the recognition result providing unit 124 . The recognition data selection unit 123 may select some or all of the preprocessed data according to a preset criterion. Also, the recognition data selection unit 123 may select data according to a preset criterion by learning by the model learning unit 114 .

The recognition result providing unit 124 may obtain result data by applying the selected data to the data learning model. The recognition result providing unit 124 may output the result data as voice or text. The recognition result providing unit 124 may apply the selected data to the data learning model by using the data selected by the recognition data selecting unit 123 as an input value. Also, the recognition result may be determined by a data learning model.

The model updating unit 125 may update the data learning model based on the evaluation of the recognition result provided by the recognition result providing unit 124 . For example, the model update unit 125 may provide the model learning unit 114 with the recognition result provided by the recognition result providing unit 124 so that the model learning unit 114 updates the data learning model. have.

Meanwhile, at least one of the data acquisition unit 121 , the preprocessor 122 , the recognition data selection unit 123 , the recognition result providing unit 124 , and the model update unit 125 in the data recognition unit 120 is at least It may be manufactured in the form of a single hardware chip and mounted in an electronic device. For example, at least one of the data acquisition unit 121 , the preprocessor 122 , the recognition data selection unit 123 , the recognition result providing unit 124 , and the model update unit 125 is artificial intelligence (AI). ), or may be manufactured as a part of an existing general-purpose processor (eg, CPU or application processor) or graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

In addition, the data acquisition unit 121 , the preprocessor 122 , the recognition data selection unit 123 , the recognition result providing unit 124 , and the model update unit 125 may be mounted in one electronic device or separately. It may be mounted on each of the electronic devices of For example, some of the data acquiring unit 121 , the preprocessing unit 122 , the recognition data selection unit 123 , the recognition result providing unit 124 , and the model updating unit 125 are included in the electronic device, and the remaining parts are included in the electronic device. may be included in the server.

In addition, at least one of the data acquisition unit 121 , the preprocessor 122 , the recognition data selection unit 123 , the recognition result providing unit 124 , and the model update unit 125 may be implemented as a software module. At least one of the data acquisition unit 121, the preprocessor 122, the recognition data selection unit 123, the recognition result providing unit 124, and the model update unit 125 includes a software module (or instructions) When implemented as a program module), the software module may be stored in a computer-readable non-transitory computer readable medium. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

3 is a flowchart illustrating a method of operating a skin damage treatment system according to an embodiment of the present disclosure.

The user terminal 200 may include a processor and a memory. The memory may store software or a program. Software or programs may include a kernel, middleware, application programming interfaces (APIs) and/or application programs (or "applications").

The user terminal 220 may perform step 241 of receiving an image related to the user's skin damage. The user terminal 220 may include a camera for capturing an image. The user terminal 220 may display the shooting procedure on the display or output a sound to the user based on a command of the software. The user may operate the user terminal 220 according to the photographing procedure. The user terminal 220 may acquire an image related to skin damage by using a camera. In addition, the user terminal 220 may acquire an image related to the skin damage stored in the memory. In addition, the user terminal 220 may receive an image related to skin damage from an external device by wire or wireless. The image related to the skin damage may include a moving image or a still image.

When the user terminal 220 or the service server 210 uses a video, the skin damaged area may be obtained three-dimensionally. A still image includes an image of a planar skin injury, but a moving image may include an image of the skin injury taken from various angles. The user terminal 220 or the service server 210 may accurately obtain the area of skin damage by applying a predetermined algorithm to the video.

The user terminal 220 may perform step 242 of receiving information related to skin damage from the user. The user terminal 220 may display a screen for obtaining information related to skin damage to the user on the display or output a sound based on a command of the software. The user may input information into the user terminal 220 . The information related to skin damage may include information related to an environment in which skin damage to the patient has occurred. Information related to skin damage includes the part of the body with skin damage corresponding to the image data of the skin damage, the cause of the skin damage, the date of occurrence of the skin damage, the location of the skin damage, the size of the skin damage, the age of the patient, the patient's It may include at least one of skin color or patient's gender.

The user terminal 220 may include an input unit. The user terminal 220 may receive information related to skin damage by using the input unit. However, the present invention is not limited thereto, and the user terminal 220 may acquire information related to skin damage already stored in the memory.

The user terminal 220 may automatically acquire the location of the damaged skin included in the information related to the skin damage without a user input by using a sensor that can know the location of the user terminal 220, such as GPS or GLONASS.

In addition, the user terminal 220 may automatically acquire information on the skin color of the patient to be included in the information related to the skin damage based on the image related to the skin damage.

In addition, the user terminal 220 may receive information related to skin damage from an external device by wire or wireless.

The user terminal 220 may perform step 243 of transmitting an image related to skin damage and information related to skin damage to the service server 210 . The user terminal 220 and the service server 210 may communicate with each other by wire or wireless.

The service server 210 may check whether the image related to the skin damage is recent. For example, the service server 210 may check whether the date the image related to the skin damage was taken is a picture taken within a predetermined time. The predetermined time may be about 30 minutes to 1 hour. The service server 210 may transmit a signal requesting the user terminal 220 to take an image again when a predetermined time has elapsed after the image related to the skin damage was taken. The service server 210 may provide treatment information for skin damage more accurately by using a recent image.

The service server 210 may perform the step 244 of determining the degree of risk based on the image related to the skin damage and the information related to the skin damage. The information on the degree of risk may be one selected from the presence of risk or no risk. Information on the level of risk may be one selected from 'severe' or 'mild'. However, the present invention is not limited thereto, and information on the degree of risk may be expressed as an integer or a real number. For example, a higher number may mean a higher risk and a lower number may mean a lower risk. The service server 210 may include a predetermined threshold value. When the information on the risk is greater than or equal to the threshold, the service server 210 may determine the risk as 'severe'. Also, when the information on the risk is smaller than the threshold, the service server 210 may determine the risk as 'mild'.

The service server 210 may determine the degree of risk using a rule base or machine learning. First, a method for the service server 210 to determine the degree of risk based on the rule base will be described.

In order to determine the degree of risk, the service server 210 may perform a step of determining whether the skin damage cause information included in the skin damage related information is an electric image or an inhalation image. When the skin damage cause information is an electric image or an inhalation image, the service server 210 may perform a step of determining the degree of risk as severe.

Electric burns are part of a blitz injury. Electrical burns have significantly different symptoms from burns caused by scalding, and may require time to heal. In general, electric burns include skin lacerations caused by high heat of several thousand degrees from arcs or sparks, and skin damage caused by Joule heat based on internal tissue resistance when electric current flows through the human body. In addition, various causes included in electric burns overlap, so electric burns can have complex symptoms.

The thermal image included in the electrical image is different from the general thermal image. For example, high-temperature metal is liquefied or gasified and adheres to or permeates the surface of the skin, so the skin surface with lacerations is often blue. In addition, in burns caused by Joule heat, proteins coagulate due to Joule heat, which can cause tissue necrosis in the skin, tendons, periosteum, and bone joints.

Inhalation burns are cases of inhalation of high-temperature heat during a fire in an enclosed space or damage caused by inhalation of carbon dioxide or combustion materials. In addition to skin burns caused by heat, damage caused by inhalation burns can have a fatal effect on the human body and increase the mortality rate. In general, inhalation burns can be a major cause of death due to fire.

In the case of inhalation burns, the human body may be damaged by various harmful chemicals generated from burning materials. In particular, inhalation burns show symptoms of pulmonary edema due to constriction of the bronchi, damage to the ciliary function of the mucous membrane, and necrosis of alveolar cells, and there is a risk of secondary infection. Inhalation burns are divided into upper and lower airway inhalation burns. Because the upper airway has a rich vascular distribution and a large surface area, acute damage occurs easily when the outside air is hot, but heat damage is rare in the lower airway. In addition, if heat damage is applied to the upper airway, immediate edema of the pharynx and larynx may be induced, resulting in rapid airway obstruction.

As already described, information related to skin damage may include skin damage cause information. The service server 210 may determine whether the patient has an electric burn or an inhalation burn based on the skin damage cause information.

However, the present invention is not limited thereto. The service server 210 may determine whether an electric burn or a suction burn is received based on the image related to the skin damage. For example, when vaporized metal permeates into the damaged skin and gives a blue color, the service server 210 may determine that the user has received an electric burn.

In addition, the service server 210 may determine whether an electric burn or a suction burn is received based on information related to skin damage rather than skin damage cause information. For example, information related to skin damage may include weather information and location information of a patient. The service server 210 may determine that the user has received an electric burn when it is not raining at the patient's location. In addition, the service server 210 may determine that the user has suffered a suction burn when located in an enclosed space such as a theater or subway.

The service server 210 may perform the step of acquiring the area of the skin damaged area based on at least one of an image related to skin damage and information related to skin damage. The service server 210 may acquire at least one of the age of the patient, the body part where the skin damage has occurred, the height of the patient, or the weight of the patient based on the information related to the skin damage. The service server 210 may approximate the area of the skin damage based on information included in the information related to the skin damage.

The service server 210 may acquire the area of the skin damage based on information on the body part where the skin damage has occurred. For example, the user terminal 220 may display the outline of the front and back of the person on the display. The user may touch the damaged skin area. The user terminal 220 may display the part touched by the user in a color different from the background color. The user may modify, delete, or add the touch portion displayed on the display unit so that the actual skin damaged portion and the touch portion displayed in a different color match while checking the touch portion displayed on the display unit. The user terminal 220 may determine the area of the skin damaged area drawn on the display as information about the skin damaged body part based on the user's input. The user terminal 220 may transmit information on a body part with skin damage drawn on the outlines of the front and back surfaces of the person to the service server 210 . The service server 210 may obtain the area of the skin damage based on the information on the body part where the skin damage has occurred.

The user terminal 220 or the service server 210 may more accurately obtain the area of the skin damage based on at least one of the patient's age, the patient's height, or the patient's weight included in the skin damage related information. For example, the user terminal 220 or the service server 210 may enlarge or reduce the outlines of the front and back surfaces of the person based on at least one of the patient's age, the patient's height, or the patient's weight.

Specifically, if the patient's weight exceeds the standard, the user terminal 220 or the service server 210 may extend the outline left and right. Conversely, if the weight of the patient is less than the standard, the user terminal 220 or the service server 210 may reduce the outline left and right. Accordingly, the user terminal 220 or the service server 210 may make the outline corresponding to the user's weight. In addition, if the height of the patient is smaller than the standard, the user terminal 220 or the service server 210 may reduce the outline in an up and down direction. In addition, if the height of the patient is greater than the standard, the user terminal 220 or the service server 210 may extend the outline in an up and down direction. Accordingly, the user terminal 220 or the service server 210 may make the outline correspond to the user's key.

In addition, as the contours of the front and back of the person are enlarged or reduced, the user terminal 220 or the service server 210 may also enlarge or reduce the information on the body part with the skin damage input by the user. That is, since the contours of the front and back surfaces of the person may correspond to the actual size of the person, the information on the body part where the skin damage has occurred may also correspond to the size of the actual skin damaged part. The service server 210 may determine the area of the skin damage based on the information on the enlarged or reduced skin damage on the body part. For example, the service server 210 is based on the ratio of the skin damage area to the skin area of the actual person and the ratio of the information on the body part with the enlarged or reduced skin damage to the area inside the outline of the front and back of the person. Based on the skin damage area can be determined.

The user terminal 220 may acquire information on the body part where the skin damage has occurred based on the user's input. Information on the body part where the skin damage has occurred may be subdivided such as neck, elbow, finger, calf, thigh, foot, knee, and the like. The user can select a body part where the skin damage has occurred. Each body part may have an identification code. The user terminal 220 may transmit the identification code of the selected body part to the service server 210 as information on the body part where the skin damage has occurred. The service server 210 may acquire the area of skin damage based on the identification code of the selected body part with skin damage. The service server 210 may further use the patient's age, height, and weight information to obtain the area of skin damage. For example, the service server 210 may statistically obtain the body surface area of the patient's age, height, and weight. The service server 210 may calculate the area of skin damage to be larger as the body surface area is larger, and may calculate the area of skin damage to be smaller as the body surface area is smaller.

Also, the service server 210 may determine the area of the skin damage based on the image related to the skin damage. For example, the service server 210 may recognize which part of the patient's body part the image related to the skin damage is taken based on the image recognition technology. The service server 210 may obtain the actual area of the skin included in the image related to the skin damage based on the recognized body part. In order to obtain the actual area of the skin included in the image related to skin damage, the service server 210 may further use the patient's age, height, and weight information. For example, the service server 210 may statistically obtain the body surface area of the patient's age, height, and weight. The service server 210 may calculate a larger actual area as the body surface area is larger, and may calculate a smaller actual area as the body surface area is smaller.

In addition, the service server 210 may acquire a skin area in which the color is changed due to skin damage and a skin area in which the color is not changed due to skin damage among the images related to skin damage. The service server 210 may acquire the area of the damaged skin area based on the actual area of the skin, the skin area in which the color is changed, and the skin area in which the color does not change.

In addition, the service server 210 may acquire a skin area with a non-uniform surface due to skin damage and an area with a uniform surface without skin damage. The service server 210 may acquire the area of the damaged skin area based on the actual area of the skin shown in the image, the skin area with a non-uniform surface, and the skin area with a uniform surface. For example, the area of the skin damage site may be "(skin area with non-uniform surface) / (skin area with non-uniform surface + skin area with uniform surface) actual area of skin shown in the X-image".

The service server 210 may obtain a statistical body surface area based on at least one of the patient's age, height, and weight. Body surface area refers to the area of a person's skin. When the ratio of the area of the skin damaged area to the reference body surface area corresponding to at least one of the patient's age, height, and weight included in the skin damage related information is greater than or equal to the threshold value, the service server 210 determines the risk to be severe. steps can be performed. The threshold may be a predetermined value. For example, the threshold may mean 10%. That is, when 10% or more of the human skin is damaged, the service server 210 may determine the risk to be severe.

The service server 210 may acquire the face temperature based on at least one of an image related to skin damage or information related to skin damage. Here, the face temperature may mean the temperature of the patient's damaged skin. For example, the image related to skin damage may be an image of an infrared camera or a thermal imaging camera. An image related to skin damage may be displayed in a different color depending on the skin temperature. Accordingly, the service server 210 may acquire the color of the damaged skin region and acquire the face temperature corresponding to the color.

In addition, the image related to the skin damage obtained by the infrared camera or the thermal imaging camera may include a temperature value of a specific location of the skin. For example, an image related to skin damage may include temperature values of a central point, a point having the highest temperature, or a point having the lowest temperature. The temperature value may be stored in a header of an image related to skin damage or metadata of an image related to skin damage. The service server 210 may obtain a temperature value obtained from an image related to skin damage as a face temperature.

The service server 210 may determine whether the face temperature is equal to or greater than a threshold value. Also, the service server 210 may determine the risk to be severe when the face temperature is greater than or equal to the threshold.

In addition, information related to skin damage may include body temperature. The face temperature may be a value input by the user. The service server 210 may acquire the face temperature from information related to skin damage. The service server 210 may determine whether the face temperature is equal to or greater than a threshold value. Also, the service server 210 may determine the risk to be severe when the face temperature is greater than or equal to the threshold.

Also, the service server 210 may acquire the depth of the skin damage based on at least one of information related to the skin damage. The information related to the skin damage may include the depth of the skin damage. The skin damage depth may be a value input by the user. The service server 210 may determine whether the skin damage depth is equal to or greater than a threshold value. In addition, when the depth of skin damage is greater than or equal to a threshold value, the service server 210 may determine the risk to be severe.

The service server 210 may determine whether the condition is severe based on the machine learning model. A configuration for determining whether the condition is severe based on the machine learning model will be described with reference to FIGS. 9 and 10 .

9 illustrates a data learning unit 910 included in a service server according to an embodiment of the present disclosure. Also, FIG. 10 shows a machine learning model included in the service server according to an embodiment of the present disclosure.

Referring to FIG. 9 , the service server 210 may include a data learning unit 910 . The service server 210 may acquire information related to skin damage and an image 921 related to skin damage. The service server 210 may acquire information related to skin damage and an image 921 related to skin damage from a plurality of users. The accuracy of the machine learning model may increase as the number of images 921 related to skin damage and information related to skin damage from a plurality of users increases.

Also, the service server 210 may acquire information related to skin damage and risk information 922 corresponding to an image 921 related to skin damage. The risk information 922 may be a ground truth value. The risk information 922 may be a label evaluated by a medical practitioner based on information related to skin damage and an image 921 related to skin damage. The information about the risk may include risky or no risk. Information on risk may include 'severe' or 'mild'. However, the present invention is not limited thereto, and information on the degree of risk may be expressed as an integer or a real number. For example, a higher number may mean a higher risk and a lower number may mean a lower risk.

The service server 210 may acquire the machine learning model 931 by machine learning the information related to the skin damage and the correlation between the image 921 and the risk information 922 related to the skin damage. The service server 210 may store the machine learning model 931 in a memory.

Referring to FIG. 10 , the service server 210 may include a machine learning model 931 . The service server 210 may acquire information related to new skin damage and an image 1020 related to skin damage. Information related to new skin damage and risk information corresponding to the image 1020 related to skin damage may not be labeled. The service server 210 may acquire the predicted risk information 1030 by applying the machine learning model 931 to the new skin damage related information and the skin damage related image 1020 . The predicted risk information 1030 is not information labeled by a healthcare provider, but may be similar to risk information labeled by a healthcare provider. The service server 210 may perform step 251 , step 252 , or step 261 of FIG. 3 based on the predicted risk information 1030 .

So far, the service server 210 has described a method for determining the degree of risk as severe. Although some embodiments have been described above, the service server 210 may determine the risk to be severe in various ways based on an image related to skin damage and information related to skin damage. The service server 210 may determine a case where the risk is not severe as mild.

Referring back to FIG. 3 , when the risk is mild, the service server 210 may perform an operation 251 of transmitting information related to the treatment method to the user terminal 220 . The information related to the treatment method may include at least one of medicines for treating skin damage, medical devices, precautions for treatment, or treatment order. The service server 210 may store information related to a treatment method in a database. The service server 210 may derive information related to a treatment method and transmit it to the user terminal 220 .

The medical care provider terminal 230 may perform step 245 of transmitting information related to the treatment method to the service server 210 . The medical personnel terminal 230 may transmit prescription, medical practitioner opinion, and diagnosis information to the service server 210 in addition to information related to a treatment method. Prescription, medical opinion, or diagnosis information is information determined by a medical practitioner after checking the patient's status information, and may include a disease name, medicine for treatment, medical device for treatment, or disease code.

The service server 210 may receive the treatment method related information from the healthcare provider terminal 230 before transmitting the treatment method related information to the user terminal 220 . The remote medical practitioner may inform the user of the treatment method in real time through the service server 210 . The user terminal 220 may request a connection to the medical care provider terminal 230 connectable through the service server 210 . When the healthcare provider terminal 230 approves the request, the healthcare provider terminal 230 may transmit a real-time image or voice of the healthcare provider to the service server 210 . The service server 210 may transmit a real-time image or voice of a medical practitioner to the user terminal 220 . The user terminal 220 may output a real-time image or voice of a medical person. The real-time image or voice of the medical personnel may include at least one of information on a treatment method for skin damage or information on a point to be noted during treatment. The user may perform treatment while seeing and hearing the treatment method of a remote medical practitioner output on the user terminal 220 .

In addition, the user terminal 220 may output a still image or a video related to the treatment method. The user may perform treatment while viewing and listening to a still image or a moving image output to the user terminal 220 .

The service server 210 may further use information related to skin damage in order to provide a treatment method suitable for skin damage. The service server 210 may acquire information related to a treatment method based on information related to skin damage from the database. For example, the service server 210 may store information related to a treatment method corresponding to the information on the cause of the skin damage. The service server 210 may acquire information related to a treatment method based on information related to the cause of skin damage from the database.

When the risk is mild, the service server 210 may perform an operation 252 of transmitting an image related to skin damage, information related to skin damage, and information related to a treatment method to the medical care provider terminal 230 . The service server 210 may transmit the automatically generated treatment method related information to the medical care provider terminal 230 to receive the automatically generated treatment method related information from the healthcare provider. A method for the medical care provider terminal 230 to evaluate the automatically generated information related to the treatment method will be described in detail with reference to FIG. 6 .

When the risk indicates severe, the service server 210 may perform a step 261 of transmitting at least one hospital information selected based on the user's location included in the information related to skin damage to the user terminal 220 . have. The service server 210 may select at least one hospital within a threshold distance from the user's location. Here, the threshold distance may be a predetermined distance. Also, the service server 210 may select at least one hospital with few patients from among hospitals within a threshold distance from the user's location. Specifically, the service server 210 may select at least one hospital with few patients by collecting information on the number of reservations in the hospital in real time. Alternatively, the service server 210 may accumulate and store time information paid by patients at the hospital. The service server 210 may predict the time the patient gathers for each hospital based on the paid time information. The service server 210 may determine whether the current time is a time when patients are flocking to the hospital. The service server 210 may select a hospital that is not crowded with patients at the current time. The service server 210 according to the present disclosure can prevent a situation in which a user arrives at a hospital but cannot receive treatment because there are many people in the hospital.

Also, the user terminal 220 may display at least one hospital information received from the service server 210 . The user may visit one hospital by selecting one of the hospitals displayed on the user terminal 220 . The user terminal 220 may display the address or phone number of the hospital. In addition, the user terminal 220 may provide a vehicle reservation service that allows the user to quickly move to the hospital when the user does not have a means of transportation.

The service server 210 may collect information related to skin damage from a plurality of user terminals to generate skin damage occurrence status information. The skin damage occurrence status information may include at least one of a cause of skin damage according to a region, a skin damage occurrence site according to a region, an age at which skin damage occurs according to a region, or a location where a skin damage occurs according to a region. Here, the region may be a unit of a country, a province, a city, a county, a myeon, or an eup. In addition, the location of the skin damage may include a house, office, school, restaurant or mountain. More specifically, the place of occurrence of skin damage may include an industry classification such as education service industry, construction industry, mining, agriculture, fishery industry, fishery, professional scientific service industry, and the like.

In addition, the skin damage occurrence status information may include at least one of a cause of skin damage over time, a site of skin damage over time, an age at which skin damage occurs over time, or a location where skin damage occurs over time. Here, the time may be in units of hours, days, weeks, months, quarters, and years.

According to the data of the Korea Centers for Disease Control and Prevention on May 15, 2019, "there is no comprehensive domestic statistical data on the occurrence of skin damage." Since there is no comprehensive domestic statistical data on the occurrence of skin damage, it may be difficult for national institutions or individuals to realize the risk of skin damage. The service server 210 collects information related to skin damage from a plurality of users and generates skin damage occurrence status information, so it can serve as overall domestic statistical data on the skin damage occurrence status. In addition, national institutions can prepare countermeasures for skin damage, and individuals can prepare for skin damage.

The service server 210 may perform a step of comparing the skin damage occurrence status information with pre-stored skin damage statistical data. The pre-stored skin damage statistical data may be information on the skin damage occurrence status in the past. The service server 210 may determine the specific details of the skin damage issuance status information by comparing the recent skin damage occurrence status information and the past skin damage statistical data.

The service server 210 may perform a step of generating difference information by comparing the skin damage occurrence status information and skin damage statistical data. The difference information may indicate specific details of the recent skin damage occurrence status information. The service server 210 may transmit the difference information to a media agency server, a government agency server, a hospital server, a pharmacy server, a corporate server, or a user terminal. By sharing the difference information, the service server 210 may induce a national agency to analyze the reason for the difference information. In addition, government agencies, hospitals, etc., the service server 210 may prepare countermeasures to lower the incidence of skin damage based on the difference information. In addition, companies or pharmacies can quickly prepare medicines to respond to discrepancy information. It can also lower the incidence of skin damage by raising individual awareness. In addition, the media agency server may distribute information related to a prevention method or a first aid method to the public based on the difference information so that damage caused by skin damage can be minimized.

4 is a flowchart illustrating an operation of a pharmacy terminal according to an embodiment of the present disclosure.

Also, the service server 210 may perform a step of transmitting skin damage occurrence status information to the pharmacy terminal 240 . However, if not limited thereto, the service server 210 may transmit the difference information to the pharmacy terminal 240 instead of the skin damage occurrence status information. The pharmacy terminal 240 may perform step 310 of receiving skin damage occurrence status information or difference information.

The pharmacy terminal 240 may perform the step 320 of generating drug demand forecast information based on the skin damage occurrence status information. For example, if the number of skin damage caused by hot water in the area where the pharmacy terminal 240 is located among the causes of skin damage according to the region is higher than in other areas, the pharmacy terminal 240 is effective for skin damage caused by water. It can be predicted that the demand for pharmaceuticals or medical devices will be high. By way of example, the pharmacy terminal 240 has been described focusing on the cause of skin damage according to the region, but it is not limited thereto. Skin damage according to gender, location of skin damage by region, cause of skin damage over time, location of skin damage over time, age at which skin damage occurs over time, skin damage over time by gender or time It is also possible to forecast demand by using the location of skin damage.

The pharmacy terminal 240 may perform an operation 330 of outputting information on insufficient medicines by comparing the medicine demand prediction information and the medicine inventory of the pharmacy. The pharmacy terminal 240 may use a display or a speaker to output information about insufficient medicines in image or sound. Pharmacists can prevent patients from returning to the pharmacy without getting them by putting needed medicines at the pharmacy based on the information about the medicines that are in short supply. In addition, since drug distributors can predict the drugs they need at regional pharmacies, they can minimize the inconvenience caused by inefficient distribution of resources.

5 is a flowchart illustrating a process for evaluating a treatment result in a hospital by a skin damage treatment system according to an embodiment of the present disclosure.

The service server 210 may determine the risk to be severe. The service server 210 may transmit the level of risk to the user terminal 220 . When the degree of risk indicates severe, the user terminal 220 may perform an operation of receiving at least one piece of hospital information. The user may select one of the at least one hospital information displayed on the user terminal 220 . Based on the user's input, the user terminal 220 may transmit the user's information to the selected hospital server 250 from among at least one piece of hospital information. The hospital server 250 may receive the user's information, check the schedule of a medical person belonging to the hospital, and allocate a time available for medical treatment to the user. The hospital server 250 may transmit the available medical treatment time to the user terminal 220 .

The user may arrive at the hospital at a time available for treatment and receive treatment. A medical person may input prescription information and diagnosis information to the hospital server 250 . The hospital server 250 selected based on the user's information may perform an operation 421 of transmitting the prescription information and the diagnosis information to the service server 210 . The service server 210 may store prescription information and diagnostic information in response to user information.

The service server 210 may perform a step 422 of transmitting an image related to skin damage, information related to skin damage, prescription information, and diagnostic information to the plurality of medical personnel terminals 230 . The service server 210 may delete all information related to a medical institution or a medical person who has performed a treatment from the image related to the skin damage, the information related to the skin damage, the prescription information, and the diagnosis information, and transmit it to the healthcare provider terminal 230 . The medical care provider terminal 230 may be a terminal that is used by a medical person certified.

A medical person using the medical care provider terminal 230 may evaluate a medical treatment result after checking an image related to skin damage, information related to skin damage, prescription information, and diagnosis information. A medical person using the medical care provider terminal 230 may input the evaluation result into the medical care provider terminal 230 .

The service server 210 may perform an operation 423 of receiving evaluation information on prescription information and diagnosis information from a plurality of medical personnel terminals. The service server 210 may transmit the evaluation information to the insurance company server. The insurance company server may store evaluation information about the medical institution. The insurance company server may output an alarm indicating the possibility of insurance fraud when the evaluation information is lower than a threshold value. Insurance company employees can conduct due diligence at medical institutions to investigate whether there is any insurance fraud.

In addition, when recommending a hospital to the user terminal 220 , the service server 210 may position it at the top of the screen of the user terminal 220 as the evaluation information is higher. That is, the user can easily check the hospital with high evaluation information. Since users are recommended to medical institutions with high evaluation information, they are more likely to receive high-quality medical care. When evaluation information is accumulated by the service server 210 of the present disclosure, an objective evaluation of a medical institution may be performed. In addition, since medical institutions can attract more patients by improving the quality of treatment, the quality of medical services as a whole increases.

In addition, the user terminal 220 may periodically acquire an image of the user's skin damaged area to obtain a plurality of treatment progress images. The user terminal 220 may continuously acquire an image of the skin damaged area from the time the skin is damaged for the first time during the period during which the skin damage treatment is performed. The image of the skin damaged area may be periodic, and the cycle may be at an interval of one day or an interval of one week.

The user terminal 220 may perform a step of transmitting a plurality of treatment progress images and information related to the treatment method to the service server 210 . The information related to the treatment method may include a treatment method performed by a medical professional or a treatment method automatically suggested by the service server 210 .

The service server 210 may perform a step of transmitting a plurality of treatment progress images and information related to a treatment method to the plurality of medical care provider terminals 230 . The medical care provider terminal 230 may be a terminal that is used by a medical person certified.

After checking a plurality of treatment progress images and information related to a treatment method using the medical care provider terminal 230 , the treatment result may be evaluated. A medical person using the medical care provider terminal 230 may input the evaluation result into the medical care provider terminal 230 . The medical personnel can check whether the treatment for the user is being performed normally by checking the plurality of treatment progress images used and information related to the treatment method.

In addition, the service server 210 may perform the step of receiving the evaluation information on the information related to the treatment period and treatment method from the plurality of medical personnel terminals. When the evaluation information is lower than a predetermined threshold value, the service server 210 may transmit a signal requesting a hospital visit to the user terminal 220 . By revisiting the hospital and receiving treatment from other medical personnel, the patient can be confirmed whether there is an abnormality in the treatment that has been received so far.

The service server 210 according to the present disclosure allows the medical personnel to continuously verify the progress of treatment, thereby minimizing medical accidents. In addition, since the service server 210 according to the present disclosure allows medical personnel to quickly share a plurality of treatment progress images and information related to treatment methods, it is possible to induce the medical personnel to quickly find an optimal treatment method using the collective intelligence of the medical personnel. have. Accordingly, the service server 210 has the effect of improving the quality of medical services. In addition, according to the service server 210 of the present disclosure, it can be quickly verified whether a treatment method or a therapeutic agent is effective for the treatment of skin damage possessed by a patient.

In addition, the service server 210 may acquire a relationship between the drug and the skin damage treatment effect based on the evaluation information. For example, the service server 210 may accumulate and store the treatment rates of medicines for specific skin damage. The service server 210 may instruct the user to use a drug with a fast effect by placing a drug with a fast treatment speed on the screen of the user terminal 220 later for a specific skin damage. In addition, the service server 210 may increase the number of times of recommending a drug with a fast treatment speed for a specific skin damage later to induce the user to use a drug with a fast effect.

When the service server 210 recommends medicines to the user, the higher the evaluation information, the more the service server 210 may be positioned at the top of the screen of the user terminal 220 or may increase the number of recommendations. Therefore, the user can easily check the drug with high evaluation information.

In the above, the configuration in which the service server 210 receives evaluation information from a medical person has been described. However, the present invention is not limited thereto. The service server 210 may automatically acquire evaluation information based on a plurality of treatment progress images and information related to treatment methods. For example, the service server 210 may include a machine learning model learned based on a plurality of treatment progress images, information related to treatment methods, and evaluation label information of medical personnel. The service server 210 may obtain prediction label information that predicts the evaluation information of the medical personnel by applying the plurality of treatment progress images and information related to the treatment method to the machine learning model. The service server 210 may use the prediction label information as evaluation information.

6 is a flowchart illustrating an operation of a medical care provider terminal according to an embodiment of the present disclosure.

The service server 210 may receive verification by a medical professional within a short time for the treatment method automatically generated by the service server 210 . For example, the service server 210 may control to receive the verification of the medical professional within 24 hours.

The medical personnel terminal 230 may receive an image related to skin damage, information related to skin damage, and information related to a treatment method. In addition, the medical care provider terminal 230, which has received the image related to the skin damage, the information related to the skin damage, and the information related to the treatment method, may perform the step 610 of receiving the evaluation information on the information related to the treatment method from the medical person. have. The evaluation information may be represented as a number. The higher the evaluation information, the higher the evaluation, and the lower the evaluation information, the lower the evaluation.

The medical care provider terminal 230 may perform an operation 620 of transmitting the evaluation information to the service server 210 . The service server 210 performs a step of allocating a reaction rate score inversely proportional to the time from the time when the information related to the treatment method is sent to the medical care provider terminal to the time when the evaluation information is received from the medical care provider terminal 230 to the healthcare provider's account. can do. The medical care provider terminal 230 may perform step 630 of receiving the response speed score assigned to the healthcare provider account by the service server 210 . When the reaction speed score assigned to the medical practitioner's account is equal to or greater than a predetermined threshold score, the medical practitioner can act as a medical professional in the service according to the present invention. In the case of working as a medical professional in the service according to the present invention, there may be support such as advertisements in the hospital to which the medical professional belongs. The service server 210 may give a higher reaction speed score to the medical practitioner's account as the medical personnel evaluates faster, so that the verification of the treatment method is performed quickly.

When the evaluation information evaluated by the medical personnel is lower than a predetermined threshold value, the service server 210 may transmit a signal requesting a hospital visit to the user terminal 220 . By revisiting the hospital and receiving treatment from other medical personnel, the patient can be confirmed whether there is an abnormality in the treatment that has been received so far. Therefore, even if the initial treatment is wrong, the user can quickly receive normal treatment.

7 is a flowchart illustrating an operation of a service server according to an embodiment of the present disclosure.

The service server 210 may perform an operation 710 of obtaining first difference information between the first evaluation information received from the first medical care provider terminal and the second evaluation information received from the second medical care provider terminal.

As already described, the service server 210 may listen to opinions from a plurality of medical personnel on one treatment method. More specifically, the service server 210 may receive the first evaluation information from the first medical care provider terminal, and receive the second evaluation information from the second medical care provider terminal. The first evaluation information and the second evaluation information may be real numbers or integers. The service server 210 may obtain a difference between the first evaluation information and the second evaluation information as the first difference information.

When the first difference information is less than or equal to the predetermined threshold value, the service server 210 may obtain the final evaluation information based on the first evaluation information and the second evaluation information. For example, the service server 210 may obtain the final evaluation information by using at least one of an average, a median value, and a median value of the first evaluation information and the second evaluation information.

In the above description, the configuration in which the service server 210 obtains the final evaluation information using the first medical care provider terminal and the second medical care provider terminal has been described, but the present invention is not limited thereto. The service server 210 may receive a plurality of evaluation information from at least two medical care provider terminals. The service server 210 may obtain the final evaluation information based on the plurality of evaluation information when the plurality of evaluation information received from the at least two medical care provider terminals is within the threshold range.

When the first difference information is greater than a predetermined threshold, the service server 210 transmits an image related to skin damage, information related to skin damage, and information related to a treatment method to the third medical care provider terminal (720). can do.

When the first difference information is greater than the predetermined threshold value, it may mean that the opinions of the first medical personnel and the second medical personnel are significantly different. Therefore, the service server 210 uses the terminal of the third medical person to determine which of the first evaluation information and the second evaluation information is more meaningful, the image related to skin damage, information related to skin damage, and information related to a treatment method. can be sent.

The third medical care provider terminal may receive the third evaluation information on the treatment method-related information from the medical personnel and transmit the received information to the service server 210 . The service server 210 may perform step 730 of receiving the third evaluation information transmitted by the third medical care provider terminal.

The service server 210 may perform a step 740 of obtaining the second difference information between the first evaluation information and the third evaluation information, and obtaining the third difference information between the second evaluation information and the third evaluation information. . The second difference information may be a difference between the first evaluation information and the third evaluation information. Also, the third difference information may be a difference between the second evaluation information and the third evaluation information.

When the second difference information and the third difference information are smaller than the threshold value, the service server may perform the step 750 of determining the average of the first evaluation information, the second evaluation information, and the third evaluation information as the final evaluation information. have. When the second difference information and the third difference information are smaller than the threshold value, the service server 210 may determine that all of the first evaluation information, the second evaluation information, and the third evaluation information are significant. The service server 210 may determine final evaluation information based on the first evaluation information, the second evaluation information, and the third evaluation information. For example, the service server 210 may determine at least one of an average, a median value, or a median value of the first evaluation information, the second evaluation information, and the third evaluation information as the final evaluation information.

If the second difference information is smaller than the threshold value, and the third difference information is greater than the threshold value, the service server 210 determines the average of the first evaluation information and the third evaluation information as the final evaluation information (750) can be done When the second difference information is smaller than the threshold value and the third difference information is greater than the threshold value, the service server 210 may determine that only the first evaluation information and the third evaluation information are meaningful. The service server 210 may determine final evaluation information based on the first evaluation information and the third evaluation information. For example, the service server 210 may determine at least one of an average, a median value, or a median value of the first evaluation information and the third evaluation information as the final evaluation information.

If the second difference information is greater than the threshold value, and the third difference information is less than the threshold value, the service server 210 determines the average of the second evaluation information and the third evaluation information as the final evaluation information ( 750 ) can be done When the second difference information is greater than the threshold value and the third difference information is less than the threshold value, the service server 210 may determine that only the second evaluation information and the third evaluation information are meaningful. The service server 210 may determine final evaluation information based on the second evaluation information and the third evaluation information. For example, the service server 210 may determine at least one of an average, a median value, or a median value of the second evaluation information and the third evaluation information as the final evaluation information.

8 is a flowchart illustrating a method of operating a skin damage treatment system according to an embodiment of the present disclosure.

Hereinafter, the description will be focused on pharmaceuticals, but the present invention is not limited thereto. In the treatment method, not only drugs but also medical devices can be used, and in the description below, drugs can be replaced with medical devices.

The user terminal 220 may perform an operation 851 of transmitting drug information and user information included in the treatment method-related information to the service server 210 based on the user's input. The user may select one of the at least one medicine suggested by the service server 210 and input it into the user terminal 220 . The user terminal 220 may transmit the medicine information to the service server 210 together with the user information. The user may be information that can identify the user.

In addition, the service server 210 may perform a step 852 of generating an encrypted authentication code based on the user information and the medicine information. When the service server 210 receives the user information and the medicine information, it may indicate that the user needs medicine. The service server 210 may transmit a delivery service reservation signal to the server of the delivery person terminal 260 or the company to which the delivery person belongs in order to secure a delivery person who can deliver medicines. The company's server may assign a delivery man to entrust the delivery service to the delivery man terminal 260 . The delivery man may check the drug delivery request signal of the delivery man terminal 260 and depart to the pharmacy where the drug is.

The service server 210 may perform step 853 of transmitting the drug information, the user's information, and the authentication code to the pharmacy terminal 240 . The pharmacy terminal 240 may be replaced by a pharmacy server. The pharmacist may perform a procedure for delivering the drug based on the drug information, the user's information, and the authentication code received by the pharmacy terminal 240 .

When the delivery man arrives at the pharmacy, the delivery man may use the delivery man terminal 260 to perform a procedure necessary to take over the medicine. The pharmacy terminal 240 may perform a step 861 of transmitting the authentication code to the delivery man terminal 260 . Deliverymen can receive medicines from pharmacists. In addition, the delivery man terminal 260 may perform the step 862 of recognizing the drug identifier displayed on the packaging of the drug. In addition, the delivery man terminal 260 may perform a step 863 of transmitting the authentication code, the drug identifier and the identifier of the delivery man to the service server.

The delivery person may deliver the medicine to the user. The user may use the user terminal 220 to perform a procedure necessary for taking the medicine. The user terminal 220 may perform step 871 of recognizing the drug identifier displayed on the package of the drug. In addition, the user terminal 220 may perform a step 872 of recognizing the authentication code displayed on the delivery man terminal (260).

The authentication code displayed on the delivery man terminal 260 may be an encrypted QR code or barcode. However, the present invention is not limited thereto, and the authentication code may be displayed on the delivery box of the medicine instead of being displayed on the delivery man terminal 260 . The image acquisition unit of the user terminal 220 may perform the step of photographing the QR code corresponding to the authentication code displayed on the display unit of the delivery man terminal 260 . The user terminal 220 may perform a step of obtaining an authentication code based on the photographed image of the QR code.

The user terminal 220 may perform a step 873 of transmitting the recognized authentication code and the recognized drug identifier to the service server 210 . The service server 210 may receive information from the delivery man terminal 260 and the user terminal 220 .

When receiving the authentication code and drug identifier from the service server 210 delivery man terminal 260, and receiving the recognized authentication code and the recognized drug identifier from the user terminal 220, the service server sends a signal indicating the end of the service can create

In addition, the service server 210 may determine that the transaction is normally made when all the information received from the delivery man terminal 260 and the user terminal 220 is normal. In addition, when a problem occurs during delivery, the service server 210 may quickly recognize the part where the problem occurs between the pharmacy, the delivery person, or the user. For example, if the authentication code is incorrectly entered in the delivery man terminal 260, it can be understood that there was a problem between the pharmacist and the delivery man.

As already described, the delivery man may visit the user to deliver the medicine. In addition, the delivery man may provide a service to check the user's condition and transport the user to a hospital if the user's condition is serious.

At this time, the delivery man may input the user's information to the delivery man terminal 260 under the user's consent. The delivery man terminal 260 may transmit a signal indicating the transfer service together with the user information to the service server 210 . The service server 210 may transmit hospital information including the location information of the hospital and a new authentication code to the delivery man terminal 260 . The service server 210 may transmit user information to the hospital server 250 . The hospital may arrange to receive the patient. After the delivery man transfers the user to the hospital, the hospital staff may recognize the authentication code displayed on the delivery man terminal 260 using a recognizer connected to the hospital server 250 . Also, the hospital staff may input the patient's user information into the hospital server 250 . The hospital server 250 may transmit user information and an authentication code to the service server 210 . When the service server 210 normally receives the user information and the authentication code from the hospital server 250 , the service server 210 may determine that the user transfer has been normally performed.

So far, various embodiments have been mainly looked at. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments are to be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

Meanwhile, the above-described embodiments of the present invention can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium. The computer-readable recording medium includes a storage medium such as a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.) and an optically readable medium (eg, a CD-ROM, a DVD, etc.).

Claims (1)

How the skin damage treatment system works.

Images