KR102692430B1 - Telemedicine service providing device that provides doctor matching service based on recommendation - Google Patents

Abstract

According to an embodiment of the present invention, an apparatus for providing a doctor matching service based on recommendation is provided. The device receives a medical treatment matching request from the user's user terminal, provides a list of a plurality of doctors to the user terminal, and receives a doctor selection input for one of the doctors and a request to wait for treatment from the user terminal. a treatment matching unit that receives and provides the treatment waiting request to a doctor terminal of a doctor corresponding to the doctor selection input, and receives a treatment acceptance input from the doctor terminal; and a call connection unit that provides a call request to the user terminal and the doctor terminal when the medical treatment acceptance input is received, and provides channel information for the call to the user terminal and the doctor terminal.

Description

Telemedicine service provision device that provides doctor matching service based on recommendation {TELEMEDICINE SERVICE PROVIDING DEVICE THAT PROVIDES DOCTOR MATCHING SERVICE BASED ON RECOMMENDATION}

The present invention relates to a remote medical service provision device that provides a doctor matching service based on recommendations.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and is not admitted to be prior art by inclusion in this section.

As ICT (Information and Communication Technologies) technology develops, users in locations where network networks are provided can transmit video to each other without interruption.

Accordingly, much research is being conducted on technologies for performing telemedicine using this infrastructure.

Conventional technologies suggest ways to make medical appointments between users and doctors and perform remote medical treatment through video calls, but there are still many technologies to prevent leakage of personal information that may occur when medical treatment is conducted remotely. Research is not being done.

Republic of Korea Patent Publication No. 10-2001-0109031 (December 8, 2001) Republic of Korea Patent Publication No. 10-2014-0037325 (2014.03.27.)

The present invention provides remote medical treatment that provides a doctor matching service based on recommendation, where a service providing device provides a call request to the user's terminal and the doctor's terminal, and connects the user's terminal that approved the call request and the doctor's terminal. The purpose is to provide a service provision device.

In addition, the present invention provides a remote medical service providing device that provides a doctor matching service based on recommendation, which can determine a doctor suitable to perform video medical treatment for a user and provide information about the determined doctor to the user. provided for a different purpose.

In addition, the present invention is a remote medical treatment service that provides a doctor matching service based on recommendation, which determines the image of the treatment area corresponding to the input received from the doctor's terminal and provides the determined image of the treatment area to the user's terminal. Another purpose is to provide a provision device.

Another object of the present invention is to provide a remote medical service providing device that provides a doctor matching service based on recommendations, which can de-identify the user's facial parts and provide them to the doctor's terminal.

In one aspect of the present invention for achieving the above object, an apparatus for providing a doctor matching service based on recommendation is provided.

The device receives a medical treatment matching request from the user's user terminal, provides a list of a plurality of doctors to the user terminal, and receives a doctor selection input for one of the doctors and a request to wait for treatment from the user terminal. a treatment matching unit that receives and provides the treatment waiting request to a doctor terminal of a doctor corresponding to the doctor selection input, and receives a treatment acceptance input from the doctor terminal; and a call connection unit that provides a call request to the user terminal and the doctor terminal when the medical treatment acceptance input is received, and provides channel information for the call to the user terminal and the doctor terminal.

In addition, the medical treatment matching unit receives a first input for the symptom, inputs the first input as an input value to a pre-learned first machine learning model, and connects each of a plurality of medical departments from the first machine learning model. Obtain a corresponding first matching degree, determine the medical departments whose first matching degree is greater than or equal to a preset first standard matching degree as first medical departments, and provide a plurality of questionnaires previously matched and stored with the first medical departments in a database. Searching for the questionnaires, providing the questionnaires to the user terminal, receiving questionnaire results corresponding to the questionnaires from the user terminal, and providing a second matching diagram corresponding to each of the first medical departments based on the questionnaire results. , determines the first medical department with the highest second matching degree as the second medical department, searches the database for the doctors and each of the doctors' history information stored in matching with the second medical department, The list of doctors stored in matching with the second medical department and the history information for each of the doctors may be provided to the user terminal.

In addition, the history information includes waiting time, rating, and number of remote medical treatments, and the treatment matching unit determines a recommendation level corresponding to each of the doctors based on the waiting time, the rating, and the number of remote medical treatments, The list of doctors in order of highest recommendation may be provided to the user terminal.

According to one embodiment of the present invention, the service providing device provides a call request to the user's terminal and the doctor's terminal, and connects the user's terminal that approved the call request and the doctor's terminal, so the user's and doctor's phone numbers, Telemedicine can be performed via video phone while personal information such as email address, ID, etc. is not leaked.

According to another embodiment of the present invention, a doctor suitable to perform video medical treatment for the user may be recommended to the user.

Additionally, in the present invention, since an image of the treatment area corresponding to the input received from the doctor's terminal is provided to the user's terminal, telemedicine can proceed more smoothly.

Additionally, in the present invention, parts of the user's face are de-identified and provided to the doctor's terminal, so that the user's face is not leaked and remote medical treatment can be performed through video phone.

1 is a schematic diagram of a system for providing remote medical care services according to an embodiment.
FIG. 2 is a block diagram illustrating functional modules of the service providing device according to FIG. 1.
FIG. 3 is a flowchart illustrating an embodiment of a process in which the medical treatment matching unit and the call connection unit according to FIG. 2 connect a user and a doctor over a wire.
FIG. 4 is a flowchart illustrating another embodiment of a process in which the medical treatment matching unit and the call connection unit according to FIG. 2 connect a user and a doctor over a wire.
FIG. 5 is a flowchart showing the process of matching doctors by the treatment matching unit according to FIG. 2.
FIG. 6 is a flowchart illustrating a process in which the treatment assistant according to FIG. 2 provides an image of a treatment area to a user terminal.
FIG. 7 is a flowchart showing a process in which the medical treatment assistant according to FIG. 2 de-identifies or identifies parts of the user's face in the image.
FIG. 8 is a diagram illustrating an exemplary hardware configuration of the service providing device according to FIG. 1.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that it does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted in an ideal or excessively formal sense unless explicitly defined in the present application. No.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

1 is a schematic diagram of a system for providing a remote medical service according to an embodiment.

Referring to FIG. 1, a system for providing a remote medical service includes a service providing device 100, a user terminal 200, and a doctor terminal 300. In the illustrated embodiment,

The user terminal 200 is a terminal of a user who wishes to receive remote medical treatment through a remote medical treatment service, and provides user information to the service providing device 100. In one embodiment, the user's information may include information that can specify the user, such as the user's name, age, resident registration number, address, and gender.

Additionally, the doctor terminal 300 is a terminal that wishes to remotely perform medical treatment for a user through a telemedicine service, and provides doctor information to the service providing device 100. Doctor information may include information that can identify the doctor, such as the doctor's name, age, resident registration number, address, gender, and doctor's license information.

Examples of the user terminal 200 and the doctor terminal 300 include a desktop computer, a laptop computer, a laptop, a smart phone, and a tablet PC capable of communication. , mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant) It may be, etc.

The service providing device 100 may be a server for providing a remote medical service to the user terminal 200 and the doctor terminal 300.

First, the service providing device 100 may receive a medical treatment matching request from the user terminal 200 and provide the user terminal 200 with a list of matched doctors and doctor information for each of the matched doctors.

Additionally, the service providing device 100 may receive a doctor selection input and a request to wait for treatment from the user terminal 200 and provide a request to wait for treatment to the doctor terminal 300 that matches the doctor selection input.

Additionally, the service providing device 100 may receive a medical treatment acceptance input from the doctor terminal 300 and connect the user terminal 200 and the doctor terminal 300 by wire.

Additionally, the service providing device 100 may provide a medical treatment assistance service that helps the user terminal 200 and the doctor terminal 300 to smoothly perform remote medical treatment.

Additionally, the service providing device 100 may provide the prescription received from the doctor terminal 300 to the user terminal 200.

Additionally, the service providing device 100 may provide a medical fee payment service to the user terminal 200 and the doctor terminal 300.

FIG. 2 is a block diagram illustrating functional modules of the service providing device 100 according to FIG. 1 .

Referring to FIG. 2, the service providing device 100 includes a medical treatment matching unit 101 and a call connection unit 102.

FIG. 3 is a flowchart illustrating an embodiment of a process in which the medical treatment matching unit 101 and the call connection unit 102 according to FIG. 2 connect a user and a doctor over a wire.

First, the medical treatment matching unit 101 receives a medical treatment matching request (S110) from the user terminal 200. In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a user interface (User Interface) through which a user can input a medical treatment matching request.

When a medical treatment matching request is received, the medical treatment matching unit 101 matches the user and the doctor (S120).

In one embodiment, the medical treatment matching unit 101 may receive the medical department where the user wants to receive medical treatment from the user terminal 200, and search the history information of each of the plurality of doctors stored in advance by matching with the medical department in the database. there is. Additionally, the medical treatment matching unit 101 may generate a list of searched doctors. In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a user interface through which the user can input a selection for at least one of a plurality of preset medical departments. In the database of the service provision device 100, the history information of each of the plurality of preset medical departments and the plurality of doctors are matched in advance and stored.

FIG. 5 is a flowchart showing a process in which the medical treatment matching unit 101 according to FIG. 2 matches a doctor.

Referring to FIG. 5, the treatment matching unit 101 receives a first input about the symptom from the user terminal 200 (S121). In one embodiment, the first input may be text about the symptom or a voice about the symptom. In one embodiment, when the first input is a voice, the medical treatment matching unit 101 inputs the voice as an input value into a previously learned STT (Speak To Text) model and obtains text corresponding to the voice from the STT model. do.

Additionally, the medical treatment matching unit 101 inputs the first input as an input value to a previously learned machine learning model and obtains a first matching degree corresponding to each of a plurality of medical departments from the machine learning model (S123).

In one embodiment, pediatrics, internal medicine, otolaryngology, dentistry, etc. may be set as preset medical departments.

In one embodiment, the machine learning model may receive text data corresponding to the first input as an input value and output a first matching degree between the text data and each medical department. In one embodiment, the machine learning model can separate text data into morpheme units, generate vectors for a plurality of separated morphemes, and specify the probability of corresponding to each medical department based on the generated vector. there is. In one embodiment, the probability of corresponding to each medical department means the first matching degree corresponding to each medical department. In one embodiment, Recurrent Neural Network (RNN), BERT, Random Forest, etc. may be used to learn a machine learning model. However, it is not limited to this.

Additionally, the medical treatment matching unit 101 determines medical departments whose first matching degree is higher than or equal to a preset first standard matching degree as first medical departments (S123).

Additionally, the medical treatment matching unit 101 searches the database of the service providing device 100 for a plurality of questionnaires that have been previously matched and stored with the first medical departments (S124).

In the database of the service providing device 100, a questionnaire is stored in advance by matching each of the plurality of preset first medical departments. In one embodiment, the questionnaire may include a plurality of questions set to determine whether it is appropriate for the patient to receive treatment at the first medical department. In one embodiment, each of the plurality of questions may include a plurality of options.

Additionally, the medical treatment matching unit 101 provides the searched questionnaires to the user terminal 200 and receives the questionnaires and corresponding survey results from the user terminal 200 (S125).

In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a user interface through which the user can input selection input for questions included in the survey.

In one embodiment, the survey results may include selection input by the user for each of a plurality of questions included in the survey. The selection input may be an input for selecting one of the options included in the question.

Additionally, the medical treatment matching unit 101 determines a second matching degree corresponding to each of the first medical departments based on the survey results (S126).

In one embodiment, each of the options included in the question is matched with a preset score and stored in the database of the service providing device 100. The options included in the question may be matched with different scores.

The medical treatment matching unit 101 determines a score corresponding to each of the questions based on the selection input for each of the questions included in the survey results, and calculates the sum of the scores corresponding to the questions to the first medical department corresponding to the first medical department. 2 Determine the matching degree.

Through this, the medical treatment matching unit 101 can determine the second matching degree for each of the first medical departments.

Additionally, the medical treatment matching unit 101 determines the first medical department with the highest second matching degree as the second medical department (S127).

Additionally, the medical treatment matching unit 101 searches the database of the service provision device 100 for doctors and their respective history information stored in matching with the second medical department (S128).

In one embodiment, the history information may include waiting time corresponding to the doctor, rating corresponding to the doctor, number of telemedicines corresponding to the doctor, etc. Additionally, the history information may include doctor information corresponding to the doctor. The doctor terminal 300 may provide waiting times corresponding to the doctor at preset time intervals. The treatment matching unit 101 modifies the doctor's existing waiting time to the newly received waiting time and stores it in the database.

Referring again to FIG. 2, the medical treatment matching unit 101 provides a list of searched doctors to the user terminal 200 (S130).

In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a list of doctors and history information about each of the doctors.

In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a list of doctors in order of short waiting time.

In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a list of doctors in order of highest rating.

In one embodiment, the medical treatment matching unit 101 may provide the user terminal 200 with a list of doctors in order of highest number of telemedicine visits.

In one embodiment, the medical treatment matching unit 101 may determine the recommendation level corresponding to each of the searched doctors and provide the user terminal 200 with a list of doctors in order of high recommendation.

In one embodiment, the recommendation level can be determined by Equation 1 below.

[Equation 1]

R= K1/T + P/K2 + N/K3

In Equation 1 above, R means recommendation, K1 means the first coefficient, and T means waiting time. In addition, P refers to the rating, K2 refers to the second coefficient, N refers to the number of telemedicine visits, and K3 refers to the third coefficient.

The medical treatment matching unit 101 may determine the average value of waiting times corresponding to doctors matched to the same second medical department as K1.

The medical treatment matching unit 101 may determine the average value of ratings corresponding to doctors matched to the same second medical department as K2.

The medical treatment matching unit 101 may determine the average value of the number of remote medical treatments corresponding to doctors matched to the same second medical department as K3.

The medical treatment matching unit 101 receives the rankings for each of the waiting time, rating, and number of remote medical treatments from the user terminal 200, and based on the rankings for each of the waiting time, rating, and number of remote medical treatments, the first coefficient, the second The 2nd and 3rd coefficients can be corrected. For example, if the rankings for waiting time, rating, and number of telemedicine visits are 1st, 2nd, and 3rd, multiply the first, second, and third coefficients by 1.2, 0.9, and 1 to get the first, second, and third coefficients. The 2nd coefficient and the 3rd coefficient can be corrected. For example, if the rankings for waiting time, rating, and number of telemedicine visits are 3rd, 2nd, and 1st, multiply the first, second, and third coefficients by 1, 0.9, and 1.2 to get the first, second, and third coefficients. The 2nd coefficient and the 3rd coefficient can be corrected. For example, if the rankings for waiting time, rating, and number of telemedicine visits are 3rd, 2nd, and 1st, multiply the first, second, and third coefficients by 1, 0.9, and 1.2 to get the first, second, and third coefficients. The 2nd and 3rd coefficients can be corrected. For example, if the rankings for waiting time, rating, and number of telemedicine visits are 2nd, 1st, and 3rd, multiply the first, second, and third coefficients by 1.1, 0.8, and 1 to obtain the first, second, and third coefficients. The 2nd and 3rd coefficients can be corrected. The treatment matching unit 101 may correct the first coefficient by multiplying the first coefficient by a value relatively greater than 1 as the ranking of the waiting time is relatively high. The treatment matching unit 101 may correct the second coefficient by multiplying the second coefficient by a value that is relatively smaller than 1 as the rank of the waiting time is relatively high. The treatment matching unit 101 may correct the third coefficient by multiplying the third coefficient by a value that is relatively smaller than 1 as the rank of the waiting time is relatively high.

Additionally, the treatment matching unit 101 receives a doctor selection input and a request to wait for treatment from the user terminal 200 (S140).

The user can check the list of doctors searched and the history information of each doctor through the user terminal 200. Additionally, the medical treatment matching unit 101 may provide the user terminal 200 with a user interface through which a doctor selection input for one of the doctors included in the list can be entered.

Additionally, the treatment matching unit 101 transmits patient information and a request to wait for treatment to the doctor terminal 300 corresponding to the doctor selection input (S150).

In one embodiment, patient information may include the user's age, name, gender, etc. In one embodiment, the patient information may include selection input for each of the questions included in the survey provided to the user terminal 200 and the survey received from the user terminal 200.

Additionally, the medical treatment matching unit 101 receives a medical treatment acceptance input from the doctor terminal 300 (S160).

When a medical treatment acceptance input is received, the call connection unit 102 transmits a call request to the user terminal 200 and the doctor terminal 300 (S210).

In one embodiment, the call request may be a Voice over Internet Protocol (VoIP) phone.

Additionally, the call connection unit 102 opens a channel to connect the user terminal 200 and the doctor terminal 300 over a VoIP phone (S220).

Additionally, the call connection unit 102 receives a channel information request from the user terminal 200 that has received the VoIP call (S230) and returns the channel information to the user terminal 200 (S240).

Additionally, the call connection unit 102 receives a channel information request from the physician terminal 300 that has received the VoIP call (S250) and returns the channel information to the physician terminal 300 (S260).

Through this, the user terminal 200 can transmit the image input through the input interface device of the user terminal 200 to the call connection unit 102 through an established channel in the form of a digital packet.

In addition, the call connection unit (102) transmits the received digital packet to the doctor terminal (300) through the opened channel, and the doctor terminal (300) converts the received digital packet into an image and provides it to the doctor through the output interface device of the doctor terminal (300).

Additionally, the doctor's terminal 300 can transmit the image input through the input interface device of the doctor's terminal 300 to the call connection unit 102 through an established channel in the form of a digital packet.

In addition, the call connection unit 102 transmits the received digital packet to the user terminal 200 through an established channel, and the user terminal 200 converts the received digital packet into an image and provides it to the user through an output interface device. to provide.

Additionally, the user terminal (200) and the doctor terminal (300) can directly transmit and receive images in the form of digital packets through the opened channel.

Since the call connection unit 102 makes a VoIP call between the user and the doctor and the medical treatment is performed over the VoIP phone, the medical treatment can be performed without the user and the doctor exposing personal information such as phone number, email, and ID to each other.

FIG. 4 is a flowchart showing another embodiment of a process in which the medical treatment matching unit 101 and the call connection unit 102 according to FIG. 2 connect a user and a doctor over a wire.

In the illustrated embodiment, steps S110, S120, S130, S140, S150, and S160 are the same as steps S110, S120, S130, S140, S150, and S160 described above with reference to FIG. do.

When the medical treatment acceptance input is received, the call connection unit 102 opens a channel to connect the user terminal 200 and the doctor terminal 300 over a VoIP phone (S310).

Additionally, the call connection unit 102 transmits a call request to the user terminal 200 and the doctor terminal 300 (S320).

In one embodiment, the call request may be a Voice over Internet Protocol (VoIP) phone. In one embodiment, the call connection unit 102 may transmit a call request to the user terminal 200 and the doctor terminal 300 using a call application programming interface (API).

Additionally, the call connection unit 102 receives a channel information request from the user terminal 200 that has received the VoIP call (S330) and returns the channel information to the user terminal 200 (S340).

Additionally, the call connection unit 102 receives a channel information request from the physician terminal 300 that has received the VoIP call (S350) and returns the channel information to the physician terminal 300 (S360).

Through this, the user terminal 200 can transmit the image input through the input interface device of the user terminal 200 to the call connection unit 102 through an established channel in the form of a digital packet.

In addition, the call connection unit 102 transmits the received digital packet to the doctor terminal 300 through an established channel, and the doctor terminal 300 converts the received digital packet into an image and outputs the received digital packet to the doctor terminal 300. It is provided to the doctor through an interface device.

Additionally, the doctor's terminal 300 can transmit the image input through the input interface device of the doctor's terminal 300 to the call connection unit 102 through an established channel in the form of a digital packet.

In addition, the call connection unit 102 transmits the received digital packet to the user terminal 200 through an established channel, and the user terminal 200 converts the received digital packet into an image and provides it to the user through an output interface device. to provide.

Additionally, the user terminal 200 and the physician terminal 300 can directly transmit and receive images in the form of digital packets through an established channel.

Since the call connection unit 102 makes a VoIP call between the user and the doctor and the medical treatment is performed over the VoIP phone, the medical treatment can be performed without the user and the doctor exposing personal information such as phone number, email, and ID to each other.

Referring again to FIG. 2 , the service providing device 100 includes a medical treatment assistant 103.

FIG. 6 is a flowchart showing a process in which the treatment assistant 103 according to FIG. 2 provides an image of a treatment area to a user terminal.

The medical treatment assistant 103 receives a second input indicating the treatment area from the doctor terminal 300 (S410).

In one embodiment, the second input may be text or voice.

In one embodiment, when the second input is a voice, the medical assistant 103 inputs the voice as an input value into a previously learned STT (Speak To Text) model and obtains text corresponding to the voice from the STT model. .

Additionally, the medical treatment assistant 103 inputs the second input as an input value to a pre-learned machine learning model and obtains a third matching degree corresponding to each of the preset treatment area images from the machine learning model.

In one embodiment, the machine learning model may receive text data corresponding to the second input as an input value and output a third matching degree between the text data and images of each treatment area. In one embodiment, the machine learning model separates text data into morphemes, generates vectors for a plurality of separated morphemes, and specifies the probability of corresponding to each treatment area image based on the generated vector. can do. In one embodiment, the probability of corresponding to each treatment area image means the third matching degree corresponding to each treatment area image. In one embodiment, Recurrent Neural Network (RNN), BERT, Random Forest, etc. may be used to learn machine learning models. However, it is not limited to this.

Additionally, the medical treatment assistant 103 provides the doctor terminal 300 with images of treatment areas whose third matching degree is equal to or greater than the preset second reference matching degree.

Additionally, the medical treatment assistant 103 receives an image selection input for one of the treatment area images from the doctor terminal 300 (S440).

In one embodiment, the medical treatment assistant 103 may provide the doctor terminal 300 with a user interface through which the doctor can check the provided treatment area images and input an image selection input for one of the treatment area images. there is.

Additionally, the treatment assistant 103 provides the user terminal 200 with an image of the treatment area corresponding to the image selection input (S450).

Through this, the user can recognize the treatment area that the doctor wants to check, and provide an image taken of the recognized treatment area to the call connection unit 102.

FIG. 7 is a flowchart showing a process in which the medical treatment assistant 103 according to FIG. 2 de-identifies or identifies parts of the user's face in an image.

The call connection unit 102 receives the non-identification request and video (S510).

Additionally, the medical treatment assistant 103 determines whether the voice included in the video matches the user's voice stored in advance (S520). In one embodiment, the medical treatment assistant 103 may determine whether the waveform of the voice included in the image matches the waveform of the user's voice previously stored in the database.

Additionally, the medical treatment assistant 103 de-identifies a plurality of preset facial parts in the image when the voice included in the image matches the user's pre-stored voice.

In one embodiment, the medical treatment assistant 103 may input a frame included in an image as an input value to a machine learning model and obtain information about the area occupied by a plurality of facial parts from the machine learning model.

In one embodiment, when a frame is input as an input value, the machine learning model outputs an object box for objects (e.g., eyes, nose, mouth) corresponding to facial parts included in the frame, and an object box When an image containing an object included in is input as an input value, a mask-rcnn (Mask region convolutional neural network) model that is machine learned to output information about the area occupied by the object within the image may be included.

In one embodiment, the medical treatment assistant 103 de-identifies areas occupied by a plurality of facial parts. Various known de-identification processing methods can be used to de-identify areas occupied by a plurality of facial parts.

Additionally, the call connection unit 102 provides a de-identified image of a plurality of preset facial parts to the doctor terminal 300 (S530).

Additionally, the medical treatment assistant 103 may receive a request to disclose at least one of the plurality of facial parts from the doctor terminal 300 (S540).

Additionally, the medical assistant 103 may provide the user terminal 200 with a request to disclose at least one of the plurality of facial parts (S550).

Additionally, the medical treatment assistant 103 may receive disclosure request approval from the user terminal 200.

When the disclosure request approval is received, the medical assistant 103 performs identification processing on the area occupied by the facial parts corresponding to the disclosure request in the image provided to the doctor terminal 300 (S560). Various known identification processing methods can be used to identify the de-identified portion.

Referring again to FIG. 2 , the service providing device 100 includes a prescription providing unit 104 .

When remote medical treatment via VoIP phone is terminated, the prescription provision unit 104 receives a prescription from the doctor terminal 300 and provides the received prescription to the user terminal 200.

In one embodiment, the prescription providing unit 104 may provide the doctor terminal 300 with a user interface for entering a prescription. Additionally, the prescription providing unit 104 may provide the user terminal 200 with a user interface that can display the received prescription.

Additionally, the service provision device 100 includes a payment unit 105.

The payment unit 105 receives a payment request from the doctor terminal 300 and provides the received payment request to the user terminal 200.

Additionally, the payment unit 105 receives payment information from the user terminal 200 and provides the received payment information to a separate payment server (not shown).

In addition, the payment unit 105 may receive information including whether the payment is approved from the payment server, and provide information including whether the received payment is approved to the user terminal 200 and the doctor terminal 300. there is.

FIG. 8 is a diagram illustrating the hardware configuration of the service providing device 100 according to FIG. 1.

Referring to FIG. 8, the service providing device 100 stores at least one processor 110 and instructions instructing the at least one processor 110 to perform at least one operation. may include memory.

The at least one operation may include the components 101 to 105 of the service providing device 100 described above or other functions or operation methods.

Here, the at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. You can. Each of the memory 120 and the storage device 160 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium.

For example, the memory 120 may be one of read only memory (ROM) and random access memory (RAM), and the storage device 160 may be flash memory. , a hard disk drive (HDD), a solid state drive (SSD), or various memory cards (eg, micro SD card).

Additionally, the device 100 may include a transceiver 130 that performs communication through a wireless network. Additionally, the device 100 may further include an input interface device 140, an output interface device 150, a storage device 160, etc. Each component included in the device 100 is connected by a bus 170 and can communicate with each other.

Examples of the device 100 include a desktop computer, a laptop computer, a laptop, a smart phone, a tablet PC, and a mobile phone capable of communicating. , smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player. , a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, a PDA (Personal Digital Assistant), etc.

Methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. Computer-readable media may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on a computer-readable medium may be specially designed and constructed for the present invention or may be known and usable by those skilled in the computer software art.

Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions may include machine language code such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

Additionally, the above-described method or device may be implemented by combining all or part of its components or functions, or may be implemented separately.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that you can do it.

Claims (1)

As a device for providing a doctor matching service based on recommendation,
Receiving a medical treatment matching request from the user's user terminal, providing a list of a plurality of doctors to the user terminal, receiving a doctor selection input for one of the doctors and a request to wait for treatment from the user terminal, a treatment matching unit that provides the treatment waiting request to a doctor terminal of a doctor corresponding to a doctor selection input and receives a treatment acceptance input from the doctor terminal; and
When the treatment acceptance input is received, it provides a call request to the user terminal and the doctor terminal, and includes a call connection unit that provides channel information for the call to the user terminal and the doctor terminal,
The medical matching department,
receive first input about symptoms,
Entering the first input as an input value into a previously learned first machine learning model, and obtaining a first matching degree corresponding to each of a plurality of medical departments from the first machine learning model,
Determining the medical departments whose first matching degree is greater than or equal to a preset first standard matching degree as first medical departments,
Search the database for a plurality of questionnaires stored in advance by matching with the first medical departments,
Providing the questionnaires to the user terminal, receiving survey results corresponding to the questionnaires from the user terminal,
Determining a second matching degree corresponding to each of the first medical departments based on the survey results,
The first medical department with the highest second matching degree is determined as the second medical department,
Searching the database for the doctors and each of the doctors' history information stored in matching with the second medical department,
Providing the user terminal with the list of doctors stored in matching with the second medical department and the history information for each of the doctors,
The history information includes waiting time, rating, and number of remote medical treatments,
The medical matching department,
Determining a recommendation level corresponding to each of the doctors based on the waiting time, the rating, and the number of remote medical treatments,
Providing the user terminal with the list in which the doctors are listed in order of highest recommendation,
Device.