KR102165833B1 - Method and Device for diagnosing abnormal health conditions - Google Patents

Abstract

The present invention relates to a server, a terminal, and a method for automatically detecting an adverse reaction of a user's health. In a preferred embodiment of the present invention, the user's health status is analyzed in real time through data acquired from at least one of a wearable device detachable to the user's skin, a user terminal, and a node capable of communication, and an interview with the user. By classifying the stage of the adverse reaction that appeared in the patient in real time, early response to the adverse reaction is possible.

Description

Terminal, server, or method for detecting abnormal reactions {Method and Device for diagnosing abnormal health conditions}

The present invention relates to a terminal, a server, or a method for detecting an adverse reaction of a user's health condition in advance.

In recent years, amid rapid changes in the social environment, health care costs are increasing as interest in health increases. In addition, with the rapid development of IT technology, research and development in the healthcare field based on the network environment is beginning with the grafting of IT technology into the medical field.

However, despite the increase in medical expenditures and the development of new medical services, when an abnormal reaction occurs in many patients living on a daily basis, there are often cases in which abnormal symptoms cannot be detected in advance and appropriate medical services are not received.

Meanwhile, patients due to an increase in the elderly population due to rapid entry into an aging society, an increase in double-income households, an increase in the physical distance between families due to the nuclear familyization, a rapid increase in facilities concentrated in the elderly such as postpartum cooking centers and silver towns, and a medical gap due to a decrease in the rural population There is also an increasing trend in cases where appropriate measures cannot be taken when adverse reactions of

As such, early detection and rapid emergency treatment for abnormal reactions to patients are emerging as a social problem with aging and nuclear family.

In addition, the rate of sudden death due to excessive work and stress is also increasing in the general population, and accordingly, the need for a system or device that can check the health status of each individual by experts is increasing even in places other than hospitals.

KR 10-1812406 B1

Automatic detection system for cough sounds as a symptom of abnormal health condition, IEEE Trans Inf Technol Biomed. 2009 Jul;13(4):486-93. doi: 10.1109/TITB.2008.923771. Epub 2008 Apr 22.

In a preferred embodiment of the present invention, it is intended to detect in real time adverse reactions in the health of patients, elderly people, and users with chronic diseases who have been discharged after receiving hospital treatment.

In another preferred embodiment of the present invention, it is intended to provide an emergency response system that automatically classifies the state of adverse reactions detected in the health of users, and responds quickly when the adverse reaction belongs to a dangerous or emergency state.

Another preferred embodiment of the present invention is to provide an emergency response system that quickly detects and responds to adverse health reactions during clinical trials by clinical research subjects.

In another preferred embodiment of the present invention, when environmental changes such as fine dust and air pollution occur, a health abnormality detection system that quickly detects and responds to users who have an abnormality in health is proposed.

In a preferred embodiment of the present invention, the server for automatically detecting adverse reactions is data obtained from at least one of a wearable device detachable to the user's skin, a user terminal, and a node capable of communicating with the wearable device or the terminal. A data collection unit that collects; An interviewer that presents a questionnaire to the user and receives the user's questionnaire response information; And based on the collected data and the questionnaire response information, the stage of the adverse reaction that appears to the user is classified in real time and the past information is accumulated A health analysis unit that manages; In this case, the wearable device includes a device for measuring a biosignal in an invasive or non-invasive manner, and the terminal includes a camera, a display, a memory and a communication unit, and image data or audio data And an interface for transmitting/receiving, and the communication capable node includes a sensor capable of communicating with the wearable device or the terminal, a home-appliance, an imaging device including a CCTV, an ultrasonic detection unit, and an electromagnetic detection unit. It features.

As a preferred embodiment of the present invention, the health analysis unit uses at least one of the Health Insurance Corporation sample cohort database, patient treatment history database, meteorological database, atmospheric environment database data, or life log data for each user. A big data learning unit that additionally learns at least one of a region, a past diagnosis history, a past treatment type, a medication history, a fine dust concentration, a location, and the weather; and further including, by further reflecting the learning contents of the big data learning unit, the It is characterized in that the stage of the adverse reaction is classified in real time.

In a preferred embodiment of the present invention, the health analysis unit further comprises a notification unit for providing an alarm to at least one or more of a user, medical personnel, and emergency rescue personnel according to the stage of the adverse reaction classified in real time; It is characterized.

As a preferred embodiment of the present invention, the server stores the location of the wearable device attached to the user's skin, data acquired from the wearable device, or data acquired from the terminal to a location corresponding to the human body model displayed on the display. And a data providing unit for controlling the display and further displaying the amount of change in the data.

As a preferred embodiment of the present invention, the questionnaire includes a query on at least one of a skin abnormality type, a skin abnormality range, and accompanying symptoms accompanying a skin abnormality, and when inquiring about the skin abnormality type or the skin abnormality range The image input interface is activated to receive image data as the questionnaire response information of the user.

As a preferred embodiment of the present invention, when the image data is input, a two-dimensional or three-dimensional human body model is displayed on the display, and a selection interface is further provided to first select a position related to the image data in the human body model. It features.

As a preferred embodiment of the present invention, the display displays a two-dimensional or three-dimensional human body model, and when a user selects a specific area from the displayed human body model, the interviewer presents a questionnaire including a questionnaire related to the selected specific area. Characterized in that.

In another preferred embodiment of the present invention, a method of automatically detecting an adverse reaction is one of a wearable device detachable to the user's skin in the data collection unit, a user terminal, and a node capable of communicating with the wearable device or the terminal. Collecting data obtained from at least one; Presenting a questionnaire to the user by the interviewer and receiving the user's questionnaire response information; And, based on the collected data and the questionnaire response information from the health analysis unit, the stage of the adverse reaction that appears to the user is recorded in real time. Classifying and accumulating and managing past information; In this case, the wearable device includes a device that measures a biosignal in an invasive or non-invasive manner, and the terminal includes a camera, a display, a memory and a communication unit, and an image It has an interface for transmitting and receiving data or voice data, and the communication node is a sensor capable of communicating with the wearable device or the terminal, a home-appliance, an image capture device including a CCTV, an ultrasonic detection unit, and an electromagnetic field. It characterized in that it comprises at least one of the detection unit.

In a preferred embodiment of the present invention, adverse reactions appearing in the health of patients who have abnormal health or are discharged from hospital after receiving treatment, elderly people, and users with chronic diseases are detected in real time, and adverse reactions are detected in progress. According to this, it is classified as a grade, and in case of an emergency or emergency, it is effective for prompt response by medical staff.

In another preferred embodiment of the present invention, when an adverse reaction to health occurs during clinical trials of clinical research subjects, there is an effect of quickly coping with them to protect the health of clinical research subjects.

In another preferred embodiment of the present invention, when environmental changes such as fine dust and air pollution occur, users who have an abnormality in health are quickly detected and cope with it, thereby detecting in real time that an abnormality has occurred in health. have.

1 is a preferred embodiment of the present invention, showing the internal configuration of a server for automatically detecting an adverse reaction.
2 is a preferred embodiment of the present invention, showing a system diagram in which a server for automatically detecting an adverse reaction operates.
3 is a preferred embodiment of the present invention, and shows an example in which a user selects an image of an adverse reaction appearing on the skin and an abnormal skin type.
4 is a preferred embodiment of the present invention, showing an example of providing information by showing a human body model diagram on a user terminal and displaying at least one of a disease progression stage, a risk level, and a disease progression speed.
5 to 7 are preferred embodiments of the present invention, illustrating an embodiment in which question data is generated by a questionnaire and presented to a user terminal, and an example of a method for learning question data using a decision tree in the questionnaire. do.
8 is a flowchart illustrating a method of automatically detecting an adverse reaction according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE INVENTION The detailed description of the present invention to be described later refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in detail sufficient to enable those skilled in the art to practice the present invention. It is to be understood that the various embodiments of the present invention are different from each other, but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be changed from one embodiment to another and implemented without departing from the spirit and scope of the present invention. In addition, it should be understood that the positions or arrangements of individual elements in each embodiment may be changed without departing from the spirit and scope of the present invention. Therefore, the detailed description to be described below is not made in a limiting sense, and the scope of the present invention should be taken as encompassing the scope claimed by the claims of the claims and all scopes equivalent thereto. Like reference numerals in the drawings indicate the same or similar elements over several aspects.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to enable those skilled in the art to easily implement the present invention.

1 is a preferred embodiment of the present invention, showing the internal configuration of the server 100 for automatically detecting adverse reactions, Figure 2 is a system diagram in which the server 200 for automatically detecting adverse reactions operates (S200 ).

Servers 100 and 200 for automatically detecting adverse reactions will be described with reference to FIGS. 1 to 2.

The user terminal 230 disclosed in the present invention includes a user equipment (UE), a mobile equipment (ME), a mobile station (MS), a user terminal (UT), a subscriber station (SS), a mobile subscriber station (MSS), and a wireless device. (Wireless Device), portable device (Handheld Device), AT (Access Terminal), wearable device, robot, etc. are all included. Mobile phone, cellular phone, smart phone, PDA (Personal Digital Assistants), PMP ( Portable Multimedia Player), tablet device, computer, smart watch, CCTV, artificial intelligence speaker, home appliance or multimedia device. In addition, a terminal can be provided to and utilized by the patient and medical staff using cloud computing. In addition, as another embodiment of the present invention, the terminal 230 includes a camera, a display, a memory, and a communication unit, and may include an interface for transmitting and receiving image data or audio data.

The user terminal 230 may also download and install an application for automatically detecting an adverse reaction in the form of an app from the servers 100 and 200 to implement it. It should be noted that the servers 100 and 200 for automatically detecting adverse reactions disclosed in the present invention can be implemented in the form of the terminal described above.

As a preferred embodiment of the present invention, the servers 100 and 200 for automatically detecting adverse reactions include a self-medicine history database 211, a life logger database 212, an image processing server 213, a machine learning server 214, and a national Wired/wireless communication is possible with at least one of the devices 210 including the environment source database 215, the meteorological data database 216, and the health insurance spatial sample cohort database 217. In addition, when an emergency occurs, wired or wireless communication is possible with an emergency response device 220 including a call center server 221 to an emergency patient management server 222, and the like.

As a preferred embodiment of the present invention, the servers 100 and 200 for automatically detecting adverse reactions include a data collection unit 110, an interviewer 120, a health analysis unit 130, and a data providing unit 140. The questionnaire 120 includes a questionnaire providing unit 121, a questionnaire response receiving unit 123, a first machine learning unit 125, an image input interface activating unit 127, and a voice input interface activating unit 129. The health analysis unit 130 includes a big data learning unit 132, a second machine learning unit 134 and a notification unit 136.

Each component will be described.

The data collection unit 110 is implemented to collect data obtained from at least one of a wearable device detachable to the user's skin, a user terminal, and the wearable device or a node capable of communicating with the terminal.

Wearable devices detachable to the user's skin include a biometric information measuring device that measures a biosignal invasively or non-invasively. The biometric information measuring device includes a sensor or device that measures biometric information including pulse, blood pressure, and body temperature.

Each wearable device detachable to the user's skin may be assigned an identification number, and the data collected by each wearable device to which an identification number has been assigned is provided through the data providing unit 140 to correspond to the human body model diagram shown in FIG. It can be processed to be marked on the part that is being used. In addition, as in the embodiment shown in Fig. 4, the progression stages (410, 420, 430, 440, 450) of the disease, the risk level (414, 424), the progression speed of the disease (412, 422, 432, 442, for each body part) 452) can be displayed together. The method of displaying the disease progression stage (410, 420, 430, 440, 450), the risk level (414, 424), and the disease progression speed (412, 422, 432, 442, 452) is shown in FIG. In addition to the examples, various methods can be used.

A communication node includes a sensor capable of communicating with a wearable device or a terminal, a home-appliance, an imaging device including a CCTV, an ultrasonic detection unit, an electromagnetic detection unit, and the like. In addition, nodes capable of communication include objects to which a biometric information measurement sensor is attached. As an example, it may include a wheelchair, a human body transplant device, an imaging device for photographing a body temperature measurement image of an airport search desk.

The questionnaire 120 presents the questionnaire to the user through the questionnaire providing unit 121 and receives the user's questionnaire response information through the questionnaire response receiving unit 123.

As a preferred embodiment of the present invention, the questionnaire 120 manages the query data for each body part in the questionnaire providing unit 121, and is selected by the questionnaire providing unit 523 as in the embodiment shown in FIG. Query data may be displayed on the user terminal 520a.

The questionnaire providing unit 121 may perform machine learning through the first machine learning unit 125 and then select query data and display it on the user terminal 230. In this case, the first machine learning unit 125 may use a decision tree technique capable of classification and regression, as in the exemplary embodiment illustrated in FIG. 7. For details, refer to FIG. 7.

In the case where image data is requested in response to the query data as in the embodiment shown in FIG. 6 (FIGS. 6 and 621), the questionnaire providing unit 121 responds to the user through the image input interface activation unit 127 The image input interface 611 of the terminal transmitting the signal may be activated. Similarly, when voice data is requested for a response to the questionnaire data provided by the questionnaire providing unit 121, the voice input interface of the terminal through which the user transmits the questionnaire response can be activated through the voice input interface activation unit 129. have.

The questionnaire response receiving unit 123 receives a user's questionnaire response to the questionnaire data in the questionnaire provided by the questionnaire providing unit 121.

The health analysis unit 130 classifies in real time the stage of adverse reactions that appear to the user based on the data collected through the data collection unit 110 and the questionnaire response information obtained from the interviewer 120 and provides past information. Can be accumulated and managed. The severity or stage of symptoms can be classified as Grade1, Grade2, Grade3,,,, etc. In this case, machine learning may be performed through the second machine learning unit 134 and the weapons may be automatically classified according to the performed learning. In addition, when it exceeds a predetermined grade, an alarm may be provided to at least one of a user, a medical personnel, and an emergency rescuer through the notification unit 136 according to the stage of the adverse reaction. The second machine learning unit 134 uses algorithms such as DBN (Deep Belief Network), CNN (Convolutional Neural Network), and RNN (Recurrent Neural Network) used for data analysis and prediction, or various other machine learning algorithms. Can be used.

The health analysis unit 130 uses at least one of a sample cohort database of the Health Insurance Corporation, a patient treatment history database, a meteorological data database, an atmospheric environment database, or life log data through the big data learning unit 132 for each user's age. , Gender, residential area, past diagnosis history, past treatment type, medication history, fine dust concentration, location, and weather.

The health analysis unit 130 may also reflect the content learned through the big data learning unit 132 to reclassify the stage of the adverse reaction in real time. For example, in the case of analyzing the fine dust concentration and the user's life log data information, if the fine dust concentration is high at the time the user is walking, the stage of the adverse reaction of the user who has been sensational can be reclassified in real time.

3 is another preferred embodiment of the present invention, showing an example of displaying a human body model diagram showing an adverse reaction on a user terminal before presenting a questionnaire to the user.

A 2D or 3D human body model is displayed on the display of the user terminal, and the user can select a portion of the human body model that currently exhibits an adverse reaction. In this case, the interviewer presents a questionnaire including a paperweight related to a specific part selected by the user.

For example, when an adverse reaction occurs on the user's skin, the user selects the area where the adverse reaction occurs in the terminal as'skin', selects the area where the skin abnormality occurs in the body (311, 312, 313, 314), and selects Related images may be uploaded to at least one or more of the site. Also, a related symptom 330 that the user thinks may be selected in at least one or more of the selected region. Referring to FIG. 3, when a user selects the skin abnormal form 330 interface and the skin abnormal form 330 interface is selected, erythema 331, pigment change 332, bleeding 333, shingles 334 are listed. ) You can select at least one of the types of abnormal skin types. When the user uploads an image, the human body model diagram shown in the terminal may display the weight of the portion where the adverse reaction has occurred (310a).

FIG. 5 illustrates an example of generating question data in a questionnaire and an example of displaying the generated question data on a user terminal as a preferred embodiment of the present invention.

The user selects an adverse reaction that occurred to him in the terminal. Through the adverse reaction interface, it may be provided to the user as a list of skin 10, whole body 12, head 5, belly 8, chest 6, arms/legs 3, and the like.

When the user selects an adverse reaction of the skin 510a in the terminal and selects the adverse reaction 520a of'what happened to the skin' among the adverse reactions related to the abnormal reaction of the skin 510a, as a preferred embodiment of the present invention The questionnaire of the server that automatically detects adverse reactions selects a tab related to the skin 510 according to the user's selection, and selects question data necessary for the user through machine learning among the question data accumulated and managed in the corresponding tab. Present to the user in the form. In this case, the question data provided by the questionnaire of the server may be displayed in a user-friendly manner on the user terminal.

For example, the question data related to the adverse reaction 520 of'What happened to the skin' on the server is'When did the skin change occur?' (521),'Does anyone in your family have the same symptoms?' (522) ) Or'Do you have allergies?' (523), the first machine learning unit uses machine learning to'start when did your skin change?' (521) and'Do you have allergies?' (523) Among them, it is possible to learn to make a questionnaire by selecting only relevant question data. In this case, the first machine learning unit may further refer to the learning contents of the big data learning unit (FIGS. 1 and 132).

When the user answers the questionnaire '2 days ago' (521b) to the questionnaire'When did the skin change begin?' (521a), the questionnaire providing unit is based on the user's questionnaire response information through machine learning, and then (530) You can select the question data required for the interview.

6 shows an example in which question data provided by a questionnaire providing unit is displayed on a user terminal as a preferred embodiment of the present invention. When the user selects an adverse reaction related to the skin rash 610, the questionnaire providing unit allows the user to select the area where the skin rash has occurred, along with the question data,'Which part is the skin rash?' 620. Selection interfaces 622a, 622b, 622c, 622d may be displayed on the human body schematic 621. In addition, the questionnaire providing unit can control the image input interface unit of the user terminal to be activated with a guide message to the user, when the image data 611 is required,'Please upload the image of the selected area' 630. The user may upload a picture corresponding to the selected portion through the selection interfaces 622a, 622b, 622c, 622d in the human body model diagram 621.

7 is a preferred embodiment of the present invention, showing an embodiment using a decision tree technique capable of classification and regression by a machine learning method in the process of creating a questionnaire.

Question data 710 of the questionnaire includes essential question items. The required questionnaire includes information on the main complaint symptoms, aggravating factors, weakening factors, other Eastern symptoms, and the severity of symptoms. The severity of symptoms can be classified as Grade1, Grade2, Grade3,,,, etc.

In the process of preparing the questionnaire, the machine learning unit 740 asks whether the questionnaire response information x1 for the main complaint symptom exceeds a preset criterion c1 using a decision tree technique, etc. Classification is performed in such a manner as to ask whether the questionnaire response information x2 for the worsening factor exceeds the preset criterion c2 (740).

In the process of creating a questionnaire, the first machine learning unit 740 collects the user's answers to the essential question items 710 through the questionnaire response receiving unit 741, and the machine learning unit 742 uses a decision tree technique. After the machine learning is performed at, the data collected by the analysis unit 743 is analyzed. The analysis unit 743 may provide the analyzed data result to the remote server and the database 710a.

8 is a flowchart illustrating a method of automatically detecting an adverse reaction according to an embodiment of the present invention.

The data collection unit collects data acquired from at least one of a wearable device detachable to the user's skin, a user terminal, and a node capable of communicating with the wearable device or the terminal (S810). In this case, the communication method is short-range communication such as Bluetooth method, WiMAX method, Wi-fi method, ZigBee method, WBAN (Wireless Body Area Network) method, and MBAN (Medical Body Area Network) method. It includes all of the methods commonly used for communication of mobile communication terminals such as method, LTE method, LTE Advanced method, EV-DO method, Wibro method, HSPDA method, CDMA2000 method, GSM method, and WCDMA method.

The questionnaire unit presents the questionnaire including question data to the user, and receives questionnaire response information from the user (S820).

The health analysis unit classifies in real time a stage of adverse reactions that appeared to the user based on the data collected by the data collection unit and the questionnaire response information from the interviewer, and accumulates and manages the past information (S830). In this case, the past information includes all information related to the time when the adverse reaction occurred, the stage change of the adverse reaction over time, the type of the adverse reaction, and other adverse reactions. The health analysis department classifies the adverse reactions in real time, and when the stage of the adverse reaction is above a certain grade, it performs notification through the notification unit.

The apparatus described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices and components described in the embodiments are, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, such as one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to behave as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

As described above, although the embodiments have been described by the limited embodiments and drawings, various modifications and variations are possible from the above description by those of ordinary skill in the art. For example, the described techniques are performed in a different order from the described method, and/or components such as a system, structure, device, circuit, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and claims and equivalents fall within the scope of the claims to be described later.

Claims (10)

A data collection unit configured to collect data obtained from at least one of a wearable device detachable to the user's skin, a user terminal, and a node capable of communicating with the wearable device or the terminal;
An interviewer that presents a questionnaire including question data to a user, receives the user's questionnaire response information, performs machine learning based on the received questionnaire response information, and then selects question data necessary for the next questionnaire; And
Including; a health analysis unit for classifying the stage of the adverse reactions presented to the user in real time based on the collected data and the questionnaire response information and accumulating and managing past information; and
In this case, the wearable device includes a device that measures a biological signal in an invasive or non-invasive manner, and the terminal includes a camera, a display, a memory, and a communication unit, and includes an interface for transmitting and receiving image data or audio data, and the communication The possible node includes at least one of the wearable device or a sensor capable of communicating with the terminal, a home-appliance, an imaging device including a CCTV, an ultrasonic detection unit, and an electromagnetic detection unit. Server that automatically detects. The method of claim 1, wherein the health analysis unit
By using at least one of the Health Insurance Corporation sample cohort database, patient treatment history database, meteorological data database, air environment database data, or life log data for each user, age, gender, residential area, past diagnosis history, past treatment type, and medication history , A big data learning unit that additionally learns at least one of fine dust concentration, location, and weather; further comprising, and classifying the stage of the adverse reaction in real time by further reflecting the learning contents of the big data learning unit. Server that automatically detects adverse reactions. The method of claim 1, wherein the health analysis unit
A server for automatically detecting an abnormal reaction, further comprising: a notification unit for providing an alarm to at least one of a user, a medical person, and an emergency rescuer according to the stage of the abnormal reaction classified in real time. The method of claim 1,
Control to display the location of the wearable device attached to the user's skin, the data acquired from the wearable device, or the data acquired from the terminal at a location corresponding to the manikin diagram displayed on the display, and further display the amount of change in the data Server for automatically detecting an adverse reaction, characterized in that it further comprises a data providing unit. The method of claim 1,
The questionnaire includes a query for at least one of a form of a skin abnormality, a range of a skin abnormality, and accompanying symptoms associated with a skin abnormality, and activates an image input interface when inquiring about the shape of the skin abnormality or the range of the skin abnormality. Server for automatically detecting adverse reactions, characterized in that receiving image data as questionnaire response information. The method of claim 5, wherein when receiving the image data
A server for automatically detecting abnormal reactions, characterized in that: displaying a two-dimensional or three-dimensional human body model diagram on the display, and further activating a selection interface to first select a position related to the image data in the human body model view. The method of claim 1,
The display displays a two-dimensional or three-dimensional human body model, and when a user selects a specific part from the displayed human body model, the interviewer presents a questionnaire including a questionnaire related to the selected specific part. Server to detect. Collecting data obtained from at least one of a wearable device detachable to the user's skin, a user terminal, and the wearable device or a node capable of communicating with the terminal, in a data collection unit;
Presenting a questionnaire including question data to the user by the questionnaire, receiving the user's questionnaire response information, performing machine learning based on the received questionnaire response information, and selecting question data necessary for the next questionnaire; And
Including, in a health analysis unit, classifying a stage of an adverse reaction that appears to a user in real time based on the collected data and the questionnaire response information, and accumulating and managing past information; and
In this case, the wearable device includes a device that measures a biological signal in an invasive or non-invasive manner, and the terminal includes a camera, a display, a memory, and a communication unit, and includes an interface for transmitting and receiving image data or audio data, and the communication The possible node includes at least one of the wearable device or a sensor capable of communicating with the terminal, a home-appliance, an imaging device including a CCTV, an ultrasonic detection unit, and an electromagnetic detection unit. How to automatically detect. The method of claim 8,
In the process of preparing the questionnaire, the interviewer performs machine learning using a decision tree technique, and in this process, the root node asks whether the questionnaire response information x1 for the main complaint exceeds a preset criterion c1, and exceeds In the case, a method for automatically detecting adverse reactions, characterized in that the questionnaire data is selected by performing classification in a manner asking whether the questionnaire response information x2 for the worsening factor in the middle node exceeds a preset criterion c2. A data collection unit configured to collect data obtained from at least one of a wearable device detachable to the user's skin, a user terminal, and a node capable of communicating with the wearable device or the terminal;
An interviewer that presents a questionnaire including question data to a user, receives the user's questionnaire response information, performs machine learning based on the received questionnaire response information, and then selects question data necessary for the next questionnaire; And
A health analysis unit for classifying the stage of adverse reactions presented to the user in real time based on the collected data and the questionnaire response information and accumulating and managing past information; and automatically detecting adverse reactions comprising: terminal.

Images