KR102576911B1 - Apparatus and method for providing health care services to users - Google Patents

Abstract

This disclosure relates to a system that provides health care services to users. According to the present disclosure, a method of operating a health management device includes obtaining user information about the user's personal information and constitution, obtaining health information of the user, and using the health information to determine a health subregion of the user. Determining a similar user with high similarity to the user from the health information and the user information using an artificial neural network, Considering the similar user and the health sub-area, determining a health recommendation program and transmitting recommendation information regarding the health recommendation program to the manager terminal.

Description

Apparatus and method for providing health care services to users {APPARATUS AND METHOD FOR PROVIDING HEALTH CARE SERVICES TO USERS}

This disclosure relates to a health care system that provides health care services to users. More specifically, it uses an artificial neural network to identify similar users with similar tendencies to the user and to provide health information that has been effective in improving the health functions of similar users. It relates to an apparatus and method for recommending a promotion program to a user.

As human lifespans are extended and living a healthy life has become an important part of living a happy life, individuals and countries are investing a lot of money and time in human health care. Recently, with the development of ubiquitous technology that allows services to be used anytime, anywhere, research is actively being conducted on technologies that allow users to receive health-related services in their home office or while on the move, rather than in a specific location where health care services are provided. It is becoming. In other words, the health management system is operated in such a way that users measure their health status through various health-related devices in their living space, and health managers provide health management feedback to users based on information about the user's health status. .

According to a conventional health management system, a health manager receives health information about health status, directly analyzes the health information, and provides a customized health recommendation program to the user. In other words, the health manager determined the health recommendation program to be provided to the user by referring to his or her knowledge and experience, and the recommendation program provided to the user could vary depending on the health manager's decision. Accordingly, there was a problem in which the health manager could not provide an appropriate health promotion program to the user if the health manager was unable to consider the user's identity or constitution or could not accurately determine the user's health status. In response to this, recently, in order to improve the effectiveness of health promotion programs for each user, there has been a need to develop technology for recommending optimal health promotion programs to users.

The above-mentioned technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and does not necessarily indicate known technology disclosed to the general public before filing the application for the present invention.

delete

Public Patent Publication No. 10-2014-0114157 (2014.09.26) Japanese Patent Publication No. 2007-072738 (2007.03.22.) Public Patent Publication No. 10-2009-0026967 (2009.03.16.)

Based on the above discussion, the present disclosure provides an apparatus and method for providing information regarding a health referral program in a health care system that provides health care services.

Additionally, the present disclosure provides an apparatus and method for determining a health sub-area necessary for improving the user's health using health information and determining a customized health recommendation program corresponding to the user's health sub-area.

Additionally, the present disclosure provides an apparatus and method for identifying similar users with similar tendencies to new users using an artificial neural network and providing a customized health recommendation program to new users using program recommendation results provided to similar users.

Additionally, the present disclosure provides an apparatus and method for accurately determining an optimal health recommendation program by accumulating and updating information on health recommendation programs determined to be effective for users based on an artificial neural network.

According to various embodiments of the present disclosure, a method of operating a health care device that provides health care services to a user includes obtaining user information about the user's personal information and constitution, obtaining health information of the user, Using health information, determining a health sub-area of the user; determining a similar user with a high degree of similarity to the user from the health information and the user information using an artificial neural network; A step of determining a health recommendation program in consideration of a health sub-area, and transmitting recommendation information about the health recommendation program to an administrator terminal, wherein the user information includes the user's socio-demographic information, constitution information, and stress information, wherein the health sub-domain includes an exercise domain, a nutritional domain, and a psychological domain, and the artificial neural network determines a correlation between the user's personal information, constitution, and health status and the similarity between users. May include a learned neural network.

According to another embodiment, the step of determining the similar users includes dividing elements included in the user information and the health information into nominal elements and numerical elements, using weights for each element of the nominal elements. Calculating a first similarity level between the user and candidate similar users, calculating a second similarity level between the user and the candidate similar users using element-specific weights of the numeric elements, Calculating similarity levels for each of the user and the candidate similar users based on the first similarity level and the second similarity level, and determining a first similar user based on priority according to the size of the similarity levels. The second similarity level includes a difference in element values between the user and the candidate similar user in a plurality of numeric elements, weights corresponding to each of the plurality of numeric elements, and the plurality of It can be determined based on the numerical range of the numeric elements.

According to another embodiment, after a health recommendation program is provided to the user, obtaining post-mortem health information of the user, comparing elements included in the post-mortem health information with elements included in the health information, identifying whether the health recommendation program is a valid program with respect to the user's health sub-area, and if the health recommendation program is identified as not being a valid program, determining a second similar user based on the priority; , determining an additional health recommendation program different from the health recommendation program in consideration of the second similar user and the health sub-area, and transmitting recommendation information regarding the additional health recommendation program to the manager terminal. there is.
According to another embodiment, when the health recommendation program is identified as a valid program, the step of updating the artificial neural network using the user information and the health information about the user as learning data may be further included. .

delete

Various respective aspects and features of the invention are defined in the appended claims. Combinations of the features of the dependent claims may be combined with the features of the independent claims as appropriate, not just those explicitly set out in the claims.

Additionally, one or more features selected from any one embodiment described in this disclosure may be combined with one or more features selected from any other embodiments described in this disclosure, and alternatives to these features may be used. A combination of the above may at least partially alleviate one or more technical problems discussed in this disclosure, or at least partially alleviate technical problems that can be discerned by a person skilled in the art from this disclosure, and further provide the features of the embodiments ( Unless such a particular combination or permutation of embodiment features is understood by those skilled in the art to be incompatible, the combination is possible.

In any described example implementation of this disclosure, two or more physically distinct components may alternatively be integrated into a single component if such integration is possible, so forming a single component. If the same function is performed by , integration is possible. Conversely, a single component of any embodiment described in this disclosure may alternatively, where appropriate, be implemented as two or more separate components that achieve the same functionality.

It is an object of certain embodiments of the present invention to solve, alleviate or eliminate, at least in part, at least one of the problems and/or disadvantages associated with the prior art. Certain embodiments aim to provide at least one of the advantages described below.

Apparatus and methods according to various embodiments of the present disclosure enable a health care system that provides health care services to provide information about a health recommendation program.

Additionally, the apparatus and method according to various embodiments of the present disclosure determine a health sub-area necessary for improving the user's health, thereby determining a customized health recommendation program corresponding to the user's health sub-area.

In addition, the apparatus and method according to various embodiments of the present disclosure identify similar users with similar tendencies as the new user and use the program recommendation results provided to the similar users, thereby providing a customized health recommendation program to the new user. .

In addition, the apparatus and method according to various embodiments of the present disclosure accumulate and update information about health recommendation programs determined to be effective for the user based on an artificial neural network, thereby enabling the user to accurately determine a health recommendation program customized to the user. do.

The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

The accompanying drawings, which are included as part of the detailed description to aid understanding of the embodiments, provide various embodiments and together with the detailed description describe technical features of the various embodiments.
1 illustrates a health care system that provides health care services to a user, according to various embodiments of the present disclosure.
FIG. 2 illustrates the configuration of a health management device in a health management system according to various embodiments of the present disclosure.
FIG. 3 illustrates a schematic diagram of a process in which a health management device trains an artificial neural network in a health management system according to various embodiments of the present disclosure.
FIG. 4 illustrates an example of user information and health information used by a health management device to determine similar users in a health management system according to various embodiments of the present disclosure.
FIG. 5 illustrates a flowchart of a method of operating a health management device in a health management system according to various embodiments of the present disclosure.
FIG. 6 illustrates a flowchart of a method by which a health management device determines a similar user in a health management system according to various embodiments of the present disclosure.
FIG. 7 illustrates a flowchart of a method by which a health management device updates an artificial neural network in a health management system according to various embodiments of the present disclosure.

Terms used in the present disclosure are merely used to describe specific embodiments and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by a person of ordinary skill in the technical field described in this disclosure. Among the terms used in this disclosure, terms defined in general dictionaries may be interpreted to have the same or similar meaning as the meaning they have in the context of related technology, and unless clearly defined in this disclosure, have an ideal or excessively formal meaning. It is not interpreted as In some cases, even terms defined in the present disclosure cannot be interpreted to exclude embodiments of the present disclosure.

In various embodiments of the present disclosure described below, a hardware approach method is explained as an example. However, since various embodiments of the present disclosure include technology using both hardware and software, the various embodiments of the present disclosure do not exclude software-based approaches.

Hereinafter, the present disclosure relates to an apparatus and method for determining a health recommendation program for health promotion in a health care system that provides health care services. Specifically, this disclosure describes a technology for identifying similar users with similar tendencies to users using an artificial neural network in a health management system and recommending health promotion programs that have been effective in improving the health functions of similar users.

Below, various embodiments will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement them. However, since the technical idea of the present disclosure can be modified and implemented in various forms, it is not limited to the embodiments described in this specification. In describing the embodiments disclosed in this specification, if it is determined that detailed description of related known technologies may obscure the gist of the technical idea of the present disclosure, detailed descriptions of the known technologies will be omitted. Identical or similar components will be assigned the same reference number and duplicate descriptions thereof will be omitted.

In this specification, when an element is described as being "connected" to another element, this includes not only the case of being "directly connected" but also the case of being "indirectly connected" with another element in between. When an element is said to “include” another element, this means that it does not exclude another element in addition to the other element, but may further include another element, unless specifically stated to the contrary.

Some embodiments may be described in terms of functional block configurations and various processing steps. Some or all of these functional blocks may be implemented as any number of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or may be implemented by circuit configurations for certain functions. Functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks of this disclosure may be implemented as algorithms running on one or more processors. Functions performed by a functional block in the present disclosure may be performed by a plurality of functional blocks, or functions performed by a plurality of functional blocks in the present disclosure may be performed by a single functional block. Additionally, the present disclosure may employ conventional technologies for electronic environment setup, signal processing, and/or data processing.

In addition, in the present disclosure, the expressions greater than or less than are used to determine whether a specific condition is satisfied or fulfilled, but this is only a description for expressing an example and excludes descriptions of more or less. It's not about doing it. Conditions written as ‘more than’ can be replaced with ‘more than’, conditions written as ‘less than’ can be replaced with ‘less than’, and conditions written as ‘more than and less than’ can be replaced with ‘greater than and less than’.

1 illustrates a health care system 100 that provides health care services to a user, according to various embodiments of the present disclosure.

The health management system 100 determines the user's condition from information about the user's health condition and provides alternative medicine to the user, thereby instructing a system that comprehensively manages the user's health. According to the health management system 100, the user can transmit user information about the user's personal information and constitution and health information about the user's health status to the health manager. In response, the health manager can provide the user with a customized health recommendation program by considering the user information and health status. According to one embodiment of the present disclosure, the health management system 100 may include a user terminal 110, an administrator terminal 130, an emergency management server 150, a health management device 170, and a network 190. You can.

The user terminal 110 indicates a terminal used by a user in need of health care. The user terminal 110 may include a fixed terminal implemented as a computer device or a mobile terminal. According to an embodiment of the present disclosure, the user terminal 110 is a smart phone, a mobile phone, a navigation device, a computer, a laptop, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), and a tablet PC. can be instructed. The user terminal 110 may communicate with at least one of the manager terminal 130, the emergency management server 150, and the health management device 170 through the network 190 using a wireless or wired communication method. .

The administrator terminal 130 indicates the terminal used by the administrator providing health care services. The administrator terminal 130 may include a fixed terminal implemented as a computer device, such as the user terminal 110, or a mobile terminal. The administrator can check the user's health status using the administrator terminal 130. In addition, the manager terminal 130 may communicate with at least one of the user terminal 110 and the health management device 170 through the network 190, and may respond to a health recommendation program recommended by the health management device 170. You can receive information about it. The manager can use the manager terminal 130 to check the health recommendation program and provide the health recommendation program to the user.

The emergency management server 150 instructs a computer device or a device implemented with a plurality of computer devices that provides commands, codes, files, content, services, etc. by communicating through a network. The emergency management server 150 may include a database, and may use the database to store user information and health information about the user, or to store overall data for operating a health management system.

The health management device 170 directs a device that determines a user-customized health recommendation program. The health management device 170 may receive user information and health information from the user terminal 110 and determine a health recommendation program from the user information and health information. Specifically, the health management device 170 can use an artificial neural network to determine a similar user with a high degree of similarity to the user from user information and health information, and can determine the user's health sub-area using the health information. Thereafter, the health management device 170 may determine a user-customized health recommendation program by considering the health sub-area and similar users.

Here, the user information may include the user's sociodemographic information, physical constitution information, and stress information. According to an embodiment of the present disclosure, the sociodemographic information may include the user's age, gender, age, and educational background, and the constitutional information may include information indicating whether the user is a Taeyang person, a Taeeum person, a Soyang person, or a Soeum person. The stress information may include information indicating the level of stress at work and stress at home. The user may input the user's sociodemographic information, physical constitution information, and stress information into the user terminal 110 through a questionnaire test.

Health subdomains may include exercise domain, nutrition domain, and psychological domain. The health sub-area may be divided into an exercise area, a nutritional area, and a psychological area, and the health management device 170 may determine the health sub-area that is the biggest factor in the decline in the user's health from the user information and health information. Additionally, the health recommendation program may include various health promotion programs divided by health sub-area. To improve health in the exercise area, the health recommendation program may include rehabilitation exercise recommendation therapy and hand healing therapy. Here, hand healing therapy may include massage therapy such as aroma, meridian, sports, or Thai. To promote health in the area of nutrition, a health recommendation program may include a program that provides nutritional supplements containing missing nutrients. To promote health in the psychological area, health referral programs may include psychotherapy therapy. Here, psychotherapy may include music therapy, art therapy, laughter therapy, meditation therapy, and storytelling therapy.

The user terminal 110 can receive user information and obtain health information through a survey. The user terminal 110 may transmit the acquired user information and health information to the health management device 170. In response, the health management device 170 may determine the health sub-area and similar users from the user information and health information, and determine a health recommendation program by considering the health sub-area and similar users. Thereafter, the health management device 170 may transmit information about the health recommendation program to the manager terminal 130. The manager can check the health recommendation program through the manager terminal 130 and provide the health recommendation program to the user.

As shown in FIG. 1 , components of the health care system 100 may be connected through a network 190 . According to an embodiment of the present disclosure, the network 190 refers to a connection structure capable of exchanging information between nodes such as a plurality of terminals and servers. Examples of such networks include RF, 3GPP (3rd generation partnership project) network, LTE (long term evolution) network, 5GPP (5th generation partnership project) network, WIMAX (world interoperability for microwave access) network, Internet, LAN (local area network), Wireless LAN (wireless local area) network), WAN (wide area network), PAN (personal area network), Bluetooth network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (digital multimedia broadcasting) network, etc., but are not limited thereto. .

FIG. 2 illustrates a configuration 200 of a health management device 170 in a health management system 100 according to various embodiments of the present disclosure. Terms such as '... unit' and '... unit' used hereinafter refer to a unit that processes at least one function or operation, which can be implemented through hardware, software, or a combination of hardware and software. there is. The health management device 170 may include a memory 210, a processor 220, a communication unit 230, an input/output interface 240, and a display unit 250.

The memory 210 temporarily or permanently stores data such as basic programs, applications, and setting information for the operation of the health management device 170. The memory 210 may include a non-permanent mass storage device such as random access memory (RAM), read only memory (ROM), and a disk drive, but the present invention is not limited thereto. These software components may be loaded from a computer-readable recording medium separate from the memory 210 using a drive mechanism. Such separate computer-readable recording media may include computer-readable recording media such as floppy drives, disks, tapes, DVD/CD-ROM drives, and memory cards. Depending on the embodiment, software components may be loaded into the memory 210 through the communication unit 230 rather than a computer-readable recording medium. Additionally, the memory 210 may provide stored data upon request from the processor 220. According to an embodiment of the present disclosure, the memory 210 may store user information and health information regarding the user's personal information and constitution. Additionally, the memory 210 may store a health sub-area and a health recommendation program for each of the health sub-areas.

The processor 220 controls overall operations of the health management device 170. For example, the processor 220 may control signals to be transmitted and received through the communication unit 230. Additionally, the processor 220 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Commands may be provided to the processor 220 by the memory 210 or the communication unit 230. For example, processor 220 may be configured to execute received instructions according to program code stored in a recording device such as memory 210. For example, the processor 220 may control the health management device 170 to perform operations according to various embodiments described later. According to an embodiment of the present disclosure, the processor 220 acquires user information about the user's personal information and constitution, obtains the user's health information, and uses the health information to determine the user's health sub-area, Using an artificial neural network, similar users with the highest degree of similarity to the user are determined from health information and user information, considering similar users and health sub-areas, determining a health recommendation program, and providing recommendation information regarding the health recommendation program. It can be controlled to transmit to the administrator terminal that manages the user's health.

The communication unit 230 performs functions for transmitting and receiving signals through a wireless channel. All or part of the communication unit 230 may be referred to as a transmitting unit, a receiving unit, or a transmitting/receiving unit. The communication unit 230 may provide a function for the health management device 170 and at least one other node to communicate with each other through a communication network. According to an embodiment of the present disclosure, when the processor 220 of the health management device 170 generates a request signal according to a program code stored in a recording device such as the memory 210, the request signal is transmitted to the communication unit 230. Depending on the control, it may be transmitted to at least one other node through a communication network. Conversely, control signals, commands, content, files, etc. provided under the control of a processor of at least one other node may be received by the health management device 170 through the communication unit 230. According to an embodiment of the present disclosure, the communication unit 230 may receive user information and health information. Additionally, the communication unit 230 may transmit information about the health recommendation program to the manager terminal 130.

The input/output interface 240 may be a means for interfacing with an input/output device (not shown). At this time, the input device may be, for example, a device such as a keyboard or mouse, and the output device may be provided in the form of a device such as a display unit for displaying images. As another example, the input/output interface 240 may be a means for interfacing with a device that integrates input and output functions, such as a touch screen. Specifically, the processor 220 of the health management device 170 processes the commands of the computer program loaded in the memory 210, and displays a service screen or content constructed using data provided by the server through the input/output interface 240. It can be displayed on the display through . According to an embodiment of the present disclosure, the input/output interface 240 may include means for interfacing with the display unit 250. The input/output interface 240 may receive a user input for a web browsing window displayed on the display unit 250, and output data to be output through the display unit 250 in response to the above-described user input from the processor 220. It can be delivered. According to an embodiment of the present disclosure, the input/output interface 240 may receive information about the user's personal information and constitution directly from the user.

The display unit 250 indicates a display module including one or more displays. Each of the one or more displays included in the display unit 250 may individually display independent content, and the one or more displays described above may be combined to display a single content. According to an embodiment of the present disclosure, one or more displays included in the display unit 250 may include multiple physically separated displays, or may be multiple physically combined displays, and one screen may be divided and used. It may be a display that can be used. According to an embodiment of the present disclosure, the display unit 250 may display the decision result of the health recommendation program on the display.

FIG. 3 illustrates a schematic diagram 300 of a process in which the health management device 170 trains an artificial neural network in the health management system 100 according to various embodiments of the present disclosure. The health management device 170 may be implemented with an artificial neural network model structure, and the artificial neural network 320 may be trained to determine similar users with similar tendencies to the user from user information and health information.

The health management device 170 may use the artificial neural network 320 to determine similar users with similar tendencies to the user from user information and health information. That is, the health management device 170 may store information on the personal information, constitution, and health status of each of a plurality of users, and the similarity with the newly entered user may be calculated using the artificial neural network 320. Highly similar users can be determined. Here, the artificial neural network 320 may instruct an artificial neural network that has learned the similarity between the users' personal information, constitution, and health status and the users.

The learning input data 310 may indicate data including user information 311 and health information 313 regarding the user's personal information and constitution for each of a plurality of users. The learning input data 310 may include user information and health information for each of a plurality of users, and may be input to the artificial neural network 320.
The artificial neural network 320 may include an input layer 321, at least one hidden layer 323, and an output layer 325. The learning input data 310 is input to the input layer 321 of the artificial neural network 320, passes through at least one hidden layer 323, and the output layer 325, and is output as an output vector indicating similar users. You can. Output vectors for similar users may be input to a loss function layer (not shown) for similarity connected to the output layer 325. For example, the loss function layer for similarity can output a loss value for the purpose using a loss function that compares the output vector for similar users and the correct answer vector for each learning data. For example, the parameters of the artificial neural network 320 may be learned in a direction that reduces the loss value for similar users.

delete

The health management device 170 may use the artificial neural network 320 to determine a similar user with a high degree of similarity to the user from user information and health information. Specifically, the health management device 170 divides the elements included in the user information and health information into nominal elements and numerical elements, calculates the first similarity level between the user and candidate similar users from the nominal elements, and , a second similarity level between the user and candidate similar users can be calculated from the numeric element. Thereafter, the health management device 170 adds the first similarity level and the second similarity level, calculates similarity levels for each user and candidate similar users, and determines the user and tendency based on priority according to the size of the similarity levels. Similar similar users can be determined.

Here, the artificial neural network 320 may receive user information and health information and update weights corresponding to each of the elements included in the user information and health information. That is, the artificial neural network 320 updates the weight corresponding to each element and can change the proportion of elements that affect the judgment of similarity between users. Accordingly, the artificial neural network 320 can learn the correlation between the user's personal information, constitution, and health status and the similarity between users.

FIG. 4 illustrates an example 400 of user information and health information used by the health management device 170 to determine similar users in the health management system 100 according to various embodiments of the present disclosure.

Referring to FIG. 4, the artificial neural network 320 of the health management device 170 may divide elements included in user information into nominal elements and numerical elements. In the same way, the health management device 170 may divide elements included in health information into nominal elements and numerical elements. Specifically, the health management device 170 classifies gender, marital status, and religious status as nominal factors, and provides numerical values for blood viscosity, intestinal enzymes, fatty liver, osteoclasts, vitamin A, cerebrovascular disease, intestinal bacteria, and fracture incidence. It can be classified into type elements. Figure 4 illustrates part of the user information and health information for convenience of explanation, but all elements included in the user information and health information can be divided into nominal elements and numerical elements and can be used to determine correlation. .

The artificial neural network 320 of the health care device 170 calculates the first similarity level from the nominal elements. The health management device 170 may calculate the first similarity level between the user and pre-stored candidate similar users using the weight of each element of the nominal element. When the existing user is assumed to be the i-th user and the new user is assumed to be the j-th user, the health management device 170 determines that the element value of the k-th element of the i-th user and the element value of the k-th element of the j-th user are If there is a match, 0 is assigned to the element, and the similarity level for each element can be determined by applying a weight to the mismatched elements. Specifically, the first similarity level in the nominal element may be determined based on <Equation 1>.

Referring to <Equation 1>, i is the pre-stored user number, j is the user number, d _ijk is the similarity between user i and user j in the kth nominal element, x is the element value, w _k may indicate the weight corresponding to the kth nominal element. Thereafter, the health management device 170 may calculate the first similarity level by adding the similarities for each element.

The artificial neural network 320 of the health management device 170 calculates the second similarity level from the numeric elements. The health management device 170 may calculate a second similarity level between the user and a plurality of similar users using the weight of each element of the numeric element. The health management device 170 may determine the similarity level by applying a weight and an element range to the difference between the element value of the m-th element of the i-th user and the element value of the m-th element of the j-th user. Specifically, the second similarity level in the numeric element may be determined based on <Equation 2>.

Referring to <Equation 2>, i is the pre-stored user number, j is the user number, d _ijm is the similarity between the i user and the j user in the m th numeric element, and V is the m th numeric element. In the element value, w _m is the weight corresponding to the m-th numeric element, and R _m can indicate the numerical range of the m-th numeric element value. Thereafter, the health management device 170 may calculate a second similarity level by adding the similarities for each element.

The health management device 170 may calculate similarity levels for each user and candidate similar users based on the first similarity level and the second similarity level, and determine similar users based on priority according to the size of the similarity levels. there is. The health management device 170 may determine the similarity level between each of the pre-stored users and the new user, and determine that the smaller the similarity level, the higher the similarity. The health management device 170 may determine similar users to have higher priority as the size of the similarity level decreases.

Figure 4 illustrates a method of calculating similarity levels between a new user and users A to User C and determining a similar user when users A to User C are stored in advance and user information and health information about the new user are input. .

Referring to Figure 4, health management device 170 can determine the level of similarity between users and new users using three nominal factors. According to an embodiment of the present disclosure, the health management device 170 may determine initial weights for gender, marital status, and religious status to all be 0.7. Accordingly, the first similarity level between the new user and user A is determined to be 0, the first similarity level between the new user and user B is determined to be 0.7, and the first similarity level between the new user and user C is determined to be 1.4. can be decided.

The health management device 170 can determine the level of similarity between users and new users using eight numeric elements. According to one embodiment of the present disclosure, the health management device 170 sets the initial weights of blood viscosity, intestinal enzymes, fatty liver, osteoclasts, vitamin A, cerebrovascular, intestinal bacteria, and fracture severity to 2, 1.2, and 1, respectively. It can be set to 0.9, 1, 2, 0.5, or 1. Additionally, the health management device 170 may determine the numerical range of the element value by considering the normal value of each element. Specifically, the health management device 170 may determine the numerical range of the element value to be 17 because the normal range of blood viscosity is 48 to 65. In the same way, the health management device 170 determines the numerical range of the element value to be 6 because the normal range of intestinal enzymes is 59-65, and determines the numerical range of the element value to be 0.33 because the normal range of fatty liver is 0.09 to 0.42. Since the normal range of osteoclasts is 86 to 180, the numerical range of the urea value was determined to be 94, and since the normal range of vitamin A is 0.34 to 0.41, the numerical range of the urea value was determined to be 0.07, and the normal range of cerebrovascular accident was determined to be 0.07. Since it is 0.7 to 1.9, the numerical range of the element value is determined to be 1.2. Since the normal range of intestinal bacteria is 1.7 to 2.5, the numerical range of the element value is determined to be 0.9. Since the normal range of fracture severity is 0.04 to 0.16, the numerical range of the element value is determined to be 1.2. The numerical range can be determined to be 0.12. Accordingly, the health management device 170 determines the second similarity level between the new user and user A to be 1.01, the second similarity level between the new user and user B to 2.48, and the second similarity level between the new user and user C to be 2.48. The second similarity level can be determined to be 3.56.

The health management device 170 may finally determine a similarity level corresponding to each similar user by adding the first similarity level and the second similarity level. In FIG. 4, the health management device 170 may determine the similarity level with user A as 1.01, the similarity level with user B as 3.18, and the similarity level with user C as 4.96.

The health management device 170 may determine similar users using similarity levels. Since the smaller the similarity level, the higher the similarity with the new user, the health management device 170 may determine user A with the lowest similarity level as the similar user.

Referring to FIG. 4, the health management device 170 determines similar users using an artificial neural network, determines a health recommendation program by considering similar users and health sub-areas, and transmits information about the health recommendation program to the manager. can do.

Thereafter, after the health recommendation program is provided to the user, the health management device 170 may obtain post-mortem health information from the user, compare the post-mortem health information with the health information, and update the artificial neural network by changing the weights of each element. You can do it. Specifically, the health management device 170 may compare health information and post-health information to identify whether the health recommendation program is an effective program with respect to the user's health sub-area. If the health recommendation program is identified as a valid program, the health management device 170 may update the artificial neural network 320 by updating the weights for each element based on user information and health information. On the other hand, if the health management device 170 determines that the health recommendation program is not a valid program, the health management device 170 may determine an additional health recommendation program based on priority and check the effect of using the additional health recommendation program. The health management device 170 may check whether the additional health recommendation program is a valid program, and if the additional health recommendation program is a valid program, update the artificial neural network 320 based on user information and post-health information.

FIG. 5 illustrates a flowchart 500 of a method of operating the health management device 170 in the health management system 100 according to various embodiments of the present disclosure. 5 illustrates how the health management device 170 operates using the processor 220.

Referring to FIG. 5 , in step 501, the health management device 170 obtains user information regarding the user's personal information and constitution. The user terminal 110 can obtain information about the user's personal information and constitution through a questionnaire, and the health management device 170 can receive the user information from the user terminal. According to an embodiment of the present disclosure, user information may include the user's sociodemographic information, physical constitution information, and stress information.

In step 503, the health management device 170 obtains the user's health information. Users can measure health information using a terminal equipped with a health analysis function. In response, the health management device 170 may obtain health information regarding the user's health status.

At step 505, the health management device 170 uses the health information to determine the user's health sub-region. The health management device 170 may check the health status included in the health information and determine the health sub-area that has the greatest impact on the user's health. According to one embodiment of the present disclosure, the health sub-domain may include an exercise domain, a nutrition domain, and a psychological domain.

In step 507, the health management device 170 uses an artificial neural network to determine a similar user with a high degree of similarity to the user from health information and user information. The health management device 170 may receive user information and health information using an artificial neural network, compare elements included in the user information and health information, and determine similar users with similar tendencies to the user. According to an embodiment of the present disclosure, the artificial neural network may include a neural network that learns the correlation between the user's personal information, constitution, and health status and the similarity between users.

In step 509, the health management device 170 determines a health recommendation program considering similar users and health sub-areas. The health management device 170 may determine a health promotion program confirmed to be effective in the health sub-area of similar users as a health recommendation program.

In step 511, the health management device 170 transmits recommendation information regarding the health recommendation program to the manager terminal. According to an embodiment of the present disclosure, the health management device 170 may transmit information about a health recommendation program to the manager terminal 130 so that the manager can provide the health recommendation program to the user.

FIG. 6 illustrates a flowchart 600 of a method by which the health management device 170 determines similar users in the health management system 100 according to various embodiments of the present disclosure. Figure 6 illustrates how the health management device 170 operates using the processor 220.

Referring to FIG. 6, in step 601, the health management device 170 divides elements included in user information and health information into nominal elements and numerical elements. The health management device 170 can integrate user information and health information, and divide elements included in the user information and health information into nominal elements and numerical elements.

In step 603, the health management device 170 calculates a first similarity level between the user and candidate similar users using the element-specific weight of the nominal element. The health management device 170 may apply element-specific weights to element values in nominal elements. According to an embodiment of the present disclosure, the health management device 170 may calculate a first similarity level indicating the nominal element similarity between a new user and a similar user based on <Equation 1>.

In step 605, the health management device 170 calculates a second similarity level between the user and candidate similar users using the element-specific weight of the numeric element. The health management device 170 may apply element-specific weights to element values in numeric elements. According to an embodiment of the present disclosure, the health management device 170 may calculate a second similarity level indicating the similarity of numerical elements between a new user and a similar user based on Equation 2.

According to an embodiment of the present disclosure, the second similarity level is the difference in element values between the user and the candidate similar user in the plurality of numeric elements, the weights corresponding to each of the plurality of numeric elements, and the plurality of numeric elements. It can be determined based on the numerical range of the elements.

In step 607, the health management device 170 calculates similarity levels for each of the user and candidate similar users based on the first similarity level and the second similarity level. According to an embodiment of the present disclosure, the health management device 170 may determine the similarity level by adding the first similarity level and the second similarity level.

In step 609, the health management device 170 determines similar users based on priority according to the size of similarity levels. The health management device 170 may determine that the smaller the similarity level, the higher the similarity between users. Accordingly, the health management device 170 can determine priorities in descending order of similarity level and determine similar users based on the priorities.

FIG. 7 illustrates a flowchart 700 of a method by which the health management device 170 updates the artificial neural network 320 in the health management system 100 according to various embodiments of the present disclosure. Figure 7 illustrates how the health management device 170 operates using the processor 220.

Referring to FIG. 7, in step 701, the health management device 170 obtains the user's post-mortem health information. The administrator can provide a health recommendation program to the user, and the user can measure the health status after receiving the health recommendation program. In response, the health management device 170 may obtain post-mortem health information.

At step 703, the health management device 170 identifies whether the health recommendation program is a valid program. The health management device 170 may identify whether the health recommendation program is an effective program with respect to the user's health sub-area by comparing the elements included in the post-mortem health information with the elements included in the health information. According to an embodiment of the present disclosure, when the health recommendation program is identified as a valid program, the health management device 170 may update the artificial neural network using user information and health information as learning input data. According to another embodiment of the present disclosure, if the health management device 170 identifies that the health recommendation program is not a valid program, it may proceed to step 705 and determine other similar users based on priority.

At step 705, healthcare device 170 determines other similar users based on priority. The health management device 170 may check the priority determined using an artificial neural network and determine the next similar user as another new similar user.

At step 707, the health management device 170 determines an additional health recommendation program that is different from the health recommendation program considering other similar users and health sub-areas. The health management device 170 may determine a health promotion program found to be effective in the health sub-area of other similar users as an additional health recommendation program.

In step 709, the health management device 170 transmits recommendation information regarding an additional health recommendation program to the manager terminal. According to an embodiment of the present disclosure, the health management device 170 may transmit information about an additional health recommendation program to the manager terminal 130 so that the manager can provide an additional health recommendation program to the user.

At step 711, health management device 170 identifies whether the additional health recommendation program is a valid program. Users can receive additional health recommendation programs and measure new health information. Accordingly, the health management device 170 can determine whether the additional health recommendation program is a valid program by comparing the new health information and the post-mortem health information. According to an embodiment of the present disclosure, when the additional health recommendation program is identified as a valid program, the health management device 170 may update the artificial neural network using user information and additional health information as learning data.

At step 713, health care device 170 updates the artificial neural network. According to an embodiment of the present disclosure, when the health recommendation program is identified as a valid program, the health management device 170 may update the artificial neural network using user information and health information as learning data. According to another embodiment of the present disclosure, when the additional health recommendation program is identified as a valid program, the health management device 170 may update the artificial neural network using user information and post-health information as learning data.

Methods according to embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

When implemented as software, a computer-readable storage medium that stores one or more programs (software modules) may be provided. One or more programs stored in a computer-readable storage medium are configured to be executable by one or more processors in an electronic device (configured for execution). One or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.

These programs (software modules, software) include random access memory, non-volatile memory including flash memory, read only memory (ROM), and electrically erasable programmable ROM. (electrically erasable programmable read only memory, EEPROM), magnetic disc storage device, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other types of disk storage. It can be stored in an optical storage device or magnetic cassette. Alternatively, it may be stored in a memory consisting of a combination of some or all of these. Additionally, multiple configuration memories may be included.

In addition, the program may be distributed through a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), or a storage area network (SAN), or a combination thereof. It may be stored on an attachable storage device that is accessible. This storage device can be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to the device performing an embodiment of the present disclosure.

In the specific embodiments of the present disclosure described above, elements included in the disclosure are expressed in singular or plural numbers depending on the specific embodiment presented. However, singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components, and even components expressed in plural may be composed of singular or singular. Even expressed components may be composed of plural elements.

Meanwhile, in the detailed description of the present disclosure, specific embodiments have been described, but of course, various modifications are possible without departing from the scope of the present disclosure. Therefore, the scope of the present disclosure should not be limited to the described embodiments, but should be determined not only by the scope of the patent claims described later, but also by the scope of this patent claim and equivalents.

110 User terminal 130 Administrator terminal
150 Emergency Management Servers 170 Healthcare Devices
190 Network 210 Memory
220 Processor 230 Communication Department
240 input/output interface 250 display unit
310 training input data 320 artificial neural network
311 User Information 313 Health Information
321 Input Layer 323 Hidden Layer
325 output layer

Claims (4)

In a method of operating a health care device that provides health care services to a user,
Obtaining user information about the user's identity and constitution;
Obtaining health information of the user;
Using the health information, determining a health sub-area of the user;
Using an artificial neural network, determining a similar user with the highest degree of similarity to the user from the health information and the user information;
determining a health recommendation program in consideration of the similar users and the health sub-area; and
A step of transmitting recommendation information regarding the health recommendation program to an administrator terminal,
The step of determining the similar users is,
Classifying elements included in the user information and the health information into nominal elements and numerical elements;
calculating a first similarity level between the user and candidate similar users using weights for each element of the nominal element;
calculating a second similarity level between the user and the candidate similar users using a weight for each element of the numeric element;
calculating similarity levels for each of the user and the candidate similar users based on the first similarity level and the second similarity level; and
A step of determining a first similar user based on priority according to the size of the similarity levels,
The second similarity level includes differences in element values between the user and the candidate similar user among the plurality of numeric elements, weights corresponding to each of the plurality of numeric elements, and numerical ranges of the plurality of numeric elements. It is decided based on
The user information includes the user's sociodemographic information, constitutional information, and stress information,
The health sub-domain includes the exercise domain, nutritional domain, and psychological domain,
The artificial neural network includes a neural network that learns the correlation between the user's identity, constitution, and health status and the similarity between users,
The first similarity level is determined based on Equation 1,
(Equation 1)

Where i is the number of a candidate similar user, j is the number of the user, d _ijk is the similarity between user i and user j in the kth nominal element, x is the element value, w _k is the kth nominal element. Indicates the weight corresponding to the type element,
The second similarity level is determined based on Equation 2,
(Equation 2)

The d _ijm is the similarity between the i user and the j user in the mth numeric element, the V is the element value in the mth numeric element, the w _m is the weight corresponding to the mth numeric element, and the R _m is a method of indicating the numeric range of the mth numeric element value.
delete In claim 1,
After the health recommendation program is provided to the user,
Obtaining post-mortem health information of the user;
Comparing elements included in the post-health information with elements included in the health information, identifying whether the recommended health program is an effective program with respect to the health sub-area of the user; and
If the health recommendation program is identified as not a valid program, a second similar user is determined based on the priority, and an additional health recommendation different from the health recommendation program is made considering the second similar user and the health sub-area. The method further includes determining a program and transmitting recommendation information regarding the additional health recommendation program to the manager terminal.
In claim 3,
When the health recommendation program is identified as a valid program, the method further includes updating the artificial neural network using the user information and the health information about the user as learning data.