KR102170718B1 - User specialized hardware platform and operating method thereof, and manufacturing method thereof - Google Patents

Abstract

A user-specific hardware platform according to an embodiment of the present invention supplies power to a housing having at least one module for collecting biometric information data, a module receiving portion capable of mounting the module, and a module receiving portion mounted on the housing. The power supply unit to perform and store the machine learning algorithm learned based on the usage log input from the user, and apply the machine learning algorithm to the biometric information data collected from the at least one module to obtain a result value A machine learning unit capable of being transmitted to a device may be provided, and the at least one module may be selected from among a plurality of modules having different functions based on a user's state.

Description

User-specific hardware platform and its operation method, and user-specific hardware platform creation method {USER SPECIALIZED HARDWARE PLATFORM AND OPERATING METHOD THEREOF, AND MANUFACTURING METHOD THEREOF}

The present invention relates to a user-specific hardware platform that provides a customized service to a user, a method of operating the same, and a method of creating such a platform.

With the recent development of electronic technology, various technologies to help the self-reliance of vulnerable groups such as the elderly, dementia patients, the elderly living alone, the disabled, cancer patients undergoing treatment, and cancer cure patients are being introduced. In particular, the development of home IoT (internet of things) technology is being actively conducted. In home IoT technology, most devices directly recognize or communicate with voice, and smartphones as a platform and large telecommunication companies support this service.

However, most of the service models targeting the underprivileged are short-lived and have failed to settle in the market. The cause of this failure may be that the vulnerable class has difficulty in providing and maintaining the services that are practically necessary because the vulnerable class does not clearly recognize or express well the services they need. In addition, the cause of this failure may be that the vulnerable class has low learning ability and low adaptability and compliance of individual services considered as individual predictive demands. In other words, the service demand of the vulnerable group and the actual service utilization do not generally match, and the service demand and service satisfaction do not easily match.

In addition, as another cause of failure, the vulnerable group tends to deteriorate as time passes, so there is a possibility that demand for additional services will occur, and this demand must be quickly reflected. There may be a point of lack of alternatives.

Specifically, the physical and mental changes of the vulnerable group are fast and often worsen as time passes, and the service replacement cycle is short or there is a high probability of additional service demand. Even if there is no physical or environmental change of the vulnerable class, the demand for services is likely to change if the person who cares for the vulnerable class (e.g., caregiver) changes, or if the time of day and service provision level change. Products intended to provide services to vulnerable groups must quickly reflect such changing demands, but the existing service models lacked an alternative to this point.

In other words, the characteristics of the vulnerable group, for example, the service needs that the vulnerable group needs, and that these needs change rapidly, that the vulnerable group cannot use complex systems and smartphone apps, and also from the guardian side. Considering that management should be easy and maintenance costs should be inexpensive, a hardware platform that can be easily used by vulnerable groups and that guardians (administrators) can use is required.

Korean Patent Publication No. 10-2018-0109123 (published on October 08, 2018)

The problem to be solved by the present invention is to provide a user-specific hardware platform that is easy to use and takes into account the characteristics of a user, an operation method thereof, and a method of generating such a user-specific hardware platform.

However, the problems to be solved by the present invention are not limited as mentioned above, and are not mentioned, but include objects that can be clearly understood by those of ordinary skill in the art from the following description. can do.

A user-specific hardware platform according to an embodiment of the present invention supplies power to a housing having at least one module for collecting biometric information data, a module receiving portion capable of mounting the module, and a module receiving portion mounted on the housing. The power supply unit to perform and store the machine learning algorithm learned based on the usage log input from the user, and apply the machine learning algorithm to the biometric information data collected from the at least one module to obtain a result value A machine learning unit capable of being transmitted to a device may be provided, and the at least one module may be selected from among a plurality of modules having different functions based on a user's state.

In addition, the selection of the at least one module may be performed based on a result obtained by inputting a questionnaire result received through a questionnaire survey on the user's state into a module selection engine learned by deep learning. have.

In addition, the evaluation items of the above survey are: basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, elderly long-term care insurance evaluation items, economic conditions evaluation items, internet environment It includes at least one of an evaluation item and a household electronic product distribution evaluation item, and each of the at least one evaluation item is mapped to a positive or negative relationship to the at least one module, and the The score may be calculated according to the user's input for at least one evaluation item.

In addition, the at least one module may include a voice recognition module that recognizes the user's voice, a global positioning sensor (GPS) module that recognizes a location, and a home internet of things (IoT) control module that controls electronic devices installed in a specific place. , At least one of a parental call module that transmits a signal to request a parental call, an output module that provides information audibly or visually, a motion sensor module that detects motion, and a service request module that transmits a signal requesting a predetermined service. It can contain one.

In addition, the output module may output the result value or a countermeasure received from the external electronic device.

In addition, the machine learning unit may update the machine learning algorithm by learning based on the biometric information data and a response plan received from the external electronic device.

A method of operating a user-specific hardware platform according to an embodiment of the present invention includes the steps of collecting biometric information data using at least one module, and obtaining a result value by applying a machine learning algorithm to the collected biometric information data. And the at least one module may be selected based on a user's state from among a plurality of modules having different functions.

In addition, it may further include transmitting the obtained result value to an external electronic device.

In addition, the selection of the at least one module may be performed based on a result obtained by inputting a questionnaire result received through a questionnaire survey on the user's state into a module selection engine learned by deep learning. have.

In addition, the evaluation items of the above survey are: basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, elderly long-term care insurance evaluation items, economic conditions evaluation items, Internet It includes at least one of an environmental evaluation item and a household electronic product distribution evaluation item, and each of the at least one evaluation item is mapped to a positive or negative relationship to the at least one module, A score may be calculated according to the user's input for the at least one evaluation item.

In addition, the at least one module may include a voice recognition module that recognizes the user's voice, a global positioning sensor (GPS) module that recognizes a location, and a home internet of things (IoT) control module that controls electronic devices installed in a specific place. , At least one of a parental call module that transmits a signal to request a parental call, an output module that provides information audibly or visually, a motion sensor module that detects motion, and a service request module that transmits a signal requesting a predetermined service. It can contain one.

In addition, the output module may output the result value or a countermeasure received from an external electronic device.

In addition, the machine learning algorithm may be updated based on the biometric information data and a response plan received from the external electronic device.

A method of generating a user-specific hardware platform according to an embodiment of the present invention includes the steps of receiving an input of a questionnaire survey on a user's state and deriving a survey result, and using the survey result, a plurality of different functions Selecting at least one module based on the state of the user from among the modules of, and supplying power to the selected at least one module, a housing having a module receiving unit capable of mounting the module, and a module receiving unit mounted on the housing And generating a user-specific hardware platform including a power supply unit and a machine learning unit, wherein the at least one module collects biometric information data, and the machine learning unit is based on a usage log input from the user. The machine learning algorithm learned by is stored, and the machine learning algorithm may be applied to the biometric information data collected from the at least one module to obtain a result value and transmit it to an external electronic device.

In addition, the selecting may include selecting the at least one module as a result obtained by inputting the questionnaire result to a module selection engine learned by deep learning.

In addition, the evaluation items of the above survey are: basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, elderly long-term care insurance evaluation items, economic conditions evaluation items, Internet It includes at least one of an environmental evaluation item and a household electronic product distribution evaluation item, and each of the at least one evaluation item is mapped to a positive or negative relationship to the at least one module, A score may be calculated according to the user's input for the at least one evaluation item.

In addition, obtaining a usage log of the at least one module, assigning a weight to each of the evaluation items based on the obtained usage log, and applying the weight to the input of the obtained survey, It may include reselecting the at least one module.

In addition, the at least one module may include a voice recognition module that recognizes the user's voice, a global positioning sensor (GPS) module that recognizes a location, and a home internet of things (IoT) control module that controls electronic devices installed in a specific place. , At least one of a parental call module that transmits a signal to request a parental call, an output module that provides information audibly or visually, a motion sensor module that detects motion, and a service request module that transmits a signal requesting a predetermined service. It can contain one.

In addition, the machine learning unit may update the machine learning algorithm by learning based on the biometric information data and a response plan received from the external electronic device.

The user-specific hardware platform according to an embodiment of the present invention is easy to use, provides a service that satisfies user needs in consideration of the characteristics of the user, and can easily change the provided service when the user needs change. .

In addition, since the user-specific hardware platform according to the embodiment of the present invention is modular, it is not necessary to produce a complete platform for each user or whenever a user's needs are changed, and a module suitable for the user's needs is changed. It can be manufactured by making it possible to produce at low cost.

In addition, the user-specific hardware platform according to an embodiment of the present invention transmits the result value obtained by the machine learning algorithm to an external electronic device, thereby minimizing the communication load, protecting the user's privacy, and preventing the leakage of personal information. Can provide excellent performance in terms of security.

In addition, the user-specific hardware platform according to an embodiment of the present invention can utilize the result value obtained by the machine learning algorithm as feedback data for updating the machine learning algorithm, thereby minimizing data transmission for updating the machine learning algorithm. , Can reduce the communication load.

However, the effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description. I will be able to.

1 is a conceptual diagram illustrating a user-specific hardware platform according to an embodiment of the present invention.
2 illustrates an example for explaining a method of generating a user-specific hardware platform according to an embodiment of the present invention.
3 shows an example for explaining a method of reselecting a module included in a user-specific hardware platform according to an embodiment of the present invention.
4 shows another example for explaining a method of reselecting a module included in a user-specific hardware platform according to an embodiment of the present invention.
5 shows another example for explaining a method of reselecting a module included in a user-specific hardware platform according to an embodiment of the present invention.
6 is a functional block diagram of a user-specific hardware platform according to an embodiment of the present invention.
7 shows a flow of each step of a method of operating a user-specific hardware platform according to an embodiment of the present invention.
8 shows the flow of each step of a method of generating a user-specific hardware platform according to an embodiment of the present invention.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various forms, and only these embodiments make the disclosure of the present invention complete, and those skilled in the art to which the present invention pertains. It is provided to fully inform the person of the scope of the invention, and the scope of the invention is only defined by the claims.

In describing the embodiments of the present invention, detailed descriptions of known functions or configurations will be omitted except when actually necessary in describing the embodiments of the present invention. In addition, terms to be described later are terms defined in consideration of functions in an embodiment of the present invention, which may vary according to the intention or custom of users or operators. Therefore, the definition should be made based on the contents throughout this specification.

Since the present invention can make various changes and include various embodiments, specific embodiments will be illustrated in the drawings and described in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, and should be understood as including all changes, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms including an ordinal number such as first and second may be used to describe various elements, but the corresponding elements are not limited by these terms. These terms are only used for the purpose of distinguishing one component from another.

When a component is referred to as being'connected' or'connected' to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be.

1 is a conceptual diagram illustrating a user-specific hardware platform according to an embodiment of the present invention.

Referring to FIG. 1, the hardware platform 100 may include at least one module 110, a housing 120, and a machine learning unit 130. Each component of the hardware platform 100 may be implemented by hardware or software, or a combination of hardware and software.

At least one module 110 may collect biometric information data of a user of the hardware platform 100, but each may have different functions. For example, at least one module 110 is a voice recognition module that recognizes a user's voice of the hardware platform 100, a global positioning sensor (GPS) module that recognizes a location, and a home that controls electronic devices installed in a specific place. Internet of things (IoT) control module, a parental call module that transmits a signal to request a parental call, an output module that provides information audibly or visually, a motion sensor module that detects motion, a signal to request a predetermined service It may be at least one of the service request module that transmits.

At least one module 110 may be selected from among a plurality of modules based on a questionnaire result input through a questionnaire on a user's health status. Specifically, for example, at least one module 110 may be selected according to a result obtained by inputting a questionnaire result input through a questionnaire into a module selection engine learned by deep learning.

Meanwhile, in FIG. 1, at least one module 110 is composed of four modules, that is, a first module 111, a second module 112, a third module 113, and a fourth module 114. Although illustrated, the present invention is not limited thereto, and more or less than this number may be determined to be suitable for the user based on the survey result.

The module receiving portion of the housing 120 may be formed in the form of a plurality of compartments in which each of the at least one module 110 may be disposed. Accordingly, each of the at least one module 110 may be individually mounted on the module receiving unit.

The machine learning unit 130 may store a machine learning algorithm learned based on a usage log input from a user. In this case, the machine learning unit 130 may apply the machine learning algorithm to the biometric information data collected from at least one module 110 to obtain a result value and transmit it to an external electronic device.

Here, the external electronic device is a device that provides various services to a user, and may include, for example, a door lock and a cooling/heating device. For example, when an external electronic device is a door lock, the information transmitted to the external electronic device may be information that the user is located in front of the door to enter the house, and based on this information, the door lock is automatically unlocked to allow the user to You can easily get into the house.

Although not shown, the hardware platform 100 may further include a power supply unit, and the power supply unit may supply power to the module receiving unit so that power is transmitted to at least one module 110.

Meanwhile, the hardware platform 100 may have a size that is easy for a user to carry, for example, a size that can fit in a bag or a pocket included in clothes, but is not limited thereto.

Since the hardware platform 100 is a modular device, it is not necessary to manufacture a complete platform for each user or every time a user's needs are changed, and it can be manufactured by changing a module suitable for the user's needs, at low cost. Production is possible.

2 illustrates an example for explaining a method of generating a user-specific hardware platform according to an embodiment of the present invention. Specifically, FIG. 2 shows an example of a user's state determined through each evaluation item 10 of a questionnaire survey for determination of at least one module 110 and a module related to the evaluation item 10.

Referring to FIG. 2, the evaluation items 10 included in the questionnaire are, for example, basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, and the elderly. It may include at least one of a long-term care insurance evaluation item, an economic condition evaluation item, an Internet environment evaluation item, and a home electronic product distribution evaluation item. However, the evaluation items 10 included in the survey are not limited to the examples described above in this specification.

Although not shown, at least one questionnaire may exist for each evaluation item 10. For example, in the basic daily living ability evaluation items, there may be questionnaire questions on whether to walk or not and whether to cook.

According to the result of the questionnaire of the evaluation item 10, a plurality of related modules (eg, a voice recognition module, a GPS module) may be selected from the entire module group 20 as shown. Information on related modules may be previously stored for each questionnaire, and a plurality of related modules may be selected from the entire module group 20 accordingly.

In some cases, along with information on modules related to each questionnaire, weight information for each module reflecting service suitability, maintenance cost, user convenience, user health-medical benefits, etc. may be previously stored. These weights may have a positive value or a negative value. For example, if the relevance to a module previously stored as related to each questionnaire question is positive, it may have a positive value, and if the degree of relevance is negative, it may have a negative value.

After the survey is completed, information on at least one module most suitable for the user who conducted the survey may be provided based on the sum of weights. Information on at least one module may be provided in various ways, and for example, a list according to the priority of the weight score for each of the at least one module described above may be provided. As described above, at least one module related to the user may be determined as a result of the questionnaire among the entire module group 20, and the related description will be described in more detail with reference to FIGS. 3 to 5.

3 shows an example for explaining a method of reselecting a module included in a user-specific hardware platform according to an embodiment of the present invention. More specifically, FIG. 3 shows the relationship between each of the at least one module 110 selected through the process of FIG. 2 and a questionnaire question.

Referring to FIG. 3, each of the at least one module 110 may be positively or negatively related to each of the evaluation items 10 (or questionnaire items included in the evaluation item 10). More specifically, each of the at least one module 110 may be mapped to a positive score for a specific evaluation item according to the user's use, so that a positive score is assigned to a specific evaluation item, and mapped as a negative for other specific evaluation items. Negative scores can be assigned to other specific evaluation items. In this case, the positive score may be a score having a positive value, and the negative score may be a score having a negative value.

For example, when a voice recognition module is selected as one of the modules to be included in the hardware platform through the questionnaire according to FIG. 2 and mounted on the hardware platform, each time the voice recognition module is used by the user, the voice recognition module is mapped to the positive. A positive score is assigned to the questionnaire item, and a negative score may be assigned to the questionnaire item mapped to negative.

In some cases, when the number of times or frequency of use of a specific module increases, a use weight, which is a weight according to use, may be assigned to an item mapped as a positive or negative. Accordingly, a positive score or a negative score for a module having a high use frequency or a high frequency of use may be given in proportion to a use weight compared to a module with a low use frequency or a low use frequency. Here, the value of the use weight may be determined as the number of times of use or frequency of use increases, but is not limited thereto.

In this way, calculating the score for each evaluation item 10 (hereinafter,'item score') using the positive score (or negative score) and the weight used is by reflecting the user's status in the existing survey result, Although the re-examination was not performed, it can produce the same effect as the re-examination.

Although it will be described later in detail with reference to FIG. 5, by reflecting the item score calculated for each evaluation item 10 to the score of each module calculated for initial selection of at least one module, at least one reflecting the state of the user in real time. Modules can be reselected.

4 shows another example for explaining a method of reselecting a module included in a user-specific hardware platform according to an embodiment of the present invention. More specifically, FIG. 4 conceptually shows transmission and reception of data related to use when only some modules are used by a user among at least one module 110.

Among the at least one module 110 mounted on the hardware platform, a user may mainly use some modules. For example, FIG. 4 illustrates a case where a module mainly used by a user is a voice recognition module, a GPS module, a nursing home/caregiver call module, and a second home IoT control module. Each module may be related to at least some of the evaluation items 10 of the survey as described above.

According to FIG. 4, each of a voice recognition module, a GPS module, a nursing home/caregiver call module, and a second home IoT control module (hereinafter referred to as'use module') is machine learning data related to a user using the hardware platform 100. It can transmit and receive with the unit 130. The data related to the user may include, for example, whether the user uses the module, the frequency of the module use, and the user's biometric information data.

The machine learning unit 130 may store or analyze the acquired data to provide information on a countermeasure related to a user. The information on the countermeasure may be determined by the machine learning unit 130 by itself, or may be obtained from an external electronic device through communication with an external electronic device. For example, the machine learning unit 130 may recognize the user's voice through the voice recognition module and determine whether there is an emergency, and accordingly, provide data to request a parental call to the parental call module, Can be called.

The machine learning unit 130 may acquire data related to the use module for a predetermined period. Using the obtained data, the machine learning unit 130 may learn and update a machine learning algorithm included in the machine learning unit 130.

In some cases, the machine learning unit 130 may determine the usage status of each of the at least one module 110 based on the data transmission/reception log with the at least one module 110. Here, the usage status may mean the number of times or frequency of use of each of the at least one module 110, and at least one module 110 will be reselected as the most suitable module for the current status of the user based on the usage status determination. I can. An example of at least one module 110 ′ reselected based on the actual use condition will be described later with reference to FIG. 5.

5 shows another example for explaining a method of reselecting a module included in a user-specific hardware platform according to an embodiment of the present invention. More specifically, FIG. 5 conceptually illustrates a process of accumulating data related to use of at least one module 110 for a predetermined period of time, and reselecting at least one module 110 ′ using the data.

Referring to FIG. 5, at least one module 110 ′ may include a first home IoT control module and a second government office service request module instead of a voice recognition module and a second home IoT control module.

This re-determination may be performed as each of the at least one module 110 is used and a usage log is accumulated, and the number or frequency of use of each of the at least one module 110 is calculated based thereon. For example, based on the frequency of use of each of the at least one module 110, a use weight is assigned to the score of a questionnaire related to each of the at least one module 110, and based on this, at least one module 110 At least one module 110 ′ may be determined by updating the scores previously calculated for each, and performing final score recalculation and priority alignment.

For example, by the initial questionnaire, the speech recognition module may have a score of +2 according to the instrumental daily living ability evaluation item and a score of +3 according to the underlying disease evaluation item. Based on the scores of these two evaluation items, the speech recognition module may have a value of +5 and may have been selected as one of at least one module 110 constituting the hardware platform.

After that, by using each module, a score for each evaluation item is assigned, and an item score, which is a score for each evaluation item, can be calculated. For example, the item score of -1 for the instrumental daily living ability evaluation item, and the item score of +2 for the evaluation item for underlying disease may be calculated.

In this case, the item score of each evaluation item may be reflected in the score that the existing speech recognition module has for each evaluation item. For example, the speech recognition module reflects (multiplications) -1, which is the item score calculated by use, to the module score +2 previously calculated by the instrumental daily life ability evaluation item, and finally a value of -2 is obtained. In addition, a value of +6 may be finally obtained by reflecting (multiplying) +2, which is the item score, to the module score +3 previously calculated by the evaluation item for the underlying disease. Accordingly, the score of the speech recognition module can be recalculated to +4.

In this way, the score may be recalculated for each of the at least one module 110, and the module may be reselected based on the finally calculated score.

Accordingly, the priority determined through the above-described process may be changed, and accordingly, the modules included in at least one module 110 may also be changed.

Meanwhile, the user-specific hardware platform according to an embodiment of the present invention can be used by the elderly and the physically vulnerable. In such a user, since the physical function of the user changes rapidly over time, a combination of necessary service modules may also change rapidly. In this case, by periodically changing at least one module mounted on the hardware platform using the method of FIGS. 3 to 5 described above, it is possible to efficiently supplement the physical function of the user through the hardware platform.

For example, when the speech recognition module is used, a positive score may be assigned to an instrumental daily life ability evaluation item, an underlying disease evaluation item, and an economic condition evaluation item, and a negative score may be assigned to a home electronic product distribution evaluation item. In this way, each evaluation item may be given a positive score or a negative score according to the use of the module, and finally, a score for each evaluation item may be calculated.

Accordingly, the score for each evaluation item related to the score for each module calculated according to the survey result for the initial module determination is reflected, and the score for each module may be recalculated. A detailed description related thereto may be referred to FIG. 5.

6 is a functional block diagram of a user-specific hardware platform according to an embodiment of the present invention. Used below'… The term'negative' refers to a unit that processes at least one function or operation, which may be implemented by hardware or software, or a combination of hardware and software. Hereinafter, in the description of FIG. 5, contents overlapping with FIGS. 1 to 5 may be omitted.

Referring to FIG. 6, the hardware platform 100 may include at least one module 110, a housing 120, a machine learning unit 130, and a power supply unit 140. At least one module 110 may be implemented by a computing device including a microprocessor, which is the same for the housing 120, the machine learning unit 130, and the power supply unit 140 to be described later.

At least one module 110 may collect user's biometric information data. For example, at least one module 110 may collect data on a user's body temperature and a user's movement.

In some cases, at least one module 110 may collect biometric information data at a predetermined time period. The predetermined period may be collected in minutes, for example, 2 minutes, and may not be collected in seconds or in real time. This may be because the purpose of the hardware platform 100 is not to obtain data in real time and provide information, but to obtain a usage log for a certain period of time to determine whether a dangerous situation has occurred to the user. In this case, it is possible to drive the hardware platform 100 with low power, and the use of the hardware platform 100 may be actively performed for the vulnerable class having difficult economic conditions due to low maintenance costs. However, this example is one of various embodiments, and the present invention is not limited thereto.

The at least one module 110 may be selected based on a user's state from among a plurality of modules having different functions. For example, the at least one module 110 may be selected based on a result obtained by inputting a questionnaire result received through a questionnaire on a user's state into a module selection engine learned by deep learning.

The evaluation items of the survey for selecting at least one module 110 are, for example, basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying diseases evaluation items, drug use record evaluation items, and long-term It may include at least one of a nursing care insurance evaluation item, an economic condition evaluation item, an Internet environment evaluation item, and a home electronic product distribution evaluation item.

Each of these evaluation items may have a positive or negative relevance mapped to at least one module 110, and a score may be calculated according to a user's input to at least one evaluation item.

At least one module 110 may be configured as a module having various functions. For example, at least one module 110 transmits a voice recognition module that recognizes a user's voice, a GPS module that recognizes a location, a home IoT control module that controls an electronic device installed in a specific place, and a signal to request a parental call. It may include at least one of a parental call module, an output module that provides information aurally or visually, a motion sensor module that detects motion, and a service request module that transmits a signal requesting a predetermined service.

The housing 120 may be implemented in a form in which at least one module 110 can be mounted. For example, the housing 120 may be implemented to include a module receiving portion in which each of the at least one module 110 is disposed. The module accommodating unit may be a combination of individual boxes, and at least one module 110 may be mounted in such a box shape.

The machine learning unit 130 may store a machine learning algorithm learned based on a usage log input from a user. The machine learning unit 130 may obtain a result value by applying the machine learning algorithm to the biometric information data collected from at least one module 110. Here, the result value may mean a service required for a user derived based on the user's biometric information data. For example, when biometric data indicating a case where a user stays at a location for a certain period of time is collected from the GPS module, a machine learning algorithm is applied to the data to provide services required by the user (e.g., parental call or notification function). Provided) can be derived. Through this, a method most suitable for the current state of the user among numerous services can be derived as a result value and provided to the user.

The machine learning unit 130 may transmit a result value to the external electronic device based on a wired or wireless connection with the external electronic device. In this case, since the data is not transmitted in real time, the communication load can be minimized, and because the biometric data is not transmitted to the outside, the privacy of the user can be protected and the leakage of personal information can be prevented. You can have performance.

The machine learning unit 130 may use the result value obtained by the machine learning algorithm as feedback data for updating the machine learning algorithm. Accordingly, data transmission for updating the machine learning algorithm can be minimized, and a communication load can be reduced.

The machine learning unit 130 may provide a result value to an output module among at least one module 110 so that the result value is visually or audibly output. In some cases, the machine learning unit 130 may receive a countermeasure for the user's condition (eg, a notification of a drug taking time) from an external electronic device. In this case, the machine learning unit 130 may provide a coping plan to the output module so that the coping plan is output visually or aurally.

Meanwhile, as described above, the machine learning algorithm of the machine learning unit 130 may be an algorithm previously learned using a usage log input from a user. The machine learning unit 130 may perform learning for a machine learning algorithm based on a usage log (eg, result value) obtained by use of the hardware platform 100 and a response plan received from an external electronic device. . Accordingly, the machine learning algorithm can be updated. That is, the machine learning unit 130 may improve the accuracy of obtaining a result value by continuously learning the machine learning algorithm.

The power supply unit 140 may supply power to a module receiving unit mounted on the housing 120. Specifically, the power supply unit 140 may supply power to the module receiving unit so that power is supplied to each of the at least one module 110 mounted in the module receiving unit. Through this, the function of at least one module 110 may be performed.

7 shows a flow of each step of a method of operating a user-specific hardware platform according to an embodiment of the present invention. It goes without saying that each step of the method illustrated in FIG. 7 may be performed in a different order as illustrated in the drawings depending on the case. Hereinafter, in the description of FIG. 7, content overlapping with FIGS. 1 to 6 may be omitted.

Referring to FIG. 7, biometric information data may be collected using at least one module 110 (S110). For example, the biometric information data may mean data about a user's movement, a user's body temperature, and a user's voice. Biometric information data acquired by each of the at least one module 110 may be pre-designated according to each function. For example, a voice recognition module may collect user's voice data, a GPS module may collect user's location data, and a motion recognition module may collect user's motion data.

A result value may be obtained by applying a machine learning algorithm to the biometric information data (S120). The result value may include information on a service to be provided to the user, for example, a door lock unlock request, a 119 call request, and the like. The machine learning algorithm may be an algorithm learned based on a usage log input from a user. The machine learning algorithm may continuously learn based on a usage log accumulated as the hardware platform 100 is used.

The result value may be transmitted to an external electronic device by the machine learning unit 130 or may be output through an output module (S130). The machine learning unit 130 may be implemented to transmit a result value to an external electronic device. Accordingly, the result value can be transmitted to an external electronic device.

In some cases, the machine learning unit 130 may transmit at least a portion of the result value to an external electronic device. At least some of the result values transmitted to the external electronic device may be related to services that can be provided through the external electronic device. For example, a result of requesting a service such as opening and closing of a door lock, which is an external electronic device, may be transmitted to an external electronic device, and an alarm service that can be provided through at least one module 110 itself is not transmitted to the external electronic device. May not.

On the other hand, since the information transmitted to the external electronic device is not the biometric data obtained from the user itself, but the result value derived by the machine learning unit 130 using the biometric information data, the user's personal information can be protected. have. In addition, since only a minimum amount of information can be transmitted, the hardware platform 100 can be operated with low power consumption due to low data usage, and maintenance cost can be minimized.

8 shows the flow of each step of a method of generating a user-specific hardware platform according to an embodiment of the present invention. It goes without saying that each step of the method illustrated in FIG. 7 may be performed in a different order as illustrated in the drawings depending on the case. In the description of FIG. 7 below, content overlapping with FIGS. 1 to 7 may be omitted.

Referring to FIG. 8, a questionnaire result may be derived by receiving an input of a questionnaire on a user's state (S210). The input of the survey may be obtained from a user or a guardian of the user. The survey may include various evaluation items to determine the user's status.

At least one module 110 based on a user's state may be selected from among a plurality of modules having different functions using the questionnaire result (S220). A plurality of modules are components having different functions in relation to a service to be provided to a user, and each module constituting at least one module 110 may be part of the plurality of modules.

At least one module 110 may be selected as a result obtained by inputting a survey result to a module selection engine learned by deep learning. The module selection engine provides the type and number of modules most necessary to the user as a result, and may be learned by using a correct answer value indicating a module required according to the state and state of the user. The user's state may be data predetermined for various user states, and the correct answer value may be information on a module required according to the user's state previously designated by a doctor or related expert.

Accordingly, when the survey result is input to the module selection engine, at least one module 110 suitable for the user's state may be derived as a result. In some cases, at least one module 110 may be performed based on the final score calculation of the module according to the score for each evaluation item through FIGS. 3 to 5.

When at least one module 110 is determined, a user-specific hardware platform including at least one module 110, a housing 120, a machine learning unit 130, and a power supply unit 140 may be generated (S230). ).

Combinations of each block in the block diagram attached to the present specification and each step in the flowchart may be performed by computer program instructions. Since these computer program instructions can be mounted on a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, the instructions executed by the processor of the computer or other programmable data processing equipment are shown in each block or flow chart of the block diagram. Each step creates a means to perform the functions described. These computer program instructions can also be stored in computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular way, so that the computer-usable or computer-readable memory It is also possible to produce an article of manufacture in which the instructions stored in the block diagram contain instruction means for performing the functions described in each block or flow chart. Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operating steps are performed on a computer or other programmable data processing equipment to create a computer-executable process to create a computer or other programmable data processing equipment. It is also possible for the instructions to perform the processing equipment to provide steps for performing the functions described in each block of the block diagram and each step of the flowchart.

In addition, each block or each step may represent a module, segment, or part of code comprising one or more executable instructions for executing the specified logical function(s). In addition, it should be noted that in some alternative embodiments, functions mentioned in blocks or steps may occur out of order. For example, two blocks or steps shown in succession may in fact be performed substantially simultaneously, or the blocks or steps may sometimes be performed in the reverse order depending on the corresponding function.

The above description is merely illustrative of the technical idea of the present invention, and those of ordinary skill in the art to which the present invention pertains will be able to make various modifications and variations without departing from the essential quality of the present invention. Accordingly, the embodiments disclosed in the present specification are not intended to limit the technical idea of the present disclosure, but to explain the technical idea, and the scope of the technical idea of the present disclosure is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: hardware platform
110: at least one module
120: housing
130: machine learning department
140: power supply

Claims (19)

At least one module for collecting biometric information data,
A housing having a module receiving portion capable of mounting the module,
A power supply unit for supplying power to a module accommodating unit mounted in the housing,
A machine that stores a machine learning algorithm learned based on a usage log input from a user, and applies the machine learning algorithm to the biometric information data collected from the at least one module to obtain a result value and transmit it to an external electronic device It has a learning department,
The at least one module is selected based on the state of the user from among a plurality of modules having different functions,
Selection of the at least one module,
It is performed based on the result obtained by inputting the questionnaire result input through the questionnaire on the user's state into the module selection engine learned by deep learning,
The above survey,
Contains at least one evaluation item,
Each of the at least one evaluation item is mapped to a positive or negative relationship to the at least one module, and a score is calculated according to the user's input to the at least one evaluation item felled
User-specific hardware platform.
delete The method of claim 1,
The at least one evaluation item,
Basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, long-term care insurance evaluation items for the elderly, economic conditions evaluation items, internet environment evaluation items and home electronic product distribution evaluation items Containing at least one of
User-specific hardware platform.
The method of claim 1,
The at least one module,
A voice recognition module that recognizes the user's voice, a global positioning sensor (GPS) module that recognizes the location, a home Internet of things (IoT) control module that controls electronic devices installed in a specific place, and transmits a signal requesting a parental call Including at least one of a parental call module, an output module that provides information audibly or visually, a motion sensor module that detects motion, and a service request module that transmits a signal for requesting a predetermined service.
User-specific hardware platform.
The method of claim 4,
The output module,
Outputting the result value or a countermeasure received from the external electronic device
User-specific hardware platform.
The method of claim 5,
The machine learning unit,
The machine learning algorithm is updated by learning based on the biometric information data and the response plan received from the external electronic device.
User-specific hardware platform.
Collecting biometric information data using at least one module,
Obtaining a result value by applying a machine learning algorithm to the collected biometric information data,
The at least one module is selected based on the state of the user from among a plurality of modules having different functions,
Selection of the at least one module,
It is performed based on the result obtained by inputting the questionnaire result input through the questionnaire on the user's state into the module selection engine learned by deep learning,
The above survey,
Contains at least one evaluation item,
Each of the at least one evaluation item is mapped to a positive or negative relationship to the at least one module, and a score is calculated according to the user's input to the at least one evaluation item felled
How the user-specific hardware platform works.
The method of claim 7,
Further comprising the step of transmitting the obtained result value to an external electronic device
How the user-specific hardware platform works.
delete The method of claim 7,
The at least one evaluation item,
Basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, long-term care insurance evaluation items for the elderly, economic conditions evaluation items, internet environment evaluation items and home electronic product distribution evaluation items Containing at least one of
How the user-specific hardware platform works.
The method of claim 7,
The at least one module,
A voice recognition module that recognizes the user's voice, a global positioning sensor (GPS) module that recognizes the location, a home Internet of things (IoT) control module that controls electronic devices installed in a specific place, and transmits a signal requesting a parental call Including at least one of a parental call module, an output module that provides information audibly or visually, a motion sensor module that detects motion, and a service request module that transmits a signal for requesting a predetermined service.
How the user-specific hardware platform works.
The method of claim 11,
The output module,
Outputting the result value or a countermeasure received from an external electronic device
How the user-specific hardware platform works.
The method of claim 8,
The machine learning algorithm is
Updated based on the biometric information data and the response plan received from the external electronic device
How the user-specific hardware platform works.
Receiving an input of a survey on the state of the user and deriving a survey result
Selecting at least one module based on the state of the user from among a plurality of modules having different functions using the survey result; and
The step of creating a user-specific hardware platform including the selected at least one module, a housing having a module receiving portion capable of mounting the module, a power supply supplying power to the module receiving portion mounted on the housing, and a machine learning unit. Including,
The at least one module,
Collecting biometric data,
The machine learning unit,
Stores the machine learning algorithm learned based on the usage log input from the user, and applies the machine learning algorithm to the biometric information data collected from the at least one module to obtain a result value and transmit it to an external electronic device and,
The above survey,
Contains at least one evaluation item,
Each of the at least one evaluation item is mapped to a positive or negative relationship to the at least one module, and a score is calculated according to the user's input to the at least one evaluation item felled
How to create a user-specific hardware platform.
The method of claim 14,
The selecting step,
And selecting the at least one module as a result obtained by inputting the survey result to a module selection engine learned by deep learning.
How to create a user-specific hardware platform.
The method of claim 14,
The at least one evaluation item,
Basic daily living ability evaluation items, instrumental daily living ability evaluation items, underlying disease evaluation items, drug use record evaluation items, long-term care insurance evaluation items for the elderly, economic conditions evaluation items, internet environment evaluation items and home electronic product distribution evaluation items Containing at least one of
How to create a user-specific hardware platform
The method of claim 16,
Obtaining a usage log of the at least one module,
Assigning a weight to each of the evaluation items based on the obtained usage log, and
And reselecting the at least one module by applying the weight to the input of the obtained survey survey.
How to create a user-specific hardware platform.
The method of claim 14,
The at least one module,
A voice recognition module that recognizes the user's voice, a global positioning sensor (GPS) module that recognizes the location, a home Internet of things (IoT) control module that controls electronic devices installed in a specific place, and transmits a signal requesting a parental call Including at least one of a parental call module, an output module that provides information audibly or visually, a motion sensor module that detects motion, and a service request module that transmits a signal for requesting a predetermined service.
How to create a user-specific hardware platform.
The method of claim 14,
The machine learning unit,
The machine learning algorithm is updated by learning based on the biometric information data and the response plan received from the external electronic device.
How to create a user-specific hardware platform.

Images