KR102145433B1 - Cardiovascular analyzer - Google Patents

Abstract

According to an embodiment of the present disclosure, a cardiovascular analyzer is disclosed. The cardiovascular analyzer,
A cuff part that wraps around a specific body part of the user and provides a pressing force that changes to the specific body part, a blood pressure measurement part that measures the user's first blood pressure according to the change of the pressing pressure, and occurs according to the activity of the user's heart. A plurality of ECG (electrocardiogram) sensor units attached to different body parts of the user and detecting a potential difference, a photoplethysmography (PPG) sensor unit for irradiating light through a light emitting means and detecting the intensity of a reflected or transmitted light signal, A conversion unit for converting into an electrocardiogram waveform by using the potential difference sensed for a predetermined time by the ECG sensor unit, and converting to a pulse waveform by using the intensity of the optical signal sensed for a predetermined time by the PPG sensor unit, and the first It may include a control unit for recognizing whether a re-measurement condition has been achieved based on at least one of a blood pressure, an electrocardiogram waveform, and the pulse waveform.

Description

Cardiovascular Analyzer {CARDIOVASCULAR ANALYZER}

The present disclosure relates to a cardiovascular analyzer, and more particularly, to a cardiovascular analyzer for recognizing whether a re-measurement condition has been achieved based on at least one of a user's blood pressure, an electrocardiogram waveform, and a pulse waveform.

Blood vessels are the lifeline that nourishes 60 trillion cells in our body. In order to maintain human life, it is necessary to pass the blood released by the beating of the heart to various parts of the body along the arteries without blockage, and to return blood to the heart through veins. As a result, oxygen and nutrients can be supplied to each tissue of the body, and waste products consumed through metabolism can be removed. As such, blood vessel health is directly related to our health, and if blood vessel management is wrong, serious diseases can occur.

However, our blood vessels are increasingly clogged by recent westernized eating habits, stress, obesity, lack of exercise, overeating, drinking, smoking and various environmental pollutants.

When fat, blood clots, and plaque accumulate on the inner wall of blood vessels, it causes inflammation and inflammatory substances accumulate and accumulate, resulting in a hardened blood vessel wall. When the blood vessels become narrow due to accumulation of accumulations on the walls of blood vessels, blood and oxygen supply disorders occur, and various vascular diseases appear. For example, representative vascular diseases include angina pectoris, myocardial infarction, stroke, and arterial obstruction of the lower extremities. In particular, failure to supply enough blood and oxygen to the heart and brain, which are vital organs for life support, can lead to body paralysis or sudden death.

Cardiovascular disease and cerebrovascular disease are counted as major causes of death not only in Korea but also in the world. These vascular diseases proceed silently and do not have any special subjective symptoms until they are blocked, so if neglected, they reach an irreversible state. Therefore, even in the absence of subjective symptoms, it is important to diagnose and prevent cardiovascular disease, cerebrovascular disease, and the risk factors of arteriosclerosis that cause it early.

Conventionally, a portable electrocardiogram measuring device has been developed to measure an electrocardiogram outside of a hospital due to the nature of busy modern people, but there are problems such as lack of function or inability to provide various cardiovascular indicators at once.

Korean Registered Patent Publication 10-1851107

The present disclosure has been devised in response to the above-described background technology, and is intended to provide a cardiovascular analyzer.

The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

According to an embodiment of the present disclosure for solving the above-described problem, a cardiovascular analyzer may be provided. The cardiovascular analyzer may include a cuff part surrounding a specific body part of the user and providing a pressing force that changes to the specific body part, a blood pressure measuring part measuring the user's first blood pressure according to the change of the pressing pressure, and the user's heart. A PPG that senses the potential difference generated according to the activity, irradiates light through a plurality of ECG (electrocardiogram) sensor units attached to different body parts of the user, and light emitting means, and detects the intensity of reflected or transmitted light signals ( Photoplethysmography) Transforms into an electrocardiogram waveform by using the potential difference detected by the sensor unit and the ECG sensor unit for a predetermined time, and converts to a pulse waveform by using the intensity of the optical signal detected by the PPG sensor unit for a predetermined time. And a controller for recognizing whether a re-measurement condition has been achieved based on at least one of the first blood pressure, the electrocardiogram waveform, and the pulse waveform.

According to some other exemplary embodiments of the present disclosure, a vibration output unit that is located inside the cuff unit and outputs a vibration feedback when the re-measurement condition is achieved may be further included.

According to still another exemplary embodiment of the present disclosure, when the re-measurement condition is achieved, a sound output unit for outputting preset sound data may be further included.

According to still another exemplary embodiment of the present disclosure, when the re-measurement condition is achieved, a display unit may further include a display configured to output information related to the re-measurement condition.

According to still another embodiment of the present disclosure, the controller calculates a heart rate per minute value using the electrocardiogram waveform, calculates a pulse rate per minute value using the pulse wave, and the heart rate per minute value and the pulse rate per minute value When the difference between the values is greater than or equal to a predetermined value, it may be recognized that the remeasurement condition is satisfied.

According to still another exemplary embodiment of the present disclosure, the control unit calculates a pulse wave conduction rate value based on the pulse wave waveform, calculates an arteriosclerosis index based on the pulse wave conduction rate value, and corresponds to the arteriosclerosis index. The second blood pressure is recognized, and when the difference between the second blood pressure and the first blood pressure is equal to or greater than a predetermined value, it may be recognized that the re-measurement condition is satisfied.

According to still another embodiment of the present disclosure, the control unit generates a model for calculating an arterial stiffness index according to a pulse wave conduction rate using machine learning, and calculates the arterial stiffness index according to the pulse wave conduction rate The output value inputted into the model can be calculated as the arteriosclerosis index.

According to still another exemplary embodiment of the present disclosure, the model for calculating an arterial stiffness index according to the pulse wave conduction speed includes inputting training data into an artificial neural network, an output value obtained by inputting the training data, and a correct answer corresponding to the training data. A process of comparing values to derive an error, backpropagating the error to the artificial neural network, and updating the weight of the artificial neural network may be generated by repeating a predetermined number of times.

According to still another embodiment of the present disclosure, the artificial neural network may include a deep neural network.

According to still another exemplary embodiment of the present disclosure, the cardiovascular analyzer is manufactured in the form of a massage chair, the cuff part is provided in a first area for massaging the user's upper arm, and the ECG sensor part , It is provided in a second region around the user's hand, the PPG sensor unit is provided in a third region around the user's hand, and the second region may be a different region from the third region.

Technical solutions obtainable in the present disclosure are not limited to the above-mentioned solutions, and other solutions that are not mentioned are clearly to those of ordinary skill in the technical field to which the present disclosure belongs from the following description. It will be understandable.

The present disclosure can provide a cardiovascular analyzer.

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

Various aspects are now described with reference to the drawings, wherein like reference numbers are used collectively to refer to like elements. In the examples that follow, for illustrative purposes, a number of specific details are presented to provide a holistic understanding of one or more aspects. However, it will be apparent that such aspect(s) may be practiced without these specific details.
1 is a block diagram of a cardiovascular analyzer according to some embodiments of the present invention.
2 is a flowchart illustrating an example of a method of operating a cardiovascular analyzer according to some embodiments of the present invention.
3 is a diagram illustrating an example of an ECG waveform in a stable state according to some embodiments of the present invention.
4 is a diagram illustrating an example of an ECG waveform in a non-stable state according to some embodiments of the present invention.
5 is a diagram illustrating an example of an ECG waveform in a first section and an ECG waveform in a second section according to some embodiments of the present invention.
6 is a flowchart illustrating another example of a method of operating a cardiovascular analyzer according to still another exemplary embodiment of the present invention.
7 is a diagram illustrating an example of a cardiovascular analyzer including a sliding unit according to some embodiments of the present invention.
8 is a view for explaining an example of a method of measuring the arm length using a cardiovascular analyzer including a sliding unit according to some embodiments of the present invention
9 is a diagram illustrating a cardiovascular analyzer including a line according to some embodiments of the present invention.
10 is a view for explaining an example of a method of measuring arm length using a cardiovascular analyzer including a line according to some embodiments of the present invention
11 is a diagram illustrating an example of a time difference between a peak of an electrocardiogram waveform and a peak of a pulse waveform according to some embodiments of the present invention.
12 is a flowchart illustrating another example of a method of operating a cardiovascular analyzer according to still another exemplary embodiment of the present invention.
13 is a flowchart illustrating still another example of a method of operating a cardiovascular analyzer according to still another exemplary embodiment of the present invention.
14 is a schematic diagram showing an artificial neural network according to some embodiments of the present invention.
15 is a schematic diagram showing a model according to some embodiments of the present invention.
16 is a view showing an example when the cardiovascular analyzer according to some embodiments of the present invention is manufactured in the form of a massage chair.
17 is a diagram illustrating a line 250 wound around a reel 280 according to an embodiment of the present invention.
18 is an exploded perspective view of a reel 280 and a line 250 according to an embodiment of the present invention.
19 is a cross-sectional view showing a reel 280 and a rotating member according to an embodiment of the present invention.

Various embodiments and/or aspects are now disclosed with reference to the drawings. In the following description, for illustrative purposes, a number of specific details are disclosed to aid in an overall understanding of one or more aspects. However, it will also be appreciated by those of ordinary skill in the art that this aspect(s) may be practiced without these specific details. The following description and the annexed drawings set forth in detail certain illustrative aspects of one or more aspects. However, these aspects are illustrative and some of the various methods in the principles of the various aspects may be used, and the descriptions described are intended to include all such aspects and their equivalents. Specifically, as used herein, "an embodiment", "example", "aspect", "example" and the like are not construed as having any aspect or design being better or advantageous than other aspects or designs. May not.

Hereinafter, the same or similar components are assigned the same reference numerals regardless of the reference numerals, and redundant descriptions thereof will be omitted. In addition, in describing the embodiments disclosed in the present specification, when it is determined that a detailed description of related known technologies may obscure the subject matter of the embodiments disclosed in the present specification, the detailed description thereof will be omitted. In addition, the accompanying drawings are for easy understanding of the embodiments disclosed in the present specification, and the technical spirit disclosed in the present specification is not limited by the accompanying drawings.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless otherwise specified in the phrase. As used in the specification, “comprises” and/or “comprising” do not exclude the presence or addition of one or more other elements other than the mentioned elements.

Although the first, second, etc. are used to describe various devices or components, it is a matter of course that these devices or components are not limited by these terms. These terms are only used to distinguish one device or component from another device or component. Accordingly, it goes without saying that the first element or component mentioned below may be a second element or component within the technical idea of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used with meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise or is not clear from the context, "X employs A or B" is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, when X uses both A and B, “X uses A or B” can be applied to either of these cases. In addition, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

In addition, the terms "comprising" and/or "comprising" mean that the corresponding feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. It should be understood as not. In addition, unless otherwise specified or when the context is not clear as indicating a singular form, the singular in the specification and claims should be interpreted as meaning "one or more" in general.

In addition, the terms “information” and “data” as used herein may often be used interchangeably with each other.

Hereinafter, the same or similar components are assigned the same reference numerals regardless of the reference numerals, and redundant descriptions thereof will be omitted. In addition, in describing the embodiments disclosed in the present specification, when it is determined that a detailed description of related known technologies may obscure the subject matter of the embodiments disclosed in the present specification, the detailed description thereof will be omitted. In addition, the accompanying drawings are for easy understanding of the embodiments disclosed in the present specification, and the technical spirit disclosed in the present specification is not limited by the accompanying drawings.

Although the first, second, etc. are used to describe various devices or components, it is a matter of course that these devices or components are not limited by these terms. These terms are only used to distinguish one device or component from another device or component. Therefore, it goes without saying that the first device or component mentioned below may be a second device or component within the spirit of the present disclosure.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings that can be commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it is directly connected to or may be connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The suffixes "module" and "unit" for constituent elements used in the following description are given or used interchangeably in consideration of only the ease of preparation of the specification, and do not have a distinct meaning or role by themselves.

When an element or layer is referred to as “on” or “on” of another element or layer, it is not only above the other element or layer, but also the other layer or other element in the middle. Includes all intervening cases. On the other hand, when a component is referred to as "directly on" or "directly on", it means that no other component or layer is interposed therebetween.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc., as shown in the figure It can be used to easily describe a component or a correlation with other components. Spatially relative terms should be understood as terms including different directions of the device during use or operation in addition to the directions shown in the drawings.

For example, if a component shown in a drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. I can. Accordingly, the exemplary term “below” may include both directions below and above. Components may be oriented in other directions, and thus spatially relative terms may be interpreted according to the orientation.

Objects and effects of the present disclosure, and technical configurations for achieving them will become apparent with reference to embodiments described in detail later with reference to the accompanying drawings. In describing the present disclosure, when it is determined that a detailed description of a well-known function or configuration may unnecessarily obscure the subject matter of the present disclosure, a detailed description thereof will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the present disclosure and may vary according to the intention or custom of users or operators.

However, the present disclosure is not limited to the embodiments disclosed below, and may be implemented in various different forms. The present embodiments are provided only to make the present disclosure complete, and to completely inform the scope of the disclosure to those of ordinary skill in the art to which the present disclosure belongs, and the present disclosure is only defined by the scope of the claims. . Therefore, the definition should be made based on the contents throughout this specification.

1 is a block diagram of a cardiovascular analyzer according to some embodiments of the present invention.

Referring to FIG. 1, the cardiovascular analyzer 100 includes a cuff part 110, a blood pressure measuring part 120, an electrocardiogram (ECG) sensor part 130, a photoplethysmography (PPG) sensor part 140, and a conversion part 150. , A control unit 160, a memory 170, an input unit 180, and an output unit 190. However, the above-described components are not essential to implement the cardiovascular analyzer 100, and the cardiovascular analyzer 100 may have more or fewer components than the components listed above. Here, each component may be composed of a separate chip, module or device, or may be included in a single device.

The cuff part 110 may surround a specific body part of the user and provide a changing pressure to the specific body part.

The cuff part 110 provides an environment in which the blood pressure measurement part 120 can measure blood pressure by providing a changing pressure to a specific body part of the user.

The specific body part covered by the cuff part 110 may be the left arm or the right arm. However, the present invention is not limited thereto, and various user body parts may be wrapped by the cuff part 110.

According to some embodiments, the cuff part 110 may be manufactured in a plurality of numbers, and each may wrap a specific body part of a different user.

For example, the first cuff portion may wrap the fore arm of the user's left arm, and the second cuff portion may wrap the fore arm of the user's right arm. However, the present invention is not limited thereto, and the plurality of cuff portions 110 may surround various body parts of the user.

The above-described examples are only examples, and the range of the number of cuff portions 110, the body portion covered by the cuff portion 110, and the body portion covered by the cuff portion 110 according to the present disclosure are not limited to the above-described examples. Does not.

Meanwhile, the cuff part 110 may include a blood pressure measuring part 120 therein. When the blood pressure measurement unit 120 is included in the cuff part 110, the cardiovascular analyzer 100 may measure blood pressure more easily. However, this is only an example, and the present disclosure is not limited thereto.

According to some other embodiments, the cuff unit 110 may include a vibration output unit capable of outputting vibration feedback therein. The vibration output unit may output vibration feedback under the control of the controller 160.

The blood pressure measurement unit 120 may measure the user's blood pressure according to a change in the pressing force.

According to some embodiments, the blood pressure measurement unit 120 may measure the user's blood pressure by using at least one of a Kortkov phonetic method, a vibration oscillometric method, and a volume oscillometric method. Here, the blood pressure may include systolic blood pressure and diastolic blood pressure.

In the Kortkov sound method, after pressing the cuff part 110 by a preset pressure higher than the expected systolic pressure, the cuff part 110 is gradually decompressed to detect the fricative sound (Kortkov sound) between the blood and the arterial wall, and the detected It may be a method of measuring blood pressure based on the strength of the sound and the strength of the pressing force.

The vibration oscillometric method pressurizes the cuff part 110 by a preset pressure higher than the expected systolic pressure, and then gradually decompresses the cuff part 110 to detect the vibration of the artery wall, and adjusts the detected vibration intensity and the applied pressure. It may be a method of measuring blood pressure based on it.

The volume oscillometric method is, after pressing the cuff part 110 by a preset pressure higher than the expected systolic pressure, gradually decompressing the cuff part 110 to detect the volume of the blood vessel, and the volume change of the detected blood vessel and the pressure It may be a method of measuring blood pressure based on intensity.

The blood pressure measuring unit 120 may measure blood pressure by performing at least two of the Kortkov phonetic method, the vibration oscillometer method, and the volume oscillometer method in parallel, and thereby increase the accuracy of blood pressure measurement. However, the above-described examples in which the blood pressure measuring unit 120 measures blood pressure are only examples, and the method of measuring the blood pressure by the blood pressure measuring unit 120 is not limited to the above-described examples.

The blood pressure measurement unit 120 may include components necessary to perform blood pressure measurement. For example, when measuring blood pressure using the Kortkov phonetic method, the blood pressure measuring unit 120 may include a microphone capable of measuring sound and a pressure sensor capable of measuring a pressing force.

In addition, the blood pressure measurement unit 120 may include components for improving accuracy of blood pressure measurement. For example, the blood pressure measurement unit 120 may include a band filter for removing a noise signal.

The above-described examples are only examples, and the type and number of components included in the blood pressure measuring unit 120 of the present disclosure are not limited.

The ECG sensor unit 130 may detect a potential difference generated according to the user's heart activity.

More specifically, the ECG sensor unit 130 may be manufactured in plural and attached to different body parts of the user to sense a potential difference generated according to the user's heart activity.

For example, the first ECG sensor unit is attached to a specific finger (eg, index finger) of the left hand, and the second ECG sensor unit is attached to a specific finger (eg, index finger) of the right hand to perform the activity of the user's heart. It is possible to detect the potential difference that occurs according to the. This is only an example, and the present disclosure is not limited to the above-described example in terms of the number and attachment positions of the ECG sensor units 130.

In addition, the ECG sensor unit 130 may include an electrode to detect a user's potential difference. The electrode may be used to detect a potential difference generated according to the activity of the user's heart by contacting the user's skin.

The PPG sensor unit 140 may irradiate light through a light emitting means and detect the intensity of a reflected or transmitted light signal.

As an example, a light emitting diode (LED) may be used as a light emitting means of the PPG sensor unit 140. However, the present disclosure is not limited thereto.

As another example, the PPG sensor unit 140 may include a photodiode or the like. Here, the photodiode may be a diode that converts an optical signal into an electric signal.

However, the above-described examples are only examples, and the present disclosure is not limited thereto.

According to some embodiments, the PPG sensor unit 140 may be attached to the user's body part and detect the intensity of an optical signal that is changed by a change in blood flow.

The conversion unit 150 may convert data sensed by the ECG sensor unit 130 and the PPG sensor unit 140 into waveform data. Here, the waveform data may include an electrocardiogram waveform and a pulse waveform.

More specifically, the conversion unit 150 may convert the ECG sensor unit 130 into an electrocardiogram waveform using a potential difference sensed for a predetermined time. In addition, the conversion unit 150 may convert the pulse wave waveform by using the intensity of the optical signal detected by the PPG sensor unit 140 for a predetermined time.

The conversion unit 150 may include components for converting an input signal. For example, a filter for removing noise and an amplifying unit for amplifying a signal may be included.

The above-described examples are only examples, and the present disclosure is not limited thereto.

The controller 160 may generally control the overall operation of the cardiovascular analyzer 100. The controller 160 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the above-described components or by driving an application program stored in the memory 170.

In addition, the controller 160 may control at least some of the components of the cardiovascular analyzer 100 in order to drive an application program stored in the memory 170. Furthermore, the controller 160 may operate by combining at least two or more of the components included in the cardiovascular analyzer 100 to drive the application program.

The embodiments described in the present disclosure, or particularly the embodiments described in connection with the control unit 160, are computer-readable storage media or any storage media similar to those through software, hardware, or a combination thereof, for example. It can be implemented by one or more processors within.

According to hardware implementation, the embodiments described herein include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), It may be implemented using at least one of processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions. The embodiments described in may be implemented by the controller 160 itself.

According to software implementation, embodiments such as procedures and functions described in the present specification may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein. The software code can be implemented with a software application written in an appropriate programming language. The software code may be stored in the memory 170 and executed by the controller 160.

A detailed operation of the cardiovascular analyzer 100 that can be controlled by the controller 160 according to some embodiments of the present disclosure will be described later in FIG. 2.

The memory 170 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), and RAM. (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic It may include at least one type of storage medium among a disk and an optical disk.

The memory 170 may store a plurality of application programs (application programs or applications) driven by the cardiovascular analyzer 100, data for operation of the cardiovascular analyzer 100, and instructions. At least some of these application programs may be downloaded from an external server through wired or wireless communication.

According to some embodiments, the memory 170 may store matching data in which the height and arm length are matched.

Meanwhile, the application program may be stored in the memory 170, installed on the cardiovascular analyzer 100, and driven by the controller 160 to perform an operation (or function) of the cardiovascular analyzer 100.

The input unit 180 may receive data from a user through an input device. Here, the input device may include a wired/wireless input device, specifically, a touch screen, a keypad, a number pad, a physical button, a keyboard, a mouse, a joystick, a jog wheel, a jog switch, a game pad, a stylus pen, and a microphone. The example of the input device described above is only an example, and the present disclosure is not limited thereto.

In addition, the input unit 180 may detect an input through a user's utterance by using speech recognition technology.

In addition, the input unit 180 is provided with buttons in the form of a hot key and/or selection buttons for selecting, canceling, and executing input according to a preset user setting function or a preset function by itself. can do. The input unit 180 may include a touch sensor capable of converting a change in pressure applied to a specific region or capacitance generated at a specific region into an electrical signal. The touch sensor may detect not only the location and area to be touched, but also the intensity of pressure on the touch.

According to some embodiments, the input unit 180 may include a numerical input unit for receiving a numerical value.

The output unit 190 may output at least one of visual information, auditory information, and tactile information. The output unit 190 may include a vibration output unit, an audio output unit, and a display unit.

The vibration output unit generates various tactile effects that a user can feel. A typical example of the tactile effect generated by the vibration output unit may be vibration. The intensity and pattern of the vibration generated by the vibration output unit may be controlled by a user's selection or setting by a controller. For example, the vibration output unit may synthesize and output different vibrations or sequentially output them. The vibration output unit may not only deliver a tactile effect through direct contact, but may also be implemented so that a user can feel the tactile effect through muscle sensations such as a finger or an arm. Two or more vibration output units may be provided depending on the configuration aspect of the cardiovascular analyzer 100.

The sound output unit may output audio data stored in the memory 170. The sound output unit also outputs an sound signal related to a function (eg, a remeasurement condition satisfaction guide sound, etc.) performed by the cardiovascular analyzer 100. The sound output unit may include a receiver, a speaker, and a buzzer.

The display unit may include at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), and an organic light-emitting diode (OLED).

The above-described example of the output unit 190 is only an example, and the present disclosure is not limited thereto.

According to some embodiments, the cardiovascular analyzer 100 may be manufactured in the form of a massage chair. Regarding that the cardiovascular analyzer is manufactured in the form of a massage chair, it will be described later in FIG. 16.

2 is a flowchart illustrating an example of a method of operating a cardiovascular analyzer according to some embodiments of the present invention. 3 is a diagram illustrating an example of an ECG waveform in a stable state according to some embodiments of the present invention. 4 is a diagram illustrating an example of an ECG waveform in a non-stable state according to some embodiments of the present invention. 5 is a diagram illustrating an example of an ECG waveform in a first section and an ECG waveform in a second section according to some embodiments of the present invention. With reference to FIGS. 2 to 5, the content overlapping with those described above will not be described again, but will be described with focus on the differences.

Referring to FIG. 2, the cardiovascular analyzer 100 may measure a user's blood pressure (S110).

Specifically, the control unit 160 of the cardiovascular analyzer 100 may measure the user's blood pressure by controlling the cuff unit 110 and the blood pressure measurement unit 120. As described above, the cardiovascular analyzer 100 may specifically measure the user's blood pressure by at least one of a Kortkov sound method, a vibration oscillometric method, and a volume oscillometric method.

The control unit 160 of the cardiovascular analyzer 100 may recognize whether the user is in a stable state when measuring blood pressure (S110) based on the ECG waveform (S120).

For example, the controller 160 calculates an auto correlation value of the ECG waveform received from the conversion unit 150, and based on the calculated auto correlation value, whether the user was in a stable state when measuring blood pressure. Whether it is possible to determine.

In general, the ECG waveform is constantly repeated when the user is in a stable state. Referring to FIG. 3, an electrocardiogram waveform in a stable state is shown. Further, referring to FIG. 4, an electrocardiogram waveform in an unstable state is shown. When comparing the electrocardiogram waveform in the stable state of FIG. 3 and the electrocardiogram waveform in the non-stable state of FIG. 4, it can be seen that the electrocardiogram waveform in the stable state repeats more regularly than the electrocardiogram waveform in the non-stable state. .

Autocorrelation is one of the operations used to analyze a signal, and is a measure of correlation with oneself that is shifted in time by τ of a signal. As for the autocorrelation value at a specific τ value, a signal having periodicity may have a higher autocorrelation value than a signal having no periodicity. That is, it is possible to determine whether the waveform is constantly repeated according to the result of analyzing the autocorrelation value.

Therefore, when measuring blood pressure, the controller 160 may determine that the ECG waveform is constant if the autocorrelation value of the corresponding ECG waveform is greater than or equal to a predetermined value, and if the ECG waveform is constant, the user is in a stable state. Therefore, if the autocorrelation of the ECG waveform is higher than or equal to a predetermined value, the controller 160 may determine that the user is in a stable state when measuring blood pressure.

Accordingly, the controller 160 may calculate an autocorrelation value of an electrocardiogram waveform, and determine whether the user is in a stable state when the user measures blood pressure according to whether the autocorrelation value is equal to or greater than a predetermined value.

As another example, the controller 160 may calculate a frequency domain value of the electrocardiogram waveform received from the conversion unit 150 and determine whether the user was in a stable state when measuring blood pressure based on the calculated frequency domain value. .

The control unit 160 may calculate a frequency domain value through Fourier transform of the ECG waveform, but the present disclosure is not limited thereto.

In general, in a stable state, the frequency domain value of the ECG waveform falls within a specific range or specific value. On the other hand, in the non-stable state, the frequency domain value of the ECG waveform may deviate from a specific range or specific value of the frequency domain value of the ECG waveform in the stable state.

Accordingly, the controller 160 may analyze the calculated frequency-domain value and determine whether the user is in a stable state or non-stable state when measuring the blood pressure based on the calculated frequency-domain value.

In another example, the controller 160 generates a stable state determination model according to a waveform using machine learning, and inputs the corresponding ECG waveform to the steady state determination model according to the waveform when measuring blood pressure, and the output value Accordingly, it is possible to determine whether the user is in a stable state when measuring blood pressure.

The controller 160 may generate a stable state determination model using machine learning, and the stable state determination model may output an output value in either a stable state or a non-stable state according to the type of the input waveform. Accordingly, the controller 160 may input the ECG waveform corresponding to the measurement of the blood pressure into the stable state determination model according to the waveform, and the controller 160 may determine whether the user is in a stable state based on the output value of the steady state determination model. You can figure out whether or not.

A detailed method for the control unit 160 to generate a model using machine learning will be described later in FIG. 14.

Examples have been presented in which the control unit 160 recognizes whether the user is in a stable state when measuring blood pressure based on the electrocardiogram waveform, but these are only examples, and the present disclosure allows the control unit 160 to measure the blood pressure by the user. The method of recognizing whether or not it is in a stable state is not limited to the above-described examples.

Meanwhile, according to some embodiments, the controller 160 includes an electrocardiogram waveform of a first section corresponding to a time at which the systolic blood pressure is measured among the user's blood pressure measured through the blood pressure measuring unit and the diastolic device measured through the blood pressure measuring unit among the user's blood pressure. Based on the ECG waveform of the second section corresponding to the time at which the blood pressure was measured, it is possible to recognize whether the user has been in a stable state when measuring the blood pressure.

That is, the controller 160 may recognize whether or not it is in a stable state based on the electrocardiogram waveform of a partial section, rather than recognizing whether it is in a stable state based on the entire ECG waveform.

In the case of blood pressure, since the main purpose is to measure systolic blood pressure and diastolic blood pressure, it may be sufficient to determine whether a user is in a stable state when measuring systolic blood pressure and diastolic blood pressure. Accordingly, the controller 160 allows the user to set the blood pressure based on the ECG waveform of the first section corresponding to the time at which the systolic blood pressure is measured, not the entire ECG waveform, and the electrocardiogram waveform of the second section corresponding to the time at which the diastolic blood pressure is measured. When measuring, it is possible to recognize whether it was in a stable state.

Specifically, referring to FIG. 5, (a) shows an electrocardiogram waveform 331 of a first section and an electrocardiogram waveform 332 of a second section, and (b) shows a time 333 when the systolic blood pressure is measured. The time 334 when the and diastolic blood pressure were measured is shown.

The control unit 160 is a section from a time preceding a preset time (for example, 0.5 seconds) to a time lagging behind a preset time (for example, 0.5 seconds) based on the measured time 333 of the systolic blood pressure. The ECG waveform corresponding to may be recognized as an ECG waveform of the first section. In addition, the control unit 160, from a time preceding a preset time (eg, 0.5 seconds) based on the measured time 334 of the diastolic blood pressure to a time lagging by a preset time (eg, 0.5 seconds). An electrocardiogram waveform corresponding to the section of can be recognized as an electrocardiogram waveform of the second section.

The controller 160 may recognize whether the user is in a stable state when measuring blood pressure, based on the electrocardiogram waveform 331 of the first section and the electrocardiogram waveform 332 of the second section determined through the above-described process. .

Referring back to FIG. 2, when it is recognized that the user's state is unstable (S130, No), the control unit 160 may measure the user's blood pressure again by controlling the cuff and the blood pressure measurement unit (S110).

That is, the control unit 160 may recognize that the blood pressure value measured in step S120 is the blood pressure measured in the non-stable state according to the type of the input ECG waveform, and the blood pressure value measured in the non-stable state may have low accuracy. Since this is high, the cuff unit 110 and the blood pressure measurement unit 120 can be controlled to measure the blood pressure again.

According to at least one of the above-described embodiments, accuracy of blood pressure measurement may be improved by re-measurement of blood pressure when blood pressure is measured when the user is in an unstable state.

6 is a flowchart illustrating another example of a method of operating a cardiovascular analyzer according to still another exemplary embodiment of the present invention. 7 is a diagram illustrating an example of a cardiovascular analyzer including a sliding unit according to some embodiments of the present invention. 8 is a diagram illustrating an example of a method of measuring arm length using a cardiovascular analyzer including a sliding unit according to some embodiments of the present invention. 9 is a diagram illustrating a cardiovascular analyzer including a line according to some embodiments of the present invention. 10 is a view for explaining an example of a method of measuring the arm length using a cardiovascular analyzer including a line according to some other embodiments of the present invention. 11 is a diagram illustrating an example of a time difference between a peak of an electrocardiogram waveform and a peak of a pulse waveform according to some embodiments of the present invention. With reference to FIGS. 6 to 11, the content overlapping with those described above will not be described again, but will be described with focus on the differences.

Referring to FIG. 6, the controller 160 of the cardiovascular analyzer 100 may determine the user's arm length (S210).

According to some embodiments, the user's arm length may have a default value set.

According to some other embodiments, the user's arm length may be input through the input unit 180.

According to some other embodiments, the user's arm length may be a value calculated based on a value of the user's key input through the numeric input unit.

As an example, the controller 160 may control to receive a value for a user's key through a numeric input unit. In addition, the controller 160 calculates a value of the user's height inputted by the numeric input unit through a specific formula, estimates the user's arm length, and determines this as the user's arm length. For example, a certain formula could be dividing the key by 3. However, this is only an example, and the present disclosure is not limited thereto.

As another example, the controller 160 may control to receive a value for a user's key through a numeric input unit. The controller 160 may determine the user's arm length based on the input value of the user's key and matching data in which the key and arm length stored in the memory 170 are matched. For example, when the arm length matched with the height value of 170cm is 60cm and the input key value is 170cm, the controller 160 may determine the user's arm length as 60cm. This is only an example, and the present disclosure is not limited thereto.

According to still another exemplary embodiment, the controller 160 may determine the length of the user's arm based on the length of the user's body part measured through the length measuring unit.

As an example, referring to FIGS. 7 and 8, the cardiovascular analyzer 100 may include a cuff part 110, a support part 210, a sliding part 220, and a first contact part 230. However, the above-described components are not essential to implement the cardiovascular analyzer 100, and the cardiovascular analyzer 100 may have more or fewer components than the components listed above. Here, each component may be composed of a separate chip, module or device, or may be included in a single device.

The support part 210 may be coupled to the front of the cuff part 110 to support a part of the user's fore arm.

The sliding part 220 is connected to the support part 210 and can be moved by an external force. For example, when a user puts a finger in the first contact part 230 while putting the hand inside the cuff part 110, a force is applied to the sliding part 220 so that the sliding part 220 slides forward. I can.

The first contact part 230 may be provided at one end of the sliding part and may contact a user's finger. Here, the first contact unit 230 may include the ECG sensor unit 130 in the first contact area and the PPG sensor unit 140 in a second contact area different from the first contact area. The first contact area and the second contact area are set to distinguish between the contact areas and do not refer to a specific place.

When the first contact unit 230 with the ECG sensor unit 130 and the PPG sensor unit 140 is provided at one end of the sliding unit 220, the ECG waveform and the pulsation waveform are measured at a time while measuring the user's arm length. There may be a noticeable effect.

The first length measuring unit (not shown) may be configured inside the sliding unit 220, but is not limited thereto.

As the user places his hand on the support part 210 after putting his hand on the cuff part 110, an external force may be applied to the first contact part 230 to apply an external force to the sliding part 220. The first length measuring unit may measure the length of movement of the sliding unit 220 by an external force.

Referring to FIG. 7 for explanation, the sliding part 220 is in a non-moving state. Here, when the user puts his arm in the cuff part 110 and contacts the first contact part 230 on the sliding part 220 along the support part 210 to take a posture for measuring blood pressure, the first contact part 230 ), the user's arm may be extended to the end and an external force may be applied. Further, since the first contact part 230 is coupled to one end of the sliding part 220, an external force applied to the first contact part 230 may be transmitted to the sliding part 220. Referring to FIG. 8, when an external force is applied to the sliding unit 220, the sliding unit 220 is moved by the external force, and the sliding unit 220 can move by a length 240 corresponding to the external force. The first length measurement unit may measure the length 240 that the sliding unit 220 has moved.

Meanwhile, the controller 160 may determine the arm length based on the length measured by the first length measuring unit. The length of the sliding part 220 is changed according to the length of the user's arm. And in general, if the value of the moved length is large, the value of the user's arm length will be large. Accordingly, the controller 160 may determine the user's arm length based on the value of the length measured by the first length measuring unit.

More specifically, the controller 160 may determine the arm length by substituting the measured length into a specific equation. For example, the controller 160 may determine a value obtained by multiplying the length measured by the first length measuring unit by 1.7 as the arm length. However, the method of determining the arm length described above is only an example, and the present disclosure is not limited thereto.

As another example, referring to FIGS. 9 and 10, the cardiovascular analyzer may include a cuff part 110, a support part 210, a line 250, and a second contact part 260. However, the above-described components are not essential to implement the cardiovascular analyzer 100, and the cardiovascular analyzer 100 may have more or fewer components than the components listed above. Here, each component may be composed of a separate chip, module or device, or may be included in a single device.

Although no reference number is given in the drawings, the cardiovascular analyzer may include a body portion to which a cuff portion is coupled. Here, the body portion may be a portion formed by the body of the cardiovascular analyzer 100. More specifically, in FIGS. 9 and 10, the body portion may mean a portion of the cardiovascular analyzer 100 other than the line 250 and the second contact portion 260. However, this is only an example, and the present disclosure is not limited thereto.

The support part 210 may be coupled to the front of the cuff part 110 to support a part of the user's fore arm.

The length of the line 250 may be changed as one end is coupled to the body and the other end is coupled to the second contact. As an example, one end of the line 250 may be coupled to one end of the support 210. That is, the line 250 may be coupled to one end of the support portion 210, and the other end of the support portion 210 may be coupled to the cuff portion 110. However, the position where the line 250 is coupled is not limited thereto.

According to some embodiments, the line 250 may receive a continuous restoring force in the direction of the body portion. Due to the restoring force, the length of the line 250 may return to a specific length when there is no other external force. However, the restoring force is set weaker than the user's external force, and the line length may change according to the user's external force. An example of a specific device for applying a restoring force in the direction of the body portion may include a reel 280. The reel 280 may be located inside the body. However, this is only an example, and the present disclosure is not limited thereto. A specific configuration of the reel 280 will be described later in FIG. 17.

According to some embodiments, the second contact part 260 may include an ECG sensor and a PPG sensor. When the ECG sensor and the PPG sensor are provided on the second contact part, there is no need to attach an additional sensor at a separate location, and there may be an effect of knowing the ECG waveform and the pulsating waveform at once while measuring the user's arm length.

According to some embodiments, the second contact part 260 may include an ECG sensor in a third contact area, and a PPG sensor in a fourth contact area different from the third contact area. The third contact area and the fourth contact area are only for indicating an area that does not overlap between the contact areas, and are not limited to specific places.

The second length measuring unit may be configured on the body or the line 250. However, this is only an example, and the present disclosure is not limited thereto.

In addition, the second length measuring unit (not shown) may measure the length. Here, the length may mean the length of the line 250 exposed to the outside of the body part.

Referring to FIG. 9, since the second length measuring unit does not have the length of the line 250 exposed to the outside of the body, the length may be recognized as zero.

Referring to FIG. 10, when a user puts an arm in the cuff part 110 and takes a posture for measuring blood pressure by contacting the second contact part with a finger, the line 250 is outside the body part as the second contact part moves. The length can be increased. The second length measuring unit may measure the length 270 in which the line 250 is extended.

Meanwhile, the controller 160 may determine the arm length based on the length 270 measured by the second length measuring unit. The length of the line 250 exposed to the outside of the body portion may vary according to the length of the user's arm. In addition, as the length value of the generally exposed line 250 increases, the user's arm length value increases. Accordingly, the controller 160 may determine the user's arm length based on the value of the length measured by the second length measuring unit. More specifically, the controller 160 may determine the arm length by substituting the measured length into a specific equation. For example, a value obtained by multiplying the length measured by the second length measuring unit by 1.7 may be determined as the arm length. However, the specific formula described above is only an example, and the present disclosure is not limited thereto.

Referring back to FIG. 6, the control unit 160 of the cardiovascular analyzer 100 may calculate the pulse wave conduction rate using the user's arm length, electrocardiogram waveform, and pulse waveform determined in step S210 (S220). .

The pulse wave rate may be a value obtained by dividing a distance from the position of the PPG sensor unit 140 to the user's heart by a difference between a time when the peak of the ECG waveform is recorded and a time when the peak of the pulse wave is recorded.

First, the controller 160 may calculate the distance from the position of the PPG sensor unit 140 to the heart using the user's arm length.

According to some embodiments, the PPG sensor unit 140 may be located on the user's finger among the user's body parts. Accordingly, the distance from the position of the PPG sensor unit 140 to the user's heart may be the length of the user's arm + the distance from the user's shoulder to the heart.

Here, the distance from the user's shoulder to the heart may be the user's arm length * a predetermined value. The predetermined value may be different based on whether the PPG sensor unit 140 is located in the left or right hand of the user, and whether the user's heart is located on the left or the right.

Accordingly, the control unit 160 may calculate the distance from the position of the PPG sensor unit 140 to the heart as (1 + a predetermined value) * the length of the user's arm.

Next, the controller 160 may calculate a difference value between the time when the peak of the ECG waveform is recorded and the time when the peak of the pulse waveform is recorded using the ECG waveform and the pulse waveform.

Specifically, referring to FIG. 11, the controller 160 may use a time when one peak among a plurality of peaks included in the ECG waveform is measured as a first reference time.

In addition, the controller 160 may set a time at which the first peak present after the first reference time among the plurality of peaks included in the pulse wave is measured as the second reference time.

In addition, the controller 160 may set a difference value between the second reference time and the first reference time as a difference value 410 between the time when the peak of the ECG waveform is recorded and the time when the peak of the pulse waveform is recorded.

Finally, the control unit 160 divides the distance from the position of the PPG sensor unit 140 to the user's heart by a difference value 410 between the time at which the peak of the ECG waveform is recorded and the time at which the peak of the pulse wave is recorded. The conduction velocity can be calculated.

However, the above-described example is only an example, and the present disclosure is not limited to the above-described example in terms of an equation for calculating a pulse wave conduction rate and the type and number of variables used to calculate the pulse wave conduction rate.

12 is a flowchart illustrating another example of a method of operating a cardiovascular analyzer according to still another exemplary embodiment of the present invention.

Referring to FIG. 12, the controller 160 of the cardiovascular analyzer 100 may recognize whether a re-measurement condition has been achieved based on at least one of a first blood pressure, an electrocardiogram waveform, and a pulse waveform (S310).

As an example, the controller 160 calculates a heart rate per minute value using an electrocardiogram waveform, calculates a pulse rate per minute value using the pulse wave, and reloads when the difference between the heart rate per minute value and the pulse rate per minute value is more than a predetermined value. It can be recognized that the measurement conditions are satisfied. The heart rate per minute value is a value indicating how many times the heart beats in one minute, and the pulse rate per minute value is a value indicating how many times the artery beats in one minute. Since the pulse is caused by the heart rate, there is no difference between the heart rate and the pulse rate in the general case. However, a difference between heart rate and pulse rate may occur due to problems such as sudden movement of a person, an inaccurate measurement posture, or an improperly attached sensor.

Accordingly, the controller 160 may recognize that the re-measurement condition is satisfied when the difference between the pulse rate per minute value and the heart rate per minute value is equal to or greater than a predetermined value. For example, when the difference between the pulse rate per minute value and the heart rate per minute value is 2 or more, the controller 160 may recognize that the re-measurement condition is satisfied. However, this is only an example, and the present disclosure is not limited thereto.

As another example, the controller 160 calculates a pulse wave conduction rate value based on the electrocardiogram waveform and the pulse wave wave, calculates an arteriosclerosis index based on the pulse wave conduction rate value, and recognizes the second blood pressure corresponding to the arteriosclerosis index. can do. In addition, when the difference between the second blood pressure and the first blood pressure is greater than or equal to a predetermined value, the controller 160 may recognize that the re-measurement condition is satisfied. Here, the blood pressure may include systolic blood pressure and diastolic blood pressure.

A method of calculating the pulse wave conduction velocity value based on the ECG waveform and the pulse wave by the controller 160 may be as described above with reference to FIG. 6.

According to some embodiments, the control unit 160 generates an arterial stiffness index calculation model according to the pulse wave conduction rate using machine learning, and inputs the pulse wave conduction rate value to the arteriosclerosis index calculation model according to the pulse wave conduction rate, and outputs the output. The value can be calculated as the arteriosclerosis index.

A specific method for the control unit 160 to generate a model for calculating an arteriosclerosis index according to a pulse wave conduction rate using machine learning will be described later in FIG. 14.

According to some other embodiments, the controller 160 may calculate the arterial hardening index by substituting the pulse wave conduction rate value into an equation capable of calculating the arterial stiffness index as the pulse wave conduction speed value, and calculating this value.

The arteriosclerosis index indicates how hard the arteries are, and the arteriosclerosis index and blood pressure are generally proportional to each other. More specifically, when the arteriosclerosis index is high, blood pressure also tends to be high. And when the arteriosclerosis index is low, blood pressure tends to be low. However, the blood pressure value may be too high or too low compared to the arteriosclerosis index due to problems such as sudden movement of a person, inaccurate measurement posture, or not properly attaching a sensor.

Accordingly, the controller 160 recognizes the second blood pressure corresponding to the arteriosclerosis index, and may recognize that the re-measurement condition is satisfied when the difference between the second blood pressure and the first blood pressure is greater than or equal to a predetermined value.

Meanwhile, when it is recognized that the remeasurement condition has been achieved (S320, Yes), the controller 160 may control to output at least one of vibration feedback, sound data, and information related to the remeasurement condition (S330).

For example, when the re-measurement condition is achieved, the controller 160 may control a vibration output unit located inside the cuff unit 110 to output vibration feedback. When the re-measurement condition is achieved, since vibration feedback is provided through the vibration output unit located inside the cuff unit 110, the user can easily recognize that re-measurement is required. This is only an example, and the present disclosure is not limited thereto.

As another example, when the re-measurement condition is achieved, the controller 160 may control the sound output unit to output preset sound data. Here, the preset sound data may be sound data that informs the user that the remeasurement condition is satisfied. If the re-measurement condition has been achieved, the user can easily recognize that a re-measurement should be made once acoustic data is provided. This is only an example, and the present disclosure is not limited thereto.

As another example, when the re-measurement condition is achieved, the controller 160 controls the display unit to output information related to the re-measurement condition. Here, the information related to the re-measurement condition is that the re-measurement condition is satisfied? It may include guiding characters, emoticons, pictograms, images, and the like. However, the present disclosure is not limited thereto, and the information related to the re-measurement condition may include information on the reason for the re-measurement (eg, information on comparing the correct posture and the current posture).

According to at least one of the above-described embodiments in FIG. 12, the user may recognize that the re-measurement should be easily performed.

13 is a flowchart illustrating still another example of a method of operating a cardiovascular analyzer according to still another embodiment of the present invention.

Referring to FIG. 13, the controller 160 of the cardiovascular analyzer 100 may recognize whether a user's state is a stable state based on at least one of an electrocardiogram waveform and a pulse waveform (S410).

As an example, the controller 160 calculates a first auto correlation value of the ECG waveform and a second auto correlation value of the pulse waveform, and based on the first autocorrelation value and the second autocorrelation value, the user It is possible to determine whether or not the state of is stable.

As described above in FIG. 2, autocorrelation can be used to analyze a signal, and whether a user is in a stable state can be determined according to a first autocorrelation value of an electrocardiogram waveform.

In addition, when the user is in a stable state, the pulse waveform tends to be repeated more periodically than when the user is in a non-stable state, and according to the second autocorrelation value of the pulse waveform, it is possible to determine whether the user is in a stable state.

Accordingly, when the first autocorrelation value of the electrocardiogram waveform and the second autocorrelation value of the pulse waveform are equal to or greater than a predetermined value, the controller 160 may determine that the user is in a stable state. Accordingly, the controller 160 calculates the first autocorrelation value of the ECG waveform and the second autocorrelation value of the pulse waveform, and according to whether the first autocorrelation value and the second autocorrelation value are equal to or greater than a predetermined value, the user You can determine whether or not is in a stable state.

As another example, the control unit 160 calculates a first frequency domain value of an electrocardiogram waveform and a second frequency domain value of the pulse waveform received from the conversion unit 150, and calculates the calculated first frequency domain value and the second frequency domain value. Based on the value, it is possible to determine whether the user is in a stable state.

As described above in FIG. 2, in a stable state, the frequency domain value of the ECG waveform corresponds to a specific range or specific value. On the other hand, in the non-stable state, the frequency domain value of the ECG waveform may deviate from a specific range or specific value of the frequency domain value of the ECG waveform in the stable state. Likewise for the pulse wave, the frequency domain value of the pulse wave corresponds to a specific range or specific value in a stable state. Accordingly, the controller 160 may determine whether the user is in a stable state or an unstable state by analyzing the first frequency domain value of the electrocardiogram waveform and the second frequency domain value of the pulse waveform.

In another example, the controller 160 generates a stable state determination model according to a waveform using machine learning, and inputs the ECG waveform and the pulse wave into the steady state determination model according to the waveform, and according to the output value, the user You can determine whether it is stable or not.

As described above in FIG. 2, by using machine learning, a stable state determination model can be generated, and the stable state determination model outputs an output value in either a stable state or a non-stable state according to the input waveform or the type of waveforms. I can. Accordingly, the controller 160 can determine whether the user is in a stable state based on the output value of the stable state determination model.

A detailed method for the control unit 160 to generate a model using machine learning will be described later in FIG. 14.

According to some embodiments, when the user's state is maintained as a stable state for a preset time, the controller 160 may recognize that the user's state is a stable state.

That is, it is not determined whether the user is in a stable state by analyzing only one waveform, but when the user is held for a certain period of time, the user can be recognized as a stable state.

Meanwhile, when it is recognized that the user's state is a stable state (S420, Yes), the control unit 160 may control the cuff and the blood pressure measuring unit to start measuring the user's blood pressure (S430).

The controller 160 may start measuring blood pressure while the user is in a stable state. Through this, there may be an effect of improving the accuracy of the measured blood pressure.

In addition, there may be a case where the user puts both arms in the cuff part 110 to measure blood pressure, and in this case, it may be difficult for the user to press a button for starting blood pressure measurement by hand. In some embodiments of the present disclosure, since the control unit 160 automatically starts blood pressure measurement when the user is in a stable state, blood pressure measurement can be started without the user pressing a button, so that the cardiovascular analyzer 100 of the present disclosure The cardiovascular analyzer 100 of the present disclosure allows the user to measure blood pressure in a more stable state compared to the prior art in which the user needs to press a button to start the measurement and then quickly establish a posture. There may be an effect of improving.

According to some embodiments, when measuring the user's blood pressure, the controller 160 may control a vibration output unit located inside the cuff unit 110 to output vibration feedback. When blood pressure measurement is started, since vibration feedback is provided through the vibration output unit located inside the cuff part 110, the user can easily recognize that blood pressure measurement starts. This is only an example, and the present disclosure is not limited thereto.

When it is recognized that the user's state is an unstable state (S420, No), the controller 160 may re-recognize whether the user's state is a stable state based on at least one of an electrocardiogram waveform and a pulse waveform (S410). ).

That is, when the user is not in a stable state, the control unit 160 receives the ECG waveform and the pulse waveform from the conversion unit 150 again, and the user's state is stabilized based on at least one of the received ECG waveform and the pulse waveform. You can recognize again whether it is in a state or not.

As a result, when the state of the user is in an unstable state, the controller 160 recognizes the state of the user again until the state of the user becomes a stable state, and starts blood pressure measurement when the state of the user becomes stable. It is possible to control the cuff part and the blood pressure measuring part.

14 is a schematic diagram showing an artificial neural network according to some embodiments of the present invention.

Throughout this specification, a computational model, a neural network, an artificial neural network, a network function, and a neural network may be used with the same meaning. A neural network can be made up of a set of interconnected computational units, which can generally be referred to as “nodes”. These “nodes” may also be referred to as “neurons”. The neural network includes at least one or more nodes. The nodes (or neurons) that make up neural networks can be interconnected by one or more “links”.

In a neural network, one or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may have an input node relationship in a relationship with another node, and vice versa. As described above, the relationship between the input node and the output node may be created around a link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node includes values input to input nodes connected to the output node and a link corresponding to each input node. The output node value may be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and an output node relationship in the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the association relationship between the nodes and the links, and a weight value assigned to each of the links. For example, when the same number of nodes and links exist, and two neural networks having different weight values between the links exist, the two neural networks may be recognized as being different from each other.

A neural network can be configured including one or more nodes. Some of the nodes constituting the neural network may configure one layer based on the distances from the initial input node. For example, a set of nodes with a distance n from the initial input node, n layers can be configured. The distance from the first input node may be defined by the minimum number of links that must be traversed to reach the node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of the layer in the neural network may be defined in a different way than that described above. For example, the layer of nodes may be defined by the distance from the last output node.

The initial input node may mean one or more nodes to which data is directly input without going through a link in a relationship with other nodes among nodes in the neural network. Alternatively, in a relationship between nodes in a neural network network based on a link, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may mean one or more nodes that do not have an output node in a relationship with other nodes among nodes in the neural network. In addition, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the input layer proceeds to the hidden layer. I can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of an input layer is less than the number of nodes of an output layer, and the number of nodes decreases as the number of nodes progresses from the input layer to the hidden layer. have. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of an input layer is greater than the number of nodes of an output layer, and the number of nodes increases as the number of nodes progresses from the input layer to the hidden layer. I can. A neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may mean a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify potential structures in data. In other words, it is possible to understand the potential structures of photos, texts, videos, voices, and music (e.g., what objects are in photos, what are the content and emotions of the text, what are the contents and emotions of the voice, etc.) . Deep neural networks include convolutional neural networks (CNNs), recurrentneural networks (RNNs), auto encoders, Generative Adversarial Networks (GANs), and restricted boltzmann machines (RBMs). machine), deep belief network (DBN), Q network, U network, Siam network, and the like. The foregoing description of the deep neural network is only an example, and the present disclosure is not limited thereto.

The neural network may be learned by at least one of supervised learning, unsupervised learning, and semi supervised learning. Learning of neural networks is to minimize output errors. In learning of a neural network, iteratively inputs training data to the neural network, calculates the output of the neural network for the training data and the error of the target, and reduces the error from the output layer of the neural network to the input layer. This is a process of updating the weight of each node of the neural network by backpropagation in the direction. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (ie, labeled learning data), and in the case of non-satellite learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning related to data classification, the learning data may be data in which a category is labeled with each learning data. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network with a label of the training data. As another example, in the case of comparative history learning regarding data classification, an error may be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the neural network in the reverse direction (ie, from the output layer to the input layer), and the connection weight of each node of each layer of the neural network may be updated according to the backpropagation. The amount of change in the connection weight of each node to be updated may be determined according to a learning rate. The computation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, a high learning rate is used in the early stages of learning of a neural network, so that the neural network quickly secures a certain level of performance to increase efficiency, and a low learning rate can be used in the later stages of learning to increase accuracy.

In the learning of a neural network, in general, the training data may be a subset of actual data (that is, data to be processed using the learned neural network), and thus, errors in the training data decrease, but errors in the actual data occur. There may be increasing learning cycles. Overfitting is a phenomenon in which errors in actual data increase due to over-learning on learning data. For example, a neural network learning a cat by showing a yellow cat may not recognize that it is a cat when it sees a cat other than yellow, which may be a kind of overfitting. Overfitting can cause an increase in errors in machine learning algorithms. Various optimization methods can be used to prevent such overfitting. In order to prevent overfitting, methods such as increasing training data, regulation, or dropout in which some nodes of the network are omitted during the training process may be applied.

15 is a schematic diagram showing a model according to some embodiments of the present invention.

A method of generating a model by the control unit 160 according to an embodiment of the present disclosure will be described. Here, the model may include a stable state determination model according to the waveforms described above in FIGS. 2 and 13 and an arteriosclerosis index calculation model according to the pulse wave conduction velocity described above in FIG. 12. However, this is only an example, and the present disclosure is not limited thereto.

In this exemplary view, one or more hidden layers may be included between the hidden layer 1 640 and the hidden layer 2 650, and the one or more hidden layers may be omitted and illustrated in the exemplary diagram.

The controller 160 may generate a model including one or more network functions 600. The network function 600 may include one input layer 630, one or more hidden layers, and one output layer 660.

The controller 160 may input training data to the network function 600 of the model. Each item of training data may be input to each input node included in the input layer 630 of the network function 600 of the model. For example, in the case of a steady state determination model based on a waveform, at least one of an ECG waveform and a pulse waveform may be input as an item of the training data, and in the case of a model for calculating an arteriosclerosis index according to the pulse wave conduction rate, the pulse wave conduction rate is the training data Can be entered as an item of. The description of the above-described item value is only an example, and the present disclosure is not limited thereto.

The controller 160 may calculate each item value input to the input node included in the input layer 630 of the network function 600 with a weight set for a link connected to the input node and propagate to the hidden layer. For example, the first hidden node 620 included in the hidden layer 1 640 is a value obtained by calculating a value transmitted to the first input node 601 and a first weight 611, and a second input node 602. ), the value transferred to the third input node 603 and the value obtained by calculating the third weight, the value transferred to the fourth input node 604 and the fourth weight. The calculated value, the value transferred to the fifth input node 605, and the calculated value of the fifth weight may be received. For example, the first hidden node 620 included in the hidden layer 1 640 is a value obtained by multiplying the value transmitted to the first input node 601 and the first weight 611, and the second input node 602 A value obtained by multiplying the value transmitted to the second weight, the value transmitted to the third input node 603 and the value obtained by multiplying the third weight, the value transmitted to the fourth input node 604 and multiplying the fourth weight, A sum of a value obtained by multiplying a value transmitted to the fifth input node 605 and a fifth weight may be received. The description of the above operation is only an example, and the present disclosure is not limited thereto.

The training data of the network function 600 may be propagated from the input layer 630 to the output layer 660 through the hidden layer 1 640 and the hidden layer 2 650. The weight of the network function 600 may be adjusted based on an error between an output value from the output node 662 included in the output layer 660 and a correct answer. The control unit 160 passes from the output layer 660 of the network function 500 to the input layer 630 through one or more hidden layers (e.g., in the order of hidden layer 2 650 and then hidden layer 1 640). While propagating the error, the weights set for each link may be updated (eg, after adjusting the weight of W2(1,1) 631), the weight of W1(1,1) 611 may be adjusted.

Through the above process, the controller 160 may generate a model using machine learning according to an embodiment of the present disclosure.

16 is a view showing an example when the cardiovascular analyzer according to some embodiments of the present invention is manufactured in the form of a massage chair.

Referring to FIG. 16, the cardiovascular analyzer 700 manufactured in the form of a massage chair may include a body structure 701, a massage part 702, and a cuff part 703.

The body structure 701 may form and define any type of space for accommodating a user. The body structure 701 may have an external shape corresponding to the shape of the user's body. As shown in FIG. 16, for example, the body structure 701 may have a chair or bed shape capable of accommodating a user's whole body or a part of the body. For example, portions of the body structure 701 that directly contact the user's body may be made of a relatively soft material such as leather, cloth, or cotton in order to increase the user's fit. In addition, portions of the body structure 101 that are not in direct contact with the user may be made of a relatively hard material such as plastic and/or metal in order to achieve fixation and stability of the device. In the body structure 701, the part in contact with the ground is an arbitrary material for increasing the frictional force in order to reinforce the fixedness with the ground, or any member for increasing the frictional force (for example, any material for increasing the contacting force with the ground. An anti-slip pad, a binding portion, a bonding portion, a contact portion, etc.), and a movable wheel portion for enhancing mobility of the device may also be provided at the lower end of the body structure 701.

The body structure 701 may accommodate, for example, a head sheet that can be in contact with the user's head, a back sheet that can be in contact with the user's back, a hip sheet that can be in contact with the user's hip, and an arm of the user. Any type of user contact portions, including an armrest portion capable of, and a leg massage portion capable of receiving and providing stimulation to the user's leg and foot portions, and the like may be provided.

The body structure 701 includes an outer panel having a fixed shape, and the user contacts inside the outer panel move relative to the outer panel in various forms such as sliding movement, hinge movement, pivot movement and/or tilting movement. This could be possible. The relative movement of each component in the body structure 701 may be made differently for each massage pattern (e.g., about 20° from the ground in the first step, about 40° from the ground in the second step, and In step 3, about 170° from the ground, etc.), the massage effect according to each massage pattern can be maximized. That is, according to the automatic massage mode, the posture at which the user receives the massage can be variably adjusted, so that the massage effect provided to the user can be maximized.

Additionally, the body structure 701 may have one or more pressure sensors. In this case, the contact area and the contact position between the user and the body structure 701 are sensed, and the positions and/or areas of the contact areas with the user in the body structure 701 may be changed to fit the user's body shape. For example, when it is determined that the user's leg length is longer than the current state of the body structure 701, a frame in which the user's leg is located in the body structure 701 (eg, a frame of the leg massage unit) may be extended. .

The massage unit 702 may be configured and positioned within the cardiovascular analyzer 700 manufactured in the form of a massage chair to provide mechanical stimulation of any form to a user accommodated in the body structure 701. As shown in FIG. 16, the massage unit 702 may provide mechanical stimulation to various positions while moving along a rail-shaped structure formed inside (or outside) the cardiovascular analyzer 700 manufactured in the form of a massage chair. . In this example, the massage unit 702 may have a ball shape or a roller shape.

The massage unit 702 may apply pressure to the outside through a pneumatic control method, may apply vibration to the outside using a vibration motor, and may move an arbitrary type of treatment body or protrusion through a solenoid method. It can also provide irritation to the massage area. In addition, since the above-described protrusion or treatment body may be formed of a magnet, iron content present in the blood of the human body is affected by magnetism, and an effect of further promoting blood circulation may be derived.

The massage unit 702 may provide a massage function in the form of at least one of tapping, kneading, tapping on a hand, and acupressure according to the above-described operating principle.

The cuff part 703 may be provided in the first area for massaging the user's upper arm. The cuff portion 703 may be used to measure blood vessels, but may provide a massage to the user using a pressing force.

The ECG sensor unit 130 may be provided in a second area around the user's hand 704. More specifically, the hand circumference 704 may include a position surrounding the hand, a position contacting the back of the hand, a position contacting the bottom of the hand, a position contacting the wrist, and the like. However, this is only an example, and the present disclosure is not limited thereto.

The PPG sensor unit 140 may be provided in a third area around the user's hand 704.

Here, the third region may be a different region from the second region. Here, the different regions may mean that they are not provided at overlapping positions.

The controller 160 may provide a massage to a user by controlling the operations of the massage unit 702 and the cuff unit 703. In addition, the controller 160 may control the operation of the massage unit 702 and the cuff unit 703 based on the massage pattern stored in the memory 170.

The memory 170 may temporarily or permanently store any data related to the massage operation. Specifically, the memory 170 may store information on massage patterns operable by the massage unit 702 and the cuff unit 703. However, this is only an example, and the present disclosure is not limited thereto.

The cardiovascular analyzer 700 manufactured in the form of a massage chair may include an input unit 180 for receiving an arbitrary selection related to control of an operation of a massage device from a user. The input unit 180 may mean a button and/or a display integrally formed with the cardiovascular analyzer 700 manufactured in the form of a massage chair. As another example, the input unit 180 may include a user terminal or a remote control that is located remotely from the cardiovascular analyzer 700 manufactured in the form of a massage chair and can communicate with the cardiovascular analyzer 700 manufactured in the form of a massage chair. .

The input unit 180 includes, for example, selection of a massage mode, selection of a massage pattern, selection of a massage type, selection of a massage intensity, selection of a massage time, selection of a massage site, a display of the current massage state, and a body structure 701 Selecting the location and operation of ), selecting the power of the massage device on-off, selecting the automatic mode, selecting whether or not to operate the thermal function, selecting the sound source playback, etc. can do.

The output unit 190 may include a display for displaying the operation of the cardiovascular analyzer 700 manufactured in the form of a massage chair or a current state of the user. Two or more displays may exist depending on the implementation form of the output unit 190.

In addition, the output unit 190 may output the operation of the cardiovascular analyzer 700 manufactured in the form of a massage chair or a current user's state through voice to the user including a speaker.

In addition, the output unit 190 may output music through a speaker. Through this, there may be an effect of simultaneously listening to music while the user performs a massage.

In addition, the output unit 190 may include a vibration output unit and output an operation of the cardiovascular analyzer 700 manufactured in the form of a massage chair or a current user's state to the user through vibration feedback.

17 is a view showing a line 250 wound around the reel 280 according to an embodiment of the present invention, and FIG. 18 is an exploded perspective view of the reel 280 and the line 250 according to an embodiment of the present invention to be.

According to some embodiments, the reel 280 may be included in the body part of the cardiovascular analyzer 100 to provide the line 250 with a continuous restoring force in the body part direction.

The reel 280 is a cylindrical member and serves to receive the line 250 by being wound around the outer circumferential surface while rotating the center around the shaft 282. In order to rotate the reel 280 so that the line 250 is wound around the outer circumferential surface of the reel 280, a rotating member may be provided in the reel 280 as shown in FIG. 18.

The rotating member may use a spiral spring 285 in which a strip-shaped metal plate is wound in a coil shape on a plane. When the center of the spiral spring 285 is connected to the reel 280 and rotates the reel 280 in a direction opposite to the winding direction of the spiral, the line 250 is released and is drawn out of the body. At this time, the spiral spring 285 is loosely released, and an elastic force is generated in the spiral spring 285 in the winding direction of the spiral.

By the spiral spring 285, the line 250 receives a force in the direction of winding the line 250 around the reel 280. In order to maintain the line 250, the reel 280 is A stopper 283 and a protrusion 281 for blocking rotation by the spring 285 may be provided.

19 is a cross-sectional view showing a reel 280 and a rotating member according to an embodiment of the present invention, and a protrusion 281, a spiral spring 285, and a stopper 283 are shown. The protrusion 281 protrudes to the outside of the reel 280 and may be formed in a form of a straight line in the direction of rotation by the spiral spring 285 and a gentle curve in the opposite direction. The stopper 283 maintains a state pushed in the direction of the reel 280 by an elastic member 283 ′ that applies a force in the center direction of the reel 280, supports the straight portion of the protrusion 281, and supports the reel 280 Prevent it from rotating.

When the control unit 160 controls the stopper 283 to apply a force in the direction away from the reel 280, the reel 280 is rotated by the elastic force of the spiral spring 285 as the coupling with the protrusion 281 is released. do. When the control unit 160 removes the force applied to the stopper 283, it moves toward the reel 280 again due to the elasticity of the elastic member 283'. The control unit 160 may control the stopper 283 to move or not move in a direction opposite to the elasticity of the elastic member 283 ′, thereby rotating or not rotating the reel 280. That is, the controller 160 may control the force received by the line 250 in the direction in which the reel 280 is wound.

The control unit 160 controls the force received in the direction in which the line 250 is wound around the reel 280, thereby providing convenience when the user measures the arm length.

On the other hand, in order to measure the length of the line 250, the second length measuring unit 286 is positioned under the reel 280, and the brush is connected to the line 250 regardless of the rotation of the reel 280. 287) may be provided.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those of ordinary skill in the art, and general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments presented herein, but is to be interpreted in the widest scope consistent with the principles and novel features presented herein.

Claims (10)

In the cardiovascular analyzer,
A cuff part surrounding a specific body part of the user and providing a changing pressing force to the specific body part;
A blood pressure measuring unit configured to measure a first blood pressure of the user according to a change in the pressing force;
A plurality of ECG (Electrocardiogram) sensor units attached to different body parts of the user and sensing a potential difference generated according to the user's heart activity;
A photoplethysmography (PPG) sensor unit that irradiates light through a light emitting means and senses an intensity of a reflected or transmitted light signal;
A conversion unit for converting into an electrocardiogram waveform by using the electric potential difference sensed for a predetermined time by the ECG sensor unit and converting to a pulse waveform by using the intensity of the optical signal sensed by the PPG sensor unit for a predetermined time;
A controller configured to recognize whether a re-measurement condition has been achieved based on at least one of the first blood pressure, the electrocardiogram waveform, and the pulse waveform; And
A vibration output unit located inside the cuff unit and outputting vibration feedback when the re-measurement condition is achieved;
Containing,
Cardiovascular analyzer.
delete The method of claim 1,
A sound output unit for outputting preset sound data when the re-measurement condition is achieved;
Further comprising,
Cardiovascular analyzer.
The method of claim 1,
A display unit for outputting information related to the re-measurement condition when the re-measurement condition is achieved;
Further comprising,
Cardiovascular analyzer.
The method of claim 1,
The control unit,
A heart rate per minute value is calculated using the ECG waveform,
Calculating a pulse rate per minute value using the pulse wave,
Recognizing that the re-measurement condition is satisfied when the difference between the heart rate per minute value and the pulse rate per minute value is equal to or greater than a predetermined value,
Cardiovascular analyzer.
The method of claim 1,
The control unit,
Calculate a pulse wave conduction velocity value based on the pulse wave,
An arteriosclerosis index is calculated based on the pulse wave conduction velocity value,
Recognizing the second blood pressure corresponding to the atherosclerosis index,
Recognizing that the re-measurement condition is satisfied when a difference value between the second blood pressure and the first blood pressure is equal to or greater than a predetermined value,
Cardiovascular analyzer.
The method of claim 6,
The control unit,
Using machine learning, a model for calculating the arterial stiffness index according to the pulse wave conduction rate is generated,
Inputting the pulse wave conduction rate value into an arteriosclerosis index calculation model according to the pulse wave conduction rate and calculating an output value as the arteriosclerosis index,
Cardiovascular analyzer.
The method of claim 7,
The arterial stiffness index calculation model according to the pulse wave conduction rate,
The training data is input into an artificial neural network, and an error is derived by comparing the output value obtained by inputting the training data with a correct answer value corresponding to the training data, and backpropagating the error to the artificial neural network, Generated by repeating the process of updating the weights a predetermined number of times,
Cardiovascular analyzer.
The method of claim 8,
The artificial neural network,
Including deep neural networks,
Cardiovascular analyzer.
The method of claim 1,
The cardiovascular analyzer,
It is produced in the form of a massage chair,
The cuff part,
It is provided in a first area for massaging the user's upper arm,
The ECG sensor unit,
It is provided in a second area around the user's hand,
The PPG sensor unit,
It is provided in a third area around the user's hand,
The second area is an area different from the third area,
Cardiovascular analyzer.

Images