KR20250171500A - A method and device for measuring blood pressure based on PPG sensor and artificial intelligence technology - Google Patents

Abstract

The present invention relates to a technology for measuring blood pressure using a PPG sensor, a method for measuring blood pressure using a PPG sensor and artificial intelligence technology, which detects a wearer's pulse signal using a ring-shaped bio-signal measuring device worn on a finger, extracts bio-information from the pulse signal, analyzes it using a machine learning algorithm, and estimates a blood pressure value.

Description

Blood pressure measurement method and device using PPG sensor and artificial intelligence technology {A method and device for measuring blood pressure based on PPG sensor and artificial intelligence technology}

The present invention relates to a technology for predicting hypertension by measuring blood pressure using a PPG sensor, detecting a pulse signal of a wearer using a ring-shaped bio-signal measuring device worn on a finger, extracting bio-information from the pulse signal, analyzing it using a machine learning algorithm to estimate a blood pressure level, and predicting hypertension, and relates to a blood pressure measuring method and measuring device using a PPG sensor and artificial intelligence technology.

The incidence of chronic diseases is increasing worldwide due to improved living standards and westernized eating habits, and among them, the number of patients with hypertension is steadily increasing.

Blood pressure, the pressure exerted by blood flowing through blood vessels against their walls, is one of the most important vital signs. Hypertension, which is abnormally high blood pressure, and hypotension, which is abnormally low blood pressure, are both conditions requiring management in their own right and can also act as causes or risk factors for various other diseases. Therefore, accurately monitoring blood pressure is crucial for maintaining good health.

High blood pressure is caused by a variety of environmental factors, including poor eating habits, family history, drinking, smoking, lack of exercise, and stress, and can be broadly divided into two types.

One is "essential hypertension," which occurs without an underlying disease. The other is "secondary hypertension," which develops secondary to conditions such as kidney disease, vascular abnormalities, or endocrine disorders. The incidence of secondary hypertension is estimated to be less than 5% among all hypertensive patients, and among these, hypertension caused by kidney disease accounts for a significant proportion. Conversely, if essential hypertension persists, the risk of developing kidney disease increases.

Therefore, regular blood pressure measurement and diagnosis of hypertension are necessary to prevent the onset of other diseases and treat hypertension.

Hypertension is typically diagnosed by measuring blood pressure using a blood pressure monitor, either at a hospital or at home, and then determining the severity based on the measured blood pressure. However, without a blood pressure monitor, this method is unavailable, and the difficulty of immediately measuring blood pressure in an emergency situation is particularly significant.

Moreover, in the case of the commonly used mercury sphygmomanometer (which applies pressure to the measurement site and slowly releases it while detecting the pulse with a stethoscope or hand, and measures blood pressure by the height of the mercury column that appears at the starting and ending points of the pulse), there was a problem that the measurement site became swollen or, in some cases, painful because the blood circulation was not properly achieved due to the need to press the measurement site.

Accordingly, research is being conducted and patents have been filed for a technology to check blood pressure by obtaining biometric information in a non-restrictive manner rather than using a structure worn on the patient's body, such as a mercury blood pressure monitor.

However, it is only a simple process of obtaining and confirming biometric information, and the accuracy of blood pressure is not high, and it cannot objectively predict the onset of hypertension.

In addition, since blood pressure must be measured periodically or as needed rather than continuously, there is inconvenience or inconvenience in measuring, and since measurement is intermittent rather than continuous, there is a problem of low accuracy.

As an example of a blood pressure measuring device, the applicant has been granted patent registration No. 2517533 (Blood pressure measuring device using ballistic cardiography and artificial intelligence technology).

Patent Publication No. 10-2517533 (March 30, 2023, Blood Pressure Measurement Device Using Ballistic Cardiography and Artificial Intelligence Technology) Public Utility Model Publication No. 20-2010-0009565 (September 29, 2010, Blood Pressure Measurement Device)

The present invention has been created to solve the above-mentioned problem, and uses a PPG (pulse wave) sensor to detect a wearer's pulse wave signal and analyze it with a machine learning algorithm to estimate a blood pressure level. In particular, by detecting the wearer's pulse wave signal using a ring-shaped bio-signal measuring device worn on a finger, the close contact with the skin is increased, thereby accurately detecting the pulse wave signal, thereby increasing the measurement accuracy. In particular, because it is in a ring shape, it is not cumbersome or uncomfortable to use, and blood pressure can be measured while wearing it for 24 hours without discomfort, thereby enabling continuous blood pressure management. The present invention relates to a blood pressure measuring method and measuring device using a PPG sensor and artificial intelligence technology.

The blood pressure measurement method using the PPG sensor and artificial intelligence technology of the present invention for solving the above problem comprises the steps of: receiving a pulse signal of a wearer measured at a set time interval through a ring-shaped bio-signal measuring device (10) worn on a finger; extracting bio-information from the plurality of pulse signals received and inputting it into a pre-learned machine learning algorithm to calculate a blood pressure value estimation and a hypertension prediction probability; A step of determining an alarm level by determining whether the calculated hypertension prediction probability falls within a set threshold range and outputting the determined alarm level; wherein the bio-signal measuring device (10) comprises a measuring device body (11) formed in a ring shape to be worn on the wearer's finger, a wearing position display unit (12) indicating a wearing position on one side of the outer surface of the measuring device body (11), a PPG sensor (13) installed on one side of the inner surface of the measuring device body (11) facing the inner side of the finger and in close contact with the inner skin of the finger to detect the wearer's pulse signal, and a control unit (14) receiving the pulse signal detected by the PPG sensor (13) and transmitting the pulse signal to a user terminal (20) through wireless communication.

The biometric information extracted from the above pulse signal includes HR (heart rate), HRV (heart rate variability), PI (an index related to the oxygen saturation of blood pressure and the quality of blood pressure signals), AC (an index representing changes in heart rate and blood pressure by measuring variability in changing blood pressure signals), SDNN (standard deviation of normal RR (heartbeat cycles per minute) intervals in the entire ballistocardiographic record), RMSSD (a value expressed as the square root of the average of the sum of the square roots of the differences in adjacent HRV intervals), PNN50 (a ratio of the number of intervals in which the difference in consecutive RR intervals exceeds 50 ms), LF (low frequency in the 0.04 to 0.15 Hz band), HF (high frequency in the 0.15 to 0.4 Hz band), HF_LF (LF divided by HF, frequency in the 0.5 to 2 MHz band), and further includes age and gender information as basic biometric information of the wearer.

At this time, it is preferable that the machine learning algorithm is a LSTM (Long Short Term Memory) algorithm.

The blood pressure measuring device utilizing the PPG sensor and artificial intelligence technology of the present invention comprises: a bio-signal measuring device (10) worn on a finger to acquire a pulse signal of a wearer; a user terminal (20) connected to the bio-signal measuring device (10) by wire or wirelessly to receive the pulse signal acquired from the bio-signal measuring device and to receive bio-information extracted from the pulse signal and to which a program having a machine learning algorithm for predicting high blood pressure is installed, or which is capable of accessing a server (30) on which the program is installed via a wireless communication network; wherein the bio-signal measuring device (10) comprises: a measuring device body (11) formed in the shape of a ring to be worn on a wearer's finger; a wearing position display unit (12) formed on one side of an outer surface of the measuring device body (11) to display a wearing position when the measuring device body (11) is worn on the wearer's finger; a PPG sensor (13) installed on one side of an inner surface of the measuring device body (11) facing the inside of the finger, and detecting the wearer's pulse signal while being in close contact with the inner skin of the finger when worn on the wearer's finger; It is composed of a control unit (14) installed in the measuring device body (11) and receiving a pulse signal detected from the PPG sensor (13) and transmitting the pulse signal to the terminal (20) through wireless communication.

On the inner surface of the measuring device body (11), guide protrusions (15) are formed to protrude to a certain length at positions spaced apart from each other on both sides of the PPG sensor (13). When the measuring device body (11) is worn on a finger, the guide protrusions (15) press both inner sides of the finger, thereby causing the inner central part of the finger to protrude and induce the skin to come into close contact with the PPG sensor (13).

Here, a temperature sensor (17) is installed on the inner surface of the measuring device body (11) to measure the skin temperature inside the wearer's finger.

According to the present invention having the above configuration, the wearer's pulse information is detected, analyzed using a machine learning algorithm, and blood pressure values are estimated to predict high blood pressure. In addition, since it is in the form of a ring that is worn on the wearer's finger, it is possible to measure in a state of more effective contact with the skin, thereby obtaining a pulse signal with higher accuracy than before, and accordingly, the accuracy of blood pressure measurement can be improved.

In particular, it is possible to wear it on the finger 24 hours a day in the form of a ring, so continuous blood pressure measurement is possible, and blood pressure management can be effectively done through continuous measurement without having to measure it at regular intervals or time intervals as in the past.

Figure 1 is a configuration diagram of a blood pressure measuring device utilizing a PPG sensor and artificial intelligence technology according to the present invention.
Figure 2 is a perspective view of a biosignal measuring device according to the present invention;
Figure 3 is a cross-sectional view of a biosignal measuring device according to the present invention;
Figure 4 is a diagram showing a state in which the inner central part of the finger is in contact with the PPG sensor by the inductive protrusion while wearing the biosignal measuring device according to the present invention on the finger.
Figure 5 is a flowchart showing a blood pressure measurement process using a PPG sensor and artificial intelligence technology according to the present invention.

Hereinafter, with reference to the attached drawings, a blood pressure measurement method and measurement device utilizing a PPG sensor and artificial intelligence technology according to a preferred embodiment of the present invention will be described in detail.

As illustrated, the blood pressure measuring device utilizing the PPG sensor and artificial intelligence technology according to the present invention acquires the pulse signal of the wearer using a biometric information measuring device (10) equipped with a PPG (pulse wave) sensor and transmits it to a user terminal (20), and the user terminal (20) analyzes the pulse signal received through a measurement program to extract the wearer's biometric information and measures blood pressure using the same.

The above biometric information measuring device (10) is manufactured in the form of a ring and is worn on the wearer's finger to measure blood pressure. As such, it has high adhesion to the skin and has little movement, allowing it to accurately detect pulse signals, thereby providing reliable and highly accurate results.

The above biometric information measuring device (10) transmits the pulse signal acquired to a user terminal (20) connected via wired or wireless communication, extracts biometric information from the user terminal (20), and inputs it into a machine learning algorithm to estimate a blood pressure value. The blood pressure value estimated in this way can be visually confirmed by the wearer through the screen of the user terminal.

The user terminal (20) is a terminal that is connected to the biometric information measuring device (10) by wire or wireless communication (short-range wireless communication), and is equipped with a memory for storing a measurement program, a microprocessor for executing the measurement program, and performing calculations and control.

For example, the user terminal is a terminal capable of communication, such as a personal computer (PC), a laptop, a personal digital assistant (PDA), a mobile communication terminal, a tablet terminal, etc. For convenience of use, a smart pad or smart phone carried by the wearer can be used as a mobile communication terminal.

A dedicated app (application) is installed on the user terminal (20) to connect to the server (30) for analyzing pulse signals, and the wearer's basic biometric information is input into the dedicated app, and the pulse signal detected by the biometric information measuring device (10) is collected through the dedicated app.

A machine learning algorithm is installed in the server (30), and the terminal (20) accesses the server to extract bio-information from the pulse signal received from the control unit (14), inputs this into the machine learning algorithm, analyzes it through machine learning, and estimates a blood pressure value. Measurement information including the estimated value is transmitted to the user terminal (20) and displayed on the screen.

Accordingly, when a dedicated app is run on a user terminal (20) and a pulse wave is measured by the biometric information measuring device (10), the measured pulse wave signal is used to extract biometric information (variables), and then the extracted biometric information is input into a machine learning algorithm to estimate a blood pressure level, determine an alarm level, and display the result on the screen. The wearer can predict high blood pressure along with the blood pressure level based on the information displayed on the screen of the user terminal.

Meanwhile, in the present invention, a machine learning algorithm is installed in the server (30) and configured to be accessed through a dedicated app from the user terminal (20). However, if the server (30) is not separately provided, a measurement program may be installed in the user terminal (20) to extract the wearer's biometric information using the pulse signal from the user terminal itself, thereby predicting blood pressure levels and hypertension.

The variables for estimating blood pressure are divided into dependent and independent variables. The dependent variable is blood pressure, and the independent variables are age, sex, HR (heart rate), HRV (heart rate variability), PI (an index related to the quality of oxygen saturation and blood pressure signals), AC (an index that represents changes in heart rate and blood pressure by measuring the variability of changing blood pressure signals), SDNN (standard deviation of normal RR (heart rate cycles per minute) intervals in the entire ballistocardiographic recording), RMSSD (the square root of the average of the sum of the square roots of the differences in adjacent HRV intervals), PNN50 (the ratio of intervals in which the difference in consecutive RR intervals exceeds 50 ms), LF (low frequency in the 0.04–0.15 Hz band), HF (high frequency in the 0.15–0.4 Hz band), and HF_LF (LF divided by HF, which is the frequency in the 0.5–2 MHz band) can be specified as variables.

The above biometric information measuring device (10) is composed of a measuring device body (11), a wearing position display unit (12), a PPG sensor (13), and a control unit (14) that communicates with a user terminal (20) via wired or wireless communication.

The measuring device body (11) is formed in a ring shape to be worn on the wearer's finger.

The above measuring device body (11) may be equipped with a separate storage case and configured to be wirelessly charged in the storage case. Since it is formed in a ring shape, the circuit may be configured to operate by supplying power by pulling it out from the storage case and putting it on the wearer's finger without having a separate power button.

Additionally, the operation of the control unit (14) can be configured to be turned on/off through a dedicated app installed on the user terminal (20).

At this time, a lamp that flashes when turned on by power supply may be installed in the measuring device body (11).

The wearing position indicator (12) is formed on one side of the outer surface of the measuring device body (11), and is a part that indicates the wearing position when worn on a finger.

The above-mentioned wearing position indicator (12) should be worn with the measuring device body (11) facing the upper outer side of the finger when worn on the finger.

The PPG sensor (13) is installed on one side of the inner surface of the measuring device body (11) facing the inside of the finger, and detects the wearer's pulse signal while in close contact with the skin on the inside of the finger.

The pulse signal detected from the above PPG sensor (13) is transmitted to the control unit (14).

The control unit (14) is configured to include a control board and a microcomputer (MCU), and receives pulse information detected by the PPG sensor (13) and transmits a pulse signal to a user terminal (20) connected via wired or wireless communication.

The control unit (14) may be configured to directly transmit the pulse signal detected by the PPG sensor (13) to the user terminal (20), or may be configured to temporarily store the pulse signal in a separate memory and then transmit it to the user terminal (20) via wired or wireless communication.

The above control board is formed flexibly due to the characteristics of the ring-shaped measuring body (11) and may be formed in a ring shape by being rolled up in the entire internal space of the measuring body (11), or may be formed in an arc shape with one side open in addition to a complete circular ring shape.

At this time, on the inner surface of the measuring device body (11), an induction protrusion (15) is formed to protrude at a certain length at positions spaced apart from each other on both sides of the PPG sensor (13).

The above-mentioned induction protrusion (15) presses both inner sides of the finger when the measuring device body (11) is worn on the finger, thereby causing the inner central part of the finger to protrude and induce the skin to come into close contact with the PPG sensor (13).

Accordingly, the PPG sensor (13) is in close contact with the skin, and the measuring device body (11) does not shake or move, so that the pulse signal can be accurately detected, and the accuracy of the pulse signal increases, so that more accurate blood pressure value estimation and measurement reliability can be increased.

Here, only one PPG sensor (13) may be provided, but for higher accuracy, two sensors may be provided and installed spaced apart from each other on the inner surface of the measuring device body (11).

When two PPG sensors are provided, the measurement program of the user terminal (20) adds up the pulse signals detected at the same time among the pulse signals input from the two PPG sensors, sets the average value as a reference value, extracts biometric information from the reference value, and inputs it into the machine learning algorithm to measure blood pressure. By measuring blood pressure using the average value of the two pulse signals, the accuracy in determining blood pressure value data and alarm level can be further increased.

Meanwhile, a temperature sensor (17) is installed on the inner surface of the measuring device body (11) to measure the skin temperature inside the wearer's finger, thereby measuring the wearer's body temperature and confirming the wearer's health status.

Additionally, the measuring device body (11) may be equipped with a three-axis gyro sensor (18).

The 3-axis gyro sensor (18) detects the movement of the wearer's hands or fingers as well as the movement of the body, and through this, the wearer's current posture and condition, such as exercise or sleep, can be checked.

A blood pressure measurement method using the artificial intelligence technology of the present invention is described.

The blood pressure measurement method using the artificial intelligence technology of the present invention receives the pulse signal of the wearer from a PPG sensor, extracts biometric information, inputs the extracted biometric information into a machine learning algorithm to estimate the output blood pressure value, and predicts the probability of hypertension based on the estimated value to confirm whether or not hypertension is present.

The blood pressure measurement method using the artificial intelligence technology of the present invention is performed by a computer, and the computer stores a computer program that performs the blood pressure measurement method. The computer refers to a broad computing device that includes not only general personal computers, including servers, but also smart devices such as smartphones and tablet PCs.

The blood pressure measurement method of the present invention includes a step of receiving a pulse signal from a PPG sensor, a step of calculating a probability of hypertension prediction using a blood pressure value, and a step of determining and outputting an alarm level.

Specifically, when a pulse signal is input from a PPG sensor, noise in the input signal is removed. To remove noise, the signal size of the input pulse signal is scaled.

A pulse signal corresponding to a preset minimum root mean square (RMS) value and maximum root mean square (RMS) value range is extracted from the scaled pulse signal, and a signal corresponding to a preset minimum amplitude value and maximum amplitude value is extracted from the extracted pulse signal, thereby completing noise removal of the final input pulse signal.

The pulse signal with noise removed is input into a machine learning algorithm to estimate blood pressure levels and output the probability of hypertension prediction.

As independent variables, basic biometric information such as age and gender are included, and as biometric information of pulse signal, HR (heart rate), HRV (heart rate variability), PI (an index related to the quality of oxygen saturation and blood pressure signal), AC (an index representing changes in heart rate and blood pressure by measuring variability with changing blood pressure signals), SDNN (standard deviation of normal RR (heartbeat cycles per minute) intervals in the entire ballistocardiographic record), RMSSD (the value expressed as the square root of the average of the sum of the square roots of the differences in adjacent HRV intervals), PNN50 (the ratio of the number of intervals in which the difference in consecutive RR intervals exceeds 50 ms), LF (low frequency in the 0.04–0.15 Hz band), HF (high frequency in the 0.15–0.4 Hz band), and HF_LF (the value of LF divided by HF, which is the frequency in the 0.5–2 MHz band) are designated as variables.

In the present invention, by additionally setting variables for age, sex, heart rate, heart rate variability, PI (an index related to the oxygen saturation of blood pressure and the quality of blood pressure signals), AC (an index indicating changes in heart rate and blood pressure by measuring variability with changing blood pressure signals), SDNN (standard deviation of normal RR (heart rate cycles per minute) intervals in the entire ballistocardiographic record), RMSSD (a value expressed as the square root of the average of the sum of the square roots of the differences in adjacent HRV intervals), and PNN50 (the ratio of the number of intervals in which the difference in consecutive RR intervals exceeds 50 ms), it is possible to estimate blood pressure values more accurately than in the past, thereby significantly increasing measurement accuracy as well as reliability.

That is, in the present invention, in addition to basic bio-information, the standard deviation of the normal RR (heartbeat cycle per minute) interval in the entire ballistic cardiogram record is used as a reference, and the variability is measured by changing the blood pressure signal as well as the indicators of the oxygen saturation of blood pressure and the quality of the blood pressure signal, thereby increasing the measurement accuracy by setting the indicators of the changes in heart rate and blood pressure as variables.

SDNN is a measure of heart rate variability and represents the standard deviation of heart rate cycle (RR) interval data over a one-minute period. SDNN measures heart rate cycle variability over a full minute, representing the standard deviation of normal RR intervals across all recordings detected by the PPG sensor over that one-minute period.

A decrease in SDNN may predict an increased risk of left ventricular dysfunction and ventricular tachycardia.

RMSSD is one of the measures of heart rate variability, and is the average of the square roots of the differences between consecutive heartbeat cycles (RR intervals).

The higher the RMSSD value, the healthier the condition.

PNN50 is expressed as the percentage of RR intervals in which the difference between consecutive RR intervals exceeds 50 ms.

The smaller the PNN50 value, the healthier the condition.

The average value of the detected biometric information, excluding age and gender, is calculated, and each calculated average value is input into the machine learning algorithm.

The above machine learning algorithm is an algorithm that allows a computer to learn on its own through input data, and the present invention uses the LSTM (Long Short Term Memory) algorithm.

The reason for using the LSTM (Long Short Term Memory) algorithm as the above machine learning algorithm is to increase measurement accuracy by enabling extraction of biometric information using independent variables at short time intervals.

The machine learning algorithm used in conventional blood pressure measuring devices is a multi-layer perceptron (MLP) algorithm that extracts bio-information using independent variables at 60-second intervals. However, in the present invention, by using the LSTM algorithm, bio-information can be extracted at shorter time intervals (e.g., 1-second intervals) from pulse signal data that changes over time.

Pulse signal data is input into the above machine learning algorithm to finally output a blood pressure value, and the probability of predicting high blood pressure is calculated based on the output value, and the alarm level is determined.

The above warning level can be classified into “safety”, “concern”, “caution”, and “suspicion”, and when the predicted probability of hypertension is 0% to 10%, it is judged as “safety”, when the predicted probability of hypertension is 11% to 30%, it is judged as “concern”, when the predicted probability of hypertension is 31% to 50%, it is judged as “caution”, and when the predicted probability of hypertension is 51% or more, it is judged as “suspicion” and output.

Through these steps, it is possible to diagnose whether the wearer has high blood pressure, and the output results can be monitored on the screen of the user's terminal.

10: Biosignal measuring device 11: Measuring device body
12: Wearing position indicator 13: PPG sensor
14: Control unit 15: Guide projection
17: Temperature sensor 18: 3-axis gyroscope sensor
20: User terminal 30: Server

Claims (8)

A step of receiving the wearer's pulse signal measured at set time intervals through a ring-shaped bio-signal measuring device (10) worn on the finger;
A step of extracting bio-information from a plurality of input pulse signals and inputting it into a pre-learned machine learning algorithm to calculate a blood pressure value estimation and a hypertension prediction probability;
A step of determining an alarm level by determining whether the calculated hypertension prediction probability falls within a set threshold range and outputting the result;
The above bio-signal measuring device (10) is characterized by comprising a measuring device body (11) formed in a ring shape to be worn on the wearer's finger, a wearing position indicating portion (12) indicating a wearing position on one side of the outer surface of the measuring device body (11), a PPG sensor (13) installed on one side of the inner surface of the measuring device body (11) facing the inside of the finger to detect the wearer's pulse signal while in close contact with the inner skin of the finger, and a control portion (14) that receives the pulse signal detected by the PPG sensor (13) and transmits the pulse signal to a user terminal (20) through wireless communication, a blood pressure measuring method using a PPG sensor and artificial intelligence technology.
In the first paragraph,
The biometric information extracted from the pulse signal includes HR (heart rate), HRV (heart rate variability), PI (an index related to the oxygen saturation of blood pressure and the quality of blood pressure signals), AC (an index indicating changes in heart rate and blood pressure by measuring variability in changing blood pressure signals), SDNN (standard deviation of normal RR (heartbeat cycles per minute) intervals in the entire ballistic cardiogram record), RMSSD (a value expressed as the square root of the average of the sum of the square roots of the differences in adjacent HRV intervals), PNN50 (a ratio of the number of intervals in which the difference in consecutive RR intervals exceeds 50 ms), LF (low frequency in the 0.04 to 0.15 Hz band), HF (high frequency in the 0.15 to 0.4 Hz band), and HF_LF (frequency in the 0.5 to 2 MHz band obtained by dividing LF by HF).
A blood pressure measurement method using a PPG sensor and artificial intelligence technology, characterized in that it further includes age and gender information as basic biometric information of the wearer.
In the first paragraph,
The above PPG sensors (13) are provided in two units and are installed spaced apart from each other on the inner surface of the measuring device body (11).
A blood pressure measurement method using a PPG sensor and artificial intelligence technology, characterized in that the pulse signals detected at the same time among the pulse signals received from two PPG sensors are searched, the pulse signals are added to calculate an average value, the calculated average value is set as a reference value, and then biometric information is extracted from the reference value and input into the machine learning algorithm.
In the first paragraph,
A blood pressure measurement method using a PPG sensor and artificial intelligence technology, characterized in that the above machine learning algorithm is an LSTM (Long Short Term Memory) algorithm.
A biosignal measuring device (10) worn on a finger to obtain the wearer's pulse signal;
It is composed of a user terminal (20) that is connected to the bio-signal measuring device (10) by wire or wirelessly and receives pulse signals acquired from the bio-signal measuring device, and a program in which a machine learning algorithm for predicting high blood pressure is built by inputting bio-information extracted from the pulse signals is installed, or a server (30) in which the program is installed, and is capable of connecting to the server through a wireless communication network.
The above biosignal measuring device (10) has a measuring device body (11) formed in the shape of a ring to be worn on the wearer's finger;
A wearing position display portion (12) formed on one side of the outer surface of the measuring device body (11) to indicate the wearing position when the measuring device body (11) is worn on the wearer's finger;
A PPG sensor (13) installed on one side of the inner surface of the measuring device body (11) facing the inside of the finger, and detecting the pulse signal of the wearer while being in close contact with the inner skin of the finger when worn on the wearer's finger;
A blood pressure measuring device utilizing a PPG sensor and artificial intelligence technology, characterized in that it comprises a control unit (14) installed in the measuring device body (11) to receive a pulse signal detected from the PPG sensor (13) and transmit the pulse signal to the terminal (20) via wireless communication.
In paragraph 5,
On the inner surface of the above measuring device body (11), guide protrusions (15) are formed to protrude at a certain length at positions spaced apart from each other of the PPG sensor (13).
A blood pressure measuring device utilizing PPG sensor and artificial intelligence technology, characterized in that the above-mentioned induction protrusion (15) presses both inner sides of the finger when the measuring device body (11) is worn on the finger, thereby causing the inner central part of the finger to protrude and induce the skin to come into close contact with the PPG sensor (13).
In paragraph 5 or 6,
The above PPG sensors (13) are provided in two units and are installed spaced apart from each other on the inner surface of the measuring device body (11).
The above program is a blood pressure measuring device utilizing a PPG sensor and artificial intelligence technology, characterized in that it adds pulse signals detected at the same time among pulse signals input from two PPG sensors, sets the average value as a reference value, and extracts biometric information from the reference value and inputs it into the machine learning algorithm.
In paragraph 5 or 6,
A blood pressure measuring device utilizing a PPG sensor and artificial intelligence technology, characterized in that a temperature sensor (17) is installed on the inner surface of the measuring device body (11) to measure the skin temperature inside the wearer's finger.