Blood pressure measurement method for wearable device and wearable device

1 . A wearable device, comprising:

a memory storing a computer program;

a processor coupled to a memory;

three pressure transducers (PTs); and

a photoplethysmography (PPG) sensor, wherein the PPG sensor comprises three light emitting diodes (LEDs) and one photo diode (PD), the one PD is located at a central position of the PPG sensor, and the three LEDs and the three PTs are all arranged around the PD in a circular array;

wherein the three PTs and the PPG sensor contact a wearer when the wearable device is in a worn state;

wherein the processor is configured to execute the computer program to cause the wearable device to perform operations comprising:

obtaining a plurality of pressure values collected by the three PTs;

obtaining a plurality of PPG signals collected by the PPG sensor; and

determining a blood pressure value of the wearer based on the plurality of pressure values and the plurality of PPG signals;

wherein the plurality of pressure values are in one-to-one correspondence with the plurality of PPG signals, and a collection moment of each pressure value of the plurality of pressure values is same as that of a corresponding PPG signal of the plurality of PPG signals; and

wherein the determining the blood pressure value of the wearer comprises:

respectively extracting waveform features of the plurality of PPG signals; and

determining, based on a first PPG signal whose waveform feature amplitude is less than or equal to a preset waveform feature amplitude, a pressure value corresponding to the first PPG signal as a systolic blood pressure (SBP) in the blood pressure value of the wearer.

2 . The wearable device according to claim 1 , wherein the determining the blood pressure value of the wearer comprises:

inputting the plurality of pressure values and the waveform features of the plurality of PPG signals into a neural network model, wherein the neural network model is trained based on a historical pressure value and a waveform feature of a historical PPG signal, and is configured to measure blood pressure; and

determining output of the neural network model as a diastolic blood pressure (DBP) in the blood pressure value of the wearer.

3 . The wearable device according to claim 1 , wherein before the obtaining the plurality of pressure values collected by the three PTs, the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

outputting an operation guide, wherein the operation guide is configured to guide the wearer to apply a pressure perpendicular to a contact surface between the wearable device and human skin to the wearable device, and the operation guide comprises a pressure value required for the wearer to press.

4 . The wearable device according to claim 3 , wherein the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

ending, during the pressure application by the wearer, blood pressure measurement based on at least one of the following conditions being satisfied:

an acceleration of the wearable device is greater than an acceleration threshold; and/or

an angular velocity of the wearable device is greater than an angular velocity threshold.

5 . The wearable device according to claim 3 , wherein the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

displaying a first interface, wherein a pressing position, prompt information, a pressure curve, and waveforms of the plurality of PPG signals are displayed on the first interface, the pressing position is a position where the wearer applies the pressure to the wearable device, the prompt information is used to prompt the wearer to apply the pressure to the wearable device based on the operation guide, and the pressure curve is the operation guide.

6 . The method according to claim 5 , wherein the pressing position comprises a first position and a second position of a screen of the wearable device, the first position is pressed by an index finger of the wearer, and the second position is pressed by a thumb of the wearer.

7 . The wearable device according to claim 5 , wherein the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

displaying the blood pressure value on the first interface.

8 . The wearable device according to claim 1 , wherein before the obtaining the plurality of pressure values collected by the three PTs, the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

detecting a triggering operation performed by the wearer on an automatic blood pressure measurement option; and

determining, in response to the triggering operation performed by the wearer on the automatic blood pressure measurement option, whether a measurement time is reached;

wherein the obtaining the plurality of pressure values collected by the three PTs comprises:

obtaining the plurality of pressure values collected by the three PTs when the measurement time is reached.

9 . The wearable device according to claim 8 , wherein the determining the blood pressure value of the wearer comprises:

inputting, based on historical data comprising at least one pressure value of the plurality of pressure values, the plurality of pressure values, a waveform feature of a PPG signal corresponding to the at least one pressure value in the historical data, and waveform features of the plurality of PPG signals into a neural network model, to obtain the blood pressure value, wherein the historical data is used to represent measured data during historical blood pressure measurement, and the neural network model is trained based on a historical pressure value and a historical PPG signal and is configured for the blood pressure measurement.

10 . The wearable device according to claim 8 , wherein the determining the blood pressure value of the wearer comprises:

inputting, based on historical data not comprising a pressure value in the plurality of pressure values, the plurality of pressure values and waveform features of the plurality of PPG signals into a neural network model to obtain a temporary blood pressure value, wherein the historical data is used to represent measured data during historical blood pressure measurement; and

determining the blood pressure value based on the temporary blood pressure value and a blood pressure value in the historical data.

11 . The wearable device according to claim 1 , wherein before the obtaining the plurality of pressure values collected by the three PTs, the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

determining whether the wearable device satisfies a measurement condition;

wherein the obtaining the plurality of pressure values collected by the three PTs comprises:

obtaining the plurality of pressure values collected by the three PTs based on the measurement condition being satisfied.

12 . The wearable device according to claim 11 , wherein the measurement condition comprises at least one of the following:

an acceleration of the wearable device is less than or equal to an acceleration threshold,

an initial pressure value is greater than or equal to a pressure threshold,

an angular velocity of the wearable device is less than or equal to an angular velocity threshold, or

an initial PPG signal satisfies a signal quality requirement,

wherein the acceleration is used to represent a contact situation between the wearable device and the wearer, and the initial pressure value is used to represent a tightness for wearing the wearable device.

13 . The wearable device according to claim 11 , wherein the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

prompting the wearer to wear the wearable device properly based on the measurement condition not being satisfied.

14 . The method wearable device according to claim 2 , wherein before the obtaining the plurality of pressure values collected by the three PTs, the processor is further configured to execute the computer program to cause the wearable device to perform operations comprising:

outputting an operation guide, wherein the operation guide is configured to guide the wearer to apply a pressure perpendicular to a contact surface between the wearable device and human skin to the wearable device, and the operation guide comprises a pressure value required for the wearer to press.