CN117122296A

CN117122296A - Blood pressure measurement method and wearable device

Info

Publication number: CN117122296A
Application number: CN202310452573.7A
Authority: CN
Inventors: 毛维高
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-04-17
Filing date: 2023-04-17
Publication date: 2023-11-28

Abstract

A blood pressure measurement method and wearable equipment relate to the field of wearable equipment. Wherein the method is applied to a wearable device wearable on a wrist, comprising: and acquiring a photoplethysmography (PPG) signal of the back of the wrist of the user and a pressure signal of the radial artery on the inner side of the wrist in a preset time period. Based on the pressure signal, combining first information indicating a magnitude of a phase difference of the PPG signal and the pressure signal to obtain a first blood pressure; wherein the first blood pressure is the blood pressure of the arteriole. And converting the first blood pressure into a second blood pressure, wherein the second blood pressure is the blood pressure of the brachial artery of the user. By adopting the scheme, the accuracy of blood pressure measurement can be improved, and a more accurate reference basis is provided for blood pressure judgment of a user.

Description

Blood pressure measurement method and wearable device

Technical Field

The embodiment of the application relates to the field of wearable equipment, in particular to a blood pressure measurement method and wearable equipment.

Background

Blood pressure is one of the most commonly measured clinical parameters. The existing blood pressure measurement methods can be classified into a cuff measurement method and a sleeveless measurement method.

The cuff type measuring method needs frequent pressurization blocking in the measuring process, and has low comfort; moreover, the existing cuff type measuring equipment generally adopts a form of an external large-volume pump and an armband type air bag, has poor portability and is inconvenient for daily measurement. Compared with the cuff-type measuring method, the cuff-free-type measuring method can overcome the problems of low comfort and inconvenience in daily measurement. However, currently used cuff-free measurement methods, such as pulse wave velocity (pulse wave velocity, PWV) and Photoplethysmographic (PPG), have low accuracy of measurement results, and cannot be used as a reference basis for blood pressure measurement.

Disclosure of Invention

In view of the above, the application provides a blood pressure measurement method and a wearable device, which can improve the accuracy of blood pressure measurement and provide a more accurate reference basis for blood pressure judgment of a user.

In a first aspect, the present application provides a blood pressure measurement method applied to a wearable device, such as a smart watch, a smart bracelet, etc., which is wearable on a wrist. The method comprises the following steps: and acquiring a photoplethysmography (PPG) signal of the back of the wrist of the user and a pressure signal of the radial artery on the inner side of the wrist in a preset time period. Based on the pressure signal, a first blood pressure is obtained in combination with first information indicative of a magnitude of a phase difference of the PPG signal and the pressure signal. Wherein the first blood pressure is the blood pressure of the arterioles. The first blood pressure is converted to a second blood pressure, the second blood pressure being the blood pressure of the brachial artery of the user.

Unlike PPG signals measured by light irradiation, the following are: the pressure signal is obtained by measuring the pressure generated by direct contact, and thus the accuracy of the data measured by the pressure signal tends to be higher. By adopting the method and the device, the wearable device calculates the blood pressure component of the arteriole through the first information and the pressure signal, instead of directly using the PPG signal to determine the blood pressure component of the arteriole, and the accuracy of the determined blood pressure component of the arteriole can be improved. In addition, although there is a scheme of measuring blood pressure using PPG signals and pressure signals in the conventional art, it does not take into consideration a phase difference between two blood vessels, and it is not possible to obtain a blood pressure component of the arterioles by reasonably utilizing a difference in blood pressure influence time. It will be appreciated that on the basis of obtaining a more accurate blood pressure component of the arteriole, a more accurate blood pressure of the brachial artery may also be converted.

In one possible design manner of the first aspect, after acquiring the photoplethysmography PPG signal at the micro-artery on the back of the wrist and the pressure signal at the radial artery on the inner side of the wrist of the user for a preset period of time, the method further includes: a PPG waveform corresponding to the PPG signal and a pressure waveform corresponding to the pressure signal are generated. Wherein the first information includes a phase difference of the PPG waveform and the pressure waveform. Alternatively, the first information includes a phase difference of the PPG waveform and the pressure waveform, and a period of the PPG waveform or the pressure waveform, so that the magnitude of the phase difference can be measured by the relative magnitudes of the phase difference and the period.

In another possible implementation manner of the first aspect, the obtaining the first blood pressure based on the pressure signal in combination with first information indicating a magnitude of a phase difference between the PPG signal and the pressure signal includes: and taking the signal amplitude of the pressure waveform and the first information as input, and operating a first AI model to obtain a first blood pressure. The first AI model has a function of calculating the blood pressure component of the micro artery according to the phase magnitude of the blood pressure variation waveform of the micro artery and the blood pressure variation waveform of the radial artery and the amplitude of the blood pressure variation waveform of the radial artery.

By adopting the design mode, the wearable device can predict the blood pressure component of the micro-artery, namely the first blood pressure through the AI model.

In another possible design manner of the first aspect, the converting the first blood pressure into the second blood pressure includes: the first blood pressure is converted to a second blood pressure based on the first parameter. Wherein the first parameter comprises one or more of the following parameters: parameters for reflecting the degree of obesity of the user, parameters for reflecting the degree of tightness of the wearable device wearing, and parameters for reflecting the skin condition of the user.

By adopting the design mode, when the wearable device converts the blood pressure component (namely the first blood pressure) of the micro artery into the blood pressure (namely the second blood pressure) of the radial artery, the wearable device can refer to the personalized parameter (namely the first parameter) of the user for conversion so as to improve the rationality of the conversion.

In another possible design manner of the first aspect, the first parameter includes: the wearable device's wearing circumference, body mass index BMI, and skin elasticity.

In another possible design of the first aspect, the converting the first blood pressure into the second blood pressure based on the first parameter includes: substituting the first parameter and the first blood pressure into a preset relational expression to obtain a second blood pressure. Or, taking the first parameter and the first blood pressure as inputs, and operating the second AI model to obtain the second blood pressure. Wherein the second AI model has a function of predicting the blood pressure of the brachial artery from the blood pressure component of the arteriole and the first parameter.

By adopting the design mode, the wearable equipment can obtain the second blood pressure through conversion by the preset relational expression or the AI model, and the intelligence of obtaining the second blood pressure is improved.

In a further possible embodiment of the first aspect, the first blood pressure comprises a first systolic pressure and a first diastolic pressure, and the second blood pressure comprises a second systolic pressure and a second diastolic pressure. Converting the first blood pressure to a second blood pressure based on the first parameter, comprising: based on the first parameter, the first systolic pressure is converted to a second systolic pressure and the first diastolic pressure is converted to a second diastolic pressure.

In another possible design manner of the first aspect, obtaining a photoplethysmography PPG signal at a micro-artery at a back of a wrist of the user and a pressure signal at a radial artery inside the wrist for a preset period of time includes: and responding to a first event, acquiring a photoplethysmography (PPG) signal at a micro-artery at the back of the wrist and a pressure signal at a radial artery at the inner side of the wrist of the user within a preset time period, wherein the first event is used for triggering blood pressure measurement.

In the design mode, the wearable device can respond to the event triggering the blood pressure measurement, start to acquire data for calculating the blood pressure, and flexibly meet the requirements of various blood pressure measurement.

In another possible design of the first aspect, the first event includes at least one of: receiving an operation triggering blood pressure measurement; receiving voice triggering blood pressure measurement; and, the preset time arrives.

In another possible design manner of the first aspect, the method further includes: acquiring motion information of the wearable device in a preset time period, and detecting the motion time period of the wearable device in the preset time period based on the motion information. Based on the pressure signal, combining first information indicative of a magnitude of a phase difference of the PPG signal and the pressure signal, obtaining a first blood pressure, comprising: and if the movement duration is lower than a preset threshold value, based on the pressure signal, combining first information indicating the phase difference between the PPG signal and the pressure signal to obtain the first blood pressure.

By adopting the design mode, the wearable device can use the PPG signal and the pressure signal to calculate the blood pressure under the condition that no movement or short movement occurs, and the inaccuracy of the measured PPG signal or pressure signal caused by continuous movement is avoided, so that the accuracy of blood pressure calculation is influenced. In this way, the accuracy of blood pressure measurement can be improved.

In another possible design manner of the first aspect, the method further includes: if the movement time length is higher than or equal to a preset threshold value, a first prompt is sent out, and the first prompt is used for prompting to restart measuring blood pressure. The first event includes: an operation to resume measuring blood pressure is received.

In another possible design of the first aspect, the motion information includes acceleration information.

In a second aspect, embodiments of the present application further provide a wearable device, the wearable device being wearable on a wrist, the wearable device including a photoplethysmography, PPG, sensor, memory, and processor coupled; the PPG sensor is for acquiring PPG signals of a wrist back arteriole, the pressure sensor is for acquiring pressure signals of a wrist inner radial artery, and the memory has stored therein computer program code comprising computer instructions which, when executed by the processor, cause the wearable device to perform the method as in the first aspect and any of its possible designs.

In one possible design manner of the second aspect, the wearable device further includes an operation detection module (such as an acceleration sensor), and the motion detection module is configured to detect a motion condition of the wearable device.

In a third aspect, the present application also provides a chip system for use in a mobile terminal comprising a photoplethysmography, PPG, sensor, pressure sensor, processor and memory, the chip system comprising one or more interface circuits and one or more processors interconnected by wires, the interface circuits being arranged to receive signals from the memory of the mobile terminal and to transmit signals to the processor, the signals comprising computer instructions stored in the memory, which when executed by the processor cause the wearable device to perform the method of the first aspect and any of its possible designs.

In a fourth aspect, the application also provides a computer readable storage medium comprising computer instructions which, when run on a wearable device, cause the wearable device to perform the method of the first aspect and any of its possible designs.

In a fifth aspect, the present application provides a computer program product which, when run on a computer, causes the computer to perform the method according to the second aspect and any one of its possible designs.

It will be appreciated that the advantages achieved by the wearable device, the chip system, the computer readable storage medium, the computer program product provided above may refer to the advantages of the first aspect and any one of the possible designs thereof, and are not further described herein

Drawings

FIG. 1 is a schematic diagram of an arterial branch provided by an embodiment of the present application;

FIG. 2 is a schematic illustration of the location of the arterioles, radial arteries, and ulnar arteries provided in an embodiment of the application;

fig. 3 is a working schematic diagram of a PPG sensor according to an embodiment of the present application;

FIG. 4 is a schematic flow chart of a blood pressure measurement method according to an embodiment of the present application;

fig. 5 is a hardware composition diagram of a wearable device according to an embodiment of the present application;

Fig. 6 is a schematic diagram of the positions of the pressure sensor and the PPG sensor according to an embodiment of the present application;

FIG. 7 is a second schematic diagram of the positions of the pressure sensor and the PPG sensor according to the embodiment of the present application;

fig. 8 is a diagram showing a positional relationship between each module and a wrist when the smart phone provided by the embodiment of the application is in a wearing state;

FIG. 9 is a diagram of one of the mobile phone interface diagrams according to the embodiment of the present application;

FIG. 10 is a schematic diagram of waveform clipping according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a phase difference provided by an embodiment of the present application;

FIG. 12 is a second flowchart of a blood pressure measurement method according to an embodiment of the present application;

FIG. 13 is a third flow chart of a blood pressure measurement method according to an embodiment of the present application;

FIG. 14 is a flowchart of a blood pressure measurement method according to an embodiment of the present application;

FIG. 15 is a flowchart of a blood pressure measurement method according to an embodiment of the present application;

FIG. 16 is a second diagram of a mobile phone interface according to an embodiment of the present application;

FIG. 17 is a block diagram of a blood pressure measuring device according to an embodiment of the present application;

fig. 18 is a component structure diagram of a chip system according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application are described below with reference to the accompanying drawings in the embodiments of the present application. In the description of embodiments of the application, the terminology used in the embodiments below is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include, for example, "one or more" such forms of expression, unless the context clearly indicates to the contrary. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" means one or more than two (including two). The term "and/or" is used to describe an association relationship of associated objects, meaning that there may be three relationships; for example, a and/or B may represent: a alone, a and B together, and B alone, wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise. The term "coupled" includes both direct and indirect connections, unless stated otherwise. The terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated.

In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

Before explaining the embodiments of the present application, technical terms related to the present application are briefly described:

1. and (5) blood vessels.

The blood circulation system is composed of a heart, which is a dynamic organ that pushes blood to flow, and a blood vessel, which is a conduit for blood to flow. Blood vessels are classified into three major categories, arterial, capillary and venous. Arteries originate from the heart, branch continuously, taper in caliber, and gradually increase in wall thickness, and finally divide into a large number of capillaries, and are distributed among tissues and cells of the whole body. The capillaries rejoin and gradually form veins. During blood circulation, blood ejected from the ventricles returns to the atrium via arteries, capillaries and veins.

Referring to fig. 1, taking the brachial artery of the arteries as an example, branches of the brachial artery include the ulna and the radial artery, branches of the radial artery include the interosseous anterior artery, which may further branch into arterioles. Referring to fig. 2, there are typically a large number of arterioles on the back of the wrist of the human body, and radial (on the side near the thumb) and ulnar (on the side near the little finger) arteries on the inside of the wrist. It should be understood that "pulse" in the pulse refers to the radial artery described above.

2. Blood Pressure (BP).

Blood pressure is the lateral pressure of blood acting on the wall of a blood vessel per unit area when flowing in the blood vessel, and is the motive force for pushing the blood to flow in the blood vessel. Wherein the blood vessels are divided into arteries, capillaries and veins. Accordingly, blood pressure can be divided into arterial blood pressure, capillary blood pressure, and venous blood pressure. The blood pressure in daily life refers to the blood pressure of the brachial artery in the artery. It is understood that measuring blood pressure herein is also the blood pressure of the brachial artery.

3. Systolic (systolic blood pressure, SBP), diastolic (diastolic blood pressure, DBP).

Blood pressure further includes systolic (i.e., high pressure as people speak during daily life) and diastolic (i.e., low pressure as people speak during daily life). Systolic pressure refers to the pressure at which the heart contracts by pumping blood into the artery, which expands to cushion the pressure, at which time the blood pressure is systolic. Diastolic pressure refers to the time when the heart is diastolic, the artery contracts so that blood returns to the heart, and the blood pressure at this time is the diastolic pressure.

4. A PPG sensor.

A PPG sensor is a sensor that irradiates light into the skin and measures light scattering due to blood flow. Referring to fig. 3, ppg sensors typically include a light emitter (e.g., the LED in fig. 3) and a light detector. The light emitter emits a light beam with a certain wavelength to irradiate the skin, and the light beam is reflected to the light detector after penetrating the skin (such as epidermis, dermis and/or subcutaneous tissue in fig. 3), and the light beam is attenuated to a certain extent. It will be appreciated that the absorption of light by muscles, bones, veins, etc. is substantially unchanged without a substantial change in the measurement site. However, the absorption of light by arteries due to blood flow varies between systole and diastole. Just as the absorption of light by arteries varies while the absorption of light by other tissues (such as the aforementioned muscles, bones, veins, etc.) is substantially unchanged, a waveform reflecting the characteristics of blood flow (referred to herein as a PPG waveform) can be obtained by extracting an alternating component (referred to herein as a PPG signal) in an electrical signal corresponding to an optical signal after measuring the optical signal by a photodetector for a period of time. Thereby being used for determining physiological parameters such as blood oxygen saturation, blood pressure, heart rate and the like.

The technical terms are helpful for understanding the scheme, and the technical scheme of the embodiment of the application is described below in combination with the technical terms.

The blood pressure measuring method and the wearable device provided by the embodiment of the application can be applied to a scene of measuring blood pressure.

For example, it can be applied to the measurement of daily blood pressure. For example, when a user needs to measure blood pressure, the wearable device can be triggered to start to execute the blood pressure measurement method, so that the blood pressure measurement requirement of the user can be flexibly met.

Also exemplary, it can be applied to the scenes of daytime and nighttime blood pressure monitoring, dynamic blood pressure tracking of hypertensive patients, arytenoid/non-arytenoid blood pressure tracking, etc. For example, the timing time may be set by the user or the wearable device automatically sets the timing time, and after the timing time arrives, the wearable device may be triggered to start executing the blood pressure measurement method, so that the blood pressure of the user may be continuously monitored at a fixed time. The obtained blood pressure can be more accurately used for blood pressure evaluation (such as whether hypertension exists) and judgment of hypertension type (such as arytenoid/non arytenoid type).

In the conventional art, the blood pressure may be measured using a cuff-type measurement method or a sleeveless-type measurement method. The cuff type measuring method needs frequent pressurization blocking in the measuring process, and has low comfort; moreover, the existing cuff type measuring equipment generally adopts a form of an external large-volume pump and an armband type air bag, has poor portability and is inconvenient for daily measurement.

Compared with the cuff-type measuring method, the cuff-free-type measuring method can overcome the problems of low comfort and inconvenience in daily measurement. However, the currently used cuff-free measurement methods, such as PWV method and PPG method, have low accuracy of measurement results, and it is difficult to achieve standards of measurement accuracy for blood pressure in various countries or internationally, such as standards of american society of medical and instrument (The Association for the Advancement of Medical Instrumentation, AAMI), the british society of hypertension (British Hypertension Society, BHS), international organization for standardization (International Organization for Standardization, ISO), and institute of electrical and electronics engineers (Institute of Electrical and Electronics Engineers, IEEE) 1708. Therefore, the PWV method and PPG method described above cannot generally be used as reference bases for blood pressure measurement.

Based on the above-mentioned problems in the conventional technology, referring to fig. 4, an embodiment of the present application provides a blood pressure measurement method, which can be applied to a wearable device that is wearable on a wrist. The wearable device can collect pressure signals of radial artery inside the wrist and PPG signals of the back of the wrist. It should be understood that the blood vessels in the back of the wrist are mainly arterioles, and thus, the PPG signal in the back of the wrist can also be regarded as the PPG signal in the arterioles in the back of the wrist (hereinafter collectively referred to as arterioles). The wearable device uses the pressure signal in combination with information (which may be referred to as first information) that may indicate the magnitude of the phase difference of the pressure signal and the PPG signal to predict the blood pressure component (which may be referred to as first blood pressure) of the arteriole.

In practice, arteries originate from the heart, continue to branch, and eventually divide into a large number of capillaries. The earlier the blood pressure effect time on the artery near the front end is, the later the blood pressure effect time on the artery near the end is, during systole or diastole. And, as the artery branches off, the pressure of the blood against the vessel is also dispersed. That is, for two blood vessels, there is a relationship between the blood pressure influence time and the blood pressure value as follows: the blood vessel near the front end has earlier blood pressure influence time and higher blood pressure value; blood vessels near the tip have a later blood pressure impact time and lower blood pressure values.

As shown in connection with fig. 1, the ulnar artery may branch into a micro-artery, while the ulnar artery and the radial artery are the same level of arteries. I.e. the radial artery is closer to the front end and the arteriole is closer to the end. Thus, when the heart contracts or expands, the blood pressure of the radial artery affects the blood pressure earlier than the blood pressure of the arteriole, and the blood pressure of the radial artery is higher than the blood pressure of the arteriole.

Then, after knowing the difference in the time of influence of the blood pressure of the two blood vessels and the blood pressure of one of the blood vessels, the blood pressure of the other blood vessel can be determined. The blood pressure is reduced by Deltax when the blood pressure influence time is delayed by Deltat, the difference of the blood pressure influence time of two blood vessels is tx, the blood pressure of one blood vessel close to the front end is x0, and the blood pressure of the other blood vessel close to the rear end is x0- (tx/Deltat) Deltax.

Therefore, in the embodiment of the present application, after acquiring the pressure signal of the radial artery and the PPG signal of the micro artery, the wearable device may use the first information to represent: the difference in blood pressure of the two vessels (i.e., radial artery and arteriole) affects time. That is, the difference between the time of the systolic or diastolic effect on the radial artery and the time of the arterial effect on the arteriole is shown. And the wearable device may correspond the signal amplitude of the pressure waveform to the blood pressure of the radial artery. Based on this, the wearable device can then calculate the blood pressure component of the arterioles.

Unlike PPG signals measured by light irradiation, the following are: the pressure signal is obtained by measuring the pressure generated by direct contact, and thus the accuracy of the data measured by the pressure signal tends to be higher. By adopting the embodiment of the application, the wearable device calculates the blood pressure component of the arteriole through the first information and the pressure signal, rather than directly using the PPG signal to determine the blood pressure component of the arteriole, and the accuracy of the determined blood pressure component of the arteriole can be improved. In addition, although there is a scheme of measuring blood pressure using PPG signals and pressure signals in the conventional art, it does not take into consideration a phase difference between two blood vessels, and it is not possible to obtain a blood pressure component of the arterioles by reasonably utilizing a difference in blood pressure influence time.

Finally, the wearable device converts the blood pressure component of the arteriole to the blood pressure of the brachial artery (which may be referred to as a second blood pressure). Thereby obtaining what is conventionally referred to as blood pressure. It will be appreciated that on the basis of the above-described blood pressure component which results in a more accurate arteriole, a more accurate brachial artery blood pressure can also be converted.

The following describes possible product forms of the wearable device and structural components of the wearable device.

For example, the wearable device may be a device that is wearable on a wrist, such as a smart watch, a smart bracelet, a smart wristband, or a smart jewelry. The embodiment of the application does not limit the specific type of the wearable device. In one aspect, the wearable device may detect PPG signals of wrist dorsal arterioles; on the other hand, the wearable device may detect a pressure signal of the radial artery inside the wrist. And thus for blood pressure prediction.

Referring to fig. 5, a hardware configuration diagram of a wearable device (such as a smart watch) that is wearable on a wrist is provided in an embodiment of the present application. As shown in fig. 5, the wearable device includes: processor 510, display 520, ppg sensor 530, pressure sensor 540, acceleration (ACC) sensor 550, memory 560, and wireless communication module 570. Processor 510 may include one or more interfaces for interfacing with other components of the electronic device. Wherein the one or more interfaces may include: input/Output (I/O) interfaces (also known as I/O pins), interrupt pins, and data bus interfaces, among others. Wherein the data bus interface may comprise: one or more of a serial peripheral interface (serial peripheral interface, SPI), an integrated circuit (inter-integrated circuit, I2C) interface, and the like.

Processor 510 may include, among other things, one or more processing units, such as: processor 510 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.

The processor 510 may generate operation control signals according to the instruction operation code and the timing signals to complete instruction fetching and instruction execution control.

A memory may also be provided in the processor 510 for storing instructions and data. In some embodiments, the memory in processor 510 may be a cache memory. The memory may hold instructions or data that are used or used more frequently by the processor 510. If the processor 510 needs to use the instruction or data, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 510 is reduced, thereby improving the efficiency of the system.

In some embodiments, the processor 510 may be used to perform the calculation of the blood pressure prediction. For example, processor 510 may predict blood pressure based on a phase difference of the pressure waveform and the PPG waveform, a period of the PPG waveform, and a signal amplitude of the pressure waveform.

The display 520 is used to display images, videos, and the like. The display 520 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED) or an active-matrix organic light-emitting diode (matrix organic light emitting diode), a flexible light-emitting diode (flex), a mini, a Micro led, a Micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, QLED), or the like. In some embodiments, the wearable device may include 1 or more display screens 520.

In some embodiments, display 520 may display predicted blood pressure values, relevant controls for blood pressure measurements, such as a start control, an end control, and the like.

Memory 560 may be used to store computer-executable program code that includes instructions. The memory 560 may include a stored program area and a stored data area. The storage program area may store an application program (such as a sound playing function, an image playing function) required for at least one function of the operating system, etc. The storage data area may store data created during use of the wearable device (e.g., audio data, phonebook, etc.), and so on. In addition, memory 560 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash memory (universal flash storage, UFS), and the like. The processor 510 performs various functional methods or data processing of the wearable device by executing instructions stored in the memory 560 and/or instructions stored in a memory provided in the processor.

The wireless communication module 570 may support data exchange between electronic devices and other electronic devices including bluetooth, global navigation satellite system (global navigation satellite system, GNSS), wireless local area network, frequency modulation (frequency modulation, FM), near field wireless communication technology (near field communication, NFC), infrared technology (IR), and the like.

The PPG sensor 530 is used to emit light and detect a reflected light signal, and convert the light signal into an electrical signal. The alternating component of the electrical signal may reflect the characteristics of the blood flow and may thus be used to calculate blood pressure.

The pressure sensor 540 is used for sensing a pressure signal, and may convert the pressure signal into an electrical signal. The pressure sensor 540 is of a wide variety, such as a resistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, and the like. The capacitive pressure sensor may be a capacitive pressure sensor comprising at least two parallel plates with conductive material. When a force is applied to the pressure sensor 540, the capacitance between the electrodes changes. The wearable device determines the strength of the pressure from the change in capacitance.

Taking the example that the wearable device is a smart watch, see fig. 6 and 7, the PPG sensor 530 is disposed on the back of the dial of the smart watch. And, the pressure sensor 540 is provided on the back of the watch band of the smart watch. Further, since the radial artery is located inside the wrist, the pressure sensor 540 is provided in the area of the wristband immediately inside the wrist when the smart watch is in the worn state. It should be appreciated that PPG sensor 530 and pressure sensor 540 shown in dashed lines in fig. 6 are shown in an invisible state. The PPG sensor 530 and the pressure sensor 540 shown in solid lines in fig. 7 are shown in a visible state.

Referring to fig. 8, with the arrangement shown in fig. 6 and 7, when the user wears the smart watch normally, the back of the dial is closely attached to the back of the wrist, and then the PPG sensor 530 disposed on the back of the dial can detect the blood flow characteristics in the arterioles on the back of the wrist, so as to obtain a PPG signal. And, in case that the user wears the smart watch normally, the back of the wristband is closely attached to the wrist, and then the pressure sensor 540 provided inside the wristband may detect a pressure signal applied to the pressure sensor 540 by the radial artery inside the wrist due to the blood flow.

In some embodiments, the wearable device further comprises an acceleration sensor 550. The acceleration sensor 550 may be used to detect the magnitude of acceleration of the wearable device in various directions (typically three axes). Thereby being used to determine the movement of the wearable device. For example, the wearable device can measure blood pressure without movement of the wearable device, so that the accuracy of a measurement result is prevented from being influenced by movement of the wearable device.

It should be noted that, in actual implementation, the hardware components of the wearable device are not limited to those shown in fig. 5. The wearable device may also include, for example, a power management module, a battery, a camera, a motor, keys, and the like.

The blood pressure measuring method provided by the embodiment of the application can be realized in the wearable equipment. In the following, taking the example that the wearable device is a smart watch as an example, the blood pressure measurement method provided by the embodiment of the application is further described in detail.

During the operation of the smart watch, after detecting an event of starting blood pressure measurement, the blood pressure measurement can be started.

In some embodiments, the event that begins the blood pressure measurement may be an operation that begins the blood pressure measurement. For example, the smart watch may provide a blood pressure measurement control and/or a blood pressure measurement button, and the operation of starting blood pressure measurement may be a preset operation (such as clicking, long pressing, etc.) of the blood pressure measurement control and/or the blood pressure measurement button by the user. For example, the smart watch may display the interface 901 shown in fig. 9, the blood pressure measurement control is a "start" button in the interface 901, and the operation of starting the blood pressure measurement may be a click operation of the "start" button in the interface 901 by the user.

Of course, the operation of starting the blood pressure measurement is not limited thereto. For example, the operation of starting the blood pressure measurement may also be a tap operation of the dial by the user; or the user inputs a preset voice operation, such as inputting a voice of "please start measuring blood pressure".

In other embodiments, the event that begins the blood pressure measurement may also be an event that arrives at a timed time. For example, the user may set the time to measure blood pressure at regular intervals in the smart watch, such as setting to measure blood pressure once every 3 hours, or setting to measure blood pressure at 8, 14, and 20 points each day. Then, after the timing time has arrived, the smart watch may trigger the start of blood pressure measurement.

Because pressure sensor sets up in the table area, and PPG sensor sets up in the dial plate bottom, then, in order to realize that pressure sensor can gather the pressure signal of wrist inboard radial artery, PPG sensor can gather the PPG signal of wrist back micro-artery, then need guarantee at blood pressure measurement's in-process, the dial plate is located at the wrist back, the watchband surrounds the wrist inboard. That is, the smart watch is guaranteed to be in a normal wearing state. Based on this, in some embodiments, the smart watch may prompt the user to adjust the smart watch to be in a normal wearing state after detecting an event that begins blood pressure measurement. For example, in response to a clicking operation of a "start" button in the interface 901 shown in fig. 9 by a user, an interface 904 shown in fig. 9 may be displayed, where the interface 904 includes a prompt text "please confirm that the watch is worn normally, and the dial is located at the back of the wrist", so as to prompt the user to adjust that the smart watch is worn normally. Accordingly, in this embodiment, the smart watch starts blood pressure measurement in response to the user confirming that the smart watch is correctly worn. Illustratively, the interface 904 shown in fig. 9 further includes a "confirm" button, and the operation of confirming that the smart watch is worn correctly may be a click operation of the "confirm" button in the interface 904 shown in fig. 9 by the user.

After starting the blood pressure measurement, the smart watch may then start acquiring PPG signals as well as pressure signals. For example, after starting a blood pressure measurement, a PPG sensor in the smart watch may be activated to acquire a PPG signal, and a pressure sensor in the smart watch may be activated to acquire a pressure signal.

It should be understood that blood pressure is a changing process. Therefore, the smart watch may acquire PPG signals and pressure signals for a preset period of time (e.g., 30 seconds, 60 seconds, etc.) to predict blood pressure.

Since at least the preset time period needs to be detected, the user needs to wait for the preset time period. Based on this, in some embodiments, in response to an event that begins a blood pressure measurement, the smart watch may issue a prompt that a measurement is being made to prompt the user that a measurement is being made. Taking the example of a user clicking the "start" button in the interface 901 of fig. 9 as an event for starting blood pressure measurement, the smart watch may display the interface 902 of fig. 9 in response to the user clicking the "start" button in the interface 901 of fig. 9. The prompt text "in measurement, please be … …" is included in the interface 902 to prompt the user that measurement is in progress.

In some scenarios, during the measurement of blood pressure, the part (i.e. wrist) wearing the smart watch may be in motion. If the wrist moves, the PPG signal or the pressure signal obtained is not only a result of blood flow, but is further doped with a result of movement. Taking a pressure sensor as an example, if the wrist moves, the pressure signal acquired by the pressure sensor is not only the pressure generated by the blood flow in the radial artery on the pressure sensor, but also the pressure of the wrist on the pressure sensor caused by the acceleration of the movement.

It will be appreciated that if the PPG signal or pressure signal obtained is doped with a motion-induced result, then the PPG signal and pressure signal are subsequently used to predict blood pressure, possibly resulting in inaccurate prediction results.

Based on the problem of inaccurate blood pressure measurements caused by movement, in some embodiments, the smart watch may also detect its own movement conditions, including movement and non-movement, after starting the blood pressure measurement. It should be understood that the movement of the wrist drives the smart watch, so that the movement of the smart watch can reflect the movement of the wrist. For example, after starting the blood pressure measurement, an acceleration sensor in the smart watch may be activated to acquire an acceleration signal for detecting the movement of the smart watch. In this embodiment, if the movement duration of the smart watch within the preset duration is lower than the preset threshold, the smart watch may further predict the blood pressure. If the movement time length of the intelligent watch within the preset time length is higher than or equal to the preset threshold value, the intelligent watch does not further predict the blood pressure. Therefore, the problem of inaccurate blood pressure prediction caused by continuous wrist movement can be avoided, and the accuracy of blood pressure prediction is improved.

Taking the preset threshold value of 15s as an example, if the movement time length of the intelligent watch within the preset time length reaches 15s, the intelligent watch does not use the PPG signal and the pressure signal within the preset time length to predict the blood pressure; if the movement duration of the smart watch within the preset duration is less than 15s, the smart watch can use the PPG signal and the pressure signal within the preset duration to predict the blood pressure.

In actual implementation, during the process of obtaining the PPG signal and the pressure signal (i.e. within a preset time length), the smart watch can detect whether the motion time length of the smart watch within the preset time length is higher than or equal to a preset threshold value in real time (recorded as an implementation mode I); or, after the preset duration is over, the smart watch may detect whether the motion duration of the smart watch within the preset duration is higher than or equal to a preset threshold (denoted as implementation two). The following will explain separately.

In the first implementation manner, after starting blood pressure measurement, the smart watch starts to acquire an acceleration signal, and at intervals of a first time (such as 30ms,1s, 2s, etc.), the smart watch can detect whether the movement duration of the smart watch within a preset duration is higher than or equal to a preset threshold value at the current moment. The first duration is smaller than a preset duration. If the motion duration of the intelligent watch in the preset duration is lower than the preset threshold value at the current moment, the intelligent watch can continuously acquire the PPG signal, the pressure signal and the acceleration signal and perform next round of detection. If the movement time of the intelligent watch in the preset time is still lower than the preset threshold value until the preset time is over, the intelligent watch can further predict the blood pressure. If the motion time length of the intelligent watch in the preset time length is higher than or equal to a preset threshold value at the current moment, the intelligent watch can empty the acquired PPG signal and pressure signal. In this way, the smart watch does not use the PPG signal and the pressure signal acquired during continuous motion to predict blood pressure.

In a first implementation, if the movement duration within the preset duration is greater than or equal to the preset threshold, the smart watch may also stop acquiring the PPG signal and the pressure signal, prompt the user to keep the wrist stationary and continue the measurement. For example, if the movement duration of the smart watch within the preset duration is greater than or equal to the preset threshold value at the current time, the smart watch may display the interface 903 shown in fig. 9. Included in interface 903 is the prompt text "please keep the wrist stationary and return to continue measuring" to prompt the user to keep the wrist stationary and continue measuring. Further, in response to a confirmation operation to continue the measurement, the smart watch may resume the blood pressure measurement. Continuing with the example of fig. 9, the interface 903 may further include a "continue measurement" button, where the confirmation operation may be a user click operation on the "continue measurement" button in the interface 903, and in response to the user click operation on the "continue measurement" button in the interface 903, the smart watch may return to displaying the interface 902 shown in fig. 9, and continue measurement.

According to the first implementation mode, the intelligent watch can timely detect the continuous motion condition of the wrist within a preset time period and immediately stop measurement after detection, so that excessive and useless PPG signals and pressure signals are prevented from being generated.

In a second implementation manner, after starting the blood pressure measurement, the smart watch acquires and stores the acceleration signal, for example, acquires the acceleration signal once every second time period (for example, 30ms,1s,2s, etc.). The second time period is smaller than the preset time period. After the preset time period is over, the intelligent watch detects whether the movement time period of the intelligent watch in the preset time period is higher than or equal to a preset threshold value or not based on the stored multiple groups of acceleration signals. If the movement time of the intelligent watch in the preset time is lower than the preset threshold value, further predicting the blood pressure. And if the movement time length of the intelligent watch in the preset time length is higher than or equal to the preset threshold value, the acquired PPG signal and pressure signal are emptied. In this way, the PPG signal and the pressure signal acquired with continued wrist motion can be avoided for further predicting blood pressure.

Similarly, in the second implementation manner, if the movement duration within the preset duration is greater than or equal to the preset threshold, the smart watch may prompt the user to keep the wrist still and continue measurement, and the detailed description of the first implementation manner may be omitted herein.

By adopting the second implementation mode, after the preset time length is over, the intelligent watch can uniformly detect the motion condition once, and the frequent occupation of computing resources is not needed.

After obtaining the PPG signal and the pressure signal, the intelligent watch can splice the signals according to the time stamp corresponding to the signals to obtain waveforms corresponding to the signals. Illustratively, the smart watch splices the PPG signals according to the sequence of the time stamps to obtain a PPG waveform; and the intelligent watch splices the pressure signals according to the sequence of the time stamps to obtain pressure waveforms. Furthermore, after the PPG waveform and the pressure waveform are obtained, the intelligent watch can also preprocess the PPG waveform and the pressure waveform, filter noise and obtain an effective PPG waveform and an effective pressure waveform. For example, the smart watch may use butterworth bandpass filtering or blind source separation to separate effective PPG waveforms and pressure waveforms.

In practice, different hardware has different time delays at start-up or shut-down. Taking starting as an example, the processor of the smart watch sends a starting notification to the PPG sensor and the pressure sensor simultaneously, but the PPG sensor completes starting and starts acquiring the PPG signal first, and the pressure sensor completes starting and starts acquiring the pressure signal after. That is, the time points at which the PPG sensor and the pressure sensor begin and/or end operation may not be exactly coincident. For example, compared to a pressure sensor: the PPG sensor starts to operate as early as 30ms and ends to operate as early as 30 ms.

Based on this, in some embodiments, the smart watch may also align the PPG waveform and the pressure waveform according to the timestamp, and clip out the unaligned portion so that the start-stop times corresponding to the reserved PPG waveform and the reserved pressure waveform are completely consistent. In this way, the PPG waveform and the pressure waveform over the same period of time may be used later to predict blood pressure.

Illustratively, the PPG waveform is the waveform shown in FIG. 10 during the time period t0-t1 before alignment, and the pressure waveform is the waveform shown in FIG. 10 during the time period t2-t3 before alignment. Wherein t0< t2< t1< t3, that is, the time t0 when the PPG sensor starts collecting the PPG signal is earlier than the time t2 when the pressure sensor starts collecting the pressure signal, and the time t1 when the PPG sensor ends collecting the PPG signal is earlier than the time t3 when the pressure sensor ends collecting the pressure signal. Then the overlapping time stamp interval in the PPG waveform and the pressure waveform is t2-t1. Therefore, the smart watch can cut out the waveform in the time period t0-t2 in the PPG waveform to obtain the PPG waveform in the time period t2-t1 shown in FIG. 10; and cutting out the waveform in the time period t1-t3 in the pressure waveform to obtain the pressure waveform in the time period t2-t1 shown in fig. 10.

After the PPG waveform and the pressure waveform are obtained through the process, the intelligent watch can obtain first information and the signal amplitude of the pressure waveform so as to be used for predicting the blood pressure. The following description will be given respectively:

First, first information.

In some embodiments, the first information is represented by a phase difference of the pressure waveform and the PPG waveform.

Typically, blood will flow through the brachial artery first, then through the radial and ulnar arteries via branches, and blood pressure through the ulnar arteries will further branch through the arterioles. Then, the blood flow caused by the systole and diastole of the heart will affect the radial artery first and then the arteriole. Therefore, the PPG waveform should be delayed compared to the pressure waveform.

Based on this, the smart watch can find the time difference between one peak in the pressure waveform (denoted as peak 1) and the other peak in the PPG waveform (denoted as peak 2) as a phase difference. Wherein, the peak 1 and the peak 2 are two adjacent peaks in time sequence, and the peak 2 is located behind the peak 1.

For example, peak 1 is peak A1 in the pressure waveform shown in fig. 11, peak 2 is peak B1 in the PPG waveform shown in fig. 11, peak A1 and peak B1 are two adjacent peaks in time sequence, and peak B1 is located after peak A1, then a phase difference Pw1 shown in fig. 11 can be calculated.

As another example, peak 1 is peak A2 in the pressure waveform shown in fig. 11, peak 2 is peak B2 in the PPG waveform shown in fig. 11, peak A2 and peak B2 are two peaks adjacent in time sequence, and peak B2 is located after peak A2, so that still another phase difference is calculated as Pw2 shown in fig. 11.

As another example, peak 1 is peak A3 in the pressure waveform shown in fig. 11, peak 2 is peak B3 in the PPG waveform shown in fig. 11, peak A3 and peak B3 are two peaks adjacent in time sequence, and peak B3 is located after peak A3, and another phase difference is calculated to be Pw3 shown in fig. 11.

The smart watch may take one phase difference (e.g., pw1, pw2, or Pw 3) as the phase difference between the pressure waveform and the PPG waveform. Alternatively, the smart watch may average the plurality of phase differences to obtain the phase difference between the pressure waveform and the PPG waveform. Illustratively, the plurality of phase differences include Pw1, pw2, and Pw3 shown in fig. 11, and the smart watch may determine that the phase difference of the pressure waveform and the PPG waveform is (pw1+pw2+pw 3)/3.

In practice, the smart watch may directly determine the time difference between one peak (denoted as peak 3) in the pressure waveform and the other peak (denoted as peak 4) in the PPG waveform as a phase difference, without considering the problem that the PPG waveform lags behind the pressure waveform. Wherein, the peak 3 and the peak 4 are two adjacent peaks in time sequence, but the peak 3 and the peak 4 are not sequential. Still taking fig. 11 as an example, with the present embodiment, not only the above Pw1, pw2, and Pw3 but also the time difference between the peak B1 and the peak A2 and the time difference between the peak B2 and the peak A3 can be calculated as the phase difference.

Further, in this embodiment, the smart watch may select a target phase difference smaller than T/2 or larger than T/2 from among the plurality of phase differences based on the period T of the PPG waveform or the pressure waveform. Taking the example of selecting a target phase difference smaller than T/2, pw1, pw2, and Pw3 in fig. 11 can be selected as target phase differences. Taking the example of selecting a target phase difference greater than T/2, the time difference T-Pw1 between the peak B1 and the peak A2 and the time difference T-Pw2 between the peak B2 and the peak A3 in fig. 11 may be selected as the target phase difference. In this way, the time differences (e.g., pw1, pw2, and Pw 3) calculated before the peak 3 is located at the peak 4 may be unified as the target phase difference, or the time differences (e.g., T-Pw1 and T-Pw 2) calculated after the peak 3 is located at the peak 4 may be unified as the target phase difference. In this way, the smart watch can take a target phase difference as the phase difference between the pressure waveform and the PPG waveform. Alternatively, the smart watch may average the target phase differences to obtain the phase difference between the pressure waveform and the PPG waveform.

To this end, it should be noted that: the smart watch may also calculate a time difference between one trough in the pressure waveform and another trough in the PPG waveform to obtain a phase difference between the pressure waveform and the PPG waveform, which is not described herein, and may refer to the foregoing specific description of obtaining the phase difference between the pressure waveform and the PPG waveform according to the peaks.

In other embodiments, the first information further includes a period of the heart beat (abbreviated as cardiac period T, i.e., a period of the PPG waveform or the pressure waveform) on the basis of the phase difference including the pressure waveform and the PPG waveform described above. Illustratively, the phase difference between the pressure waveform and the PPG waveform is the average value (pw1+pw2+pw3)/3 of Pw1, pw2, and Pw3 shown in fig. 11, and the closer (pw1+pw2+pw3)/3 is to T, the larger the difference representing the blood pressure influence time. Also, for example, the phase difference between the pressure waveform and the PPG waveform is the average value T- (Pw1+Pw2)/2 of T-Pw1 and T-Pw2 shown in FIG. 11, and the closer T- (Pw1+Pw2)/2 is to T, the smaller the difference indicating the blood pressure influence time. By combining the cardiac cycle T, not just the phase difference of the pressure waveform and the PPG waveform, the difference in blood pressure affecting time can be more reasonably measured based on the phase difference of the pressure waveform and the PPG waveform and the relative size of the cardiac cycle T. The description hereinafter will be mainly made in connection with the cardiac cycle T.

Second, the signal amplitude of the pressure waveform.

The signal amplitude of the pressure waveform includes a maximum and a minimum. It will be appreciated that when the heart contracts, the blood pressure in the radial artery is greatest and the pressure generated by the radial artery against the pressure sensor is also greatest. That is, the maximum value of the signal amplitude of the pressure waveform should be the corresponding amplitude at the time of systole. Thus, the maximum value in the signal amplitude of the pressure waveform may also be referred to as the systolic amplitude. During diastole, the blood pressure in the radial artery is minimal, and the pressure generated by the radial artery on the pressure sensor is also minimal. That is, the minimum of the signal amplitudes of the pressure waveform should be the corresponding amplitude at diastole. Therefore, the minimum of the signal amplitudes of the pressure waveform may also be referred to as the diastolic amplitude.

The smart watch may take the signal amplitude of a certain peak in the pressure waveform (i.e. the value of the vertical axis, the same applies hereinafter), or the average of the signal amplitudes of a plurality of peaks as the systolic amplitude. And the smart watch may take the signal amplitude of a certain trough in the pressure waveform, or the average value of the signal amplitudes of a plurality of troughs as the diastolic amplitude.

Taking the contraction amplitude as an example, the smart watch may average the signal amplitude of the peak A1 and the signal amplitude of the peak A2 in the pressure waveform shown in fig. 11, so as to obtain the contraction amplitude.

The smart watch can predict the blood pressure based on the difference in phase between the pressure waveform and the PPG waveform and the signal amplitude of the pressure waveform.

In some embodiments, referring to fig. 12, the process of predicting blood pressure includes:

s1201, calculating blood pressure components.

In particular, the smart watch may be represented by a difference in phase between the pressure waveform and the PPG waveform (e.g., a phase difference Pw of the pressure waveform and the PPG waveform, and a cardiac cycle T): blood pressure of the arterioles and radial arteries affects time gap. And the smart watch uses the blood pressure corresponding to the signal amplitude (e.g. the systolic amplitude BP-s and the diastolic amplitude BP-d) of the pressure waveform as the blood pressure of the radial artery. It will be appreciated that the higher the signal amplitude, the greater the pressure on the radial artery that indicates blood flow in the radial artery, and the greater the blood pressure in the radial artery; the lower the signal amplitude, the less pressure the blood flow in the radial artery is at the radial artery, and the less the pressure in the radial artery is at this time. That is, the signal amplitude has a positive correlation with the blood pressure of the radial artery. Thus, the signal amplitude may be mapped to the blood pressure of the radial artery.

Then, the smart watch calculates the blood pressure component of the micro artery based on the correspondence between the difference of the blood pressure influence time and the blood pressure value (i.e., the earlier the blood pressure influence time is, the higher the blood pressure value is, the later the blood pressure influence time is, and the lower the blood pressure value is). The blood pressure component includes a systolic pressure component (e.g., denoted as SBP-0) and a diastolic pressure component (e.g., denoted as DBP-0).

In one particular implementation, the smart watch may calculate the blood pressure component using a first artificial intelligence (Artificial Intelligence, AI) model. Wherein the first AI model has the ability to calculate a blood pressure component of the arteriole from a phase difference of the pressure waveform and the PPG waveform, a cardiac cycle, and a signal amplitude of the pressure waveform. Referring to fig. 13, the smart watch takes the phase difference Pw, cardiac cycle T, and signal amplitudes BP-s and BP-d as inputs to a first AI model, and runs the first AI model to obtain blood pressure components SBP-0 and DBP-0.

It should be noted that if the cardiac cycle is not combined, the input of the first AI model does not include the cardiac cycle T, and will not be described in detail below.

The first AI model may be a tree model, or may be a neural network model such as a transfer learning or convolutional neural network.

Taking a neural network model as an example, the training process to obtain the first AI model will be described herein in the embodiment of the present application:

A pressure signal sample of the radial artery on the medial side of the wrist and a PPG signal sample of the dorsal micro-artery of the wrist are collected. And acquiring the blood pressure of the user by using a professional measuring instrument to obtain a systolic pressure sample and a diastolic pressure sample. The pressure signal sample and the PPG signal sample are processed to obtain a pressure waveform sample and a PPG waveform sample, and a phase difference (i.e., a phase difference between the pressure waveform sample and the PPG waveform sample) sample, a period (i.e., a cardiac period) sample, a systolic amplitude sample and a diastolic amplitude sample are calculated. And converting the systolic pressure sample into a systolic pressure component sample and converting the diastolic pressure sample into a diastolic pressure component sample. Regarding the conversion of the systolic pressure sample into the systolic pressure component sample, the inverse conversion of the systolic pressure component into systolic pressure can be used as follows in S1202; and, regarding the conversion of the diastolic blood pressure sample into the diastolic blood pressure component sample, the following reverse conversion of the diastolic blood pressure component into diastolic blood pressure may be used, which is not described herein. Thus, a set of training samples is obtained, namely: a phase difference sample, a period sample, a systolic amplitude sample and a diastolic amplitude sample, and corresponding systolic and diastolic pressure component samples. After the same multiple collection and processing, multiple groups of training samples can be obtained.

And taking the phase difference samples, the period samples, the systolic amplitude samples and the diastolic amplitude samples in the plurality of groups of training samples as input samples, taking the corresponding systolic pressure component samples and diastolic pressure component samples as output samples, training a first network model, and adjusting model parameters of the first network model based on the difference value between the actual output and the output samples of the first network model. And ending training until the difference value between the actual output and the output sample of the first network model is smaller than the first difference value, wherein the first network model is the first AI model.

S1202, blood pressure conversion.

The smart watch can convert the blood pressure components SBP-0 and DBP-0 of the wrist back arterioles into the blood pressure of the brachial artery, thereby obtaining the blood pressure in the conventional sense. The blood pressure of the brachial artery includes systolic (e.g., noted SBP) and diastolic (e.g., noted DBP).

It will be appreciated that blood in the brachial artery, after continuing to branch, will flow through the arterioles on the back of the wrist. The blood pressure in the brachial artery is high, and correspondingly, the blood pressure when blood flows through the arterioles is high; the blood pressure in the brachial artery is low and, correspondingly, the blood pressure as it flows through the arterioles is also low. That is, the blood pressure component of the arteriole and the blood pressure of the brachial artery are related to each other. Then, a relationship function between the blood pressure component of the arteriole and the blood pressure of the brachial artery can be obtained by big data analysis. Wherein the relationship function includes a relationship function f of systolic pressure (SBP-0) and a relationship function f of diastolic pressure (DBP-0).

After obtaining the blood pressure component, the smart watch can then use the relationship function f (SBP-0) to obtain the systolic pressure; and, the smart watch may use the relationship function f (DBP-0) to derive the diastolic pressure. The relationship function f (SBP-0) and the relationship function f (DBP-0) may also be referred to as a preset relationship.

In a specific implementation, the variables in the relationship function f (SBP-0) are only the systolic pressure component SBP-0 and the variables in the relationship function f (DBP-0) are only the diastolic pressure component DBP-0. Then the smart watch may substitute the systolic pressure component SBP-0 into the relation function f (SBP-0), resulting in a systolic pressure; and, the smart watch may substitute the diastolic pressure component DBP-0 into the relational function f (DBP-0) to obtain the diastolic pressure.

Illustratively, f (SBP-0) =k1×SBP-0, f (DBP-0) =k2×DBP-0, k1 and k2 being constants. Then, the smart watch substitutes the systolic pressure component SBP-0 into the relation function f (SBP-0), and the systolic pressure is k1 SBP-0; and substituting the diastolic pressure component DBP-0 into a relation function f (DBP-0) by the intelligent watch, so that the systolic pressure is k1 times DBP-0.

By adopting the implementation mode, the blood pressure conversion can be simply and rapidly completed.

In another specific implementation, the variables in the relationship function f (SBP-0) include not only the systolic pressure component SBP-0, but also the personalization parameters of the user; likewise, the variables in the relationship function f (DBP-0) include not only the diastolic blood pressure component DBP-0, but also the user's personalization parameters. That is, the relationship function f (SBP-0) and the relationship function f (DBP-0) are different for different users.

Some common personalization parameters are listed below:

first, parameters reflecting the physical condition of the user.

Different physical conditions such as height and weight may cause different relationships between the blood pressure component and the blood pressure of the brachial artery. For example, the relationship between the blood pressure component and the blood pressure of the brachial artery may be different in obese and non-obese people. As another example, in a high-height population and a low-height population, the distance between the arterioles at the back of the wrist and the brachial arteries may be different, and accordingly, the relationship between the blood pressure component and the blood pressure of the brachial arteries may be different.

Thus, the relationship function f (SBP-0) and the relationship function f (DBP-0) may also be related to parameters reflecting the physical condition of the user, such as height, weight, body Mass Index (BMI).

And secondly, parameters reflecting the degree of tightness and/or skin state of the watch.

The degree of tightness or skin state of the watch is different, and the accuracy of the measured pressure signals is different. For example, if the wristwatch is worn loosely, the pressure signal measured by the pressure sensor may be low; the watch is worn tightly, and the pressure signal measured by the pressure sensor may be high. As another example, the more compact the skin, the more sensitive it is to pressure, and the higher the pressure signal measured by the pressure sensor may be; the more relaxed the skin, the less sensitive it is to pressure, and the lower the pressure signal measured by the pressure sensor may be. Inaccurate pressure signals may also cause a difference in deviation between the calculated blood pressure component and the actual blood pressure component, and accordingly, the relationship between the calculated blood pressure component and the blood pressure of the brachial artery may be different.

Thus, the relationship function f (SBP-0) and the relationship function f (DBP-0) may also be related to parameters reflecting the tightness of the watch wear and/or the skin condition. For example, the ratio of the BMI to the band circumference L may be used to indicate the tightness of the watch, with a tighter the watch is worn and a lower the ratio of BMI to L, a looser the watch is worn.

Thirdly, physiological parameters such as gender, age and the like.

The relationship between the blood pressure component and the blood pressure of the brachial artery may be different if the physiological parameters such as sex, age, etc. are different. For example, young and old people may have different relationships between their blood pressure components and the blood pressure of the brachial artery. As another example, the relationship between the blood pressure component of a male and female and the blood pressure of the brachial artery may be different. Based on this, the relationship function f (SBP-0) and the relationship function f (DBP-0) may also be related to physiological data of gender, age, etc.

Thus, the relationship function f (SBP-0) and the relationship function f (DBP-0) may also be related to physiological parameters of the user, such as gender, age, etc.

Taking the example that the relation function f (SBP-0) and the relation function f (DBP-0) are also related to BMI, L and skin tightness Z, see FIG. 14, in S1202, the smart watch may use BMI, L and Z as inputs for converting blood pressure of radial artery in addition to systolic pressure component SBP-0 and diastolic pressure component DBP-0 when converting blood pressure. For example, the expressions of the relationship function f (SBP-0) and the relationship function f (DBP-0) are as follows:

f(SBP-0)＝(k3*BMI*Z*SBP-0)/L；

f(DBP-0)＝(k4*BMI*Z*DBP-0)/L；

Where k3 and k4 are constants. Then, the smart watch brings the systolic components SBP-0, BMI, L and Z into the relation function f (SBP-0), and can obtain the systolic component (k 3. BMI. Z. SBP-0)/L; and, bringing the diastolic pressures DBP-0, BMI, L and Z into the correlation function f (DBP-0) can result in a diastolic pressure of (k3.times.BMI.times.Z.DBP-0)/L.

Note that, in the present design, the acquisition method of the personalized parameters of the user is not limited. The intelligent watch can prompt and receive the personalized parameters input by the user, can automatically detect the personalized parameters, or can acquire the personalized parameters from the devices such as a mobile phone, a tablet and the like which are connected with the intelligent watch.

By adopting the design scheme, the intelligent watch performs blood pressure conversion based on the personalized parameters of the user, so that more accurate blood pressure can be obtained through conversion.

The above description of S1202 will be mainly described with respect to an implementation using a relational function. In practice, the smart watch may also use the second AI model to learn the relationship between the blood pressure component of the arteriole, the personalized parameters, and the blood pressure of the brachial artery. Then, the inching blood pressure component and the personalized parameters are used as input, and the second AI model is operated, so that the blood pressure of the brachial artery is obtained.

Taking a neural network model as an example, the training process to obtain the second AI model will be described herein in the embodiment of the present application:

blood pressure component samples of the wrist back arterioles are collected, and the blood pressure component samples comprise a systolic pressure component sample and a diastolic pressure component sample. For example, the blood pressure component sample may be obtained by obtaining the blood pressure component of the arteriole based on the blood pressure of the radial artery as described above. And collecting personalized parameters of the user to obtain personalized parameter samples. And acquiring a blood pressure sample of the user by using a professional measuring instrument to obtain a systolic pressure sample and a diastolic pressure sample. Thus, a set of training samples is obtained, namely: a systolic blood pressure component sample, a diastolic blood pressure component sample, a personalized parameter sample, a systolic blood pressure sample, and a diastolic blood pressure sample. After the same multiple collection and processing, multiple groups of training samples can be obtained.

And taking the systolic pressure component sample, the diastolic pressure component sample and the personalized parameter sample in the plurality of groups of training samples as input samples, taking the corresponding systolic pressure sample and diastolic pressure sample as output samples, training a second network model, and adjusting model parameters of the second network model based on the difference value between the actual output and the output samples of the second network model. And ending training until the difference value between the actual output and the output sample of the second network model is smaller than the second difference value, wherein the second network model is the second AI model.

In the foregoing embodiments, the smart watch calculates the blood pressure component of the arteriole and then converts the blood pressure component to the blood pressure. Of course, in order to simplify the calculation step, the step of calculating the blood pressure of the arteriole and the step of converting the blood pressure of the arteriole into the blood pressure of the brachial artery may be integrated into one step. Illustratively, the step of calculating the blood pressure component of the arteriole is substituted into the aforementioned relationship function f (SBP-0) and relationship function f (DBP-0) as the step of calculating the systolic blood pressure component. For example, the step of calculating the systolic blood pressure component SBP-0 (denoted as s (SBP-0)) is substituted into f (SBP-0), resulting in a calculation formula of calculating the systolic blood pressure SBP as f (s (SBP-0)); the step of calculating the diastolic pressure component DBP-0 (denoted as s (DBP-0)) is substituted into f (DBP-0), and the calculation formula of calculating the diastolic pressure DBP is obtained as f (s (DBP-0)). Therefore, the intelligent watch does not need to calculate to obtain the blood pressure component first and then convert to obtain the blood pressure, and can directly obtain the blood pressure in one step.

Referring to fig. 15, the smart watch may directly calculate the blood pressure using the third AI model. Wherein the third AI model has the ability to calculate the blood pressure of the brachial artery from the phase difference of the pressure waveform and the PPG waveform, the cardiac cycle, and the signal amplitude of the pressure waveform. Specifically, the smart watch may take the phase difference Pw, cardiac cycle T, and signal amplitudes BP-s and BP-d as inputs to a third AI model and operate the third AI model to obtain the systolic SBP and diastolic DBP pressures.

Similarly, the third AI model may be a tree model, or may be a neural network model such as a transfer learning or convolutional neural network.

Exemplary, embodiments of the present application will now be described with respect to training to obtain a third AI model:

a pressure signal sample of the radial artery on the medial side of the wrist and a PPG signal sample of the dorsal micro-artery of the wrist are collected. And acquiring the blood pressure of the user by using a professional measuring instrument to obtain a systolic pressure sample and a diastolic pressure sample. The pressure signal sample and the PPG signal sample are processed to obtain a pressure waveform sample and a PPG waveform sample, and a phase difference (i.e., a phase difference between the pressure waveform and the PPG waveform) sample, a period (i.e., a cardiac period) sample, a systolic amplitude sample and a diastolic amplitude sample are calculated. Thus, a set of training samples is obtained, namely: a phase difference sample, a period sample, a systolic amplitude sample, and a diastolic amplitude sample. After the same multiple collection and processing, multiple groups of training samples can be obtained.

And taking phase difference samples, periodic samples, systolic amplitude samples and diastolic amplitude samples in the plurality of groups of training samples as input samples, taking corresponding systolic pressure samples and diastolic pressure samples as output samples, training a third network model, and adjusting model parameters of the third network model based on the difference value between the actual output and the output samples of the third network model. And ending training until the difference value between the actual output and the output sample of the third network model is smaller than the third difference value, wherein the third network model is the third AI model.

With continued reference to fig. 15, to further improve accuracy of blood pressure prediction, the smart watch may also use personalized parameters (e.g., BMI, L, Z, etc.) as inputs to the third AI model. Correspondingly, in the process of training the third AI model, a personalized parameter sample needs to be acquired, and the personalized parameter sample is taken as an input sample.

In practice, in the process of using the AI models (such as the first AI model, the second AI model, and the third AI model), complex calculation in the AI models needs to be completed, the calculation amount is extremely large, and sufficient calculation resources are needed. Meanwhile, the operation capability of the smart watch is limited, so that in actual implementation, the operation related to the AI model can be completed by a mobile phone, a tablet or a server connected with the smart watch.

After the blood pressure is predicted, the smart watch can prompt the blood pressure value. For example, during the course of measuring blood pressure, the smartwatch may display interface 1601 shown in fig. 16 to prompt the user that measurement is being performed; and after the measurement is completed, the smart watch may display an interface 1602 as shown in fig. 16 to indicate a systolic pressure of 120 millimeters of mercury (mmHg) and a diastolic pressure of 120mmHg.

Referring to fig. 17, an embodiment of the present application provides a blood pressure measurement device 1700, where the blood pressure measurement device 1700 may be applied to the wearable apparatus described above, for example, a wrist-wearable apparatus such as a wristwatch, a wristband, a smart jewelry, etc. The blood pressure measurement device 1700 includes a pressure sensor 1701, a PPG sensor 1702, and a processing module 1703. Wherein, the pressure sensor 1701 is used for obtaining a radial artery pressure signal; the PPG sensor 1702 is used to acquire PPG signals of the arterioles. The pressure signal acquired by the pressure sensor 1701 and the PPG signal acquired by the PPG sensor 1702 may be transmitted to the processing module 1703. Illustratively, it may be transmitted to the processing module 1703 via a serial peripheral interface (Serial Peripheral Interface, SPI). The processing module 1703 is configured to predict the blood pressure based on a phase difference between a waveform of the pressure signal (i.e., a pressure waveform) and a waveform of the PPG signal (i.e., a PPG waveform), a period of the PPG waveform, and a signal amplitude of the pressure waveform.

In some embodiments, blood pressure measurement device 1700 further includes a motion detection module 1704. The motion detection module 1704 is used to detect a motion condition. Illustratively, the motion detection module 1704 is an acceleration sensor. The motion signal acquired by the motion detection module 1704 may also be transmitted to the processing module 1703. Accordingly, in the present embodiment, the processing module 1703 is further configured to predict the blood pressure according to the phase difference between the pressure waveform and the PPG waveform, the period of the PPG waveform, and the signal amplitude of the pressure waveform when the movement duration of the blood pressure measuring apparatus 1700 is below the preset threshold. With the blood pressure measurement device 1700 of the present embodiment, it is possible to predict blood pressure without movement or with only a short movement. Thus, the problem of inaccurate prediction result of blood pressure prediction caused by movement can be avoided, and the accuracy of blood pressure prediction is improved.

The embodiment of the application also provides a wearable device, which can comprise: a memory and one or more processors. The memory is coupled to the processor. The memory is for storing computer program code, the computer program code comprising computer instructions. The wearable device, when executing computer instructions, may perform the various functions or steps of the method embodiments described above.

Embodiments of the present application also provide a system on a chip, as shown in FIG. 18, the system on a chip 1800 including at least one processor 1801 and at least one interface circuit 1802. The processor 1801 and interface circuit 1802 may be interconnected by wires. For example, interface circuit 1802 may be used to receive signals from other devices (e.g., a memory of a wearable apparatus). For another example, interface circuit 1802 may be used to send signals to other devices (e.g., processor 1801). The interface circuit 1802 may, for example, read instructions stored in a memory and send the instructions to the processor 1801. The instructions, when executed by the processor 1801, may cause the wearable device to perform the various steps of the embodiments described above. Of course, the system-on-chip may also include other discrete devices, which are not particularly limited in accordance with embodiments of the present application.

The present embodiment also provides a computer readable storage medium having stored therein computer instructions which, when run on a wearable device, cause the wearable device to perform the functions or steps of the method embodiments described above.

The present embodiment also provides a computer program product which, when run on a computer, causes the computer to perform the functions or steps of the method embodiments described above.

The wearable device, the communication system, the computer readable storage medium, the computer program product or the chip provided in this embodiment are used to execute the corresponding method provided above, so that the beneficial effects achieved by the wearable device, the communication system, the computer readable storage medium, the computer program product or the chip can refer to the beneficial effects in the corresponding method provided above, and are not repeated herein.

From the foregoing description of the embodiments, it will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of functional modules is illustrated, and in practical application, the above-described functional allocation may be implemented by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to implement all or part of the functions described above.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and the parts displayed as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated unit may be stored in a readable storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a device (may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present application without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method of blood pressure measurement, for application to a wearable device wearable on a wrist, the method comprising:

acquiring a photoplethysmography (PPG) signal of the back of the wrist of a user and a pressure signal of the radial artery on the inner side of the wrist in a preset time period;

based on the pressure signal, combining first information indicating a magnitude of a phase difference of the PPG signal and the pressure signal to obtain a first blood pressure; wherein the first blood pressure is the blood pressure of the arterioles;

and converting the first blood pressure into a second blood pressure, wherein the second blood pressure is the blood pressure of the brachial artery of the user.

2. The method of claim 1, wherein after the acquiring photoplethysmography, PPG, signal at the back arteriole of the user's wrist and pressure signal at the radial artery on the medial side of the wrist for a preset period of time, the method further comprises:

Generating a PPG waveform corresponding to the PPG signal and a pressure waveform corresponding to the pressure signal;

wherein the first information includes a phase difference of the PPG waveform and the pressure waveform; alternatively, the first information includes a phase difference of the PPG waveform and the pressure waveform, and a period of the PPG waveform or the pressure waveform.

3. The method of claim 2, wherein the deriving a first blood pressure based on the pressure signal in combination with first information indicative of a magnitude of a phase difference of the PPG signal and the pressure signal comprises:

taking the signal amplitude of the pressure waveform and the first information as inputs, and operating a first AI model to obtain the first blood pressure;

the first AI model has a function of calculating the blood pressure component of the micro artery according to the phase magnitude of the blood pressure variation waveform of the micro artery and the blood pressure variation waveform of the radial artery and the amplitude of the blood pressure variation waveform of the radial artery.

4. A method according to any one of claims 1-3, wherein said converting said first blood pressure to a second blood pressure comprises:

converting the first blood pressure to the second blood pressure based on a first parameter;

Wherein the first parameter comprises one or more of the following parameters: parameters for reflecting the degree of obesity of the user, parameters for reflecting the degree of tightness of the wearable device, and parameters for reflecting the skin condition of the user.

5. The method of claim 4, wherein the first parameter comprises: the wearable device's wearing circumference, body mass index BMI, and skin elasticity.

6. The method of claim 4 or 5, wherein the converting the first blood pressure to the second blood pressure based on the first parameter comprises:

substituting the first parameter and the first blood pressure into a preset relation to obtain the second blood pressure; or,

taking the first parameter and the first blood pressure as inputs, and operating a second AI model to obtain the second blood pressure;

wherein the second AI model has a function of predicting the blood pressure of the brachial artery based on the blood pressure component of the arteriole and the first parameter.

7. The method of any one of claims 4-6, wherein the first blood pressure comprises a first systolic pressure and a first diastolic pressure and the second blood pressure comprises a second systolic pressure and a second diastolic pressure;

The converting the first blood pressure to the second blood pressure based on the first parameter includes:

based on the first parameter, the first systolic pressure is converted to the second systolic pressure and the first diastolic pressure is converted to the second diastolic pressure.

8. The method of any one of claims 1-7, wherein the acquiring photoplethysmography, PPG, signals at the back arteriole of the wrist and pressure signals at the radial artery on the inside of the wrist of the user for a preset period of time comprises:

and responding to a first event, and acquiring a photoplethysmography (PPG) signal at a micro-artery at the back of the wrist and a pressure signal at a radial artery at the inner side of the wrist of the user within a preset time period, wherein the first event is used for triggering blood pressure measurement.

9. The method of claim 8, wherein the first event comprises at least one of:

receiving an operation triggering blood pressure measurement;

receiving voice triggering blood pressure measurement; the method comprises the steps of,

the preset time arrives.

10. The method according to claim 8 or 9, characterized in that the method further comprises:

acquiring motion information of the wearable equipment within the preset time period, and detecting the motion time period of the wearable equipment within the preset time period based on the motion information;

The deriving a first blood pressure based on the pressure signal in combination with first information indicative of a magnitude of a phase difference of the PPG signal and the pressure signal, comprises:

and if the movement duration is lower than a preset threshold value, based on the pressure signal, combining the first information indicating the phase difference magnitude of the PPG signal and the pressure signal to obtain the first blood pressure.

11. The method according to claim 10, wherein the method further comprises:

if the movement time length is higher than or equal to the preset threshold value, a first prompt is sent out, and the first prompt is used for prompting to restart measuring blood pressure;

the first event includes: an operation to resume measuring blood pressure is received.

12. The method of claim 10 or 11, wherein the motion information comprises acceleration information.

13. A wearable device, wherein the wearable device is wearable on a wrist, the wearable device comprising a photoplethysmography, PPG, sensor, pressure sensor, memory, and processor, the PPG sensor, pressure sensor, memory, and processor coupled; the PPG sensor is for acquiring PPG signals of a wrist back arteriole, the pressure sensor is for acquiring pressure signals of a wrist inner radial artery, the memory has stored therein computer program code comprising computer instructions which, when executed by the processor, cause the wearable device to perform the method of any of claims 1-12.

14. The wearable device of claim 13, further comprising a motion detection module to detect a motion condition of the wearable device.

15. A computer readable storage medium comprising computer instructions which, when run on a wearable device, cause the wearable device to perform the method of any of claims 1-12.

16. A chip system for application to a wearable device comprising a photoplethysmography, PPG, sensor, pressure sensor, processor and memory, the chip system comprising one or more interface circuits and one or more processors interconnected by wires, the interface circuits for receiving signals from the memory of the wearable device and transmitting the signals to the processor, the signals comprising computer instructions stored in the memory, which when executed by the processor, cause the wearable device to perform the method of any one of claims 1-12.