Blood pressure monitoring method, device, wearable device and medium

Abstract

This disclosure provides a blood pressure monitoring method, device, wearable device, and medium, applied to a wearable device. The method includes: when the blood pressure monitoring function is enabled, continuously collecting the wearer's PPG signal through the wearable device's PPG sensor; obtaining the wearer's blood pressure mutation identification result within the latest time period based on the PPG signal within the latest time period and a set blood pressure mutation identification model; and outputting a prompt to the wearer that the blood pressure mutation identification result is a blood pressure mutation when the blood pressure mutation identification result is a blood pressure mutation.

Description

Technical Field

[0001] This disclosure relates to the field of wearable device technology, and more specifically, to a blood pressure monitoring method, apparatus, wearable device, and medium. Background Technology

[0002] Blood pressure fluctuations, especially short-term blood pressure spikes, are a crucial health indicator, significant for early disease intervention and patient observation. Many hypertension-related illnesses are characterized by a sharp rise in blood pressure, potentially leading to life-threatening consequences within a short period. However, severe blood pressure elevations may not present with, or only with mild, symptoms, making blood pressure spike monitoring essential.

[0003] In related technologies, a common technique for blood pressure monitoring on non-cuff wearable devices is to collect the wearer's current photoplethysmography (PPG), electrocardiogram (ECG), and phonocardiogram (PCG) signals, and combine the current PPG, ECG, and PCG signals to calculate the current blood pressure value in order to determine whether the user has a risk of hypertension or hypotension.

[0004] However, current blood pressure monitoring requires the use of PPG signals in conjunction with ECG and PCG signals. But collecting ECG and PCG signals requires users to wear the device correctly and remain still in a set posture, which affects their daily lives. Furthermore, this type of blood pressure monitoring lacks tracking of the user's blood pressure change trend and can only rely on the user to actively and repeatedly monitor blood pressure at different times throughout the day. Summary of the Invention

[0005] One objective of this disclosure is to provide a new technical solution for blood pressure monitoring.

[0006] According to a first aspect of the present disclosure, a blood pressure monitoring method is provided, applied to a wearable device, the method comprising:

[0007] With the blood pressure monitoring function enabled, the wearable device continuously collects the wearer's PPG signal through its PPG sensor.

[0008] Based on the PPG signal within the latest time period and the established blood pressure mutation identification model, the blood pressure mutation identification result of the wearer within the latest time period is obtained;

[0009] If the blood pressure mutation identification result is a blood pressure mutation, a prompt will be output to the wearer indicating that the blood pressure mutation identification result is a blood pressure mutation.

[0010] Optionally, obtaining the wearer's blood pressure mutation identification result within the latest time period based on the PPG signal and the established blood pressure mutation identification model includes:

[0011] Obtain the first-order derivative PPG signal of the PPG signal within the latest time period;

[0012] Obtain the second-order derivative PPG signal of the PPG signal within the latest time period;

[0013] Based on the PPG signal, the first-order PPG signal, the second-order PPG signal, and the established blood pressure mutation recognition model within the latest time period, the blood pressure mutation recognition result of the wearer within the latest time period is obtained.

[0014] Optionally, obtaining the wearer's blood pressure mutation identification result within the latest time period based on the PPG signal, the first-order PPG signal, the second-order PPG signal, and the established blood pressure mutation identification model within the latest time period includes:

[0015] The feature extraction network in the blood pressure mutation identification model is used to extract features from the PPG signal, the first-order PPG signal, and the second-order PPG signal in the latest time period to obtain time-series feature information.

[0016] The blood pressure mutation identification result of the wearer in the latest time period is obtained by predicting blood pressure mutations based on the time-series feature information through the prediction network in the blood pressure mutation identification model.

[0017] Optionally, after continuously collecting the wearer's PPG signal through the wearable device's PPG sensor while the blood pressure monitoring function is enabled, the method further includes:

[0018] The PPG signal continuously collected by the PPG sensor is written into the storage module;

[0019] The latest N consecutive frames of PPG signals are read from the storage module and used as the PPG signals in the latest time period.

[0020] Where N is a positive integer.

[0021] Optionally, the method further includes:

[0022] Every set time interval, delete all PPG signals stored in the storage module except for the latest consecutive M-frame PPG signal;

[0023] Where M is a positive integer, and M is greater than N.

[0024] Optionally, the method further includes:

[0025] Receive input operations for the wearable device;

[0026] In response to the input operation, the blood pressure detection function is activated.

[0027] Optionally, the step of outputting a prompt to the wearer that the blood pressure change identification result is a blood pressure change when the blood pressure change identification result is a blood pressure change includes:

[0028] If the blood pressure change identification result is a blood pressure change, the control output device will provide a prompt indicating that the blood pressure change identification result is a blood pressure change.

[0029] If the blood pressure mutation identification result is a blood pressure mutation, the terminal device communicating with the wearable device will send a prompt through the target application indicating that the blood pressure mutation identification result is a blood pressure mutation.

[0030] According to a second aspect of the present disclosure, a blood pressure monitoring device is provided for use in a wearable device, the device comprising:

[0031] The acquisition module is used to continuously acquire the wearer's PPG signal through the PPG sensor of the wearable device when the blood pressure monitoring function is turned on;

[0032] The identification module is used to obtain the blood pressure mutation identification result of the wearer in the latest time period based on the PPG signal in the latest time period and the set blood pressure mutation identification model;

[0033] The output module is used to output a prompt to the wearer that the blood pressure mutation identification result is a blood pressure mutation when the blood pressure mutation identification result is a blood pressure mutation.

[0034] According to a third aspect of the present disclosure, a wearable device is provided, the wearable device including a PPG sensor, the wearable device further including:

[0035] Memory is used to store executable computer instructions;

[0036] A processor, configured to execute the blood pressure monitoring method according to the first aspect above, under the control of the executable computer instructions.

[0037] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, perform the blood pressure monitoring method described in the first aspect above.

[0038] One beneficial effect of this disclosure is that it can make relatively accurate predictions of blood pressure mutations using only PPG signals. Users only need to wear the wearable device naturally, making full use of their free time to continuously and imperceptibly monitor their blood pressure, greatly improving user-friendliness. Furthermore, after the blood pressure monitoring function is enabled, the wearable device can continuously and imperceptibly collect PPG signals, and by setting a blood pressure recognition model to identify the PPG signals of the latest time period, the results of blood pressure mutation identification within the latest time period can be obtained. That is, by monitoring blood pressure mutations in a short period of time, more comprehensive protection for the user's health can be provided, with early warnings of danger in the early stages of illness, reducing sudden injuries.

[0039] Other features and advantages of this specification will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of this specification and, together with their description, serve to explain the principles of this specification.

[0041] Figure 1 This is a schematic diagram of the structure of a wearable device according to an embodiment of the present disclosure;

[0042] Figure 2 This is a schematic flowchart of a blood pressure monitoring method according to an embodiment of the present disclosure;

[0043] Figure 3 This is a schematic diagram of the management of PPG signals by a wearable device according to an embodiment of the present disclosure;

[0044] Figure 4 This is a schematic diagram illustrating the working process of setting a blood pressure mutation recognition model according to an embodiment of this disclosure;

[0045] Figure 5 This is a schematic diagram of a blood pressure monitoring device according to an embodiment of the present disclosure;

[0046] Figure 6 This is a schematic diagram of a wearable device according to an embodiment of the present disclosure. Detailed Implementation

[0047] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the embodiments of the present disclosure.

[0048] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0049] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0050] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0051] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0052] <Hardware Configuration>

[0053] Figure 1 This is a block diagram of the hardware configuration of a wearable device 1000 according to an embodiment of the present disclosure.

[0054] The wearable device 1000 includes, but is not limited to, watches and rings; this embodiment does not limit it.

[0055] like Figure 1 As shown, the wearable device 1000 may include a processor 1100, a memory 1200, a communication device 1300, an input device 1400, an output device 1500, and a PPG sensor 1600. The processor 1100 may include, but is not limited to, a central processing unit (CPU), a microprocessor (MCU), etc. The memory 1200 may include, for example, ROM (Read-Only Memory), RAM (Random Access Memory), or non-volatile memory such as a hard disk. The communication device 1300 may be capable of wired or wireless communication. The input device 1400 may include, for example, a touchscreen. The output device 1500 may include, for example, a vibration output device and an audio output device, wherein the vibration output device can provide cues through vibration, and the audio output device can provide cues through voice and / or a buzzer. The PPG sensor 1600 is used to collect the wearer's PPG signals.

[0056] In this embodiment, the memory 1200 of the wearable device 1000 is used to store instructions that control the processor 1100 to operate in order to implement or support the implementation of the blood pressure monitoring method according to any embodiment. Those skilled in the art can design instructions based on the schemes disclosed in this specification. How the instructions control the processor to operate is well known in the art and will not be described in detail here.

[0057] Those skilled in the art should understand that, although in Figure 1 The wearable device 1000 is shown in the specification, but the wearable device 1000 of the embodiments herein may only involve some of the devices, or may also include other devices, which is not limited here.

[0058] Figure 1 The wearable device 1000 shown is for illustrative purposes only and is not intended to limit this specification, its application, or its use.

[0059] Hereinafter, various embodiments and examples according to the present disclosure will be described with reference to the accompanying drawings.

[0060] <Method Implementation>

[0061] Figure 2 This disclosure illustrates a blood pressure monitoring method according to an embodiment of the present disclosure, applied to a wearable device. The blood pressure monitoring method of this embodiment can be, for example, by... Figure 1 The wearable device 1000 shown is implemented.

[0062] like Figure 2 As shown, the blood pressure monitoring method of this embodiment may include the following steps S2100 to S2300.

[0063] Step S2100: With the blood pressure monitoring function enabled, the wearer's PPG signal is continuously collected by the PPG sensor of the wearable device.

[0064] Wearable devices include PPG sensors, which are used to collect the wearer's PPG signals. PPG signals can reflect changes in blood concentration in blood vessels over time.

[0065] Understandably, when the blood pressure monitoring function of a wearable device is enabled, the PPG sensor can continuously collect the wearer's PPG signal. Typically, when collecting the wearer's PPG signal through the PPG sensor, the user only needs to wear the device naturally; the user does not need to maintain a set posture and remain still. This allows for continuous and unobtrusive blood pressure monitoring during a significant amount of the user's free time.

[0066] In this embodiment, when the user wears the wearable device and the blood pressure monitoring function of the wearable device is turned on, the wearable device can continuously collect the wearer's PPG signal through the PPG sensor.

[0067] In an optional embodiment, before step S2100, when the blood pressure monitoring function is enabled, and before continuously collecting the wearer's PPG signal through the PPG sensor of the wearable device, the blood pressure monitoring method of this embodiment further includes: receiving an input operation to the wearable device; and enabling the blood pressure monitoring function in response to the input operation.

[0068] In one example, the wearer can use touch input on the wearable device's input mechanism, such as a "blood pressure monitoring control" displayed on a touchscreen, to activate the blood pressure monitoring function. With the blood pressure monitoring function enabled, the wearer's PPG signal is continuously collected via the PPG sensor.

[0069] In another example, the terminal device that establishes a communication connection with the wearable device runs a target application that is compatible with the wearable device. The wearer can activate the blood pressure monitoring function of the wearable device through the target application running on the terminal device. When the blood pressure monitoring function of the wearable device is activated, the PPG sensor continuously collects the wearer's PPG signal.

[0070] After performing the above step S2100 with the blood pressure monitoring function enabled, and continuously collecting the wearer's PPG signal through the wearable device's PPG sensor, the process proceeds to:

[0071] Step S2200: Based on the PPG signal within the latest time period and the established blood pressure mutation identification model, obtain the blood pressure mutation identification result of the wearer within the latest time period.

[0072] The blood pressure mutation identification model is used to identify blood pressure mutations. This model is typically pre-trained based on a training dataset. The input to the blood pressure mutation identification model includes at least the PPG signal from the most recent time period, and the output is the blood pressure mutation identification result from the most recent time period. Generally, the blood pressure mutation identification result includes either a blood pressure mutation or no blood pressure mutation. For example, an output of "0" indicates no blood pressure mutation, while an output of "1" indicates a blood pressure mutation.

[0073] In an optional embodiment, step S2200, which involves obtaining the wearer's blood pressure mutation identification result within the latest time period based on the PPG signal and the established blood pressure mutation identification model, may further include: extracting features from the PPG signal within the latest time period using the feature extraction network in the established blood pressure mutation identification model to obtain temporal feature information; and predicting blood pressure mutations based on the temporal feature information using the prediction network in the established blood pressure mutation identification model to obtain the wearer's blood pressure mutation identification result within the latest time period.

[0074] The feature extraction network can be a Long Short-Term Memory (LSTM) network. The prediction network can be a fully connected layer.

[0075] In practice, the wearable device inputs the PPG signal from the latest time period into the blood pressure mutation identification model. First, the feature extraction network in the blood pressure mutation identification model extracts features from the PPG signal from the latest time period to obtain temporal feature information. Then, the prediction network in the blood pressure mutation identification model predicts blood pressure mutations based on the temporal feature information to obtain the blood pressure mutation identification result.

[0076] In an optional embodiment, step S2200, based on the PPG signal within the latest time period and the established blood pressure mutation identification model, may further include the following steps S2210 to S2230:

[0077] Step S2210: Obtain the first-order derivative PPG signal of the PPG signal within the latest time period.

[0078] The first-order derivative of the PPG signal is the differential signal of the PPG signal, obtained by differentiating the PPG signal. The first-order derivative of the PPG signal highlights the rate of change in the PPG signal, i.e., the change in blood flow velocity.

[0079] Step S2220: Obtain the second-order PPG signal of the PPG signal within the latest time period.

[0080] The second-derivative PPG signal is the second-order differential of the PPG signal, obtained by performing a second differentiation operation on the PPG signal. The second-derivative PPG signal further highlights the high-frequency components in the PPG signal, which are related to the minute vibrations of blood vessels and changes in blood flow acceleration.

[0081] Step S2230: Based on the PPG signal, the first-order PPG signal, the second-order PPG signal, and the set blood pressure mutation recognition model within the latest time period, obtain the blood pressure mutation recognition result of the wearer within the latest time period.

[0082] Optionally, step S2230, which obtains the wearer's blood pressure mutation identification result within the latest time period based on the PPG signal, the first-order PPG signal, the second-order PPG signal, and the set blood pressure mutation identification model within the latest time period, may further include: extracting features from the PPG signal, the first-order PPG signal, and the second-order PPG signal within the latest time period using the feature extraction network in the set blood pressure mutation identification model to obtain temporal feature information; and predicting blood pressure mutations based on the temporal feature information using the prediction network in the set blood pressure mutation identification model to obtain the wearer's blood pressure mutation identification result within the latest time period.

[0083] In specific implementation, refer to Figure 4 The PPG signal, first-order PPG signal, and second-order PPG signal within the latest time period are input into the blood pressure mutation identification model. First, the feature extraction network in the blood pressure mutation identification model extracts features from the PPG signal, first-order PPG signal, and second-order PPG signal within the latest time period to obtain time-series feature information. Then, the prediction network in the blood pressure mutation identification model predicts blood pressure mutations based on the time-series feature information to obtain the blood pressure mutation identification result.

[0084] After performing the above step S2200, based on the PPG signal within the latest time period and the established blood pressure mutation identification model, and obtaining the wearer's blood pressure mutation identification result within the latest time period, proceed to:

[0085] Step S2300: If the blood pressure mutation identification result is a blood pressure mutation, output a prompt to the wearer that the blood pressure mutation identification result is a blood pressure mutation.

[0086] In this embodiment, when the blood pressure change identification result is a blood pressure change, the wearable device can output a prompt to the wearer indicating that the blood pressure change has occurred, so as to inform the wearer of the blood pressure change.

[0087] In an optional embodiment, if the blood pressure mutation identification result is a blood pressure mutation, step S2300 outputs a prompt to the wearer indicating that the blood pressure mutation identification result is a blood pressure mutation, including at least one of the following:

[0088] First item: If the blood pressure change identification result is a blood pressure change, the control output device shall provide a prompt that the blood pressure change identification result is a blood pressure change.

[0089] The output module includes at least one of a vibration output device and an audio output device.

[0090] Specifically, if the output module includes a vibration output device, and the blood pressure change detection result is a blood pressure change, the vibration output device can be controlled to output a prompt to the wearer that the blood pressure change detection result is a blood pressure change through vibration.

[0091] If the output module includes an audio output device, and the blood pressure mutation recognition result is a blood pressure mutation, the audio output device can be controlled to output a prompt to the wearer via voice and / or buzzer indicating that the blood pressure mutation recognition result is a blood pressure mutation.

[0092] Second item: When the blood pressure mutation identification result is a blood pressure mutation, control the terminal device that is communicating with the wearable device to prompt that the blood pressure mutation identification result is a blood pressure mutation through the target application.

[0093] Specifically, if the blood pressure mutation detection result is a blood pressure mutation, the wearable device can send a control command through the terminal device with which it has established a communication connection. This control command is used to control the terminal device to provide a notification that the blood pressure mutation detection result is a blood pressure mutation. The terminal device receives the control command and outputs a voice prompt and / or text prompt indicating that the blood pressure mutation detection result is a blood pressure mutation to the wearer through the target application it is running.

[0094] According to this embodiment, it can make relatively accurate predictions of blood pressure mutations using only PPG signals. Users only need to wear the wearable device naturally, making full use of their free time for continuous and imperceptible blood pressure monitoring, greatly improving user-friendliness. Furthermore, after the blood pressure monitoring function is activated, the wearable device can continuously and imperceptibly collect PPG signals and identify the PPG signals of the latest time period by setting a blood pressure recognition model, thus obtaining the blood pressure mutation identification results for the latest time period. In other words, by monitoring blood pressure mutations within a short period, it can provide more comprehensive protection for the user's health, providing early warnings of danger in the early stages of illness and reducing sudden injuries.

[0095] In one embodiment, after performing step S2100 above with the blood pressure monitoring function enabled, and continuously collecting the wearer's PPG signal through the PPG sensor of the wearable device, the blood pressure monitoring method of this embodiment further includes: writing the PPG signal continuously collected by the PPG sensor into a storage module; reading the latest consecutive N frames of PPG signal from the storage module as the PPG signal in the latest time period; wherein N is a positive integer; and deleting other PPG signals stored in the storage module except for the latest consecutive M frames of PPG signal every set time period; wherein M is a positive integer and M is greater than N.

[0096] Among them, the PPG signals in the storage module other than the latest continuous M-frame PPG signal can be understood as expired PPG signals.

[0097] The time period can be set according to the actual scenario and actual needs, and this embodiment does not limit it.

[0098] In practice, the PPG sensor can write the continuously collected PPG signals into the wearable device's storage module. If the user manually ends the blood pressure monitoring, the data acquisition and writing process stops. The wearable device can process the PPG signals stored in the storage module in two ways:

[0099] On one hand, the wearable device can find the latest N consecutive frames of PPG signals in the storage module as the PPG signals for the latest time period, and package the PPG signals for the latest time period. Then, based on the packaged PPG signals for the latest time period and the established blood pressure mutation recognition model, the wearer's blood pressure mutation recognition result for the latest time period is obtained.

[0100] On the other hand, the wearable device can actively release expired PPG signals in the storage module every set time period, retaining only the latest continuous M-frame PPG signals in the storage module, and releasing and discarding other PPG signals except for the latest continuous M-frame PPG signals.

[0101] Reference Figure 3 The latest PPG signal acquired by the PPG sensor is PPG signal 1. The latest consecutive N frames of PPG signals include PPG signal 1, PPG signal 2, PPG signal 3, PPG signal 4, PPG signal 5, PPG signal 6, PPG signal 7, and PPG signal 8. The latest consecutive M frames of PPG signals include PPG signal 1, PPG signal 2, PPG signal 3, PPG signal 4, PPG signal 5, PPG signal 6, PPG signal 7, PPG signal 8, PPG signal 9, and PPG signal 10, that is, M is 10, N is 8, and M>N. Expired PPG signals include PPG signal 1.

[0102] The wearable device can take the latest eight consecutive frames of PPG signals, namely PPG signal 1, PPG signal 2, PPG signal 3, PPG signal 4, PPG signal 5, PPG signal 6, PPG signal 7 and PPG signal 8, as the PPG signals in the latest time period, and package the PPG signals in the latest time period.

[0103] The wearable device can also store 10 consecutive PPG signals (PPG signal 1, PPG signal 2, PPG signal 3, PPG signal 4, PPG signal 5, PPG signal 6, PPG signal 7, PPG signal 8, PPG signal 9, and PPG signal 10) in the storage module. This means that PPG signals 9 and 10 are retained but not packaged; they are stored as a buffer in the storage module as backup PPG signals for blood pressure mutation identification in the event of problems with the aforementioned 8 consecutive PPG signals. The wearable device can also actively release PPG signal 11 from the storage module.

[0104] By managing the PPG signals stored in the storage module as described above, the wearable device can be kept in good condition for long-term operation.

[0105] <Example>

[0106] The following is an example of a blood pressure monitoring method, which further includes:

[0107] Step 401: Activate the blood pressure monitoring function of the wearable device.

[0108] Step 402: With the blood pressure monitoring function of the wearable device enabled, the wearable device continuously collects the wearer's PPG signal through its PPG sensor and writes it into the wearable device's storage module.

[0109] Step 403: The signal management module of the wearable device is responsible for processing the PPG signals stored in the storage module. On one hand, the signal management module reads the latest N consecutive frames of PPG signals from the storage module and packages them as the PPG signals for the latest time period. On the other hand, the signal management module is responsible for releasing expired signals in the storage module, retaining only the latest M consecutive frames of PPG signals in the storage module, and releasing and discarding the remaining PPG signals, where M>N.

[0110] Step 404: The feature extraction network of the neural network prediction module of the wearable device extracts features from the PPG signal, the first-order derivative PPG signal, and the second-stage PPG signal in the latest time period to obtain temporal feature information; and the prediction module of the neural network prediction module performs blood pressure mutation prediction on the temporal feature information to obtain the blood pressure mutation identification result of the wearer in the latest time period.

[0111] For example, the results of blood pressure mutation identification at different times are shown in Table 1 below. A blood pressure mutation identification result of "1" indicates that there is a blood pressure mutation, and a blood pressure mutation identification result of "0" indicates that there is no blood pressure mutation.

[0112] Table 1 Results of blood pressure mutation identification

[0113] date time Sudden blood pressure change 2024.1.1 7:00 0 2024.1.1 7:20 1 …… …… …… 2024.12.31 14:30 0 2024.12.31 14:40 0

[0114] Step 405: When the blood pressure change identification result is a blood pressure change, the wearable device controls the vibration output device to output a prompt that the blood pressure change identification result is a blood pressure change to the wearer, and / or controls the terminal device communicating with the wearable device to send a prompt that the blood pressure change identification result is a blood pressure change through the target application.

[0115] Based on this example, compared with existing technologies, the blood pressure monitoring method it provides transforms the blood pressure prediction task from traditional numerical prediction (regression task) to trend prediction (classification task), offering two main advantages: First, by increasing the monitoring of sudden blood pressure changes within a short period, it provides more comprehensive protection for users' health, enabling early warnings of potential dangers and reducing the risk of sudden injury. Second, this method uses only PPG signals for relatively accurate prediction of sudden blood pressure changes and requires only the user to wear the device naturally. In contrast, existing accurate blood pressure measurements require the use of PPG signals in conjunction with other signals such as ECG and PCG signals, requiring the user to remain still in a specific posture and unable to perform other activities. This method effectively utilizes a significant amount of the user's free time, providing continuous and imperceptible blood pressure monitoring, greatly improving user-friendliness.

[0116] <Device Embodiment>

[0117] Figure 5 This is a schematic diagram of the structure of a blood pressure monitoring device according to one embodiment, such as... Figure 5 As shown, the blood pressure monitoring device 500 includes a data acquisition module 510, an identification module 520, and an output module 530.

[0118] The acquisition module 510 is used to continuously acquire the wearer's PPG signal through the PPG sensor of the wearable device when the blood pressure monitoring function is turned on.

[0119] The identification module 520 is used to obtain the blood pressure mutation identification result of the wearer in the latest time period based on the PPG signal in the latest time period and the set blood pressure mutation identification model;

[0120] The output module 530 is used to output a prompt to the wearer that the blood pressure mutation identification result is a blood pressure mutation when the blood pressure mutation identification result is a blood pressure mutation.

[0121] In one embodiment, the identification module 520 is specifically used to acquire the first-order PPG signal of the PPG signal in the latest time period; acquire the second-order PPG signal of the PPG signal in the latest time period; and obtain the blood pressure mutation identification result of the wearer in the latest time period based on the PPG signal in the latest time period, the first-order PPG signal, the second-order PPG signal and the set blood pressure mutation identification model.

[0122] In one embodiment, the identification module 520 is specifically used to extract features from the PPG signal, the first-order PPG signal, and the second-order PPG signal within the latest time period through the feature extraction network in the set blood pressure mutation identification model to obtain temporal feature information; and to predict blood pressure mutations based on the temporal feature information through the prediction network in the set blood pressure mutation identification model to obtain the blood pressure mutation identification result of the wearer within the latest time period.

[0123] In one embodiment, the device 500 further includes a writing module and a reading module (both not shown in the figure).

[0124] The writing module is used to write the PPG signal continuously collected by the PPG sensor into the storage module;

[0125] The reading module is used to read the latest N consecutive frames of PPG signals from the storage module as the PPG signals in the latest time period;

[0126] Where N is a positive integer.

[0127] In one embodiment, the device 500 further includes a deletion module (not shown).

[0128] The deletion module is used to delete PPG signals stored in the storage module, except for the latest consecutive M-frame PPG signal, at set time intervals.

[0129] Where M is a positive integer, and M is greater than N.

[0130] In one embodiment, the device 500 further includes a receiving module and an enabling module (not shown in the figure).

[0131] A receiving module is used to receive input operations on the wearable device;

[0132] The module is activated in response to the input operation to enable the blood pressure monitoring function.

[0133] In one embodiment, the output module 530 is specifically configured to, when the blood pressure change identification result is a blood pressure change, control the output device to provide a prompt that the blood pressure change identification result is a blood pressure change; and, when the blood pressure change identification result is a blood pressure change, control the terminal device communicating with the wearable device to provide a prompt that the blood pressure change identification result is a blood pressure change through a target application.

[0134] According to this embodiment, it can make relatively accurate predictions of blood pressure mutations using only PPG signals. Users only need to wear the wearable device naturally, making full use of their free time for continuous and imperceptible blood pressure monitoring, greatly improving user-friendliness. Furthermore, after the blood pressure monitoring function is activated, the wearable device can continuously and imperceptibly collect PPG signals and identify the PPG signals of the latest time period by setting a blood pressure recognition model, thus obtaining the blood pressure mutation identification results for the latest time period. In other words, by monitoring blood pressure mutations within a short period, it can provide more comprehensive protection for the user's health, providing early warnings of danger in the early stages of illness and reducing sudden injuries.

[0135] <Equipment Example>

[0136] Figure 6 This is a schematic diagram of the hardware structure of a wearable device according to one embodiment. Figure 6 As shown, the wearable device 600 includes a PPG sensor 610, and the wearable device 600 also includes a processor 620 and a memory 630.

[0137] The memory 630 can be used to store executable computer instructions.

[0138] The processor 620 can be used to execute the blood pressure monitoring method according to the method embodiments of this disclosure, under the control of the executable computer instructions.

[0139] The wearable device 600 can be as follows: Figure 1 The wearable device 1000 shown may also be a device with other hardware structures, which are not limited here. In another embodiment, the wearable device 600 may include the blood pressure monitoring device 500 described above.

[0140] In one embodiment, each module of the blood pressure monitoring device 500 can be implemented by the processor 620 running computer instructions stored in the memory 630.

[0141] Computer-readable storage media

[0142] This disclosure also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, perform the blood pressure monitoring method provided in this disclosure.

[0143] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0144] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0145] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0146] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0147] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0148] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0149] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It will be known to those skilled in the art that implementation in hardware, implementation in software, and implementation in a combination of software and hardware are equivalent.

[0151] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this disclosure is defined by the appended claims.

Claims

1. A wearable device, comprising: The wearable device comprises a PPG sensor, and further comprises: a memory for storing executable computer instructions; and a processor for executing the following method steps under the control of the executable computer instructions: continuously collecting PPG signals of a wearer through the PPG sensor of the wearable device in a case where a blood pressure monitoring function is in an open state; obtaining a blood pressure mutation recognition result of the wearer in a latest time period according to the PPG signals in the latest time period and a set blood pressure mutation recognition model; wherein the set blood pressure mutation recognition model is used for performing a classification task, and the blood pressure mutation recognition result comprises blood pressure mutation and no blood pressure mutation; outputting a prompt that the blood pressure mutation recognition result is blood pressure mutation to the wearer in a case where the blood pressure mutation recognition result is blood pressure mutation; wherein the set blood pressure mutation recognition model comprises a feature extraction network and a prediction network, the feature extraction network comprises a long short-term memory network, and the prediction network comprises a fully connected layer; and the processor obtains the blood pressure mutation recognition result of the wearer in the latest time period according to the PPG signals in the latest time period and the set blood pressure mutation recognition model by: obtaining time sequence feature information by performing feature extraction on the PPG signals in the latest time period through the feature extraction network; and obtaining the blood pressure mutation recognition result of the wearer in the latest time period by performing blood pressure mutation prediction based on the time sequence feature information through the prediction network.

2. The wearable device of claim 1, wherein, The processor obtains the blood pressure mutation recognition result of the wearer in the latest time period according to the PPG signals in the latest time period and the set blood pressure mutation recognition model by: obtaining a first-order derivative PPG signal of the PPG signals in the latest time period; obtaining a second-order derivative PPG signal of the PPG signals in the latest time period; obtaining the blood pressure mutation recognition result of the wearer in the latest time period according to the PPG signals in the latest time period, the first-order derivative PPG signal, the second-order derivative PPG signal and the set blood pressure mutation recognition model.

3. The wearable device of claim 2, wherein, The processor obtains the blood pressure mutation recognition result of the wearer in the latest time period according to the PPG signals in the latest time period, the first-order derivative PPG signal, the second-order derivative PPG signal and the set blood pressure mutation recognition model by: performing feature extraction on the PPG signals in the latest time period, the first-order derivative PPG signal and the second-order derivative PPG signal through a feature extraction network in the set blood pressure mutation recognition model to obtain time sequence feature information; performing blood pressure mutation prediction based on the time sequence feature information through a prediction network in the set blood pressure mutation recognition model to obtain the blood pressure mutation recognition result of the wearer in the latest time period.

4. The wearable device of claim 1, wherein, The processor, after continuously collecting PPG signals of a wearer through the PPG sensor of the wearable device in a case where a blood pressure monitoring function is in an open state, further executes the following method steps: writing the PPG signals continuously collected through the PPG sensor into a storage module; read the latest continuous N frames of PPG signals from the storage module as the PPG signals in the latest time period; wherein N is a positive integer.

5. The wearable device of claim 4, wherein, The processor further performs the following method steps: Every set time period, delete the PPG signals stored in the storage module other than the latest continuous M frames of PPG signals; wherein M is a positive integer, and M is greater than N.

6. The wearable device of claim 1, wherein, The processor further performs the following method steps: receive an input operation on the wearable device; in response to the input operation, start the blood pressure monitoring function.

7. The wearable device of claim 1, wherein, The processor performs the following steps in the case where the blood pressure mutation identification result is blood pressure mutation: outputting a prompt to the wearer that the blood pressure mutation identification result is blood pressure mutation, specifically including: in the case where the blood pressure mutation identification result is blood pressure mutation, controlling the output device to prompt that the blood pressure mutation identification result is blood pressure mutation; in the case where the blood pressure mutation identification result is blood pressure mutation, controlling the terminal device in communication connection with the wearable device to prompt that the blood pressure mutation identification result is blood pressure mutation through a target application.

8. A blood pressure monitoring device, characterized by, The device is applied to a wearable device, and the device comprises: a collection module configured to continuously collect PPG signals of a wearer through a PPG sensor of the wearable device in the case where a blood pressure monitoring function is in a started state; an identification module configured to obtain a blood pressure mutation identification result of the wearer in a latest time period according to the PPG signals in the latest time period and a set blood pressure mutation identification model; wherein the set blood pressure mutation identification model is configured to perform a classification task, and the blood pressure mutation identification result comprises blood pressure mutation and no blood pressure mutation; an output module configured to output a prompt to the wearer that the blood pressure mutation identification result is blood pressure mutation in the case where the blood pressure mutation identification result is blood pressure mutation. The set blood pressure mutation identification model comprises a feature extraction network and a prediction network, the feature extraction network comprises a long short-term memory network, the prediction network comprises a fully connected layer, and the blood pressure mutation identification result of the wearer in the latest time period is obtained according to the PPG signals in the latest time period and the set blood pressure mutation identification model by: performing feature extraction on the PPG signals in the latest time period through the feature extraction network to obtain time sequence feature information; and performing blood pressure mutation prediction based on the time sequence feature information through the prediction network to obtain the blood pressure mutation identification result of the wearer in the latest time period.

9. A computer readable storage medium having computer instructions stored thereon, the computer instructions being executed by a processor to perform the following method steps: in the case where a blood pressure monitoring function is in a started state, continuously collect PPG signals of a wearer through a PPG sensor of a wearable device; According to the PPG signal in the latest time period and a set blood pressure mutation recognition model, a blood pressure mutation recognition result of the wearer in the latest time period is obtained; wherein, the set blood pressure mutation identification model is configured to perform a classification task, and the blood pressure mutation identification result comprises blood pressure mutation and no blood pressure mutation; in the case where the blood pressure mutation identification result is blood pressure mutation, output a prompt to the wearer that the blood pressure mutation identification result is blood pressure mutation. The setting blood pressure mutation recognition model comprises a feature extraction network and a prediction network, the feature extraction network comprises a long short-term memory network, the prediction network comprises a full connection layer, and the blood pressure mutation recognition result of the wearer in the latest time period is obtained according to the PPG signal in the latest time period and the setting blood pressure mutation recognition model, which comprises: the feature extraction network is used for feature extraction on the PPG signal in the latest time period, and time sequence feature information is obtained; and the prediction network is used for blood pressure mutation prediction based on the time sequence feature information, and a blood pressure mutation recognition result of the wearer in the latest time period is obtained.

Images