Device and method for measuring blood pressure

Abstract

The present application provides a device and method for measuring blood pressure. The device includes a processor 101, a first measurement component 102, and a second measurement component 103. The first measurement component 102 is configured to collect a user's blood pressure value; the second measurement component 103 is configured to collect the user's PPG signal. The processor 101 controls the first measurement component 102 to collect N sets of blood pressure values ​​from the user, and controls the second measurement component 103 to collect N sets of PPG signals corresponding to the N sets of blood pressure values. A target model is generated based on the N sets of blood pressure values ​​and PPG signals, where the input of the target model is the PPG signal and the output is the blood pressure value. After the target model is generated, the second measurement component 103 is controlled to collect the user's first PPG signal, and the first blood pressure value is determined based on the target model and the first PPG signal. This device can improve the accuracy of the measurement results when measuring the user's blood pressure value and is easy to operate.

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and more specifically, to a device and method for measuring blood pressure. Background Art

[0002] At present, the number of hypertensive patients in China accounts for a very large proportion of the total number of cardiovascular disease patients. For hypertensive patients, daily blood pressure monitoring by measuring blood pressure is essential.

[0003] Methods for measuring blood pressure usually include auscultation and oscillometric methods. Both methods require that the cuff be wrapped around the person's arm and then manually or automatically inflated and deflated. This method of measuring blood pressure can be called a cuff measurement method, and the corresponding equipment can be called a cuff-type blood pressure measurement device.

[0004] Although the measurement accuracy of the cuff-type blood pressure measuring device can meet medical standards, it is inconvenient to operate and easily causes discomfort to the user. Therefore, it is necessary to provide a blood pressure measuring device that is easy to operate and has high measurement accuracy. Summary of the Invention

[0005] The present application provides a device and method for measuring blood pressure, which can improve the accuracy of measurement results when measuring the blood pressure value of a user and is easy to operate.

[0006] In a first aspect, a device for measuring blood pressure is provided, characterized in that the device for measuring blood pressure includes a processor 101, a first measuring component 102, and a second measuring component 103, wherein the first measuring component 102 includes an inflatable component 1022, an airbag 1023, and an air pressure sensor 1024, wherein the airbag 1023 is connected to the inflatable component 1022 and the air pressure sensor 1024, respectively, and the second measuring component 103 includes a light source 1031 and a PPG sensor 1032; the first measuring component 102 is used to collect the user's blood pressure value; the second measuring component 103 is used to collect the user's PPG value. PG signal; the processor 101 is used to control the first measurement component 102 to collect N groups of blood pressure values ​​of the user; control the second measurement component 103 to collect N groups of PPG signals corresponding to the N groups of blood pressure values; generate a target model based on the N groups of blood pressure values ​​and the N groups of PPG signals, where the input of the target model is the PPG signal and the output is the blood pressure value, and N is an integer greater than or equal to 2; the processor 101 is further used to control the second measurement component 103 to collect the first PPG signal of the user after the target model is generated; and determine the first blood pressure value based on the target model and the first PPG signal.

[0007] Based on the above technical solution, since the target model is obtained after model training based on the user's own N sets of blood pressure values ​​(these N sets of blood pressure values ​​are obtained through the first measurement component 102, and the accuracy of the blood pressure values ​​obtained through the first measurement component 102 is relatively high) and N sets of PPG signals corresponding one to one to the N sets of blood pressure values, therefore, when the user's blood pressure value is subsequently determined based on the user's PPG signal through the target model 2, the measurement result of the blood pressure value obtained will be more accurate.

[0008] In addition, by integrating the second measurement component for collecting PPG signals with the first measurement component, it is possible to more conveniently obtain N sets of blood pressure values ​​for generating a target model and N sets of PPG signals corresponding to the N sets of blood pressure values. The target model in this application corresponds to the target model 2 described above.

[0009] In a possible implementation, the processor is further configured to, when acquiring the i-th group of PPG signals among the N groups of PPG signals, control the second measurement component 103 to acquire a PPG signal of a first duration; determine a category to which the PPG signal of the first duration belongs; determine a similarity between the PPG signal of the first duration and a center of the category of the PPG signal of the first duration in a first historical PPG signal, wherein the first historical PPG signal includes a PPG signal acquired before acquiring the i-th group of PPG signals; determine a second duration based on the similarity; control the second measurement component 103 to acquire the PPG signal of the second duration; and merge the PPG signal of the first duration and the PPG signal of the second duration into the i-th group of PPG signals.

[0010] Based on the above technical solution, by first acquiring a PPG signal of a first duration and determining the category to which the PPG signal of the first duration belongs, further determining the similarity between the PPG signal of the first duration and the center of the category of the PPG signal of the first duration in the first historical PPG signal, and determining whether to continue acquiring the PPG signal of the second duration based on the similarity, the acquisition duration of a group of PPG signals can be flexibly determined without affecting the measurement accuracy of the target model 2.

[0011] In a possible implementation, the processor is further configured to, when collecting the first to Mth groups of PPG signals among the N groups of PPG signals, control the second measurement component 103 to obtain PPG signals of a third duration, where M is an integer less than i.

[0012] In one possible implementation, the processor 101 is further configured to, when determining to update the target model, prompt the user to trigger an instruction to measure blood pressure through the first measurement component 102 and the second measurement component 103; in response to the user's first operation, control the first measurement component 102 to collect a second blood pressure value, and control the second measurement component 103 to collect a second PPG signal corresponding to the second blood pressure value; and update the target model according to the second blood pressure value and the second PPG signal.

[0013] Based on the above technical solution, in order to further improve the measurement accuracy of target model 2, when it is determined that target model 2 needs to be updated, the user is prompted to trigger an instruction to measure blood pressure through the first measurement component, and then the target model 2 is updated according to the blood pressure value and PPG signal obtained based on the instruction to measure blood pressure through the first measurement component triggered by the user.

[0014] In a possible implementation, the processor 101 is further configured to determine a category of the first PPG signal;

[0015] The processor 101 is further configured to determine a similarity between the first PPG signal and centers of PPG signals belonging to the category of the first PPG signal in a second historical PPG signal, and determine whether it is necessary to update the target model based on the similarity and the number of groups of PPG signals belonging to the category of the first PPG signal in the second historical PPG signal, wherein the second historical PPG signal includes the N groups of PPG signals.

[0016] In a possible implementation, the processor 101 is further configured to determine whether the target model needs to be updated according to a period of time during which the target model has not been updated.

[0017] In a possible implementation, the inflatable component 1022 is used to inflate the airbag 1023;

[0018] The air pressure sensor 1024 is used to collect multiple air pressure values ​​of the airbag 1023, where the first air pressure value and the second air pressure value among the multiple air pressure values ​​are the blood pressure values ​​of the user. The first air pressure value corresponds to the moment when the oscillation wave of the air pressure in the airbag 1023 reaches the maximum value, and the second air pressure value corresponds to the moment when the oscillation wave reaches a× the maximum value, where a is greater than 0 and less than 1.

[0019] In one possible implementation, the difference between the moment of starting to inflate the airbag 1023 and the moment of collecting the i-th group of PPG signals is greater than or equal to a preset first threshold and less than or equal to a preset second threshold, and the moment of starting to inflate the airbag 1023 is after the moment of collecting the i-th group of PPG signals, or the difference between the moment of collecting the i-th group of PPG signals and the moment of stopping to inflate the airbag 1023 is greater than or equal to a preset third threshold and less than or equal to a preset fourth threshold, and the moment of stopping to inflate the airbag 1023 is before the moment of collecting the i-th group of PPG signals.

[0020] When collecting the i-th group of blood pressure values ​​of the user, the inflatable component 1022 needs to inflate the airbag 1023. Since the inflated airbag 1023 will exert pressure on the user's wrist, it will affect the accuracy of the obtained i-th group of PPG signals of the user.

[0021] In order to avoid affecting the accuracy of the PPG signal, the i-th group of PPG signals is collected at a time before the airbag 1023 starts to be inflated or a time after the airbag 1023 stops being inflated. This allows the time period for collecting the i-th group of PPG signals to avoid the time period when the gas inside the airbag 1023 may press on the user's wrist. In other words, the i-th group of PPG signals is collected during the time period other than the time period when the gas inside the airbag 1023 may press on the user's wrist, thereby improving the accuracy of the i-th group of PPG signals obtained for the user.

[0022] In a second aspect, a method for measuring blood pressure is provided. The method is applied to a blood pressure measuring device, the blood pressure measuring device including a first measurement component 102 and a second measurement component 103. The first measurement component 102 includes an inflatable component 1022, an airbag 1023, and an air pressure sensor 1024, the airbag 1023 being connected to the inflatable component 1022 and the air pressure sensor 1024, respectively. The second measurement component 103 includes a light source 1031 and a PPG sensor 1032. The method includes: controlling the first measurement component 102 to collect N sets of blood pressure values ​​of the user; controlling the second measurement component 103 to collect N sets of PPG signals corresponding to the N sets of blood pressure values; generating a target model based on the N sets of blood pressure values ​​and the N sets of PPG signals, wherein the input of the target model is the PPG signal and the output is the blood pressure value, and N is an integer greater than or equal to 2; after the target model is generated, controlling the second measurement component to collect a first PPG signal of the user; and determining a first blood pressure value based on the target model and the first PPG signal.

[0023] In a possible implementation, when collecting the i-th group of PPG signals among the N groups of PPG signals, controlling the second measurement component 103 to collect N groups of PPG signals corresponding to the N groups of blood pressure values ​​includes: controlling the second measurement component 103 to obtain PPG signals of a first duration; determining the category to which the PPG signals of the first duration belong; determining the similarity between the PPG signals of the first duration and the center of the category of the PPG signals belonging to the first duration in first historical PPG signals, wherein the first historical PPG signals include PPG signals that have been obtained before obtaining the i-th group of PPG signals; determining a second duration based on the similarity; controlling the second measurement component 103 to collect the PPG signals of the second duration; and merging the PPG signals of the first duration and the PPG signals of the second duration into the i-th group of PPG signals.

[0024] In one possible implementation, when collecting the first to Mth groups of PPG signals among the N groups of PPG signals, controlling the second measurement component 103 to collect N groups of PPG signals corresponding to the N groups of blood pressure values ​​includes: controlling the second measurement component 103 to obtain PPG signals of a third duration, where M is an integer less than i.

[0025] In one possible implementation, the method further includes: when it is determined to update the target model, prompting the user to trigger an instruction to measure blood pressure through the first measurement component 102 and the second measurement component 103; in response to the user's first operation, controlling the first measurement component 102 to collect a second blood pressure value, and controlling the second measurement component 103 to collect a second PPG signal corresponding to the second blood pressure value; and updating the target model according to the second blood pressure value and the second PPG signal.

[0026] In a possible implementation, the method further includes: determining a category of the first PPG signal;

[0027] determining a similarity between the first PPG signal and centers of PPG signals belonging to the category of the first PPG signal in a second historical PPG signal, and determining whether it is necessary to update the target model based on the similarity and the number of groups of PPG signals belonging to the category of the first PPG signal in the second historical PPG signal, wherein the second historical PPG signal includes the N groups of PPG signals.

[0028] In a possible implementation, the method further includes: determining whether the target model needs to be updated according to a period of time during which the target model has not been updated.

[0029] In one possible implementation, controlling the first measuring component 102 to collect N groups of blood pressure values ​​of the user includes: controlling the inflatable component 1022 to inflate the airbag 1023; controlling the air pressure sensor 1024 to collect multiple air pressure values ​​of the airbag 1023, where the first air pressure value and the second air pressure value among the multiple air pressure values ​​are a group of blood pressure values ​​of the user, the first air pressure value corresponds to the air pressure value at the moment when the oscillation wave of the air pressure in the airbag 1023 reaches the maximum value, and the second air pressure value corresponds to the air pressure value at the moment when the oscillation wave reaches a×the maximum value, where a is greater than 0 and less than 1.

[0030] In one possible implementation, the difference between the moment of starting to inflate the airbag 1023 and the moment of collecting the i-th group of PPG signals is greater than or equal to a preset first threshold and less than or equal to a preset second threshold, and the moment of starting to inflate the airbag 1023 is after the moment of collecting the i-th group of PPG signals, or the difference between the moment of collecting the i-th group of PPG signals and the moment of stopping to inflate the airbag 1023 is greater than or equal to a preset third threshold and less than or equal to a preset fourth threshold, and the moment of stopping to inflate the airbag 1023 is before the moment of collecting the i-th group of PPG signals.

[0031] For the beneficial effects of any implementation method in the second aspect, please refer to the relevant description of the first aspect. For the sake of brevity, they will not be repeated here.

[0032] In a third aspect, a device for measuring blood pressure is provided, which has the functionality to implement the device behavior described in the aforementioned aspects and any of the possible design methods. This functionality can be implemented via hardware or via hardware executing corresponding software. The hardware or software includes at least one module or unit corresponding to the aforementioned functionality. For example, a measurement module or unit, a sensor module or unit, an inflation module or unit, etc.

[0033] In a fourth aspect, a computer storage medium is provided, comprising computer instructions. When the computer instructions are executed on a device for measuring blood pressure, the device for measuring blood pressure executes the method for measuring blood pressure in any possible design of the above aspects.

[0034] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is caused to execute the method for measuring blood pressure in any possible design of the above aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a schematic block diagram of the device 100 for measuring blood pressure provided in the present application.

[0036] Figure 2This is a schematic diagram of the electrical control logic of the blood pressure measuring device 100 provided in this application.

[0037] Figure 3 This is a schematic structural diagram of the blood pressure measuring device 100 provided in this application.

[0038] Figure 4 This is a schematic diagram of the distribution of multiple light sources and multiple photoelectric sensors provided in this application on the device body.

[0039] Figure 5 Schematic diagram of a user wearing a watch to measure blood pressure provided in this application.

[0040] Figure 6 This is a schematic diagram of the display interface of the display screen of a watch for measuring blood pressure provided in this application.

[0041] Figure 7 This is a schematic flow chart of the method for measuring blood pressure provided in this application. DETAILED DESCRIPTION

[0042] The technical solutions in each embodiment of the present application will be described below with reference to the accompanying drawings. In the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity or execution order, and the words "first" and "second" do not necessarily mean different.

[0043] The present application provides a device 100 for measuring blood pressure.

[0044] In one implementation, the device 100 may be pre-configured with a target model 1, which represents the correspondence between the PPG signal and the blood pressure value. For example, the target model 1 may be pre-configured for the device 100 before the device 100 leaves the factory. The input of the target model 1 may be the user's photoplethysmogram (PPG) signal, and the output may be a set of blood pressure values ​​of the user. In other words, after the user's PPG signal is input into the target model 1, a set of blood pressure values ​​of the user may be obtained through the target model 1.

[0045] It should be understood that a set of blood pressure values ​​of a user in this application includes the user's systolic blood pressure (SBP) and diastolic blood pressure (DBP). For the sake of ease of description, this application uses a set of blood pressure values ​​to replace the user's systolic blood pressure and diastolic blood pressure.

[0046] To improve the accuracy of the user's blood pressure values ​​obtained based on the user's PPG signals, multiple sets of the user's PPG signals and multiple sets of the user's blood pressure values ​​(the multiple sets of the user's blood pressure values ​​here are not obtained through the above-mentioned target model 1, but are obtained through the first measurement component below) can be used to update target model 1 to obtain target model 2, where the multiple sets of blood pressure values ​​correspond one-to-one with the multiple sets of PPG signals. Since target model 2 is obtained by updating target model 1 based on the user's own multiple sets of blood pressure values ​​and multiple sets of PPG signals, the user's blood pressure values ​​obtained through target model 2 and based on the user's PPG signals will be more accurate than target model 1. Target model 2 in this application corresponds to the target model.

[0047] In this case, the apparatus 100 includes a processor 101, a first measurement component 102 and a second measurement component 103. Figure 1 A schematic block diagram of the apparatus 100 is shown.

[0048] For example, the first measurement component 102 is used to collect the user's blood pressure value. In other words, the first measurement component 102 collects the user's blood pressure N times, obtaining N sets of the user's blood pressure values, where N is an integer greater than 2. For example, after detecting a user-triggered instruction to measure the blood pressure through the first measurement component 102, the processor 101 may send a blood pressure collection instruction to the first measurement component 102, and the first measurement component 102 executes the blood pressure collection instruction to collect the user's blood pressure value.

[0049] The second measurement component 103 is used to collect the user's PPG signal, and the processor 101 is used to control the second measurement component 103 to collect a set of PPG signals corresponding to the user's blood pressure value. For the method by which the processor 101 obtains a set of PPG signals corresponding to the user's blood pressure value, please see the relevant description below.

[0050] It is worth mentioning that the blood pressure value of the user and a set of PPG signals corresponding to the blood pressure value in this application are obtained after measuring the same part of the user.

[0051] Processor 101 is used to update target model 1 based on N groups of blood pressure values ​​and N groups of PPG signals of the user to obtain target model 2. Target model 2 represents the correspondence between the user's PPG signal and blood pressure value. The input of target model 2 is the user's PPG signal, and the output is the user's blood pressure value.

[0052] When measuring the user's blood pressure based on the target model 2, the processor 101 is further configured to: after acquiring the user's first PPG signal, input the first PPG signal into the target model 2 to obtain the user's first blood pressure value.

[0053] It should be noted that the above-mentioned processor 101 is pre-configured with target model 1 only as an example and does not constitute a limitation to the present application. In a specific implementation, the target model 1 may not be pre-configured in the processor 101, but the processor 101 may directly generate target model 2 based on N groups of blood pressure values ​​and N groups of PPG signals.

[0054] Optionally, the first measurement component 102 may include an inflatable component 1022 , an airbag 1023 , and an air pressure sensor 1024 , wherein the airbag 1023 is connected to the inflatable component 1022 and the air pressure sensor 1024 , respectively.

[0055] When collecting the user's blood pressure value: the inflatable component 1022 is used to inflate the airbag 1023; the air pressure sensor 1024 is used to collect multiple air pressure values ​​of the airbag 1023, wherein, among the multiple air pressure values, the air pressure value corresponding to the moment when the oscillation wave of the air pressure in the airbag 1023 reaches the maximum value is the first air pressure value, and the air pressure value corresponding to the moment when the oscillation wave of the air pressure in the airbag 1023 reaches a×maximum value is the second air pressure value, the first air pressure value is the user's systolic pressure, and the second air pressure value is the user's diastolic pressure, wherein a is greater than 0 and less than 1.

[0056] For example, if the pressure value corresponding to the moment when the oscillation wave of the air pressure in the airbag 1023 reaches the maximum value is 128, then 128 can be determined as the user's systolic blood pressure. Assuming that the value of a is 0.45, and assuming that the pressure value corresponding to the moment when the oscillation wave of the air pressure in the airbag 1023 reaches 0.45×the maximum value is 80, then 80 can be determined as the user's diastolic blood pressure. At this time, the systolic pressure of 128 and the diastolic pressure of 80 constitute a set of blood pressure values ​​for the user.

[0057] Optionally, the second measurement component 103 may include multiple light sources 1031 and multiple PPG sensors 1032 . The multiple light sources 1031 and the multiple PPG sensors 1032 may be disposed on the contact surface between the device 100 and the user's body part.

[0058] When collecting PPG signals: multiple light sources 1031 are used to emit light, and multiple PPG sensors 1032 are used to obtain reflected light after the emitted light is reflected by the body part of the user that is in contact with the device 100, and convert the received light signal into a PPG signal.

[0059] Optionally, the device 100 may further include a display module 104 and a power module 105. The power module 105 is used to supply power to the device 100, and the display module 104 is used to display the user's blood pressure value to the user. Figure 2 FIG. 1 shows a schematic diagram of an electrical control logic of the device 100 , wherein the processor 101 may be a microcontroller unit (MCU), and the display module 104 may be a display screen.

[0060] Optionally, the device 100 is a watch for measuring blood pressure. Figure 3 In this case, the device 100 may further include a binding component 1021, which may be a watch strap. The airbag 1023 may be adhered to the strap or fixed to the strap via a buckle. The display module 104 may be a display screen of the watch. It is worth mentioning that when the device 100 is a watch, the air pressure sensor 1024 ( Figure 3 Not shown) and the inflatable component 1022 ( Figure 3 Not shown) is also deployed inside the watch dial.

[0061] When the device 100 is a watch, the plurality of light sources 1031 and the plurality of PPG sensors 1032 may be distributed on the back of the watch dial. Figure 4 Schematic diagram showing the distribution of multiple light sources 1031 and multiple PPG sensors 1032 on the back of a watch dial. For example, the light source 1031 may be a light-emitting diode (LED) that emits green light.

[0062] After the user wears the watch on the wrist, if an instruction to measure blood pressure through the first measuring component 102 triggered by the user is detected, the processor 101 can start collecting the user's blood pressure value. The processor 101 can send an instruction to the inflatable component 1022 to inflate the airbag 1023. The inflatable component 1022 executes the instruction to inflate the airbag 1023. At the same time, the processor 101 can send an instruction to collect the air pressure value of the airbag 1023 to the air pressure sensor 1024. The air pressure sensor 1024 executes the instruction to collect multiple air pressure values ​​of the airbag 1023. The processor 101 determines the user's blood pressure value based on the first air pressure value and the second air pressure value among the multiple air pressure values. Figure 5 A schematic diagram showing a user wearing a watch for measuring blood pressure.

[0063] When collecting the user's PPG signal, the light source 1031 first emits light. After the emitted light is reflected by the user's wrist, the PPG sensor 1032 obtains the reflected light after the emitted light is reflected by the user's wrist and converts the obtained light signal into a PPG signal.

[0064] After obtaining the user's first blood pressure value based on the user's first PPG signal and the target model 2, the processor 101 can display the first blood pressure value to the user through the display screen of the watch. At this time, the display interface of the display screen of the watch can be as follows: Figure 6 shown.

[0065] In addition, the processor 101 can also display the user's blood pressure value obtained by the first measuring component 102 to the user through the display screen of the watch.

[0066] It should be noted that after determining the blood pressure value, the processor 101 may display the blood pressure value to the user, or may output the blood pressure value through voice, which is not limited in this application.

[0067] Optionally, the user's PPG signal may be collected at a time before inflation of the airbag 1023 begins or at a time after inflation of the airbag 1023 stops. In other words, the difference between the time when inflation of the airbag 1023 begins and the time when the user's PPG signal is collected is greater than or equal to a preset first threshold and less than or equal to a preset second threshold; alternatively, the difference between the time when the user's PPG signal is collected and the time when inflation of the airbag 1023 stops is greater than or equal to a preset third threshold and less than or equal to a preset fourth threshold.

[0068] When collecting the user's blood pressure, the inflatable component 1022 needs to inflate the airbag 1023. Since the inflated airbag 1023 will press on the user's wrist, this will affect the accuracy of the acquired PPG signal. Therefore, to avoid affecting the accuracy of the PPG signal, the user's PPG signal can be collected during a time period that does not involve the gas inside the airbag 1023 pressing on the user's wrist. In other words, the i-th group of PPG signals can be collected during a time period outside of the time period when the gas inside the airbag 1023 presses on the user's wrist.

[0069] For example, the processor 101 may determine a moment before the airbag 1023 starts to be inflated or a moment after the airbag 1023 stops being inflated as the collection moment of the i-th group of PPG signals, so that the time period for collecting the user's PPG signals avoids the time period when the gas inside the airbag 1023 may press on the user's wrist.

[0070] In some embodiments, to ensure that the user's physical condition is as consistent as possible when collecting PPG signals and measuring blood pressure, the two times can be close to each other. For example, if the preset first threshold is 10 seconds and the preset second threshold is 40 seconds, and the processor 101 begins inflating the airbag 1023 at time t1, the time corresponding to t1-(30 seconds) can be used as the time for collecting the i-th group of PPG signals. Alternatively, if the preset third threshold is 5 seconds and the preset fourth threshold is 20 seconds, the processor 101 stops inflating the airbag 1023 at time t2, and the time corresponding to t2+(10 seconds) can be used as the time for collecting the i-th group of PPG signals. This ensures that the gas inside the airbag 1023 does not press on the user's wrist during the collection of the i-th group of PPG signals.

[0071] Optionally, when collecting the i-th group of PPG signals among the N groups of PPG signals, the second measurement component 103 is configured to obtain a PPG signal of a first duration; the processor 101 is configured to determine a category to which the PPG signal of the first duration belongs. For ease of description, the category to which the PPG signal of the first duration belongs is referred to as the first category; further determine a similarity between the PPG signal of the first duration and the centers of multiple groups of PPG signals belonging to the first category in the first historical PPG signals; and based on the similarity, send an instruction to collect a PPG signal of a second duration to the second measurement component 103. Upon receiving the instruction to collect the PPG signal of the second duration, the second measurement component 103 is configured to collect the PPG signal of the second duration. In this case, the i-th group of PPG signals includes the PPG signal of the first duration and the PPG signal of the second duration. The value of the second duration may be related to the similarity.

[0072] Assume that when updating target model 1, blood pressure values ​​and PPG signals of N groups of users are collected. When collecting PPG signals from the N groups of users, processor 101 may first collect several groups of PPG signals for a fixed duration and classify them. When subsequently collecting PPG signals other than the N groups, for each group of PPG signals, a PPG signal for a fixed duration may be collected, and the category to which the PPG signal for this duration belongs may be determined. The similarity between the PPG signal for this duration and the centers of multiple PPG signals belonging to the category in the aforementioned groups of PPG signals may be further determined. Based on the similarity, it is determined whether to continue collecting PPG signals for a longer duration. If it is determined that it is not necessary to continue collecting PPG signals, the previously collected PPG signals for the previously collected duration are used as a group of PPG signals. If it is determined that it is necessary to continue collecting PPG signals, the previously collected PPG signals and the previously collected PPG signals for the previously collected duration are combined into a group of PPG signals. This method allows for flexible determination of the collection duration of a group of PPG signals. The fixed duration in this application corresponds to the third duration.

[0073] Assume that when the target model 1 is updated, a total of 50 groups of user blood pressure values ​​and 50 groups of user PPG signals are collected. For the PPG signals of these 50 groups of users, assume that the processor 101 first collects the first 30 groups of PPG signals for a fixed duration, that is, the value of M is 30. Among the above 50 groups of user PPG signals, the PPG signals other than the first 30 groups of PPG signals can be collected by dynamically determining the collection duration. The following first exemplifies the collection process of the first 30 groups of PPG signals.

[0074] For example, the processor 101 first collects 30 sets of PPG signals for a fixed time period, and then classifies the 30 sets of PPG signals based on the k-means clustering algorithm (k-means). The first 30 sets of PPG signals correspond to the first historical PPG signals.

[0075] For example, features are extracted from each of the 30 PPG signals. These features may include, for example, the pulse onset peak, dicrotic wave height, and rising phase duration of the PPG signal waveform. Based on the extracted features, the 30 PPG signals are classified using a k-means clustering algorithm. For example, the first 30 PPG signals fall into three categories, which are labeled Category 1, Category 2, and Category 3 for ease of description.

[0076] The last 20 groups of PPG signals among the 50 groups of users' PPG signals can be collected in the following manner. The following describes the collection process of the last 20 groups of PPG signals by taking the 31st group of PPG signals as an example.

[0077] For the 31st group of PPG signals, the processor 101 may first obtain PPG signals corresponding to three pulse cycles of the user. The processor 101 may then determine the most likely category of the PPG signals corresponding to these three pulse cycles based on a k-nearest neighbor classification algorithm. For example, the processor 101 may determine, based on the k-nearest neighbor classification algorithm, that the PPG signals corresponding to these three pulse cycles most likely belong to category 2 of the three categories described above. Here, the three pulse cycles correspond to the first duration. The method for determining the most likely category of the PPG signals corresponding to these three pulse cycles based on the k-nearest neighbor classification algorithm is described below.

[0078] After determining the most likely category to which the PPG signals corresponding to the three pulse cycles belong, the processor 101 may determine the similarity between the aforementioned features of the PPG signals corresponding to the three pulse cycles and corresponding features of the central PPG signal of the multiple PPG signal groups belonging to category 2 among the first 30 PPG signal groups. A method for determining the central PPG signal of the multiple PPG signal groups belonging to category 2 will be described below.

[0079] For example, assuming that the PPG signals belonging to category 2 include: Group 2, Group 6, Group 7, Group 11, Group 14, Group 17, and Group 18 PPG signals, and assuming that the center of Group 2, Group 6, Group 7, Group 11, Group 14, Group 17, and Group 18 PPG signals belonging to category 2 is Group 6 PPG signals, the processor 101 can determine the normalized distance between the pulse onset peak, dicrotic wave height, and rising period duration of the PPG signals corresponding to three pulse cycles and the pulse onset peak, dicrotic wave height, and rising period duration of the PPG signals in Group 6. The normalized distance corresponds to the similarity in this application. In other words, the normalized distance can represent the similarity. For example, a smaller normalized distance value indicates a higher similarity, and conversely, a larger normalized distance value indicates a lower similarity. It is worth noting that Group 6 PPG signals here correspond to the center of the multiple groups of PPG signals belonging to the first category of the first historical PPG signal.

[0080] The processor 101 may determine whether to continue acquiring the PPG signal according to the normalized distance. When it is necessary to continue acquiring the PPG signal, the processor 101 may continue acquiring the PPG signal for the second duration.

[0081] For example, the processor 101 may compare the normalized distance between the PPG signals corresponding to the above three pulse cycles and the sixth group of PPG signals with a preset fifth threshold value. When the above normalized distance is less than or equal to the preset fifth threshold value, the processor 101 may determine that there is no need to continue acquiring PPG signals. In this case, the PPG signals corresponding to the above three pulse cycles are the 31st group of PPG signals. Alternatively, when the above normalized distance is greater than the preset fifth threshold value, the processor 101 may determine that it is necessary to continue acquiring PPG signals, and then continue to acquire PPG signals of the second duration. In this case, the PPG signals of the second duration that are continued to be acquired and the PPG signals corresponding to the above three pulse cycles together constitute the 31st group of PPG signals. For example, if the preset fifth threshold is 0.3 and the normalized distance between the PPG signals corresponding to the above three pulses and the sixth group of PPG signals is 0.2, the processor 101 may determine that there is no need to continue acquiring the PPG signals. Alternatively, if the normalized distance between the PPG signals corresponding to the above three pulses and the sixth group of PPG signals is 0.5, the processor 101 may determine that it is necessary to continue acquiring the PPG signals, and thus continue to acquire the PPG signals for the second duration.

[0082] In addition, when it is necessary to continue to acquire the PPG signal, the processor 101 can also determine the second duration corresponding to the continued acquisition of the PPG signal based on the normalized distance. In other words, in this case, the value of the second duration is related to the similarity.

[0083] For example, the processor 101 may determine the second duration based on a correspondence between intervals corresponding to a plurality of normalized distances and a plurality of durations. For example, the correspondence between intervals corresponding to the normalized distances and the durations may be as shown in Table 1:

[0084] Table 1

[0085]

[0086] For example, if the normalized distance between the PPG signals corresponding to the above three pulse cycles and the sixth group of PPG signals falls within the interval corresponding to 0 to 0.3, the processor 101 may determine that there is no need to acquire the collected PPG signals. Alternatively, if the normalized distance between the PPG signals corresponding to the above three pulse cycles and the sixth group of PPG signals falls within the interval corresponding to 0.7 to 0.9, the processor 101 may determine that it is necessary to continue acquiring the PPG signals, and may determine to continue acquiring the PPG signals for 45 seconds. Then, the processor 101 continues to acquire the PPG signals for 45 seconds. At this time, the PPG signals continued to be acquired for 45 seconds and the PPG signals corresponding to the above three pulse cycles together constitute the 31st group of PPG signals.

[0087] It should be noted that the above scheme is only an exemplary description and does not constitute a limitation on the present application. The present application does not limit the number of PPG signal groups collected by a fixed-duration collection method and the number of PPG signal groups collected by a flexible determination of the collection duration.

[0088] The following describes a method for determining the most likely category of the PPG signals corresponding to the three pulse cycles based on the k-nearest neighbor classification algorithm.

[0089] When determining the most likely category of the PPG signals corresponding to the three pulse cycles, the normalized distances between the pulse onset peak, dicrotic wave height, and rising period duration of the PPG signals corresponding to the three pulse cycles and the pulse onset peak, dicrotic wave height, and rising period duration of the first 30 groups of PPG signals can be determined respectively. A total of 30 normalized distances are obtained. For ease of description, these 30 normalized distances are recorded as normalized distance 1 to normalized distance 30.

[0090] The 30 normalized distances are sorted in ascending order, and according to the size of the 30 normalized distances, several groups of PPG signals corresponding to the first several normalized distances are selected from the 30 groups of PPG signals. For example, 10 groups of PPG signals corresponding to the first 10 normalized distances are selected from the 30 groups of PPG signals.

[0091] Among the 10 selected PPG signals, it is assumed that 3 PPG signals belong to category 1, 5 PPG signals belong to category 2, and 2 PPG signals belong to category 3. Since the number of groups belonging to category 2 is the largest among the 10 PPG signals, it can be determined that the PPG signals corresponding to the three pulse cycles most likely belong to category 2.

[0092] It is worth mentioning that after determining the category to which the 31st group of PPG signals belongs, the 31st group of PPG signals can be added to the category to which it belongs before collecting the 32nd group of PPG signals. For example, if it is determined that the 31st group of PPG signals belongs to category 2, the 31st group of PPG signals can be added to category 2. In other words, before adding the 31st group of PPG signals to category 2, the PPG signals belonging to category 2 include: group 2, group 6, group 7, group 11, group 14, group 17, group 18, and group 18 PPG signals. After adding the 31st group of PPG signals to category 2, the PPG signals belonging to category 2 include: group 2, group 6, group 7, group 11, group 14, group 17, group 18, and group 31 PPG signals.

[0093] After adding the 31st PPG signal group to category 2, before acquiring the 32nd PPG signal group, the center of the multiple PPG signals belonging to category 2 can be re-determined. Similarly, when acquiring the 32nd to 50th PPG signals, after determining the category of each PPG signal group, before acquiring the next PPG signal group, the PPG signal group can be added to the corresponding category and the center of the multiple PPG signals belonging to that category can be re-determined. The following describes a method for determining the center PPG signal of multiple PPG signals belonging to category 2.

[0094] When determining the center PPG signal of the multiple groups of PPG signals belonging to category 2, the 2nd, 6th, 7th, 11th, 14th, 17th and 18th groups of PPG signals belonging to category 2 can be traversed. For example, for the 2nd group of PPG signals, the normalized distances between the pulse onset peak, dicrotic wave height and rising period duration of the 6th, 7th, 11th, 14th, 17th and 18th groups of PPG signals and the pulse onset peak, dicrotic wave height and rising period duration of the 2nd group of PPG signals are calculated respectively to obtain 6 normalized distances, and the sum of these 6 normalized distances is determined. For the 6th group of PPG signals, a sum is also obtained, and so on, and finally 7 sums are obtained. The PPG signal corresponding to the maximum value of the 7 sums is determined as the center of the multiple groups of PPG signals belonging to category 2.

[0095] For example, the sum corresponding to the sixth group of PPG signals is the maximum value among the seven sums, and the sixth group of PPG signals is the center of the multiple groups of PPG signals belonging to category 2.

[0096] In this application, a set of PPG signals can correspond to multiple pulses of a user, with one pulse cycle of the user corresponding to a PPG signal segment within the set. In other words, a set of PPG signals can include multiple PPG signal segments, and the characteristics of each set of PPG signals can be the average or median of multiple characteristics corresponding to the multiple PPG signal segments. For example, assuming a set of PPG signals includes three PPG signal segments, each PPG signal segment includes three characteristics: the pulse onset peak, the dicrotic wave height, and the duration of the rising phase. In this case, the characteristics of this set of PPG signals can include the average of the three pulse onset peaks, the average of the three dicrotic wave heights, and the average of the three dicrotic wave heights. Accordingly, the characteristics of the PPG signals corresponding to the three pulses are the average or median of the three characteristics corresponding to the three PPG signal segments. It is worth noting that the duration of the rising phase in this application can be understood as the length of time required for the waveform of each PPG signal segment to rise from the minimum value to the maximum value.

[0097] It should be noted that, regarding the method of determining the characteristics of a group of PPG signals based on multiple characteristics of multiple PPG signals, the above-mentioned methods of taking the average value or the median value are only for illustrative purposes and do not constitute a limitation of the present application.

[0098] In the present application, whether the generated target model 2 is usable can be determined in the following manner. In other words, it is determined whether the generated target model 2 is sufficient to meet the measurement accuracy of the blood pressure value. If it is satisfied, it means that the target model 2 is successfully generated. In this case, the processor 101 can prompt the user to stop triggering the instruction to measure blood pressure through the first measurement component 102.

[0099] Method 1

[0100] The processor 101 may determine whether the target model 2 is available according to the value of N. For example, when the value of N is greater than or equal to 50, the processor 101 may determine that the target model 2 is available.

[0101] Method 2

[0102] The processor 101 may determine that the target model 2 is available based on the number of PPG signal groups belonging to category 1, category 2, and category 3.

[0103] For example, the processor 101 may determine whether the target model 2 is available based on a comparison result of the number of groups N belonging to category 1, category 2, and category 3 with a preset sixth threshold.

[0104] The preset sixth threshold value is 10. Therefore, when the number of groups belonging to category 1, category 2, and category 3 is greater than or equal to 10, the processor 101 can determine that the target model 2 is available.

[0105] Method 3

[0106] After generating target model 2 using N groups of blood pressure values ​​and N groups of PPG signals, the processor 101 may prompt the user to trigger an instruction to measure blood pressure through the first measurement component 102. After obtaining the blood pressure value collected by the first measurement component 102, the processor may compare the blood pressure value collected by the first measurement component 102 with the blood pressure value obtained through target model 2. If the absolute value of the difference between the blood pressure value collected by the first measurement component 102 and the blood pressure value obtained through target model 2 is less than or equal to the preset seventh threshold, the processor 101 may determine that target model 2 is available.

[0107] For example, the preset seventh threshold value is 10. When the absolute value of the difference between the blood pressure value collected by the first measurement component 102 and the blood pressure value obtained by the target model 2 is less than or equal to 10, the processor 101 can determine that the target model 2 is available.

[0108] Optionally, after obtaining target model 2 based on N groups of blood pressure values ​​and N groups of PPG signals, the processor 101 is also used to: determine whether target model 2 needs to be updated during the process of measuring the user's blood pressure based on target model 2, and if it is determined that target model 2 needs to be updated, prompt the user to trigger an instruction to measure blood pressure.

[0109] For example, after collecting the first PPG signal, the processor 101 can determine the category to which the first PPG signal belongs. For the sake of description, the category to which the first PPG signal belongs is recorded as the second category. The processor 101 further determines the similarity between the first PPG signal and the centers of multiple groups of PPG signals belonging to the second category in the second historical PPG signal, and determines to update the target model 2 based on the similarity and the number of groups of PPG signals belonging to the second category in the second historical PPG signal.

[0110] After acquiring the first PPG signal, the processor 101 determines, based on the first PPG signal and the aforementioned 50 groups of PPG signals, that the first PPG signal belongs to the second category, where the second category is one of categories 1 to 3. The processor 101 further determines the normalized distance between the first PPG signal and the centers of the 50 groups of PPG signals belonging to the second category. Finally, the processor 101 determines whether to update the target model 2 based on the normalized distance between the first PPG signal and the center PPG signal and the number of PPG signals belonging to the second category among the 50 groups of PPG signals. The method for determining the most likely category of the first PPG signal and determining the normalized distance between the first PPG signal and the center PPG signal by the processor 101 is described above and will not be further elaborated here for the sake of brevity. The 50 groups of PPG signals herein correspond to the second historical PPG signal.

[0111] For example, when the normalized distance between the first PPG signal and the central PPG signal is less than or equal to a preset fifth threshold, and the number of groups of PPG signals belonging to the second category is less than or equal to a preset sixth threshold, the processor 101 may determine that the target model 2 needs to be updated.

[0112] For example, the preset fifth threshold is 0.3, the preset sixth threshold is 10, the normalized distance between the first PPG signal and the center PPG signal is 0.2, and the number of groups of PPG signals belonging to the second category is 8, then the processor 101 can determine that the target model 2 needs to be updated.

[0113] When it is determined that the target model 2 needs to be updated, the processor 101 can prompt the user to trigger the instruction to measure blood pressure through the first measurement component 102 through voice prompts, vibration prompts, and pop-up windows, or the processor 101 can also prompt the user to trigger the instruction to measure blood pressure by controlling the display screen to flash.

[0114] After receiving the prompt, the user can trigger the instruction to measure blood pressure through the first measurement component 102. For example, the user can click the blood pressure measurement button on the watch to send the instruction to measure blood pressure through the first measurement component 102 to the processor 101, or the user can issue a voice message "start measuring blood pressure". After receiving the instruction triggered by the user to measure blood pressure through the first measurement component 102, the processor 101 can collect the user's second blood pressure value through the first measurement component 102, and collect the second PPG signal corresponding to the second blood pressure value through the second measurement component 103.

[0115] After acquiring multiple second blood pressure values ​​and multiple sets of second PPG signals, the processor 101 may update the target model 2 based on the multiple second blood pressure values ​​and multiple sets of second PPG signals. For details on how the processor 101 acquires the second blood pressure values ​​and second PPG signals, please refer to the aforementioned description, which will not be repeated here for the sake of brevity.

[0116] After the processor 101 prompts the user to trigger the instruction to measure blood pressure through the first measurement component 102, the user can set the watch so that the processor 101 can collect the user's second blood pressure value through the first measurement component 102 at a regular interval, or the user can also set the watch so that the processor 101 can continuously collect the user's second blood pressure value through the first measurement component 102.

[0117] For example, if after the target model 2 is updated, the processor 101 still receives an instruction to measure blood pressure through the first measurement component 102. In this case, the processor 101 can compare the blood pressure value of the user collected by the first measurement component 102 after receiving the instruction to measure blood pressure through the first measurement component 102 with the blood pressure value of the user obtained through the updated target model 2. If the blood pressure value of the user collected by the first measurement component 102 is close to the blood pressure value of the user obtained through the updated target model 2, the processor 101 can prompt the user to stop triggering the instruction to measure blood pressure. For example, the processor 101 can prompt the user to stop triggering the instruction to measure blood pressure through voice prompts, vibration prompts, or pop-up windows.

[0118] It should be noted that the processor 101 can also determine whether to update the target model 2 based on the time when the target model 2 has not been updated. For example, when the processor 101 detects that the target model 2 has not been updated for more than a preset time, the processor 101 can determine that the target model 2 needs to be updated.

[0119] For example, the preset time period may be 1 day. When the processor 101 detects that the target model 2 has not been updated for more than one day, the processor 101 may determine that the target model 2 needs to be updated.

[0120] In the present application, in order to improve the accuracy of the user's PPG signal collected by the second measurement component 103, the processor 101 can prompt the user to keep the wrist position still during the period when the second measurement component 103 collects the PPG signal. For example, the processor 101 can prompt the user to keep the wrist position still through voice prompts, vibration prompts, or pop-up windows.

[0121] Based on the blood pressure measuring device provided by the present application, since the target model 2 is obtained after model training based on the user's N sets of blood pressure values ​​(these N sets of blood pressure values ​​are obtained through the first measurement component 102, and the accuracy of the blood pressure values ​​obtained through the first measurement component 102 is relatively high) and N sets of PPG signals corresponding one-to-one to the N sets of blood pressure values, when the user's blood pressure value is subsequently determined based on the user's PPG signal through the target model 2, the blood pressure value measurement result obtained will be more accurate.

[0122] In addition, by integrating the second measurement component for collecting PPG signals with the first measurement component, it is possible to more conveniently obtain N groups of blood pressure values ​​for generating the target model 2 and N groups of PPG signals corresponding one-to-one to the N groups of blood pressure values.

[0123] The present application also provides a method for measuring blood pressure, which is applied to the above-mentioned device for measuring blood pressure. Figure 7 : shows an exemplary flow chart of the method 700. The method 700 is described below by taking the case where the target model 1 is pre-configured in the processor 101 as an example.

[0124] In step 701 , the processor 101 detects whether the user triggers an instruction to measure blood pressure via the first measurement component 102 .

[0125] If the processor 101 detects a user-triggered instruction to measure blood pressure via the first measurement component 102, the processor 101 executes step 702. If the processor 101 has not detected a user-triggered instruction to measure blood pressure via the first measurement component 102, the processor 101 executes step 709. It is worth mentioning that if the processor 101 detects a user-triggered instruction to measure blood pressure via the first measurement component 102, the instruction to measure blood pressure may be triggered by the user in the following two situations:

[0126] Case 1: During the process of updating the target model 1 , the user triggers an instruction to measure blood pressure through the first measurement component 102 .

[0127] Case 2: After obtaining the target model 2, when the target model 2 needs to be updated, the user triggers an instruction to measure blood pressure through the first measurement component 102.

[0128] In step 702 , the processor 101 collects a set of blood pressure values ​​of the user and obtains a PPG signal of a first duration.

[0129] When the processor 101 detects an instruction triggered by the user to measure blood pressure through the first measurement component 102, the processor 101 collects a set of blood pressure values ​​of the user through the first measurement component 102. When obtaining a set of PPG signals corresponding to the blood pressure values, the processor 101 can first obtain the PPG signal of the first duration.

[0130] In step 703 , the processor 101 determines the category to which the PPG signal of the first duration belongs, and determines the similarity between the PPG signal of the first duration and the centers of multiple groups of PPG signals in the historical PPG signals that belong to the category corresponding to the PPG signal of the first duration.

[0131] After acquiring the PPG signal of the first duration, the processor 101 may determine the category to which the PPG signal of the first duration belongs, and determine the similarity between the PPG signal of the first duration and the centers of multiple groups of PPG signals belonging to the category corresponding to the PPG signal of the first duration in historical PPG signals. The historical PPG signals herein may be understood as all PPG signals corresponding to the user's blood pressure values ​​acquired by the first measurement component 102 and acquired by the processor 101 before acquiring the PPG signal of the first duration. For the specific methods by which the processor 101 determines the category to which the PPG signal of the first duration belongs and determines the similarity between the PPG signal of the first duration and the centers of multiple groups of PPG signals belonging to the category in historical PPG signals, please refer to the aforementioned related description, which will not be repeated here for the sake of brevity.

[0132] In step 704 , the processor 101 determines whether the similarity between the PPG signal of the first duration and the centers of multiple groups of PPG signals belonging to the category corresponding to the PPG signal of the first duration in the historical PPG signals is greater than a preset fifth threshold.

[0133] If the similarity between the centers of the PPG signal of the first duration and the multiple groups of PPG signals belonging to the category corresponding to the PPG signal of the first duration in the historical PPG signals is greater than a preset fifth threshold, the processor 101 executes step 705; or if the similarity between the centers of the PPG signal of the first duration and the multiple groups of PPG signals belonging to the category corresponding to the PPG signal of the first duration in the historical PPG signals is less than or equal to the preset fifth threshold, the processor 101 executes step 707. In this case, the PPG signal of the first duration acquired in step 702 is a group of PPG signals corresponding to the blood pressure value in step 702.

[0134] Step 705: Processor 101 determines a second duration.

[0135] If the processor 101 determines that the similarity between the PPG signal of the first duration and the center of the PPG signal belonging to the category in the historical PPG signals is greater than a preset fifth threshold, the processor 101 may determine that it is necessary to continue acquiring the PPG signal and may determine that it is necessary to continue acquiring the PPG signal for a second duration. For the specific method of determining whether it is necessary to continue acquiring the PPG signal and determining the second duration when it is necessary to continue acquiring the PPG signal, please refer to the above description, which will not be repeated here for the sake of brevity.

[0136] Step 706: The processor 101 obtains a PPG signal of a second duration.

[0137] After determining that the PPG signal needs to be continuously acquired for the second duration, the processor 101 may continue to acquire the PPG signal for the second duration. In this case, the PPG signal acquired for the second duration and the PPG signal acquired for the first duration in step 702 constitute a set of PPG signals corresponding to the blood pressure value in step 702. For the specific method by which the processor 101 acquires the PPG signal for the first duration and the PPG signal for the second duration, please refer to the aforementioned related description, which will not be repeated here for the sake of brevity.

[0138] In step 707 , the processor 101 determines whether to update the current model.

[0139] After obtaining the user's blood pressure value and a set of PPG signals corresponding to the blood pressure value, the processor 101 can determine whether to update the current model. For example, the processor 101 can determine whether to update the current model based on the accumulated blood pressure values ​​and PPG signals corresponding to the blood pressure values. For example, if the processor 101 has accumulated a certain number of blood pressure values ​​and PPG signals, the processor 101 can execute step 708; otherwise, execute step 701.

[0140] The so-called current model, before executing step 707, if the processor 101 has not updated the pre-configured target model 1, then the current model here is target model 1, or, before executing step 707, if the processor 101 has updated the target model 1, then the current model here is target model 2, or, before executing step 707, if the processor 101 has updated the target model 2, then the current model here is the updated target model 2.

[0141] In step 708 , the processor 101 updates the current model according to the collected blood pressure value and PPG signal.

[0142] The processor 101 can update the current model based on the collected multiple blood pressure values ​​and multiple sets of PPG signals. For the specific method of updating the current model, please refer to the above related description, which will not be repeated here for the sake of brevity.

[0143] In step 709 , the processor 101 collects a first PPG signal through the second measurement component 103 .

[0144] In step 710 , the processor 101 inputs the first PPG signal into the current model to obtain a first blood pressure value.

[0145] In step 711 , the processor 101 determines the category to which the first PPG signal belongs, and determines the similarity between the first PPG signal and the centers of multiple groups of PPG signals belonging to the category in the historical PPG signals, as well as the number of groups of PPG signals belonging to the category in the historical PPG signals.

[0146] After acquiring the first PPG signal, the processor 101 may determine the category to which the first PPG signal belongs, and determine the similarity between the first PPG signal and the centers of PPG signals belonging to the category in historical PPG signals. The historical PPG signals herein may be understood as all PPG signals corresponding to the user's blood pressure values ​​acquired by the first measurement component 102 and acquired by the processor 101 before acquiring the first PPG signal. The specific methods for the processor 101 to determine the category to which the first PPG signal belongs and to determine the similarity between the first PPG signal and the centers of PPG signals belonging to the category in historical PPG signals are described above and are not repeated here for the sake of brevity.

[0147] In step 712, the processor 101 determines whether a similarity between the first PPG signal and the centers of multiple groups of PPG signals in the historical PPG signals that belong to the category corresponding to the first PPG signal is less than or equal to a preset fifth threshold, and whether the number of groups of PPG signals in the historical PPG signals that belong to the category is less than or equal to a preset sixth threshold.

[0148] If the similarity between the first PPG signal and the centers of multiple groups of PPG signals belonging to the category corresponding to the first PPG signal in the historical PPG signals is less than or equal to a preset fifth threshold, and the number of groups of PPG signals belonging to the category in the historical PPG signals is less than or equal to a preset sixth threshold, the processor 101 executes step 713; otherwise, the processor 101 executes step 701. The historical PPG signals here can be understood as: all PPG signals that the processor 101 has acquired before acquiring the first PPG signal.

[0149] In step 713 , the processor 101 prompts the user to trigger an instruction to measure blood pressure.

[0150] If the similarity between the first PPG signal and the centers of multiple groups of PPG signals belonging to the category corresponding to the first PPG signal in the historical PPG signals is less than or equal to a preset fifth threshold, and the number of groups of PPG signals belonging to the category in the historical PPG signals is less than or equal to a preset sixth threshold, it indicates that the current model needs to be updated. In this case, the processor 101 may prompt the user to trigger an instruction to measure blood pressure. After prompting the user to trigger the instruction to measure blood pressure, the processor 101 proceeds to step 701. For the specific method of the processor 101 prompting the user to trigger an instruction to measure blood pressure, please refer to the above related description, which is not repeated here for the sake of brevity.

[0151] Based on the blood pressure measuring method provided in the present application, since target model 2 is obtained by updating target model 1 based on the user's own N groups of blood pressure values ​​(these N groups of blood pressure values ​​are obtained through the first measurement component 102, and the accuracy of the blood pressure values ​​obtained through the first measurement component 102 is relatively high) and N groups of PPG signals corresponding one-to-one to the N groups of blood pressure values, when the target model 1 is subsequently used to determine the user's blood pressure value based on the user's PPG signal, the blood pressure value measurement result obtained will be more accurate compared to target model 1.

[0152] In addition, by integrating the second measurement component for collecting PPG signals with the first measurement component, it is possible to more conveniently obtain N groups of blood pressure values ​​for updating the target model 1 and N groups of PPG signals corresponding one-to-one to the N groups of blood pressure values.

[0153] It is worth mentioning that, in the present application, the operation performed by the user when triggering the instruction to measure blood pressure through the first measurement component 102 corresponds to the first operation.

[0154] The present application also provides a computer storage medium comprising computer instructions. When the computer instructions are executed on a device for measuring blood pressure, the device for measuring blood pressure executes the method for measuring blood pressure provided in the present application.

[0155] The present application also provides a computer program product, which, when executed on a computer, enables the computer to execute the method for measuring blood pressure provided in the present application.

[0156] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid state drive (SSD).

[0157] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of this application.

[0158] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0159] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0160] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0161] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0162] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0163] The above description is merely a specific implementation of the embodiments of the present application, but the scope of protection of the embodiments of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the embodiments of the present application should be included in the scope of protection of the embodiments of the present application. Therefore, the scope of protection of the embodiments of the present application should be based on the scope of protection of the claims.

Claims

1. A device for measuring blood pressure, characterized in that: The blood pressure measuring device comprises a processor (101), a first measuring component (102), and a second measuring component (103); the first measuring component (102) comprises an inflatable component (1022), an airbag (1023), and an air pressure sensor (1024); the airbag (1023) is connected to the inflatable component (1022) and the air pressure sensor (1024), respectively; the second measuring component (103) comprises a light source (1031) and a PPG sensor (1032); The first measuring component (102) is used to collect the user's blood pressure value; The second measurement component (103) is used to collect the PPG signal of the user; The processor (101) is configured to control the first measurement component (102) to collect N sets of blood pressure values ​​of the user; control the second measurement component (103) to collect N sets of PPG signals corresponding to the N sets of blood pressure values; and generate a target model based on the N sets of blood pressure values ​​and the N sets of PPG signals, wherein the input of the target model is the PPG signal and the output is the blood pressure value, and N is an integer greater than or equal to 2; The processor (101) is further configured to control the second measurement component (103) to collect a first PPG signal of the user after the target model is generated; and determine a first blood pressure value based on the target model and the first PPG signal; The processor (101) is further configured to, when collecting the i-th group of PPG signals among the N groups of PPG signals, Controlling the second measurement component (103) to obtain a PPG signal of a first duration; determining a second duration based on the PPG signal of the first duration; Controlling the second measurement component (103) to collect the PPG signal of the second duration; Combining the PPG signal of the first duration and the PPG signal of the second duration into an i-th group of PPG signals; The determining a second duration according to the PPG signal of the first duration includes: extracting features of the PPG signal of the first duration, and determining the category to which the PPG signal of the first duration belongs according to the extracted features; determining a similarity between features of the PPG signal of the first duration and features of a central PPG signal in a first historical PPG signal belonging to a category of the PPG signals of the first duration, wherein the first historical PPG signal includes a PPG signal that has been acquired before acquiring the i-th group of PPG signals; The second duration is determined according to the correspondence between the similarity and the second duration.

2. The device for measuring blood pressure according to claim 1, wherein: The processor (101) is further configured to, when collecting the first to Mth groups of PPG signals among the N groups of PPG signals, control the second measurement component (103) to obtain PPG signals of a third duration, where M is an integer less than i.

3. The device for measuring blood pressure according to claim 1, characterized in that: The processor (101) is further configured to, when determining to update the target model, prompt the user to trigger an instruction to measure blood pressure through the first measurement component (102) and the second measurement component (103); In response to a first operation by the user, controlling the first measurement component (102) to collect a second blood pressure value, and controlling the second measurement component (103) to collect a second PPG signal corresponding to the second blood pressure value; The target model is updated according to the second blood pressure value and the second PPG signal.

4. The device for measuring blood pressure according to any one of claims 1 to 3, characterized in that: The processor (101) is further configured to determine the category of the first PPG signal, comprising: extracting features of the first PPG signal, and determining the category to which the first PPG signal belongs based on the extracted features; The processor (101) is further configured to determine a similarity between features of the first PPG signal and features of a central PPG signal of PPG signals belonging to the category of the first PPG signal in N groups of PPG signals, and determine whether it is necessary to update the target model based on the similarity and the number of groups of PPG signals belonging to the category of the first PPG signal in the N groups of PPG signals.

5. The device for measuring blood pressure according to any one of claims 1 to 3, characterized in that: The processor (101) is further configured to determine whether the target model needs to be updated based on a duration during which the target model has not been updated.

6. The device for measuring blood pressure according to any one of claims 1 to 3, characterized in that: The inflatable component (1022) is used to inflate the airbag (1023); The air pressure sensor (1024) is used to collect multiple air pressure values ​​of the airbag (1023), wherein the first air pressure value and the second air pressure value of the multiple air pressure values ​​are the blood pressure values ​​of the user, the first air pressure value is the air pressure value corresponding to the moment when the oscillation wave of the air pressure in the airbag (1023) reaches the maximum value, and the second air pressure value is the air pressure value corresponding to the moment when the oscillation wave reaches the maximum value multiplied by a, where a is greater than 0 and less than 1.

7. The device for measuring blood pressure according to any one of claims 1 to 3, characterized in that: The difference between the moment of starting to inflate the airbag (1023) and the moment of collecting the i-th group of PPG signals among the N groups of PPG signals is greater than or equal to a preset first threshold value, and less than or equal to a preset second threshold value, and the moment of starting to inflate the airbag (1023) is after the moment of collecting the i-th group of PPG signals, or the difference between the moment of collecting the i-th group of PPG signals among the N groups of PPG signals and the moment of stopping to inflate the airbag (1023) is greater than or equal to a preset third threshold value, and less than or equal to a preset fourth threshold value, and the moment of stopping to inflate the airbag (1023) is before the moment of collecting the i-th group of PPG signals.

8. A method for measuring blood pressure, characterized in that: The method is applied to a device for measuring blood pressure, the device comprising a first measuring component (102) and a second measuring component (103), the first measuring component (102) comprising an inflatable component (1022), an airbag (1023), and an air pressure sensor (1024), the airbag (1023) being connected to the inflatable component (1022) and the air pressure sensor (1024), respectively, the second measuring component (103) comprising a light source (1031) and a PPG sensor (1032), and the method comprising: Controlling the first measurement component (102) to collect N sets of blood pressure values ​​of the user; controlling the second measurement component (103) to collect N groups of PPG signals corresponding to the N groups of blood pressure values; generating a target model according to the N groups of blood pressure values ​​and the N groups of PPG signals, wherein the input of the target model is the PPG signal, the output is the blood pressure value, and N is an integer greater than or equal to 2; After the target model is generated, controlling the second measurement component to collect the first PPG signal of the user; determining a first blood pressure value based on the target model and the first PPG signal; The processor (101) is further configured to, when collecting the i-th group of PPG signals among the N groups of PPG signals, Controlling the second measurement component (103) to obtain a PPG signal of a first duration; determining a second duration based on the PPG signal of the first duration; Controlling the second measurement component (103) to collect the PPG signal of the second duration; Combining the PPG signal of the first duration and the PPG signal of the second duration into an i-th group of PPG signals; The determining a second duration according to the PPG signal of the first duration includes: extracting features of the PPG signal of the first duration, and determining the category to which the PPG signal of the first duration belongs according to the extracted features; determining a similarity between features of the PPG signal of the first duration and features of a central PPG signal in a first historical PPG signal belonging to a category of the PPG signals of the first duration, wherein the first historical PPG signal includes a PPG signal that has been acquired before acquiring the i-th group of PPG signals; The second duration is determined according to the correspondence between the similarity and the second duration.

9. The method for measuring blood pressure according to claim 8, wherein: When collecting the first to Mth groups of PPG signals among the N groups of PPG signals, controlling the second measurement component (103) to collect the N groups of PPG signals corresponding to the N groups of blood pressure values ​​comprises: The second measurement component (103) is controlled to obtain a PPG signal of a third duration, where M is an integer less than i.

10. The method for measuring blood pressure according to claim 8, characterized in that: The method further comprises: In the case of determining to update the target model, prompting the user to trigger an instruction to measure blood pressure through the first measurement component (102) and the second measurement component (103); In response to a first operation by the user, controlling the first measurement component (102) to collect a second blood pressure value, and controlling the second measurement component (103) to collect a second PPG signal corresponding to the second blood pressure value; The target model is updated according to the second blood pressure value and the second PPG signal.

11. The method for measuring blood pressure according to any one of claims 8 to 10, characterized in that: The method further comprises: Determining the category of the first PPG signal includes: extracting features of the first PPG signal, and determining the category to which the first PPG signal belongs based on the extracted features; Determine a similarity between features of the first PPG signal and a central PPG signal of N groups of PPG signals that belong to the category of the first PPG signal, and determine whether it is necessary to update the target model based on the similarity and the number of groups of PPG signals that belong to the category of the first PPG signal in the N groups of PPG signals.

12. The method for measuring blood pressure according to any one of claims 8 to 10, characterized in that: The method further comprises: Determine whether the target model needs to be updated based on a period of time during which the target model has not been updated.

13. The method for measuring blood pressure according to any one of claims 8 to 10, characterized in that: The controlling the first measurement component (102) to collect N sets of blood pressure values ​​of the user comprises: controlling the inflatable component (1022) to inflate the airbag (1023); The air pressure sensor (1024) is controlled to collect multiple air pressure values ​​of the airbag (1023), wherein a first air pressure value and a second air pressure value of the multiple air pressure values ​​are a set of blood pressure values ​​of the user, wherein the first air pressure value corresponds to the moment when the oscillation wave of the air pressure in the airbag (1023) reaches a maximum value, and the second air pressure value corresponds to the air pressure value corresponding to the moment when the oscillation wave reaches the maximum value multiplied by a, where a is greater than 0 and less than 1.

14. The method for measuring blood pressure according to any one of claims 8 to 10, characterized in that: The difference between the moment of starting to inflate the airbag (1023) and the moment of collecting the i-th group of PPG signals among the N groups of PPG signals is greater than or equal to a preset first threshold value, and less than or equal to a preset second threshold value, and the moment of starting to inflate the airbag (1023) is after the moment of collecting the i-th group of PPG signals, or the difference between the moment of collecting the i-th group of PPG signals among the N groups of PPG signals and the moment of stopping to inflate the airbag (1023) is greater than or equal to a preset third threshold value, and less than or equal to a preset fourth threshold value, and the moment of stopping to inflate the airbag (1023) is before the moment of collecting the i-th group of PPG signals.

15. A computer storage medium, characterized in that The method comprises computer instructions, which, when executed on a device for measuring blood pressure, enable the device for measuring blood pressure to perform the method for measuring blood pressure according to any one of claims 8 to 14.

16. A computer program product, characterized in that When the computer program product is run on a computer, the computer is caused to execute the method for measuring blood pressure according to any one of claims 8 to 14 .

Images