Blood pressure detection method and device

Abstract

The embodiment of the invention discloses a blood pressure detection method and device which are applied to electronic equipment. The method comprises the following steps: acquiring a first photoplethysmography (PPG) signal of a user, and determining a first electrocardio (ECG) signal of the user based on the first PPG signal; performing peak detection on the first PPG signal and the first ECG to determine first pulse transit time of the user; and performing first quality detection on the first ECG signal and the first pulse conduction time, and if it is determined that the result of the first quality detection is normal, determining the blood pressure value of the user based on the first pulse conduction time. By adopting the embodiment of the invention, the accuracy of a blood pressure detection result can be improved, and the blood pressure detection cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of smart terminal technology, and in particular to a method and device for blood pressure detection. Background Art

[0002] Hypertension is a common chronic disease, which refers to long-term and sustained high blood pressure. This disease can easily lead to cardiovascular and cerebrovascular diseases, seriously affecting human health. At present, there are more than 245 million hypertensive patients in China, which is a huge group. For hypertensive patients, regular blood pressure monitoring is very important, which can help them better understand their condition, adjust treatment plans in time, and avoid the occurrence of cardiovascular and cerebrovascular diseases.

[0003] In addition to the poor signal quality of traditional blood pressure testing, professional medical staff may be required to operate and interpret the test during the test, which is not only inconvenient but also costly. Therefore, how to improve the accuracy of blood pressure test results and reduce the cost of blood pressure testing is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The technical problem to be solved by the embodiments of the present application is to provide a method and device for blood pressure detection, which can improve the accuracy of blood pressure detection results and reduce the cost of blood pressure detection.

[0005] In a first aspect, an embodiment of the present application provides a method for blood pressure detection, which is applied to an electronic device; the method may include: acquiring a first photoplethysmogram (PPG) signal of a user, and determining a first electrocardiogram (ECG) signal of the user based on the first PPG signal; performing peak detection on the first PPG signal and the first ECG to determine a first pulse conduction time of the user; performing a first quality detection on the first ECG signal and the first pulse conduction time, and if the result of the first quality detection is determined to be normal, determining the blood pressure value of the user based on the first pulse conduction time.

[0006] At present, most wearable devices on the market need to record the subject's ECG signal and photoelectric volume pulse wave (PPG) signal at the same time when performing blood pressure detection in order to obtain more accurate blood pressure detection results. However, there are few devices that support the acquisition of both ECG and PPG signals, and the resulting price costs are generally high. In response to this technical problem, the embodiment of the present application can determine the user's blood pressure value based on the PPG signal without collecting the user's ECG signal, and perform quality detection on various types of user data during the blood pressure detection process, thereby reducing the cost of blood pressure detection while ensuring the accuracy of the detection results. Specifically, in an embodiment of the present application, the user's PPG signal is first obtained (for example, data collection can be based on a wearable device such as a smart watch or a smart bracelet), and the user's ECG signal is determined based on the PPG signal (for example, it can be calculated based on a pre-trained machine algorithm model); further, the above-mentioned ECG signal and PPG signal can be peak detected to determine the user's pulse conduction time (for example, the R wave peak value of the ECG signal and the pulse wave peak value of the PPG signal can be determined based on peak detection, and the time difference between the peak values ​​corresponding to the two signals is calculated); finally, the above-mentioned ECG signal and pulse conduction time can be quality detected (for example, the difference in the number and time difference between the R wave peak value of the ECG and the pulse wave peak value of the PPG signal can be compared with preset thresholds, respectively, to determine the quality detection result of the ECG signal and the pulse conduction time). When the quality detection result shows a normal condition, the user's blood pressure value is calculated based on the pulse conduction time, thereby ensuring the accuracy of the user's blood pressure detection result. In summary, in the embodiments of the present application, the user's blood pressure value can be determined based on the PPG signal, thereby reducing the cost of blood pressure detection (that is, the PPG signal can be converted into an ECG signal, and there is no need to collect the ECG signal, which reduces the rigid requirements for the equipment), and by ensuring that the blood pressure value is calculated when the quality detection indicators are normal, the accuracy of blood pressure detection is ensured, which can greatly reduce the detection quality problems caused by equipment failure, incorrect usage or external interference.

[0007] In a possible implementation, determining the blood pressure value of the user based on the first pulse conduction time includes: inputting the first pulse conduction time into a calibrated first blood pressure regression model, and outputting the blood pressure value of the user. In an embodiment of the present application, the blood pressure value of the user can be output by inputting the first pulse conduction time of the user into a calibrated first blood pressure regression model. Specifically, the pulse conduction time of the user can be used as an input parameter and input into a calibrated blood pressure regression model. For example, the pulse conduction velocity can be calculated based on the pulse conduction time and the distance between different blood vessels, and the blood pressure value can be further calculated based on the data. In summary, the embodiment of the present application can calculate the blood pressure value by inputting the user's data into the model, which not only improves the accuracy of blood pressure detection, but also provides users with a fast and convenient blood pressure detection method.

[0008] In a possible implementation, the method further includes: if the calibration result of the user is detected, then obtaining the first blood pressure regression model based on the calibration result. In the embodiment of the present application, it is possible to detect whether the user has performed a calibration operation, and then obtain the first blood pressure regression model based on the calibration result. This method optimizes the accuracy of blood pressure measurement. Specifically, after the user completes the calibration, the system obtains the corresponding calibration data, and obtains the blood pressure regression model corresponding to the user based on the calibration data. The method of obtaining the corresponding blood pressure regression model based on individual calibration data in the embodiment of the present application can more accurately reflect the specific blood pressure condition of each user, improve the reliability and effectiveness of blood pressure monitoring, and thus help to better guide users' health management and disease prevention.

[0009] In a possible implementation, the method further includes: if the calibration result of the user is not detected, obtaining the calibration data of the user, wherein the calibration data includes the second PPG signal and the gold standard blood pressure value of the user; determining the second ECG signal of the user based on the second PPG signal, and determining the second pulse conduction time of the user based on the second PPG signal and the second ECG signal; performing a second quality test on the second ECG signal and the second pulse conduction time; if the result of the second quality test is determined to be normal, calibrating the second blood pressure regression model based on the second pulse conduction time and the gold standard blood pressure value to determine the first blood pressure regression model. In an embodiment of the present application, after the calibration data of the user is not detected, the calibration data of the user may be collected, and further processing may be performed based on the calibration data, so as to finally calibrate the blood pressure regression model corresponding to the user. Specifically, when the user turns on the calibration function, or when the calibration result of the current user is not detected, the user's PPG signal (for example, collected by wearable devices such as smart watches and smart bracelets) and the gold standard blood pressure value (for example, collected based on a cuff) can be collected, and the user's pulse conduction time can be further determined based on the PPG signal (for example, the PPG signal can be converted into an ECG signal, and the pulse conduction time can be determined based on the PPG signal and the ECG signal), and the ECG signal and the pulse conduction time can be quality tested to ensure the accuracy of the calibration data; further, the pulse conduction time and the blood pressure gold standard value can be input into the blood pressure regression model to calibrate the blood pressure regression model. In summary, in the embodiment of the present application, the data of an uncalibrated user can be collected, and the pulse conduction time of the user can be calculated based on the data, and finally the corresponding blood pressure regression model can be calibrated based on the pulse conduction time of the user and the blood pressure gold standard value. Different blood pressure regression models are calibrated for different users' data. When blood pressure detection is performed later, the individual's blood pressure changes can be more accurately reflected, and the accuracy of the measurement results can be improved to ensure that the user's blood pressure value is closer to the true value.

[0010] In a possible implementation, it is characterized in that the first PPG signal includes M first R peaks, the first ECG signal includes N second R peaks, and M and R are both integers greater than 0; the peak detection of the first PPG signal and the first ECG to determine the first pulse conduction time of the user includes: determining the first pulse conduction time of the user based on the time difference between the M first R peaks and the N second R peaks. In the embodiment of the present application, the pulse conduction time of the user can be accurately determined by performing peak detection on the first PPG signal and the first ECG signal. Specifically, in the embodiment of the present application, the peak detection can be performed on the PPG signal and the ECG signal to determine multiple R peaks (i.e., high point peaks) of the above two signals, and the time difference is calculated based on the M first R peaks and the N second R peaks (for example, the PPG signal and ECG signal that are adjacent in time sequence can be determined as a group, and the time difference is calculated for each group of signals), and finally the pulse conduction time of the user is determined. In summary, in the embodiments of the present application, the time difference can be calculated based on the peak values ​​of the ECG signal and the PPG signal, so that a more accurate pulse conduction time can be calculated, and more accurate data can be used for blood pressure detection in the subsequent blood pressure detection process, thereby ensuring the accuracy of blood pressure detection.

[0011] In one possible implementation, the first R peak is the R wave peak of the ECG signal; the second R peak is the pulse wave peak of the PPG signal. In an embodiment of the present application, by accurately identifying and distinguishing the R wave peak in the ECG signal and the pulse wave peak in the PPG signal, the system can more accurately calculate the pulse conduction time and obtain more accurate blood pressure detection results. Specifically, accurate identification of the first R peak (R wave peak of the ECG signal) and the second R peak (pulse wave peak of the PPG signal) can enable the system to process and analyze these two different types of physiological signals separately, and more accurately calculate the time difference between the peaks based on these two signals, thereby more accurately determining the pulse conduction time to increase the accuracy of subsequent blood pressure detection.

[0012] In a possible implementation, the determining of the user's first pulse conduction time based on the time difference between the M first R peaks and the N second R peaks includes: determining the R wave peaks and pulse wave peaks that are adjacent in time sequence as a group among the M R wave peaks and the N pulse wave peaks; and determining the first pulse conduction time based on the time difference between each group of R wave peaks and pulse wave peaks. In an embodiment of the present application, a more accurate and reliable blood pressure detection method is provided by determining the user's first pulse conduction time based on the time difference between M R wave peaks and N pulse wave peaks. Specifically, in an embodiment of the present application, by effectively identifying the R wave peaks and pulse wave peaks that are adjacent in time sequence, and determining every two ECG signals and PPG signals that are adjacent in time sequence as a group, the time difference between each group of R wave peaks and pulse wave peaks is accurately calculated, and finally the pulse conduction time is determined based on the time difference, thereby improving the accuracy of blood pressure detection. Furthermore, compared to a single signal source that traditional methods may rely on (for example, measuring blood pressure based only on PPG signals) or a simpler data processing method, the embodiments of the present application are based on comprehensive signal analysis (i.e., determining PPG signals and ECG signals that are adjacent in time sequence as a group) and calculating the time difference, which can provide patients with more accurate test results.

[0013] In a possible implementation, the first quality detection of the first ECG signal and the first pulse conduction time includes: if the difference between M and N is greater than a preset first threshold, and the time difference between the M R wave peaks and the N pulse wave peaks is greater than a preset second threshold, then judging that the result of the first quality detection is normal. In this embodiment, by performing quality detection on the first ECG signal and the first pulse conduction time, the normal condition of the physiological signal can be more accurately judged. Specifically, by setting the preset first threshold and second threshold, when the difference between M and N exceeds the first threshold (for example, it can be to judge whether the number of ECG signals converted from the PPG signal is consistent with the PPG signal), and the time difference between the M R wave peaks and the N pulse wave peaks exceeds the second threshold (for example, to judge whether the pulse conduction time determined based on the ECG signal and the PPG signal exceeds the normal value, abnormal conditions occur, etc.), when the detection results are all "yes", the system can judge that the result of this quality detection is normal, so as to perform subsequent blood pressure detection. In summary, in the embodiments of the present application, quality detection can be performed on two situations at the same time (for example, quality detection of ECG signals and PPG signals can be performed to determine whether the difference in the number and time difference of peak values ​​exceeds the corresponding thresholds) to ensure the accuracy of blood pressure detection parameters and improve the accuracy of subsequent blood pressure detection.

[0014] In a possible implementation, the first quality detection of the first ECG signal and the first pulse conduction time includes: if the difference between M and N is less than the first threshold, then judging the result of the first quality detection as an abnormal condition, and prompting the user to retest; or, if the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold, then judging the result of the first quality detection as an abnormal condition, and prompting the user to retest. In the embodiment of the present application, when an abnormality occurs in the quality detection by performing the first quality detection on the first ECG signal and the first pulse conduction time, the user is prompted to perform the test. Specifically, in the embodiment of the present application, by setting two thresholds - a first threshold and a second threshold - the system can determine whether there are abnormalities in the ECG and pulse conduction time. If the difference between M and N is less than the first threshold (that is, it is determined that the number of ECG signals converted from the PPG signal exceeds the preset first threshold), or the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold (that is, it is determined that the pulse conduction time has an abnormality that exceeds the preset second threshold), when one of the two situations occurs, the system will determine these results as abnormal conditions and prompt the user to retest, thereby avoiding interference with the accuracy of the final blood pressure detection results due to partial data errors, improving the overall efficiency and accuracy of the test, and thereby enhancing the reliability of the blood pressure detection solution.

[0015] In one possible implementation, determining the first electrocardiogram (ECG) signal based on the first PPG signal includes: inputting the first PPG signal into an electrocardiogram (ECG) signal conversion model, and outputting the first ECG signal. In an embodiment of the present application, the user's PPG signal can be input into a signal quality detection model to obtain an ECG signal converted from the PPG signal, which can significantly improve processing efficiency, especially when processing large-scale data. Furthermore, the ECG signal conversion model can be a pre-trained machine learning algorithm model, and the ECG signal is determined based on the ECG signal conversion model, so that the speed of subsequent blood pressure detection can be improved, the accuracy of blood pressure detection can be increased, and the cost of blood pressure detection can be reduced (that is, the blood pressure detection device can be a wearable device that supports the collection of PPG signals, without the need to simultaneously integrate PPG signals and ECG signals).

[0016] In a possible implementation, the ECG signal conversion model is obtained by inputting Q third PPG signals as sample data in the server and training with a preset third ECG signal as a label, or by training in the server based on historical sample documents. In an embodiment of the present application, the ECG signal conversion model can be trained in the server by inputting a pre-prepared PPG signal as sample data and using a preset ECG signal as a label, or the ECG signal conversion model can be trained based on historical sample documents, which may include a PPG signal of an already determined ECG signal. By analyzing these historical data, the ECG signal conversion model can learn and train from past events to more accurately convert the PPG signal into an ECG signal. In summary, the embodiment of the present application can train the ECG signal conversion model by inputting a PPG signal as sample data or analyzing historical events, so that the model can effectively identify and distinguish high-quality and low-quality conversion results, thereby enhancing the adaptability and accuracy of the ECG signal conversion model when processing actual data, so as to obtain a higher quality ECG signal, and further improve the accuracy of blood pressure detection based on the ECG signal.

[0017] In a second aspect, an embodiment of the present application provides a blood pressure detection device, which may include:

[0018] a first ECG signal determining unit, configured to obtain a first photoplethysmogram (PPG) signal of a user, and determine a first electrocardiogram (ECG) signal of the user based on the first PPG signal;

[0019] a first pulse transit time determining unit, configured to perform peak detection on the first PPG signal and the first ECG signal to determine a first pulse transit time of the user;

[0020] The blood pressure value determination unit is used to perform a first quality detection on the first ECG signal and the first pulse transmission time, and if the result of the first quality detection is determined to be normal, determine the blood pressure value of the user based on the first pulse transmission time.

[0021] At present, most wearable devices on the market need to record the subject's ECG signal and photoelectric volume pulse wave (PPG) signal at the same time when performing blood pressure detection in order to obtain more accurate blood pressure detection results. However, there are few devices that support the acquisition of both ECG and PPG signals, and the resulting price costs are generally high. In response to this technical problem, the embodiment of the present application can determine the user's blood pressure value based on the PPG signal without collecting the user's ECG signal, and perform quality detection on various types of user data during the blood pressure detection process, thereby reducing the cost of blood pressure detection while ensuring the accuracy of the detection results. Specifically, in an embodiment of the present application, the user's PPG signal is first obtained (for example, data collection can be based on a wearable device such as a smart watch or a smart bracelet), and the user's ECG signal is determined based on the PPG signal (for example, it can be calculated based on a pre-trained machine algorithm model); further, the above-mentioned ECG signal and PPG signal can be peak detected to determine the user's pulse conduction time (for example, the R wave peak value of the ECG signal and the pulse wave peak value of the PPG signal can be determined based on peak detection, and the time difference between the peak values ​​corresponding to the two signals is calculated); finally, the above-mentioned ECG signal and pulse conduction time can be quality detected (for example, the difference in the number and time difference between the R wave peak value of the ECG and the pulse wave peak value of the PPG signal can be compared with preset thresholds, respectively, to determine the quality detection result of the ECG signal and the pulse conduction time). When the quality detection result shows a normal condition, the user's blood pressure value is calculated based on the pulse conduction time, thereby ensuring the accuracy of the user's blood pressure detection result. In summary, in the embodiments of the present application, the user's blood pressure value can be determined based on the PPG signal, thereby reducing the cost of blood pressure detection (that is, the PPG signal can be converted into an ECG signal, and there is no need to collect the ECG signal, which reduces the rigid requirements for the equipment), and by ensuring that the blood pressure value is calculated when the quality detection indicators are normal, the accuracy of blood pressure detection is ensured, which can greatly reduce the detection quality problems caused by equipment failure, incorrect usage or external interference.

[0022] In a possible implementation, the blood pressure value determination unit is specifically configured to:

[0023] The first pulse transit time is input into a calibrated first blood pressure regression model, and the blood pressure value of the user is output.

[0024] In a possible implementation manner, the device further includes:

[0025] The first blood pressure regression model acquisition unit acquires the first blood pressure regression model based on the calibration result if the calibration result of the user is detected.

[0026] In a possible implementation manner, the device further includes:

[0027] an acquisition calibration data unit, which acquires calibration data of the user if the calibration result of the user is not detected, wherein the calibration data includes a second PPG signal and a gold standard blood pressure value of the user;

[0028] a second ECG signal determining unit, which determines a second ECG signal of the user based on the second PPG signal, and determines a second pulse transit time of the user based on the second PPG signal and the second ECG signal;

[0029] a second pulse transit time determination unit, configured to perform a second quality detection on the second ECG signal and the second pulse transit time;

[0030] The calibration unit calibrates the second blood pressure regression model based on the second pulse transmission time and the gold standard blood pressure value to determine the first blood pressure regression model if the result of the second quality detection is determined to be normal.

[0031] In a possible implementation, the first PPG signal includes M first R peaks, the first ECG signal includes N second R peaks, and M and R are both integers greater than 0; and the first pulse transit time determination unit is specifically configured to:

[0032] A first pulse transit time of the user is determined based on a time difference between the M first R peaks and the N second R peaks.

[0033] In a possible implementation, the first R peak is an R wave peak of an ECG signal; and the second R peak is a pulse wave peak of a PPG signal.

[0034] In a possible implementation manner, the first pulse transit time determining unit is specifically configured to:

[0035] Among the M R wave peaks and the N pulse wave peaks, determining the R wave peaks and pulse wave peaks that are adjacent in time sequence as a group;

[0036] The first pulse transmission time is determined based on the time difference between each group of R wave peaks and the pulse wave peaks.

[0037] In a possible implementation, the blood pressure value determination unit is specifically configured to:

[0038] If the difference between M and N is greater than a preset first threshold, and the time difference between the M R wave peaks and the N pulse wave peaks is greater than a preset second threshold, the result of the first quality detection is determined to be normal.

[0039] In a possible implementation, the blood pressure value determination unit is specifically configured to:

[0040] If the difference between M and N is less than the first threshold, the result of the first quality detection is judged to be abnormal, and the user is prompted to retest; or,

[0041] If the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold, the result of the first quality detection is determined to be an abnormal condition, and the user is prompted to retest.

[0042] In a possible implementation, the first ECG signal determining unit is specifically configured to:

[0043] The first PPG signal is input into an electrocardiogram signal conversion model, and the first ECG signal is output.

[0044] In a possible implementation, the ECG signal conversion model is obtained by inputting Q third PPG signals as sample data in the server and training with a preset third ECG signal as a label, or is obtained by training in the server based on historical sample documents.

[0045] In a third aspect, an embodiment of the present application provides a computer storage medium for storing computer software instructions used in a blood pressure detection device provided in the second aspect above, which includes a program designed for executing the above aspect.

[0046] In a fourth aspect, an embodiment of the present application provides a computer program, which includes instructions. When the computer program is executed by a computer, the computer can execute the process executed in the blood pressure detection device in the second aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0048] Figure 1A It is a schematic diagram of a system architecture provided in an embodiment of the present application.

[0049] Figure 1B It is a schematic diagram of a medical detection device provided in an embodiment of the present application.

[0050] Figure 1C This is another system architecture schematic diagram provided in an embodiment of the present application.

[0051] Figure 2 This is a schematic diagram of a blood pressure detection module provided in an embodiment of the present application.

[0052] Figure 3A It is a flow chart of a blood pressure detection provided in an embodiment of the present application.

[0053] Figure 3B This is a schematic diagram of blood pressure detection provided in an embodiment of the present application.

[0054] Figure 3C A schematic diagram of a PPG signal provided in an embodiment of the present application.

[0055] Figure 3D This is another schematic diagram of blood pressure detection provided in an embodiment of the present application.

[0056] Figure 3E A schematic diagram of an ECG signal conversion model module provided in an embodiment of the present application.

[0057] Figure 3F This is a schematic diagram of an ECG signal provided in an embodiment of the present application.

[0058] Figure 3G This is a schematic diagram of ECG signal comparison provided in an embodiment of the present application.

[0059] Figure 3H This is an example diagram of a PTT calculation module provided in an embodiment of the present application.

[0060] Fig. 3I A schematic diagram of calculating pulse conduction time provided in an embodiment of the present application.

[0061] Figure 3J Another schematic diagram of calculating pulse transmission time provided in an embodiment of the present application.

[0062] Figure 3K This is an example diagram of abnormal blood pressure detection provided in an embodiment of the present application.

[0063] Figure 3L This is a schematic diagram of age-based blood pressure value comparison provided in an embodiment of the present application.

[0064] Figure 3M A schematic diagram of a detection result provided in an embodiment of the present application.

[0065] Figure 4A A schematic diagram of a blood pressure calibration process provided in an embodiment of the present application.

[0066] Figure 4B This is a schematic diagram before blood pressure calibration provided in an embodiment of the present application.

[0067] Figure 4C A blood pressure calibration schematic diagram provided in an embodiment of the present application.

[0068] Figure 5 It is a structural schematic diagram of a blood pressure detection device provided in an embodiment of the present application.

[0069] Fig. 6A This is a hardware structure block diagram of the electronic device provided in the embodiment of the present application.

[0070] Figure 6B It is a software structure block diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0071] The embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0072] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0073] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0074] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. For example, a component may communicate through a local and / or remote process according to a signal having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0075] First, some terms in this application are explained to facilitate understanding by those skilled in the art.

[0076] (1) Electrocardiography (ECG) refers to the process of recording the heart's electrical activity through an electrocardiogram device. It is an important part of cardiology and medical diagnosis, and is used in heart health monitoring, disease diagnosis, and treatment effect evaluation. The ECG recording process usually includes steps such as electrode placement, signal acquisition, waveform analysis, and diagnostic interpretation, aiming to accurately and comprehensively reflect the electrophysiological state of the heart, help users diagnose heart disease, and monitor the progression of the disease.

[0077] (2) PPG signal (Photoplethysmogram Signal) is a physiological signal that measures changes in blood volume by optical methods. It mainly detects small changes in blood volume in blood vessels by placing sensors on the surface of the body and using the principle of light absorption or reflection. PPG signals have important applications in medical health monitoring, cardiovascular disease diagnosis, and physiological status assessment. Its signal waveform reflects the heart beat cycle and can be used to analyze heart rate, blood oxygen saturation, and other circulatory system parameters. Accurate measurement of PPG signals is particularly critical for non-invasive cardiovascular monitoring, telemedicine services, and personal health management.

[0078] (3) R-wave Peak refers to the highest point reached by the R wave in the ECG waveform, representing the characteristics of rapid ventricular depolarization. It is one of the core elements of ECG analysis and cardiac electrophysiology, and is crucial in the fields of arrhythmia diagnosis, ECG signal processing, and cardiac function assessment. The R-wave peak recognition process usually includes steps such as waveform signal capture, peak detection, waveform analysis, and clinical relevance assessment, aiming to accurately identify and interpret the ECG waveform to monitor heart health and guide clinical decision-making.

[0079] (4) PTT Pulse Transit Time (PTT) is a physiological parameter used to measure the time required for the pulse wave generated by the heart to propagate along the arteries to specific parts of the body. As an indirect indicator of cardiovascular function, PTT is widely used in the monitoring and evaluation of cardiovascular diseases. The basic principle of PTT measurement is to determine the time difference in the propagation of the pulse wave between two anatomical points. Usually, these points include the heart and distal parts of the body, such as fingers or ankles. The measurement of PTT requires the synchronous recording of electrocardiographic signals (such as ECG) and distal pulse wave signals (such as PPG) to determine the starting point of the heart beat and the moment when the pulse wave reaches the distal part.

[0080] (5) Hypertension is a common cardiovascular disease that refers to persistent high blood pressure. Blood pressure is the pressure exerted on the arterial wall when blood flows through the arteries. Hypertension means that this pressure is abnormally high, placing an additional burden on the heart and arteries. Long-term high blood pressure increases the risk of a variety of health problems, including heart disease, stroke, and kidney disease. The diagnostic criteria for hypertension are defined based on blood pressure values.

[0081] (6) Pulse wave refers to the pressure wave formed when blood propagates in blood vessels as the heart beats. This fluctuation reflects the rhythm of the heart pumping blood and the dynamics of blood flow in the vascular system. Pulse wave can not only provide information about heart rate (heartbeat rate), but also reflect the health status of blood vessels and hemodynamic characteristics.

[0082] (7) The gold standard for blood pressure measurement refers to the most accurate and reliable method for blood pressure measurement. In clinical practice, this usually refers to the best practices for invasive arterial blood pressure measurement and non-invasive blood pressure measurement.

[0083] (8) Pulse Wave Velocity (PWV) is an important indicator for assessing the degree of arteriosclerosis and vascular health. The principle of PWV measurement is based on the relationship between the propagation speed of the pulse wave in the blood vessels and blood pressure. The lower the blood pressure, the slower the pulse wave propagates in the blood vessels; conversely, the higher the blood pressure, the faster the pulse wave propagates. Therefore, blood pressure levels can be indirectly inferred by measuring PWV.

[0084] First, the technical problems to be solved by this application are analyzed and proposed. In the prior art, the technology for blood pressure detection includes the following solutions:

[0085] Option 1: Professional medical staff help users measure blood pressure using professional equipment such as cuffs and stethoscopes.

[0086] The above solution is currently mainly applicable to professional medical scenarios, but it also has the following disadvantages:

[0087] Disadvantage 1: High operational complexity. Traditional blood pressure measurement methods usually require the use of professional medical equipment such as cuffs and stethoscopes, which may be complicated to operate for ordinary users. For example, it takes certain skills and experience to correctly fix the cuff and adjust it to the appropriate tightness. In addition, it is even more difficult for non-professionals to use a stethoscope to accurately listen to and identify the beating sound of the heart. The complexity of these operations not only increases the risk of measurement errors, but also makes it difficult for ordinary users to measure blood pressure independently.

[0088] Disadvantage 2: Unable to provide continuous monitoring. Traditional blood pressure measurement methods can usually only provide one-time blood pressure readings and cannot achieve long-term continuous monitoring, which is an obvious shortcoming for patients who need to closely monitor blood pressure changes. For example, for patients with hypertension or cardiovascular disease, it is important to understand the fluctuations of their blood pressure throughout the day for disease management and treatment. However, traditional methods cannot provide such continuous data records, which limits their application scope in disease management.

[0089] Solution 2: Blood pressure detection based on wearable devices that can support both ECG signals and PPG signals.

[0090] The above solution is currently mainly suitable for a small number of users who can accept high costs, but it also has the following disadvantages:

[0091] Disadvantage 1: Equipment limitations and cost issues. Currently, there are relatively few wearable devices on the market that can simultaneously record ECG (electrocardiogram) and PPG (photoplethysmography) signals, which limits the range of choices for consumers. In addition, wearable devices with dual monitoring functions of ECG and PPG are often expensive. This may pose a great financial pressure for ordinary consumers, especially for hypertensive patients who need long-term blood pressure monitoring. Especially in low-income areas or environments with limited funding for medical equipment, this high cost may be an insurmountable obstacle.

[0092] In order to solve the problem that the current blood pressure detection solution does not meet the actual business needs and achieve the goal of meeting the needs of users and actual business, taking into account the shortcomings of the existing technology, the technical problems actually to be solved by this application include one or more of the following three aspects:

[0093] 1. Simplify the operation process and improve user-friendliness (for disadvantage 1 of solution 1): In view of the high operational complexity of traditional blood pressure measurement methods, it is necessary to develop more simplified and user-friendly blood pressure measurement technologies. This may include designing more intuitive and easy-to-use equipment so that ordinary users can easily measure blood pressure without professional training. For example, consider developing a system that automatically adjusts the tightness of the cuff, or using simpler sound or visual instructions to guide users to perform correct operations. At the same time, provide a more intuitive feedback mechanism, such as displaying measurement results and guidance through applications or embedded screens to reduce reliance on professional medical knowledge.

[0094] 2. Realize continuous and dynamic blood pressure monitoring (for disadvantage 2 of solution 1): In order to overcome the limitation that traditional methods cannot provide continuous monitoring, it is necessary to develop technologies that can perform long-term and continuous blood pressure monitoring. This may involve the development of new portable or wearable devices that can continuously record blood pressure data in daily life, rather than being limited to one-time readings. Such devices should be able to adapt to the user's daily activities while providing accurate and reliable data to enable patients to better manage and monitor blood pressure changes.

[0095] 3. Reduce costs and increase the penetration of equipment (for disadvantage 1 of option 2): Considering the high cost of current high-function blood pressure measurement equipment, especially in areas with limited resources, it is necessary to develop more affordable blood pressure measurement solutions. This may include simplifying the design of the device, or adopting a modular design to reduce production and maintenance costs. In addition, it is also possible to consider improving the performance of existing devices through software optimization and algorithm improvements, rather than relying entirely on expensive hardware upgrades. By reducing costs, these devices can be made more popular, especially among groups with limited economic conditions, thereby improving the overall public health level.

[0096] In summary, the existing blood pressure detection scheme cannot meet the actual business requirements of signal quality detection. Therefore, the blood pressure detection method provided in this application is used to solve the above technical problems.

[0097] Based on the above technical issues and to facilitate understanding of the embodiments of the present application, the following first describes one of the system architectures on which the embodiments of the present application are based. Figure 1A , Figure 1A This is an example diagram of a system architecture provided in an embodiment of the present application. The structure in the embodiment of the present application may include Figure 1A The smart wearable device 01 in the embodiment of the present application may include a system architecture based on which the smart wearable device 01 can independently complete the blood pressure detection function; optionally, see Figure 1B , Figure 1B is a schematic diagram of a medical detection device provided in an embodiment of the present application, Figure 1B The medical monitoring device 02 can be used to assist the smart wearable device 01 in performing blood pressure calibration.

[0098] Among them, the smart wearable device 01 refers to an electronic technology product that can be worn on the body or in contact with the body. In the embodiment of the present application, the smart wearable device 01 can be a smart watch (Smartwatches), a health and fitness monitor (Fitness Trackers), a smart bracelet (Smart Bands), a portable vital sign monitoring device (Biometric Monitors), and other devices that are used to contact the body and collect data information from the body. The smart wearable device 01 mainly collects personal health data, such as PPG signals, through physical contact. For example, see Figure 1A , Figure 1A This is an example diagram of a system architecture provided in an embodiment of the present application. Figure 1A The smart wearable device 01 may be included. Figure 1A Take the smart bracelet as an example for the smart wearable device 01. Figure 1A The function selection interface 01A may include blood pressure detection 11 and blood pressure calibration 12, and different functions may be selected based on the usage of different users. Taking the system architecture based on which the smart wearable device 01 can independently complete the blood pressure detection function as an example, the user can independently complete the blood pressure detection function based on the smart wearable device 01, and display the blood pressure detection result in the interface of the smart wearable device 01; further, if the user has not calibrated, the calibration function can be completed by clicking the blood pressure calibration 12 in the smart wearable device 01 and cooperating with the medical monitoring device 02, and then performing blood pressure detection 11 to improve the accuracy of blood pressure detection. In addition, in the system architecture described in the embodiment of the present application, the smart wearable device 01 collects PPG signals, and the medical monitoring device 02 collects blood pressure gold standard values. The collected blood pressure gold standard values ​​can be input into the smart wearable device 01, and the smart wearable device 01 can input the above-mentioned blood pressure gold standard values ​​and PPG signals into the trained machine algorithm model to determine the corresponding PTT signal, and the blood pressure detection result obtained based on the PTT signal calculation is displayed to the user in the smart wearable device 01.

[0099] The medical monitoring device 02, such as a cuff, is used to cooperate with the device to complete the blood pressure calibration. The medical monitoring device 02 may also include a pressure sensor, an electric inflation pump and an exhaust valve, etc., which can measure the blood pressure around the arm and collect the blood pressure gold standard value. The medical monitoring device 02 may also include other health monitoring functions, such as heart rate monitoring, activity monitoring, etc. For example, see Figure 1B , Figure 1BThis is a schematic diagram of a medical monitoring device provided in an embodiment of the present application. Figure 1B The medical monitoring device 02 may be included. Figure 1B Taking the medical monitoring device 02 as an example of a cuff, the user can fit the cuff tightly against the body and apply pressure to correctly measure the blood pressure, ensure that the blood pressure measurement reaches the blood pressure gold standard value, and input the blood pressure gold standard value into the smart wearable device 01 to assist in completing the blood pressure calibration function.

[0100] For different business scenarios, the system architecture used for ECG signal detection is also different. The following describes another system architecture based on the embodiment of the present application. Figure 1C , Figure 1C This is another schematic diagram of the system architecture provided by the embodiment of the present application. The structure in the present application may include Figure 1C Terminal device 03 in Figure 1C The business scenario is a schematic diagram of the system architecture that completes the blood pressure detection function through the terminal device 03 and the smart wearable device 01. For example, the system architecture in the embodiment of the present application can be a system architecture in which the smart wearable device 01 is responsible for collecting user data and displaying the blood pressure detection result in the terminal device 03. Figure 1B , Figure 1B is a schematic diagram of a medical detection device provided in an embodiment of the present application, Figure 1B The medical monitoring device 02 in the embodiment can be used to assist the terminal device 03 and the smart wearable device 01 in performing the blood pressure calibration function.

[0101] The terminal device 03 may be a smart phone, tablet, personal computer (PC), laptop, network terminal, or other smart device that supports the function of connecting with the smart wearable device 01 and the medical monitoring device 02. For example, the system architecture in the embodiment of the present application may be a system architecture based on the smart wearable device 01 and the terminal device 03 jointly completing the blood pressure test function, with Figure 1C For example, the terminal device 03 is a smart phone. Figure 1CThe application selection interface 03A and the smart bracelet application interface 03B may be included; wherein the terminal device 03 may be connected to one or more of the smart wearable device 01 and the medical monitoring device 02 (for example, via communication connection methods such as Bluetooth, NFC, WiFi, or wired connection). In the application selection interface 03A in the terminal device 03, click on the smart bracelet 31 to enter the smart bracelet application interface 03B, which displays the connected smart wearable device 01 in the bracelet 32 ​​of RY, or displays the connected medical monitoring device 02 in the cuff 33 of RY. The user data collected can be completed by the user by clicking on the blood pressure detection 34 to cooperate with the smart wearable device 01 to complete the blood pressure detection function, or by clicking on the blood pressure calibration 35 to cooperate with the smart wearable device 01 and the medical monitoring device 02 to complete the blood pressure calibration function. In addition, in the system architecture described in the embodiment of the present application, the smart wearable device 01 collects PPG signals, and the medical monitoring device 02 collects blood pressure gold standard values. The two devices can input the collected blood pressure gold standard values ​​and PPG signals into the terminal device 03. The terminal device 03 can calculate the PTT signal based on the above-mentioned blood pressure gold standard values ​​and PPG signals, and obtain the blood pressure value based on the PTT signal calculation and display it to the user in the terminal device 03, thereby providing more accurate blood pressure monitoring results.

[0102] Understandably, Figure 1A-Figure 1C The system architecture in the embodiment is only one or more exemplary implementations in the embodiments of the present application. The structure in the embodiments of the present application includes but is not limited to the above system architecture.

[0103] Based on the system architecture in which the smart wearable device 01 can independently complete the blood pressure detection function, the smart wearable device 01 may include a blood pressure detection module. Figure 2 , Figure 2 is a schematic diagram of a blood pressure detection module provided in an embodiment of the present application, Figure 2 The blood pressure detection module 10 may include a blood pressure detection module 10, and the blood pressure detection module 10 may include a calibration module 102 and a detection module 103.

[0104] in:

[0105] The calibration module 102 can be used to calibrate the user data collected by the smart wearable device 01 and the medical monitoring device 02 to ensure the accuracy and reliability of blood pressure measurement. Exemplarily, the calibration module 102 may include a user prompt calibration unit 1021, a calibration PPG data collection unit 1022, a blood pressure gold standard collection unit 1023, a first PTT calculation module unit 1024, a first signal quality detection unit 1025, and a calibration blood pressure regression formula unit 1026; specifically, when the user uses the device for blood pressure detection for the first time, the smart wearable device 01 may remind the user to calibrate through the user prompt calibration unit 1021, collect the user's PPG signal through the calibration PPG data collection unit 1022, and obtain the user's gold standard blood pressure value (i.e., a blood pressure reference value that meets high standards) collected by the medical monitoring device 02 through the blood pressure gold standard collection unit 1023, so as to obtain the blood pressure calibration required for the user. User data is obtained and the user data is input into the smart wearable device 01; further, the first PTT calculation module unit 1024 in the smart wearable device 01 can calculate the PTT signal based on the above-mentioned PPG signal (for example, the ECG signal is restored based on the PPG signal, and the PTT signal is calculated based on the peak matching of the PPG signal and the ECG signal), and the quantity of the restored ECG signal and the quality of the PTT signal are detected based on the first signal quality detection unit 1025, and finally the blood pressure gold standard value and the PTT signal are input into the calibration blood pressure regression formula unit 1026 for calibrating the blood pressure regression formula. In the detection module 103, the smart wearable device 01 can calculate the blood pressure value based on the calibrated blood pressure regression formula.

[0106] In the detection module 103, the smart wearable device 01 can collect the user's PPG signal in real time during the blood pressure detection, and input the pulse transmission time into the calibrated blood pressure regression formula in the calibration module 102 to calculate the user's blood pressure value. Exemplarily, the detection module 103 may include a PPG data collection unit 1031, a second PTT calculation module unit 1032, a second signal quality detection unit 1033, a blood pressure regression formula input unit 1034 and a predicted blood pressure acquisition unit 1035; specifically, for each different user, if the user is using it for the first time, they need to calibrate through the calibration module 102 first. After the calibration module 102 completes the calibration work, blood pressure detection can be performed through the detection module 103. The smart wearable device 01 can collect the user's PPG signal in real time through the PPG data collection unit 1031, and obtain the predicted blood pressure through the second signal quality detection unit 1033. The second PTT calculation module unit 1032 calculates the PTT signal in real time during the blood pressure detection process (for example, the ECG signal is restored based on the PPG signal, and the PTT signal is calculated based on the peak matching between the PPG signal and the ECG signal), and the number of restored ECG signals and the quality of the PTT signal are detected based on the second signal quality detection unit 1033; finally, the user's blood pressure value is determined in the predicted blood pressure obtaining unit 1035 by inputting the above PTT signal into the above blood pressure regression formula (i.e., the blood pressure regression formula established by the calibration blood pressure regression formula unit 1026 in the calibration module 102). In addition, in the calibration module 102 and the detection module 103, the second PTT calculation module unit 1032 and the first PTT calculation module unit 1024 can be the same module or different modules, and the first signal quality detection unit 1025 and the second signal quality detection unit 1033 can also be the same module or different modules, which are not specifically limited in the embodiments of the present application.

[0107] based on Figure 1A-Figure 1C The provided system architecture and the blood pressure detection module in the smart wearable device 01, combined with the blood pressure detection method provided in the embodiment of the present application, specifically analyze and solve the technical problems raised in the present application.

[0108] See also Figure 3A , Figure 3A This is a flow chart of a blood pressure detection process provided by an embodiment of the present application. Taking the system architecture in which the smart wearable device 01 can independently complete the blood pressure detection function as an example, the system architecture can be used to support and execute Figure 3A The method flow shown in FIG. 1 includes steps S300 to S302. The method may include the following steps S300 to S302.

[0109] Step S300: Acquire a first photoplethysmography (PPG) signal of a user, and determine a first electrocardiogram (ECG) signal of the user based on the first PPG signal.

[0110] Specifically, in the blood pressure detection process in the embodiment of the present application, the user's PPG signal can be recorded and collected based on the smart wearable device 01 (for example, a smart watch, a smart bracelet, etc.) to measure blood flow changes, and the user's PPG signal can be converted into an ECG signal to further perform blood pressure detection. For example, taking the system architecture in which the smart wearable device 01 can independently complete the blood pressure detection function as an example, see Figure 3B , Figure 3B This is a schematic diagram of a blood pressure detection method provided in an embodiment of the present application. Figure 3B The smart wearable device 01 may include a wristband blood pressure detection front interface 01B and a wristband blood pressure detection middle interface 01C; as shown in the wristband blood pressure detection front interface 01B, the user can perform blood pressure detection by clicking the start detection button 18 and enter the wristband blood pressure detection middle interface 01C. As shown in the wristband blood pressure detection middle interface 01C, when performing blood pressure detection, the smart wearable device 01 can collect PPG signals by detecting the photoelectric capacitance change of the blood vessels under the user's arm. The collection process usually involves the LED in the smart wearable device 01 emitting light and the photosensitive sensor receiving reflected light. The smart wearable device 01 converts the collected data into a visual waveform, which can be seen in Figure 3C , Figure 3C A schematic diagram of a PPG signal provided in an embodiment of the present application, Figure 3C The PPG signal shown in can show the dynamic changes of blood passing through blood vessels, and subsequent blood pressure detection can be performed based on the PPG signal; further, the smart wearable device 01 can analyze the specific features of the above PPG signal, such as peak value, waveform duration, etc., to determine the corresponding ECG signal (for example, based on the PPG2ECG autoencoder to realize the conversion of PPG signal into ECG signal). In addition, in a possible implementation method, the system architecture in the embodiment of the present application can also be an example of a system architecture in which the smart wearable device 01 and the terminal device 03 jointly complete the blood pressure detection function, which can be seen in Figure 3D , Figure 3D This is another schematic diagram of blood pressure detection provided in an embodiment of the present application. Figure 3D The terminal device 03 may include a function selection interface 03B, a test preparation interface 03C, and a terminal device test interface 03D; as shown in the function selection interface 03B, the function selection interface 03B may include a wristband device 32, a cuff device 33, start blood pressure detection 34, and start blood pressure calibration 35. The user can check the connection status of the personal device by checking the wristband device 32 and the cuff device 33, and then enter the blood pressure detection by clicking on the start blood pressure detection 34. Figure 3DThe preparation detection interface 03C may include the user's basic personal information and start detection 36. The user may perform blood pressure detection by clicking start detection 36 to start the collection of PPG signals and determine the corresponding ECG signal based on the PPG signal. The detection interface may refer to the terminal device detection interface 03D.

[0111] In one possible implementation, determining the first electrocardiogram (ECG) signal based on the first PPG signal includes: inputting the first PPG signal into an electrocardiogram (ECG) signal conversion model, and outputting the first ECG signal. In an embodiment of the present application, the user's PPG signal can be input into a signal quality detection model to obtain an ECG signal converted from the PPG signal, which can significantly improve processing efficiency, especially when processing large-scale data. Furthermore, the ECG signal conversion model can be a pre-trained machine learning algorithm model, and the ECG signal is determined based on the ECG signal conversion model, so that the speed of subsequent blood pressure detection can be improved, the accuracy of blood pressure detection can be increased, and the cost of blood pressure detection can be reduced (that is, the blood pressure detection device can be a wearable device that supports the collection of PPG signals, without the need to simultaneously integrate PPG signals and ECG signals).

[0112] In a possible implementation, the ECG signal conversion model in the embodiment of the present application can be a PPG2ECG autoencoder, that is, a machine learning model, which can be trained in the server to realize the function of determining the ECG signal from the PPG signal. Figure 3E , Figure 3E Schematic diagram of an ECG signal conversion model module provided in an embodiment of the present application. Taking the training model in the server as an example, the server may include a PPG2ECG model module 105, and the PPG2ECG model module 105 may include a PPG+ECG data acquisition unit 1051, a data set production unit 1052, a training PPG2ECG autoencoder unit 1053 and an acquisition PPG2ECG model unit 1054. The server may first obtain a PPG signal and an ECG signal (these two signals may be prepared in advance or directly collected) through the PPG+ECG data acquisition unit 1051, and determine the corresponding PPG data set and ECG data set through the data set production unit 1052, and input the PPG data set as sample data into the training PPG2ECG autoencoder unit 1053, and train with the ECG data set as a label, and finally obtain a trained acquisition PPG2ECG model unit 1054; further, see Figure 3F , Figure 3F This is a schematic diagram of an ECG signal provided in an embodiment of the present application. In the blood pressure detection process, it is assumed that Figure 3Cis the currently collected PPG signal, which can be obtained by Figure 3C The PPG signal in is input into the above PPG2ECG autoencoder, which can parse and convert the PPG signal after training, and finally outputs Figure 3F In addition, for the same target user, the amplitude comparison of the ECG signal restored by the PPG2ECG autoencoder and the ECG signal acquired by the device supporting ECG signal acquisition can be seen in Figure 3G , Figure 3G A schematic diagram of ECG signal comparison provided in an embodiment of the present application is shown in FIG. Figure 3G As shown in the figure, the high peak is the amplitude of the original ECG signal, and the peak in the middle marked in black is the amplitude of the restored ECG signal. Except for the difference in signal amplitude, the phases of the two ECG signals are relatively close. Further, the data comparison in actual application can be seen in Table 1. Table 1 is a comparison diagram of the algorithm effects of different ECG signals provided in the embodiment of the present application. As shown in Table 1, Table 1 shows a data table of blood pressure measurement error, which includes statistical error indicators of systolic blood pressure (SBP) and diastolic blood pressure (DBP) under two different ECG signal states (resting state and exercise state), where the indicators may include mean error (Mean Error, ME), mean absolute error (Mean Absolute Error, ME), and mean absolute error (Mean Absolute Error, ME). Error, MAE), standard deviation (StandardDeviation, STD), for SBP and DBP under the original scheme (i.e., ECG signal collected by the device) and this scheme (i.e., ECG signal restored by PPG signal through PPG2ECG autoencoder), the table shows the values ​​of the above three indicators respectively; for example, taking the systolic SBP data comparison of the two schemes as an example, the average error of systolic SBP under the original scheme is 0.17, the average absolute error is 17.50, and the standard deviation is 12.46, while the average error of systolic SBP in this scheme is -0.25, the average absolute error is 17.62, and the standard deviation is 12.56. After data comparison, it can be obtained that the results obtained by this scheme are basically consistent with those obtained using the original ECG signal. This scheme can be used in subsequent blood pressure detection to reduce costs while ensuring the accuracy of blood pressure detection (i.e., blood pressure detection no longer needs to be completed based on equipment that needs to collect PPG signals and ECG signals at the same time, and the blood pressure detection function can be completed by equipment that supports collecting PPG signals, avoiding high costs).

[0113] Table 1

[0114]

[0115] In a possible implementation, the PPG2ECG model is obtained by inputting Q second PPG signals as sample data and training with a preset second ECG signal as a label, or is obtained by training based on historical sample documents. In an embodiment of the present application, the ECG signal conversion model can be trained in a server by inputting a pre-prepared PPG signal as sample data and using a preset ECG signal as a label, or the ECG signal conversion model can be trained based on historical sample documents, which may include a PPG signal of an already determined ECG signal. By analyzing these historical data, the ECG signal conversion model can learn and train from past events to more accurately convert the PPG signal into an ECG signal. In summary, the embodiment of the present application can train the ECG signal conversion model by inputting a PPG signal as sample data or analyzing historical events, so that the model can effectively identify and distinguish high-quality and low-quality conversion results, thereby enhancing the adaptability and accuracy of the ECG signal conversion model when processing actual data, so as to obtain a higher quality ECG signal, and further improve the accuracy of blood pressure detection based on the ECG signal.

[0116] Step S301: Perform peak detection on the first PPG signal and the first ECG to determine a first pulse transmission time of the user.

[0117] Specifically, in the process of blood pressure detection, first based on Figure 3A-3G After obtaining the ECG signal according to the embodiment steps described in the embodiment, the pulse transmission time can be determined based on the PPG signal and the ECG signal in the embodiment of the present application. For example, see Figure 3H , Figure 3H1 is an example diagram of a PTT calculation module provided in an embodiment of the present application. Taking the operation of the PTT calculation module in the smart wearable device 01 as an example, the smart wearable device 01 may include a PTT calculation module 104, wherein the PTT calculation module 104 may include a PPG signal acquisition unit 1041, an input PPG2ECG model unit 1042, a first peak detection unit 1043, an ECG signal acquisition prediction unit 1044, a second peak detection unit 1045, a peak matching unit 1046 and a PTT calculation unit 1047; first, the smart wearable device 01 acquires the user's PPG signal through the PPG signal acquisition unit 1041, and inputs the PPG signal into the PPG2ECG model unit 1042 (the The PPG2ECG model unit 1042 may be a trained machine algorithm model), and the ECG signal is determined based on the predicted ECG signal unit 1044. Please refer to step S300 in the above embodiment, which will not be described in detail in the embodiment of the present application; further, the smart wearable device 01 can also obtain the peak value corresponding to the PPG signal based on the first peak detection unit 1043, and obtain the A group peak value corresponding to the ECG signal based on the second peak detection unit 1045, and perform peak matching on the PPG signal and the ECG signal based on the peak matching unit 1046, and finally calculate the time difference of the peak for each group of corresponding PPG signals and ECG signals based on the calculation PTT unit 1047, and obtain the pulse conduction time PTT. The pulse conduction time PTT can be used for subsequent blood pressure detection for further analysis to obtain more accurate blood pressure detection results.

[0118] In a possible implementation, the first PPG signal includes M first R peaks, and the first ECG signal includes N second R peaks, where M and R are both integers greater than 0; the peak detection of the first PPG signal and the first ECG to determine the first pulse conduction time of the user includes: determining the first pulse conduction time of the user based on the time difference between the M first R peaks and the N second R peaks. In the embodiment of the present application, the pulse conduction time of the user can be accurately determined by performing peak detection on the first PPG signal and the first ECG signal. Specifically, in the embodiment of the present application, peak detection can be performed on the PPG signal and the ECG signal to determine multiple R peaks (i.e., high peaks) of the above two signals, and the time difference is calculated based on the M first R peaks and the N second R peaks (for example, the PPG signal and ECG signal that are adjacent in time sequence can be determined as a group, and the time difference is calculated for each group of signals), and finally the pulse conduction time of the user is determined. In summary, in the embodiments of the present application, the time difference can be calculated based on the peak values ​​of the ECG signal and the PPG signal, so that a more accurate pulse conduction time can be calculated, and more accurate data can be used for blood pressure detection in the subsequent blood pressure detection process, thereby ensuring the accuracy of blood pressure detection.

[0119] In one possible implementation, the first R peak is the R wave peak of the ECG signal; the second R peak is the pulse wave peak of the PPG signal. In an embodiment of the present application, by accurately identifying and distinguishing the R wave peak in the ECG signal and the pulse wave peak in the PPG signal, the system can more accurately calculate the pulse conduction time and obtain more accurate blood pressure detection results. Specifically, accurate identification of the first R peak (R wave peak of the ECG signal) and the second R peak (pulse wave peak of the PPG signal) can enable the system to process and analyze the above two different types of physiological signals separately, and more accurately calculate the time difference between the peaks based on the two signals, thereby more accurately determining the pulse conduction time to increase the accuracy of subsequent blood pressure detection.

[0120] In a possible implementation, the determining of the user's first pulse conduction time based on the time difference between the M first R peaks and the N second R peaks includes: determining the R wave peaks and pulse wave peaks that are adjacent in time sequence among the M R wave peaks and the N pulse wave peaks as a group; and determining the first pulse conduction time based on the time difference between each group of R wave peaks and pulse wave peaks. In an embodiment of the present application, by determining the user's first pulse conduction time based on the time difference between M R wave peaks and N pulse wave peaks, a more accurate and reliable blood pressure detection method is provided. Specifically, in an embodiment of the present application, by identifying R wave peaks and pulse wave peaks that are adjacent in time sequence, and determining every two ECG signals and PPG signals that are adjacent in time sequence as a group, the time difference between each group of R wave peaks and pulse wave peaks is accurately calculated, and finally the pulse conduction time is determined based on the time difference, thereby improving the accuracy of blood pressure detection. Furthermore, after obtaining the ECG signal and the PPG signal, the system (such as the smart wearable device 01) can perform peak detection to determine each R wave peak in the ECG signal. These R waves represent the rapid depolarization of the ventricles and are the most significant peaks in each heart cycle. At the same time, the system will also detect the pulse wave peaks in the PPG signal. These peaks correspond to the changes in the optical signal caused by the blood pulsating in the blood vessels. On this basis, the system pairs each R wave peak with the corresponding pulse wave peak, calculates the time difference between each pair of peaks, that is, the pulse conduction time, and performs subsequent blood pressure detection based on the pulse conduction time.

[0121] For example, see Fig. 3I , Fig. 3I This is a schematic diagram of calculating pulse transmission time provided in an embodiment of the present application. Fig. 3I The corresponding ECG signal waveform and PPG signal waveform may be included (for example, the ECG signal and PPG signal adjacent in time sequence may be determined as a group), Fig. 3IThe upper part of the diagram shows the waveform of the ECG signal, wherein the "R-Wave Peak" is highlighted, indicating the highest point (i.e., the R-wave peak) in the ECG waveform during ventricular contraction; Fig. 3I The lower part of the diagram shows the waveform of the PPG signal, which can be obtained by measuring the change in blood flow using an optical sensor (such as the smart wearable device 01) on the surface of the arm, wherein "Pulse Peak" is marked, i.e., the pulse wave peak value; after determining the R wave peak value of the ECG signal and the pulse wave peak value of the PPG signal, the smart wearable device 01 can match the temporally adjacent R wave peak values ​​with the pulse wave peak values ​​as a group, for example, the first R wave peak value will be paired with the first pulse wave peak value detected, the second R wave peak value will be paired with the subsequently detected pulse wave peak value, and so on; further, the pulse conduction time PTT can be the time difference between the R wave peak value of the ECG signal and the pulse wave peak value of the PPG signal, Fig. 3I In the figure, the correspondence between the two peaks can be seen through the vertical dotted line. The horizontal arrow from the R wave peak to the pulse wave peak represents the time delay between the two points. This time is PTT. In addition, the embodiment of the present application only provides a possible implementation method. The specific time unit and peak matching correspondence are not specifically limited in the embodiment of the present application. For example, PTT can be calculated based on PPG signals and ECG signals. Figure 3J , Figure 3J This is another schematic diagram of calculating pulse transmission time provided in an embodiment of the present application. Figure 3J The diagram may include continuous ECG signal waveforms and PPG signal waveforms, each two adjacent dotted lines include a group of corresponding PPG signals and ECG signals, and PTT may be calculated based on the peak matching results of the PPG signal and the ECG signal. The top of each group of adjacent dotted lines may include time marks, which may be PTT measurement results; for example, the "0.128" displayed on the top of the third pair of adjacent dotted lines may indicate that the actual measurement value of PTT is 128 milliseconds. Through continuous waveform detection, blood pressure can be continuously detected to obtain more accurate monitoring results.

[0122] Step S302: performing a first quality detection on the first ECG signal and the first pulse transmission time, and if it is determined that the result of the first quality detection is normal, determining the blood pressure value of the user based on the first pulse transmission time.

[0123] Specifically, the system (e.g., smart wearable device 01) first performs a quality test on the collected ECG signal. If the result of the first quality test is confirmed to be normal, that is, the ECG signal and pulse conduction time meet the quality standards, the system will proceed to the next step; at this stage, the system can calculate the user's blood pressure value based on the pulse conduction time. For example, the system may use an algorithm to model the relationship between pulse conduction time and known blood pressure values, so as to accurately estimate the current blood pressure value. In this way, the system can not only provide instant blood pressure detection, but also warn of potential blood pressure problems, providing users and medical professionals with important health information.

[0124] In a possible implementation, the first quality detection of the first ECG signal and the first pulse conduction time includes: if the difference between M and N is greater than a preset first threshold, and the time difference between the M R wave peaks and the N pulse wave peaks is greater than a preset second threshold, then the result of the first quality detection is judged to be normal. In this embodiment, by performing quality detection on the first ECG signal and the first pulse conduction time, the normal condition of the physiological signal can be more accurately judged. Specifically, by setting the preset first threshold and the second threshold, when the smart wearable device 01 detects that the difference between M and N exceeds the first threshold (for example, it can be to determine whether the number of ECG signals converted from the PPG signal is consistent with the PPG signal), and detects that the time difference between the M R wave peaks and the N pulse wave peaks exceeds the second threshold (for example, to determine whether the pulse conduction time or the Pearson correlation coefficient determined based on the ECG signal and the PPG signal exceeds the normal value, abnormal conditions occur, etc.), the smart wearable device 01 can determine that the result of this quality detection is normal, so as to perform subsequent blood pressure detection. In summary, in the embodiments of the present application, quality detection can be performed on two situations at the same time (for example, quality detection of ECG signals and PPG signals can be performed to determine whether the difference in the number and time difference of peak values ​​exceeds the corresponding thresholds) to ensure the accuracy of blood pressure detection parameters and improve the accuracy of subsequent blood pressure detection.

[0125] In a possible implementation, the first quality detection of the first ECG signal and the first pulse conduction time includes: if the difference between M and N is less than the first threshold, then judging the result of the first quality detection as an abnormal condition, and prompting the user to retest; or, if the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold, then judging the result of the first quality detection as an abnormal condition, and prompting the user to retest. In the embodiment of the present application, when an abnormality occurs in the quality detection by performing the first quality detection on the first ECG signal and the first pulse conduction time, the user is prompted to perform the test. Specifically, in the embodiment of the present application, by setting two thresholds - a first threshold and a second threshold - the smart wearable device 01 can determine whether there are abnormalities in the ECG and pulse conduction time. If the smart wearable device 01 detects that the difference between M and N is less than the first threshold (i.e., it is determined that the number of ECG signals converted from the PPG signal exceeds the preset first threshold), or the smart wearable device 01 detects that the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold (i.e., it is determined that the pulse conduction time has an abnormality that exceeds the preset second threshold), when one of the two situations occurs, the smart wearable device 01 will determine that these results are abnormal conditions and prompt the user to retest, thereby avoiding interference with the accuracy of the final blood pressure detection results due to partial data errors, improving the overall efficiency and accuracy of the test, and thus enhancing the reliability of the blood pressure detection solution. For example, see Figure 3K , Figure 3K This is an example diagram of blood pressure detection abnormality provided in an embodiment of the present application, which includes a detection abnormality interface 01D. When the system detects that the number of electrocardiogram signals (ECG) is less than a preset threshold, or when the pulse transmission time (PTT) is less than a preset threshold range, the system prompts the user to retest.

[0126] In a possible implementation, determining the blood pressure value of the user based on the first pulse conduction time includes: inputting the first pulse conduction time into a calibrated first blood pressure regression model, and outputting the blood pressure value of the user. Specifically, the smart wearable device 01 can be based on the user's pulse conduction time as an input parameter, and input it into a calibrated blood pressure regression model. The blood pressure regression model can calculate the pulse conduction velocity based on the pulse conduction time and the distance between different blood vessels, and calculate the blood pressure value based on the data. Furthermore, the above-mentioned blood pressure regression model can be a blood pressure regression formula, which is optimized by statistical methods and machine learning techniques after collecting the user's blood pressure data and related physiological parameters for calibration. For example, the historical calibration data of a specific user may include the relationship between his blood pressure value and pulse conduction time (PTT), and the blood pressure value can be restored based on a specific blood pressure regression formula. The blood pressure regression formula can include a linear model. When the heart contracts, blood is pumped into the aorta to form pulse waves. These pulse waves propagate outward along the arterial system and are closely related to changes in blood pressure. By measuring the pulse wave arrival time difference PTT at different vascular locations and the distance L between different vascular locations, the pulse wave conduction velocity PWV in the blood vessels can be calculated.

[0127]

[0128] And the relationship between blood pressure and conduction velocity PWV can be established according to the Moens-Korteweg equation, where E0 is the elastic modulus of the blood vessel, h is the thickness of the blood vessel wall, α is a constant, ρ is the blood density, and r is the radius of the blood vessel.

[0129]

[0130] Since E0, h, α, ρ, and r in the above formula are all fixed values, in actual operation, a large number of samples are often used to perform linear fitting on blood pressure P and pulse wave arrival time difference PTT, that is, blood pressure P is linearly mapped through PTT.

[0131] P=αlnPTT+β

[0132] For example, after the smart wearable device 01 determines the pulse transmission time, the data can be input into the calibrated blood pressure regression formula to determine the corresponding blood pressure value. In addition, the blood pressure regression formula may consider multiple variables, such as age, gender, weight, and historical blood pressure values, to more accurately predict the user's blood pressure value; see Figure 3L , Figure 3L This is a schematic diagram of age-based blood pressure comparison provided in an embodiment of the present application. Figure 3LAs shown, the hypertension rate may be highest among people aged 35-44. Based on different age categories, other parameters can be set for different ages to jointly calculate the blood pressure value, and the corresponding blood pressure test result can be given to the user based on the blood pressure value. For example, see Figure 3M , Figure 3M This is a schematic diagram of a detection result provided in an embodiment of the present application, Figure 3M The blood pressure detection result interface 01E may be included. As shown in the blood pressure detection result interface 01E, assuming that the current user's blood pressure value is higher than the normal average value (for example, the blood pressure average value may be calculated based on different age groups), it is determined that the current user has high blood pressure, or it is determined whether the user's blood pressure value has increased based on the detection results over a period of time, so as to remind the user of his or her physical health condition.

[0133] Optionally, in the above method steps S300 to S302, the blood pressure value may be determined based on the user's PPG signal. For a detailed process of blood pressure calibration, please refer to Figure 4A , Figure 4A Schematic diagram of a blood pressure calibration process provided in an embodiment of the present application; Figure 4A As shown, the following steps S400 to S403 may also be included:

[0134] Step S400: If the calibration result of the user is not detected, the calibration data of the user is obtained.

[0135] Specifically, the calibration data includes the second PPG signal of the user and the gold standard blood pressure value. In the embodiment of the present application, when the user turns on the calibration function, or when the calibration result of the current user is not detected, the user's PPG signal (for example, collected by a wearable device such as a smart watch or smart bracelet) and the gold standard blood pressure value (for example, collected based on a cuff) can be collected. For example, see Figure 4B , Figure 4B This is a schematic diagram before blood pressure calibration provided in an embodiment of the present application. Figure 4B The blood pressure calibration reminder interface 01F and the blood pressure calibration pre-interface 01G of the smart wearable device 01 may be included; when the smart wearable device 01 does not include the historical calibration data of the user (for example, it may be caused by the user's first use or the time interval is too long), as shown in the blood pressure calibration reminder interface 01F, the smart wearable device 01 pops up a detection reminder, prompting the user to perform blood pressure calibration before blood pressure detection, and the user can click to start blood pressure calibration 13 to enter the blood pressure calibration pre-interface 01G; as shown in the blood pressure calibration pre-interface 01G, the interface may include the connection status of personal devices such as RY's cuff, and prompt the user to wear the above two devices correctly. The user can perform the blood pressure calibration function by clicking the start calibration button 14; further, see Figure 4C , Figure 4C A blood pressure calibration diagram provided in an embodiment of the present application is shown in FIG. Figure 4C The smart wearable device 01 may include a wristband blood pressure detection interface 01H and a medical monitoring device 02; Figure 4C As shown, the smart wearable device 01 and the medical monitoring device 02 have established a communication connection (for example, it can be through Bluetooth, NFC, WiFi, wired connection, etc.). When performing blood pressure detection, the smart wearable device 01 (such as a smart bracelet) can detect the photoelectric capacitance change of the blood vessels under the user's arm to collect the PPG signal, and determine the blood pressure gold standard value based on the medical monitoring device 02. Assuming that the medical monitoring device 02 is a cuff, a cuff can be placed around the arm to determine the user's gold standard blood pressure value, and then blood pressure verification can be performed based on the above two data.

[0136] In one possible implementation, if the calibration result of the user is detected, the first blood pressure regression model is obtained based on the calibration result. In the embodiment of the present application, it is possible to detect whether the user has performed a calibration operation, and then obtain the first blood pressure regression model based on the calibration result. This method optimizes the accuracy of blood pressure measurement. Specifically, after the user completes the calibration, the system obtains the corresponding calibration data, and obtains the blood pressure regression model corresponding to the user based on the calibration data. The method of obtaining the corresponding blood pressure regression model based on individual calibration data in the embodiment of the present application can more accurately reflect the specific blood pressure condition of each user, improve the reliability and effectiveness of blood pressure monitoring, and thus help to better guide users' health management and disease prevention.

[0137] Step S401: Determine a second ECG signal of the user based on the second PPG signal, and determine a second pulse transit time of the user based on the second PPG signal and the second ECG signal.

[0138] Specifically, see Figure 3A The embodiment described in step S302 will not be repeated in the embodiments of this application.

[0139] Step S402: performing a second quality detection on the second ECG signal and the second pulse transmission time.

[0140] Specifically, see Figure 3A The embodiment described in step S302 will not be repeated in the embodiments of this application.

[0141] Step S403: If it is determined that the result of the second quality detection is normal, the second blood pressure regression model is calibrated based on the second pulse transmission time and the gold standard blood pressure value to determine the first blood pressure regression model.

[0142] Specifically, in the embodiment of the present application, the pulse transmission time of the user can be determined based on the PPG signal (for example, the PPG signal can be converted into an ECG signal, and the pulse transmission time can be determined based on the PPG signal and the ECG signal), and the ECG signal and the pulse transmission time can be quality tested to ensure the accuracy of the calibration data; further, the pulse transmission time and the gold standard blood pressure value can be input into the blood pressure regression model to calibrate the blood pressure regression model. Exemplarily, the parameters of the blood pressure prediction model can be learned and adjusted by analyzing multiple groups of pulse signals and corresponding blood pressure values ​​in the server, thereby improving its prediction accuracy. Assuming that the smart wearable device 01 has measured the user's PPG signal and the gold standard blood pressure value by a non-invasive method, the relationship between the pulse signal and the blood pressure reading can be identified by comparing the two sets of data, and the blood pressure regression model can be adjusted accordingly. The calibration process may involve multiple iterations, and each iteration adjusts the model according to the newly collected data until the predetermined accuracy standard is reached. Furthermore, the above-mentioned blood pressure regression model can be a blood pressure regression formula, and the calibration steps of the blood pressure regression formula can include: the smart wearable device 01 first inputs the collected PTT data and the gold standard blood pressure value into the preset blood pressure regression formula P=αln(PTT)+β, wherein α and β can be coefficients to be determined, which are obtained by statistically analyzing a series of data sets of known blood pressure and PTT values. The regression technology in the analysis process can include the least squares method to find the best α and β values, so that the formula can accurately predict the blood pressure value. Finally, in the actual blood pressure detection process, the PPG signal can be collected by the smart wearable device 01, and the pulse transmission time PTT determined based on the PPG signal can be input into the calibrated blood pressure regression formula to determine the user's blood pressure value and provide the user with accurate blood pressure detection results.

[0143] The method of the embodiment of the present application is described in detail above, and the related device of the embodiment of the present application is provided below.

[0144] See also Figure 5 , Figure 5 It is a structural schematic diagram of a blood pressure detection device provided in an embodiment of the present application. The blood pressure detection device 50 may include a first ECG signal determination unit 501, a first pulse conduction time determination unit 502, a blood pressure value determination unit 503, a first blood pressure regression model acquisition unit 504, a calibration data acquisition unit 505, a second ECG signal determination unit 506, a second pulse conduction time determination unit 507 and a calibration unit 508, wherein each unit is described in detail as follows.

[0145] A first ECG signal determining unit 501 is used to obtain a first photoplethysmography (PPG) signal of a user, and determine a first electrocardiogram (ECG) signal of the user based on the first PPG signal;

[0146] In a possible implementation, the first ECG signal determining unit 501 is specifically configured to:

[0147] The first PPG signal is input into an electrocardiogram signal conversion model, and the first ECG signal is output.

[0148] In a possible implementation, the ECG signal conversion model is obtained by inputting Q third PPG signals as sample data in the server and training with a preset third ECG signal as a label, or is obtained by training in the server based on historical sample documents.

[0149] A first pulse transit time determining unit 502, configured to perform peak detection on the first PPG signal and the first ECG signal to determine a first pulse transit time of the user;

[0150] In a possible implementation, the first PPG signal includes M first R peaks, the first ECG signal includes N second R peaks, and M and R are both integers greater than 0; the first pulse transmission time determination unit 502 is specifically configured to:

[0151] A first pulse transit time of the user is determined based on a time difference between the M first R peaks and the N second R peaks.

[0152] In a possible implementation, the first pulse transit time determining unit 502 is specifically configured to:

[0153] Among the M R wave peaks and the N pulse wave peaks, determining the R wave peaks and pulse wave peaks that are adjacent in time sequence as a group;

[0154] The first pulse transmission time is determined based on the time difference between each group of R wave peaks and the pulse wave peaks.

[0155] In a possible implementation, the first R peak is an R wave peak of an ECG signal; and the second R peak is a pulse wave peak of a PPG signal.

[0156] The blood pressure value determination unit 503 is used to perform a first quality detection on the first ECG signal and the first pulse transmission time, and if the result of the first quality detection is determined to be normal, determine the blood pressure value of the user based on the first pulse transmission time.

[0157] In a possible implementation, the blood pressure value determining unit 503 is specifically configured to:

[0158] The first pulse transit time is input into a calibrated first blood pressure regression model, and the blood pressure value of the user is output.

[0159] In a possible implementation, the blood pressure value determining unit 503 is specifically configured to:

[0160] If the difference between M and N is greater than a preset first threshold, and the time difference between the M R wave peaks and the N pulse wave peaks is greater than a preset second threshold, the result of the first quality detection is determined to be normal.

[0161] In a possible implementation, the blood pressure value determining unit 503 is specifically configured to:

[0162] If the difference between M and N is less than the first threshold, the result of the first quality detection is judged to be abnormal, and the user is prompted to retest; or,

[0163] If the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold, the result of the first quality detection is determined to be an abnormal condition, and the user is prompted to retest.

[0164] The first blood pressure regression model acquisition unit 504 acquires the first blood pressure regression model based on the calibration result if the calibration result of the user is detected.

[0165] The calibration data acquisition unit 505 acquires the calibration data of the user if the calibration result of the user is not detected, wherein the calibration data includes the second PPG signal and the gold standard blood pressure value of the user;

[0166] a second ECG signal determining unit 506, which determines a second ECG signal of the user based on the second PPG signal, and determines a second pulse transmission time of the user based on the second PPG signal and the second ECG signal;

[0167] A second pulse transit time determination unit 507, configured to perform a second quality detection on the second ECG signal and the second pulse transit time;

[0168] The calibration unit 508 calibrates the second blood pressure regression model based on the second pulse transmission time and the gold standard blood pressure value to determine the first blood pressure regression model if it is determined that the result of the second quality detection is normal.

[0169] The following introduces the terminal device provided in the embodiment of the present application.

[0170] Fig. 6AThe hardware structure diagram of the terminal device 1000 provided in the embodiment of the present application is shown. The terminal device 1000 is used to execute the blood pressure detection method provided in the above method embodiment.

[0171] The terminal device 1000 may include a processor 1001, a memory 1002, a wireless communication module 1003, a mobile communication module 1004, an antenna 1003A, an antenna 1004A, a power switch 1005, a sensor module 1006, a display screen 1009, etc. Among them, the sensor module 1006 may include a gyroscope sensor 1006A, an acceleration sensor 1006B, an ambient light sensor 1006C, a PPG signal sensor 1006D, a distance sensor 1006E, etc. Among them, the wireless communication module 1003 may include a WLAN communication module, a Bluetooth communication module, etc. The above multiple parts can transmit data through a bus.

[0172] The processor 1001 may include a variety of processing units to optimize the performance of the terminal device 1000 when processing blood pressure detection. For example, these processing units may include a main application processor (AP) responsible for complex data processing tasks, a graphics processing unit (GPU) to optimize the display of blood pressure detection results, and a specially designed digital signal processor (DSP) and a neural network processor (NPU) to accelerate the execution of blood pressure detection. These units work together to improve the efficiency and accuracy of the blood pressure detection scheme in determining ECG signals based on PPG signals, determining pulse transmission time based on PPG signals and ECG signals, quality detection, and determining blood pressure values ​​based on pulse transmission time. In addition, this multi-processing unit design can support the blood pressure detection scheme to process multiple tasks in parallel, thereby providing fast response and accurate detection results when processing large blood pressure data sets.

[0173] The memory 1002 is used to store the operating system, application code and other data of the terminal device 1000. For example, it may include local applications (such as blood pressure value calculation applications, etc.) and program codes and data required for blood pressure detection. The processor 1001 implements device functions and blood pressure data processing tasks by executing program codes stored in the memory 1002. The program storage area of ​​the memory 1002 is used to place the operating system and application code, while the data storage area is used to save data generated when running the application. In addition to including fast-access random access memory (RAM), the memory 1002 may also include one or more forms of non-volatile memory, such as a hard disk drive, a solid-state drive, or a flash memory device, to provide a persistent storage solution.

[0174] The wireless communication function of the terminal device 1000 can be implemented through the antenna 1003A, the antenna 1004A, the mobile communication module 1004, the wireless communication module 1003, the modem processor and the baseband processor.

[0175] Antenna 1003A and antenna 1004A can be used to transmit and receive electromagnetic wave signals. Each antenna in terminal device 1000 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.

[0176] The mobile communication module 1004 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the terminal device 1000. The mobile communication module 1004 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 1004 can receive electromagnetic waves through the antenna 1004A, and filter, amplify, etc. the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 1004 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1004A.

[0177] The modem processor may include a modulator and a demodulator. The function of the modulator is to convert the low-frequency PPG signal to be sent into a medium-high frequency signal for transmission. The demodulator at the receiving end is responsible for demodulating the received medium-high frequency signal back to a low-frequency baseband signal. These demodulated signals are then transmitted to the baseband processor for further processing, such as signal amplification, filtering and digitization. The processed PPG signal is passed to the application processor, which further analyzes these signals to detect the user's blood pressure and display the relevant blood pressure value or other physiological information through the display screen 1009.

[0178] The wireless communication module 1003 provides a variety of wireless communication methods, which are applicable to the terminal device 1000. This includes wireless local area network (WLAN), Bluetooth (BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), infrared technology (IR), etc. In particular, the wireless communication module 1003 uses Bluetooth technology to connect multiple terminal devices together to form a collaborative network. In this network, each terminal device can share PPG signal data and gold standard blood pressure values ​​to achieve collaborative blood pressure detection functions. This connection method not only enhances the scope and efficiency of data collection, but also improves the accuracy and reliability of blood pressure detection. The wireless communication module 1003 receives and sends electromagnetic wave signals through the antenna 1003A to ensure the effective transmission of data.

[0179] The power switch 1005 may be used to control the supply of power to the terminal device 1000 .

[0180] The gyroscope sensor 1006A can be used to determine the motion posture of the terminal device 1000. In some embodiments, the angular velocity of the terminal device 1000 around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor 1006A. The gyroscope sensor 1006A can be used for anti-shake shooting. For example, when the shutter is pressed, the gyroscope sensor 1006A detects the angle of the terminal device 1000 shaking, calculates the distance that the lens module needs to compensate based on the angle, and allows the lens to offset the shaking of the terminal device 1000 through reverse movement to achieve anti-shake. The gyroscope sensor 1006A can also be used for navigation and somatosensory game scenes.

[0181] The acceleration sensor 1006B can detect the magnitude of the acceleration of the terminal device 1000 in various directions (generally three axes). When the terminal device 1000 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the terminal device. For example, the acceleration sensor 1006B can be applied to applications such as horizontal and vertical screen switching, pedometers, etc.

[0182] The ambient light sensor 1006C is used to sense the brightness of the ambient light. The terminal device 1000 can adaptively adjust the brightness of the display screen 1009 according to the sensed brightness of the ambient light. The ambient light sensor 1006C can also be used to automatically adjust the white balance when taking pictures.

[0183] The PPG signal sensor 1006D can be used to capture PPG signals. The PPG signal sensor 1006D may include at least one light source (e.g., an LED), a photodetector, and necessary circuits to process the PPG signal. The LED of the PPG signal sensor 1006D emits light (usually red light or infrared light) to illuminate the user's skin, and then the photodetector captures the light absorbed or reflected by the blood. Slight changes in the amount of blood (such as changes caused by heartbeats) will cause changes in the amount of light received. These changes are converted into electrical signals, and after amplification, filtering, and other processing by the signal processing circuit, a PPG signal reflecting the blood flow characteristics is obtained.

[0184] The distance sensor 1006E can be used to measure the distance. The terminal device 1000 can measure the distance by infrared or laser. In some shooting scenarios, the terminal device 1000 can use the distance sensor 1006E to measure the distance to achieve fast focusing.

[0185] The video codec is used to compress or decompress digital images. The terminal device 1000 may support one or more image codecs. In this way, the terminal device 1000 can open or save pictures or videos in multiple encoding formats.

[0186] The terminal device 1000 can realize the display function through a GPU, a display screen 1009, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 1009 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 1001 may include one or more GPUs, which execute program instructions to generate or change display information.

[0187] The blood pressure detection module 1007 can be used to measure and monitor blood pressure. The blood pressure detection module 1007 can determine the ECG signal based on the user's PPG signal collected by the PPG signal sensor 1006D, and based on the analysis of the above two signals, the blood pressure detection module 1007 can accurately calculate the user's pulse transit time (Pulse Transit Time, PTT), and then estimate the user's blood pressure value. Optionally, the blood pressure detection module 1007 can also be a software module (including an algorithm model) executed by the processor 1001.

[0188] The display screen 1009 is used to display images, videos, etc. The display screen 1009 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicrOLED, Micro-OLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the terminal device 1000 may include 1 or N display screens 1009, where N is a positive integer greater than 1.

[0189] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the terminal device 1000. In other embodiments of the present application, the terminal device 1000 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0190] For details on the operations performed by each device in the terminal device 1000, please refer to Figure 3A-3B The relevant description of the embodiments in the embodiment will not be expanded in detail here.

[0191] The software system of the terminal device 1000 can adopt one or more of a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture, and can support local blood pressure detection and analysis functions based on blood pressure detection algorithms. For example, the application framework layer in the mobile operating system provides an application programming interface (API) and a programming framework for the PPG signal analysis application. In addition, the system library may include multiple functional modules, such as a media library and a graphics processing library for processing user physiological data, which can support the analysis, display and storage of blood pressure values. The embodiment of the present application takes a mobile operating system with a layered architecture as an example to illustrate the software structure of the terminal device 1000.

[0192] Figure 6B It is a software structure block diagram of the terminal device 1000 of an embodiment of the present application.

[0193] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the mobile operating system is divided into four layers, from top to bottom: application layer, application framework layer / core service layer, system library and runtime, and kernel layer.

[0194] The application layer can include a series of application packages.

[0195] like Figure 6B As shown, the application package may include camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message and other applications.

[0196] The application framework layer provides an application programming interface (API) and a programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

[0197] like Figure 6B As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0198] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0199] Content providers can be used to store and retrieve data, and after making these data accessible to applications, they can be used to access and index local data such as phone books, browsing history and bookmarks, and provide users with the prompt information they need when testing blood pressure. The data may include video, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0200] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0201] The phone manager is used to provide communication functions for terminal devices, such as the management of call status (including answering, hanging up, etc.).

[0202] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0203] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, the terminal device vibrates, the indicator light flashes, etc.

[0204] Runtime can refer to all code libraries, frameworks, etc. required for the program to run. For example, a Java virtual machine and core library are provided to provide the necessary environment for the operation of the blood pressure detection solution.

[0205] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0206] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0207] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0208] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0209] A 2D graphics engine is a drawing engine for 2D drawings.

[0210] The kernel layer is the layer between hardware and software. The kernel layer contains at least display drivers, audio drivers, and sensor drivers. For example, it can provide underlying hardware support for blood pressure detection, so that the blood pressure detection and analysis system can effectively access and process blood pressure data stored in the file system. This underlying support ensures accurate data processing and fast analysis of blood pressure values, thereby improving the overall performance of blood pressure detection.

[0211] It should be understood that each step in the above method embodiment can be completed by an integrated logic circuit of hardware in a processor or by instructions in the form of software. The method steps disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware processor, or by a combination of hardware and software modules in a processor.

[0212] The present application also provides a terminal device, which may include: a memory and a processor. The memory may be used to store a computer program; the processor may be used to call the computer program in the memory, so that the terminal device executes the method executed by the terminal device side in any of the above embodiments.

[0213] The present application also provides a terminal device, which may include: a memory and a processor. The memory may be used to store a computer program; the processor may be used to call the computer program in the memory, so that the terminal device executes the method executed by the terminal device side in any of the above embodiments.

[0214] The present application also provides a chip system, which includes at least one processor for implementing the functions involved in the terminal device side in any of the above embodiments.

[0215] In one possible design, the chip system also includes a memory, which is used to store program instructions and data, and the memory is located inside or outside the processor.

[0216] The chip system may be composed of the chip, or may include the chip and other discrete devices.

[0217] Optionally, the processor in the chip system may be one or more. The processor may be implemented by hardware or by software. When implemented by hardware, the processor may be a logic circuit, an integrated circuit, etc. When implemented by software, the processor may be a general-purpose processor implemented by reading software code stored in a memory.

[0218] Optionally, the memory in the chip system may also be one or more. The memory may be integrated with the processor or may be separately arranged with the processor, which is not limited in the embodiments of the present application. Exemplarily, the memory may be a non-transient processor, such as a read-only memory ROM, which may be integrated with the processor on the same chip or may be arranged on different chips respectively. The embodiments of the present application do not specifically limit the type of memory and the arrangement of the memory and the processor.

[0219] Exemplarily, the chip system can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD) or other integrated chips.

[0220] The present application also provides a computer program product, which includes: a computer program (also referred to as code, or instruction), which, when executed, enables a computer to execute the method executed by the terminal device side in any of the above embodiments.

[0221] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program (also referred to as code or instruction). When the computer program is executed, the computer executes the method executed by the terminal device side in any of the above embodiments.

[0222] The various implementation modes of the present application can be combined arbitrarily to achieve different technical effects.

[0223] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it 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 and executed on a computer, the process or function described in 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 a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. 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 includes one or more available media integrated. 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 (e.g., a solid-state disk (SSD)), etc.

[0224] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0225] In short, the above is only an embodiment of the technical solution of this application, and is not intended to limit the protection scope of this application. Any modification, equivalent replacement, improvement, etc. made according to the disclosure of this application shall be included in the protection scope of this application.

Claims

1. A method for blood pressure detection, characterized in that: Applied to electronic equipment; the method comprises: Acquire a first photoplethysmography (PPG) signal of a user, and determine a first electrocardiogram (ECG) signal of the user based on the first PPG signal; Performing peak detection on the first PPG signal and the first ECG to determine a first pulse transmission time of the user; A first quality detection is performed on the first ECG signal and the first pulse transmission time. If a result of the first quality detection is determined to be normal, a blood pressure value of the user is determined based on the first pulse transmission time.

2. The method according to claim 1, characterized in that The determining the blood pressure value of the user based on the first pulse transit time comprises: The first pulse transit time is input into a calibrated first blood pressure regression model, and the blood pressure value of the user is output.

3. The method according to claim 2, characterized in that The method further comprises: If the calibration result of the user is detected, the first blood pressure regression model is acquired based on the calibration result.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: If the calibration result of the user is not detected, obtaining calibration data of the user, wherein the calibration data includes a second PPG signal and a gold standard blood pressure value of the user; determining a second ECG signal of the user based on the second PPG signal, and determining a second pulse transit time of the user based on the second PPG signal and the second ECG signal; performing a second quality detection on the second ECG signal and the second pulse transmission time; If it is determined that the result of the second quality detection is normal, the second blood pressure regression model is calibrated based on the second pulse transmission time and the gold standard blood pressure value to determine the first blood pressure regression model.

5. The method according to any one of claims 1 to 4, characterized in that The first PPG signal includes M first R peaks, and the first ECG signal includes N second R peaks, where M and R are both integers greater than 0; and performing peak detection on the first PPG signal and the first ECG to determine the first pulse transmission time of the user includes: A first pulse transit time of the user is determined based on a time difference between the M first R peaks and the N second R peaks.

6. The method according to claim 5, characterized in that The first R peak is the R wave peak of the ECG signal; the second R peak is the pulse wave peak of the PPG signal.

7. The method according to claim 6, characterized in that The determining the first pulse transmission time of the user based on the time difference between the M first R peaks and the N second R peaks includes: Among the M R wave peaks and the N pulse wave peaks, determining the R wave peaks and pulse wave peaks that are adjacent in time sequence as a group; The first pulse transmission time is determined based on the time difference between each group of R wave peaks and the pulse wave peaks.

8. The method according to claim 6 or 7, characterized in that: The performing a first quality detection on the first ECG signal and the first pulse transmission time comprises: If the difference between M and N is greater than a preset first threshold, and the time difference between the M R wave peaks and the N pulse wave peaks is greater than a preset second threshold, the result of the first quality detection is determined to be normal.

9. The method according to claim 6 or 7, characterized in that: The performing a first quality detection on the first ECG signal and the first pulse transmission time comprises: If the difference between M and N is less than the first threshold, the result of the first quality detection is judged to be abnormal, and the user is prompted to retest; or, If the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold, the result of the first quality detection is determined to be an abnormal condition, and the user is prompted to retest.

10. The method according to any one of claims 1 to 9, characterized in that The determining a first electrocardiogram (ECG) signal based on the first PPG signal comprises: The first PPG signal is input into an electrocardiogram signal conversion model, and the first ECG signal is output.

11. The method according to claim 10, characterized in that The electrocardiogram signal conversion model is obtained by inputting Q third PPG signals as sample data in the server and training with a preset third ECG signal as a label, or is obtained by training in the server based on historical sample documents.

12. A blood pressure detection device, characterized in that: The device comprises: a first ECG signal determining unit, configured to obtain a first photoplethysmogram (PPG) signal of a user, and determine a first electrocardiogram (ECG) signal of the user based on the first PPG signal; a first pulse transit time determining unit, configured to perform peak detection on the first PPG signal and the first ECG signal to determine a first pulse transit time of the user; The blood pressure value determination unit is used to perform a first quality detection on the first ECG signal and the first pulse transmission time, and if the result of the first quality detection is determined to be normal, determine the blood pressure value of the user based on the first pulse transmission time.

13. The device according to claim 12, characterized in that The blood pressure value determination unit is specifically used for: The first pulse transit time is input into a calibrated first blood pressure regression model, and the blood pressure value of the user is output.

14. The device according to claim 13, characterized in that The device also includes: The first blood pressure regression model acquisition unit acquires the first blood pressure regression model based on the calibration result if the calibration result of the user is detected.

15. The device according to claim 13 or 14, characterized in that The device also includes: an acquisition calibration data unit, which acquires calibration data of the user if the calibration result of the user is not detected, wherein the calibration data includes a second PPG signal and a gold standard blood pressure value of the user; a second ECG signal determining unit, which determines a second ECG signal of the user based on the second PPG signal, and determines a second pulse transit time of the user based on the second PPG signal and the second ECG signal; a second pulse transit time determination unit, configured to perform a second quality detection on the second ECG signal and the second pulse transit time; The calibration unit calibrates the second blood pressure regression model based on the second pulse transmission time and the gold standard blood pressure value to determine the first blood pressure regression model if the result of the second quality detection is determined to be normal.

16. The device according to any one of claims 12 to 15, characterized in that The first PPG signal includes M first R peaks, the first ECG signal includes N second R peaks, and M and R are both integers greater than 0; the first pulse transmission time determination unit is specifically used to: A first pulse transit time of the user is determined based on a time difference between the M first R peaks and the N second R peaks.

17. The device according to claim 16, characterized in that The first R peak is the R wave peak of the ECG signal; the second R peak is the pulse wave peak of the PPG signal.

18. The device according to claim 17, characterized in that The first pulse transmission time determining unit is specifically configured to: Among the M R wave peaks and the N pulse wave peaks, determining the R wave peaks and pulse wave peaks that are adjacent in time sequence as a group; The first pulse transmission time is determined based on the time difference between each group of R wave peaks and the pulse wave peaks.

19. The device according to claim 17 or 18, characterized in that The blood pressure value determination unit is specifically used for: If the difference between M and N is greater than a preset first threshold, and the time difference between the M R wave peaks and the N pulse wave peaks is greater than a preset second threshold, the result of the first quality detection is determined to be normal.

20. The device according to claim 17 or 18, characterized in that The blood pressure value determination unit is specifically used for: If the difference between M and N is less than the first threshold, the result of the first quality detection is judged to be abnormal, and the user is prompted to retest; or, If the time difference between the M R wave peaks and the N pulse wave peaks is less than the second threshold, the result of the first quality detection is determined to be an abnormal condition, and the user is prompted to retest.

21. The device according to any one of claims 12 to 20, characterized in that The first ECG signal determining unit is specifically configured to: The first PPG signal is input into an electrocardiogram signal conversion model, and the first ECG signal is output.

22. The device according to claim 21, characterized in that The electrocardiogram signal conversion model is obtained by inputting Q third PPG signals as sample data in the server and training with a preset third ECG signal as a label, or is obtained by training in the server based on historical sample documents.

23. A computer storage medium, characterized in that The computer storage medium stores a computer program, which implements the method according to any one of claims 1 to 11 when executed by a processor.

24. A computer program, characterized in that The computer program comprises instructions, and when the computer program is executed by a computer, the computer is caused to perform the method according to any one of claims 1 to 11.

Images