Blood pressure detection method and device based on frequency modulated continuous wave radar and electronic equipment

Abstract

The invention provides a blood pressure detection method and device based on a frequency modulated continuous wave radar and electronic equipment, and can be applied to the technical field of signal processing. The method comprises the steps that a radar echo signal is acquired, and the radar echo signal is acquired at a preset height position away from a neck-chest area of a target object; performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals at different positions and angles in the neck-chest area; pulse wave time features and pulse wave clustering features of the pulse wave signals are extracted, the pulse wave time features represent phase information of pulse waves collected at different positions in the neck-chest area, and the pulse wave clustering features represent the similarity between the pulse waves collected at different angles in the neck-chest area; inputting the pulse wave time features and the pulse wave clustering features into a blood pressure detection network, and outputting a blood pressure detection result of the target object.

Description

Technical Field

[0001] The present disclosure relates to the field of signal processing technology, and more specifically, to a blood pressure detection method, device and electronic equipment based on frequency modulated continuous wave radar. Background Art

[0002] Blood pressure (BP) is an important indicator of overall health, especially related to the cardiovascular system. Blood pressure monitoring is very important for human health, especially the diagnosis and treatment of cardiovascular diseases. In recent years, the technological progress of radar technology in vital sign monitoring has provided a new solution for blood pressure monitoring, which has the ability to measure heart and aortic vibrations in a non-contact manner.

[0003] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related art: the blood pressure detection method in the related art has limitations in terms of comfort and reliability. Summary of the invention

[0004] In view of this, the present disclosure provides a blood pressure detection method, device and electronic device based on frequency modulated continuous wave radar.

[0005] One aspect of the present disclosure provides a blood pressure detection method based on frequency modulated continuous wave radar, comprising:

[0006] Acquiring a radar echo signal, wherein the radar echo signal is collected at a preset height position from the neck-chest region of the target object;

[0007] Performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals representing different positions and angles in the neck-chest region;

[0008] Extracting a pulse wave time feature and a pulse wave clustering feature of the pulse wave signal, wherein the pulse wave time feature represents the phase information of the pulse wave collected at different positions in the neck-chest region, and the pulse wave clustering feature represents the similarity between the pulse waves collected at different angles in the neck-chest region;

[0009] The pulse wave time feature and the pulse wave clustering feature are input into a blood pressure detection network, and the blood pressure detection result of the target object is output, wherein the blood pressure detection network is trained using radar echo sample signals and blood pressure label sample data.

[0010] According to an embodiment of the present disclosure, the pulse wave signal includes multiple pulse wave time features and pulse wave clustering features of the pulse wave signal, including:

[0011] According to the plurality of pulse wave signals, the pulse wave time feature is obtained using a pulse wave model, wherein the pulse wave model indicates that the pulse wave signals at different positions in the neck-chest region have the same period; and

[0012] According to the plurality of pulse wave signals, the pulse wave clustering features are obtained by using a morphology-based distance clustering method.

[0013] According to an embodiment of the present disclosure, the pulse wave time feature is obtained by using a pulse wave model based on the plurality of pulse wave signals, including:

[0014] Performing Fourier transform on the plurality of pulse wave signals using the pulse wave model to obtain fundamental wave phases and harmonic phases of the plurality of pulse wave signals; and

[0015] According to the heart rate of the target object, the fundamental wave phase and the harmonic phase of each of the plurality of pulse wave signals are converted to obtain the pulse wave time feature.

[0016] According to an embodiment of the present disclosure, the pulse wave clustering features are obtained by using a morphology-based distance clustering method based on the plurality of pulse wave signals, including:

[0017] Performing distance measurement on the plurality of the pulse wave signals to obtain distances between the plurality of the pulse wave signals;

[0018] Determining the centroid position of the neck-chest region of the target object based on the distances between the plurality of pulse wave signals; and

[0019] According to the centroid position of the neck-region, the pulse wave clustering feature of the neck-chest region is obtained.

[0020] According to an embodiment of the present disclosure, the pulse wave time feature and the pulse wave cluster feature are input into a blood pressure detection network, and the blood pressure detection result of the target object is output, including:

[0021] Input the pulse wave time feature into the pulse wave time flow network, and output the pulse wave time data;

[0022] Inputting the pulse wave clustering features into the pulse wave clustering flow network, and outputting the pulse wave morphology data; and

[0023] The pulse wave time data and the pulse wave morphology data are input into the multi-head attention layer and the fully connected layer, and the blood pressure detection result of the target object is output.

[0024] According to an embodiment of the present disclosure, the above-mentioned radar echo signal is subjected to beam focusing processing and phase demodulation processing to obtain pulse wave signals representing different positions and angles, including:

[0025] Performing Fourier transform on the radar echo signal to obtain radar distance signals representing different distances;

[0026] Performing beam focusing on the radar distance signal to obtain radar position signals representing different positions;

[0027] Performing circle fitting on the radar position signal to adjust the center position of the radar signal in the complex plane; and

[0028] The phase of the radar position signal after circle fitting is demodulated using a differential cross-multiplication algorithm to obtain the above-mentioned pulse wave signals representing different positions and angles.

[0029] According to an embodiment of the present disclosure, the above method further includes:

[0030] transmitting a detection signal to the target object using a frequency modulated continuous wave radar at a preset height from the neck-chest region of the target object; and

[0031] A reflection signal generated based on the detection signal is received to obtain the radar echo signal.

[0032] According to an embodiment of the present disclosure, the above method further includes:

[0033] Obtain the radar echo sample data and the blood pressure label data;

[0034] The initial blood pressure detection network is trained according to the radar echo sample signal and the blood pressure label data to obtain the blood pressure detection network.

[0035] Another aspect of the present disclosure provides a blood pressure detection device based on a frequency modulated continuous wave radar, comprising:

[0036] A first acquisition module is used to acquire a radar echo signal, wherein the radar echo signal is collected at a preset height position from the neck-chest area of ​​the target object;

[0037] A processing module, used for performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals representing different positions and angles in the neck-chest region;

[0038] An extraction module, used to extract the pulse wave time feature and the pulse wave clustering feature of the pulse wave signal, wherein the pulse wave time feature represents the phase information of the pulse wave collected at different positions in the neck-chest region, and the pulse wave clustering feature represents the similarity between the pulse waves collected at different angles in the neck-chest region;

[0039] The output module is used to input the above-mentioned pulse wave time characteristics and the above-mentioned pulse wave clustering characteristics into the blood pressure detection network, and output the blood pressure detection result of the above-mentioned target object, wherein the above-mentioned blood pressure detection network is trained using radar echo sample signals and blood pressure label sample data.

[0040] Another aspect of the present disclosure provides an electronic device, comprising:

[0041] one or more processors;

[0042] a memory for storing one or more programs,

[0043] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0044] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0045] Another aspect of the present disclosure provides a computer program product, which includes computer executable instructions, and when the instructions are executed, are used to implement the method as described above.

[0046] According to the embodiments of the present disclosure, by acquiring radar echo signals collected based on target objects, processing and extracting features of the radar echo signals, the pulse wave time features and the pulse wave clustering features are extracted, and the blood pressure detection results are obtained through a pre-trained blood pressure detection network, thereby avoiding the problem of inconvenience in real-time monitoring caused by measuring blood pressure in direct contact with the human body and avoiding the problem of causing discomfort to the human body, thereby improving the comfort of the human body and facilitating real-time monitoring of the human body's blood pressure, and at the same time obtaining the pulse wave time features and the pulse wave clustering features, thereby improving the reliability of blood pressure detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0048] Figure 1 Schematically illustrates an exemplary system architecture to which a blood pressure detection method, device, and electronic device based on a frequency modulated continuous wave radar can be applied according to an embodiment of the present disclosure;

[0049] Figure 2 The flowchart of the blood pressure detection method based on frequency modulated continuous wave radar according to the embodiment of the present disclosure is schematically shown;

[0050] Figure 3 A schematic diagram of a blood pressure detection method based on a frequency modulated continuous wave radar according to an embodiment of the present disclosure is schematically shown;

[0051] Figure 4 The structure diagram of the blood pressure detection network according to the embodiment of the present disclosure is schematically shown;

[0052] Figure 5 A block diagram schematically shows a blood pressure detection device based on a frequency modulated continuous wave radar according to an embodiment of the present disclosure; and

[0053] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0054] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0055] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0056] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0057] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0058] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0059] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0060] Commonly used ambulatory or continuous BP measurement methods, such as oscillometric BP monitors, arterial catheter placement, and constant volume method, are not suitable for long-term BP monitoring due to their invasiveness, discomfort, and possible interference with sleep. This has prompted researchers to explore unobtrusive, ambulatory, or continuous BP monitoring methods. These new methods can be roughly divided into two categories based on their principles: pulse transit time (PTT) and pulse wave analysis (PWA). PTT measures the delay between different positions of the pulse wave to correlate with BP, while PWA uses the shape, amplitude, and other characteristics of the pulse wave to estimate BP. Regardless of whether PTT or PWA methods are used, photoplethysmography (PPG) is the most commonly used method to obtain pulse waves. However, when finger PPG is used as the distal pulse wave for PTT calculation, the presence of smooth muscle in peripheral arteries, which is regulated by neurohumoral control mechanisms on a time scale of seconds to minutes, results in vascular characteristics that are not related to BP changes. Therefore, PTT-based PTT methods require frequent calibration. Furthermore, when PPG is used for PWA, the complex pressure-volume relationship as well as the effects of smooth muscle activity, sensor contact pressure, and ambient light limit its reliability.

[0061] In recent years, the widespread application of radar in vital sign monitoring has provided a new solution for non-invasive BP monitoring. Radar obtains pulse wave movement through the modulation of electromagnetic waves by the heart and arteries. Compared with PPG, radar directly obtains mechanical signals, avoiding volume-pressure conversion during BP measurement. At present, there are some radar-based blood pressure estimation methods, but some of them require contact measurement of pulse waves, some use additional contact sensors for multi-point pulse wave measurement, and some estimate BP values ​​through single-point pulse wave analysis, which has limitations in comfort and reliability.

[0062] In view of this, an embodiment of the present disclosure provides a blood pressure detection method based on a frequency modulated continuous wave radar, comprising acquiring a radar echo signal, wherein the radar echo signal is collected at a preset height position from the neck-chest region of a target object; performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain a pulse wave signal representing different positions and angles in the neck-chest region; extracting a pulse wave time feature and a pulse wave clustering feature of the pulse wave signal, wherein the pulse wave time feature represents the phase information of the pulse wave collected at different positions in the neck-chest region, and the pulse wave clustering feature represents the similarity between the pulse waves collected at different angles in the neck-chest region; inputting the pulse wave time feature and the pulse wave clustering feature into a blood pressure detection network, and outputting a blood pressure detection result of the target object, wherein the blood pressure detection network is trained using the radar echo sample signal and the blood pressure label sample data.

[0063] Figure 1 The exemplary system architecture 100 to which the blood pressure detection method, device and electronic device based on frequency modulated continuous wave radar can be applied according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0064] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0065] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only for example).

[0066] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0067] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0068] It should be noted that the blood pressure detection method based on frequency modulated continuous wave radar provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the blood pressure detection device based on frequency modulated continuous wave radar provided in the embodiment of the present disclosure can generally be set in the server 105. The blood pressure detection method based on frequency modulated continuous wave radar provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the blood pressure detection device based on frequency modulated continuous wave radar provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Alternatively, the blood pressure detection method based on frequency modulated continuous wave radar provided in the embodiment of the present disclosure may also be performed by the first terminal device 101, the second terminal device 102 or the third terminal device 103, or may also be performed by other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103. Accordingly, the blood pressure detection device based on frequency modulated continuous wave radar provided in the embodiment of the present disclosure may also be provided in the first terminal device 101, the second terminal device 102 or the third terminal device 103, or may be provided in other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0069] For example, the radar echo signal may be originally stored in any one of the first terminal device 101, the second terminal device 102 or the third terminal device 103 (for example, the first terminal device 101, but not limited thereto), or stored in an external storage device and may be imported into the first terminal device 101. Then, the first terminal device 101 may locally execute the blood pressure detection method based on the frequency modulated continuous wave radar provided in the embodiment of the present disclosure, or send the radar echo signal to other terminal devices, servers, or server clusters, and the other terminal devices, servers, or server clusters that receive the radar echo signal may execute the blood pressure detection method based on the frequency modulated continuous wave radar provided in the embodiment of the present disclosure.

[0070] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0071] Figure 2 The flowchart of the blood pressure detection method based on frequency modulated continuous wave radar according to an embodiment of the present disclosure is schematically shown.

[0072] like Figure 2 As shown, the blood pressure detection method based on FMCW radar includes operations S210 to S240.

[0073] In operation S210 , a radar echo signal is acquired, wherein the radar echo signal is collected at a preset height position from a neck-chest region of a target object.

[0074] In operation S220, beam focusing processing and phase demodulation processing are performed on the radar echo signal to obtain pulse wave signals representing different positions and angles in the neck-chest region.

[0075] In operation S230, a pulse wave time feature and a pulse wave clustering feature of the pulse wave signal are extracted, wherein the pulse wave time feature represents the phase information of the pulse wave collected at different positions in the neck-chest region, and the pulse wave clustering feature represents the similarity between the pulse waves collected at different angles in the neck-chest region.

[0076] In operation S240, the pulse wave time feature and the pulse wave clustering feature are input into a blood pressure detection network, and a blood pressure detection result of the target object is output, wherein the blood pressure detection network is trained using radar echo sample signals and blood pressure label sample data.

[0077] According to an embodiment of the present disclosure, the central artery in the neck-chest region of the target object can better reflect the blood pressure condition of the target user.

[0078] According to an embodiment of the present disclosure, beam focusing processing can extract position information from radar echo signals, and phase demodulation processing can extract angle information from radar echo signals, thereby obtaining pulse wave signals representing different positions and angles in the neck-chest region.

[0079] According to the embodiments of the present disclosure, the pulse wave generates vibrations at different locations on the body surface, so the vibrations on the body surface can reflect the transmission of the pulse wave, the phase information of the pulse wave can reflect the transmission speed of the pulse wave, and the pulse wave clustering features can reduce the complexity of the pulse wave signal.

[0080] According to the embodiments of the present disclosure, the accuracy of blood pressure monitoring can be improved by training a blood pressure detection network.

[0081] According to the embodiments of the present disclosure, by acquiring radar echo signals collected based on target objects, processing and extracting features of the radar echo signals, the pulse wave time features and the pulse wave clustering features are extracted, and the blood pressure detection results are obtained through a pre-trained blood pressure detection network, thereby avoiding the problem of inconvenience in real-time monitoring caused by measuring blood pressure in direct contact with the human body and avoiding the problem of causing discomfort to the human body, thereby improving the comfort of the human body and facilitating real-time monitoring of the human body's blood pressure, and at the same time obtaining the pulse wave time features and the pulse wave clustering features, thereby improving the reliability of blood pressure detection.

[0082] According to an embodiment of the present disclosure, a radar echo signal is subjected to beam focusing processing and phase demodulation processing to obtain a pulse wave signal representing different positions and angles, including: performing Fourier transform on the radar echo signal to obtain a radar distance signal representing different distances; performing beam focusing on the radar distance signal to obtain a radar position signal representing different positions; performing circle fitting on the radar position signal to adjust the center position of the radar signal in the complex plane; and performing phase demodulation on the radar position signal after circle fitting using a differential cross multiplication algorithm to obtain a pulse wave signal representing different positions and angles.

[0083] According to the embodiments of the present disclosure, the radar echo signal directly acquired cannot be used directly, and needs to be processed so that it can be turned into a pulse wave signal that can be analyzed.

[0084] According to an embodiment of the present disclosure, the radar echo signal will include signals from non-neck-chest areas. Since different distances from the target object correspond to different signals in the radar echo signal, by performing Fourier transform on each radar echo signal, signals at different distances can be distinguished, thereby screening out the radar distance signal from the neck-chest area.

[0085] According to an embodiment of the present disclosure, beam focusing is to separate signals at different locations, and T transmitting antennas and R antennas form M=T*R virtual arrays. The array of multiple virtual channels from a Range Bin can be expressed as:

[0086] (1)

[0087] Among them, t is the slow time index, which is across chirps. is the observation data vector, is the steering matrix, is the steering vector of length M, and are the target signal and noise vector respectively.

[0088] By applying different weights to different channels , the output is:

[0089] (2)

[0090] At this time, the output power of the array is:

[0091] (3)

[0092] in, represents the mathematical expectation, represents the Hermitian transpose, is the covariance matrix of the observed data.

[0093] In order to improve the clarity and separation of signals at different target locations without distortion, the Minimum Variance Distortionless Response (MVDR) design is adopted. of .

[0094] (4)

[0095] Solving this optimization problem by Lagrangian method, we finally get The optimal weight vector at is , then the signal at the target is .

[0096] Through this beam focusing step, we can separate the radar range signals from different positions and obtain the radar position signal.

[0097] According to an embodiment of the present disclosure, an ideal radar I / Q signal should form a circle or arc around the origin in the complex plane according to the size of the target displacement. Usually, breathing forms a circle, and the heartbeat during breath holding forms a small arc. However, the DC component caused by static objects will offset the center of the circle. Through the circle fitting algorithm, the center of the in-phase / quadrature (I / Q) can be adjusted back to the origin to ensure the correct shape of the dynamic electrocardiogram (DCG).

[0098] The cost function of the circle fitting algorithm can be expressed as:

[0099] (5)

[0100] in represents the candidate circle center, and represents the I / Q signal. The circle fitting problem is solved by minimizing to solve.

[0101] According to an embodiment of the present disclosure, a change in the signal phase can represent a slight change in the target displacement. Typically, arctan transform is used to demodulate the phase value from the I / Q signal. However, this demodulated phase may be affected by phase ambiguity. Although unwrapping can alleviate this problem to a certain extent, there is still error accumulation, resulting in baseline drift in the signal. Therefore, the improved differential cross multiplication (MDACM) algorithm is used for I / Q phase demodulation to obtain a more stable pulse wave signal while enhancing the heartbeat component in the signal.

[0102] The MDACM algorithm is expressed as follows:

[0103] (6)

[0104] After the above radar echo processing steps, pulse wave signals representing different positions and angles are obtained.

[0105] According to an embodiment of the present disclosure, a pulse wave signal includes multiple pulse wave time features and pulse wave clustering features of the pulse wave signal are extracted, including: based on the multiple pulse wave signals, the pulse wave time features are obtained using a pulse wave model, wherein the pulse wave model characterizes that pulse wave signals at different positions in the neck-chest region have the same period; based on the multiple pulse wave signals, the pulse wave clustering features are obtained using a morphology-based distance clustering method.

[0106] According to an embodiment of the present disclosure, the plurality of pulse wave signals may be signals generated by pulses at different locations in the neck-chest region.

[0107] According to the embodiments of the present disclosure, the pulse wave signal can be a signal with a similar shape but not completely the same. The fundamental wave and period of the pulse wave signals at different positions are the same, but the phases are different. Different phases represent the speed of pulse wave transmission. Therefore, a pulse wave model can be established, and the pulse wave signal can be analyzed through pulse wave analysis to extract the pulse wave time feature. The pulse wave time feature can also be called the PTT feature.

[0108] According to the embodiments of the present disclosure, multiple similar pulse wave signals are collected in the neck-chest region. To reduce the workload, pulse wave signals with high similarity can be clustered to obtain pulse wave clustering features. Pulse wave clustering features can also be called PWA features.

[0109] According to an embodiment of the present disclosure, a pulse wave model is used to obtain a pulse wave time feature based on multiple pulse wave signals, including: performing Fourier transform on the multiple pulse wave signals using the pulse wave model to obtain the fundamental wave phase and harmonic phase of each of the multiple pulse wave signals; and converting the fundamental wave phase and harmonic phase of each of the multiple pulse wave signals according to the heart rate of the target object to obtain the pulse wave time feature.

[0110] According to the embodiments of the present disclosure, it is unrealistic to directly locate feature points from multiple pulse wave signals to calculate PTT, because the pulse wave signals obtained by radar have a low signal-to-noise ratio and the morphology of different pulse wave signals varies greatly. Therefore, the present disclosure proposes to extract PTT features by constructing a harmonic phase array of multi-position pulse waves.

[0111] First, the pulse wave at any position i in the neck-chest region is modeled as:

[0112] (7)

[0113] in, It is a quasi-periodic signal with a heart rate cycle, representing the pulse wave shape of each heartbeat, which may vary with position. and are the scale factor and the offset factor, respectively, which also vary with position. It is caused by PTT. Through Fourier series expansion (FSD), this quasi-periodic signal can be decomposed into the sum of sine and cosine, each of which represents the fundamental frequency and harmonic components of the pulse wave signal. The complex exponential expression of the pulse wave signal is:

[0114] (8)

[0115] The amplitude and phase shift of the nth harmonic component of the pulse wave signal are expressed as and It is worth noting that in this case, Changes in form can be made by and to identify the changes.

[0116] For a given pulse wave signal The processing steps are as follows: First, A Hamming window is applied. After this, a Fourier transform is performed to obtain the phase of various harmonic frequencies of the heart rate, written as:

[0117] (9)

[0118] The pulse wave is not a perfect sine wave, so each pulse wave signal has harmonics, phase In heart rate The subharmonics can be expressed as:

[0119] (10)

[0120] in, and Respectively The imaginary and real parts of .

[0121] By performing these operations on the pulse wave signal of each part, the fundamental wave phase and harmonic phase of each of the multiple pulse wave signals can be obtained, and the following array can be obtained:

[0122] (11)

[0123] Further, each The conversion to time-related quantities is done by the following heart rate-related operations:

[0124] (12)

[0125] in, Indicates the target subject's heart rate.

[0126] According to an embodiment of the present disclosure, based on multiple pulse wave signals, pulse wave clustering features are obtained using a morphology-based distance clustering method, including: performing distance measurement on multiple pulse wave signals to obtain the distance between the multiple pulse wave signals; determining the center of mass position of the neck-chest region of the target object based on the distance between the multiple pulse wave signals; and obtaining the pulse wave clustering features of the neck-chest region based on the center of mass position of the neck-region.

[0127] According to an embodiment of the present disclosure, in order to avoid the occurrence of dimensionality disaster, the data input to the model needs to reduce the dimension, but at the same time, information should not be lost. We expect to extract a few channels from multiple DCGs as subsequent model inputs. However, the shapes of pulse wave signals at different positions are different. If they are directly averaged, the signal morphology will be unexpectedly distorted. If one wave is extracted based on simple rules such as signal quality, it is difficult to contain the desired information. The present disclosure reduces the dimensionality of the pulse wave signals in the pulse wave array by dividing them into several clusters. The k-Shape clustering is used to adapt to the characteristics of the pulse wave by the scale invariance and translation invariance of time series data. The distance measurement method is the shape-based distance (Shape-Based Distance, SBD):

[0128] (13)

[0129] SBD describes the distance between x and y after eliminating the effect of sequence shift. The clustering process of k-Shape is similar to k-means, iteratively classifying samples to the nearest centroid, where the centroid is calculated according to the following formula:

[0130] (14)

[0131] Finally, the cluster containing the most samples in the neck area and chest area (such as corresponding to radar angles of 85-95 degrees and 110-120 degrees) is selected as the required cluster, and the centroids corresponding to these two clusters are selected as the final output of this step.

[0132] Figure 3 A schematic diagram of a blood pressure detection method based on a frequency modulated continuous wave radar according to an embodiment of the present disclosure is schematically shown.

[0133] like Figure 3 As shown, a detection signal is transmitted to the target object by using a frequency modulated continuous wave (FMCW) radar at a preset height from the neck-chest region of the target object; a reflection signal generated based on the detection signal is received to obtain a radar echo signal.

[0134] According to an embodiment of the present disclosure, a multi-antenna (MIMO) FMCW radar may be used to collect radar echo signals at a certain distance above the neck-chest region of the target object.

[0135] When the target object is at rest, the surface motion of a certain body position can be modeled as:

[0136] (15)

[0137] in, is the distance between the radar and the target object's body at time t, is the reference distance, and and It's breathing and heartbeat. contribution.

[0138] The principle of FMCW radar to obtain body surface vibration signals is that FMCW radar transmits electromagnetic waves (chirp signals) with linearly increasing frequencies. These signals are modulated by the movement of the human body surface and then received by the radar. The FMCW radar transmits and receives signals and mixes them to obtain an intermediate frequency signal:

[0139] (16)

[0140] in, It is a fast time index, that is, the time within a chirp. and are radar transmitting signal and receiving signal respectively. Indicates the distance between the radar and the surface of the target object. is the path loss. and They are the chirp start frequency and chirp slope of the FMCW signal respectively.

[0141] According to an embodiment of the present disclosure, the collected radar echo signal is subjected to Fourier transform, beam focusing processing, circle fitting processing and demodulation processing to obtain a pulse wave signal, and feature extraction is performed on the pulse wave signal to obtain PTT features and PWA features, which are then input into a blood pressure detection network.

[0142] Figure 4 The structural diagram of the blood pressure detection network according to the embodiment of the present disclosure is schematically shown.

[0143] like Figure 4 As shown, the pulse wave time feature is input into the pulse wave time flow network, and the pulse wave time data is output; the pulse wave clustering feature is input into the pulse wave clustering flow network, and the pulse wave morphology data is output; the pulse wave time data and the pulse wave morphology data are input into the multi-head attention layer and the fully connected layer, and the blood pressure detection result of the target object is output.

[0144] The PTT stream adopts a BiLSTM structure to explore the temporal relationship between phase differences at different locations, while the PWA stream uses 1D-CNN to capture the morphological information of the pulse wave. The subsequent key feature integration is through a multi-head attention layer followed by two fully connected layers to estimate the values ​​of systolic blood pressure (SBP) and diastolic blood pressure (DBP).

[0145] According to an embodiment of the present disclosure, the blood pressure detection method based on frequency modulated continuous wave radar also includes: acquiring radar echo sample data and blood pressure label data; training an initial blood pressure detection network according to the radar echo sample signal and the blood pressure label data to obtain a blood pressure detection network.

[0146] According to an embodiment of the present disclosure, the loss function used when training the initial blood pressure detection network is a weighted Huber loss, which is used to reduce the sensitivity to outliers and the over-representation of blood pressure values ​​with a higher frequency:

[0147] (17)

[0148] The Huber loss function works as follows: With the predicted value The difference is less than When , the standard mean square error is used to calculate the loss. If the difference exceeds , the linear absolute error loss function is used. In addition, the loss function The weight in It is determined based on the distribution of BP intervals in the dataset, with each 10 mmHg segment defining an interval:

[0149] (18)

[0150] in Indicates The number of samples in a BP interval. is the smoothing factor, controlling the degree of smoothing in the weight distribution.

[0151] Finally, the systolic and diastolic pressures are optimized simultaneously, and the final loss function is:

[0152] (19)

[0153] The present disclosure provides a non-contact blood pressure detection method based on frequency modulated continuous wave radar. The method only requires a single FMCW radar, can realize pulse wave measurement of multiple parts, and focuses on the central artery pulse wave instead of the peripheral artery; in addition, the method combines the feature construction guided by physiological knowledge and the feature extraction capability of the deep learning model to realize accurate and robust blood pressure estimation.

[0154] Figure 5 The block diagram of a blood pressure detection device based on a frequency modulated continuous wave radar according to an embodiment of the present disclosure is schematically shown.

[0155] like Figure 5 As shown, the blood pressure detection device 500 based on FMCW radar includes a first acquisition module 510 , a processing module 520 , an extraction module 530 and an output module 540 .

[0156] A first acquisition module 510 is used to acquire a radar echo signal, wherein the radar echo signal is collected at a preset height position from the neck-chest region of the target object;

[0157] The processing module 520 is used to perform beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals representing different positions and angles in the neck-chest area;

[0158] An extraction module 530 is used to extract a pulse wave time feature and a pulse wave clustering feature of the pulse wave signal, wherein the pulse wave time feature represents the phase information of the pulse wave collected at different positions in the neck-chest region, and the pulse wave clustering feature represents the similarity between the pulse waves collected at different angles in the neck-chest region;

[0159] The output module 540 is used to input the pulse wave time feature and the pulse wave clustering feature into the blood pressure detection network, and output the blood pressure detection result of the target object, wherein the blood pressure detection network is trained using the radar echo sample signal and the blood pressure label sample data.

[0160] According to an embodiment of the present disclosure, the pulse wave signal includes multiple, and the extraction module 530 for extracting the pulse wave time feature and the pulse wave clustering feature of the pulse wave signal includes:

[0161] A first extraction unit is used to obtain a pulse wave time feature based on a plurality of pulse wave signals using a pulse wave model, wherein the pulse wave model indicates that pulse wave signals at different positions in the neck-chest region have the same period; and

[0162] The second extraction unit is used to obtain pulse wave clustering features according to multiple pulse wave signals by using a morphology-based distance clustering method.

[0163] According to an embodiment of the present disclosure, a first extraction unit for obtaining a pulse wave time feature using a pulse wave model according to a plurality of pulse wave signals includes:

[0164] A first extraction subunit is used to perform Fourier transform on multiple pulse wave signals using a pulse wave model to obtain fundamental wave phases and harmonic phases of the multiple pulse wave signals; and

[0165] The second extraction subunit is used to convert the fundamental wave phase and the harmonic phase of each of the multiple pulse wave signals according to the heart rate of the target object to obtain the pulse wave time feature.

[0166] According to an embodiment of the present disclosure, a second extraction unit for obtaining pulse wave clustering features based on a plurality of pulse wave signals by using a morphology-based distance clustering method comprises:

[0167] A third extraction subunit is used to measure the distance between the multiple pulse wave signals to obtain the distance between the multiple pulse wave signals;

[0168] a fourth extraction subunit, configured to determine a centroid position in a neck-chest region of the target object based on distances between the plurality of pulse wave signals; and

[0169] The first extraction subunit is used to obtain the pulse wave clustering features of the neck-chest region according to the centroid position of the neck-region.

[0170] According to an embodiment of the present disclosure, the output module 540 for inputting the pulse wave time feature and the pulse wave clustering feature into the blood pressure detection network and outputting the blood pressure detection result of the target object includes:

[0171] A first output unit, used for inputting the pulse wave time feature into the pulse wave time flow network and outputting the pulse wave time data;

[0172] a second output unit, configured to input the pulse wave clustering features into the pulse wave clustering flow network and output pulse wave morphology data; and

[0173] The second output unit is used to input the pulse wave time data and the pulse wave morphology data into the multi-head attention layer and the fully connected layer, and output the blood pressure detection result of the target object.

[0174] According to an embodiment of the present disclosure, the processing module 520 for performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain the pulse wave signal representing different positions and angles includes:

[0175] A first processing unit is used to perform Fourier transform on the radar echo signal to obtain radar range signals representing different distances;

[0176] A second processing unit is used to perform beam focusing on the radar distance signal to obtain radar position signals representing different positions;

[0177] A third processing unit is used to perform circle fitting on the radar position signal to adjust the center position of the radar signal in the complex plane; and

[0178] The fourth processing unit is used to perform phase demodulation on the radar position signal after circle fitting by using a differential cross-multiplication algorithm to obtain pulse wave signals representing different positions and angles.

[0179] According to an embodiment of the present disclosure, the above-mentioned device 500 further includes:

[0180] a transmitting module for transmitting a detection signal to the target object using a frequency modulated continuous wave radar at a preset height from the neck-chest region of the target object; and

[0181] The obtaining module is used to receive the reflection signal generated based on the detection signal to obtain the radar echo signal.

[0182] According to an embodiment of the present disclosure, the above-mentioned device 500 further includes:

[0183] The second acquisition module is used to acquire radar echo sample data and blood pressure label data;

[0184] The training module is used to train the initial blood pressure detection network according to the radar echo sample signal and the blood pressure label data to obtain the blood pressure detection network.

[0185] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0186] For example, any multiple of the first acquisition module 510, the processing module 520, the extraction module 530, and the output module 540 can be combined in one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the first acquisition module 510, the processing module 520, the extraction module 530, and the output module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, at least one of the first acquisition module 510 , the processing module 520 , the extraction module 530 , and the output module 540 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0187] It should be noted that the blood pressure detection device part based on frequency modulated continuous wave radar in the embodiment of the present disclosure corresponds to the blood pressure detection method part based on frequency modulated continuous wave radar in the embodiment of the present disclosure. The description of the blood pressure detection device part based on frequency modulated continuous wave radar specifically refers to the blood pressure detection method part based on frequency modulated continuous wave radar, which will not be repeated here.

[0188] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0189] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0190] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0191] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0192] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0193] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0194] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0195] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0196] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the blood pressure detection method based on frequency modulated continuous wave radar provided by the embodiment of the present disclosure.

[0197] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0198] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0199] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0200] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0201] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A blood pressure detection method based on frequency modulated continuous wave radar, comprising: Acquiring a radar echo signal, wherein the radar echo signal is collected at a preset height position from a neck-chest region of the target object; Performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals representing different positions and angles in the neck-chest region; Extracting a pulse wave time feature and a pulse wave clustering feature of the pulse wave signal, wherein the pulse wave time feature represents phase information of the pulse waves collected at different positions in the neck-chest region, and the pulse wave clustering feature represents similarity between the pulse waves collected at different angles in the neck-chest region; and The pulse wave time feature and the pulse wave clustering feature are input into a blood pressure detection network, and a blood pressure detection result of the target object is output, wherein the blood pressure detection network is trained using radar echo sample signals and blood pressure label sample data.

2. The method according to claim 1, wherein: The pulse wave signal includes a plurality of pulse wave time features and pulse wave clustering features of the pulse wave signal, including: According to the plurality of pulse wave signals, the pulse wave time characteristic is obtained using a pulse wave model, wherein the pulse wave model indicates that the pulse wave signals at different positions in the neck-chest region have the same period; and According to the plurality of pulse wave signals, the pulse wave clustering features are obtained by utilizing a morphology-based distance clustering method.

3. The method according to claim 2, wherein: The step of obtaining the pulse wave time feature using a pulse wave model according to the plurality of pulse wave signals comprises: Performing Fourier transform on the plurality of pulse wave signals using the pulse wave model to obtain fundamental wave phases and harmonic phases of the plurality of pulse wave signals; and According to the heart rate of the target object, the fundamental wave phase and the harmonic phase of each of the plurality of pulse wave signals are converted to obtain the pulse wave time feature.

4. The method according to claim 2, wherein: The step of obtaining the pulse wave clustering features by using a morphology-based distance clustering method based on the plurality of pulse wave signals includes: Performing distance measurement on the plurality of pulse wave signals to obtain distances between the plurality of pulse wave signals; Determining the centroid position of the neck-chest region of the target object based on the distances between the plurality of pulse wave signals; as well as The pulse wave clustering features of the neck-chest region are obtained according to the centroid position of the neck-region.

5. The method according to any one of claims 1 to 4, wherein The step of inputting the pulse wave time feature and the pulse wave clustering feature into a blood pressure detection network and outputting the blood pressure detection result of the target object comprises: Inputting the pulse wave time feature into the pulse wave time flow network, and outputting the pulse wave time data; Inputting the pulse wave clustering features into a pulse wave clustering flow network, and outputting pulse wave morphology data; and The pulse wave time data and the pulse wave morphology data are input into the multi-head attention layer and the fully connected layer, and the blood pressure detection result of the target object is output.

6. The method according to any one of claims 1 to 4, wherein The performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals representing different positions and angles includes: Performing Fourier transform on the radar echo signal to obtain radar distance signals representing different distances; Performing beam focusing on the radar distance signal to obtain radar position signals representing different positions; Performing circle fitting on the radar position signal to adjust the center position of the radar signal in the complex plane; and The radar position signal after circle fitting is phase demodulated by using a differential cross-multiplication algorithm to obtain the pulse wave signals representing different positions and angles.

7. The method according to any one of claims 1 to 4, further comprising: transmitting a detection signal to the target object using a frequency modulated continuous wave radar at a preset height from the neck-chest region of the target object; as well as A reflection signal generated based on the detection signal is received to obtain the radar echo signal.

8. The method according to any one of claims 1 to 4, further comprising: Acquire the radar echo sample data and the blood pressure label data; as well as The initial blood pressure detection network is trained according to the radar echo sample signal and the blood pressure label data to obtain the blood pressure detection network.

9. A blood pressure detection device based on frequency modulated continuous wave radar, comprising: A first acquisition module, configured to acquire a radar echo signal, wherein the radar echo signal is collected at a preset height position from a neck-chest region of a target object; A processing module, used for performing beam focusing processing and phase demodulation processing on the radar echo signal to obtain pulse wave signals representing different positions and angles in the neck-chest region; an extraction module, configured to extract a pulse wave time feature and a pulse wave clustering feature of the pulse wave signal, wherein the pulse wave time feature represents phase information of pulse waves collected at different positions in the neck-chest region, and the pulse wave clustering feature represents similarities between pulse waves collected at different angles in the neck-chest region; and The output module is used to input the pulse wave time feature and the pulse wave clustering feature into a blood pressure detection network, and output the blood pressure detection result of the target object, wherein the blood pressure detection network is trained using radar echo sample signals and blood pressure label sample data.

10. An electronic device comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

Images