Method and device for detecting continuous blood pressure with assistance of double radars based on physiological guidance

Abstract

The invention provides a physiological guidance-based double-radar-assisted continuous blood pressure detection method and device, and is applied to the technical field of electromagnetic induction. The method comprises the steps that multiple cardiac pulse signals of a target object are obtained, and the multiple cardiac pulse signals represent mixed signals of multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals; target signals are determined from the multiple cardiac pulse signals, and the target signals represent the cardiac pulse signals with the fundamental frequency definition larger than a preset definition threshold value; performing physiological feature extraction processing on the target signal to obtain physiological feature information of the target object; feature extraction is conducted on the physiological feature information and the target signal through a continuous blood pressure prediction generation model, a first feature and a second feature are obtained, the first feature represents a four-dimensional feature corresponding to systolic pressure, and the second feature represents an eight-dimensional feature corresponding to diastolic pressure; and performing feature fusion processing on the first feature and the second feature to obtain the target continuous blood pressure.

Description

Technical Field

[0001] The present invention relates to the field of electromagnetic induction technology, and more particularly to a method and device for dual-radar assisted continuous blood pressure detection based on physiological guidance. Background Art

[0002] Continuous blood pressure monitoring is an important auxiliary tool for early cardiovascular risk management. Currently, wearable sensors are often used for continuous monitoring of a person's blood pressure, but these sensors pose a risk of irritation to the person's skin. Therefore, non-contact radar systems can be used to continuously monitor a person's blood pressure.

[0003] In the process of realizing the above-mentioned inventive concept, it was found through research that in the related technology, in the process of using a single-point non-contact radar to perform continuous auxiliary monitoring of the target's blood pressure, due to the problems of physiological noise, signal separation and low measurement resolution, it is difficult to perform high-reliability continuous blood pressure monitoring of the target. In addition, in the process of obtaining physiological information, it is difficult to apply the hemodynamic mechanism to the analysis process, resulting in the technical problem of difficulty in performing high-accuracy continuous blood pressure monitoring of the target. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method and device for dual radar assisted continuous blood pressure detection based on physiological guidance.

[0005] According to a first aspect of the present invention, a method for dual-radar assisted detection of continuous blood pressure based on physiological guidance is provided, comprising: acquiring multiple cardiac pulse signals of a target object, wherein the multiple cardiac pulse signals represent a mixed signal of multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals; determining a target signal from the multiple cardiac pulse signals, wherein the target signal represents a cardiac pulse signal having a fundamental frequency clarity greater than a predetermined clarity threshold; performing physiological feature extraction processing on the target signal to obtain physiological feature information of the target object; performing feature extraction on the physiological feature information and the target signal using a continuous blood pressure prediction generation model to obtain a first feature and a second feature, wherein the first feature represents a four-dimensional feature corresponding to the systolic pressure, and the second feature represents an eight-dimensional feature corresponding to the diastolic pressure; performing feature fusion processing on the first feature and the second feature to obtain a target continuous blood pressure, wherein the target continuous blood pressure represents the continuous changes in the systolic and diastolic pressures of the target object within a predetermined time period.

[0006] The second aspect of the present invention provides a device for dual-radar assisted detection of continuous blood pressure based on physiological guidance, including: an acquisition module for acquiring multiple cardiac pulse signals of a target object, wherein the multiple cardiac pulse signals represent a mixed signal of multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals; a determination module for determining a target signal from the multiple cardiac pulse signals, wherein the target signal represents a cardiac pulse signal with a fundamental frequency clarity greater than a predetermined clarity threshold; a first extraction module for performing physiological feature extraction processing on the target signal to obtain physiological feature information of the target object; a second extraction module for performing feature extraction on the physiological feature information and the target signal using a continuous blood pressure prediction generation model to obtain a first feature and a second feature, wherein the first feature represents a four-dimensional feature corresponding to the systolic pressure, and the second feature represents an eight-dimensional feature corresponding to the diastolic pressure; a fusion module for performing feature fusion processing on the first feature and the second feature to obtain a target continuous blood pressure, wherein the target continuous blood pressure represents the continuous changes in the systolic and diastolic pressures of the target object within a predetermined time period.

[0007] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0008] A fourth aspect of the present invention further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above method.

[0009] The fifth aspect of the present invention further provides a computer program product, comprising a computer program, which implements the above method when executed by a processor.

[0010] According to the method and device for dual-radar assisted continuous blood pressure detection based on physiological guidance of the present invention, multiple cardiac artery pulse signals including multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals are first obtained, and then multiple target signals are extracted from the multiple cardiac artery pulse signals based on the fundamental frequency clarity and a predetermined clarity threshold of each cardiac artery pulse signal. This achieves the goal of obtaining high-quality target signals from the original radar signal full of noise and interference by using the fundamental frequency clarity of each signal as the screening criterion and through multiple rounds of algorithms from the multiple cardiac artery pulse signals, so as to facilitate the extraction of more accurate physiological feature information from the high-quality target signals.

[0011] According to an embodiment of the present invention, the target signal is then subjected to physiological feature extraction processing, and relevant physiological feature information such as the target object's current accurate beat-to-beat interval sequence, pulse arrival time series, and respiratory signal is extracted from the target signal. The accurate physiological feature information and high-quality target signal are then input into a pre-trained continuous blood pressure prediction generation model. The continuous blood pressure prediction generation model is used to perform multi-resolution feature extraction on the extracted accurate physiological feature information and high-quality target signal, thereby obtaining first features corresponding to systolic pressure and second features corresponding to diastolic pressure at different granularities and levels. Feature fusion processing such as upsampling is performed on the first and second features of different dimensions to obtain fused features, which are then decoded to restore the target continuous blood pressure predicted for the target object. By utilizing a dual radar detection system, multi-dimensional feature capture and feature analysis extraction of chest and neck signals after interference noise processing are achieved. A comprehensive analysis is conducted from multiple perspectives such as hemodynamics and cardiac dynamics. Based on accurate physiological characteristic information, an optimized and highly robust continuous blood pressure prediction model is used to generate the prediction. Multiple feature separations, extractions, and fusions are then performed on the physiological characteristic information extracted once, thereby fully fusing and predicting the features corresponding to diastolic pressure and systolic pressure, and obtaining a target continuous blood pressure with high accuracy and reliability. This can then assist relevant professionals in subsequent processing, improving processing efficiency while saving costs.

[0012] According to embodiments of the present invention, further, by subjecting the continuous blood pressure prediction model to extensive model learning and training, the trained continuous blood pressure prediction model can perform multiple rounds of feature extraction and fusion processing on the input physiological information and target signal, deeply exploring and analyzing the relationship between systolic pressure and neck and chest signals, as well as the relationship between diastolic pressure, respiratory sinus arrhythmia, and changes in thoracic pressure, which are hidden in the physiological feature information and target signal. This allows the target continuous blood pressure to be accurately generated based on features from different dimensions, resulting in a continuous blood pressure prediction model with high robustness, reliability, efficiency, and output accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0014] Figure 1 A diagram showing an application scenario of a method for dual-radar assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown;

[0015] Figure 2A flow chart of a method for dual radar assisted detection of continuous blood pressure based on physiological guidance according to an embodiment of the present invention is shown;

[0016] Figure 3 A schematic diagram showing a method for dual radar-assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown;

[0017] Figure 4 A schematic diagram illustrating processing physiological characteristic information and target signals using a continuous blood pressure prediction generation model according to an embodiment of the present invention is shown;

[0018] Figure 5a A schematic diagram showing a comparison between the result output by the method of the present invention and the actual continuous blood pressure according to the first embodiment of the present invention;

[0019] Figure 5b A schematic diagram showing a comparison between the result output by the method of the present invention and the actual continuous blood pressure according to the second embodiment of the present invention;

[0020] Figure 5c A schematic diagram showing a comparison between a result output by the method of the present invention and actual continuous blood pressure according to a third embodiment of the present invention is shown;

[0021] Figure 5d A schematic diagram showing a comparison between a result output by the method of the present invention and actual continuous blood pressure according to a fourth embodiment of the present invention is shown;

[0022] Figure 5e A schematic diagram showing a comparison between a result output by the method of the present invention and actual continuous blood pressure according to a fifth embodiment of the present invention is shown;

[0023] Figure 5f A schematic diagram showing a comparison between a result output by the method of the present invention and actual continuous blood pressure according to a sixth embodiment of the present invention is shown;

[0024] Figure 5g A schematic diagram showing a comparison between a result output by the method of the present invention and actual continuous blood pressure according to a seventh embodiment of the present invention is shown;

[0025] Figure 5h A schematic diagram showing a comparison between a result output by the method of the present invention and actual continuous blood pressure according to an eighth embodiment of the present invention is shown;

[0026] Figure 6 A structural block diagram of a device for dual-radar assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown;

[0027] Figure 7A block diagram of an electronic device illustrating a method for dual radar-assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present invention 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 invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. 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 concept of the present invention.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the presence of the features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0030] All terms used herein (including technical and scientific terms) 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.

[0031] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning 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.).

[0032] In the technical solution of the present invention, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] In recent years, continuous blood pressure collection and monitoring has become an important adjunct to early cardiovascular risk management. Continuous systolic blood pressure (SBP) and diastolic blood pressure (DBP) monitoring offers substantial benefits for target guidance, particularly assisting personnel in cardiovascular risk assessment and personalized medication management.

[0034] Related technologies can utilize wearable sensors for continuous supplemental monitoring of a subject's blood pressure. However, wearable sensors carry the risk of irritating the subject's skin, potentially causing problems beyond blood pressure. Alternatively, non-contact radar can be used for continuous supplemental monitoring of a subject's blood pressure. These methods primarily rely on single-channel peripheral waveform analysis, neglecting complex hemodynamic interactions. For example, changes in compensatory peripheral resistance in hypotensive patients can lead to waveform distortion and other changes. Furthermore, due to propagation characteristics, pulse signals acquired by radar are more susceptible to physiological noise. Multi-point peripheral arterial wave analysis is a current analytical approach that bridges non-contact sensing with clinical-grade hemodynamic monitoring. This analysis estimates pulse transit time, which becomes less sensitive to noise as blood flow distance increases, enabling estimation of pulse velocity. Furthermore, these methods struggle to fully utilize the rich physiological information contained in radar signals. Most employ end-to-end prediction models, ignoring hemodynamic mechanisms or requiring individual calibration of the estimated results. During the research and development process, it was found that in the related technology, when using a single-point non-contact radar to perform continuous auxiliary monitoring of the target's blood pressure, due to problems such as physiological noise, signal separation and low measurement resolution, it is difficult to perform high-reliability continuous blood pressure monitoring of the target. In addition, in the process of obtaining physiological information, it is difficult to apply the hemodynamic mechanism to the analysis process, resulting in technical problems that make it difficult to perform high-accuracy continuous blood pressure monitoring of the target.

[0035] In view of this, an embodiment of the present invention provides a method for dual-radar assisted detection of continuous blood pressure based on physiological guidance, including: acquiring multiple cardiac pulse signals of a target object, wherein the multiple cardiac pulse signals represent a mixed signal of multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals; determining a target signal from the multiple cardiac pulse signals, wherein the target signal represents a cardiac pulse signal with a fundamental frequency clarity greater than a predetermined clarity threshold; performing physiological feature extraction processing on the target signal to obtain physiological feature information of the target object; using a continuous blood pressure prediction generation model to perform feature extraction on the physiological feature information and the target signal to obtain a first feature and a second feature, wherein the first feature represents a four-dimensional feature corresponding to the systolic pressure, and the second feature represents an eight-dimensional feature corresponding to the diastolic pressure; performing feature fusion processing on the first feature and the second feature to obtain a target continuous blood pressure, wherein the target continuous blood pressure represents the continuous changes in the systolic and diastolic pressures of the target object within a predetermined time period.

[0036] Figure 1 A diagram showing an application scenario of a method for dual-radar assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown.

[0037] like Figure 1 As shown, the application scenario according to this embodiment may include a first radar device 101, a second radar device 102, a target object 103, and a receiver 104. The first radar device 101 and the second radar device 102 are used to send electromagnetic wave signals to the target object 103.

[0038] The user may use the first radar device 101 and the second radar device 102 to interact with the target object 103 and the receiver 104 to receive or send signals, etc.

[0039] Receiver 104 may be a receiver for receiving various electromagnetic echo signals, such as receiving and processing electromagnetic echo signals transmitted by first radar device 101 and second radar device 102 (for example only). Receiver 104 may analyze and process received electromagnetic echo signals and other data, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal device.

[0040] It should be noted that the method for dual-radar assisted detection of continuous blood pressure based on physiological guidance provided in the embodiment of the present invention can generally be performed by the receiver 104. Accordingly, the device for dual-radar assisted detection of continuous blood pressure based on physiological guidance provided in the embodiment of the present invention can generally be set in the receiver 104. The method for dual-radar assisted detection of continuous blood pressure based on physiological guidance provided in the embodiment of the present invention can also be performed by a receiver or a receiver cluster that is different from the receiver 104 and can communicate with the first radar device 101, the second radar device 102 and / or the receiver 104. Accordingly, the device for dual-radar assisted detection of continuous blood pressure based on physiological guidance provided in the embodiment of the present invention can also be set in a receiver or a receiver cluster that is different from the receiver 104 and can communicate with the first radar device 101, the second radar device 102 and / or the receiver 104.

[0041] It should be understood that Figure 1 The number of the first radar device, the second radar device, the target object, and the receiver in FIG is merely illustrative. Any number of radar devices, target objects, and receivers may be provided according to implementation requirements.

[0042] The following will be based on Figure 1 The scene described by Figure 2~Figure 5h The method for dual-radar assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is described in detail.

[0043] Figure 2 A flow chart of a method for dual-radar assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown.

[0044] like Figure 2 As shown, the method for dual-radar assisted continuous blood pressure detection based on physiological guidance of this embodiment includes operations S210 to S250.

[0045] In operation S210 , a plurality of cardiac pulse signals of a target object are acquired.

[0046] According to an embodiment of the present invention, the plurality of cardiac pulse signals represent a mixed signal of a plurality of chest electromagnetic echo signals and a plurality of neck electromagnetic echo signals.

[0047] According to an embodiment of the present invention, a radar is placed at a predetermined position away from the chest area and the neck area of ​​the target object, respectively. The transmitting antennas of the two radars transmit radar signals to the chest area and the neck area of ​​the target object, respectively. The chest area and the neck area generate electromagnetic echo signals and return them to the receiving antennas of the two radars. The millimeter wave radar can have multiple transmitting antennas and multiple receiving antennas. The predetermined distance of the radar setting can be 40 cm, and the relevant parameters of the two radars can be set to a starting frequency of 77 GHz and a sweep slope of 99.987. , sweep duration 40 , sweep repetition rate 200Hz, idle time 80 , analog-to-digital converter (ADC) sampling number 256, ADC sampling rate 8000kbps, receiving gain 48dB.

[0048] According to an embodiment of the present invention, multiple cardiac pulse signals are reflected from different spatial points on a target subject through different transmission channels and returned to multiple receiving antennas. The multiple target signals may include multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals. The chest electromagnetic echo signal may reflect relevant activity information of the target subject's heart region and may be a cardiac signal. The neck electromagnetic echo signal may reflect vibration information of the target subject's carotid artery and may be vibration caused by pressure wave conduction.

[0049] In operation S220 , a target signal is determined from among a plurality of cardiac pulse signals.

[0050] According to an embodiment of the present invention, the target signal represents a cardiac pulse signal having a fundamental frequency clarity greater than a predetermined clarity threshold.

[0051] According to an embodiment of the present invention, the target signal may be a signal extracted from multiple cardiac pulse signals using fundamental frequency clarity as a signal extraction criterion. Furthermore, a predetermined clarity threshold or a predetermined number may be set as a reference for the number of high-quality target signals screened out, wherein there may be multiple target signals.

[0052] In operation S230 , a physiological feature extraction process is performed on the target signal to obtain physiological feature information of the target object.

[0053] According to an embodiment of the present invention, the physiological characteristic information may include relevant physiological information of the target object, such as a beat-to-beat interval sequence, a pulse arrival time sequence, and a respiratory signal.

[0054] According to an embodiment of the present invention, by acquiring the current physiological information of the target object, a multi-dimensional comprehensive analysis can be performed on the above physiological characteristic information, so as to predict and generate the continuous blood pressure of the target object.

[0055] In operation S240 , the continuous blood pressure prediction generation model is used to perform feature extraction on the physiological feature information and the target signal to obtain a first feature and a second feature.

[0056] According to an embodiment of the present invention, the first feature characterizes a four-dimensional feature corresponding to the systolic pressure, and the second feature characterizes an eight-dimensional feature corresponding to the diastolic pressure.

[0057] According to an embodiment of the present invention, a continuous blood pressure prediction generation model can be pre-trained using a sample training data set, so that during application, the continuous blood pressure prediction generation model can be directly used to perform multi-resolution feature extraction processing on the input physiological characteristic information of the target object, thereby obtaining a first feature and a second feature corresponding to the diastolic pressure and systolic pressure, respectively. The first feature can be a fine-grained, low-level feature that can represent the temporal relationship between the neck and chest signals related to the systolic pressure, and the second feature can be a coarse-grained, high-level feature that can represent respiratory sinus arrhythmia and thoracic pressure changes used to model the impact of diastolic pressure.

[0058] In operation S250 , feature fusion processing is performed on the first feature and the second feature to obtain the target continuous blood pressure.

[0059] According to an embodiment of the present invention, the target continuous blood pressure represents the continuous changes in the systolic blood pressure and the diastolic blood pressure of the target subject within a predetermined period of time.

[0060] According to an embodiment of the present invention, after multi-resolution feature extraction processing is performed on the physiological characteristic information and the target signal using the continuous blood pressure prediction generation model, feature fusion is performed on the extracted first feature and the second feature, and then the fused features are subjected to relevant decoding processing to obtain the target continuous blood pressure including continuous diastolic pressure and systolic pressure.

[0061] According to an embodiment of the present invention, the target continuous blood pressure may be auxiliary information for predicting the target object. It should be noted that the target continuous blood pressure obtained here is only reference information for medical staff to make a diagnosis and is not a direct diagnosis result.

[0062] For example, two radars are used to transmit electromagnetic signals to the chest and neck areas of the target object respectively, and preliminary processing is performed on the multiple electromagnetic echo signals received to obtain multiple cardiac artery pulse signals. The target signal is determined from the multiple cardiac artery pulse signals based on the fundamental frequency clarity, and then physiological feature extraction processing is performed on the target signal and the multiple cardiac artery pulse signals to obtain physiological feature information of the target object. The physiological feature information is subjected to multi-resolution feature extraction processing using a continuous blood pressure prediction generation model to obtain a first feature related to systolic pressure and a second feature related to diastolic pressure. Feature fusion processing is then performed on the first feature and the second feature to obtain and generate a target continuous blood pressure for assisting in the prediction of the target object, so that scientists or professionals in related fields can monitor the relevant status of the measured object based on the target continuous blood pressure and make judgments that are appropriate for the target object.

[0063] According to an embodiment of the present invention, a plurality of cardiac pulse signals including a plurality of chest electromagnetic echo signals and a plurality of neck electromagnetic echo signals are first acquired. Then, based on the fundamental frequency clarity of each cardiac pulse signal and a predetermined clarity threshold, a plurality of target signals are extracted from the plurality of cardiac pulse signals. This achieves the goal of obtaining high-quality target signals from the original radar signal full of noise and interference by using the fundamental frequency clarity of each signal as a screening criterion and through multiple rounds of algorithms, so as to facilitate the extraction of more accurate physiological characteristic information from the high-quality target signals.

[0064] According to an embodiment of the present invention, the target signal is then subjected to physiological feature extraction processing, and relevant physiological feature information such as the target object's current accurate beat-to-beat interval sequence, pulse arrival time series, and respiratory signal is extracted from the target signal. The accurate physiological feature information and high-quality target signal are then input into a pre-trained continuous blood pressure prediction generation model. The continuous blood pressure prediction generation model is used to perform multi-resolution feature extraction on the extracted accurate physiological feature information and high-quality target signal, thereby obtaining first features corresponding to systolic pressure and second features corresponding to diastolic pressure at different granularities and levels. Feature fusion processing such as upsampling is performed on the first and second features of different dimensions to obtain fused features, which are then decoded to restore the target continuous blood pressure predicted for the target object. By utilizing a dual radar detection system, multi-dimensional feature capture and feature analysis extraction of chest and neck signals after interference noise processing are achieved. A comprehensive analysis is conducted from multiple perspectives such as hemodynamics and cardiac dynamics. Based on accurate physiological characteristic information, an optimized and highly robust continuous blood pressure prediction model is used to generate the prediction. Multiple feature separations, extractions, and fusions are then performed on the physiological characteristic information extracted once, thereby fully fusing and predicting the features corresponding to diastolic pressure and systolic pressure, and obtaining a target continuous blood pressure with high accuracy and reliability. This can then assist relevant professionals in subsequent processing, improving processing efficiency while saving costs.

[0065] According to embodiments of the present invention, further, by subjecting the continuous blood pressure prediction model to extensive model learning and training, the trained continuous blood pressure prediction model can perform multiple rounds of feature extraction and fusion processing on the input physiological information and target signal, deeply exploring and analyzing the relationship between systolic pressure and neck and chest signals, as well as the relationship between diastolic pressure, respiratory sinus arrhythmia, and changes in thoracic pressure, which are hidden in the physiological feature information and target signal. This allows the target continuous blood pressure to be accurately generated based on features from different dimensions, resulting in a continuous blood pressure prediction model with high robustness, reliability, efficiency, and output accuracy.

[0066] It should be noted that the target continuous blood pressure obtained by the present invention is only an intermediate result, and the diagnostic result or health status cannot be directly derived from the target continuous blood pressure obtained by the method of the present invention.

[0067] According to an embodiment of the present invention, a method for acquiring multiple cardiac pulse signals of a target object may include the following operations.

[0068] According to an embodiment of the present invention, a plurality of initial electromagnetic echo signals of a target object are acquired.

[0069] According to an embodiment of the present invention, the multiple initial electromagnetic echo signals include an initial mixed signal of multiple chest initial electromagnetic echo signals reflected by the chest area of ​​the target object and multiple neck initial electromagnetic echo signals reflected by the neck area.

[0070] According to an embodiment of the present invention, two radars located in the chest area and the neck area are first used to transmit electromagnetic signals to the target object, and then a receiving antenna array is used to receive multiple chest initial electromagnetic echo signals and multiple neck initial electromagnetic echo signals from various spatial points and radar channels.

[0071] According to an embodiment of the present invention, arc tangent demodulation is performed on the initial electromagnetic echo signal to obtain a plurality of phase signals.

[0072] According to an embodiment of the present invention, the phase signal can be obtained as expressed in formula (1).

[0073] (1);

[0074] in, It can be characterized as a phase signal, Q(t) can be characterized as the real part of the initial electromagnetic echo signal, and I(t) can be characterized as the imaginary part of the initial electromagnetic echo signal.

[0075] According to an embodiment of the present invention, a plurality of phase signals are subjected to second-order differential filtering processing to obtain a plurality of cardiac pulse signals.

[0076] According to an embodiment of the present invention, a second-order differential filter capable of robustly suppressing signal noise is used to suppress noise and interference on multiple initial electromagnetic echo signals to obtain multiple cardiac arterial pulse signals. The cardiac arterial pulse signals can be expressed according to formula (2).

[0077] (2);

[0078] Among them, V m (t) can be represented as the cardiac arterial pulse signal, N can be represented as the half-width length of the second-order differential filter, h can be represented as the sampling time step, and s can be represented as the second-order differential filter.

[0079] According to an embodiment of the present invention, the length of the second-order differential filter used above can be as shown in formula (3), the coefficients of the second-order differential filter can be calculated through a recursive relationship, and the coefficients of the second-order differential filter need to satisfy the symmetry relationship and boundary conditions. The coefficients of the second-order differential filter can be as shown in formula (4), the symmetry relationship can be as shown in formula (5), and the boundary conditions can be as shown in formula (6).

[0080] L=2N+1(3);

[0081] Wherein, L can be represented as the length of the second-order differential filter.

[0082] (4);

[0083] Among them, s[k] can be represented as the coefficient of the second-order differential filter, and k can be represented as an index.

[0084] s[L-1-k]= s[k](5);

[0085] Here, s[L-1-k] can be represented as the symmetric coefficient of the second-order differential filter coefficient s[k].

[0086] s[N]=1(6);

[0087] Among them, s[N] can be represented as a boundary condition.

[0088] According to an embodiment of the present invention, the length L of the second-order differential filter can be set to 43, and can also be specifically set according to a specific application scenario.

[0089] According to an embodiment of the present invention, a plurality of initial electromagnetic echo signals reflected from the chest area and the neck area of ​​the target object are first acquired, and then phase extraction is performed on the plurality of initial electromagnetic echo signals to obtain a plurality of phase signals, and then second-order differential filtering is performed on the plurality of phase signals to obtain a plurality of cardiac pulse signals, thereby achieving preliminary filtering of the plurality of initial electromagnetic echo signals to suppress and filter out some noise and interference, thereby improving the quality of subsequent signals to be processed and avoiding the influence of noise interference on the processing process.

[0090] According to an embodiment of the present invention, a method for determining a target signal from a plurality of cardiac pulse signals may include the following operations.

[0091] According to an embodiment of the present invention, correlation processing is performed on multiple preliminarily processed cardiac pulse signals based on a harmonic-conscious synchronized compression wavelet cardiac tracker (HCSCT) algorithm, so that accurate current physiological characteristic information of a target subject can be extracted from the multiple cardiac pulse signals. The harmonic-conscious synchronized compression wavelet cardiac tracker algorithm can be implemented based on synchronized compression wavelet transform, harmonic verification, and determination of fundamental frequency clarity information based on the target heart rate fundamental frequency.

[0092] According to an embodiment of the present invention, synchronous compression wavelet transform and harmonic verification processing are performed on a plurality of cardiac pulse signals to obtain a target heart rate fundamental frequency of the target subject.

[0093] According to an embodiment of the present invention, by performing synchronous compression wavelet transform and harmonic verification processing on multiple cardiac arterial pulse signals, the global heart rate fundamental frequency that can currently be applied globally, that is, the target heart rate fundamental frequency, can be determined from the heart rate fundamental frequency corresponding to each cardiac arterial pulse signal.

[0094] According to an embodiment of the present invention, fundamental frequency clarity information of each cardiac pulse signal is determined based on a fundamental frequency clarity selection rule and a target heart rate fundamental frequency.

[0095] According to an embodiment of the present invention, the fundamental frequency clarity of each cardiac arterial pulse signal is calculated based on a fundamental frequency clarity selection rule using a determined target heart rate fundamental frequency that can be globally adapted, thereby obtaining fundamental frequency clarity information of each cardiac arterial pulse signal. The fundamental frequency clarity information of each cardiac arterial pulse signal is used as a selection index and sorted from largest to smallest to facilitate screening out multiple target signals from multiple cardiac arterial pulse signals.

[0096] According to an embodiment of the present invention, a target signal is determined from a plurality of cardiac arterial pulse signals based on a predetermined clarity threshold and fundamental frequency clarity information of each cardiac arterial pulse signal.

[0097] According to an embodiment of the present invention, after sorting the fundamental frequency clarity information of each cardiac artery pulse signal, a predetermined clarity threshold can be used to select a portion of the cardiac artery pulse signals that is greater than the predetermined clarity threshold as multiple target signals. At the same time, a predetermined number can be set as a selection limit for the target signals, and a predetermined number of cardiac artery pulse signals with higher fundamental frequency clarity can be selected from the multiple cardiac artery pulse signals as multiple target signals, and a corresponding target signal set can be constructed. .

[0098] According to an embodiment of the present invention, a target heart rate fundamental frequency of a target object is obtained by performing synchronous compression wavelet transform and harmonic verification processing on multiple cardiac arterial pulse signals. Then, based on a fundamental frequency clarity selection rule and the target heart rate fundamental frequency, fundamental frequency clarity information of each cardiac arterial pulse signal is determined. Then, based on a predetermined clarity threshold and the fundamental frequency clarity information of each cardiac arterial pulse signal, a target signal is determined from the multiple cardiac arterial pulse signals. This realizes the processing of the multiple cardiac arterial pulse signals by a harmonic-aware synchronous compression wavelet heart tracker algorithm. The fundamental frequency clarity of each cardiac arterial pulse signal can be used as an indicator for selection. Multiple high-quality related target signals can be selected from the multiple cardiac arterial pulse signals, and the target fundamental frequency can be determined at the same time, so as to extract the current and accurate physiological characteristic information of the target object from the multiple target signals.

[0099] According to an embodiment of the present invention, a method for performing synchronous compression wavelet transform and harmonic verification processing on multiple cardiac pulse signals to obtain a target heart rate fundamental frequency of a target subject may include the following operations.

[0100] According to an embodiment of the present invention, a mother wavelet function is used to perform continuous wavelet transform processing on a plurality of cardiac arterial pulse signals to obtain wavelet coefficients corresponding to each cardiac arterial pulse signal.

[0101] According to an embodiment of the present invention, by performing continuous wavelet transform (CWT) processing on multiple cardiac arterial pulse signals, the time-frequency characteristics of each cardiac arterial pulse signal can be analyzed to obtain a matrix of wavelet coefficients that can reflect the time-frequency characteristics.

[0102] According to an embodiment of the present invention, before performing continuous wavelet transform processing on multiple cardiac arterial pulse signals, it is necessary to separate multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals from the multiple cardiac arterial pulse signals, so as to perform continuous wavelet transform processing on the multiple chest electromagnetic echo signals and the multiple neck electromagnetic echo signals respectively. Taking the case of performing continuous wavelet transform processing on the multiple chest electromagnetic echo signals as an example, the wavelet coefficients of the chest electromagnetic echo signals can be expressed as shown in Formula (7).

[0103] (7);

[0104] Among them, W c (a, b) can be represented as the wavelet coefficients of the chest electromagnetic echo signal, a can be represented as the scale parameter, b can be represented as the time translation parameter, V c (t) can be represented as the wavelet coefficient of the chest electromagnetic echo signal, It can be represented as the mother wavelet function, It can be characterized as the conjugate of the mother wavelet function.

[0105] According to an embodiment of the present invention, in the same manner, continuous wavelet transform processing is performed on multiple neck electromagnetic echo signals respectively, so as to obtain the wavelet coefficient of each neck electromagnetic echo signal.

[0106] According to an embodiment of the present invention, synchronous compression transformation processing is performed on the wavelet coefficients corresponding to each cardiac arterial pulse signal to obtain multiple target time-frequency matrices.

[0107] According to an embodiment of the present invention, in order to further improve the energy concentration and resolution of the time-frequency characteristics, synchronous compression transform (SST) processing can be performed on the wavelet coefficients of each chest electromagnetic echo signal and the wavelet coefficients of each neck electromagnetic echo signal. Through the synchronous compression transform processing, the energy of the wavelet coefficients can be remapped to its true instantaneous frequency, thereby effectively concentrating the energy related to the heart beat and suppressing noise and interference components at the same time.

[0108] According to an embodiment of the present invention, taking the synchronous compression transformation of wavelet coefficients of multiple chest electromagnetic echo signals as an example, the target time-frequency matrix of the chest electromagnetic echo signal can be expressed as shown in formula (8).

[0109] (8);

[0110] in, It can be represented as the target time-frequency matrix of the chest electromagnetic echo signal, It can be represented as frequency, It can be represented as the instantaneous frequency of the chest electromagnetic echo signal extracted from the phase information of the wavelet coefficients obtained after wavelet transformation of the chest electromagnetic echo signal. It can be represented as a Dirac function.

[0111] According to an embodiment of the present invention, synchronous compression transformation is performed on the wavelet coefficients of multiple neck electromagnetic echo signals in the same manner, thereby obtaining a target time-frequency matrix of each neck electromagnetic echo signal.

[0112] According to an embodiment of the present invention, harmonic verification processing is performed on a plurality of target time-frequency matrices to obtain a target heart rate fundamental frequency of the target subject.

[0113] According to an embodiment of the present invention, harmonic verification processing is performed on the target time-frequency matrix of each chest electromagnetic echo signal and the target time-frequency matrix of each neck electromagnetic echo signal, so as to ensure the consistency of each element in the subsequently extracted beat-to-beat interval sequence at the spatial point, and fundamental frequency detection is performed to obtain the target heart rate fundamental frequency of the target object.

[0114] According to an embodiment of the present invention, a method for performing harmonic verification processing on multiple target time-frequency matrices to obtain a target heart rate fundamental frequency of a target object may include the following operations.

[0115] According to an embodiment of the present invention, based on the time shift parameter, each element value in a plurality of target time-frequency matrices is accumulated to obtain a cardiac energy spectrum corresponding to each target time-frequency matrix.

[0116] According to an embodiment of the present invention, by accumulating the energy values ​​of all time points at a predetermined frequency in the target time-frequency matrix of each chest electromagnetic echo signal and the target time-frequency matrix of each neck electromagnetic echo signal based on a time shift parameter, a cardiac energy spectrum corresponding to the target time-frequency matrix of each chest electromagnetic echo signal and a cardiac energy spectrum corresponding to the target time-frequency matrix of each neck electromagnetic echo signal can be obtained.

[0117] According to an embodiment of the present invention, taking the energy accumulation processing of target time-frequency matrices of multiple chest electromagnetic echo signals as an example, the cardiac energy spectrum of each chest electromagnetic echo signal can be shown according to formula (9).

[0118] (9);

[0119] in, It can be characterized as the cardiac energy spectrum of the chest electromagnetic echo signal.

[0120] According to an embodiment of the present invention, in the same manner, energy accumulation processing is performed on target time-frequency matrices of multiple neck electromagnetic echo signals, thereby obtaining a cardiac energy spectrum of each neck electromagnetic echo signal.

[0121] According to an embodiment of the present invention, a plurality of cardiac energy spectra are smoothed using a filter to obtain a plurality of target energy spectra.

[0122] According to an embodiment of the present invention, after obtaining the cardiac energy spectrum of each chest electromagnetic echo signal and the cardiac energy spectrum of each neck electromagnetic echo signal, each cardiac energy spectrum is smoothed again using a filter to reduce its noise fluctuation and obtain a target energy spectrum.

[0123] According to an embodiment of the present invention, based on a frequency peak selection rule, a target heart rate fundamental frequency of a target subject is determined from within a first cardiac frequency interval corresponding to a plurality of target energy spectra.

[0124] According to an embodiment of the present invention, the frequency peak selection rule may be characterized as selecting two peaks with the highest energy from the target energy spectrum.

[0125] According to an embodiment of the present invention, a method for determining a target heart rate fundamental frequency of a target subject from a first cardiac frequency interval corresponding to a plurality of target energy spectra based on a frequency peak selection rule may include the following operations.

[0126] According to an embodiment of the present invention, based on a frequency peak selection rule, a first cardiac peak value and a second cardiac peak value are determined from a first cardiac frequency interval corresponding to each target energy spectrum.

[0127] According to an embodiment of the present invention, the first cardiac frequency interval can be generally set to 0.6 Hz to 2.5 Hz, but is not limited thereto, and the first cardiac frequency interval can also be specifically set according to actual conditions. It can be characterized as the first peak with the highest energy selected based on the frequency peak selection rule, the second cardiac peak It can be characterized as the second peak with the highest energy selected based on the frequency peak selection rule.

[0128] For example, based on the frequency peak selection rule, the two peaks with the highest energy are selected in the range of 0.6 Hz to 2.5 Hz of each energy spectrum, the first peak selected is used as the first cardiac peak, and the second peak selected is used as the second cardiac peak.

[0129] According to an embodiment of the present invention, the harmonic relationship between the frequency of the first cardiac peak and the frequency of the second cardiac peak of each target energy spectrum is verified to determine the intermediate heart rate fundamental frequency of each target energy spectrum.

[0130] According to an embodiment of the present invention, harmonic relationship verification can be characterized as verifying whether the frequency of the selected first cardiac peak and the frequency of the second cardiac peak satisfy a harmonic relationship. When the frequency of the second cardiac peak is an integer multiple of the frequency of the first cardiac peak, it is determined that the harmonic relationship is satisfied. When the frequency of the second cardiac peak is not an integer multiple of the frequency of the first cardiac peak, it is determined that the harmonic relationship is not satisfied. When the harmonic relationship is satisfied, the intermediate heart rate fundamental frequency corresponding to the target energy spectrum is determined to be the first cardiac peak and the frequency. When the harmonic relationship is not satisfied, the frequency of the peak with the highest energy between the first cardiac peak and the second cardiac peak is selected as the intermediate heart rate fundamental frequency corresponding to the target energy spectrum. For example, when the harmonic relationship is not satisfied, the frequency of the first cardiac peak is 1.7 Hz, the energy is 30 J, the frequency of the second cardiac peak is 0.8 Hz, and the energy is 20 J, so the frequency of the first cardiac peak of 1.7 Hz is used as the intermediate heart rate fundamental frequency corresponding to the target energy spectrum.

[0131] According to an embodiment of the present invention, the operations of verifying the harmonic relationship and determining the intermediate heart rate fundamental frequency are performed on each target energy spectrum to obtain the intermediate heart rate fundamental frequency of each target energy spectrum.

[0132] According to an embodiment of the present invention, a target heart rate fundamental frequency is determined from a plurality of intermediate heart rate fundamental frequencies based on a heart rate fundamental frequency selection rule.

[0133] According to an embodiment of the present invention, the heart rate fundamental frequency selection rule can be characterized as selecting two intermediate heart rate fundamental frequencies with the highest occurrence frequency from multiple intermediate heart rate fundamental frequencies and verifying the harmonic relationship again. When the harmonic relationship is satisfied, the first intermediate heart rate fundamental frequency is used as the target heart rate fundamental frequency. When the harmonic relationship is not satisfied, the fundamental frequency with higher energy among the two intermediate heart rate fundamental frequencies is used as the target heart rate fundamental frequency. For example, there are 10 intermediate heart rate fundamental frequencies, among which the intermediate heart rate fundamental frequencies with a frequency of 10 Hz and the intermediate heart rate fundamental frequencies with a frequency of 0.8 Hz appear the most times, 5 times and 3 times respectively. The energy of the intermediate heart rate fundamental frequency with a frequency of 1.7 Hz is 20 J, and the energy of the intermediate heart rate fundamental frequency with a frequency of 0.8 Hz is 10 J. The intermediate heart rate fundamental frequency of 1.7 Hz is used as the first potential heart rate fundamental frequency, and the intermediate heart rate fundamental frequency of 0.8 Hz is used as the second potential heart rate fundamental frequency. The harmonic relationship between the first potential heart rate fundamental frequency and the second potential heart rate fundamental frequency is verified. The second potential heart rate fundamental frequency is not an integer multiple of the first potential heart rate fundamental frequency. It is confirmed that the harmonic relationship is not satisfied, and the first potential heart rate fundamental frequency with the highest energy is used as the target heart rate fundamental frequency.

[0134] According to an embodiment of the present invention, a plurality of cardiac artery pulse signals are subjected to continuous wavelet transform processing using a mother wavelet function, thereby obtaining a plurality of wavelet coefficients that can represent the time-frequency characteristics of the signals. Each wavelet coefficient is then subjected to synchronous compression transform processing, thereby achieving energy concentration and improved resolution of the time-frequency characteristics. The synchronous compression transform processing is used to remap the energy of the wavelet coefficients to their true instantaneous frequency, effectively concentrating the energy related to the cardiac pulsation while suppressing noise and interference components, so as to determine the target heart rate fundamental frequency of the target object based on the obtained target time-frequency matrix. Then, based on a time shift parameter, the energy of all time points in the target time-frequency matrix is ​​accumulated at a predetermined frequency, thereby constructing a cardiac energy spectrum for each cardiac artery pulse signal. Each cardiac energy spectrum is then subjected to a filter to filter out noise and interference and smooth the spectrum to obtain multiple target energy spectra. Harmonic verification is performed based on the frequency peak selection rules, heart rate fundamental frequency selection principles, and the cardiac frequency intervals that correspond to the energy spectrum and the intermediate heart rate fundamental frequency, thereby determining the target heart rate fundamental frequency. Harmonic characteristics are utilized to ensure that the subsequent heartbeat intervals inferred from different spatial points have inherent physiological consistency. At the same time, fundamental frequency clarity information corresponding to each cardiac arterial pulse signal is calculated based on the corresponding peak energy. The fundamental frequency clarity information is used as a reference indicator for screening target signals from multiple cardiac arterial pulse signals, and high-quality target signals are screened to facilitate the extraction of physiological characteristic information based on the target signal, thereby obtaining accurate physiological characteristic information with physiological consistency and high accuracy.

[0135] According to an embodiment of the present invention, a method for determining fundamental frequency clarity information of each cardiac pulse signal based on a fundamental frequency clarity selection rule and a target heart rate fundamental frequency may include the following operations.

[0136] According to an embodiment of the present invention, based on a fundamental frequency clarity selection rule, a third cardiac peak value and a fourth cardiac peak value are determined from the second cardiac frequency interval corresponding to each cardiac energy spectrum.

[0137] According to an embodiment of the present invention, the second cardiac frequency interval is obtained according to the target heart rate fundamental frequency and the first error fundamental frequency.

[0138] According to an embodiment of the present invention, the fundamental frequency clarity selection rule can be characterized as selecting a peak with the highest energy from the cardiac energy spectrum and locating a nearest minimum energy point to the right of the peak with the highest energy (in the direction of higher frequency) as the fourth cardiac peak.

[0139] According to an embodiment of the present invention, the first error fundamental frequency can be a predetermined value, and the second cardiac frequency interval can be obtained for the target heart rate fundamental frequency ± the first error fundamental frequency. For example, the first error fundamental frequency can be 0.4 Hz, and the target heart rate fundamental frequency is 2 Hz, then the second cardiac frequency interval is 1.6 Hz~2.4 Hz.

[0140] For example, based on the fundamental frequency clarity selection rule, within the range of ±0.4 Hz of the target heart rate fundamental frequency of each cardiac energy spectrum, the peak with the highest energy is selected as the third cardiac peak, and then on the right side of the third cardiac peak, a minimum energy point closest to the third cardiac peak is located as the fourth cardiac peak.

[0141] According to an embodiment of the present invention, fundamental frequency clarity information of each cardiac pulse signal is obtained based on energy information of the third cardiac peak and energy information of the fourth cardiac peak of each cardiac energy spectrum.

[0142] According to an embodiment of the present invention, fundamental frequency clarity information is obtained according to the ratio between the energy information of the third cardiac peak and the energy information of the fourth cardiac peak. The fundamental frequency clarity information may be as shown in formula (10).

[0143] (10);

[0144] Among them, R i It can be characterized as the fundamental frequency clarity information, E peak，i It can be represented as the energy information of the third cardiac peak, E min，i It can be represented as the energy information of the fourth cardiac peak.

[0145] According to the embodiment of the present invention, by performing the above operation on each cardiac energy spectrum, fundamental frequency clarity information of each cardiac energy spectrum can be obtained.

[0146] According to an embodiment of the present invention, by determining the third cardiac peak and the fourth cardiac peak from the second cardiac frequency interval corresponding to each cardiac energy spectrum based on the fundamental frequency clarity selection rule, and based on the energy information of the third cardiac peak and the energy information of the fourth cardiac peak of each cardiac energy spectrum, the fundamental frequency clarity information of each cardiac arterial pulse signal is confirmed, so that the fundamental frequency clarity information of each signal can be used as a screening indicator to screen out partial target signals with higher quality from multiple cardiac arterial pulse signals, so as to prepare for extracting accurate physiological characteristic information.

[0147] According to an embodiment of the present invention, the target signal may be P target signals, where P is a positive integer, and the physiological characteristic information may include a target chest beat-to-beat interval sequence and a target neck beat-to-beat interval sequence, a pulse arrival time sequence, and a respiratory signal.

[0148] According to an embodiment of the present invention, a method for performing physiological feature extraction processing on a target signal to obtain physiological feature information of a target object may include the following operations.

[0149] According to an embodiment of the present invention, for the p-th target signal, a plurality of candidate peaks are determined from the p-th target signal based on the first cardiac frequency cycle.

[0150] According to an embodiment of the present invention, p=1, 2, 3, ..., P, and p and P are both positive integers.

[0151] According to an embodiment of the present invention, the first cardiac frequency cycle can be used to divide each target signal. By dividing the target signal, candidate peaks can be determined within each first cardiac frequency cycle, thereby obtaining a series of candidate peaks for the pth target signal, thereby avoiding extracting too few candidate peak samples. The first cardiac frequency cycle can be set according to specific circumstances.

[0152] According to an embodiment of the present invention, a plurality of cardiac time differences are calculated based on the time points of adjacent candidate peaks among a plurality of candidate peaks.

[0153] For example, there are currently 5 candidate peaks, the cardiac time difference between the 1st candidate peak and the 2nd candidate peak is 500ms, the cardiac time difference between the 2nd candidate peak and the 3rd candidate peak is 1000ms, the cardiac time difference between the 3rd candidate peak and the 4th candidate peak is 700ms, and the cardiac time difference between the 4th candidate peak and the 5th candidate peak is 600ms.

[0154] According to an embodiment of the present invention, a plurality of cardiac time differences are sorted to obtain a first beat-to-beat interval sequence of the p-th target signal.

[0155] According to an embodiment of the present invention, multiple cardiac parallaxes are sorted in chronological order to obtain a first beat-to-beat interval sequence of the pth target signal. For example, the first beat-to-beat interval sequence is represented as 500ms, 1000ms, 700ms, and 600ms.

[0156] According to an embodiment of the present invention, the first beat-to-beat interval sequence is divided based on the signal source to obtain the first chest beat-to-beat interval sequence or the first neck beat-to-beat interval sequence.

[0157] According to an embodiment of the present invention, the signal source can be characterized as an area that reflects the electromagnetic echo signal, specifically a chest area and a neck area.

[0158] According to an embodiment of the present invention, the above-mentioned operation is performed on each target signal to obtain the first beat-to-beat interval sequence of each target signal. Then, the multiple target signals are divided according to the chest region and the neck region. The target signals corresponding to the chest are divided into one group, and their first beat-to-beat interval sequence is determined as the first chest beat-to-beat interval sequence. The target signals corresponding to the neck are divided into another group, and their first beat-to-beat interval sequence is determined as the first neck beat-to-beat interval sequence, so that separate information analysis is performed on the two groups of signals without interfering with each other.

[0159] According to an embodiment of the present invention, a target chest beat-to-beat interval sequence is determined from a plurality of first chest beat-to-beat interval sequences based on a predetermined cardiac cycle.

[0160] According to an embodiment of the present invention, a difference between each cardiac time difference in the target chest beat-to-beat interval sequence and a predetermined cardiac cycle is smaller than other cardiac time differences in each first chest beat-to-beat interval sequence corresponding to each cardiac time difference.

[0161] According to an embodiment of the present invention, the target chest beat-to-beat interval sequence and the target neck beat-to-beat interval sequence may both include multiple cardiac time differences. Based on a predetermined cardiac cycle, the process of determining the optimal target chest beat-to-beat interval sequence from multiple first chest beat-to-beat interval sequences and the process of determining the optimal target neck beat-to-beat interval sequence from multiple first neck beat-to-beat interval sequences may both be as shown in formula (11).

[0162] (11);

[0163] in, It can be represented as the optimal cardiac time difference selected from the cardiac time differences in multiple first chest beat-to-beat interval sequences, i can be represented as the sequence number of the i-th cardiac time difference in the multiple first chest beat-to-beat interval sequences, and M can be represented as the total number of cardiac time differences in the multiple first chest beat-to-beat interval sequences. It can be represented as a calculation to find the minimum value from M cardiac time differences. It can be represented as the i-th cardiac time difference, It can be represented as the target heart rate fundamental frequency, It can be characterized as a predetermined cardiac cycle.

[0164] For example, there are currently three first chest beat-to-beat interval sequences corresponding to the chest, the first first chest beat-to-beat interval sequence is 500ms, 1000ms, 700ms, and 900ms, the second first chest beat-to-beat interval sequence is 600ms, 100ms, 300ms, and 500ms, and the third first chest beat-to-beat interval sequence is 1200ms, 1400ms, 600ms, and 550ms, and the predetermined heart cycle is 600ms.

[0165] The absolute value difference between the cardiac time difference in the first column of the three first chest beat-to-beat interval sequences and the predetermined cardiac cycle is calculated, and the obtained values ​​are 100ms, 0ms, and 600ms. Based on the minimum value principle, the first cardiac time difference in the second first chest beat-to-beat interval sequence is determined as the first cardiac time difference in the target chest beat-to-beat interval sequence.

[0166] The absolute value difference between the cardiac time difference in the second column of the three first chest beat-to-beat interval sequences and the predetermined cardiac cycle is calculated, and the obtained values ​​are 400ms, 500ms, and 800ms. Based on the minimum value principle, the second cardiac time difference in the first first chest beat-to-beat interval sequence is determined as the second cardiac time difference in the target chest beat-to-beat interval sequence.

[0167] The absolute value difference between the cardiac time difference in the third column of the three first chest beat-to-beat interval sequences and the predetermined cardiac cycle is calculated, and the obtained values ​​are 100ms, 300ms, and 200ms. Based on the minimum value principle, the third cardiac time difference in the first first chest beat-to-beat interval sequence is determined as the third cardiac time difference in the target chest beat-to-beat interval sequence.

[0168] The absolute difference between the cardiac time difference in the fourth column of the three first chest beat-to-beat interval sequences and the predetermined cardiac cycle is calculated, resulting in values ​​of 300ms, 100ms, and 50ms. Based on the minimum value principle, the fourth cardiac time difference in the third first chest beat-to-beat interval sequence is determined as the fourth cardiac time difference in the target chest beat-to-beat interval sequence. This constructs the target chest beat-to-beat interval sequence.

[0169] According to an embodiment of the present invention, a target cervical beat-to-beat interval sequence is determined from a plurality of first cervical beat-to-beat interval sequences based on a predetermined cardiac cycle.

[0170] According to an embodiment of the present invention, a difference between each cardiac time difference in the target cervical beat-to-beat interval sequence and a predetermined cardiac cycle is smaller than other cardiac time differences in each first cervical beat-to-beat interval sequence corresponding to each cardiac time difference.

[0171] According to an embodiment of the present invention, the process of determining the target cervical beat-to-beat interval sequence is consistent with the process of determining the target thoracic beat-to-beat interval sequence, and will not be described in detail here.

[0172] According to an embodiment of the present invention, based on the fundamental frequency clarity information, the target signal corresponding to the chest and the target signal corresponding to the neck with the highest fundamental frequency clarity information can be directly selected from multiple target signals corresponding to the chest and the neck, and these two signals can be directly used as the chest beat-to-beat interval signal and the neck beat-to-beat interval signal. Multiple candidate peaks can then be determined from the chest beat-to-beat interval signal and the neck beat-to-beat interval signal, and multiple cardiac time differences of the chest beat-to-beat interval signal and the neck beat-to-beat interval signal can be calculated. A time series consisting of the multiple cardiac time differences of the chest beat-to-beat interval signal can be used as a target chest beat-to-beat interval sequence, and a time series consisting of the multiple cardiac time differences of the neck beat-to-beat interval signal can be used as a target neck beat-to-beat interval sequence.

[0173] According to an embodiment of the present invention, a pulse arrival time sequence is obtained based on the difference between the target chest beat-to-beat interval sequence and the target neck beat-to-beat interval sequence.

[0174] According to an embodiment of the present invention, the pulse arrival time series can be expressed as formula (12).

[0175] (12);

[0176] Among them, PAT(t) can be characterized as the pulse arrival time series, IBI c (t) can be characterized as the target chest beat-to-beat interval sequence, IBI n (t) can be characterized as a target sequence of beat-to-beat intervals in the neck.

[0177] According to an embodiment of the present invention, low-pass filtering is performed on phase signals of a plurality of initial electromagnetic echo signals to obtain a respiratory signal.

[0178] According to an embodiment of the present invention, the initial electromagnetic echo signal may be characterized as a signal received by the radar receiving antenna array without any processing.

[0179] According to an embodiment of the present invention, the breathing signal can be expressed as shown in formula (13).

[0180] (13);

[0181] Among them, Rm (t) can be characterized as a breathing signal, and F(·) can be characterized as a low-pass filter.

[0182] According to an embodiment of the present invention, by using a low-pass filter to perform low-pass filtering on the phase signals of multiple initial electromagnetic echo signals, high-frequency cardiac pulsation components and other noise can be effectively filtered out, thereby isolating relevant low-frequency signals that can reflect respiratory motion. The respiratory signal can include a respiratory signal corresponding to the chest region and a respiratory signal corresponding to the neck region.

[0183] According to an embodiment of the present invention, multiple candidate peaks are determined from each target signal, the cardiac time difference is calculated based on each two adjacent candidate peaks, and multiple first beat-to-beat interval sequences are constructed. The multiple first beat-to-beat interval sequences are divided into corresponding chest and neck regions based on the signal source to obtain multiple first chest beat-to-beat interval sequences and multiple first neck beat-to-beat interval sequences. Then, based on a predetermined cardiac cycle, a target chest beat-to-beat interval sequence is determined from the multiple first chest beat-to-beat interval sequences, and a target neck beat-to-beat interval sequence is determined from the multiple first neck beat-to-beat interval sequences. This enables a more accurate and stable beat-to-beat interval sequence to be obtained through a frequency-constrained peak selection method. A pulse arrival time sequence is then obtained based on the difference between the target chest beat-to-beat interval sequence and the target neck beat-to-beat interval sequence. Furthermore, the phase signal of the initial electromagnetic echo signal is low-pass filtered, thereby effectively filtering out high-frequency cardiac pulsation components and other noise in the signal and separating a low-frequency signal reflecting respiratory motion, namely a respiratory signal. This achieves accurate extraction of physiological characteristic information from the target signal, thereby facilitating output of the physiological characteristic information to a model for continuous blood pressure prediction and generation.

[0184] According to an embodiment of the present invention, a method for extracting features from physiological feature information and a target signal using a continuous blood pressure prediction generation model to obtain a first feature and a second feature may include the following operations.

[0185] According to an embodiment of the present invention, a sequence to be predicted is generated based on physiological feature information and a target signal.

[0186] According to an embodiment of the present invention, the target signal may include multiple target chest electromagnetic echo signals and multiple target neck electromagnetic echo signals. The target chest beat-to-beat interval sequence and target neck beat-to-beat interval sequence, pulse arrival time sequence, respiratory signal, target chest electromagnetic echo signal, and target neck electromagnetic echo signal are input into a continuous blood pressure prediction generation model. The continuous blood pressure prediction generation model generates a sequence to be predicted based on the above sequences and signals for predicting continuous blood pressure. The sequence to be predicted may be a multivariate time series, so that the continuous blood pressure prediction generation model can obtain continuous diastolic pressure and continuous systolic pressure based on continuous feature analysis in the time series.

[0187] According to an embodiment of the present invention, initial features are extracted from the sequence to be predicted to obtain initial features.

[0188] According to an embodiment of the present invention, the initial signature represents a mixed signature corresponding to diastolic and systolic pressure.

[0189] According to an embodiment of the present invention, multi-resolution feature extraction is performed on the initial features to obtain the first features and the second features.

[0190] According to an embodiment of the present invention, multi-level feature extraction can be performed on the initial features, specifically including low-level (fine-grained) feature extraction on the initial features, thereby obtaining lower-dimensional features, which can be used to identify the temporal relationship between neck and chest signals related to systolic pressure, and high-level (coarse-grained) feature extraction on the initial features, thereby obtaining higher-dimensional features, which can be used to model respiratory sinus arrhythmia and thoracic pressure changes that affect diastolic pressure.

[0191] According to an embodiment of the present invention, the specific sequence to be predicted, the initial feature, the first feature, and the second feature may refer to the formula expression and extraction in the training process.

[0192] According to an embodiment of the present invention, a sequence to be predicted is generated based on physiological characteristic information and a target signal, initial feature extraction is performed on the sequence to be predicted to obtain a mixed feature corresponding to diastolic pressure and systolic pressure, and multi-resolution feature extraction is performed on the initial feature to obtain a first feature and a second feature. Multi-level and multi-granularity feature extraction is achieved from the physiological characteristic information and the target signal, thereby mining and analyzing the features related to systolic pressure and the features related to diastolic pressure from multiple dimensions and levels, so as to generate a target continuous blood pressure containing continuous diastolic pressure information and systolic pressure information based on the time characteristics of the sequence to be predicted.

[0193] According to an embodiment of the present invention, after extracting the first feature and the second feature from the initial feature, the first feature and the second feature can be encoded using the continuous blood pressure prediction generation model to obtain the corresponding first encoding feature and the second encoding feature. The first encoding feature and the second encoding feature can then be feature fused to obtain the target fusion feature, and the target fusion feature can then be decoded, so that the target continuous blood pressure of the target object can be directly predicted.

[0194] According to an embodiment of the present invention, the continuous blood pressure prediction generation model is trained in the following manner, and the training method may include the following operations.

[0195] According to an embodiment of the present invention, an initial model to be trained and a sample training data set are obtained.

[0196] According to an embodiment of the present invention, the sample training data set includes a plurality of continuous blood pressure samples, a plurality of training physiological feature information, a plurality of training chest signals, and a plurality of training neck signals.

[0197] According to an embodiment of the present invention, the multiple training physiological characteristic information may include multiple training chest beat-to-beat interval sequences, multiple training neck beat-to-beat interval sequences, multiple training pulse arrival time sequences, and multiple training breathing signals.

[0198] According to an embodiment of the present invention, each continuous blood pressure sample includes continuous sample diastolic pressure information and continuous sample systolic pressure information.

[0199] According to an embodiment of the present invention, continuous blood pressure samples may be expressed as shown in formula (14).

[0200] (14);

[0201] Among them, y(t) can be represented as continuous blood pressure samples, SBP(t) can be represented as continuous sample systolic pressure information, and DBP(t) can be represented as continuous sample diastolic pressure information.

[0202] According to an embodiment of the present invention, a plurality of training physiological feature information, a plurality of training chest signals and a plurality of training neck signals are input into an initial model to be trained for sequence generation processing to obtain a plurality of training sequences.

[0203] According to an embodiment of the present invention, the training sequence may be as shown in formula (15).

[0204] (15);

[0205] Among them, x(t) can be represented as a training sequence, T can be represented as the time length of the sequence, It can be represented as a real number field, Rc (t) can be represented as a training respiratory signal corresponding to the chest area, and the training sequence can be a sequence of 6-dimensional features, V c (t) can be characterized as the training chest signal, V n (t) can be characterized as the training neck signal.

[0206] According to an embodiment of the present invention, feature extraction is performed on a plurality of training sequences to obtain a plurality of first training features and a plurality of second training features.

[0207] According to an embodiment of the present invention, the first training feature represents a four-dimensional training feature corresponding to systolic pressure, and the second training feature represents an eight-dimensional training feature corresponding to diastolic pressure.

[0208] According to an embodiment of the present invention, initial features are first extracted from a plurality of training sequences to obtain training initial features. The training initial features can represent training mixed features corresponding to diastolic pressure and systolic pressure.

[0209] According to an embodiment of the present invention, the training initial features may be as shown in formula (16).

[0210] (16);

[0211] Among them, v r It can be characterized as the initial feature of training, F r (·) can be characterized as the process of extracting initial features from the training sequence, and D can be characterized as the feature dimension.

[0212] According to an embodiment of the present invention, after the initial training features are extracted, multi-resolution feature extraction is performed on the initial training features to obtain the first training features and the second training features.

[0213] According to an embodiment of the present invention, multi-level feature extraction can be performed on the initial training features, specifically including low-level (fine-grained) feature extraction on the initial training features, thereby obtaining lower-dimensional features, which can be used for training to identify the time relationship between neck and chest signals related to systolic pressure, and high-level (coarse-grained) feature extraction on the initial training features, thereby obtaining higher-dimensional features, which can be used for training modeling of respiratory sinus arrhythmia and thoracic pressure changes that affect diastolic pressure.

[0214] According to an embodiment of the present invention, the first training feature may be as shown in formula (17), and the second training feature may be as shown in formula (18).

[0215] (17);

[0216] Among them, v lCan be characterized as the first training feature, F l (·) can be characterized as the process of extracting the first training feature from the initial training feature.

[0217] (18);

[0218] Among them, v h Can be characterized as the second training feature, F h (·) can be characterized as the process of extracting the second training features from the initial training features.

[0219] According to an embodiment of the present invention, a plurality of first training features and a plurality of second training features are input into an encoder for encoding processing to obtain a plurality of first training encoding features and a plurality of second training encoding features.

[0220] According to an embodiment of the present invention, the first training coding feature may be as shown in formula (19), and the second training coding feature may be as shown in formula (20).

[0221] (19);

[0222] Among them, z l It can be characterized as the first training encoding feature, G l (·) can be characterized as the process of encoding the first training feature.

[0223] (20);

[0224] Among them, z h It can be represented as the second training encoding feature, G h (·) can be characterized as the process of encoding the second training feature.

[0225] According to an embodiment of the present invention, feature fusion processing is performed on multiple first training coding features and multiple second training coding features, and the obtained multiple training fusion features are input into a decoder for decoding processing to obtain multiple predicted continuous blood pressures.

[0226] According to an embodiment of the present invention, the second training coding feature is first upsampled to improve its resolution, and then the feature dimension of the upsampled second training coding feature and the first training coding feature are aligned to achieve feature fusion and obtain a training fusion feature.

[0227] According to an embodiment of the present invention, the training fusion feature can be expressed as formula (21).

[0228] (twenty one);

[0229] Among them, zo It can be characterized as training fusion features, Concat (·) can be characterized as alignment processing, and Upsample (·) can be characterized as upsampling processing.

[0230] According to an embodiment of the present invention, the above-mentioned progressive upsampling method can retain physiologically relevant details in the signals from the two radar sources, thereby enabling continuous prediction of diastolic and systolic blood pressure.

[0231] According to an embodiment of the present invention, after the training fusion features are obtained, a decoder may be used to decode the training fusion features, thereby restoring the predicted continuous blood pressure.

[0232] According to an embodiment of the present invention, the continuous blood pressure may be predicted as shown in formula (22).

[0233] (twenty two);

[0234] in, It can be characterized as predicting continuous blood pressure.

[0235] According to an embodiment of the present invention, in actual application, this step can directly output the target continuous blood pressure.

[0236] According to an embodiment of the present invention, based on a loss function, a training loss value is calculated according to a plurality of predicted continuous blood pressures and a plurality of continuous blood pressure samples.

[0237] According to an embodiment of the present invention, the training loss value can be calculated as shown in formula (23).

[0238] (twenty three);

[0239] Among them, l can be represented as the training loss value.

[0240] According to an embodiment of the present invention, the model parameters of the initial model to be trained are adjusted according to the training loss value to obtain a trained continuous blood pressure prediction generation model.

[0241] According to an embodiment of the present invention, a predetermined training round can be set, and a predetermined loss threshold can also be set. When the iterative training rounds of the model meet the predetermined training rounds or the training loss value of the model is less than the predetermined loss threshold, the training of the model can be stopped to obtain a trained continuous blood pressure prediction generation model.

[0242] According to an embodiment of the present invention, multiple training physiological feature information, multiple training chest signals, and multiple training neck signals in a sample training data set are input into an initial model to be trained, and multiple training sequences are generated using the initial model to be trained based on the multiple training physiological feature information, multiple training chest signals, and multiple training neck signals. Then, initial features are first extracted from the multiple training sequences to obtain multiple training initial features, and then multi-resolution feature extraction is performed on each of the training initial features to obtain multiple first training features and multiple second training features. Then, targeted encoding processing is performed on the multiple first training features and the multiple second training features, and the encoded multiple first training coded features and the multiple second training coded features are subjected to feature fusion and decoding. Processing is performed to obtain multiple predicted continuous blood pressures generated by the initial model to be trained during the training process, and then based on the loss function, the training loss value is calculated according to the multiple predicted continuous blood pressures and the multiple continuous blood pressure samples, so that the model parameters of the initial model to be trained are adjusted based on the predetermined rounds or based on the predetermined loss threshold according to the training loss value, so that a trained continuous blood pressure prediction generation model can be obtained, and the training of the initial model is realized. By using a large amount of training data to perform comprehensive repeated learning and training on the model's feature extraction, encoding, fusion, decoding, etc., the robustness and maturity of the continuous blood pressure prediction generation model can be improved, and a highly accurate target continuous blood pressure can be output to adapt to the blood pressure prediction generation in various environments and improve efficiency.

[0243] Figure 3 A schematic diagram of a method for dual-radar assisted detection of continuous blood pressure based on physiological guidance according to an embodiment of the present invention is shown.

[0244] like Figure 3 As shown, two radars are used to transmit radar signals to the chest and neck areas of the target object, and multiple initial electromagnetic echo signals are received. The multiple initial electromagnetic echo signals are subjected to second-order differential filtering to obtain multiple cardiac arterial pulse signals, and then the multiple cardiac arterial pulse signals are subjected to harmonic-aware synchronous compression wavelet transform processing to determine the target heart rate fundamental frequency and multiple target signals. Then, based on the target heart rate fundamental frequency, the target beat-to-beat interval sequence, pulse arrival time series, and respiratory signal are extracted from the multiple target signals and the multiple initial electromagnetic echo signals. The target beat-to-beat interval sequence, pulse arrival time series, and respiratory signal are then input into a continuous blood pressure prediction generation model for multi-resolution feature extraction, encoding, feature fusion, and decoding processing to output the target continuous blood pressure.

[0245] Figure 4 A schematic diagram illustrating processing physiological characteristic information and target signals using a continuous blood pressure prediction generation model according to an embodiment of the present invention is shown.

[0246] like Figure 4As shown, the continuous blood pressure prediction generation model performs multi-resolution feature extraction on the input sequence to be predicted consisting of physiological feature information, target chest electromagnetic echo signal and target neck electromagnetic echo signal to obtain the first feature and the second feature, then encodes the first feature and the second feature to obtain the first encoding feature and the second encoding feature, then upsamples the second encoding feature, aligns and fuses the upsampled second encoding feature with the first encoding feature to obtain the target fusion feature, and decodes the target fusion feature to obtain the target continuous blood pressure including continuous diastolic pressure and continuous systolic pressure.

[0247] Figure 5a A schematic diagram showing a comparison between the result output by the method of the present invention according to the first embodiment of the present invention and the actual continuous blood pressure is shown.

[0248] like Figure 5a As shown, the blue and purple curves are the predicted values ​​of systolic and diastolic blood pressure of the present invention, and the orange and yellow curves are the true values ​​of systolic and diastolic blood pressure of the prior art. When multiple target subjects were tested, the target continuous blood pressure output by the method of the present invention was compared with the actual continuous blood pressure. The error between the predicted value and the true value of continuous systolic blood pressure SBP was smaller, and the correlation between the predicted value and the true value was r=0.725. The mean of the predicted value of systolic blood pressure was is 2.73, with a standard deviation The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.740. The mean of the predicted value of diastolic blood pressure is is -0.27, standard deviation The error distribution is 1.51, and the overall predicted diastolic blood pressure is approximately consistent with the true value. The mean error for systolic and diastolic blood pressures of the present invention is -0.33 / -0.17 mmHg, and the mean absolute error is 7.32 / 5.69 mmHg. Based on existing evaluation criteria, the dual radar system of the present invention achieves a mean absolute deviation of 6.43 mmHg (systolic) and 5.32 mmHg (diastolic), meeting the key clinical benchmark of less than 7 mmHg.

[0249] Figure 5b A schematic diagram showing a comparison between the result output by the method of the present invention according to the second embodiment of the present invention and the actual continuous blood pressure is shown.

[0250] like Figure 5bAs shown, the blue and purple curves are the predicted values ​​of systolic and diastolic blood pressure of the present invention, and the orange and yellow curves are the true values ​​of systolic and diastolic blood pressure of the prior art. The target subjects were tested in different test positions (lying position). Compared with the actual continuous blood pressure, the error between the predicted value and the true value of the continuous systolic blood pressure (SBP) output by the method of the present invention is smaller, and the correlation between the predicted value and the true value is r=0.922. The mean of the predicted value of systolic blood pressure is is 1.24, standard deviation The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.732. The mean of the predicted value of diastolic blood pressure is The standard deviation is -0.14. The error distribution is 1.55, and the predicted value of diastolic blood pressure is slightly higher than the true value.

[0251] Figure 5c A schematic diagram showing a comparison between the result output by the method of the present invention according to the third embodiment of the present invention and the actual continuous blood pressure is shown.

[0252] like Figure 5c As shown, the blue and purple curves are the predicted values ​​of systolic and diastolic blood pressure of the present invention, and the orange and yellow curves are the true values ​​of systolic and diastolic blood pressure of the prior art. Multiple target subjects were tested in different seasons. Compared with the actual continuous blood pressure, the error between the predicted value and the true value of continuous systolic blood pressure SBP output by the method of the present invention is smaller, and the correlation between the predicted value and the true value is r=0.769. The mean of the predicted value of systolic blood pressure is is 1.53, with a standard deviation The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.627. The mean of the predicted value of diastolic blood pressure is is -0.64, standard deviation The error distribution is 1.92, and the predicted value of the overall diastolic blood pressure is approximately consistent with the true value.

[0253] Figure 5d A schematic diagram showing a comparison between the result output by the method of the present invention according to the fourth embodiment of the present invention and the actual continuous blood pressure is shown.

[0254] like Figure 5dAs shown, the blue and purple curves are the predicted values ​​of systolic and diastolic blood pressure of the present invention, and the orange and yellow curves are the true values ​​of systolic and diastolic blood pressure of the prior art. By using the new detection radar to detect multiple target subjects, the error between the target continuous blood pressure output by the present invention and the actual continuous blood pressure is smaller, the correlation between the predicted value and the true value is r=0.811, and the mean of the predicted value of systolic blood pressure is is 1.95, standard deviation The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.799. The mean of the predicted value of diastolic blood pressure is The standard deviation is -0.24. The error distribution is 1.62, and the predicted value of diastolic blood pressure is slightly lower than the true value.

[0255] Figure 5e A schematic diagram showing a comparison between the result output by the method of the present invention according to the fifth embodiment of the present invention and the actual continuous blood pressure is shown. Figure 5f A schematic diagram showing a comparison between the result output by the method of the present invention according to the sixth embodiment of the present invention and the actual continuous blood pressure is shown. Figure 5g A schematic diagram showing a comparison between the result output by the method of the present invention according to the seventh embodiment of the present invention and the actual continuous blood pressure is shown.

[0256] like Figure 5e~Figure 5g As shown, the blue curve and the purple curve are the predicted values ​​of systolic pressure and diastolic pressure of the present invention, and the orange curve and the yellow curve are the true values ​​of systolic pressure and diastolic pressure of the prior art. Figure 5e In order to test multiple targets in the morning, Figure 5f In order to test multiple targets in the afternoon, Figure 5g To detect multiple targets at night.

[0257] Figure 5e The target continuous blood pressure output by the present invention is compared with the actual continuous blood pressure. The error between the predicted value and the true value of the continuous systolic blood pressure SBP is small, the correlation between the predicted value and the true value is r=0.695, and the mean of the predicted value of the systolic blood pressure is is -0.53, standard deviation The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.637. The mean of the predicted value of diastolic blood pressure is is 0.54, with a standard deviation The error distribution is 1.85, and the predicted value of diastolic blood pressure is slightly higher than the true value.

[0258] Figure 5f The target continuous blood pressure output by the present invention is compared with the actual continuous blood pressure. The error between the predicted value and the true value of the continuous systolic blood pressure SBP is small. The correlation between the predicted value and the true value is r=0.809. The mean μ of the predicted value of systolic blood pressure is 1.70 and the standard deviation is The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.835. The mean μ of the predicted value of diastolic blood pressure is -0.52, and the standard deviation is The error distribution is 2.76, and the predicted value of diastolic blood pressure is slightly lower than the true value.

[0259] Figure 5g The target continuous blood pressure output by the present invention is compared with the actual continuous blood pressure. The error between the predicted value and the true value of the continuous systolic blood pressure SBP is small, the correlation between the predicted value and the true value is r=0.870, and the mean of the predicted value of the systolic blood pressure is is 1.85, standard deviation The error between the predicted value and the true value of continuous diastolic blood pressure DBP is small, and the correlation between the predicted value and the true value is r=0.697. The mean of the predicted value of diastolic blood pressure is is 3.61, with a standard deviation The error distribution is 2.57, and the predicted value of diastolic blood pressure is slightly higher than the true value.

[0260] Figure 5h A schematic diagram showing a comparison between the result output by the method of the present invention according to the eighth embodiment of the present invention and the actual continuous blood pressure is shown.

[0261] like Figure 5h As shown, the blue curve and the purple curve are the predicted values ​​of systolic pressure and diastolic pressure of the present invention, and the orange curve and the yellow curve are the true values ​​of systolic pressure and diastolic pressure of the prior art. In the morning and evening of the same day, the target continuous blood pressure output by the present invention is compared with the actual continuous blood pressure. It can be seen that in the two blood pressure tests in the morning, the errors between the predicted values ​​and the true values ​​of the continuous systolic pressure SBP and the continuous diastolic pressure DBP are small, with the correlation r=0.661 for the systolic pressure test and the correlation r=0.625 for the diastolic pressure test. In the two blood pressure tests in the afternoon, the errors between the predicted values ​​and the true values ​​of the continuous systolic pressure SBP and the continuous diastolic pressure DBP are small, with the correlation r=0.839 for the systolic pressure test and the correlation r=0.619 for the diastolic pressure test.

[0262] Figure 6 A structural block diagram of a device for dual-radar assisted detection of continuous blood pressure based on physiological guidance according to an embodiment of the present invention is shown.

[0263] like Figure 6 As shown, the apparatus for dual-radar assisted continuous blood pressure detection based on physiological guidance of this embodiment includes: an acquisition module 610 , a determination module 620 , a first extraction module 630 , a second extraction module 640 and a fusion module 650 .

[0264] The acquisition module 610 is configured to acquire multiple cardiac pulse signals of the target subject, wherein the multiple cardiac pulse signals represent a mixed signal of multiple chest electromagnetic echo signals and multiple neck electromagnetic echo signals. The acquisition module 610 can be configured to perform the aforementioned operation S210 and will not be further described herein.

[0265] The determination module 620 is configured to determine a target signal from multiple cardiac pulse signals, wherein the target signal represents a cardiac pulse signal having a fundamental frequency clarity greater than a predetermined clarity threshold. The determination module 620 can be configured to perform the aforementioned operation S220, which will not be described in detail here.

[0266] The first extraction module 630 is configured to perform physiological feature extraction processing on the target signal to obtain physiological feature information of the target object. The first extraction module 630 can be configured to perform the operation S230 described above, which will not be described in detail here.

[0267] Second extraction module 640 is configured to extract features from the physiological characteristic information and the target signal using the continuous blood pressure prediction model to obtain a first feature and a second feature, wherein the first feature represents a four-dimensional feature corresponding to systolic pressure, and the second feature represents an eight-dimensional feature corresponding to diastolic pressure. Second extraction module 640 can be configured to perform operation S240 described above and will not be further described here.

[0268] Fusion module 650 is configured to perform feature fusion processing on the first feature and the second feature to obtain a target continuous blood pressure, where the target continuous blood pressure represents the continuous changes in the systolic and diastolic blood pressures of the target subject over a predetermined period of time. Fusion module 650 can be used to perform operation S250 described above and will not be further described here.

[0269] According to an embodiment of the present invention, any multiple modules among the acquisition module 610, determination module 620, first extraction module 630, second extraction module 640, and fusion module 650 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to an embodiment of the present invention, at least one of the acquisition module 610, determination module 620, first extraction module 630, second extraction module 640, and fusion module 650 may 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 may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of software, hardware, and firmware, or any appropriate combination of these. Alternatively, at least one of the acquisition module 610 , the determination module 620 , the first extraction module 630 , the second extraction module 640 and the fusion module 650 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0270] Figure 7 A block diagram of an electronic device illustrating a method for dual radar-assisted continuous blood pressure detection based on physiological guidance according to an embodiment of the present invention is shown.

[0271] like Figure 7 As shown, an electronic device according to an embodiment of the present invention includes a processor 701, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 702 or programs loaded from a storage unit 708 into a random access memory (RAM) 703. Processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or related chipsets and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 701 may also include onboard memory for caching purposes. Processor 701 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 invention.

[0272] Various programs and data required for the operation of the electronic device are stored in RAM 703. Processor 701, ROM 702, and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations according to the method flow of the embodiment of the present invention by executing the programs in ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also perform various operations according to the method flow of the embodiment of the present invention by executing the programs stored in the one or more memories.

[0273] According to an embodiment of the present invention, the electronic device may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage portion 708 including a hard disk; and a communication portion 709 including a network interface card such as a LAN card or a modem. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. Removable media 711, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 710 as needed, so that computer programs read from the removable media can be installed in the storage portion 708 as needed.

[0274] The present invention 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 and not incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0275] According to an embodiment of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but 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 invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present invention, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above, and / or one or more memories other than ROM 702 and RAM 703.

[0276] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for executing the method shown in the flowchart. When the computer program product is executed in a computer system, the program code causes the computer system to implement the method for continuous blood pressure detection using dual radar assisted detection based on physiological guidance, as provided in an embodiment of the present invention.

[0277] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when the computer program is executed by the processor 701. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0278] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 709, and / or installed from a removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0279] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 709 and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above-described functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0280] Those skilled in the art will appreciate that various combinations and / or combinations of features described in the various embodiments and / or claims of the present invention may be made, even if such combinations and / or combinations are not explicitly described in the present invention. In particular, various combinations and / or combinations of features described in the various embodiments and / or claims of the present invention may be made, without departing from the spirit and teachings of the present invention. All such combinations and / or combinations fall within the scope of the present invention.

Claims

1. A method for continuous blood pressure detection using dual radars based on physiological guidance, characterized in that: include: Acquiring a plurality of cardiac pulse signals of a target object, wherein the plurality of cardiac pulse signals represent mixed signals of a plurality of chest electromagnetic echo signals and a plurality of neck electromagnetic echo signals; determining a target signal from the plurality of cardiac arterial pulse signals, wherein the target signal represents a cardiac arterial pulse signal having a fundamental frequency clarity greater than a predetermined clarity threshold; Performing physiological feature extraction processing on the target signal to obtain physiological feature information of the target object; Performing feature extraction on the physiological characteristic information and the target signal using a continuous blood pressure prediction generation model to obtain a first feature and a second feature, wherein the first feature represents a four-dimensional feature corresponding to systolic pressure, and the second feature represents an eight-dimensional feature corresponding to diastolic pressure; The first feature and the second feature are subjected to feature fusion processing to obtain a target continuous blood pressure, wherein the target continuous blood pressure represents the continuous changes of the systolic blood pressure and the diastolic blood pressure of the target subject within a predetermined time period.

2. The method according to claim 1, characterized in that Determining a target signal from the plurality of cardiac pulse signals comprises: Performing synchronous compression wavelet transform and harmonic verification processing on the plurality of cardiac pulse signals to obtain a target heart rate fundamental frequency of the target subject; Determining fundamental frequency clarity information of each cardiac pulse signal based on a fundamental frequency clarity selection rule and the target heart rate fundamental frequency; The target signal is determined from the plurality of cardiac arterial pulse signals based on the predetermined clarity threshold and fundamental frequency clarity information of each cardiac arterial pulse signal.

3. The method according to claim 2, characterized in that The performing synchronous compression wavelet transform and harmonic verification processing on the plurality of cardiac arterial pulse signals to obtain the target heart rate fundamental frequency of the target object includes: Using a mother wavelet function, performing continuous wavelet transform processing on the plurality of cardiac arterial pulse signals respectively to obtain wavelet coefficients corresponding to each cardiac arterial pulse signal; performing synchronous compression transformation processing on the wavelet coefficients corresponding to each cardiac arterial pulse signal to obtain multiple target time-frequency matrices; The harmonic verification process is performed on the multiple target time-frequency matrices to obtain the target heart rate fundamental frequency of the target object.

4. The method according to claim 3, characterized in that The performing the harmonic verification process on the multiple target time-frequency matrices to obtain the target heart rate fundamental frequency of the target subject includes: Based on the time shift parameter, each element value in the multiple target time-frequency matrices is accumulated to obtain a cardiac energy spectrum corresponding to each target time-frequency matrix; Utilizing filters to smooth multiple cardiac energy spectra to obtain multiple target energy spectra; Based on a frequency peak selection rule, a target heart rate fundamental frequency of the target subject is determined from the first cardiac frequency interval corresponding to the multiple target energy spectra.

5. The method according to claim 4, characterized in that The determining, based on a frequency peak selection rule, a target heart rate fundamental frequency of the target subject from a first cardiac frequency interval corresponding to the multiple target energy spectra includes: Based on the frequency peak selection rule, determining a first cardiac peak value and a second cardiac peak value from the first cardiac frequency interval corresponding to each target energy spectrum; Verifying the harmonic relationship between the frequency of the first cardiac peak and the frequency of the second cardiac peak of each target energy spectrum to determine the intermediate heart rate fundamental frequency of each target energy spectrum; Based on a heart rate fundamental frequency selection rule, the target heart rate fundamental frequency is determined from a plurality of intermediate heart rate fundamental frequencies.

6. The method according to claim 2, characterized in that The determining of the fundamental frequency clarity information of each cardiac pulse signal based on the fundamental frequency clarity selection rule and the target heart rate fundamental frequency includes: Based on the fundamental frequency clarity selection rule, determining a third cardiac peak and a fourth cardiac peak from a second cardiac frequency interval corresponding to each cardiac energy spectrum, wherein the second cardiac frequency interval is obtained according to the target heart rate fundamental frequency and the first error fundamental frequency; The fundamental frequency clarity information of each cardiac pulse signal is obtained according to the energy information of the third cardiac peak and the energy information of the fourth cardiac peak of each cardiac energy spectrum.

7. The method according to claim 1, characterized in that The target signals include P, and the physiological characteristic information includes a target chest beat-to-beat interval sequence, a target neck beat-to-beat interval sequence, a pulse arrival time sequence, and a respiratory signal; The performing physiological feature extraction processing on the target signal to obtain physiological feature information of the target object includes: For a p-th target signal, based on a first cardiac frequency cycle, determining a plurality of candidate peaks from the p-th target signal, where p=1, 2, 3, ..., P, and p and P are both positive integers; Calculating a plurality of cardiac time differences according to the time of each adjacent candidate peak among the plurality of candidate peaks; sorting the plurality of cardiac time differences to obtain a first beat-to-beat interval sequence of the p-th target signal; Based on the signal source, the first beat-to-beat interval sequence is divided to obtain a first chest beat-to-beat interval sequence or a first neck beat-to-beat interval sequence; determining the target chest beat-to-beat interval sequence from a plurality of first chest beat-to-beat interval sequences based on a predetermined cardiac cycle, wherein a difference between each cardiac time difference in the target chest beat-to-beat interval sequence and the predetermined cardiac cycle is smaller than other cardiac time differences in each first chest beat-to-beat interval sequence corresponding to each cardiac time difference; Based on the predetermined cardiac cycle, the target cervical beat-to-beat interval sequence is determined from a plurality of first cervical beat-to-beat interval sequences, wherein the difference between each cardiac time difference in the target cervical beat-to-beat interval sequence and the predetermined cardiac cycle is smaller than other cardiac time differences in each first cervical beat-to-beat interval sequence corresponding to each cardiac time difference.

8. The method according to claim 7, characterized in that The method further comprises: Obtaining the pulse arrival time sequence according to a difference between the target chest beat-to-beat interval sequence and the target neck beat-to-beat interval sequence; Low-pass filtering is performed on the phase signals of the multiple initial electromagnetic echo signals to obtain the breathing signal.

9. The method according to claim 1, characterized in that The step of extracting features from the physiological feature information and the target signal using the continuous blood pressure prediction generation model to obtain a first feature and a second feature includes: generating a sequence to be predicted according to the physiological characteristic information and the target signal; Performing initial feature extraction on the sequence to be predicted to obtain initial features, wherein the initial features represent mixed features corresponding to the diastolic pressure and the systolic pressure; Perform multi-resolution feature extraction on the initial features to obtain the first features and the second features.

10. The method according to claim 1, characterized in that The step of acquiring multiple cardiac pulse signals of the target object includes: Acquiring a plurality of initial electromagnetic echo signals of the target object, wherein the plurality of initial electromagnetic echo signals include an initial mixed signal of a plurality of chest initial electromagnetic echo signals reflected by a chest region of the target object and a plurality of neck initial electromagnetic echo signals reflected by a neck region; performing arc tangent demodulation processing on the multiple initial electromagnetic echo signals to obtain multiple phase signals; Performing second-order differential filtering on the multiple phase signals to obtain the multiple cardiac arterial pulse signals.

11. The method according to claim 1, wherein The continuous blood pressure prediction generation model is trained using the following methods, including: Obtaining an initial model to be trained and a sample training data set, wherein the sample training data set includes a plurality of continuous blood pressure samples, a plurality of training physiological feature information, a plurality of training chest signals, and a plurality of training neck signals; Inputting the plurality of training physiological feature information, the plurality of training chest signals, and the plurality of training neck signals into the initial model to be trained for sequence generation processing to obtain a plurality of training sequences; Performing the feature extraction on the multiple training sequences to obtain multiple first training features and multiple second training features, wherein the first training features represent four-dimensional training features corresponding to systolic pressure, and the second training features represent eight-dimensional training features corresponding to diastolic pressure; Inputting the plurality of first training features and the plurality of second training features into an encoder for encoding processing to obtain a plurality of first training encoding features and a plurality of second training encoding features; Performing feature fusion processing on the plurality of first training coding features and the plurality of second training coding features, and inputting the obtained plurality of training fusion features into a decoder for decoding processing to obtain a plurality of predicted continuous blood pressures; Based on the loss function, calculating a training loss value according to the plurality of predicted continuous blood pressures and the plurality of continuous blood pressure samples; According to the training loss value, the model parameters of the initial model to be trained are adjusted to obtain the trained continuous blood pressure prediction generation model.

12. A device for continuous blood pressure detection using dual radars based on physiological guidance, characterized in that: include: an acquisition module, configured to acquire a plurality of cardiac pulse signals of a target object, wherein the plurality of cardiac pulse signals represent mixed signals of a plurality of chest electromagnetic echo signals and a plurality of neck electromagnetic echo signals; a determination module, configured to determine a target signal from the plurality of cardiac arterial pulse signals, wherein the target signal represents a cardiac arterial pulse signal having a fundamental frequency clarity greater than a predetermined clarity threshold; A first extraction module is used to perform physiological feature extraction processing on the target signal to obtain physiological feature information of the target object; a second extraction module, configured to perform feature extraction on the physiological characteristic information and the target signal using a continuous blood pressure prediction generation model to obtain a first feature and a second feature, wherein the first feature represents a four-dimensional feature corresponding to systolic pressure, and the second feature represents an eight-dimensional feature corresponding to diastolic pressure; A fusion module is used to perform feature fusion processing on the first feature and the second feature to obtain a target continuous blood pressure, wherein the target continuous blood pressure represents the continuous changes of the systolic blood pressure and the diastolic blood pressure of the target object within a predetermined time period.

Images