Parameter acquisition method and device, terminal equipment and computer program product
By filtering and extracting features from radar reflection signals, the problem of inaccurate acquisition of vital sign parameters in existing technologies has been solved, achieving higher accuracy and realism.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NATIONAL UNIVERSITY OF SINGAPORE
- Filing Date
- 2024-11-13
- Publication Date
- 2026-05-15
AI Technical Summary
Existing technologies do not take all factors into account when acquiring vital signs parameters, resulting in low accuracy.
By acquiring radar reflection signals, filtering them to obtain target waveforms related to heartbeats, and then extracting features to calculate vital sign parameters.
It improves the accuracy of acquiring vital sign parameters, provides richer data, and ensures that the acquired parameters accurately and truly reflect the physiological condition of the subject being tested.
Smart Images
Figure CN122050859A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of signal processing technology, and in particular relates to a parameter acquisition method, apparatus, terminal equipment, and computer program product. Background Technology
[0002] In real life, the detection of vital signs parameters such as heart rate and blood pressure is of great significance for sleep quality monitoring, prevention and diagnosis of respiratory diseases, and prevention and diagnosis of cardiovascular diseases. Therefore, these vital signs parameters can be acquired in real time through various sensors.
[0003] Current technologies typically acquire these vital sign parameters through non-contact radar-collected radar reflection signals. However, existing technologies suffer from insufficient comprehensiveness and low accuracy in acquiring vital sign parameters. Summary of the Invention
[0004] This application provides a parameter acquisition method, apparatus, terminal device, and computer program product to address the problems of insufficient consideration and low accuracy in acquiring vital sign parameters in the prior art.
[0005] In a first aspect, embodiments of this application provide a parameter acquisition method, including:
[0006] Acquire the radar reflection signal corresponding to the object to be detected;
[0007] The radar reflection signal is filtered to obtain the target waveform of the object to be detected; the target waveform refers to a waveform related to the heartbeat.
[0008] Feature extraction is performed on the target waveform to obtain the time-series features corresponding to the target waveform;
[0009] Based on the aforementioned temporal characteristics, the vital signs parameters of the object to be detected are calculated.
[0010] Optionally, the step of filtering the radar reflection signal to obtain the target waveform of the object to be detected includes:
[0011] The radar reflection signal is demodulated to obtain a vibration signal; the vibration signal is used to characterize the minute vibration signals of the skin of the object under test caused by cardiovascular activity.
[0012] Frequency domain analysis was performed on the vibration signal to determine the respiratory signal and the corresponding harmonic signal.
[0013] Based on the breathing signal and the harmonic signal, the radar reflection signal is filtered to obtain the target waveform.
[0014] Optionally, the step of filtering the radar reflection signal based on the breathing signal and the harmonic signal to obtain the target waveform includes:
[0015] Based on the respiratory signal and the harmonic signal, the respiratory index is calculated;
[0016] The radar reflection signal is subjected to high-pass filtering to obtain the initial filtered signal;
[0017] Based on the respiratory indicators, the target number of filters is determined;
[0018] The initial filtered signal is input to the target number of filters for filtering to obtain the target waveform.
[0019] Optionally, the calculation of respiratory indicators based on the respiratory signal and the harmonic signal includes:
[0020] The dominant frequency component of respiration is determined from the respiratory signal and the harmonic signal;
[0021] The respiratory index is calculated based on the dominant frequency component.
[0022] Optionally, the temporal features include multiple components, and the vital sign parameters include multiple components; the step of calculating the vital sign parameters of the object to be detected based on the temporal features includes:
[0023] Based on the type of each vital sign parameter, determine the calculation method corresponding to each vital sign parameter;
[0024] Each of the aforementioned time-series features is calculated using different calculation methods to obtain the parameters of each vital characteristic.
[0025] Optionally, the time-series features include multiple components, and the vital sign parameters include blood pressure, which includes diastolic and systolic blood pressure; the calculation of the vital sign parameters of the subject under test based on the time-series features includes:
[0026] The average diastolic blood pressure and average systolic blood pressure of the object to be detected are obtained, as well as the average transmission time of the target waveform.
[0027] Based on the attribute information of the object to be detected, the fitting factor is determined;
[0028] The average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time are imported into a preset diastolic blood pressure calculation model to calculate the target diastolic blood pressure.
[0029] The target diastolic blood pressure, the average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time are imported into a preset diastolic blood pressure calculation model to calculate the target systolic blood pressure.
[0030] Optionally, the timing features include: the timestamps of the diastolic points, the contraction points, and the dicrotic notch in the target waveform, the peak points of the first derivative waveform corresponding to the target waveform, and the peak points of the second derivative waveform corresponding to the target waveform.
[0031] Secondly, embodiments of this application provide a parameter acquisition device, including:
[0032] The first acquisition unit is used to acquire the radar reflection signal corresponding to the object to be detected;
[0033] The first filtering unit is used to filter the radar reflection signal to obtain the target waveform of the object to be detected; the target waveform refers to a waveform related to heartbeat.
[0034] The feature extraction unit is used to extract features from the target waveform to obtain the time-series features corresponding to the target waveform;
[0035] The first calculation unit is used to calculate the vital signs parameters of the object to be detected based on the time-series characteristics.
[0036] Thirdly, embodiments of this application provide a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the parameter acquisition method as described in any one of the first aspects above.
[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the parameter acquisition method as described in any one of the first aspects above.
[0038] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, enables the terminal device to execute the parameter acquisition method described in any of the first aspects above.
[0039] The beneficial effects of the embodiments in this application compared with the prior art are:
[0040] This application provides a parameter acquisition method that involves acquiring the radar reflection signal corresponding to a target object; filtering the radar reflection signal to obtain the target waveform of the target object; the target waveform refers to a waveform related to heartbeat; extracting features from the target waveform to obtain the corresponding temporal features; and calculating the vital sign parameters of the target object based on the temporal features. Compared with the prior art, this application can filter the radar reflection signal to avoid interference from other signals and obtain a high-quality target waveform, thereby providing richer data for the acquisition of vital sign parameters. Subsequently, this application can obtain accurate and true vital sign parameters reflecting the target object based on the extracted temporal features, thus improving the accuracy of vital sign parameter acquisition. Attached Figure Description
[0041] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 This is a flowchart illustrating the implementation of a parameter acquisition method provided in an embodiment of this application;
[0043] Figure 2 This is a schematic diagram of a radar system according to an embodiment of this application detecting an object to be detected;
[0044] Figure 3 This is a schematic diagram of the structure of a radar system provided in one embodiment of this application;
[0045] Figure 4 This is a flowchart illustrating the implementation of a parameter acquisition method provided in another embodiment of this application;
[0046] Figure 5 This is a flowchart illustrating the implementation of a parameter acquisition method provided in another embodiment of this application;
[0047] Figure 6 This is a waveform comparison diagram provided in an embodiment of this application;
[0048] Figure 7 This is a schematic diagram of timing features provided in an embodiment of this application;
[0049] Figure 8 This is a flowchart illustrating the implementation of a parameter acquisition method provided in another embodiment of this application;
[0050] Figure 9 This is a schematic diagram of the structure of a parameter acquisition device provided in an embodiment of this application;
[0051] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation
[0052] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.
[0053] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.
[0054] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0055] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."
[0056] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0057] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.
[0058] In practical applications, the detection of vital signs parameters such as heart rate and blood pressure is of great significance for sleep quality monitoring, prevention and diagnosis of respiratory diseases, and prevention and diagnosis of cardiovascular diseases. Therefore, these vital signs parameters can be acquired in real time using various sensors.
[0059] Currently, to overcome the discomfort caused by traditional sensor detection methods, radar-based non-contact vital sign detection methods are becoming increasingly popular due to their advantages such as resistance to light interference, strong privacy, and all-weather capability. However, in practical applications, when using radar to detect the body of a target object, the target object's breathing and other interference signals, such as harmonics, can be superimposed on the detected radar signal.
[0060] Therefore, this application proposes a parameter acquisition method that can avoid interference from other interference signals mentioned above, thereby improving the accuracy of acquiring vital sign parameters.
[0061] Please see Figure 1 , Figure 1 This is a flowchart illustrating the implementation of a parameter acquisition method according to an embodiment of this application. In this embodiment, the execution subject of the parameter acquisition method is a terminal device. The terminal device includes, but is not limited to, laptops, desktop computers, and computers.
[0062] like Figure 1 As shown, a parameter acquisition method provided in one embodiment of this application may include S101 to S104, which are described in detail below:
[0063] In S101, the radar reflection signal corresponding to the object to be detected is acquired.
[0064] In this embodiment of the application, in order to obtain a clear waveform related to the heartbeat of the object to be detected, the radar system can detect the radial artery pulse wave at the wrist or elbow of the object to be detected. For example, please refer to... Figure 2 , Figure 2This is a schematic diagram illustrating the detection of an object by a radar system according to an embodiment of this application. Figure 2 As shown, the radar system is used to detect the wrist of the object to be detected.
[0065] After detecting the echo signal of the object to be detected, in order to reduce interference, the radar system can process the echo signal through its own mixer and output an intermediate frequency signal.
[0066] Specifically, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of a radar system provided in one embodiment of this application. Figure 3 As shown, the voltage-controlled oscillator (VCO) in the radar system generates a signal at a specific frequency (such as 2.4 GHz, 5.8 GHz, 24 GHz, 60 GHz, 77 GHz, or 120 GHz) and transmits it to the power amplifier (PA). After amplification, the transmitting antenna emits an electromagnetic wave signal. This electromagnetic wave signal returns upon contact with the target object. The receiving antenna receives the echo signal from the target object and first passes it through a low-noise amplifier (LNA) before transmitting it to the mixer. In the mixer, the echo signal undergoes a mixing process to reduce the high-frequency signal to an intermediate frequency (IF) signal.
[0067] It should be noted that intermediate frequency (IF) signals include single-channel signals, such as in-phase (I) signals, quadrature (Q) signals, and quadrature (I / Q) signals.
[0068] In this embodiment of the application, after receiving the intermediate frequency signal sent by the radar system, the terminal device can determine the intermediate frequency signal as a radar reflection signal.
[0069] In S102, the radar reflection signal is filtered to obtain the target waveform of the object to be detected; the target waveform refers to the waveform related to the heartbeat.
[0070] In this embodiment, after receiving the radar reflection signal, the terminal device can filter the radar reflection signal to obtain a clean target waveform in order to restore the heartbeat-related waveform of the object to be detected as much as possible and reduce interference. The target waveform includes, but is not limited to, heartbeat waveforms (such as electrocardiograms) and pulse waveforms.
[0071] It should be noted that, in combination Figure 2Taking the detection of the wrist of the object to be detected by the radar system as an example, in all embodiments of this application, the target waveform will be a pulse wave waveform as an example to describe this application in detail.
[0072] It is understandable that when the target waveform is a pulse wave waveform, its waveform is used to characterize the relationship between the cardiovascular activity of the subject being tested and time.
[0073] In one embodiment of this application, since the respiration and harmonics of the object to be detected are superimposed on the radar reflection signal, in order to suppress the respiration and harmonic components in the radar reflection signal, reduce the interference caused by the respiration and harmonic components, and at the same time ensure the linearity of the signal during processing, thereby restoring the heartbeat-related signal as much as possible, the terminal device can specifically achieve this by means of... Figure 4 Steps S201 to S203 are executed in step S102, as detailed below:
[0074] In S201, the radar reflection signal is demodulated to obtain a vibration signal; the vibration signal is used to characterize the minute vibration signals of the skin of the object to be detected due to cardiovascular activity.
[0075] In S202, frequency domain analysis is performed on the vibration signal to determine the breathing signal and the harmonic signal corresponding to the breathing signal.
[0076] In this embodiment, to obtain accurate respiration and its harmonic components, the terminal device can first perform signal demodulation processing on the radar reflection signal to obtain a vibration signal. This vibration signal is used to characterize the minute vibrations in the skin of the object being tested caused by cardiovascular activity.
[0077] It should be noted that demodulation algorithms for signal demodulation processing include, but are not limited to: inverse trigonometric function demodulation, orthogonal demodulation, extended differentiate and cross-multiply (DACM), and modified differentiate and cross-multiply (MDACM).
[0078] Afterwards, the terminal device can perform frequency domain analysis on the vibration signal to determine the respiratory signal and the corresponding harmonic signal.
[0079] In some possible embodiments, the terminal device can use Fast Fourier Transform (FFT) to perform frequency domain analysis of the vibration signal.
[0080] In S203, the radar reflection signal is filtered based on the breathing signal and the harmonic signal to obtain the target waveform.
[0081] In this embodiment, after determining the breathing signal and harmonic signal, that is, after determining the breathing and its harmonic components, the terminal device can filter the radar reflection signal according to the existing breathing and its harmonic filtering methods to obtain the target waveform.
[0082] In practical applications, existing methods for filtering respiration and its harmonics include, but are not limited to, high-pass filtering and band-pass filtering.
[0083] In one embodiment of this application, in order to improve the filtering success rate of respiration and its harmonic components, the terminal device can specifically achieve the following: Figure 5 Steps S301 to S304 shown are executed in step S203, as detailed below:
[0084] In S301, respiratory indicators are calculated based on the respiratory signal and the harmonic signal.
[0085] It should be noted that respiratory indicators are used to characterize respiration and the number of its harmonic components.
[0086] In one embodiment of this application, the terminal device may determine respiratory indicators according to the following steps, detailed below:
[0087] The dominant frequency component of respiration is determined from the respiratory signal and the harmonic signal;
[0088] The respiratory index is calculated based on the dominant frequency component.
[0089] It should be noted that the dominant frequency component, also known as the primary frequency component, refers to the frequency component that dominates a complex signal.
[0090] In some possible embodiments, the terminal device can determine the signal with the largest amplitude among the breathing signal and harmonic signal as the main frequency component of breathing.
[0091] Then, the terminal device can determine respiratory indicators based on this main frequency component.
[0092] Specifically, the respiratory index = main frequency component / frequency threshold. The frequency threshold can be determined according to actual needs and is not limited here. For example, the frequency threshold can be set to 1 Hz.
[0093] In this embodiment, taking a main frequency component of 0.3Hz and a frequency threshold of 1Hz as an example, the terminal device can calculate the respiratory index as 3. Therefore, the terminal device can determine that there are three frequency points of respiratory and its harmonic components in the radar reflection signal, that is, the number of respiratory and its harmonic components is 3.
[0094] In S302, the radar reflection signal is subjected to high-pass filtering to obtain an initial filtered signal.
[0095] In this embodiment, to avoid signal distortion due to defects in the filter itself, the terminal device can perform zero-phase high-pass filtering on the radar reflection signal to obtain the initial filtered signal.
[0096] In practical applications, high-pass filtering includes finite impulse response (FIL) and infinite impulse response (IRR). The specific passband and cutoff frequencies can be set according to different application scenarios, and will not be elaborated upon here.
[0097] In S303, the target number of filters is determined based on the breathing index.
[0098] In this embodiment, after obtaining the respiratory index, the terminal device can determine the number of respiratory signals and their harmonic components. Therefore, in order to further improve the filtering success rate of respiratory signals and their harmonic components, the terminal device can determine the target number of filters for filtering respiratory signals and harmonic signals based on the respiratory index.
[0099] In some possible embodiments, the terminal device may directly determine the actual value of the respiratory index as the target number of the filter.
[0100] In other possible embodiments, to further improve the filtering success rate, the terminal device can add a preset value to the actual value corresponding to the respiratory index to avoid undetected harmonic components not being suppressed. The preset value can be determined according to actual needs and is not limited here.
[0101] In this embodiment, the filter type can be a notch filter.
[0102] In S304, the initial filtered signal is input to the target number of filters for filtering to obtain the target waveform.
[0103] In this embodiment, after determining the number of filters, the terminal device can also set the parameters of the filters according to the frequency of the breathing signal and the frequency of the harmonic signal to obtain filters for different frequencies.
[0104] Subsequently, the terminal device can input the initial filtered signal to the target number of filters for filtering processing, so as to achieve filtering processing of the breathing and its harmonic components, thereby obtaining the target waveform.
[0105] For example, please refer to Figure 6 , Figure 6 This is a waveform comparison diagram provided in one embodiment of this application. For example... Figure 6 As shown, taking the heartbeat waveform as an example, Figure 6 In the diagram, (a) represents the waveform of the unprocessed radar reflection signal. Figure 6 In the diagram, (b) represents the waveform corresponding to the reference signal, i.e., the standard pulse wave waveform. Figure 6 In this scheme, (c) represents the pulse wave waveform obtained after filtering the radar reflection signal by its breathing and harmonic components.
[0106] In S103, feature extraction is performed on the target waveform to obtain the time-series features corresponding to the target waveform.
[0107] In this embodiment of the application, after obtaining the target waveform, the terminal device can extract the timing features of the target waveform to obtain the timing features corresponding to the target waveform. The timing features include multiple components.
[0108] Specifically, the terminal device can extract multiple timing feature points from the target waveform and obtain multiple timing features based on the starting point of the target waveform and each timing feature point.
[0109] In some possible embodiments, taking the target waveform as a pulse wave waveform as an example, the timing features include, but are not limited to: the timestamps of the diastolic points, the systolic points, and the dicrotic notch in the pulse wave waveform, the peak points of the first derivative waveform corresponding to the pulse wave waveform, and the peak points of the second derivative waveform corresponding to the pulse wave waveform.
[0110] In practical applications, the dicrotic notch is a characteristic feature of arterial blood pressure waveforms, appearing in the descending limb after the systolic high pressure, representing the end of the systolic phase in the entire cardiac cycle. It is a transient pressure fluctuation caused by aortic valve closure and is usually located in the anterior segment of the descending limb.
[0111] It should be noted that a pulse wave waveform can include multiple waveforms, and correspondingly, the diastolic point, systolic point, and dilatational notch can all include multiple waveforms.
[0112] Specifically, the relaxation point can be the location of the first peak in each waveform. The contraction point can be the location of the second peak in each waveform.
[0113] In other possible embodiments, the timing features may also include the duration features between the starting point of the pulse wave waveform and each timing feature point, as well as the duration features between each timing feature point.
[0114] For example, please refer to Figure 7 , Figure 7 This is a schematic diagram of timing features provided in an embodiment of this application. For example... Figure 7 As shown, taking the pulse wave as the target waveform as an example, W1 represents the pulse wave waveform, W2 represents the first derivative waveform, and W3 represents the second derivative waveform. The shaded area indicates the vasoconstriction phase, and the unshaded area indicates the vasodilation phase. Point a represents the peak of the second derivative waveform, point b represents the trough of the second derivative waveform, point p represents the peak of the first derivative waveform, point SP is the systolic peak, point DN is the dicrotic notch, and point DP is the diastolic peak. Temporal characteristics may include: t_a, t_b, t_p, t_ap, t_up, t_dp, t_ptt, t_down, and t_de.
[0115] Combination Figure 7 t_a represents the time from the start point of the pulse wave waveform to point a, t_b represents the time from the start point of the pulse wave waveform to point b, t_p represents the time from the start point of the pulse wave waveform to point p, t_ap represents the time from point a to point p, t_up represents the time from the start point of the pulse wave waveform to point SP, t_dp represents the time from the start point of the pulse wave waveform to point DP, t_ptt represents the time from point SP to point DP, t_down represents the time from point SP to the end of the cycle, and t_de represents the time from point DP to the end of the cycle.
[0116] In S104, the vital signs parameters of the object to be detected are calculated based on the time-series characteristics.
[0117] In this embodiment of the application, in conjunction with S103, after the terminal device obtains the time-series features, since the time-series features include multiple time-series feature points, the terminal device can calculate the vital signs parameters of the object to be detected based on the duration between the multiple time-series feature points.
[0118] In practical applications, vital signs parameters include, but are not limited to, respiratory rate, heart rate, and blood pressure.
[0119] In one embodiment of this application, the terminal device can sequentially input temporal features into detection models for detecting different vital sign parameters for processing, thereby obtaining various vital sign parameters. The detection models for different vital sign parameters are all trained from pre-constructed deep learning models.
[0120] In another embodiment of this application, in order to improve the accuracy of determining different vital sign parameters, the terminal device may also implement step S104 according to the following steps, detailed below:
[0121] Based on the type of each vital sign parameter, determine the calculation method corresponding to each vital sign parameter;
[0122] Each of the aforementioned time-series features is calculated using different calculation methods to obtain the parameters of each vital characteristic.
[0123] In this embodiment, the types of vital sign parameters include, but are not limited to, respiratory type, heart rate type, and blood pressure type. The respiratory rate type is the respiratory type, the heart rate type is the heart rate type, and the blood pressure type is the blood pressure type.
[0124] It should be noted that different types of vital sign parameters have different calculation methods. Therefore, in this embodiment, the terminal device can calculate multiple time-series features based on the calculation method corresponding to a certain vital sign parameter to obtain the specific value of that vital sign parameter.
[0125] Specifically, when the vital sign parameter is heart rate, its calculation method can be based on the distance between each contraction point in the time series characteristics, that is, the interval between each contraction point.
[0126] When the vital sign parameter is blood pressure, since blood pressure includes diastolic blood pressure (DBP) and systolic blood pressure (SBP), its calculation can be performed by inputting multiple time-series features into separate systolic and diastolic blood pressure calculation models. Both the systolic and diastolic blood pressure calculation models are constructed using the Moens-Korteweg formula, the Hughes formula, the Bramwell-Hill formula, and mathematical models of transit time (TT).
[0127] Based on this, in one embodiment of this application, in order to improve the accuracy of blood pressure calculation, the terminal device can specifically use, as follows: Figure 8 The target diastolic blood pressure and target systolic blood pressure are calculated using steps S401 to S404, as detailed below:
[0128] In S401, the average diastolic blood pressure and average systolic blood pressure of the object to be detected are obtained, as well as the average transmission time of the target waveform is obtained.
[0129] In S402, a fitting factor is determined based on the attribute information of the object to be detected.
[0130] In S403, the average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time are imported into a preset diastolic blood pressure calculation model to calculate the target diastolic blood pressure.
[0131] In S404, the diastolic blood pressure, the average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time are imported into a preset diastolic blood pressure calculation model to calculate the target systolic blood pressure.
[0132] It should be noted that both the average diastolic blood pressure and the average systolic blood pressure are used to characterize the average blood pressure obtained from the measurements.
[0133] In this embodiment, combined with Figure 7 The time series features can include: t_a, t_b, t_p, t_ap, t_up, t_dp, t_ptt, t_down, and t_de.
[0134] The transmission time can specifically be the aforementioned timing characteristics or a combination of multiple timing characteristics.
[0135] For example, the combination of time-series features t_ap and t_de can be expressed as: t_muds = t_ap + t_de.
[0136] Based on this, the average transmission time is used to characterize the average value corresponding to the aforementioned transmission time obtained through measurement.
[0137] In this embodiment, the fitting factor is used as an intermediate parameter to characterize the Young's modulus of blood vessels.
[0138] Since different users have slightly different fitting factors, the terminal device can determine the corresponding fitting factor based on the attribute information of the object to be detected. This attribute information includes, but is not limited to, vascular parameters (such as diameter, length, wall thickness, and pressure).
[0139] In this embodiment, the preset diastolic blood pressure calculation model is as follows:
[0140]
[0141] Where DBP represents the target diastolic blood pressure, SBP0 represents the average systolic blood pressure, DBP0 represents the average diastolic blood pressure, γ represents the fitting factor, TT0 represents the average transit time, TT represents the transit time determined by multiple time-series features, and α represents a constant term. The value range of α is [0, 1].
[0142] The preset systolic blood pressure calculation mode is as follows:
[0143]
[0144] Where SBP represents the target systolic blood pressure, DBP represents the target diastolic blood pressure, SBP0 represents the average systolic blood pressure, DBP0 represents the average diastolic blood pressure, TT0 represents the average transit time, TT represents the transit time determined by multiple time-series features, and α represents a constant term. The value range of α is [0, 1].
[0145] As can be seen from the above, the parameter acquisition method provided in this application involves acquiring the radar reflection signal corresponding to the object to be detected; filtering the radar reflection signal to obtain the target waveform of the object to be detected; the target waveform refers to a waveform related to heartbeat; extracting features from the target waveform to obtain the corresponding time-series features; and calculating the vital signs parameters of the object to be detected based on the time-series features. Compared with the prior art, this application can filter the radar reflection signal to avoid interference from other signals and obtain a high-quality waveform related to heartbeat, thereby providing richer data for the acquisition of vital signs parameters. Subsequently, this application can obtain accurate and true vital signs parameters reflecting the object to be detected based on the extracted time-series features, thus improving the accuracy of vital signs parameter acquisition.
[0146] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0147] Corresponding to the parameter acquisition method described in the above embodiments, Figure 9 A schematic diagram of a parameter acquisition device according to an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown. (Refer to...) Figure 9 The parameter acquisition device 500 includes: a first acquisition unit 51, a first filtering unit 52, a feature extraction unit 53, and a first calculation unit 54. Wherein:
[0148] The first acquisition unit 51 is used to acquire the radar reflection signal corresponding to the object to be detected.
[0149] The first filtering unit 52 is used to filter the radar reflection signal to obtain the target waveform of the object to be detected; the target waveform refers to the waveform related to the heartbeat.
[0150] The feature extraction unit 53 is used to extract features from the target waveform to obtain the time-series features corresponding to the target waveform.
[0151] The first calculation unit 54 is used to calculate the vital signs parameters of the object to be detected based on the time series characteristics.
[0152] In one embodiment of this application, the first filtering unit 52 specifically includes: a demodulation unit, an analysis unit, and a second filtering unit. Wherein:
[0153] The demodulation unit is used to demodulate the radar reflection signal to obtain a vibration signal; the vibration signal is used to characterize the minute vibration signals of the skin of the object to be detected due to cardiovascular activity.
[0154] The analysis unit is used to perform frequency domain analysis on the vibration signal to determine the breathing signal and the corresponding harmonic signal.
[0155] The second filtering unit is used to filter the radar reflection signal based on the breathing signal and the harmonic signal to obtain the target waveform.
[0156] In one embodiment of this application, the second filtering unit specifically includes: a second calculation unit, a third filtering unit, a quantity determination unit, and a fourth filtering unit. Wherein:
[0157] The second calculation unit is used to calculate respiratory indicators based on the respiratory signal and the harmonic signal.
[0158] The third filtering unit is used to perform high-pass filtering on the radar reflection signal to obtain the initial filtered signal.
[0159] The quantity determination unit is used to determine the target number of filters based on the breathing index.
[0160] The fourth filtering unit is used to input the initial filtered signal into the target number of filters for filtering processing to obtain the target waveform.
[0161] In one embodiment of this application, the second calculation unit specifically includes: a frequency component determination unit and a third calculation unit. Wherein:
[0162] The frequency component determination unit is used to determine the main frequency component of breathing from the breathing signal and the harmonic signal.
[0163] The third calculation unit is used to calculate the respiratory index based on the main frequency component.
[0164] In one embodiment of this application, the time-series features include multiple components, and the vital sign parameters include multiple components; the first calculation unit 54 specifically includes: a mode determination unit and a fourth calculation unit. Wherein:
[0165] The method determination unit is used to determine the calculation method corresponding to each vital characteristic parameter based on the type of each vital characteristic parameter.
[0166] The fourth calculation unit is used to calculate the multiple time-series features based on different calculation methods to obtain each of the vital characteristic parameters.
[0167] In one embodiment of this application, the time-series features include multiple components, the vital sign parameters include blood pressure, and the blood pressure includes diastolic and systolic blood pressure; the first calculation unit 54 specifically includes: a second acquisition unit, a factor determination unit, a fifth calculation unit, and a sixth calculation unit. Wherein:
[0168] The second acquisition unit is used to acquire the average diastolic blood pressure and average systolic blood pressure of the object to be detected, and to acquire the average transmission time of the target waveform.
[0169] The factor determination unit is used to determine the fitting factor based on the attribute information of the object to be detected.
[0170] The fifth calculation unit is used to import the average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time into a preset diastolic blood pressure calculation model to calculate the target diastolic blood pressure.
[0171] The sixth calculation unit is used to import the target diastolic blood pressure, the average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time into a preset diastolic blood pressure calculation model to calculate the target systolic blood pressure.
[0172] In one embodiment of this application, the timing features include: the timestamps of the diastolic point, the systolic point, and the dicrotic notch in the target waveform, the peak points of the first derivative waveform corresponding to the target waveform, and the peak points of the second derivative waveform corresponding to the target waveform.
[0173] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.
[0174] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0175] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 10 As shown, the terminal device 6 in this embodiment includes: at least one processor 60 ( Figure 10 (Only one is shown) a processor, a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60, wherein the processor 60 executes the computer program 62 to implement the steps in any of the above-described parameter acquisition method embodiments.
[0176] The terminal device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 10 This is merely an example of terminal device 6 and does not constitute a limitation on terminal device 6. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.
[0177] The processor 60 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.
[0178] In some embodiments, the memory 61 may be an internal storage unit of the terminal device 6, such as the RAM of the terminal device 6. In other embodiments, the memory 61 may be an external storage device of the terminal device 6, such as a plug-in hard drive, smart media card (SMC), secure digital card (SD) card, flash card, etc., equipped on the terminal device 6. Furthermore, the memory 61 may include both internal and external storage units of the terminal device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.
[0179] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.
[0180] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.
[0181] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.
[0182] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0183] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for obtaining parameters, characterized in that, include: Acquire the radar reflection signal corresponding to the object to be detected; The radar reflection signal is filtered to obtain the target waveform of the object to be detected; The target waveform refers to a waveform related to heartbeat; Feature extraction is performed on the target waveform to obtain the time-series features corresponding to the target waveform; Based on the aforementioned temporal characteristics, the vital signs parameters of the object to be detected are calculated.
2. The parameter acquisition method as described in claim 1, characterized in that, The step of filtering the radar reflection signal to obtain the target waveform of the object to be detected includes: The radar reflection signal is demodulated to obtain a vibration signal; the vibration signal is used to characterize the minute vibration signals of the skin of the object under test caused by cardiovascular activity. Frequency domain analysis was performed on the vibration signal to determine the respiratory signal and the corresponding harmonic signal. Based on the breathing signal and the harmonic signal, the radar reflection signal is filtered to obtain the target waveform.
3. The parameter acquisition method as described in claim 2, characterized in that, The step of filtering the radar reflection signal based on the breathing signal and the harmonic signal to obtain the target waveform includes: Based on the respiratory signal and the harmonic signal, the respiratory index is calculated; The radar reflection signal is subjected to high-pass filtering to obtain the initial filtered signal; Based on the respiratory indicators, the target number of filters is determined; The initial filtered signal is input to the target number of filters for filtering to obtain the target waveform.
4. The parameter acquisition method as described in claim 3, characterized in that, The respiratory index is calculated based on the respiratory signal and the harmonic signal, including: The dominant frequency component of respiration is determined from the respiratory signal and the harmonic signal; The respiratory index is calculated based on the dominant frequency component.
5. The parameter acquisition method as described in claim 1, characterized in that, The temporal features include multiple components, and the vital sign parameters include multiple components; the calculation of the vital sign parameters of the object to be detected based on the temporal features includes: Based on the type of each vital sign parameter, determine the calculation method corresponding to each vital sign parameter; Each of the aforementioned time-series features is calculated using different calculation methods to obtain the parameters of each vital characteristic.
6. The parameter acquisition method as described in claim 1, characterized in that, The time-series features include multiple components, and the vital sign parameters include blood pressure, which includes target diastolic blood pressure and target systolic blood pressure. The calculation of the vital sign parameters of the subject under test based on the time-series features includes: The average diastolic blood pressure and average systolic blood pressure of the object to be detected are obtained, as well as the average transmission time of the target waveform. Based on the attribute information of the object to be detected, the fitting factor is determined; The average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time are imported into a preset diastolic blood pressure calculation model to calculate the target diastolic blood pressure. The target diastolic blood pressure, the average diastolic blood pressure, the second average systolic blood pressure, the fitting factor, multiple time-series features, and the average transit time are imported into a preset diastolic blood pressure calculation model to calculate the target systolic blood pressure.
7. The parameter acquisition method according to any one of claims 1-6, characterized in that, The timing features include: the timestamps of the diastolic point, the systolic point, and the dicrotic notch in the target waveform; the peak points of the first derivative waveform corresponding to the target waveform; and the peak points of the second derivative waveform corresponding to the target waveform.
8. A parameter acquisition device, characterized in that, include: The first acquisition unit is used to acquire the radar reflection signal corresponding to the object to be detected; The first filtering unit is used to filter the radar reflection signal to obtain the target waveform of the object to be detected; the target waveform refers to a waveform related to heartbeat. The feature extraction unit is used to extract features from the target waveform to obtain the time-series features corresponding to the target waveform; The first calculation unit is used to calculate the vital signs parameters of the object to be detected based on the time-series characteristics.
9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the parameter acquisition method as described in any one of claims 1 to 7.
10. A computer program product, characterized in that, It includes a computer program that, when run, implements the parameter acquisition method as described in any one of claims 1 to 7.