Heart rate determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a heart rate determination method and device, electronic equipment and a storage medium. The method comprises the steps that echo signals are received based on radar, the echo signals and emission signals are subjected to frequency mixing, heartbeat signals are obtained, multiple heartbeat phase signals in a target area are determined according to the heartbeat signals and the preset chest size of a target object, and the heartbeat phase signals are phase signals of different distances and different angles; determining the correlation intensity between every two heartbeat phase signals which are adjacent in distance and angle, selecting a plurality of first heartbeat phase signals from the plurality of heartbeat phase signals according to the correlation intensity, determining the signal-to-noise ratio of the first heartbeat phase signals, determining a second preset number of second heartbeat phase signals according to the signal-to-noise ratio, and determining the second preset number of second heartbeat phase signals according to the second preset number of second heartbeat phase signals. The heart rate classification interval of the second heartbeat phase signal is determined, the heart rate value of the heartbeat signal is determined according to the second heartbeat phase signal and the heart rate classification interval, accurate determination of the heart rate is achieved, the robustness and classification accuracy of heartbeat detection are improved, and the method is suitable for non-contact heart rate detection in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of signal processing, and in particular to a heart rate determination method, device, electronic device and storage medium. Background Art

[0002] With the development of non-contact vital signs monitoring technology, radar-based heartbeat detection has been widely studied due to its advantages such as non-sensing, long-distance, and all-weather.

[0003] However, in related technologies, since the echo signal received by the radar contains information from multiple scattering points, and the amplitude of chest movement caused by the heartbeat is extremely small, it is easily affected by environmental noise, body motion interference, and multi-target aliasing, making it difficult to accurately extract and identify the heartbeat signal, resulting in difficulty in accurately determining the heart rate. Summary of the Invention

[0004] The present invention provides a heart rate determination method, device, electronic device and storage medium to solve the problems in related technologies of difficulty in extracting effective heartbeat information from multi-source signals and susceptibility of classification results to interference.

[0005] According to one aspect of the present invention, a method for determining a heart rate is provided, the method comprising:

[0006] Based on the radar receiving echo signal, the echo signal is mixed with the transmission signal to obtain a heartbeat signal, and multiple heartbeat phase signals in the target area are determined according to the heartbeat signal and the preset chest size of the target object, wherein the heartbeat phase signals are phase signals at different distances and different angles;

[0007] Determine the correlation strength between each two of the heartbeat phase signals that are adjacent in distance and angle, select multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, and determine the signal-to-noise ratio of the first heartbeat phase signals;

[0008] A second preset number of second heartbeat phase signals is determined according to the signal-to-noise ratio, a heart rate classification interval of the second heartbeat phase signals is determined, and a heart rate value of the heartbeat signal is determined according to the second heartbeat phase signals and the heart rate classification interval.

[0009] According to another aspect of the present invention, there is provided a heart rate determination device comprising:

[0010] a heartbeat phase signal determination module, configured to receive an echo signal from a radar, mix the echo signal with a transmitted signal to obtain a heartbeat signal, and determine a plurality of heartbeat phase signals in a target area according to the heartbeat signal and a preset chest cavity size of the target object, wherein the heartbeat phase signals are phase signals at different distances and angles;

[0011] a signal-to-noise ratio determination module, configured to determine a correlation strength between each two heartbeat phase signals that are adjacent in distance and angle, select a plurality of first heartbeat phase signals from the plurality of heartbeat phase signals based on the correlation strength, and determine a signal-to-noise ratio of the first heartbeat phase signals;

[0012] A heart rate value determination module is used to determine a second preset number of second heartbeat phase signals based on the signal-to-noise ratio, determine the heart rate classification interval of the second heartbeat phase signal, and determine the heart rate value of the heartbeat signal based on the second heartbeat phase signal and the heart rate classification interval.

[0013] According to another aspect of the present invention, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the heart rate determination method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the heart rate determination method according to any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention is to receive echo signals based on radar, mix the echo signals with the transmitted signals to obtain heartbeat signals, and determine multiple heartbeat phase signals in the target area according to the heartbeat signals and the preset chest cavity size of the target object, wherein the heartbeat phase signals are phase signals of different distances and different angles, which can realize accurate positioning and multi-angle feature extraction of the heartbeat signals of the target object; then, determine the correlation strength between every two heartbeat phase signals with adjacent distances and angles, select multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, determine the signal-to-noise ratio of the first heartbeat phase signals, and effectively screen high The heartbeat phase signal with high correlation and excellent signal-to-noise ratio improves the accuracy and reliability of subsequent heart rate classification; finally, a second preset number of second heartbeat phase signals are determined according to the signal-to-noise ratio, the heart rate classification interval of the second heartbeat phase signal is determined, and the heart rate value of the heartbeat signal is determined according to the second heartbeat phase signal and the heart rate classification interval. It can screen high signal-to-noise ratio signals and accurately determine the heart rate of the heartbeat signal, which solves the problems in related technologies that it is difficult to extract effective heartbeat information from multi-source signals and the classification results are easily interfered with, realizes accurate determination of heart rate, improves the robustness and classification accuracy of heartbeat detection, and is suitable for non-contact heart rate detection in complex environments.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a heart rate determination method provided according to embodiment 1 of the present invention;

[0022] Figure 2 is a flow chart of a heart rate determination method provided according to embodiment 2 of the present invention;

[0023] Figure 3 2 is a schematic structural diagram of a heart rate determination device provided according to a third embodiment of the present invention;

[0024] Figure 4 is a flow chart of a heart rate determination method provided by an embodiment of the present invention;

[0025] Figure 5 2 is a schematic structural diagram of an electronic device for implementing the heart rate determination method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0029] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0030] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0031] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0032] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0033] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0034] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0035] Example 1

[0036] Figure 1 A flowchart of a heart rate determination method is provided for embodiment 1 of the present invention. This embodiment is applicable to non-contact heart rate detection in complex environments. The method can be performed by a heart rate determination device, which can be implemented in the form of hardware and / or software. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, PC or server, etc.

[0037] like Figure 1 As shown, the method may specifically include:

[0038] S110. Based on the radar receiving echo signal, the echo signal is mixed with the transmission signal to obtain a heartbeat signal, and multiple heartbeat phase signals in the target area are determined according to the heartbeat signal and a preset chest size of the target object, wherein the heartbeat phase signals are phase signals at different distances and different angles.

[0039] The echo signal can be understood as the signal received by the radar antenna after the electromagnetic wave emitted by the radar system is reflected from an object. By analyzing the echo signal, various information about the target object, such as distance, speed, and angle, can be obtained. The transmitted signal can be understood as the electromagnetic wave signal emitted by the radar system for detecting the target. This transmitted signal serves as the basis for comparison with the received echo signal to determine information such as the target object's location. Frequency mixing can be understood as the process of mixing the radar's received echo signal with the original transmitted signal to generate a new frequency signal, thereby extracting a signal containing heartbeat information. The heartbeat signal can be understood as the mixed signal, which contains the relevant characteristics of the changes in the electromagnetic wave reflection characteristics in the chest area caused by the target object's heartbeat and can reflect information such as the heartbeat rhythm. The target object can be understood as the individual or entity whose heartbeat activity the radar system is attempting to monitor. In this embodiment, the target object primarily refers to the human body, specifically a person whose heartbeat activity is detected by receiving the radar echo signal. The preset chest size can be understood as the approximate size range of the target object's chest cavity set according to the category to which the target object belongs (such as adults, children, etc.) or measured by other means, which is used to determine the effective detection range and spatial resolution of the heartbeat signal, and help distinguish the heartbeat phase signals at different distances and angles. The heartbeat phase signal can be understood as a signal representing the state of heartbeat activity obtained at different distances and angles of the heartbeat signal, reflecting the heartbeat characteristics at different positions in the target area. The distance can be understood as the actual physical distance between the radar and the detected target object. The angle can be understood as the direction of the target object relative to the radar, that is, the angle of arrival (DOA), which is used to determine in which direction the target (such as the heart, etc.) is located. The distance and angle work together to enable the radar system to accurately locate the position of the target.

[0040] On the basis of the above scheme, optionally, the method of determining multiple heartbeat phase signals in the target area based on the heartbeat signal and the preset chest size of the target object includes: performing digital-to-analog conversion on the heartbeat signal to obtain a discrete signal, and extracting a distance spectrum of the discrete signal according to the fast time dimension; determining a target image according to the antenna dimension and the distance spectrum, wherein the target image is used to characterize the relationship between distance and angle; determining the angle and distance corresponding to the maximum energy in the spatial spectrum of the target image, and determining the target area according to the angle, the distance and the preset chest size of the target object; determining channel signals at different angles within the target area, extracting phase information of the channel signal according to the slow time dimension, and determining the heartbeat phase signal according to the phase information and a preset high-pass filter.

[0041] The digital-to-analog conversion can be understood as the process of converting a continuous analog signal into a discrete digital signal. In this embodiment, it is used to convert the heartbeat signal into a digital form that can be further processed. The discrete signal can be understood as a series of discrete values obtained after the digital-to-analog conversion, representing the value of the heartbeat signal at a specific time point. The fast time dimension can be understood as the time dimension required for the radar signal to travel to and from the target, which is used to extract information about the target's distance. In this embodiment, by analyzing the fast time dimension, techniques such as the Doppler effect can be used to extract target distance information, thereby obtaining a range spectrum, which provides an important basis for subsequent determination of the target image. The range spectrum can be understood as a frequency spectrum reflecting the signal intensity distribution at different distances, obtained by processing and analyzing the discrete signal in the fast time dimension. It is used to display the characteristics of the target signal in the distance dimension. The antenna dimension can be understood as a dimension related to the antenna direction, which is used to distinguish the signal distribution at different spatial angles and reflects the characteristics of the signal reflected from different directions. The target image can be understood as a two-dimensional or three-dimensional image generated by combining the antenna dimension information and the range spectrum, which is used to represent the target object's position in space (i.e., the relationship between distance and angle). The spatial spectrum can be understood as displaying the signal power distribution at different directions and distances within the target image, used to identify the direction and distance of the target object. The energy maximum can be understood as the point of maximum signal strength determined in the spatial spectrum. The preset chest size can be understood as a reference value for the target object's chest size. By using the preset chest size, the algorithm can be better adjusted to match the target object's physical characteristics. The target area can be understood as the target object's chest area defined based on the preset chest size and the angle and distance determined from the spatial spectrum, used to more accurately detect heartbeat activity. The channel signal can be understood as the signal carried by the signal channel corresponding to different angles within the target area. Each channel signal represents a component of the heartbeat signal received from a different direction. The slow time dimension can be understood as a dimension used in radar signal processing to describe the target's motion changes over a short period of time, used to extract target motion characteristics, such as phase information such as chest vibration caused by heartbeats. The phase information can be understood as the phase changes of the channel signal in the slow time dimension, used to reflect the phase characteristics of chest vibration during heartbeats. The preset high-pass filter can be understood as a pre-set high-pass filter that allows signals above a certain frequency to pass through, while suppressing signals below this frequency. It is used to remove low-frequency interference components in the heartbeat signal, such as slow movement caused by breathing, static noise, etc., and retain high-frequency phase information related to the heartbeat, thereby improving the quality and accuracy of the heartbeat phase signal.

[0042] In an optional implementation, the echo signal received by the radar is mixed with the transmitted signal to obtain a heartbeat signal. The discrete signal obtained after the digital-to-analog conversion of the heartbeat signal can be expressed as Where m represents the slow time index, n represents the fast time index, and k represents the number of receiving antennas. A fast Fourier transform (FFT) is performed on the discrete signal along the fast time dimension to obtain the range spectrum Y(m, r, k), where r is the range bin index. A two-dimensional Capon is then performed on Y(m, r, k) along the antenna dimension to produce a range-angle heatmap, representing the angle of arrival (DOA) estimates at different ranges and angles.

[0043] Based on the heat map, the 2D-CFAR algorithm is used to find the angle corresponding to the maximum value of the spatial spectrum and its corresponding distance, which is expressed as (r max ,j max ). According to the size of the human chest, the distance-angle candidate range is defined. Specifically: the distance-angle site (r max ,j max ) as the center, select Δr distance units on the left and right: [r max -Δr, r max +Δr], Δj angle units on the left and right: [j max -Δj,j max +Δj], and obtain the coarse positioning area of the chest cavity:

[0044] span{r, j}={(r, j)|r∈[r max -Δr, r max +Δr],j∈[j max -Δj,j max +Δj]};

[0045] In this area, a minimum mean square error beamformer is used to synthesize multiple channel signals to enhance the target signal and suppress interference and noise. For a given angular position j1, there is:

[0046]

[0047] in, Represents the channel signal, N RX Indicates the number of receiving antennas, w H =[w(0), ..., w(N RX -1)] T According to the angle j max The designed beamformer weight vector.

[0048] For the signal sequences of each angle and distance obtained above, the phase information is extracted along the slow time dimension to obtain H(j, m, r), and the differential cross multiplication (DACM) algorithm is used. Then, in order to remove the low-frequency noise in the signal, a fourth-order Butterworth high-pass filter is designed with a cutoff frequency of 0.85Hz to obtain the heartbeat phase signal H iir (j, m, r).

[0049] This technical solution uses radar to acquire heartbeat signals, and combines the chest size of the target object to accurately locate the target area, effectively improving the accuracy of heartbeat phase signal extraction; using fast-time dimension and antenna dimension information to construct a target image, it is possible to achieve a joint analysis of target distance and angle; then, phase information is extracted through the slow-time dimension and combined with a high-pass filter to effectively suppress noise interference and extract high-quality heartbeat phase signals, providing a reliable data basis for subsequent heart rate classification and health testing.

[0050] S120. Determine the correlation strength between each two heartbeat phase signals that are adjacent in distance and angle, select multiple first heartbeat phase signals from the multiple heartbeat phase signals based on the correlation strength, and determine the signal-to-noise ratio of the first heartbeat phase signals.

[0051] Among them, the correlation strength can be understood as an indicator for measuring the similarity or correlation between two heartbeat phase signals. It can be understood that the higher the correlation strength, the more similar the two heartbeat phase signals are, and they may come from the heartbeat activity at the same or similar position. The first heartbeat phase signal can be understood as a plurality of heartbeat phase signals screened out from all heartbeat phase signals according to the correlation strength between them, which are used for further processing of subsequent signals. The signal-to-noise ratio can be understood as the ratio of signal strength to noise strength, which is used to evaluate the quality of heartbeat phase signals. Signals with high signal-to-noise ratio are more suitable for heart rate classification.

[0052] On the basis of the above scheme, optionally, the determination of the correlation strength between each two heartbeat phase signals that are adjacent in distance and angle, and the selection of multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength include: determining the correlation coefficient between each two heartbeat phase signals that are adjacent in distance and angle, and determining the correlation strength according to the correlation coefficient; binarizing the correlation strength according to a preset correlation strength threshold, and filling the result of the binarization into a preset spatial matrix to obtain a spatial binary image, wherein the preset spatial matrix is used to characterize the positional relationship between each two heartbeat phase signals; dividing the heartbeat phase signal into regions according to the adjacent relationship of the correlation strength in the spatial binary image to obtain the heartbeat phase signals in multiple different regions, and determining multiple different first heartbeat phase signals according to the correlation strengths of different regions.

[0053] Among them, the correlation coefficient can be understood as a measure of the similarity or correlation between heartbeat phase signals with adjacent distances and adjacent angles. In this embodiment, the smallest correlation coefficient of heartbeat phase signals with adjacent distances and adjacent angles can be selected as the correlation strength. The correlation strength threshold can be understood as a pre-set numerical standard for judging whether the correlation strength between heartbeat phase signals is strong enough to be considered a meaningful connection. For example, only when the correlation strength exceeds the correlation strength threshold will it be considered to be significantly correlated. The binarization process can be understood as a process of converting the correlation strength into a binary form (usually 0 and 1). In this embodiment, by comparing the correlation strength with the preset correlation strength threshold, it is determined whether each heartbeat phase signal pair is marked as correlated (1) or uncorrelated (0). The spatial matrix can be understood as a mathematical structure for characterizing the spatial strength between each two heartbeat phase signals, which can be a two-dimensional array, in which each element represents the relationship state (correlated or uncorrelated) between a pair of heartbeat phase signals. The spatial binary image can be understood as an image representation formed by mapping the result of the binarization process to the spatial matrix, which can intuitively show the correlation between heartbeat phase signals and help the subsequent classification and selection process. The region division can be understood as a process of grouping heartbeat phase signals according to the adjacent relationship of correlation intensities in the spatial binary image, which is used to divide signals with similar correlation into a region for further analysis.

[0054] In an optional implementation, when the range and angle resolutions are sufficient, vital sign signal motion typically affects multiple adjacent resolution units, and the signals between these units exhibit strong correlation. Based on this characteristic, the spatial correlation strength C(j, r) is first defined, determined by calculating the minimum correlation coefficient between the signals of adjacent angle and range units. The correlation strength expression for the qth angle-range unit is:

[0055] C(j q , r q )=min(ρ[(j q , r q ), (j q , r q+1 )],ρ[(j q , r q ), (j q+1 , r q )],ρ[(j q , r q ), (j q+2 , r q )]);

[0056] Among them, the formula for calculating the correlation coefficient between two signals is:

[0057]

[0058] Next, set a correlation strength threshold T corr , the correlation strength below the correlation strength threshold will be set to 0, otherwise it will be set to 1, thereby screening out valid signal units and generating a spatial binary image. Then, the regional signal selector is used to classify these valid units, treating the connected bright spot units as the same type of signal, and selecting the signal corresponding to the maximum correlation coefficient as the potential heartbeat signal. Finally, N h Potential heartbeat phase signal S h (n h , m).

[0059] This technical solution analyzes the correlation of heartbeat phase signals at adjacent distances and angles, constructs a spatial binary image using correlation coefficients and threshold processing, and models the spatial distribution characteristics of the signals. Based on this, signals are classified and a representative signal from each class is selected as the first heartbeat phase signal. This effectively reduces redundant information, retains the most representative and independent signal features, and improves the accuracy and efficiency of subsequent signal-to-noise ratio analysis and heart rate classification.

[0060] Based on the above scheme, optionally, determining the signal-to-noise ratio of the first heartbeat phase signal includes: determining the maximum value in the spectrum of the first heartbeat phase signal within the target heart rate range, and determining the sum of the spectrum values outside the target heart rate range, and determining the signal-to-noise ratio of the first heartbeat phase signal based on the ratio of the maximum value and the sum.

[0061] The target heart rate range can be understood as a pre-set heart rate interval, which can be set based on the normal human heart rate range, such as 50 to 90 beats per minute. The maximum value can be understood as the peak or highest point in the spectrum within the target heart rate range, which generally represents the intensity of the main heart rate.

[0062] An optional implementation method, in N h Among the first heartbeat phase signals, the spectrum of the i-th first heartbeat phase signal can be expressed as:

[0063]

[0064] Where i=1,...,N h ,m w is the first heartbeat phase signal observation window, is the frequency of the heartbeat waveform spectrum, and FPS is the frame rate of the radar. Then the signal-to-noise ratio of the i-th first heartbeat phase signal waveform can be expressed as:

[0065]

[0066] Among them, f′∈[0.85,2]Hz is the human heart rate range, I1∈[0,0.85]Hz,

[0067] This technical solution determines the signal-to-noise ratio by calculating the ratio of the maximum spectrum within the target heart rate range to the sum of the spectrum values outside the range. This can effectively highlight the target heartbeat signal and suppress noise interference, thereby improving the accuracy and reliability of heartbeat detection and providing high-quality data support for subsequent heart rate analysis.

[0068] S130. Determine a second preset number of second heartbeat phase signals according to the signal-to-noise ratio, determine a heart rate classification interval of the second heartbeat phase signals, and determine a heart rate value of the heartbeat signal according to the second heartbeat phase signals and the heart rate classification interval.

[0069] Among them, the second heartbeat phase signal can be understood as a plurality of heartbeat phase signals that are screened again based on the signal-to-noise ratio on the basis of the first heartbeat phase signal. The second heartbeat phase signal is a screened signal used to improve the accuracy of heart rate classification. The heart rate classification interval can be understood as a pre-set heart rate range interval used for classifying the heart rate and subsequently determining the heart rate value. The heart rate value can be understood as the heart rate derived based on the second heartbeat phase signal and the heart rate classification interval, which is a specific numerical value used to reflect the heart rate status of the target object and is used for health detection or early warning.

[0070] An optional implementation method is to h The signal-to-noise ratios of the first heartbeat phase signals are arranged in descending order, and generally 5 signals are pre-selected as the second heartbeat phase signals.

[0071] On the basis of the above solution, optionally, the method for determining the heart rate classification interval includes: determining the heart rate range of the target object, dividing the heart rate range according to a preset heart rate per unit time, and obtaining the heart rate classification interval.

[0072] The heart rate range can be understood as an interval divided according to the target subject's heart rate range. Heart rate refers to the number of heartbeats per unit time, and the heart rate range defines the range of heartbeats. The preset unit time can be understood as a time unit pre-set when calculating heart rate, usually minutes (min), that is, heart rate is generally expressed as the number of heartbeats per unit time (per minute).

[0073] In an optional implementation, the heart rate of the crowd is divided into 13 categories at intervals of 3 BPM between [50, 89] beats per minute (BPM), and they are marked as C1 to C 13 That is, the classification intervals are [50, 53),

[0074] [53,56),…,[86,89].

[0075] By adopting this technical solution, by dividing the heart rate classification intervals according to the heart rate range and heart rate per unit time of the target object, a clear and reasonable heart rate classification system can be established, providing a clear judgment basis for subsequent classification models, thereby improving the accuracy and applicability of heart rate recognition.

[0076] On the basis of the above scheme, optionally, determining the heart rate value of the heartbeat signal according to the second heartbeat phase signal and the heart rate classification interval includes: obtaining a bandpass filter corresponding to the heart rate classification interval, determining a third heartbeat phase signal according to the bandpass filter and the second heartbeat phase signal, performing Fourier transform on the third heartbeat phase signal, determining a third preset number of third heartbeat phase signals according to the transformation result, determining the peak frequency of the third heartbeat phase signal, determining a frequency difference according to the center frequency of the bandpass filter and the peak frequency, and determining the heart rate value of the heartbeat signal according to the minimum value of the frequency difference.

[0077] Among them, the bandpass filter can be understood as allowing signals within a specific frequency range to pass through while suppressing signals of other frequencies. In this embodiment, the bandpass filter is designed for each classification interval and is used to further process the heartbeat phase signal. The third heartbeat phase signal can be understood as the heartbeat phase signal obtained after bandpass filtering. The filtered signal is optimized for a specific heart rate classification interval, providing a basis for further analysis. The peak frequency can be understood as the frequency corresponding to the maximum amplitude appearing in the spectrum analysis result, which is used to represent the most significant frequency component in the heartbeat phase signal, corresponding to the actual heart rate value. The center frequency can be understood as the middle value of the frequency range allowed to pass by the bandpass filter. For heart rate detection, the center frequency corresponds to the expected heartbeat frequency within the heart rate classification interval. The frequency difference can be understood as the difference between the center frequency of the bandpass filter and the peak frequency of the third heartbeat phase signal.

[0078] An optional implementation method is to first design a bandpass filter suitable for different heart rate classification intervals, determine the center frequency of each heart rate classification interval, and define it as the average of the adjacent boundary frequencies. Based on each center frequency, set the upper and lower limits, and create thirteen fourth-order Butterworth bandpass filters with different frequencies, marked as F1~F 13Then, the prediction results obtained by the LSTM classification network are used to calculate the center frequency f of the corresponding classification interval. mid (3.5Hz on each side), on the one hand, a bandpass filter is adapted to the initial feature matrix M according to this value, and then the five peak frequencies obtained after the peak detection of the positive half-axis spectrum after the N-point FFT transformation are used as the pre-selected output results of the fine estimation; on the other hand, the peak frequency is used as a comparison standard for the final selection, and f is found among these five peak frequencies. * So that f * and the f of the bandpass filter where it is located mid The difference is the smallest, and the peak frequency is used as the output result of the final heart rate value. The overall process of the program is as follows Figure 4 shown.

[0079] This technical solution uses the maximum probability to determine the preliminary category label, and then introduces the frequency difference minimization criterion to select the optimal bandpass filter, thereby accurately locating the target classification interval, effectively improving the accuracy and robustness of heart rate classification. It not only utilizes the discriminative ability of the machine learning model, but also integrates the constraints of the signal frequency domain characteristics, enhancing the reliability of the classification results. It is suitable for non-contact heart rate detection scenarios in complex environments.

[0080] In an optional implementation, the mean absolute error (MAE), root mean square error (RMSE), and the average real-time heart rate estimation error within ±2 bpm (Two-BPM Precision) are used to evaluate the effectiveness of the method. The formula is as follows:

[0081]

[0082] Among them, n represents the detection time, i represents the current time, and f estimated，i and f biopac，i They represent the heart rate values estimated by using this method and BIOPAC to extract the heartbeat signal at the current moment.

[0083] This method was used to test 21 experimental subjects (12 males and 9 females). Each test lasted for 10 minutes in each sleeping position, namely, lying on the back, side, and stomach. The heart rate result was output once per second. The experimental results showed that the MAE was 1.06BPM, the RMSE was 1.54BPM, and the Two-BPM Precision was 93.80%.

[0084] The technical solution of the embodiment of the present invention is to receive echo signals based on radar, mix the echo signals with the transmitted signals to obtain heartbeat signals, and determine multiple heartbeat phase signals in the target area according to the heartbeat signals and the preset chest cavity size of the target object, wherein the heartbeat phase signals are phase signals of different distances and different angles, which can realize accurate positioning and multi-angle feature extraction of the heartbeat signals of the target object; then, determine the correlation strength between every two heartbeat phase signals with adjacent distances and angles, select multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, determine the signal-to-noise ratio of the first heartbeat phase signals, and effectively screen high The heartbeat phase signal with high correlation and excellent signal-to-noise ratio improves the accuracy and reliability of subsequent heart rate classification; finally, a second preset number of second heartbeat phase signals are determined according to the signal-to-noise ratio, the heart rate classification interval of the second heartbeat phase signal is determined, and the heart rate value of the heartbeat signal is determined according to the second heartbeat phase signal and the heart rate classification interval. It can screen high signal-to-noise ratio signals and accurately determine the heart rate of the heartbeat signal, which solves the problems in related technologies that it is difficult to extract effective heartbeat information from multi-source signals and the classification results are easily interfered with, realizes accurate determination of heart rate, improves the robustness and classification accuracy of heartbeat detection, and is suitable for non-contact heart rate detection in complex environments.

[0085] Example 2

[0086] Figure 2 A flowchart of a heart rate determination method provided in the second embodiment of the present invention, this embodiment is based on the above embodiment, and further refines how to determine the heart rate classification interval of the second heartbeat phase signal. Optionally, determining the heart rate classification interval of the second heartbeat phase signal includes: performing Fourier transform on the second preset number of second heartbeat phase signals, combining the positive half-axis spectrum features after Fourier transform to obtain multiple feature matrices; inputting the multiple feature matrices into a trained classification model to process the feature matrices into probabilities of being located in each of the heart rate classification intervals through the classification model; determining the category label of the second heartbeat phase signal according to the probability, and determining the heart rate classification interval of the heartbeat signal according to the category label of the second heartbeat phase signal. For specific implementation methods, please refer to the description of this embodiment. Among them, technical features that are the same or similar to those in the above embodiment will not be repeated here.

[0087] like Figure 2 As shown, the method may specifically include:

[0088] S210. Based on the radar receiving echo signal, the echo signal is mixed with the transmission signal to obtain a heartbeat signal, and multiple heartbeat phase signals in the target area are determined according to the heartbeat signal and a preset chest size of the target object, wherein the heartbeat phase signals are phase signals at different distances and different angles.

[0089] S220. Determine the correlation strength between every two heartbeat phase signals that are adjacent in distance and angle, select multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, and determine the signal-to-noise ratio of the first heartbeat phase signals.

[0090] S230. Determine a second preset number of second heartbeat phase signals according to the signal-to-noise ratio, perform Fourier transform on the second preset number of second heartbeat phase signals, and combine the positive half-axis spectrum features after the Fourier transform to obtain multiple feature matrices.

[0091] Among them, the second heartbeat phase signal can be understood as a set of signals further screened from the first heartbeat phase signal, and the signal is selected for subsequent analysis based on criteria such as signal-to-noise ratio. The positive half-axis spectrum feature can be understood as the spectrum diagram obtained after Fourier transform, which only considers the part with positive frequency, and contains the main frequency information of the second heartbeat phase signal. The positive half-axis spectrum feature concentrates on the frequency components of the heartbeat signal and is crucial for determining the frequency and rhythm of the heartbeat. By analyzing the positive half-axis spectrum feature, key information related to the heartbeat can be extracted to provide data support for subsequent heart rate classification. The feature matrix can be understood as a data structure composed of the spectrum features of multiple second heartbeat phase signals. The feature matrix is a structured representation of the spectrum features of the heartbeat signal, which is convenient for input into the classification model for processing. Integrating the spectrum features of multiple second heartbeat phase signals can more comprehensively reflect the characteristics of the heartbeat signal and improve the accuracy of heart rate classification.

[0092] An optional implementation method is to preselect 5 second heartbeat phase signals to form an initial characteristic matrix M, and then perform N-point (generally N is an integer that is closest to the signal observation window length and is an exponential multiple of 2) FFT transformation on the characteristic matrix and take the positive half-axis spectrum to obtain the characteristic matrix M′.

[0093] S240: Input the plurality of feature matrices into a trained classification model, so that the classification model processes the feature matrices into probabilities of being in each of the heart rate classification intervals.

[0094] Among them, the classification model can be understood as a machine learning or deep learning model that has been trained with a large amount of data, which is used to process and classify the input feature matrix. The model has learned the characteristic patterns of different heart rate categories and is used to process each feature matrix into a probability of being in each heart rate classification interval. The heart rate classification interval can be understood as a pre-set heart rate range interval, which is used to divide the heart rate into different categories. The heart rate classification interval provides clear standards and boundaries for heart rate classification. By dividing the heart rate into different intervals, the heartbeat signal can be classified and analyzed in more detail. The probability can be understood as the output of the trained classification model, which indicates the possibility that the feature matrix belongs to each heart rate classification interval.

[0095] S250: Determine a category label for the second heartbeat phase signal based on the probability, determine a heart rate classification interval for the heartbeat signal based on the category label for the second heartbeat phase signal, and determine a heart rate value for the heartbeat signal based on the second heartbeat phase signal and the heart rate classification interval.

[0096] The category label can be understood as the result output by the classification model, which identifies the specific category or interval to which a given heartbeat signal belongs, and is used to indicate the heart rate category to which the heartbeat signal belongs.

[0097] On the basis of the above scheme, optionally, determining the category label of the second heartbeat phase signal according to the probability includes: for each of the feature matrices, determining the category corresponding to the maximum probability value of the feature matrix in each of the heart rate classification intervals as the category label of the second heartbeat phase signal corresponding to the feature matrix.

[0098] An alternative implementation uses heart rate values obtained at the same moment from the BIOPAC as labels. A LSTM-based machine learning model is proposed for the heart rate range classification task. The model consists of an LSTM layer with 128 hidden units, followed by a dropout layer to prevent overfitting. Next, the model integrates features through a thirteen-neuron fully connected layer, followed by a softmax layer that converts these features into probabilities for each class. Finally, the classification layer determines the class label for the input sequence based on the highest probability.

[0099] The technical solution of the embodiment of the present invention can effectively retain the frequency distribution law of the heartbeat signal by performing Fourier transform on the second heartbeat phase signal after screening, extracting its positive half-axis features in the frequency domain and constructing a feature matrix; the feature matrix is input into a trained classification model, and the model can identify and output the probability of the signal in each preset heart rate classification interval, thereby accurately determining the heart rate classification interval to which each heartbeat signal belongs, thereby improving the intelligence level and accuracy of heart rate classification.

[0100] Example 3

[0101] Figure 3 This is a structural diagram of a heart rate determination device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a heartbeat phase signal determination module 310, a signal-to-noise ratio determination module 320 and a heart rate value determination module 330.

[0102] The heartbeat phase signal determination module 310 is used to receive an echo signal based on a radar, mix the echo signal with the transmitted signal to obtain a heartbeat signal, and determine multiple heartbeat phase signals in the target area according to the heartbeat signal and the preset chest size of the target object, wherein the heartbeat phase signals are phase signals at different distances and angles; the signal-to-noise ratio determination module 320 is used to determine the correlation strength between each two heartbeat phase signals with adjacent distances and angles, select multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, and determine the signal-to-noise ratio of the first heartbeat phase signals; the heart rate value determination module 330 is used to determine a second preset number of second heartbeat phase signals according to the signal-to-noise ratio, determine the heart rate classification interval of the second heartbeat phase signal, and determine the heart rate value of the heartbeat signal according to the second heartbeat phase signal and the heart rate classification interval.

[0103] The technical solution of the embodiment of the present invention is to receive an echo signal based on a radar through a heartbeat phase signal determination module, mix the echo signal with a transmission signal to obtain a heartbeat signal, and determine multiple heartbeat phase signals in a target area according to the heartbeat signal and a preset chest cavity size of the target object, wherein the heartbeat phase signals are phase signals at different distances and angles, which can achieve accurate positioning and multi-angle feature extraction of the heartbeat signal of the target object; then, the signal-to-noise ratio determination module determines the correlation strength between each two heartbeat phase signals with adjacent distances and angles, selects multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, and determines the signal-to-noise ratio of the first heartbeat phase signals. Effectively screen heartbeat phase signals with high correlation and excellent signal-to-noise ratio, and improve the accuracy and reliability of subsequent heart rate classification; finally, the heart rate value determination module determines a second preset number of second heartbeat phase signals according to the signal-to-noise ratio, determines the heart rate classification interval of the second heartbeat phase signal, and determines the heart rate value of the heartbeat signal according to the second heartbeat phase signal and the heart rate classification interval. It can screen high signal-to-noise ratio signals and accurately determine the heart rate of the heartbeat signal, solving the problems in related technologies that it is difficult to extract effective heartbeat information from multi-source signals and that the classification results are easily interfered with, realizing accurate classification of heart rate, improving the robustness and classification accuracy of heartbeat detection, and being suitable for non-contact heart rate detection in complex environments.

[0104] On the basis of the above scheme, optionally, the heart rate value determination module includes: a feature matrix determination submodule, a probability determination submodule, and a heart rate classification interval determination submodule. The feature matrix determination submodule is used to perform Fourier transform on the second preset number of second heartbeat phase signals, and combine the positive half-axis spectrum features after Fourier transform to obtain multiple feature matrices; the probability determination submodule is used to input the multiple feature matrices into a trained classification model, so as to process the feature matrices into probabilities of being in each of the heart rate classification intervals through the classification model; the heart rate classification interval determination submodule is used to determine the category label of the second heartbeat phase signal according to the probability, and determine the heart rate classification interval of the heartbeat signal according to the category label of the second heartbeat phase signal.

[0105] Based on the above solution, the category label determination submodule optionally includes a category label determination unit. The category label determination unit is configured to, for each feature matrix, determine the category corresponding to the maximum probability value of the feature matrix in each heart rate classification interval as the category label of the second heartbeat phase signal corresponding to the feature matrix.

[0106] On the basis of the above scheme, optionally, the heart rate value determination module includes: a heart rate value determination sub-module, wherein the heart rate value determination sub-module is used to obtain a bandpass filter corresponding to the heart rate classification interval, determine a third heartbeat phase signal based on the bandpass filter and the second heartbeat phase signal, perform Fourier transform on the third heartbeat phase signal, determine a third preset number of third heartbeat phase signals based on the transformation result, determine the peak frequency of the third heartbeat phase signal, determine a frequency difference based on the center frequency of the bandpass filter and the peak frequency, and determine the heart rate value of the heartbeat signal based on the minimum value of the frequency difference.

[0107] Based on the above solution, the heart rate value determination module optionally includes a heart rate classification interval determination submodule, wherein the heart rate classification interval determination submodule is used to determine the heart rate range of the target subject, and divide the heart rate range into classification intervals according to a preset heart rate per unit time.

[0108] Based on the above scheme, the heartbeat phase signal determination module optionally includes: a distance spectrum extraction submodule, a target image determination submodule, a target area determination submodule, and a heartbeat phase signal determination submodule. The distance spectrum extraction submodule is used to perform digital-to-analog conversion on the heartbeat signal to obtain a discrete signal, and extract the distance spectrum of the discrete signal based on the fast time dimension; the target image determination submodule is used to determine the target image based on the antenna dimension and the distance spectrum, wherein the target image is used to characterize the relationship between distance and angle; the target area determination submodule is used to determine the angle and distance corresponding to the maximum energy in the spatial spectrum of the target image, and determine the target area based on the angle, the distance, and the preset chest size of the target object; the heartbeat phase signal determination submodule is used to determine the channel signals at different angles within the target area, extract the phase information of the channel signals based on the slow time dimension, and determine the heartbeat phase signal based on the phase information and a preset high-pass filter.

[0109] Based on the above scheme, the signal-to-noise ratio determination module optionally includes: a correlation strength determination submodule, a spatial binary image determination submodule, and a first heartbeat phase signal determination submodule. The correlation strength determination submodule is used to determine the correlation coefficient between each two heartbeat phase signals that are adjacent in distance and angle, and determine the correlation strength based on the correlation coefficient; the spatial binary image determination submodule is used to binarize the correlation strength based on a preset correlation strength threshold, and fill the binarization result into a preset spatial matrix to obtain a spatial binary image, wherein the preset spatial matrix is used to characterize the spatial strength between each two heartbeat phase signals; the first heartbeat phase signal determination submodule is used to divide the heartbeat phase signal into regions based on the adjacent relationship of the correlation strength in the spatial binary image, obtain the heartbeat phase signals in multiple different regions, and determine multiple different first heartbeat phase signals based on the correlation strengths of different regions.

[0110] Based on the above solution, the signal-to-noise ratio determination module optionally includes a signal-to-noise ratio sub-determination module. The signal-to-noise ratio sub-determination module is configured to determine a maximum value in the spectrum of the first heartbeat phase signal within a target heart rate range, determine a sum of spectrum values outside the target heart rate range, and determine the signal-to-noise ratio of the first heartbeat phase signal based on a ratio of the maximum value to the sum.

[0111] The heart rate determination device provided in the embodiment of the present invention can execute the heart rate determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0112] Example 4

[0113] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0114] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a heart rate determination method.

[0117] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

[0118] In some embodiments, a heart rate determination method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of a heart rate determination method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform a heart rate determination method in any other suitable manner (e.g., by means of firmware).

[0119] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips or systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0121] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0123] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0124] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0125] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0126] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining heart rate, characterized in that: include: Based on the radar receiving echo signal, the echo signal is mixed with the transmission signal to obtain a heartbeat signal, and multiple heartbeat phase signals in the target area are determined according to the heartbeat signal and the preset chest size of the target object, wherein the heartbeat phase signals are phase signals at different distances and different angles; Determine the correlation strength between each two of the heartbeat phase signals that are adjacent in distance and angle, select multiple first heartbeat phase signals from the multiple heartbeat phase signals according to the correlation strength, and determine the signal-to-noise ratio of the first heartbeat phase signals; A second preset number of second heartbeat phase signals is determined according to the signal-to-noise ratio, a heart rate classification interval of the second heartbeat phase signals is determined, and a heart rate value of the heartbeat signal is determined according to the second heartbeat phase signals and the heart rate classification interval.

2. The method according to claim 1, characterized in that The determining of the heart rate classification interval of the second heartbeat phase signal includes: Performing Fourier transform on the second preset number of second heartbeat phase signals, and combining the positive half-axis spectrum features after the Fourier transform to obtain a plurality of feature matrices; Inputting the plurality of feature matrices into a trained classification model, so as to process the feature matrices into probabilities of being in each of the heart rate classification intervals through the classification model; A category label of the second heartbeat phase signal is determined according to the probability, and a heart rate classification interval of the heartbeat signal is determined according to the category label of the second heartbeat phase signal.

3. The method according to claim 2, characterized in that Determining the category label of the second heartbeat phase signal according to the probability includes: For each of the feature matrices, the category corresponding to the maximum probability value of the feature matrix in each of the heart rate classification intervals is determined as the category label of the second heartbeat phase signal corresponding to the feature matrix.

4. The method according to claim 1, wherein The determining the heart rate value of the heartbeat signal according to the second heartbeat phase signal and the heart rate classification interval includes: Obtain a bandpass filter corresponding to the heart rate classification interval, determine a third heartbeat phase signal based on the bandpass filter and the second heartbeat phase signal, perform Fourier transform on the third heartbeat phase signal, determine a third preset number of third heartbeat phase signals based on the transformation result, determine the peak frequency of the third heartbeat phase signal, determine a frequency difference based on the center frequency of the bandpass filter and the peak frequency, and determine the heart rate value of the heartbeat signal based on the minimum value of the frequency difference.

5. The method according to claim 1, wherein The method for determining the heart rate classification interval includes: The heart rate range of the target subject is determined, and the heart rate range is divided according to a preset heart rate per unit time to obtain heart rate classification intervals.

6. The method according to claim 1, characterized in that The step of determining a plurality of heartbeat phase signals in a target area according to the heartbeat signal and a preset chest cavity size of the target object includes: Performing digital-to-analog conversion on the heartbeat signal to obtain a discrete signal, and extracting a distance spectrum of the discrete signal based on a fast time dimension; determining a target image according to the antenna dimension and the distance spectrum, wherein the target image is used to represent the relationship between distance and angle; determining an angle and a distance corresponding to an energy maximum in a spatial spectrum of the target image, and determining a target area according to the angle, the distance, and a preset chest size of the target object; Determine channel signals at different angles within the target area, extract phase information of the channel signals according to a slow time dimension, and determine a heartbeat phase signal according to the phase information and a preset high-pass filter.

7. The method according to claim 1, characterized in that The determining the correlation strength between each two heartbeat phase signals that are adjacent in distance and angle, and selecting a plurality of first heartbeat phase signals from the plurality of heartbeat phase signals according to the correlation strength, comprises: determining a correlation coefficient between each two heartbeat phase signals that are adjacent in distance and angle, and determining a correlation strength based on the correlation coefficient; Binarizing the correlation strength according to a preset correlation strength threshold, and filling the binarization result into a preset spatial matrix to obtain a spatial binary image, wherein the preset spatial matrix is used to characterize the spatial intensity relationship between each two heartbeat phase signals; The heartbeat phase signal is divided into regions according to the adjacent relationship of the correlation strength in the spatial binary image to obtain the heartbeat phase signals in multiple different regions, and multiple different first heartbeat phase signals are determined according to the correlation strength of different regions.

8. The method according to claim 1, characterized in that Determining the signal-to-noise ratio of the first heartbeat phase signal includes: Determine a maximum value in the spectrum of the first heartbeat phase signal within the target heart rate range, and determine a sum of spectrum values outside the target heart rate range, and determine a signal-to-noise ratio of the first heartbeat phase signal based on a ratio of the maximum value to the sum.

9. A heart rate determination device, characterized in that: include: a heartbeat phase signal determination module, configured to receive an echo signal from a radar, mix the echo signal with a transmitted signal to obtain a heartbeat signal, and determine a plurality of heartbeat phase signals in a target area according to the heartbeat signal and a preset chest cavity size of the target object, wherein the heartbeat phase signals are phase signals at different distances and angles; a signal-to-noise ratio determination module, configured to determine a correlation strength between each two heartbeat phase signals that are adjacent in distance and angle, select a plurality of first heartbeat phase signals from the plurality of heartbeat phase signals based on the correlation strength, and determine a signal-to-noise ratio of the first heartbeat phase signals; A heart rate value determination module is used to determine a second preset number of second heartbeat phase signals based on the signal-to-noise ratio, determine the heart rate classification interval of the second heartbeat phase signal, and determine the heart rate value of the heartbeat signal based on the second heartbeat phase signal and the heart rate classification interval.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, wherein the computer program is executed by the at least one processor to enable the at least one processor to perform the heart rate determination method according to any one of claims 1 to 8.

Images