CN116919370A

CN116919370A - Tracking method and tracking device for heart rate signals, electronic equipment and storage medium

Info

Publication number: CN116919370A
Application number: CN202210323949.XA
Authority: CN
Inventors: 赵明喜
Original assignee: Anhui Huami Health Technology Co Ltd
Current assignee: Anhui Huami Health Technology Co Ltd
Priority date: 2022-03-29
Filing date: 2022-03-29
Publication date: 2023-10-24

Abstract

The application discloses a heart rate signal tracking method, a tracking device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring an original PPG signal and a filtered PPG signal; respectively carrying out short-time Fourier transform on the original PPG signal and the filtered PPG signal to obtain a corresponding frequency spectrum; generating a corresponding first curve cluster and a corresponding second curve cluster according to the spectrum of the original PPG signal and the spectrum of the filtered PPG signal respectively; searching coordinate points meeting a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster from each two-dimensional coordinate point on all curves in the first curve cluster, and taking the coordinate points as matching points; detecting each curve in the second curve cluster, and if the parameters of the matching points of the curves in the second curve cluster meet the second preset condition, acquiring the jump heart rate value according to the curves in the second curve cluster, wherein the parameters of the matching points meet the second preset condition, so as to track the heart rate signal, thereby greatly improving the heart rate tracking precision.

Description

Tracking method and tracking device for heart rate signals, electronic equipment and storage medium

Technical Field

The present application relates to the field of electronic devices, and in particular, to a method and apparatus for tracking a heart rate signal, an electronic device, and a storage medium.

Background

With the increasing level of living of people, wearable devices are increasingly favored by consumers. A heart rate tracking algorithm based on PPG (Photo Pethysmo Graphic), photoplethysmography) signals is a necessary algorithm for wearable devices. Typically, the heart rate tracking algorithm searches for the heart rate value at the current time around the heart rate at the previous time (e.g. + -6BPM (Beat Per Minute)), but this algorithm has the disadvantage that: if the quality of the PPG signal after removing the motion disturbance is poor, the predicted heart rate value is brought to an error interval, and no method is available for obtaining the real heart rate value.

Therefore, how to improve the accuracy of tracking the heart rate by the wearable device is a problem to be solved at present.

Disclosure of Invention

The present application aims to solve at least one of the technical problems in the above-described technology to some extent.

The embodiment of the application provides a tracking method of heart rate signals, which comprises the following steps: acquiring an original photoplethysmography (PPG) signal and a filtered PPG signal; respectively carrying out short-time Fourier transform on the original PPG signal and the filtered PPG signal to obtain a corresponding frequency spectrum of the original PPG signal and a corresponding frequency spectrum of the filtered PPG signal; generating a corresponding first curve cluster and a corresponding second curve cluster according to the spectrum of the original PPG signal and the spectrum of the filtered PPG signal respectively; searching coordinate points meeting a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster from each two-dimensional coordinate point on all curves in the first curve cluster, and taking the coordinate points as matching points; the two-dimensional coordinate points are used for representing points of time and frequency; detecting each curve in the second curve cluster, and if the parameter of the matching point of the curve in the second curve cluster meets a second preset condition, acquiring a jump heart rate value according to the curve in the second curve cluster, wherein the parameter of the matching point of the curve in the second curve cluster meets the second preset condition, so as to track the heart rate signal.

According to the heart rate signal tracking method, an original photoplethysmography PPG signal and a filtered PPG signal are obtained, short-time Fourier transform is conducted on the original PPG signal and the filtered PPG signal respectively to obtain a corresponding spectrum of the original PPG signal and a corresponding spectrum of the filtered PPG signal, a corresponding first curve cluster and a corresponding second curve cluster are generated according to the original spectrum of the PPG signal and the corresponding spectrum of the filtered PPG signal respectively, coordinate points which are used for representing time and frequency and are located on all the two-dimensional coordinate points of all the curves in the first curve cluster are searched for and used as matching points, each two-dimensional coordinate point of each curve in the second curve cluster meets a first preset condition, if matching parameters of the curve in the second curve cluster meet a second preset condition, a jump rate value is obtained according to the matching parameters of the curve in the second curve cluster meeting the second preset condition, and the heart rate signal is tracked. Therefore, the method can be used in the jump of heart rate tracking, and the accuracy of heart rate tracking can be greatly improved.

In some embodiments, the obtaining the jump-heart value according to the curves in the second curve cluster that the pairing point meets the second preset condition includes: and acquiring the frequency corresponding to the pairing point as the jump heart rate value according to the time of the pairing point when the parameter of the pairing point meets a second preset condition.

In some embodiments, the generating corresponding first and second curve clusters from the spectrum of the original PPG signal and the spectrum of the filtered PPG signal, respectively, includes: respectively carrying out amplitude normalization processing on the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal; the frequency spectrum of the original PPG signal after amplitude normalization and the frequency spectrum of the filtered PPG signal after amplitude normalization are respectively searched for local peaks to obtain a plurality of corresponding first point pairs and a plurality of corresponding second point pairs; wherein the first and second point pairs are respectively used for characterizing a frequency and an amplitude point pair; and generating the corresponding first curve cluster and second curve cluster according to the plurality of first point pairs and the plurality of second point pairs respectively.

In some embodiments, the generating the first curve cluster according to the plurality of the first point pairs includes: when the current moment is larger than zero, pairing the first point pair at the current moment with the first point pair at the previous moment according to a third preset condition; if the first point pair at the current moment and the first point pair at the previous moment are successfully paired according to the third preset condition, judging whether the first point pair at the previous moment is in a first curve or not; if the first point pair at the previous moment is in a first curve, adding the first point pair at the current moment into the first curve; or if the first point pair of the previous moment is not in the first curve, generating a second curve according to the first point pair of the current moment and the first point pair of the previous moment; and generating the first curve cluster according to the first curve and the second curve.

In some embodiments, after the normalizing the frequency spectrum of the original PPG signal to the amplitude, by searching for local peaks to obtain a plurality of first point pairs, the method further includes: judging whether the amplitude of the first point pair is smaller than a first preset amplitude or not; and deleting the first point pair with the amplitude smaller than the first preset amplitude if the amplitude of the first point pair is smaller than the first preset amplitude.

In some embodiments, the generating the second curve cluster according to the plurality of the second point pairs includes: when the current moment is larger than zero, pairing the second point pair at the current moment with the second point pair at the previous moment according to a fourth preset condition; if the second point pair at the current moment and the second point pair at the last moment are successfully paired according to the fourth preset condition, judging whether the second point pair at the last moment is in a third curve or not; wherein if the second point pair at the previous time is in a third curve, adding the second point pair at the current time to the third curve; or if the second point pair at the previous moment is not in the third curve, generating a fourth curve according to the second point pair at the current moment and the second point pair at the previous moment; and generating the second curve cluster according to the third curve and the fourth curve.

In some embodiments, after the normalizing the frequency spectrum of the filtered PPG signal to the amplitude, by searching for local peaks to obtain a plurality of second point pairs, the method further includes: judging whether the amplitude of the second point pair is smaller than a second preset amplitude or not; if the amplitude of the second point pair is smaller than the second preset amplitude, deleting the second point pair with the amplitude smaller than the second preset amplitude; wherein the second preset amplitude is greater than the first preset amplitude.

In some embodiments, the acquiring the filtered PPG signal comprises: and filtering an acceleration signal from the original PPG signal by using a filtering algorithm to obtain the filtered PPG signal.

The embodiment of the application provides a heart rate signal tracking device, which comprises: a first acquisition module for acquiring an original photoplethysmography PPG signal and a filtered PPG signal; the processing module is used for performing short-time Fourier transform on the original PPG signal and the filtered PPG signal respectively to obtain a corresponding frequency spectrum of the original PPG signal and a corresponding frequency spectrum of the filtered PPG signal; the generation module is used for generating a corresponding first curve cluster and a corresponding second curve cluster according to the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal respectively; the searching module is used for searching coordinate points meeting a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster from each two-dimensional coordinate point on all curves in the first curve cluster, and taking the coordinate points as matching points; the two-dimensional coordinate points are used for representing points of time and frequency; the second obtaining module is configured to detect each curve in the second curve cluster, and if the parameter of the matching point of the curve in the second curve cluster meets a second preset condition, obtain a jump heart rate value according to the curve in the second curve cluster, where the parameter of the matching point meets the second preset condition, so as to track the heart rate signal.

According to the heart rate signal tracking device provided by the embodiment of the application, an original photoplethysmography PPG signal and a filtered PPG signal are obtained through the first obtaining module, short-time Fourier transform is respectively carried out on the original PPG signal and the filtered PPG signal through the processing module, a corresponding original PPG signal frequency spectrum and a corresponding filtered PPG signal frequency spectrum are obtained, a corresponding first curve cluster and a corresponding second curve cluster are generated through the generating module according to the original PPG signal frequency spectrum and the filtered PPG signal frequency spectrum respectively, coordinate points which are used for representing time and frequency and meet a first preset condition on each two-dimensional coordinate point on all curves in the first curve cluster are searched through the searching module, the coordinate points which are used for meeting a first preset condition on each curve in the second curve cluster are used as matching points, if the matching parameters of the curves in the second curve cluster meet the second preset condition, the heart rate value is obtained according to the matching parameters of the matching points meeting the second preset condition in the second curve cluster, and the heart rate value is tracked. Therefore, the device can be used in the jump of heart rate tracking, and the accuracy of heart rate tracking can be greatly improved.

In some embodiments, the second acquisition module is configured to: and acquiring the frequency corresponding to the pairing point as the jump heart rate value according to the time of the pairing point when the parameter of the pairing point meets a second preset condition.

In some embodiments, the generating module is configured to: respectively carrying out amplitude normalization processing on the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal, respectively carrying out local peak value searching on the frequency spectrum of the original PPG signal after amplitude normalization and the frequency spectrum of the filtered PPG signal after amplitude normalization to obtain a plurality of corresponding first point pairs and a plurality of corresponding second point pairs, and respectively generating a corresponding first curve cluster and a corresponding second curve cluster according to the plurality of first point pairs and the plurality of second point pairs; wherein the first and second point pairs are respectively used for characterizing a frequency and an amplitude point pair.

In some embodiments, the generating module is configured, when generating the first curve cluster according to a plurality of the first point pairs, to: when the current moment is larger than zero, pairing a first point pair at the current moment and a first point pair at the previous moment according to a third preset condition, and judging whether the first point pair at the previous moment is in a first curve or not when the pairing of the first point pair at the current moment and the first point pair at the previous moment is successful according to the third preset condition; if the first point pair at the previous moment is in a first curve, adding the first point pair at the current moment into the first curve; or if the first point pair at the previous moment is not in the first curve, generating a second curve according to the first point pair at the current moment and the first point pair at the previous moment, and further generating the first curve cluster according to the first curve and the second curve.

In some embodiments, the generating module is configured to: after the spectrum of the original PPG signal with the normalized amplitude is searched for a plurality of first point pairs, judging whether the amplitude of the first point pairs is smaller than a first preset amplitude or not, and deleting the first point pairs with the amplitude smaller than the first preset amplitude if the amplitude of the first point pairs is smaller than the first preset amplitude.

In some embodiments, the generating module is configured, when generating the second curve cluster according to a plurality of the second point pairs, to: when the current moment is larger than zero, pairing a second point pair at the current moment with a second point pair at the previous moment according to a fourth preset condition, and judging whether the second point pair at the previous moment is in a third curve or not when the second point pair at the current moment and the second point pair at the previous moment are successfully paired according to the fourth preset condition; wherein if the second point pair at the previous time is in a third curve, adding the second point pair at the current time to the third curve; or if the second point pair at the previous moment is not in the third curve, generating a fourth curve according to the second point pair at the current moment and the second point pair at the previous moment, and further generating the second curve cluster according to the third curve and the fourth curve.

In some embodiments, the generating module is configured to: after the spectrum of the filtered PPG signal with normalized amplitude is searched for a plurality of second point pairs, judging whether the amplitude of the second point pairs is smaller than a second preset amplitude or not, and deleting the second point pairs with the amplitude smaller than the second preset amplitude if the amplitude of the second point pairs is smaller than the second preset amplitude; wherein the second preset amplitude is greater than the first preset amplitude.

In some embodiments, the first acquisition module, after acquiring the filtered PPG signal, is configured to: and filtering an acceleration signal from the original PPG signal by using a filtering algorithm to obtain the filtered PPG signal.

The embodiment of the application also provides electronic equipment, which comprises: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the heart rate signal tracking method described above.

The electronic equipment provided by the embodiment of the application can be used in the jump of heart rate tracking by executing the tracking method of the heart rate signals, and can greatly improve the accuracy of heart rate tracking.

The embodiment of the application also provides a non-transitory computer readable storage medium, which enables the electronic device to execute the above-mentioned heart rate signal tracking method when the instructions in the storage medium are executed by the processor of the electronic device.

The non-transitory computer readable storage medium of the embodiment of the application can be used in the jump of heart rate tracking by executing the tracking method of the heart rate signals, and can greatly improve the accuracy of heart rate tracking.

Drawings

FIG. 1 is a flow chart of a method of tracking a heart rate signal according to an embodiment of the application;

fig. 2 is a spectral diagram of an original PPG signal and a filtered PPG signal according to an embodiment of the application;

FIG. 3 is a block schematic diagram of a tracking device for heart rate signals according to an embodiment of the application;

fig. 4 is a block diagram of an electronic device according to an embodiment of the application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.

The following describes a heart rate signal tracking method, a heart rate signal tracking device, an electronic device, and a non-transitory computer readable storage medium according to embodiments of the present application with reference to the accompanying drawings.

With the increasing level of living of people, wearable devices are increasingly favored by consumers. A heart rate tracking algorithm based on the PPG signal is a necessary algorithm for the wearable device. Among them, PPG is a method of shining light into the skin and measuring light scattering due to blood flow. The principle is as follows: green light emitted by the LED (Light Emitting Diode Light, light emitting diode) in the optical sensor passes through tissue in the skin and arterial veins and is absorbed and reflected back into the photosensor, where it is attenuated to some extent. The absorption of green light is substantially unchanged (provided that the measurement site does not move significantly) like muscle, bone, vein and other connective tissue, but the absorption of light naturally changes due to the blood flow in the artery. Then, the green light is converted into an electrical signal, and the obtained signal can be divided into a direct current signal and an alternating current signal just because the absorption of the green light by the artery is changed and the absorption of the light by other tissues is basically unchanged. Finally, the alternating current signal is extracted, so that the characteristic of blood flow can be reflected.

Typically, the heart rate tracking algorithm searches for the heart rate value at the current time around the heart rate at the previous time (e.g. + -6BPM (Beat Per Minute)), but this algorithm has the disadvantage that: if the quality of the PPG signal after removing the motion disturbance is poor, the predicted heart rate value is brought to an error interval, and no method is available for obtaining the real heart rate value. Therefore, there is a need for a heart rate that will jump to a better quality heart rate value when the heart rate signal at which the current heart rate value is determined is not good and a better quality heart rate value occurs. But the heart rate value of better quality of the jump is also likely to be a noise signal, such jump leading to larger errors.

Therefore, the application provides a novel heart rate signal tracking method, which can measure the quality of the heart rate signal in real time and improve the tracking accuracy of the heart rate signal.

Fig. 1 is a flow chart of a method of tracking a heart rate signal according to an embodiment of the application.

In the embodiment of the application, the tracking method of the heart rate signal is applied to the wearable device, wherein the wearable device can be a smart watch or a smart bracelet.

As shown in fig. 1, the heart rate tracking method of the wearable device according to the embodiment of the application includes the following steps:

S101, acquiring an original photoplethysmography (PPG) signal and a filtered PPG signal.

As an alternative implementation, acquiring the filtered PPG signal includes: the acceleration signal is filtered from the original PPG signal using a filtering algorithm to obtain a filtered PPG signal.

In this step, an original PPG signal is acquired by an optical sensor, such as a PPG optical module, which contains a motion signal, such as an acceleration signal. After the original PPG signal is obtained, a motion signal, such as an acceleration signal, may be filtered out of the original PPG signal using a related filtering algorithm, such as RLS (Recursive least squares ), and the original PPG signal and the filtered PPG signal stored until a certain amount (e.g., 8 seconds) is reached.

S102, performing short-time Fourier transform on the original PPG signal and the filtered PPG signal respectively to obtain a corresponding frequency spectrum of the original PPG signal and a corresponding frequency spectrum of the filtered PPG signal.

In the step, after a certain amount of original PPG signals are obtained, short-time Fourier transform is carried out on the original PPG signals, so that amplitude values of a certain frequency spectrum interval at the moment T, namely the frequency spectrum of the original PPG signals, are obtained; and after a certain amount of original PPG signals are obtained, carrying out short-time Fourier transform on the original PPG signals to obtain amplitude values of a certain frequency spectrum interval at the moment T, namely the frequency spectrum of the filtered PPG signals.

S103, generating a corresponding first curve cluster and a corresponding second curve cluster according to the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal respectively.

As an optional implementation manner, step S103 includes: respectively carrying out amplitude normalization processing on the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal; the frequency spectrum of the original PPG signal after amplitude normalization and the frequency spectrum of the filtered PPG signal after amplitude normalization are respectively subjected to local peak value searching to obtain a plurality of corresponding first point pairs and a plurality of corresponding second point pairs; wherein the first point pair and the second point pair are respectively used for characterizing the point pair of the frequency and the amplitude; and generating a corresponding first curve cluster and a corresponding second curve cluster according to the plurality of first point pairs and the plurality of second point pairs.

In this step, the following is done for the original PPG signal: and normalizing the maximum value and the minimum value of the amplitude of the frequency spectrum of the original PPG signal to be between 0 and 1. For example, the amplitude may be normalized in such a way that the current amplitude is divided by the maximum amplitude. Then, the frequency spectrum of the original PPG signal after amplitude normalization is searched for local peaks to obtain point pairs of frequency and amplitude, and thus a plurality of first point pairs can be obtained by the edges. Finally, a first curve cluster is generated according to the plurality of first point pairs.

The filtered PPG signal is processed as follows: and normalizing the maximum value and the minimum value of the amplitude of the frequency spectrum of the filtered PPG signal to be between 0 and 1. For example, the amplitude may be normalized in such a way that the current amplitude is divided by the maximum amplitude. Then, the frequency spectrum of the filtered PPG signal after amplitude normalization is searched for a local peak value to obtain a point pair of frequency and amplitude, so that a plurality of second point pairs can be obtained by the edge. Finally, a second curve cluster is generated according to the plurality of second point pairs.

As an alternative implementation manner for generating the first curve cluster, when the current moment is greater than zero, pairing the first point pair at the current moment with the first point pair at the previous moment according to a third preset condition; if the first point pair at the current moment and the first point pair at the previous moment are successfully paired according to the third preset condition, judging whether the first point pair at the previous moment is in a first curve or not; wherein if the first point pair at the previous moment is in the first curve, adding the first point pair at the current moment to the first curve; or if the first point pair at the previous moment is not in the first curve, generating a second curve according to the first point pair at the current moment and the first point pair at the previous moment; and generating a first curve cluster according to the first curve and the second curve.

In this step, if the current time is zero, no processing is performed; and if the current moment is a moment greater than the zero moment, pairing the first point pair at the current moment with the first point pair at the last moment according to a third preset condition. One implementation of the third preset condition is that the frequency of the first point pair at the current moment and the frequency of the first point pair at the previous moment are different by 6 BPMs. If the first point pair at the current moment and the first point pair at the last moment meet a third preset condition, judging whether the first point pair at the last moment is in the first curve. If the first point pair at the previous moment is already in the first curve, adding the first point pair at the current moment to the first curve, i.e. the length of the first curve is increased; if the first point pair at the current moment is not in a curve, a new curve is generated by the first point pair at the previous moment and the first point pair at the current moment to serve as a second curve.

With the increase of time, steps S101-S103 are circularly performed, and a curve cluster formed by a plurality of first curves and a plurality of second curves can be obtained as the first curve cluster.

In order to further improve the accuracy of tracking the heart rate signal, after searching the local peak value for the spectrum of the original PPG signal after the amplitude normalization to obtain a plurality of first point pairs, the method further comprises: judging whether the amplitude of the first point pair is smaller than a first preset amplitude; and if the amplitude of the first point pair is smaller than the first preset amplitude, deleting the first point pair with the amplitude smaller than the first preset amplitude. The first preset amplitude may be set according to actual needs, for example, may be 0.1.

That is, after the spectrum of the original PPG signal after the amplitude normalization is searched for the local peak value to obtain a plurality of first point pairs, in order to further improve the accuracy of tracking the heart rate signal, it is required to determine whether the amplitude of each first point pair is smaller than a first preset amplitude (e.g. 0.1), and delete the first point pair when the amplitude of the first point pair is smaller than the first preset amplitude, so that screening of the plurality of first point pairs can be achieved.

As an alternative implementation manner for generating the second curve cluster, when the current moment is greater than zero, pairing the second point pair at the current moment with the second point pair at the previous moment according to a fourth preset condition; if the second point pair at the current moment and the second point pair at the last moment are successfully paired according to the fourth preset condition, judging whether the second point pair at the last moment is in the third curve or not; wherein if the second point pair at the previous time is in the third curve, adding the second point pair at the current time to the third curve; or if the second point pair at the previous moment is not in the third curve, generating a fourth curve according to the second point pair at the current moment and the second point pair at the previous moment; and generating a second curve cluster according to the third curve and the fourth curve.

In this step, if the current time is zero, no processing is performed; and if the current moment is a moment greater than the zero moment, pairing the second point pair at the current moment and the second point pair at the last moment according to a fourth preset condition. The fourth preset condition may be the same as the third preset condition, and the implementation manner is that the frequency of the second point pair at the current moment and the frequency of the second point pair at the previous moment are different by 6 BPMs. And if the second point pair at the current moment and the second point pair at the last moment meet a fourth preset condition, judging whether the second point pair at the last moment is in the third curve. If the second point pair at the previous moment is already in the third curve, adding the second point pair at the current moment to the third curve, i.e. the length of the third curve is increased; if the second point pair at the current moment is not in a curve, a new curve is generated by the second point pair at the previous moment and the second point pair at the current moment to be used as a fourth curve.

With the increase of time, steps S101-S103 are circularly performed, and a curve cluster formed by a plurality of third curves and a plurality of fourth curves can be obtained as the second curve cluster.

In order to further improve the accuracy of tracking the heart rate signal, after searching the local peak value for the spectrum of the filtered PPG signal after the amplitude normalization to obtain a plurality of second point pairs, the method further includes: judging whether the amplitude of the second point pair is smaller than a second preset amplitude; if the amplitude of the second point pair is smaller than a second preset amplitude, deleting the second point pair with the amplitude smaller than the second preset amplitude; wherein the second preset amplitude is greater than the first preset amplitude. The second preset amplitude may be set according to actual needs, for example, may be 0.6.

That is, after the spectrum of the filtered PPG signal after the amplitude normalization is used to find the local peak value to obtain a plurality of second point pairs, in order to further improve the accuracy of tracking the heart rate signal, it is required to determine whether the amplitude of each second point pair is smaller than a second preset amplitude (e.g. 0.6), and delete the second point pair when the amplitude of the second point pair is smaller than the second preset amplitude, so that screening of the plurality of second point pairs can be achieved.

S104, searching coordinate points meeting a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster from each two-dimensional coordinate point on all curves in the first curve cluster, and taking the coordinate points as matching points; wherein, two-dimensional coordinate point is used for the point of characteristic time, frequency.

That is, a second cluster of curves is projected onto the first cluster of curves to find a matching point. Specifically, for each point on each curve in the second curve cluster, it is checked whether there is a point similar to the two-dimensional coordinate point in the first curve cluster (i.e. whether a first preset condition is satisfied, for example, the difference between the two-dimensional coordinates is within a certain range), and if so, the point is used as a matching point.

S105, detecting each curve in the second curve cluster, and if the parameter of the matching point exists in the curve in the second curve cluster and meets the second preset condition, acquiring the jump heart rate value according to the curve in the second curve cluster, wherein the parameter of the matching point meets the second preset condition, so as to track the heart rate signal.

As an optional implementation manner, step S105 includes: and obtaining the frequency corresponding to the pairing point as the jump heart rate value according to the time of the pairing point when the parameter of the pairing point meets the second preset condition.

In this step, each curve in the second curve cluster is detected, and if the number of paired points of a certain curve L is greater than the set number (the set number can be set according to actual needs), and the percentage of paired points is greater than the set percentage (the set percentage can be set according to actual needs), that is, the parameters of paired points on the curve L satisfy the second set condition, the jump point can be found on the curve L. The jump point is the time of the pairing point when the parameter of the pairing point meets the second preset condition, and the frequency of the pairing point corresponds to the jump point. At this time, if the current tracked heart rate value is different from (e.g., more deviated from) the jump heart rate of the curve L, the heart rate jump can be performed.

Typically, the heart rate tracking algorithm operates as follows:

the heart rate at the previous moment is obtained first, and a new heart rate is searched for by 6 BPMs of the heart rate at the previous moment, but in the case of weak heart rate signals, the error of heart rate tracking is amplified, and when the heart rate signals are obvious, the algorithm cannot accurately track the heart rate, as shown in fig. 2.

To this end, the present application proposes an improved algorithm:

after the first curve cluster and the second curve cluster are obtained, each curve in the second curve cluster is detected, and if the number of paired points of a certain curve L is greater than the set number and the percentage of paired points is greater than the set percentage, a jump point can be found on the curve L. The jump point is the time of the two-dimensional coordinate point of the matching point at the current moment, and the frequency of the matching point corresponds to the jump point. At this time, if the current tracked heart rate value is different from the jump heart rate of the curve L, the heart rate jump can be performed, as shown in FIG. 2.

In summary, according to the tracking method of the heart rate signal in the embodiment of the present application, an original PPG signal and a filtered PPG signal are obtained first, short-time fourier transform is performed on the original PPG signal and the filtered PPG signal, a corresponding spectrum of the original PPG signal and a corresponding spectrum of the filtered PPG signal are obtained, a corresponding first curve cluster and a corresponding second curve cluster are generated according to the original spectrum of the PPG signal and the corresponding spectrum of the filtered PPG signal, and coordinate points, which are used for characterizing time and frequency, on all curves in the first curve cluster are searched for, and coordinate points, which satisfy a first preset condition, on each curve in the second curve cluster are used as matching points, further detection is performed on each curve in the second curve cluster, and if a matching point parameter in the second curve cluster satisfies a second preset condition, a rotation center value is obtained according to a curve in the second curve cluster, which satisfies the second preset condition, so as to track the heart rate signal. Therefore, the method can be used in the jump of heart rate tracking, the quality of jump point signals can be improved, the accuracy of heart rate tracking is greatly improved, and the competitiveness of wearable equipment is improved.

Fig. 3 is a block schematic diagram of a tracking device for heart rate signals according to an embodiment of the application.

As shown in fig. 3, a tracking device 300 for heart rate signals according to an embodiment of the present application includes: a first acquisition module 301, a processing module 302, a generation module 303, a search module 304 and a second acquisition module 305.

Wherein the first acquisition module 301 is configured to acquire an original photoplethysmography PPG signal and a filtered PPG signal. The processing module 302 is configured to perform short-time fourier transform on the original PPG signal and the filtered PPG signal, respectively, to obtain a corresponding spectrum of the original PPG signal and a corresponding spectrum of the filtered PPG signal. The generating module 303 is configured to generate a corresponding first curve cluster and a corresponding second curve cluster according to the spectrum of the original PPG signal and the spectrum of the filtered PPG signal, respectively. The searching module 304 is configured to search, from among the two-dimensional coordinate points on all curves in the first curve cluster, coordinate points that satisfy a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster, as matching points, where the two-dimensional coordinate points are points for representing time and frequency. The second obtaining module 305 is configured to detect each curve in the second curve cluster, and if the parameter of the matching point of the curves in the second curve cluster meets a second preset condition, obtain a jump heart rate value according to the curve in the second curve cluster in which the parameter of the matching point meets the second preset condition, so as to track the heart rate signal.

In some embodiments, the second obtaining module 305 is configured to: and acquiring the frequency corresponding to the pairing point as the jump heart rate value according to the time of the pairing point when the parameter of the pairing point meets a second preset condition.

In some embodiments, the generating module 303 is configured to: respectively carrying out amplitude normalization processing on the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal, respectively carrying out local peak value searching on the frequency spectrum of the original PPG signal after amplitude normalization and the frequency spectrum of the filtered PPG signal after amplitude normalization to obtain a plurality of corresponding first point pairs and a plurality of corresponding second point pairs, and respectively generating a corresponding first curve cluster and a corresponding second curve cluster according to the plurality of first point pairs and the plurality of second point pairs; wherein the first and second point pairs are respectively used for characterizing a frequency and an amplitude point pair.

In some embodiments, the generating module 303 is configured to, when generating the first curve cluster according to a plurality of the first point pairs: when the current moment is larger than zero, pairing a first point pair at the current moment and a first point pair at the previous moment according to a third preset condition, and judging whether the first point pair at the previous moment is in a first curve or not when the pairing of the first point pair at the current moment and the first point pair at the previous moment is successful according to the third preset condition; if the first point pair at the previous moment is in a first curve, adding the first point pair at the current moment into the first curve; or if the first point pair at the previous moment is not in the first curve, generating a second curve according to the first point pair at the current moment and the first point pair at the previous moment, and further generating the first curve cluster according to the first curve and the second curve.

In some embodiments, the generating module 303 is configured to: after the spectrum of the original PPG signal with the normalized amplitude is searched for a plurality of first point pairs, judging whether the amplitude of the first point pairs is smaller than a first preset amplitude or not, and deleting the first point pairs with the amplitude smaller than the first preset amplitude if the amplitude of the first point pairs is smaller than the first preset amplitude.

In some embodiments, the generating module 303 is configured to, when generating the second curve cluster according to a plurality of the second point pairs: when the current moment is larger than zero, pairing a second point pair at the current moment with a second point pair at the previous moment according to a fourth preset condition, and judging whether the second point pair at the previous moment is in a third curve or not when the second point pair at the current moment and the second point pair at the previous moment are successfully paired according to the fourth preset condition; wherein if the second point pair at the previous time is in a third curve, adding the second point pair at the current time to the third curve; or if the second point pair at the previous moment is not in the third curve, generating a fourth curve according to the second point pair at the current moment and the second point pair at the previous moment, and further generating the second curve cluster according to the third curve and the fourth curve.

In some embodiments, the generating module 303 is configured to: after the spectrum of the filtered PPG signal with normalized amplitude is searched for a plurality of second point pairs, judging whether the amplitude of the second point pairs is smaller than a second preset amplitude or not, and deleting the second point pairs with the amplitude smaller than the second preset amplitude if the amplitude of the second point pairs is smaller than the second preset amplitude; wherein the second preset amplitude is greater than the first preset amplitude.

In some embodiments, the first acquisition module 301 is configured to, after acquiring the filtered PPG signal: and filtering an acceleration signal from the original PPG signal by using a filtering algorithm to obtain the filtered PPG signal.

It should be noted that, the implementation process of the tracking device for heart rate signals in the embodiments of the present disclosure refers to the foregoing explanation of the method in the embodiments of the present disclosure, and will not be repeated herein.

According to the heart rate signal tracking device provided by the embodiment of the application, an original photoplethysmography PPG signal and a filtered PPG signal are obtained through the first obtaining module, short-time Fourier transform is respectively carried out on the original PPG signal and the filtered PPG signal through the processing module, a corresponding original PPG signal frequency spectrum and a corresponding filtered PPG signal frequency spectrum are obtained, a corresponding first curve cluster and a corresponding second curve cluster are generated through the generating module according to the original PPG signal frequency spectrum and the filtered PPG signal frequency spectrum respectively, coordinate points which are used for representing time and frequency and meet a first preset condition on each two-dimensional coordinate point on all curves in the first curve cluster are searched through the searching module, the coordinate points which are used for meeting a first preset condition on each curve in the second curve cluster are used as matching points, if the matching parameters of the curves in the second curve cluster meet the second preset condition, the heart rate value is obtained according to the matching parameters of the matching points meeting the second preset condition in the second curve cluster, and the heart rate value is tracked. Therefore, the device can be used in the jump of heart rate tracking, the quality of jump point signals can be improved, the accuracy of heart rate tracking is greatly improved, and the competitiveness of wearable equipment is improved.

Based on the above embodiment, the present application further provides an electronic device, including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the heart rate tracking method of the wearable device described above.

Fig. 4 is a block diagram of an electronic device according to an embodiment of the present disclosure.

As shown in fig. 4, the electronic device 400 includes: memory 410 and processor 420, bus 430 connecting the different components, including memory 410 and processor 420.

Wherein the memory 410 is used to store executable instructions of the processor 420; the processor 401 is configured to invoke and execute executable instructions stored in the memory 402 to implement the heart rate signal tracking method proposed by the above-described embodiments of the present disclosure.

Bus 430 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 400 typically includes a variety of electronic device readable media. Such media can be any available media that is accessible by electronic device 800 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 410 may also include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 440 and/or cache memory 450. Electronic device 400 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 460 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard disk drive"). Although not shown in fig. 4, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 430 through one or more data medium interfaces. Memory 410 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the various embodiments of the disclosure.

A program/utility 480 having a set (at least one) of program modules 470 may be stored in, for example, memory 410, such program modules 470 including, but not limited to, an operating system, one or more functions, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 470 generally perform the functions and/or methods in the embodiments described in this disclosure.

The electronic device 400 may also communicate with one or more external devices 490 (e.g., keyboard, pointing device, display 491, etc.), with one or more devices that enable a user to interact with the electronic device 800, and/or with any device (e.g., network card, modem, etc.) that enables the electronic device 400 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 492. Also, electronic device 400 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 493. As depicted, network adapter 493 communicates with other modules of electronic device 400 over bus 430. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 400, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processor 420 executes various functional applications and data processing by running programs stored in the memory 410.

It should be noted that, the implementation process of the electronic device in the embodiment of the present disclosure refers to the foregoing explanation of the method in the embodiment of the present disclosure, and will not be repeated herein.

According to the electronic equipment provided by the embodiment of the application, by executing the tracking method of the heart rate signals, the quality of the jumping-point signals can be improved, the accuracy of heart rate tracking is greatly improved, and the competitiveness of the wearable equipment is improved.

Based on the above embodiments, the present application also proposes a non-transitory computer readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the above-described method of tracking a heart rate signal.

The non-transitory computer readable storage medium of the embodiment of the application can improve the quality of the jumping-point signal, greatly improve the accuracy of heart rate tracking and improve the competitiveness of the wearable equipment by executing the heart rate signal tracking method.

Based on the above embodiments, the present application also proposes a computer program product which, when executed by a processor of an electronic device, enables the electronic device to perform a method of tracking a heart rate signal as described above.

According to the computer program product provided by the embodiment of the application, by executing the heart rate tracking method of the wearable device, the quality of the jumping point signal can be improved, the accuracy of heart rate tracking is greatly improved, and the competitiveness of the wearable device is improved.

In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships as described based on the drawings are merely for convenience in describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present application.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the present application, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances.

In the present application, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims

1. A method of tracking a heart rate signal, comprising:

Acquiring an original photoplethysmography (PPG) signal and a filtered PPG signal;

respectively carrying out short-time Fourier transform on the original PPG signal and the filtered PPG signal to obtain a corresponding frequency spectrum of the original PPG signal and a corresponding frequency spectrum of the filtered PPG signal;

generating a corresponding first curve cluster and a corresponding second curve cluster according to the spectrum of the original PPG signal and the spectrum of the filtered PPG signal respectively;

searching coordinate points meeting a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster from each two-dimensional coordinate point on all curves in the first curve cluster, and taking the coordinate points as matching points; the two-dimensional coordinate points are used for representing points of time and frequency;

detecting each curve in the second curve cluster, and if the parameter of the matching point of the curve in the second curve cluster meets a second preset condition, acquiring a jump heart rate value according to the curve in the second curve cluster, wherein the parameter of the matching point of the curve in the second curve cluster meets the second preset condition, so as to track the heart rate signal.

2. The method for tracking a heart rate signal according to claim 1, wherein the obtaining a jump heart rate value according to the curves in the second curve cluster in which the pairing point satisfies a second preset condition includes:

And acquiring the frequency corresponding to the pairing point as the jump heart rate value according to the time of the pairing point when the parameter of the pairing point meets a second preset condition.

3. A method of tracking a heart rate signal as claimed in claim 1, wherein the generating of corresponding first and second curve clusters from the spectrum of the original PPG signal and the spectrum of the filtered PPG signal, respectively, comprises:

respectively carrying out amplitude normalization processing on the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal;

the frequency spectrum of the original PPG signal after amplitude normalization and the frequency spectrum of the filtered PPG signal after amplitude normalization are respectively searched for local peaks to obtain a plurality of corresponding first point pairs and a plurality of corresponding second point pairs; wherein the first and second point pairs are respectively used for characterizing a frequency and an amplitude point pair;

and generating the corresponding first curve cluster and second curve cluster according to the plurality of first point pairs and the plurality of second point pairs respectively.

4. A method of tracking a heart rate signal as claimed in claim 3 wherein said generating said first cluster of curves from a plurality of said first pairs of points comprises:

When the current moment is larger than zero, pairing the first point pair at the current moment with the first point pair at the previous moment according to a third preset condition;

if the first point pair at the current moment and the first point pair at the previous moment are successfully paired according to the third preset condition, judging whether the first point pair at the previous moment is in a first curve or not;

if the first point pair at the previous moment is in a first curve, adding the first point pair at the current moment into the first curve;

or if the first point pair of the previous moment is not in the first curve, generating a second curve according to the first point pair of the current moment and the first point pair of the previous moment;

and generating the first curve cluster according to the first curve and the second curve.

5. A method of tracking a heart rate signal as claimed in claim 3 or 4, wherein the step of finding local peaks in the spectrum of the raw PPG signal normalized to the amplitude, after finding a plurality of first point pairs, further comprises:

judging whether the amplitude of the first point pair is smaller than a first preset amplitude or not;

and deleting the first point pair with the amplitude smaller than the first preset amplitude if the amplitude of the first point pair is smaller than the first preset amplitude.

6. A method of tracking a heart rate signal as claimed in claim 3 wherein said generating said second cluster of curves from a plurality of said second pairs of points comprises:

when the current moment is larger than zero, pairing the second point pair at the current moment with the second point pair at the previous moment according to a fourth preset condition;

if the second point pair at the current moment and the second point pair at the last moment are successfully paired according to the fourth preset condition, judging whether the second point pair at the last moment is in a third curve or not;

wherein if the second point pair at the previous time is in a third curve, adding the second point pair at the current time to the third curve;

or if the second point pair at the previous moment is not in the third curve, generating a fourth curve according to the second point pair at the current moment and the second point pair at the previous moment;

and generating the second curve cluster according to the third curve and the fourth curve.

7. A method of tracking a heart rate signal as claimed in claim 3 or 6, wherein the frequency spectrum of the filtered PPG signal normalized to amplitude, after finding local peaks to obtain a plurality of second point pairs, further comprises:

Judging whether the amplitude of the second point pair is smaller than a second preset amplitude or not;

if the amplitude of the second point pair is smaller than the second preset amplitude, deleting the second point pair with the amplitude smaller than the second preset amplitude; wherein the second preset amplitude is greater than the first preset amplitude.

8. A method of tracking a heart rate signal as claimed in claim 1, wherein the acquiring the filtered PPG signal comprises:

and filtering an acceleration signal from the original PPG signal by using a filtering algorithm to obtain the filtered PPG signal.

9. A heart rate signal tracking device, comprising:

a first acquisition module for acquiring an original photoplethysmography PPG signal and a filtered PPG signal;

the processing module is used for performing short-time Fourier transform on the original PPG signal and the filtered PPG signal respectively to obtain a corresponding frequency spectrum of the original PPG signal and a corresponding frequency spectrum of the filtered PPG signal;

the generation module is used for generating a corresponding first curve cluster and a corresponding second curve cluster according to the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal respectively;

The searching module is used for searching coordinate points meeting a first preset condition with each two-dimensional coordinate point on each curve in the second curve cluster from each two-dimensional coordinate point on all curves in the first curve cluster, and taking the coordinate points as matching points; the two-dimensional coordinate points are used for representing points of time and frequency;

the second obtaining module is configured to detect each curve in the second curve cluster, and if the parameter of the matching point of the curve in the second curve cluster meets a second preset condition, obtain a jump heart rate value according to the curve in the second curve cluster, where the parameter of the matching point meets the second preset condition, so as to track the heart rate signal.

10. The heart rate signal tracking device of claim 9, wherein the second acquisition module is configured to:

11. The heart rate signal tracking device of claim 9, wherein the generation module is configured to: respectively carrying out amplitude normalization processing on the frequency spectrum of the original PPG signal and the frequency spectrum of the filtered PPG signal, respectively carrying out local peak value searching on the frequency spectrum of the original PPG signal after amplitude normalization and the frequency spectrum of the filtered PPG signal after amplitude normalization to obtain a plurality of corresponding first point pairs and a plurality of corresponding second point pairs, and respectively generating a corresponding first curve cluster and a corresponding second curve cluster according to the plurality of first point pairs and the plurality of second point pairs; wherein the first and second point pairs are respectively used for characterizing a frequency and an amplitude point pair.

12. The heart rate signal tracking device of claim 11, wherein the generation module is configured to: after the spectrum of the original PPG signal with the normalized amplitude is searched for a plurality of first point pairs, judging whether the amplitude of the first point pairs is smaller than a first preset amplitude or not, and deleting the first point pairs with the amplitude smaller than the first preset amplitude if the amplitude of the first point pairs is smaller than the first preset amplitude.

13. The heart rate signal tracking device of claim 11, wherein the generation module is configured to: after the spectrum of the filtered PPG signal with normalized amplitude is searched for a plurality of second point pairs, judging whether the amplitude of the second point pairs is smaller than a second preset amplitude or not, and deleting the second point pairs with the amplitude smaller than the second preset amplitude if the amplitude of the second point pairs is smaller than the second preset amplitude; wherein the second preset amplitude is greater than the first preset amplitude.

14. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

Wherein the processor is configured to execute the instructions to implement a method of tracking a heart rate signal as claimed in any one of claims 1 to 8.

15. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a method of tracking a heart rate signal as claimed in any one of claims 1-8.