CN105943013B - Heart rate detection method and device and intelligent wearable device - Google Patents

Abstract

The disclosure provides a heart rate detection method and device and intelligent wearable equipment, wherein the method comprises the following steps: acquiring motion characteristic data and heart rate data of a user in a current time period; determining the activity state of the user in the current time period according to the motion characteristic data; and acquiring the real-time heart rate value of the user at the current moment from the heart rate data according to the activity state. In this disclosure, the intelligent electronic device may determine the activity state to which the user belongs according to the motion characteristic data of the user in the current time period, so as to determine the real-time heart rate value of the user from the acquired heart rate data according to the activity state. It can be seen that the above process does not require strict alignment of time points of the motion characteristic data and the heart rate data, and has the advantages of small calculation amount, easy implementation on intelligent equipment with poor calculation capability, high usability, and portability.

Description

Heart rate detection method and device and intelligent wearable device

Technical Field

The disclosure relates to the field of communication, in particular to a heart rate detection method and device and intelligent wearable equipment.

Background

In the related art, a real-time heart rate value of a user may be determined from measured motion characteristic data and heart rate data. However, the time points of the motion characteristic data and the heart rate data need to be accurately aligned, and the calculation amount is large, so that the method is difficult to implement on an intelligent device with poor calculation capability, and the calculation result accuracy is not high.

Disclosure of Invention

In view of this, the present disclosure provides a heart rate detection method and apparatus, and a smart wearable device, so as to solve the deficiencies in the related art.

According to a first aspect of embodiments of the present disclosure, there is provided a heart rate detection method, the method comprising:

acquiring motion characteristic data and heart rate data of a user in a current time period;

determining the activity state of the user in the current time period according to the motion characteristic data;

and acquiring the real-time heart rate value of the user at the current moment from the heart rate data according to the activity state.

According to a second aspect of embodiments of the present disclosure, there is provided a heart rate detection apparatus, the apparatus comprising:

the data acquisition module is configured to acquire motion characteristic data and heart rate data of a user in a current time period;

an activity state determination module configured to determine an activity state to which the user belongs in the current time period according to the motion characteristic data;

a real-time heart rate obtaining module configured to obtain a real-time heart rate value of the user at the current moment from the heart rate data according to the activity state.

According to a third aspect of the embodiments of the present disclosure, there is provided a smart wearable device including the heart rate detection apparatus of the second aspect.

In the embodiment of the disclosure, the intelligent electronic device may determine the activity state of the user according to the motion characteristic data of the user in the current time period, so as to determine the real-time heart rate value of the user from the acquired heart rate data according to the activity state. It can be seen that the above process does not require strict alignment of time points of the motion characteristic data and the heart rate data, and has the advantages of small calculation amount, easy implementation on intelligent equipment with poor calculation capability, high usability, and portability.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

FIG. 1 is a flow chart of a heart rate detection method shown in the present disclosure according to an exemplary embodiment;

FIG. 2 is a flow chart of another heart rate detection method shown in the present disclosure according to an exemplary embodiment;

FIG. 3 is a schematic diagram illustrating the processing of a heart rate sensed data set according to an exemplary embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating motion feature data extraction during heart rate detection according to an exemplary embodiment of the present disclosure;

FIG. 5 is a flow chart of another heart rate detection method shown in the present disclosure according to an exemplary embodiment;

FIG. 6 is a flow chart of another heart rate detection method shown in the present disclosure according to an exemplary embodiment;

FIG. 7A is a schematic diagram illustrating heart rate frequency domain data at the time of heart rate detection according to an exemplary embodiment of the present disclosure;

FIG. 7B is a schematic illustration of acceleration frequency domain data at heart rate detection shown in the present disclosure according to an exemplary embodiment;

FIG. 8 is a flow chart of another heart rate detection method shown in the present disclosure according to an exemplary embodiment;

FIG. 9 is a block diagram of a heart rate detection device shown in accordance with an exemplary embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of a smart wearable device for heart rate detection according to an exemplary embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

The method provided by the embodiment of the disclosure can be used for intelligent wearable devices, such as intelligent bracelets, intelligent watches, intelligent bracelets and the like. As shown in fig. 1, fig. 1 is a heart rate detection method according to an exemplary embodiment, including the steps of:

in step 101, motion characteristic data and heart rate data of a user at a current time period are acquired.

Optionally, step 101 is as shown in fig. 2, and fig. 2 is another heart rate detection method shown on the basis of fig. 1, and may include:

in step 101-1, acceleration data generated by the user in the current time period is collected through an acceleration sensor.

In this step, the acceleration data generated by the user in the current time period may be collected according to a preset frequency by the pre-installed acceleration sensor.

In step 101-2, a target acceleration data set is determined from the acceleration data.

Wherein the target acceleration data set is a set of all the acceleration data within a target time period.

In this step, in order to ensure the accuracy of the subsequent heart rate detection result, the difference between the target acceleration sets of two adjacent times may satisfy a preset condition. Optionally, the target acceleration data set is a set of the acceleration data collected over a target time period. The target time duration may be preset, for example, in units of every second, and the target acceleration set is accordingly the set of acceleration data acquired every 1 second.

When the target acceleration set is determined, the acceleration data can be subjected to superposition processing by adopting a window moving method. In particular, the first acceleration data may be first removed from the first acceleration data set. Wherein the first acceleration data set is a set of all the acceleration data including the target time period by the present time, the first acceleration data is all the acceleration data within a preset time period selected in order from front to back in the first acceleration data set, and the preset time period is shorter than the target time period.

Further, all the acceleration data within the preset time length after the first acceleration data set, namely the second acceleration data, are added into the first acceleration data set, so that the second acceleration data set is formed. In the present disclosure, the second acceleration data set is determined as the target acceleration data set.

For example, as shown in fig. 3, a set of acceleration data of a target time period L, that is, the first acceleration data set is processed each time. The preset duration is less than the target duration and is M. Deleting all the acceleration data with the previous M duration, namely the first acceleration data, and adding the second acceleration data with the duration M, which are sequentially adjacent to the first acceleration set, into the first acceleration data set to obtain the second acceleration data set. The second acceleration data set may then be determined as the target acceleration data set.

Through the process, the difference value between the adjacent target acceleration data sets can meet the preset condition, and therefore the accuracy of subsequent heart rate detection is guaranteed.

In step 101-3, the motion characteristic data is determined from the target acceleration data set.

In this step, the target acceleration data set is obtained by superimposing the acceleration data generated on the axis in the preset direction. The corresponding target acceleration data sets on the three preset direction axes X, Y and the Z-axis are shown in fig. 4. In the present disclosure, the target acceleration data set may be sequentially subjected to a first preprocessing, a filtering processing, and a motion characteristic data extraction processing according to a related technique, so as to obtain the motion characteristic data, as also shown in fig. 4. The first preprocessing at least comprises modular length conversion and zero-averaging processing, and the motion characteristic data extraction processing comprises one of mean extraction processing, variance extraction processing, standard deviation extraction processing or difference extraction processing.

In step 101-4, the heart rate data of the user during daily activities is collected by a photoelectric volume rate pulse wave sensor.

In this step, the heart rate data may be acquired by the photoelectric volume rate pulse wave sensor according to a related technique. Of course, in the present disclosure, in order to guarantee the accuracy of heart rate detection, the heart rate data may be subjected to the superposition processing in a window shifting manner that is the same as the manner of determining the target acceleration set. The processing procedure is the same as the window moving procedure, and is not described herein again.

In step 102, the activity state of the user in the current time period is determined according to the motion characteristic data.

As can be seen from fig. 4, when the motion characteristic values of the motion characteristic data are in different intervals, the motion characteristic values correspond to different motion states.

Therefore, when the motion characteristic value is lower than a first preset value, the activity state to which the user belongs in the current time period is determined to be a first activity state, when the motion characteristic value is higher than the first preset value and lower than a second preset value, the activity state to which the user belongs in the current time period is determined to be a second activity state, and when the motion characteristic value is higher than the second preset value, the activity state to which the user belongs in the current time period is determined to be a third activity state. Alternatively, the first, second and third activity states may be a still state, a walking state and a running state, respectively.

In step 103, a real-time heart rate value of the user at the current moment is obtained from the heart rate data according to the activity status.

Alternatively, step 103 is shown in fig. 5, and fig. 5 is another heart rate detection method shown on the basis of fig. 3, which may include:

in step 103-1, filtering the heart rate data according to the activity state to obtain alternative heart rate data.

In this step, different filters can be selected according to different activity states to filter the heart rate data, so as to obtain the alternative heart rate data. Optionally, when the motion state is the first motion state or the second motion state, a high-pass filter may be used to remove an influence of baseline drift. When the exercise state is the third exercise state, a band-pass filter may be used to filter out effects due to baseline drift and doubling in the heart rate data.

In step 103-2, the real-time heart rate value of the user at the current moment is determined according to the activity state, the alternative heart rate data, the target acceleration data set and the historical heart rate value at the previous moment.

Alternatively, step 103-2 is shown in fig. 6, and fig. 6 is another heart rate detection method based on that shown in fig. 5, which may include:

in steps 103-21, all the acceleration data in the candidate heart rate data set and the target acceleration data set are converted into frequency domain data, and heart rate frequency domain data and acceleration frequency domain data are obtained respectively.

In this step, all the acceleration data in the candidate heart rate data and the target acceleration data set may be converted into frequency domain data according to a related technique, such as fast fourier transform, power spectral density calculation, and the like, so as to obtain the heart rate frequency domain data and the acceleration frequency domain data, respectively. For example, the heart rate frequency domain data and the acceleration frequency domain data of a certain second may be as shown in fig. 7A and 7B.

In step 103-22, according to the activity state and the acceleration frequency domain data, removing the first heart rate frequency domain data from the heart rate frequency domain data to obtain second heart rate frequency domain data.

In an implementation of the present disclosure, if the active state is the first active state, i.e. the static state, the first heart rate frequency domain data does not need to be removed from the heart rate frequency domain data, i.e. the number of the first heart rate frequency domain data is 0.

In an embodiment of the disclosure, the number of the first heart rate frequency domain data that needs to be removed is not 0 only when the active state is the second active state or the third active state.

Next, how to remove the first heart rate frequency domain data when the active states are the second active state and the third active state respectively, so as to obtain the second heart rate frequency domain data, will be described.

< the active state is the second active state >

In the present disclosure, a preset number of candidate acceleration frequency domain data may be selected from the acceleration peak values of the acceleration frequency domain data in the order of decreasing amplitude values. For example, as shown in fig. 7B, assuming that the preset number is 2, the smart wearable device may sequentially select two candidate acceleration frequency domain data whose frequency values respectively correspond to 140 and 70.

After the candidate acceleration frequency domain data is selected, a target threshold value can be determined according to the candidate acceleration frequency domain data. Optionally, if a first acceleration frequency value corresponding to first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of a second acceleration frequency value of second candidate acceleration frequency domain data in the candidate acceleration frequency domain data, the first acceleration frequency value and a preset frequency value need to be compared. The preset frequency value may be a normal heart rate value when the user walks.

For example, in fig. 7B, the frequency values corresponding to the selected candidate acceleration frequency domain data correspond to 140 and 70, respectively, where 70 is half the frequency of 140, that is, the first acceleration frequency value corresponding to the first candidate acceleration frequency domain data is 70. At this point, the size of the default frequency value and 70 need to be determined.

Further, the maximum value of the first acceleration frequency value and the preset frequency value is determined as the target threshold value.

When the activity state is the second activity state, i.e., the walking state, the first heart rate frequency domain data whose heart rate value of the heart rate frequency domain data is smaller than the target threshold may be removed from the heart rate frequency domain data.

For example, if the maximum value of the first candidate acceleration frequency value and the preset frequency value is 70, all the heart rate frequency domain data with the heart rate value below 70 in fig. 7A may be deleted, that is, the first heart rate frequency domain data is deleted, and the rest is the second heart rate frequency domain data.

< the active state is the third active state >

When the activity state is the third activity state, that is, the running state, the process of removing the first heart rate frequency domain data is similar to the above process, except that the first candidate acceleration frequency value is not required to be compared with the preset frequency value, the first candidate acceleration frequency value is directly determined as the target threshold value, and the first heart rate frequency domain data with the heart rate value smaller than the target threshold value is deleted to obtain the second heart rate frequency domain data.

In step 103-23, the real-time heart rate value is determined based on the second heart rate frequency domain data and the historical heart rate value.

Alternatively, steps 103-23 are shown in fig. 8, and fig. 8 is another heart rate detection method based on the method shown in fig. 6, which may include:

in step 103-.

In this step, the intelligent wearable device may select the first candidate heart rate frequency domain data according to a correlation technique and in a sequence from large amplitude values to small amplitude values. Optionally, the preset amplitude value is a product of a maximum peak value of the heart rate frequency domain data and a preset proportion, that is, the amplitude value of the first candidate heart rate frequency domain data needs to be not lower than the preset proportion of the maximum peak value.

For example, as shown in fig. 7A, if the preset amplitude value is 0.2, the selected first candidate heart rate frequency domain data are data points whose heart rate values respectively correspond to 80, 140, and 130.

In step 103, 232, the real-time heart rate value is determined according to the first alternative heart rate frequency domain data and the historical heart rate value.

In this step, the real-time heart rate value may be determined in different manners according to the number of the selected first candidate heart rate frequency domain data.

< the number of the first alternative heart rate frequency domain data is 1>

Whether a first difference value between the candidate heart rate value of the first candidate heart rate frequency domain data and the historical heart rate value is smaller than a first preset difference value can be directly judged according to the related technology. If so, the alternative heart rate value may be directly determined as the real-time heart rate value. Otherwise, determining a peak value closest to the alternative heart rate amplitude value of the first alternative heart rate frequency domain data as a target amplitude value, wherein a target heart rate value corresponding to the target amplitude value is the real-time heart rate value.

For example, the historical heart rate value is 130, the candidate heart rate value of only one of the first candidate heart rate frequency domain data is 140, it may be determined whether the first difference between the two is smaller than a first preset difference, and if so, 140 may be directly determined as the real-time heart rate value.

If not, the peak value having the amplitude value closest to 140, e.g., 138, may be determined as the real-time heart rate value.

< the number of the first alternative heart rate frequency domain data is plural >

When the number of the first candidate heart rate frequency domain data is multiple, first target candidate acceleration frequency domain data needs to be determined from the acceleration frequency domain data. Optionally, the candidate acceleration frequency domain data corresponding to the frequency multiplication of the first candidate acceleration frequency domain data and the candidate acceleration frequency domain data corresponding to the frequency multiplication of the second candidate acceleration frequency domain data may be used as the first target candidate acceleration frequency domain data.

For example, as shown in fig. 7B, if the first candidate acceleration frequency domain data is selected as the data point corresponding to the frequency value 70, and the second candidate acceleration frequency domain data is selected as the data point corresponding to the frequency value 140, the data points corresponding to the frequency values 70, 140, 210, and 280 … … are used as the first target candidate acceleration frequency domain data.

Further, the second target candidate acceleration frequency domain data needs to be deleted from the selected first target candidate acceleration frequency domain data, so as to obtain the third target candidate acceleration frequency domain data. The second target candidate acceleration frequency domain data is the first target candidate acceleration frequency domain data, wherein a second difference value between a first target candidate acceleration frequency value corresponding to the first target candidate acceleration frequency domain data and the historical heart rate value is smaller than a second preset difference value.

For example, the first target candidate acceleration frequency domain data includes data points corresponding to frequency values 70, 140, 210, and 280 … …, the historical heart rate value is 130, and the second difference between the first target candidate acceleration frequency value and the historical heart rate value of only the data point corresponding to the frequency value 140 in the first target candidate acceleration frequency domain data is smaller than the second preset difference, so that the data point corresponding to the frequency value 140 is deleted, and the obtained third target candidate acceleration frequency domain data includes data points corresponding to the frequency values 70, 210, and 280 … ….

After the third target candidate acceleration frequency domain data is determined, the real-time heart rate value may be determined according to the first candidate heart rate frequency domain data, the third target candidate acceleration frequency domain data, and the historical heart rate value.

In this disclosure, the first candidate heart rate frequency domain data in which a third difference between the candidate heart rate value and a target acceleration frequency value corresponding to the third target acceleration frequency domain data is smaller than a third preset difference needs to be deleted from the first candidate heart rate frequency domain data to obtain the second candidate heart rate frequency domain data.

For example, the first candidate heart rate frequency domain data includes data points whose frequency values respectively correspond to 80, 140, and 130, and the target acceleration frequency value corresponding to the third target acceleration frequency domain data is 70, the data point corresponding to 80 in the first candidate heart rate frequency domain data may be deleted, and the second candidate heart rate frequency domain data is obtained as data points whose frequency values respectively correspond to 140 and 130.

Further, it needs to be determined whether a fourth difference between a second target candidate heart rate value of the second candidate heart rate frequency domain data and the historical heart rate value is smaller than a fourth preset difference.

And if the fourth difference value between the second target candidate heart rate value and the historical heart rate value is smaller than the fourth preset difference value, determining the second target candidate heart rate value corresponding to the second target candidate heart rate frequency domain data with the largest amplitude value as the real-time heart rate frequency value.

For example, the second candidate heart rate frequency domain data is data points whose heart rate values correspond to 140 and 130, respectively, the fourth difference values are both smaller than the fourth preset difference value, and if the amplitude value of the data point which is the heart rate value 140 is the largest, 140 may be determined as the real-time heart rate value.

And if the fourth difference between one second target candidate heart rate value and the historical heart rate value is smaller than the fourth preset difference, determining the second target candidate heart rate value of which the fourth difference between the second target candidate heart rate value and the historical heart rate value is smaller than the fourth preset difference as the real-time heart rate value. That is, as long as the fourth difference between the second target candidate heart rate value and the historical heart rate value is smaller than the fourth preset difference, the second target candidate heart rate value is the real-time heart rate value.

For example, the second candidate heart rate frequency domain data is data points with heart rate values corresponding to 140 and 130, respectively, and only if the fourth difference between the data point with heart rate value 130 and the historical heart rate value is less than the fourth preset difference, 130 may be determined as the real-time heart rate value.

And if the fourth difference between all the second target candidate heart rate values and the historical heart rate value is not less than the fourth preset difference, determining the historical heart rate value as the real-time heart rate value.

For example, the second candidate heart rate frequency domain data is data points whose heart rate values respectively correspond to 140 and 130, the fourth difference between the second target candidate heart rate value and the historical heart rate value is not less than the fourth preset difference, and the historical heart rate value is 110, then 110 may be determined as the real-time heart rate value.

In the present disclosure, it is noted that when the user is in the second activity state or the third activity state, i.e. in a walking or running state, it may be determined that the real-time heart rate value should be equal to or higher than the historical heartbeat value in general. However, there may be cases where the fluctuation does not exceed the positive and negative thresholds in the range. For example, if the threshold is 10, then the real-time heart rate value should be in the range of [ the historical heart rate value-10, historical heart rate value +10 ]. Wherein, if the exercise state is switched from a running state to a walking state, the real-time heart rate value may rapidly decrease, i.e. the difference between the real-time heart rate value and the historical heart rate value is large.

Of course, after the real-time heart rate value is obtained, the intelligent wearable device may perform smoothing processing on the real-time heart rate value according to a related technique and then output the smoothed value, and may perform smoothing processing through at least one of a moving average filter, a kalman filter, and an autoregressive filter.

In the above process, the real-time heart rate value may be determined based on different motion states, time points of the motion characteristic data and the heart rate data are not required to be strictly aligned, and the maximum amount of calculation involved is in frequency domain conversion, so that the method may be implemented on a device with poor calculation capability. The usability is high, and the portability is realized.

Corresponding to the foregoing method embodiments, the present disclosure also provides embodiments of an apparatus.

As shown in fig. 9, fig. 9 is a block diagram of a heart rate detection apparatus according to an exemplary embodiment of the present disclosure, including:

a data acquisition module 210 configured to acquire motion characteristic data and heart rate data of a user at a current time period;

an activity state determination module 220 configured to determine an activity state to which the user belongs in the current time period according to the motion characteristic data;

a real-time heart rate obtaining module 230 configured to obtain a real-time heart rate value of the user at the current moment from the heart rate data according to the activity status.

Optionally, the data obtaining module includes:

the first acquisition submodule is configured to acquire acceleration data generated by the user in the current time period through an acceleration sensor;

a first determination submodule configured to determine a target acceleration data set from the acceleration data, the target acceleration data set being a set of all the acceleration data within a target time period;

a second determination submodule configured to determine the motion characteristic data from the target acceleration data set;

a second acquisition sub-module configured to acquire the heart rate data of the user during daily activities through a photoelectric volume rate pulse wave sensor.

Optionally, the first determining sub-module includes:

a first removal unit configured to remove first acceleration data from a first acceleration data set, the first acceleration data set being a set of all the acceleration data including the target time period by a current time, the first acceleration data being all the acceleration data within a preset time period selected in order from front to back in the first acceleration data set, the preset time period being shorter than the target time period;

an adding unit configured to add second acceleration data into the first acceleration data set to form a second acceleration data set, the second acceleration data being all the acceleration data within the preset time period after the first acceleration data set;

a determination unit configured to determine the second acceleration data set as the target acceleration data set.

Optionally, the second determining sub-module includes:

the processing unit is configured to sequentially perform first preprocessing, filtering processing and motion characteristic data extraction processing on the target acceleration data set to obtain the motion characteristic data;

the first preprocessing at least comprises modular length conversion and zero-averaging processing, and the motion characteristic data extraction processing comprises one of mean extraction processing, variance extraction processing, standard deviation extraction processing or difference extraction processing.

Optionally, the activity state determination module includes:

a third determining sub-module, configured to determine that the activity state to which the user belongs in the current time period is a first activity state when the motion feature value of the motion feature data is lower than a first preset value;

a fourth determination sub-module configured to determine that the activity state to which the user belongs in the current time period is a second activity state when the motion feature value is higher than the first preset value and lower than a second preset value;

a fifth determination sub-module configured to determine that the activity state to which the user belongs in the current time period is a third activity state when the motion feature value is higher than the second preset value.

Optionally, the real-time heart rate acquisition module comprises:

the filtering submodule is configured to filter the heart rate data according to the activity state to obtain alternative heart rate data;

a real-time heart rate determination submodule configured to determine the real-time heart rate value for the user at a current time based on the activity state, the alternative heart rate data, the target acceleration data set, and a historical heart rate value for a previous time.

Optionally, the filtering submodule includes:

a first filtering unit configured to perform filtering processing on the heart rate data by a high-pass filter when the activity state is the first activity state or the second activity state;

a second filtering unit configured to perform filtering processing on the heart rate data by a band-pass filter when the activity state is the third activity state.

Optionally, the real-time heart rate determination sub-module comprises:

a conversion unit configured to convert all the acceleration data in the candidate heart rate data and the target acceleration data set into frequency domain data, so as to obtain heart rate frequency domain data and acceleration frequency domain data, respectively;

a second removing unit, configured to remove the first heart rate frequency domain data from the heart rate frequency domain data according to the activity state and the acceleration frequency domain data to obtain second heart rate frequency domain data;

a real-time heart rate determination unit configured to determine the real-time heart rate value from the second heart rate frequency domain data and the historical heart rate value.

Optionally, when the activity state is the first activity state, the number of the first heart rate frequency domain data is 0.

Optionally, the second removing unit includes:

the first selecting subunit is configured to select a preset number of candidate acceleration frequency domain data from the acceleration peak values of the acceleration frequency domain data according to the order of magnitude values from large to small when the activity state is the second activity state or the third activity state;

a first threshold determination subunit configured to determine a target threshold from the candidate acceleration frequency domain data;

a removal subunit configured to remove, from the heart rate frequency domain data, the first heart rate frequency domain data whose heart rate value of the heart rate frequency domain data is smaller than the target threshold.

Optionally, the first threshold determining subunit includes:

the comparison subunit is configured to, when the active state is the second active state, compare the first acceleration frequency value with a preset frequency value if the first acceleration frequency value corresponding to the first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of the second acceleration frequency value of the second candidate acceleration frequency domain data in the candidate acceleration frequency domain data;

a second threshold determination subunit configured to determine a maximum value of the first acceleration frequency value and the preset frequency value as the target threshold.

Optionally, the first threshold determining subunit includes:

a third threshold determining subunit, configured to, when the active state is the third active state, determine the first acceleration frequency value as the target threshold if a first acceleration frequency value corresponding to a first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of a second acceleration frequency value of a second candidate acceleration frequency domain data in the candidate acceleration frequency domain data.

Optionally, the real-time heart rate determination unit comprises:

the second selecting subunit is configured to select, in descending order, the second heart rate frequency domain data with amplitude values larger than a preset amplitude value as first alternative heart rate frequency domain data;

a first real-time heart rate determination subunit configured to determine the real-time heart rate value from the first alternative heart rate frequency domain data and the historical heart rate value.

Optionally, the first real-time heart rate determination subunit comprises:

a first judging subunit, configured to, when the number of the first candidate heart rate frequency domain data is 1, judge whether a first difference value between a candidate heart rate value of the first candidate heart rate frequency domain data and the historical heart rate value is smaller than a first preset difference value;

a second real-time heart rate determination subunit configured to determine the alternative heart rate value as the real-time heart rate value when the first difference value is smaller than the first preset difference value;

a third real-time heart rate determining subunit configured to determine, as the real-time heart rate value, a target heart rate value corresponding to a target amplitude value when the difference is not less than the first preset difference, where the target amplitude value is a peak value closest to the amplitude value of the first candidate heart rate frequency domain data.

Optionally, the first real-time heart rate determination subunit comprises:

a first acceleration determination subunit configured to determine, when the number of the first candidate heart rate frequency domain data is plural, first target candidate acceleration frequency domain data from the acceleration frequency domain data;

a first deleting subunit, configured to delete second target candidate acceleration frequency domain data from the first target candidate acceleration frequency domain data to obtain third target candidate acceleration frequency domain data, where the second target candidate acceleration frequency domain data is the first target candidate acceleration frequency domain data in which a second difference between a first target candidate acceleration frequency value corresponding to the first target candidate acceleration frequency domain data and the historical heart rate value is smaller than a second preset difference;

a fourth real-time heart rate determination subunit configured to determine the real-time heart rate value according to the first candidate heart rate frequency domain data, the third target candidate acceleration frequency domain data, and the historical heart rate value.

Optionally, the first acceleration determination subunit includes:

a second acceleration determining subunit, configured to use the candidate acceleration frequency domain data corresponding to the frequency multiplication of the first candidate acceleration frequency domain data and the candidate acceleration frequency domain data corresponding to the frequency multiplication of the second candidate acceleration frequency domain data, which include the first candidate acceleration frequency domain data, the second candidate acceleration frequency domain data, as the first target candidate acceleration frequency domain data.

Optionally, the fourth real-time heart rate determination subunit includes:

a second deleting subunit, configured to delete, from the first candidate heart rate frequency domain data, the first candidate heart rate frequency domain data in which a third difference between the candidate heart rate value and a target acceleration frequency value corresponding to the third target acceleration frequency domain data is smaller than a third preset difference, so as to obtain second candidate heart rate frequency domain data;

a second determining subunit, configured to determine whether a fourth difference between a second target candidate heart rate value of the second candidate heart rate frequency domain data and the historical heart rate value is smaller than a fourth preset difference;

a fifth temporal heart rate determining subunit, configured to determine, if there are a plurality of the fourth difference values between the second target candidate heart rate value and the historical heart rate value are smaller than the fourth preset difference value, the second target candidate heart rate value corresponding to the second target candidate heart rate frequency domain data with the largest amplitude value as the real-time heart rate value;

a sixth real-time heart rate determination subunit configured to determine, as the real-time heart rate value, the second target heart rate candidate value having the fourth difference from the historical heart rate value smaller than the fourth preset difference, if there is one of the second target heart rate candidate value and the historical heart rate value having the fourth difference smaller than the fourth preset difference;

a seventh real-time heart rate determination subunit configured to determine the historical heart rate value as the real-time heart rate value if the fourth difference between all the second target candidate heart rate values and the historical heart rate value is not less than the fourth preset difference.

Correspondingly, the present disclosure also provides an intelligent wearable device, including any one of the above heart rate detection devices.

The present disclosure also proposes a schematic structural diagram of a smart wearable device according to an exemplary embodiment of the present application shown in fig. 10. As shown in fig. 10, at the hardware level, the smart wearable device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads a corresponding computer program from the nonvolatile memory to the memory and then runs the computer program to form the heart rate detection control device on a logic level. Of course, besides the software implementation, the present application does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only exemplary of the present disclosure and should not be taken as limiting the disclosure, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims (29)

1. A method of heart rate detection, the method comprising:

acquiring motion characteristic data and heart rate data of a user in a current time period; determining the activity state of the user in the current time period according to the motion characteristic data;

acquiring a real-time heart rate value of the user at the current moment from the heart rate data according to the activity state;

the obtaining of the real-time heart rate value of the user at the current moment from the heart rate data according to the activity state includes:

filtering the heart rate data according to the activity state to obtain alternative heart rate data;

determining the real-time heart rate value of the user at the current moment according to the activity state, the alternative heart rate data, the target acceleration data set and the historical heart rate value at the previous moment; the target acceleration data set is a set of all acceleration data within a target time duration;

the filtering the heart rate data according to the activity state includes:

when the activity state is a first activity state or a second activity state, filtering the heart rate data through a high-pass filter;

when the activity state is a third activity state, filtering the heart rate data through a band-pass filter;

determining the real-time heart rate value of the user at the current moment according to the activity state, the alternative heart rate data, the target acceleration data set and the historical heart rate value at the previous moment, including:

converting all the acceleration data in the alternative heart rate data and the target acceleration data set into frequency domain data to respectively obtain heart rate frequency domain data and acceleration frequency domain data;

according to the activity state and the acceleration frequency domain data, removing first heart rate frequency domain data from the heart rate frequency domain data to obtain second heart rate frequency domain data;

and determining the real-time heart rate value according to the second heart rate frequency domain data and the historical heart rate value.

2. The method of claim 1, wherein the obtaining motion characteristic data and heart rate data of the user over the current time period comprises:

acquiring acceleration data generated by the user in the current time period through an acceleration sensor;

determining the target acceleration data set from the acceleration data;

determining the motion characteristic data from the target acceleration data set;

and acquiring the heart rate data of the user in daily activities through a photoelectric volume rate pulse wave sensor.

3. The method of claim 2, wherein the determining the set of target accelerations from the acceleration data comprises:

removing first acceleration data from a first acceleration data set, the first acceleration data set being a set of all the acceleration data including the target duration by the present time, the first acceleration data being all the acceleration data within a preset duration selected in order from front to back in the first acceleration data set, the preset duration being shorter than the target duration;

adding second acceleration data to the first acceleration data set to form a second acceleration data set, wherein the second acceleration data is all the acceleration data within the preset time length after the first acceleration data set;

determining the second acceleration data set as the target acceleration data set.

4. The method of claim 2, wherein said determining said motion characteristic data from said target acceleration data set comprises:

sequentially performing first preprocessing, filtering processing and motion characteristic data extraction processing on the target acceleration data set to obtain the motion characteristic data;

the first preprocessing at least comprises modular length conversion and zero-averaging processing, and the motion characteristic data extraction processing comprises one of mean extraction processing, variance extraction processing, standard deviation extraction processing or difference extraction processing.

5. The method of claim 2, wherein determining the activity state to which the user belongs during the current time period based on the motion characteristic data comprises:

when the motion characteristic value of the motion characteristic data is lower than a first preset value, determining that the activity state of the user in the current time period is the first activity state;

when the motion characteristic value is higher than the first preset value and lower than a second preset value, determining that the activity state of the user in the current time period is the second activity state;

when the motion characteristic value is higher than the second preset value, determining that the activity state of the user in the current time period is the third activity state.

6. The method of claim 1, wherein the number of the first heart rate frequency domain data is 0 when the activity state is the first activity state.

7. The method of claim 1, wherein removing first heart rate frequency domain data from the heart rate frequency domain data according to the acceleration frequency domain data when the activity state is the second activity state or the third activity state comprises:

selecting a preset number of alternative acceleration frequency domain data from the acceleration peak values of the acceleration frequency domain data according to the sequence of the amplitude values from large to small;

determining a target threshold according to the alternative acceleration frequency domain data;

removing the first heart rate frequency domain data from the heart rate frequency domain data having a heart rate value less than the target threshold.

8. The method of claim 7, wherein when the activity state is the second activity state, the determining a target threshold from the alternative acceleration frequency domain data comprises:

if a first acceleration frequency value corresponding to first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of a second acceleration frequency value of second candidate acceleration frequency domain data in the candidate acceleration frequency domain data, comparing the first acceleration frequency value with a preset frequency value;

determining a maximum value of the first acceleration frequency value and the preset frequency value as the target threshold value.

9. The method of claim 7, wherein when the activity state is the third activity state, the determining a target threshold from the alternative acceleration frequency domain data comprises:

and if a first acceleration frequency value corresponding to first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of a second acceleration frequency value of second candidate acceleration frequency domain data in the candidate acceleration frequency domain data, determining the first acceleration frequency value as the target threshold value.

10. The method of claim 8 or 9, wherein determining the real-time heart rate value from the second heart rate frequency domain data and the historical heart rate value comprises:

selecting the second heart rate frequency domain data with amplitude values larger than a preset amplitude value as first alternative heart rate frequency domain data from large to small;

and determining the real-time heart rate value according to the first alternative heart rate frequency domain data and the historical heart rate value.

11. The method of claim 10, wherein when the number of the first candidate heart rate frequency domain data is 1, the determining the real-time heart rate value according to the first candidate heart rate frequency domain data and the historical heart rate value comprises:

judging whether a first difference value between the alternative heart rate value of the first alternative heart rate frequency domain data and the historical heart rate value is smaller than a first preset difference value or not;

when the first difference value is smaller than the first preset difference value, determining the alternative heart rate value as the real-time heart rate value;

and when the difference is not smaller than the first preset difference, determining a target heart rate value corresponding to a target amplitude value as the real-time heart rate value, wherein the target amplitude value is a peak value closest to the amplitude value of the first candidate heart rate frequency domain data.

12. The method of claim 10, wherein when the number of the first candidate heart rate frequency domain data is plural, the determining the real-time heart rate value from the first candidate heart rate frequency domain data and the historical heart rate value comprises:

determining first target alternative acceleration frequency domain data from the acceleration frequency domain data;

deleting second target candidate acceleration frequency domain data from the first target candidate acceleration frequency domain data to obtain third target candidate acceleration frequency domain data, wherein the second target candidate acceleration frequency domain data is the first target candidate acceleration frequency domain data of which a second difference value between a first target candidate acceleration frequency value corresponding to the first target candidate acceleration frequency domain data and the historical heart rate value is smaller than a second preset difference value;

and determining the real-time heart rate value according to the first candidate heart rate frequency domain data, the third target candidate acceleration frequency domain data and the historical heart rate value.

13. The method of claim 12, wherein determining the first target candidate acceleration frequency domain data from the acceleration frequency domain data comprises:

and taking the candidate acceleration frequency domain data which comprises first candidate acceleration frequency domain data, second candidate acceleration frequency domain data, and the candidate acceleration frequency domain data corresponding to the frequency multiplication of the first candidate acceleration frequency domain data and the candidate acceleration frequency domain data corresponding to the frequency multiplication of the second candidate acceleration frequency domain data as the first target candidate acceleration frequency domain data.

14. The method of claim 12, wherein determining the real-time heart rate value from the first candidate heart rate frequency domain data, the third target candidate acceleration frequency domain data, and the historical heart rate value comprises:

deleting the first alternative heart rate frequency domain data in which a third difference value between the alternative heart rate value and a target acceleration frequency value corresponding to the third target acceleration frequency domain data is smaller than a third preset difference value from the first alternative heart rate frequency domain data to obtain second alternative heart rate frequency domain data;

judging whether a fourth difference value between a second target alternative heart rate value of the second alternative heart rate frequency domain data and the historical heart rate value is smaller than a fourth preset difference value or not;

if the fourth difference value between the second target alternative heart rate value and the historical heart rate value is smaller than the fourth preset difference value, determining the second target alternative heart rate value corresponding to the second target alternative heart rate frequency domain data with the largest amplitude value as the real-time heart rate value;

if one of the second target candidate heart rate values is smaller than the fourth preset difference value, determining the second target candidate heart rate value with the fourth difference value smaller than the fourth preset difference value as the real-time heart rate value;

and if the fourth difference between all the second target candidate heart rate values and the historical heart rate value is not less than the fourth preset difference, determining the historical heart rate value as the real-time heart rate value.

15. A heart rate detection device, the device comprising:

the data acquisition module is configured to acquire motion characteristic data and heart rate data of a user in a current time period;

an activity state determination module configured to determine an activity state to which the user belongs in the current time period according to the motion characteristic data;

a real-time heart rate obtaining module configured to obtain a real-time heart rate value of the user at the current moment from the heart rate data according to the activity state;

the real-time heart rate acquisition module comprises:

the filtering submodule is configured to filter the heart rate data according to the activity state to obtain alternative heart rate data;

a real-time heart rate determination submodule configured to determine the real-time heart rate value of the user at a current moment according to the activity state, the alternative heart rate data, a target acceleration data set, and a historical heart rate value at a previous moment; the target acceleration data set is a set of all acceleration data within a target time duration;

the filtering submodule includes:

a first filtering unit configured to perform filtering processing on the heart rate data through a high-pass filter when the activity state is a first activity state or a second activity state;

a second filtering unit configured to perform filtering processing on the heart rate data by a band-pass filter when the activity state is a third activity state;

the real-time heart rate determination sub-module includes:

the conversion unit is configured to convert all the acceleration data in the candidate heart rate data and the target acceleration data set into frequency domain data to respectively obtain heart rate frequency domain data and acceleration frequency domain data;

a second removing unit, configured to remove the first heart rate frequency domain data from the heart rate frequency domain data according to the activity state and the acceleration frequency domain data to obtain second heart rate frequency domain data;

a real-time heart rate determination unit configured to determine the real-time heart rate value from the second heart rate frequency domain data and the historical heart rate value.

16. The apparatus of claim 15, wherein the data acquisition module comprises:

the first acquisition submodule is configured to acquire acceleration data generated by the user in the current time period through an acceleration sensor;

a first determination submodule configured to determine the target acceleration data set from the acceleration data;

a second determination submodule configured to determine the motion characteristic data from the target acceleration data set;

a second acquisition sub-module configured to acquire the heart rate data of the user during daily activities through a photoelectric volume rate pulse wave sensor.

17. The apparatus of claim 16, wherein the first determining submodule comprises:

a first removal unit configured to remove first acceleration data from a first acceleration data set, the first acceleration data set being a set of all the acceleration data including the target time period by a current time, the first acceleration data being all the acceleration data within a preset time period selected in order from front to back in the first acceleration data set, the preset time period being shorter than the target time period;

an adding unit configured to add second acceleration data into the first acceleration data set to form a second acceleration data set, the second acceleration data being all the acceleration data within the preset time period after the first acceleration data set;

a determination unit configured to determine the second acceleration data set as the target acceleration data set.

18. The apparatus of claim 16, wherein the second determining submodule comprises:

the processing unit is configured to sequentially perform first preprocessing, filtering processing and motion characteristic data extraction processing on the target acceleration data set to obtain the motion characteristic data;

the first preprocessing at least comprises modular length conversion and zero-averaging processing, and the motion characteristic data extraction processing comprises one of mean extraction processing, variance extraction processing, standard deviation extraction processing or difference extraction processing.

19. The apparatus of claim 16, wherein the activity state determination module comprises:

a third determining sub-module, configured to determine that the activity state to which the user belongs in the current time period is the first activity state when the motion feature value of the motion feature data is lower than a first preset value;

a fourth determination sub-module configured to determine that the activity state to which the user belongs in the current time period is the second activity state when the motion feature value is higher than the first preset value and lower than a second preset value;

a fifth determination sub-module configured to determine that the activity state to which the user belongs in the current time period is the third activity state when the motion feature value is higher than the second preset value.

20. The apparatus of claim 15, wherein the number of the first heart rate frequency domain data is 0 when the activity state is the first activity state.

21. The apparatus of claim 15, wherein the second removing unit comprises:

the first selecting subunit is configured to select a preset number of candidate acceleration frequency domain data from the acceleration peak values of the acceleration frequency domain data according to the order of magnitude values from large to small when the activity state is the second activity state or the third activity state;

a first threshold determination subunit configured to determine a target threshold from the candidate acceleration frequency domain data;

a removal subunit configured to remove, from the heart rate frequency domain data, the first heart rate frequency domain data whose heart rate value of the heart rate frequency domain data is smaller than the target threshold.

22. The apparatus of claim 21, wherein the first threshold determining subunit comprises:

the comparison subunit is configured to, when the active state is the second active state, compare the first acceleration frequency value with a preset frequency value if the first acceleration frequency value corresponding to the first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of the second acceleration frequency value of the second candidate acceleration frequency domain data in the candidate acceleration frequency domain data;

a second threshold determination subunit configured to determine a maximum value of the first acceleration frequency value and the preset frequency value as the target threshold.

23. The apparatus of claim 21, wherein the first threshold determining subunit comprises:

a third threshold determining subunit, configured to, when the active state is the third active state, determine the first acceleration frequency value as the target threshold if a first acceleration frequency value corresponding to a first candidate acceleration frequency domain data in the candidate acceleration frequency domain data is half of a second acceleration frequency value of a second candidate acceleration frequency domain data in the candidate acceleration frequency domain data.

24. The apparatus according to claim 22 or 23, wherein the real-time heart rate determination unit comprises:

the second selecting subunit is configured to select, in descending order, the second heart rate frequency domain data with amplitude values larger than a preset amplitude value as first alternative heart rate frequency domain data;

a first real-time heart rate determination subunit configured to determine the real-time heart rate value from the first alternative heart rate frequency domain data and the historical heart rate value.

25. The apparatus of claim 24, wherein the first real-time heart rate determination subunit comprises:

a first judging subunit, configured to, when the number of the first candidate heart rate frequency domain data is 1, judge whether a first difference value between a candidate heart rate value of the first candidate heart rate frequency domain data and the historical heart rate value is smaller than a first preset difference value;

a second real-time heart rate determination subunit configured to determine the alternative heart rate value as the real-time heart rate value when the first difference value is smaller than the first preset difference value;

a third real-time heart rate determining subunit configured to determine, as the real-time heart rate value, a target heart rate value corresponding to a target amplitude value when the difference is not less than the first preset difference, where the target amplitude value is a peak value closest to the amplitude value of the first candidate heart rate frequency domain data.

26. The apparatus of claim 24, wherein the first real-time heart rate determination subunit comprises:

a first acceleration determination subunit configured to determine, when the number of the first candidate heart rate frequency domain data is plural, first target candidate acceleration frequency domain data from the acceleration frequency domain data;

a first deleting subunit, configured to delete second target candidate acceleration frequency domain data from the first target candidate acceleration frequency domain data to obtain third target candidate acceleration frequency domain data, where the second target candidate acceleration frequency domain data is the first target candidate acceleration frequency domain data in which a second difference between a first target candidate acceleration frequency value corresponding to the first target candidate acceleration frequency domain data and the historical heart rate value is smaller than a second preset difference;

a fourth real-time heart rate determination subunit configured to determine the real-time heart rate value according to the first candidate heart rate frequency domain data, the third target candidate acceleration frequency domain data, and the historical heart rate value.

27. The apparatus of claim 26, wherein the first acceleration determination subunit comprises:

the second acceleration determining subunit is configured to use, as the first target candidate acceleration frequency domain data, candidate acceleration frequency domain data that includes first candidate acceleration frequency domain data, second candidate acceleration frequency domain data, the candidate acceleration frequency domain data corresponding to a frequency multiplication of the first candidate acceleration frequency domain data, and the candidate acceleration frequency domain data corresponding to a frequency multiplication of the second candidate acceleration frequency domain data.

28. The apparatus of claim 26, wherein the fourth real-time heart rate determination subunit comprises:

a second deleting subunit, configured to delete, in the first candidate heart rate frequency domain data, the first candidate heart rate frequency domain data in which a third difference between the candidate heart rate value and a target acceleration frequency value corresponding to the third target acceleration frequency domain data is smaller than a third preset difference, so as to obtain second candidate heart rate frequency domain data;

a second determining subunit, configured to determine whether a fourth difference between a second target candidate heart rate value of the second candidate heart rate frequency domain data and the historical heart rate value is smaller than a fourth preset difference;

a fifth temporal heart rate determining subunit, configured to determine, if there are a plurality of the fourth difference values between the second target candidate heart rate value and the historical heart rate value are smaller than the fourth preset difference value, the second target candidate heart rate value corresponding to the second target candidate heart rate frequency domain data with the largest amplitude value as the real-time heart rate value;

a sixth real-time heart rate determination subunit configured to determine, as the real-time heart rate value, the second target heart rate candidate value having the fourth difference from the historical heart rate value smaller than the fourth preset difference, if there is one of the second target heart rate candidate value and the historical heart rate value having the fourth difference smaller than the fourth preset difference;

a seventh real-time heart rate determination subunit configured to determine the historical heart rate value as the real-time heart rate value if the fourth difference between all the second target candidate heart rate values and the historical heart rate value is not less than the fourth preset difference.

29. A smart wearable device comprising the heart rate detection apparatus of any of claims 15-28.

Images