Heartbeat interval measuring device, computer program for heartbeat interval measuring device

Abstract

To accurately extract a heartbeat peak from cardiac sound waveform data and accurately measure a heartbeat interval.SOLUTION: A heartbeat interval measuring apparatus 10 comprises: a data acquisition unit 12 configured to acquire cardiac sound waveform data and biological data different from the cardiac sound waveform data; a heartbeat peak selection unit 14 configured to select a heartbeat peak of the cardiac sound waveform data on the basis of a feature amount of the biological data; and a heartbeat interval calculation unit 16 configured to calculate a heartbeat interval from the selected heartbeat peak.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology disclosed in this specification relates to a heart rate interval measuring device, a computer program for the heart rate interval measuring device, and a method for generating a learning model.

[0002] Patent Documents 1 and 2 disclose techniques for monitoring the psychological or physical state of a user from fluctuations in heartbeat intervals. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2017-124014 [Patent Document 2] Japanese Patent Publication No. 2020-075136 Summary of the Invention [Problem to be solved by the invention]

[0004] If the heartbeat interval is measured using phonocardiogram waveform data, it is possible to measure the heartbeat interval with a simple device. In order to measure the heartbeat interval using phonocardiogram waveform data, it is necessary to accurately extract heartbeat peaks from the phonocardiogram waveform data and calculate the heartbeat interval from the heartbeat peaks. This specification provides a technology that can accurately measure the heartbeat interval by accurately extracting heartbeat peaks from phonocardiogram waveform data. [Means for solving the problem]

[0005] The heartbeat interval measuring device (10) disclosed in this specification may include a data acquiring unit (12) configured to acquire phonocardiogram waveform data and biological data other than the phonocardiogram waveform data, a heartbeat peak selecting unit (14) configured to select a heartbeat peak of the phonocardiogram waveform data based on a feature of the biological data, and a heartbeat interval calculating unit (16) configured to calculate the heartbeat interval from the selected heartbeat peak. This heartbeat interval measuring device takes into account the biological data when the phonocardiogram waveform data was measured, allowing for more accurate selection of the heartbeat peak of the phonocardiogram waveform data. Therefore, the heartbeat interval measuring device disclosed in this specification can accurately measure the heartbeat interval.

[0006] The computer program for the heartbeat interval measuring device (10) disclosed herein may cause the heartbeat interval measuring device to function as the following components: a data acquisition unit (12) configured to acquire heartbeat waveform data and biological data other than the heartbeat waveform data; a heartbeat peak selection unit (14) configured to select a heartbeat peak of the heartbeat waveform data based on a feature of the biological data; and a heartbeat interval calculation unit (16) configured to calculate the heartbeat interval from the selected heartbeat peak. This computer program takes into account the biological data used when the heartbeat waveform data was measured, allowing for more accurate selection of the heartbeat peak of the heartbeat waveform data. Therefore, the computer program for the heartbeat interval measuring device disclosed herein allows for accurate measurement of the heartbeat interval.

[0007] The method for generating a learning model disclosed herein may acquire multiple training data including biological data, acoustocardiogram waveform data, and heartbeat peaks, input the biological data and acoustocardiogram waveform data, and generate a learning model that outputs the heartbeat peaks of the acoustocardiogram waveform data. When a trained model generated in this manner is used, the biological data at the time the acoustocardiogram waveform data was measured is taken into account, allowing for more accurate selection of the heartbeat peaks of the acoustocardiogram waveform data. Therefore, when a trained model generated by the generation method disclosed herein is used, the heartbeat interval can be accurately measured. [Brief explanation of the drawings]

[0008] [Figure 1] 1 shows an outline of a functional block diagram of a heart rate measurement system. [Figure 2] 1 shows an example of respiratory waveform data and cardiac sound waveform data for one breathing cycle. [Figure 3] 10 shows a processing flow of a method for selecting a heartbeat peak of cardiac sound waveform data according to a predetermined rule determined based on the feature amount of respiratory waveform data. [Figure 4] A diagram for explaining the method of FIG. 3 is shown. [Figure 5] 10 shows a process flow of a method for selecting heartbeat peaks of heart sound waveform data using sample heart sound waveform data. [Figure 6] An overview of the trained model is shown below. [Figure 7] The processing flow of a method for selecting the heartbeat peak of cardiac sound waveform data using a trained model is shown below. DETAILED DESCRIPTION OF THE INVENTION

[0009] A system for measuring a user's heart rate interval will be described below with reference to the drawings. By monitoring the fluctuations in the user's heart rate interval measured by this system, the user's psychological or physical state can be estimated. For example, by monitoring the fluctuations in the user's heart rate interval, the user's drowsiness can be estimated. Such a system may be installed in a vehicle and used to detect the driver's drowsiness.

[0010] As shown in FIG. 1, the heartbeat interval measuring system 1 includes a heartbeat interval measuring device 10 and a sensor 20. The heartbeat interval measuring device 10 is configured by a computer and has a data acquisition unit 12, a heartbeat peak selection unit 14, and a heartbeat interval calculation unit 16. The computer has a CPU, a storage device, and an input / output device. By executing a program stored in the storage device on the CPU, the CPU can function as the data acquisition unit 12, the heartbeat peak selection unit 14, and the heartbeat interval calculation unit 16 and can execute various processes described below. The sensor 20 is a sensor capable of detecting the user's heart sounds and is not particularly limited, and may be, for example, a microphone. The sensor 20, which is a microphone, inputs sounds emitted by the user (sounds including both heart sounds and respiratory sounds, as will be described later), converts the sounds into electrical sensor signals, and outputs the electrical sensor signals to the heartbeat interval measuring device 10.

[0011] The data acquisition unit 12 of the heartbeat interval measuring device 10 receives the sensor signal output from the sensor 20. The data acquisition unit 12 further extracts heart sound waveform data and respiratory waveform data from the received sensor signal. In this example, the sensor 20 is configured with a single microphone, so the data acquisition unit 12 extracts heart sound waveform data and respiratory waveform data from the sensor signal based on the frequency band. Alternatively, the sensor 20 may be configured with two sensors, i.e., a sensor that selectively acquires heart sound waveform data and a sensor that selectively acquires respiratory waveform data. In this case, the data acquisition unit 12 receives heart sound waveform data from one sensor and respiratory waveform data from the other sensor.

[0012] Figure 2 shows examples of extracted cardiac sound waveform data and respiratory waveform data. Figure 2(A) shows the respiratory waveform data, and Figure 2(B) shows the cardiac sound waveform data. As shown in Figure 2, the data acquisition unit 12 extracts respiratory waveform data from the sensor signal using a bandpass filter that passes low frequencies, and extracts cardiac sound waveform data from the sensor signal using a bandpass filter that passes high frequencies. In this example, six beats of cardiac sound waveform data appear in one respiratory cycle.

[0013] When the vertical axis of (A) in FIG. 2 is positive, it indicates that breathing is in an "exhale" state. When the vertical axis of (A) in FIG. 2 is negative, it indicates that breathing is in an "inhale" state. Each of T1 to T6 in FIG. 2 indicates respiratory waveform data and phonocardiogram waveform data corresponding to a single heartbeat in a time series with respect to that heartbeat. "T1" indicates respiratory waveform data and phonocardiogram waveform data for one beat immediately after the "inhale" of breathing becomes strongest. "T2" indicates respiratory waveform data and phonocardiogram waveform data for one beat when breathing changes from "inhale" to "exhale." "T3" indicates respiratory waveform data and phonocardiogram waveform data when breathing becomes strongest. "T4" indicates respiratory waveform data and phonocardiogram waveform data immediately after the "exhale" of breathing becomes strongest. "T5" indicates respiratory waveform data and phonocardiogram waveform data for one beat when breathing changes from "exhale" to "inhale." "T6" indicates one beat of respiratory waveform data and acoustic heart waveform data when breathing is strongest. As shown by T1 to T6 in FIG. 2, one beat of acoustic heart waveform data takes on various shapes depending on the breathing state at that time. This suggests that the heartbeat peak of the acoustic heart waveform data to be selected for measuring the heartbeat interval can be selected more accurately by taking the breathing state into consideration. As will be described below, the heartbeat interval measuring system 1 is configured to select the heartbeat peak of the acoustic heart waveform data taking the breathing state into consideration.

[0014] The heartbeat peak selection unit 14 of the heartbeat interval measuring device 10 receives the respiratory waveform data and the acoustic cardiac waveform data from the data acquisition unit 12. The heartbeat peak selection unit 14 further selects a heartbeat peak for each of the cardiac sound waveform data for one beat included in the acoustic cardiac waveform data. More specifically, when selecting a heartbeat peak for one beat of the acoustic cardiac waveform data, the heartbeat peak selection unit 14 calculates feature amounts of the respiratory waveform data associated in time series with the cardiac sound waveform data for that one beat, and selects the heartbeat peak for that one beat of the acoustic cardiac waveform data based on the feature amounts. The feature amount of the respiratory waveform data is not particularly limited, and may be, for example, the slope or phase of the respiratory waveform.

[0015] As described above, the shape of one beat's worth of cardiac sound waveform data varies depending on the breathing state at that time. Therefore, the timing at which the heartbeat peak of one beat's worth of cardiac sound waveform data should be determined is affected by the breathing state at that time. The heartbeat peak selection unit 14 can select the heartbeat peak of one beat's worth of cardiac sound waveform data based on the feature amount of the respiratory waveform data, thereby enabling more accurate selection of the heartbeat peak.

[0016] The heartbeat interval calculation unit 16 of the heartbeat interval measuring device 10 receives the heartbeat peaks of the heartbeat waveform data from the heartbeat peak selection unit 14. The heartbeat interval calculation unit 16 further calculates the interval between chronologically adjacent heartbeat peaks, i.e., the heartbeat interval. Because the accurate heartbeat peaks are extracted, the calculated heartbeat intervals are also accurate. The heartbeat interval measuring system 1 can estimate the user's psychological or physical state by monitoring fluctuations in the calculated heartbeat intervals.

[0017] Below, several specific examples are given for selecting the heartbeat peak of the phonocardiogram waveform data from the feature quantities of the respiratory waveform data. The specific examples are merely examples, and various other methods can be used to select the heartbeat peak of the phonocardiogram waveform data from the feature quantities of the respiratory waveform data. While the following describes an example in which the heartbeat interval is calculated using real-time processing, the heartbeat interval may alternatively be calculated using batch processing.

[0018] (Selection of heart rate peaks according to predetermined rules) FIG. 3 shows a processing flow of a method for selecting heartbeat peaks of cardiac sound waveform data according to a predetermined rule determined based on the feature amount of respiratory waveform data.

[0019] First, in step S1, the data acquisition unit 12 receives a sensor signal of the measurement target from the sensor 20.

[0020] Next, in step S2, the data acquiring unit 12 extracts cardiac waveform data and respiratory waveform data from the sensor signal based on the frequency band.

[0021] Next, in step S3, the heartbeat peak selection unit 14 selects a heartbeat peak of the heartbeat waveform data in accordance with a rule determined based on the feature quantities of the respiratory waveform data. In this example, as shown in FIG. 4 , when selecting a heartbeat peak of one beat's worth of heartbeat data, if the respiratory waveform data chronologically associated with that one beat's worth of heartbeat data is negative, the heartbeat peak selection unit 14 selects the maximum value (indicated by a circle) of the heartbeat waveform data as the heartbeat peak. Furthermore, when selecting a heartbeat peak of one beat's worth of heartbeat data, if the respiratory waveform data chronologically associated with that one beat's worth of heartbeat data is positive, the heartbeat peak selection unit 14 selects the maximum value (indicated by a triangle) at the timing next to the minimum value (indicated by a square) of the heartbeat waveform data as the heartbeat peak. In this way, the heartbeat peak selection unit 14 selects a heartbeat peak of the heartbeat waveform data in accordance with a predetermined rule that defines a predetermined peak in the heartbeat waveform as the heartbeat peak based on the positive / negative (i.e., phase) of the respiratory waveform data. This rule is an example. The rule for selecting the heartbeat peak may be set as appropriate depending on, for example, the environment in which the heartbeat interval measuring system 1 is used and / or the user who uses the heartbeat interval measuring system 1.

[0022] In step S4, the heartbeat interval calculation unit 16 calculates the heartbeat interval from the selected heartbeat peak.

[0023] In step S5, if the measurement is to be continued, the process returns to step S1, and if the measurement is not to be continued, the process ends.

[0024] According to this method, the heartbeat peak selection unit 14 selects heartbeat peaks of the phonocardiogram data according to a predetermined rule that is determined based on the positive or negative sign of the respiratory waveform data, i.e., the phase of the respiratory waveform data. Such rules may be set by trial and error depending on the environment (including, for example, the intended use) in which the heartbeat interval measuring system 1 is used. In this way, the heartbeat peak selection unit 14 can more accurately select heartbeat peaks of the phonocardiogram waveform data by taking the respiratory state into consideration. This allows the heartbeat interval measuring device 10 to accurately measure heartbeat intervals.

[0025] (Selection of heart rate peaks using sample heart sound waveform data) FIG. 5 shows a process flow of a method for selecting the heartbeat peak of the heart sound waveform data using sample heart sound waveform data.

[0026] First, in step S11, the data acquiring unit 12 receives a sample sensor signal from the sensor 20.

[0027] Next, in step S12, the data acquiring unit 12 extracts cardiac waveform data and respiratory waveform data from the sample sensor signal based on the frequency band.

[0028] Next, in step S13, the heartbeat peak selection unit 14 records multiple types of sample heartbeat waveform data associated in time series with the respiratory waveform data. More specifically, the heartbeat peak selection unit 14 records multiple types of sample heartbeat waveform data associated in time series with characteristic respiratory states within one respiratory cycle. In this example, as shown in FIG. 2, the heartbeat peak selection unit 14 records sample heartbeat waveform data for six beats, designated "T1" to "T6," within one respiratory cycle. The heartbeat peak selection unit 14 may sample only one respiratory cycle and record sample heartbeat waveform data for multiple beats included therein, or may sample multiple respiratory cycles and record appropriate sample heartbeat waveform data from among them. The heartbeat peak selection unit 14 may also record sample heartbeat waveform data for fewer than six beats or more than six beats. Thus, in this example, multiple types of sample heartbeat waveform data are prepared from sample sensor signals prior to measurement. Alternatively, multiple types of standard sample cardiac sound waveform data that can be generally applied to any user may be prepared in advance.

[0029] Next, in step S14, the data acquisition unit 12 receives a sensor signal of the measurement target from the sensor 20.

[0030] Next, in step S15, the data acquiring unit 12 extracts cardiac waveform data and respiratory waveform data from the sensor signal of the measurement target based on the frequency band.

[0031] Next, in step S16, the heartbeat peak selection unit 14 selects corresponding sample heartbeat waveform data from multiple types of sample heartbeat waveform data based on the feature amount (slope or phase of the respiratory waveform) of the respiratory waveform data to be measured. Specifically, when selecting a heartbeat peak of one beat's worth of heartbeat waveform data to be measured, the heartbeat peak selection unit 14 calculates the feature amount of the respiratory waveform data associated in time series with that one beat's worth of heartbeat waveform data. The heartbeat peak selection unit 14 further selects sample heartbeat waveform data associated with sample respiratory waveform data having a feature amount closest to the calculated feature amount. Referring to the example of FIG. 2, if the slope of the respiratory waveform to be measured is positive and large, the heartbeat peak selection unit 14 selects sample heartbeat waveform data corresponding to "T2" having a feature amount closest to that feature amount.

[0032] Next, in step S17, the heartbeat peak selection unit 14 selects the peak of the correlation function between the selected sample heartbeat waveform data and the heartbeat waveform data of the measurement target as the heartbeat peak of the heartbeat waveform data of the measurement target.

[0033] In step S18, the heartbeat interval calculation unit 16 calculates the heartbeat interval from the selected heartbeat peak.

[0034] In step S19, if the measurement is to be continued, the process returns to step S14, and if the measurement is not to be continued, the process ends.

[0035] According to this method, the heartbeat peak selection unit 14 selects the peak of the correlation function between the sample heartbeat waveform data and the heartbeat waveform data of the measurement target as the heartbeat peak of the heartbeat waveform data of the measurement target. Because the sample heartbeat waveform data and the heartbeat waveform data of the measurement target were obtained when the breathing states were similar, the peak of the correlation function can more accurately reflect the heartbeat peak. In this way, the heartbeat peak selection unit 14 can more accurately select the heartbeat peak of the heartbeat waveform data by taking the breathing state into consideration. This allows the heartbeat interval measuring device 10 to accurately measure the heartbeat interval.

[0036] In the above example, the same multiple types of sample cardiac sound waveform data are used as long as measurement continues. Alternatively, if measurement continues, the heartbeat peak selection unit 14 may store the cardiac sound waveform data of the measurement target as sample cardiac sound waveform data when returning from step S19 to step S14. By storing sample cardiac sound waveform data, more detailed sample cardiac sound waveform data can be prepared, allowing for more accurate selection of the heartbeat peaks of the cardiac sound waveform data. Furthermore, if measurement continues, the heartbeat peak selection unit 14 may update the cardiac sound waveform data of the measurement target as sample cardiac sound waveform data when returning from step S19 to step S14. The update may be performed every breathing cycle. The update may also be performed every breathing cycle or periodically after multiple breathing cycles have elapsed. Updating the sample cardiac sound waveform data allows the latest sample cardiac sound waveform data to be used, making it possible to follow changes in the status of the user and the device, allowing for more accurate selection of the heartbeat peaks of the cardiac sound waveform data.

[0037] (Heart rate peak selection using a trained model) FIG. 6 shows an outline of the trained model used by the heartbeat peak selection unit 14 of the heartbeat interval measuring device 10. This trained model is a machine learning model that inputs feature quantities of respiratory waveform data and phonocardiogram waveform data and outputs the heartbeat peaks of the phonocardiogram waveform data. The trained model may be generated, for example, by machine learning a neural network having an input layer, an intermediate layer, and an output layer. The trained model may also be a machine learning model with multiple intermediate layers generated using a deep learning technique.

[0038] The trained model can be generated, for example, by applying a supervised learning technique to a neural network. In this example, the feature amount of the respiratory waveform data, which is one of the inputs of the training data, includes at least one of the slope and phase of the respiratory waveform for one beat. The acoustocardiogram waveform data, which is one of the inputs of the training data, includes acoustocardiogram waveform data for one beat. The heartbeat peak of the acoustocardiogram waveform data, which is the output of the training data, is set as a true value. The generation of the machine learning model may be executed by the heart rate interval measuring device 10 (see FIG. 1 ), or may be executed by a device separate from the heart rate interval measuring device 10. The trained model is stored in a memory unit of the heart rate interval measuring device 10.

[0039] Figure 7 shows the processing flow of a method for selecting the heartbeat peak of cardiac sound waveform data using a trained model.

[0040] First, in step S21, the data acquiring unit 12 receives a sensor signal of the measurement target from the sensor 20.

[0041] Next, in step S22, the data acquiring unit 12 extracts cardiac waveform data and respiratory waveform data from the sensor signal based on the frequency band.

[0042] Next, in step S23, the heartbeat peak selection unit 14 inputs the feature amounts of the respiratory waveform data and the phonocardiogram waveform data into the trained model, and selects the heartbeat peak of the phonocardiogram waveform data.

[0043] In step S24, the heartbeat interval calculation unit 16 calculates the heartbeat interval from the selected heartbeat peak.

[0044] In step S25, if the measurement is to be continued, the process returns to step S21, and if the measurement is not to be continued, the process ends.

[0045] According to this method, the heartbeat peak selection unit 14 selects heartbeat peaks from the phonocardiogram waveform data using a trained model. The trained model selects heartbeat peaks from the phonocardiogram waveform data by taking into account the feature quantities of the respiratory waveform data. In this way, the heartbeat peak selection unit 14 can more accurately select heartbeat peaks from the phonocardiogram waveform data by taking into account the respiratory state. This allows the heartbeat interval measuring device 10 to accurately measure heartbeat intervals.

[0046] In the above examples, respiratory waveform data is used as biometric data to measure heartbeat intervals. This is just an example, and other biometric data, such as data indicating the user's posture, or vibration data generated inside the body when the user speaks or chews a drink, can also be used.

[0047] The features of the technology disclosed in this specification are summarized below. Note that the technical elements described below are independent technical elements that exhibit technical utility either alone or in various combinations, and are not limited to the combinations described in the claims at the time of filing.

[0048] (Feature 1) A heartbeat interval measuring device comprising: a data acquiring unit configured to acquire heartbeat waveform data and biological data different from the heartbeat waveform data; a heartbeat peak selecting unit configured to select a heartbeat peak of the heartbeat waveform data based on a feature of the biological data; and a heartbeat interval calculating unit configured to calculate a heartbeat interval from the selected heartbeat peak.

[0049] (Feature 2) 2. The heart rate interval measuring device according to Feature 1, wherein the biological data is respiratory waveform data.

[0050] (Feature 3) The heartbeat interval measuring device according to Feature 2, wherein the data acquisition unit is configured to extract cardiac sound waveform data and respiratory waveform data from the sensor signal acquired from the same sensor based on the frequency band.

[0051] (Feature 4) 4. The heartbeat interval measuring device according to feature 2 or 3, wherein the feature of the respiratory waveform data is the slope or phase of the respiratory waveform.

[0052] (Feature 5) The heartbeat interval measuring device according to any one of features 1 to 4, wherein the heartbeat peak selecting unit is configured to select a heartbeat peak of the cardiac sound waveform data in accordance with a predetermined rule determined based on the feature amount of the biological data.

[0053] (Feature 6) The heartbeat peak selection unit of the heartbeat interval measuring device according to any one of Features 1 to 4 is configured to prepare multiple types of sample heartbeat waveform data that are associated with the biological data in a time series manner, select corresponding sample heartbeat waveform data from the multiple types of sample heartbeat waveform data based on features of the biological data when the heartbeat waveform data of the measurement target is measured, and select the peak of the correlation function between the selected sample heartbeat waveform data and the heartbeat waveform data of the measurement target as the heartbeat peak of the heartbeat waveform data of the measurement target.

[0054] (Feature 7) 7. The heartbeat interval measuring device according to claim 6, wherein the heartbeat peak selecting unit is further configured to store and / or update the heartbeat waveform data of the measurement target as sample heartbeat waveform data.

[0055] (Feature 8) The heartbeat peak selection unit of the heartbeat interval measuring device according to any one of features 1 to 4 is configured to input the biological data and acoustic cardiac waveform data of the measurement target into a trained model trained using teacher data that inputs the biological data and acoustic cardiac waveform data and outputs the heartbeat peak of the acoustic cardiac waveform data, and select the heartbeat peak of the acoustic cardiac waveform data.

[0056] (Feature 9) 2. The heart rate interval measuring device according to Feature 1, wherein the biological data is the user's posture.

[0057] (Feature 10) A computer program for a heartbeat interval measuring device, the computer program causing the heartbeat interval measuring device to function as the following units: a data acquiring unit configured to acquire heartbeat waveform data and biological data different from the heartbeat waveform data; a heartbeat peak selecting unit configured to select a heartbeat peak of the heartbeat waveform data based on a feature amount of the biological data; and a heartbeat interval calculating unit configured to calculate a heartbeat interval from the selected heartbeat peak.

[0058] (Feature 11) A method for generating a learning model, comprising: acquiring multiple pieces of training data including biometric data, acoustocardiogram waveform data, and heartbeat peaks; inputting the biometric data and acoustocardiogram waveform data; and generating a learning model that outputs the heartbeat peaks of the acoustocardiogram waveform data.

[0059] Although the embodiments have been described in detail above, these are merely examples and do not limit the scope of the claims. The technology described in the claims includes various modifications and variations of the specific examples exemplified above. The technical elements described in this specification or drawings exhibit technical utility alone or in various combinations, and are not limited to the combinations described in the claims at the time of filing. Furthermore, the technology exemplified in this specification or drawings simultaneously achieves multiple objectives, and achieving one of these objectives itself has technical utility. [Explanation of symbols]

[0060] 1: Heartbeat interval measuring system, 10: Heartbeat interval measuring device, 12: Data acquisition unit, 14: Heartbeat peak selection unit, 16: Heartbeat interval calculation unit, 20: Sensor

Claims

1. A heartbeat interval measuring device (10), a data acquisition unit (12) configured to acquire cardiac waveform data and biological data different from the cardiac waveform data; a heartbeat peak selection unit (14) configured to select a heartbeat peak of the phonocardiogram waveform data based on the feature amount of the biological data; a heartbeat interval calculation unit (16) configured to calculate a heartbeat interval from the selected heartbeat peak, the biological data is respiratory waveform data, A heartbeat interval measuring device, wherein the feature of the respiratory waveform data is the slope or phase of the respiratory waveform.

2. The data acquisition unit The heartbeat interval measuring device according to claim 1 , configured to extract the heart sound waveform data and the respiratory waveform data from a sensor signal acquired from the same sensor based on a frequency band.

3. The heart rate peak selection unit 3. The heartbeat interval measuring device according to claim 1, wherein the heartbeat peak of the phonocardiogram waveform data is selected in accordance with a predetermined rule determined based on a feature amount of the biological data.

4. The heart rate peak selection unit preparing a plurality of types of sample cardiac waveform data corresponding to the biological data in a time series manner; selecting corresponding sample phonocardiogram waveform data from the plurality of types of sample phonocardiogram waveform data based on the feature amount of the biological data when the phonocardiogram waveform data of the measurement subject is measured; 3. The heartbeat interval measuring device according to claim 1, wherein the heartbeat interval measuring device is configured to select a peak of a correlation function between the selected sample heartbeat waveform data and the heartbeat waveform data of the object to be measured as the heartbeat peak of the heartbeat waveform data of the object to be measured.

5. The heart rate peak selection unit further comprises: The heartbeat interval measuring device according to claim 4 , configured to store and / or update the heartbeat waveform data of the measurement target as the sample heartbeat waveform data.

6. The heart rate peak selection unit 3. The heartbeat interval measuring device according to claim 1, wherein the device is configured to input the biological data and the phonocardiogram waveform data of a measurement target to a trained model that has been trained using teacher data that receives the biological data and the phonocardiogram waveform data as input and outputs the heartbeat peak of the phonocardiogram waveform data, and select the heartbeat peak of the phonocardiogram waveform data.

7. A computer program for a heartbeat interval measuring device (10), said heartbeat interval measuring device being configured to include the following parts: a data acquisition unit (12) configured to acquire cardiac waveform data and biological data different from the cardiac waveform data; a heartbeat peak selection unit (14) configured to select a heartbeat peak of the phonocardiogram waveform data based on the feature amount of the biological data; a heartbeat interval calculation unit (16) configured to calculate a heartbeat interval from the selected heartbeat peak, the biological data is respiratory waveform data, A computer program, wherein the feature of the respiratory waveform data is a slope or phase of the respiratory waveform.

8. The heart rate peak selection unit:

8. The computer program according to claim 7, wherein the computer program is configured to input the biological data and the phonocardiogram waveform data of a measurement target to a trained model trained using teacher data that receives the biological data and the phonocardiogram waveform data as input and outputs the heartbeat peak of the phonocardiogram waveform data, and to select the heartbeat peak of the phonocardiogram waveform data.

Images