A heart rate determination method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application provide a heart rate determination method and device, electronic equipment and storage medium. The method comprises: obtaining a heartbeat signal corresponding to a heart impact signal of a target to be measured; processing the heartbeat signal to obtain a heartbeat difference signal corresponding to the heartbeat signal and a target probability density curve; determining a plurality of consecutive target heartbeats in the heartbeat signal based on the heartbeat difference signal, the similarity between any two target heartbeats in the plurality of target heartbeats being greater than a preset similarity threshold; determining a plurality of predicted heart rates according to the target probability density curve, the plurality of target heartbeats and the sampling rate of the heart impact signal; and determining a target heart rate of the target to be measured based on the plurality of predicted heart rates. Based on the method, errors in heart rate calculation caused by interference signals in the heart impact signal can be avoided, and the accuracy of heart rate determination is improved.

Description

Technical Field

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

[0002] The cardiac signal is a physiological signal that reflects mechanical activities such as the heart, breathing, and body movement. The cardiac signal generally includes multiple signals such as breathing signals, heartbeat signals, body movement signals, and high-frequency interference generated by electronic devices. Therefore, it is relatively difficult to determine the heart rate based on the cardiac signal.

[0003] Currently, the heart rate is typically calculated by extracting the heartbeat signal from the heartbeat signal, filtering it, and performing envelope extraction. Alternatively, a prefabricated template is used to match the heartbeat signal within the heartbeat signal, determining the heartbeat location before calculating the heart rate. However, envelope extraction followed by a wave search cannot accurately determine the heartbeat's location, resulting in a certain error between the calculated heart rate and the true heart rate. Furthermore, the prefabricated template matching method requires manual pre-collection of the heartbeat template, as different sleeping and sitting positions, as well as sensor placement, can affect the heartbeat template, significantly limiting its practical application. Summary of the Invention

[0004] Various aspects of the present application provide a heart rate determination method, device, electronic device, and storage medium to accurately determine the true heart rate.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a heart rate, the method comprising:

[0006] Acquire a heartbeat signal corresponding to the heartbeat signal of the target to be measured;

[0007] Processing the heartbeat signal to obtain a heartbeat difference signal and a target probability density curve corresponding to the heartbeat signal;

[0008] Based on the heartbeat differential signal, determining a plurality of consecutive target heartbeats in the heartbeat signal, wherein a similarity between any two target heartbeats in the plurality of target heartbeats is greater than a preset similarity threshold;

[0009] Determining a plurality of predicted heart rates according to the target probability density curve, the plurality of target heartbeats, and a sampling rate of the ballistocardi signal;

[0010] Based on the multiple predicted heart rates, a target heart rate of the target is determined.

[0011] Further optionally, determining a plurality of predicted heart rates according to the target probability density curve, the plurality of target heartbeats, and the sampling rate of the ballistocardi signal includes:

[0012] Determining a first heartbeat interval corresponding to the heartbeat signal according to the target probability density curve;

[0013] A first predicted heart rate of the target to be measured is determined based on the first heartbeat interval and the sampling rate of the heartbeat signal.

[0014] Further optionally, determining a plurality of predicted heart rates according to the target probability density curve, the plurality of target heartbeats, and the sampling rate of the ballistocardi signal includes:

[0015] Determining a second heartbeat interval and a heartbeat template corresponding to the heartbeat signal according to the multiple target heartbeats;

[0016] Determining a third heartbeat interval corresponding to the heartbeat signal based on the heartbeat template;

[0017] Based on the second heartbeat interval, the third heartbeat interval and the sampling rate of the cardiac impulse signal, a second predicted heart rate and a third predicted heart rate of the target to be measured are determined respectively.

[0018] Further optionally, determining the target heart rate of the target to be measured based on the multiple predicted heart rates includes:

[0019] The target heart rate is determined based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate.

[0020] Further optionally, processing the heartbeat signal to obtain a target probability density curve corresponding to the heartbeat signal includes:

[0021] Processing the heartbeat signal based on a first preset algorithm to obtain at least one initial probability density curve corresponding to the heartbeat signal;

[0022] The target probability density curve is determined based on the at least one initial probability density curve.

[0023] Further optionally, the first preset algorithm includes at least one of the following: autocorrelation method, average amplitude difference function method, maximum peak method, minimum peak method.

[0024] Further optionally, determining a plurality of consecutive target heartbeats in the heartbeat signal based on the heartbeat differential signal includes:

[0025] Based on the heartbeat differential signal, determining a plurality of suspected heartbeats that meet a preset screening condition in the heartbeat signal;

[0026] Determining the similarity between any two suspected heartbeats among the multiple suspected heartbeats based on a second preset algorithm;

[0027] The continuous multiple suspected heartbeats with the similarity greater than the preset similarity threshold are determined as the target heartbeats.

[0028] In a second aspect, the embodiments of the present application provide a heart rate determination apparatus, which comprises:

[0029] The acquisition module is configured to acquire a heartbeat signal corresponding to a heart impact signal of a target to be measured, and process the heartbeat signal to acquire a heartbeat difference signal corresponding to the heartbeat signal and a target probability density curve.

[0030] The determination module is configured to determine, based on the heartbeat difference signal, a plurality of target heartbeats in the heartbeat signal, any two target heartbeats in the plurality of target heartbeats having a similarity greater than a preset similarity threshold; determine a plurality of predicted heart rates based on the target probability density curve, the plurality of target heartbeats, and a sampling rate of the heart impact signal; and determine a target heart rate of the target to be measured based on the plurality of predicted heart rates.

[0031] In a third aspect, the embodiments of the present application provide an electronic device, which comprises a memory, a processor, and a communication interface; wherein the memory stores executable codes, and when the executable codes are executed by the processor, the processor executes the heart rate determination method according to the first aspect.

[0032] In a fourth aspect, the embodiments of the present application provide a non-transitory machine readable storage medium, which stores executable codes, and when the executable codes are executed by a processor of an electronic device, the processor executes the heart rate determination method according to the first aspect.

[0033] The embodiments of the present application provide a heart rate determination method, based on which the real heart rate of a target to be measured can be accurately calculated. In actual application, first, a heartbeat signal corresponding to a heart impact signal of a target to be measured is acquired, and then the heartbeat signal is processed to acquire a heartbeat difference signal corresponding to the heartbeat signal and a target probability density curve; based on the heartbeat difference signal, a plurality of target heartbeats which are continuous and have a similarity greater than a preset similarity threshold can be determined. In this way, a plurality of predicted heart rates can be determined based on the target probability density curve, the plurality of target heartbeats, and a sampling rate of the heart impact signal, and finally a target heart rate of the target to be measured can be determined based on the plurality of predicted heart rates.

[0034] In the solution provided in the embodiments of the present application, a heartbeat differential signal and a target probability density curve are determined based on a heartbeat signal obtained from a ballistocardiogram signal, multiple target heartbeats are then determined based on the heartbeat differential signal, and finally a target heart rate is determined based on preset heart rates calculated based on the multiple target heartbeats and the target probability density curve. By first determining a predicted heart rate in a variety of ways and then determining a target heart rate based on the predicted heart rate, errors in heart rate calculation caused by interference signals in the ballistocardiogram signal can be avoided, thereby improving the accuracy of heart rate determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0036] Figure 1 A flowchart of a heart rate determination method provided by an exemplary embodiment of the present application;

[0037] Figure 2 A flowchart of a heart rate determination method provided by an exemplary embodiment of the present application;

[0038] Figure 3 A schematic structural diagram of a heart rate determination device provided by an exemplary embodiment of the present application;

[0039] Figure 4 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present application;

[0040] Figure 5 A schematic structural diagram of another electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0042] Heart rate is a professional term used to describe the cardiac cycle, referring to the number of times the heart beats per minute. Currently, heart rate plays a vital role in detecting human health. When obtaining heart rate, due to the presence of multiple interference signals in the cardiac signal and the different detection postures of the target to be measured, errors may occur in the calculation of the heart rate. To this end, embodiments of the present application provide a heart rate determination method, device, server, and storage medium. In embodiments of the present application, a heartbeat signal corresponding to the cardiac signal of the target to be measured is obtained; the heartbeat signal is processed to obtain a heartbeat difference signal and a target probability density curve corresponding to the heartbeat signal; based on the heartbeat difference signal, multiple consecutive target heartbeats are determined in the heartbeat signal, and the similarity between any two target heartbeats in the multiple target heartbeats is greater than a preset similarity threshold; multiple predicted heart rates are determined based on the target probability density curve, the multiple target heartbeats, and the sampling rate of the cardiac signal; and based on the multiple predicted heart rates, the target heart rate of the target to be measured is determined. By first determining the predicted heart rate in a variety of ways and then determining the target heart rate based on the predicted heart rate, errors in heart rate calculation caused by interference signals in the heartbeat signal can be avoided, thereby improving the accuracy of heart rate determination.

[0043] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0044] Figure 1 This is a flow chart of a heart rate determination method provided by an exemplary embodiment of the present application. Figure 1 , the method specifically comprises the following steps:

[0045] 101. Acquire a heartbeat signal corresponding to a heartbeat signal of a target to be measured.

[0046] 102. Process the heartbeat signal to obtain a heartbeat difference signal and a target probability density curve corresponding to the heartbeat signal.

[0047] 103. Based on the heartbeat differential signal, determine a plurality of consecutive target heartbeats in the heartbeat signal, wherein a similarity between any two target heartbeats in the plurality of target heartbeats is greater than a preset similarity threshold.

[0048] 104. Determine multiple predicted heart rates based on the target probability density curve, the multiple target heartbeats, and the sampling rate of the heartbeat signal.

[0049] 105. Determine a target heart rate of the target based on the multiple predicted heart rates.

[0050] The heart rate determination method provided in this application can be applied to application scenarios where heart rate calculation and determination are required. Before determining the heart rate of a target, it is necessary to first obtain a ballistic cardiac signal of the target. In this embodiment, the ballistic cardiac signal of the target can be collected by a signal acquisition unit to obtain an original ballistic cardiac signal data sequence of the target.

[0051] In practical applications, the signal acquisition unit may include a signal sensor. Specifically, it may collect a cardiac shock analog signal from the target to be measured through a piezoelectric ceramic sensor, a piezoelectric film sensor, an optical fiber sensor or a radar sensor, and then convert the cardiac shock analog signal into a digital signal (i.e., a cardiac shock signal) through analog-to-digital conversion.

[0052] After obtaining the cardiac signal of the target to be measured, it cannot be directly used to determine the heart rate because the cardiac signal contains multiple signals such as breathing signal, heartbeat signal, body movement signal, high-frequency interference generated by electronic equipment, etc. Therefore, it is necessary to obtain the heartbeat signal from the cardiac signal.

[0053] In practical applications, the ballistocardi signal can be filtered to reduce interference from high-frequency signals generated by breathing, body movement, and electronic devices, thereby extracting the heartbeat signal. In this embodiment, the ballistocardi signal can be processed using methods such as wavelet transform (WT) and finite impulse response to obtain the heartbeat signal from the ballistocardi signal.

[0054] By processing the heartbeat signal, a heartbeat difference signal and a target probability density curve corresponding to the heartbeat signal can be obtained.

[0055] In an optional embodiment, a heartbeat signal segment of a preset duration can be cached as an analysis window, and a heartbeat differential signal and a target probability density curve can be determined based on the heartbeat signal within the analysis window. Specifically, the validity of the analysis window can be determined by using the windowed information entropy, the windowed standard deviation, and the signal saturation ratio. The heartbeat differential signal and the target probability density curve are then determined based on the valid analysis window to eliminate interference signals caused by factors such as the target's body movement.

[0056] In practical applications, when obtaining a target probability density curve corresponding to a heartbeat signal, the heartbeat signal can be processed based on a first preset algorithm to obtain at least one initial probability density curve corresponding to the heartbeat signal. Then, based on the at least one initial probability density curve, the target probability density curve can be determined. In this embodiment, the first preset algorithm can include at least one of the following: an autocorrelation method, an average amplitude difference function method, a maximum peak method, and a minimum peak method.

[0057] In an optional embodiment, the heartbeat signal can be processed separately using the autocorrelation method, the average amplitude difference function method, the maximum peak method, and the minimum peak method to obtain four probability density curves corresponding to the above four algorithms. Then, the above four probability density curves are normalized and combined into the final target rate density curve. In this embodiment, the autocorrelation method, the average amplitude difference function method, the maximum peak method, and the minimum peak method are used to jointly generate the target rate density curve, thereby improving the accuracy of the target rate density curve.

[0058] After obtaining the target probability density curve, the first heartbeat interval corresponding to the heartbeat signal can be determined according to the target probability density curve, and then the first predicted heart rate of the target to be measured can be determined based on the first heartbeat interval and the sampling rate of the heartbeat signal.

[0059] In practical applications, the possible heart rate position can be determined based on the target probability density curve and the maximum position of the curve is analyzed. The first heartbeat interval is determined by the short-time average amplitude difference function (AMDF). Then, based on the first heartbeat interval and the sampling rate of the heartbeat signal, the first predicted heart rate of the target to be measured is determined. It should be noted that the first predicted heart rate calculated in this embodiment can be one or more. The first predicted heart rate can be calculated based on the following formula (1):

[0060] (1)

[0061] in, represents the first predicted heart rate, t represents the sampling rate, and i represents the first heartbeat interval.

[0062] In practical applications, when determining the heartbeat differential signal corresponding to the heartbeat signal, the heartbeat differential signal can be obtained by performing differential calculation on the heartbeat signal. In this embodiment, the differential range of the heartbeat signal differential calculation can be within 0.1 seconds.

[0063] After obtaining the heartbeat differential signal, multiple suspected heartbeats that meet the preset screening conditions can be determined in the heartbeat signal based on the heartbeat differential signal. Then, the similarity between any two suspected heartbeats among the multiple suspected heartbeats can be determined based on the second preset algorithm. Finally, multiple consecutive suspected heartbeats with similarities greater than the preset similarity threshold are determined as target heartbeats.

[0064] In actual application, positions of all suspected heartbeats can be determined according to the shape of the heartbeat difference signal, and then positions of suspected heartbeats that do not meet the requirements can be excluded based on height, width, shape and other factors, and finally positions of suspected heartbeats that are not excluded are determined as final positions of suspected heartbeats. Further, positions of suspected heartbeats in the heartbeat signal can be determined based on positions of suspected heartbeats in the heartbeat difference signal, and suspected heartbeats in the heartbeat signal are determined as suspected heartbeats. In this embodiment, the difference signal is analyzed first, and then the heartbeat signal is traced back, which avoids the interference on the calculation of heart rate caused by the incomplete filtering of low-frequency signals.

[0065] In determining target heartbeats, the determined suspected heartbeats can be processed first to determine a preset number of target heartbeats meeting a preset condition, and then the second heartbeat interval and the heartbeat template corresponding to the heartbeat signal are determined based on the preset number of target heartbeats.

[0066] In actual application, the preset condition can include that the cosine similarity between suspected heartbeats reaches a preset similarity threshold. Specifically, the cosine similarity between each suspected heartbeat and other suspected heartbeats can be calculated respectively, and then the suspected heartbeats with three consecutive similarities reaching the preset similarity threshold and with uniform intervals are used as available target heartbeats.

[0067] After the available target heartbeats are determined, the second heartbeat interval can be determined based on the cosine similarity gap between the target heartbeats, and then the second predicted heart rate of the target to be measured is determined based on the second heartbeat interval and the sampling rate of the heartbeat signal. It should be noted that the second predicted heart rate calculated in this embodiment can be one or multiple. In this embodiment, the calculation method of the second predicted heart rate is the same as that of the first predicted heart rate, which will not be described herein.

[0068] Correspondingly, the heartbeat template corresponding to the heartbeat signal can be determined according to multiple target heartbeats. Specifically, the heartbeat template can be determined according to the available target heartbeats in the multiple target heartbeats.

[0069] In an optional embodiment, the heartbeat template can include a heartbeat peak value template and a heartbeat valley value template. In actual application, the heartbeat peak value template and the heartbeat valley value template can be generated respectively according to the three consecutive available target heartbeats.

[0070] In actual applications, after determining the above-mentioned heartbeat peak template and the above-mentioned heartbeat valley template, the heartbeat peak template matching can be performed from the center of the analysis window to the left and right respectively, and the valley template matching can be performed to the left and right respectively based on the above-mentioned two templates. In this embodiment, template matching can be performed by combining cosine similarity and Chebyshev similarity. Furthermore, based on template matching, after obtaining two heartbeats, the heartbeat peak template and the heartbeat valley template can be refreshed based on the two obtained heartbeats, and the positions of all suspected heartbeats can be searched and confirmed for a second time between the two heartbeats to prevent missing heartbeats in the above-mentioned two heartbeats, thereby ensuring that the two obtained heartbeats are the smallest heartbeat intervals passed through the center of the analysis window, thereby improving the accuracy of heart rate calculation. In this embodiment, the heartbeat peak template and the heartbeat valley template are used simultaneously for template matching, thereby improving the accuracy of heart rate calculation.

[0071] Based on the above-mentioned template matching method, a third heartbeat interval corresponding to the above-mentioned heartbeat signal can be determined, and then a third predicted heart rate of the target to be measured is determined based on the third heartbeat interval and the sampling rate of the heartbeat signal. It should be noted that the third predicted heart rate calculated in this embodiment can be one or more. In this embodiment, the calculation method of the third predicted heart rate is the same as the calculation method of the first predicted heart rate, and this application will not repeat them here.

[0072] Finally, the target heart rate of the target to be measured can be determined based on multiple predicted heart rates obtained based on the target probability density curve, multiple target heartbeats, and the sampling rate of the cardiac shock signal. In practical applications, the target heart rate can be determined based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate. In this embodiment, three methods, namely the heart mirror algorithm, the probability density function method, and the automatic template matching method, are adopted, and multiple estimated heart rates are obtained by simultaneous analysis from both sides of the peak and trough, and a comprehensive decision is made to obtain a more accurate target heart rate.

[0073] In this embodiment, a target heart rate can be calculated by making a decision based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate. Specifically, a decision tree or other method can be used to make a decision based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate. It should be noted that the decision method for making a decision based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate is not limited in this application.

[0074] In an optional embodiment, heart rate variability is obtained by recording the interval between two consecutive heartbeats, wherein the two consecutive heartbeats are determined by their positions in the analysis window.

[0075] For ease of understanding, the following solution Figure 2 The heart rate determination method provided in the embodiment of the present application is described in detail.

[0076] like Figure 2 As shown, the heart rate determination method provided in the embodiment of the present application includes the following steps.

[0077] S201, obtaining a simulated cardiac ballistometry signal of a target to be measured.

[0078] In this embodiment, the ballistocardial simulation signal can be collected from the target to be measured by using a piezoelectric ceramic sensor, a piezoelectric film sensor, an optical fiber sensor, a radar sensor, and the like.

[0079] S202: Convert the cardiac shock analog signal into a cardiac shock signal by analog-to-digital conversion.

[0080] S203: Acquire the heartbeat signal from the heartbeat signal by filtering.

[0081] In this embodiment, the filtering method is wavelet transform, finite impulse response filtering or infinite impulse response filtering.

[0082] S204: Cache 5 seconds of heartbeat signals as an analysis window, and determine whether the analysis window is valid.

[0083] In this embodiment, whether the analysis window is valid is determined by using the windowed information entropy, the windowed standard deviation, and the signal saturation ratio.

[0084] If the analysis window is valid, the subsequent steps are executed. If the analysis window is invalid, another 5-second heartbeat signal is cached again as the analysis window.

[0085] S205: Obtain a target probability density curve corresponding to the heartbeat signal.

[0086] In this embodiment, the heartbeat signal is processed respectively by the autocorrelation method, the average amplitude difference function method, the maximum peak method and the minimum peak method to obtain four probability density curves corresponding to the above four algorithms one by one, and the above four probability density curves are normalized and synthesized into a target rate density curve.

[0087] S206: Determine a first heart rate interval according to the target rate density curve.

[0088] In this embodiment, the first heartbeat interval is determined by a short-time average amplitude difference function.

[0089] S207: Calculate a first predicted heart rate according to the first heartbeat interval and the sampling rate of the ballistocardi signal.

[0090] S208: Perform differential calculation on the heartbeat signal to obtain a heartbeat differential signal.

[0091] In this embodiment, the difference range of performing the difference calculation on the heartbeat signal may be within 0.1 second.

[0092] S209: Determine the suspected heartbeat position in the heartbeat signal based on the suspected heartbeat position in the heartbeat difference signal.

[0093] S210: Eliminate the suspected heartbeat positions that do not meet the requirements, and determine the suspected heartbeat positions that are not eliminated as the final suspected heartbeat positions.

[0094] In this embodiment, suspected heartbeat positions that do not meet the requirements can be excluded based on factors such as height, width, and shape.

[0095] S211, determining the similarity between two suspected heartbeats.

[0096] In this embodiment, the cosine similarity between each suspected heartbeat and other suspected heartbeats is calculated respectively.

[0097] S212: Determine three consecutive suspected heartbeats whose similarities reach a preset similarity threshold and whose intervals are relatively even as target heartbeats.

[0098] In this embodiment, the number of target heartbeats is three.

[0099] S213: Determine a second heartbeat interval based on the target heartbeat.

[0100] S214: Calculate a second predicted heart rate according to the second heartbeat interval and the sampling rate of the ballistocardi signal.

[0101] S215: Determine a heartbeat peak template and a heartbeat valley template based on the target heartbeat.

[0102] S216 , performing template matching on the heartbeat signal according to the heartbeat peak template and the heartbeat valley template to obtain a third heartbeat interval.

[0103] In this embodiment, template matching is performed by combining cosine similarity and Chebyshev similarity. After obtaining two heartbeats, the heartbeat peak template and the heartbeat valley template can be refreshed based on the two obtained heartbeats, and the positions of all suspected heartbeats between the two heartbeats are searched and confirmed again to finally obtain the third heartbeat interval.

[0104] S217: Calculate a third predicted heart rate according to the third heartbeat interval and the sampling rate of the ballistocardi signal.

[0105] S218 , obtaining a target heart rate through the first heartbeat interval, the second heartbeat interval, the third heartbeat interval, and the sampling rate of the heartbeat signal.

[0106] It should be noted that the execution entity of each step of the method provided in the above embodiment can be the same server, or the method can be executed by different servers. For example, the execution entity of steps 101 to 103 can be server A; for another example, the execution entity of steps 101 and 102 can be server A, and the execution entity of step 103 can be server B; and so on.

[0107] In addition, some of the processes described in the above embodiments and the accompanying drawings include multiple operations that appear in a specific order, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0108] The heart rate determination device of one or more embodiments of the present application will be described in detail below. Those skilled in the art will appreciate that these devices can be constructed using commercially available hardware components and configured through the steps taught in this solution.

[0109] Figure 3 A schematic diagram of a heart rate determination device provided by an exemplary embodiment of the present application is shown in FIG. Figure 3 As shown, the device includes: an acquisition module 301 and a determination module 302.

[0110] An acquisition module 301 is used to acquire a heartbeat signal corresponding to the cardiac impact signal of a target to be measured; and to process the heartbeat signal to acquire a heartbeat differential signal and a target probability density curve corresponding to the heartbeat signal; a determination module 302 is used to determine a plurality of consecutive target heartbeats in the heartbeat signal based on the heartbeat differential signal, wherein the similarity between any two target heartbeats among the plurality of target heartbeats is greater than a preset similarity threshold; to determine a plurality of predicted heart rates according to the target probability density curve, the plurality of target heartbeats and the sampling rate of the cardiac impact signal; and to determine the target heart rate of the target to be measured based on the plurality of predicted heart rates.

[0111] Optionally, the determination module 302 is specifically configured to determine a first heartbeat interval corresponding to the heartbeat signal according to the target probability density curve; and determine a first predicted heart rate of the target to be measured based on the first heartbeat interval and the sampling rate of the cardiac shock signal.

[0112] Optionally, the determination module 302 is specifically used to determine the second heartbeat interval and heartbeat template corresponding to the heartbeat signal based on the multiple target heartbeats; determine the third heartbeat interval corresponding to the heartbeat signal based on the heartbeat template; and determine the second predicted heart rate and third predicted heart rate of the target to be measured based on the second heartbeat interval, the third heartbeat interval and the sampling rate of the cardiac impact signal.

[0113] Optionally, the determination module 302 is specifically configured to determine the target heart rate according to the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate.

[0114] Optionally, the acquisition module 301 is specifically configured to process the heartbeat signal based on a first preset algorithm to obtain at least one initial probability density curve corresponding to the heartbeat signal; and determine the target probability density curve based on the at least one initial probability density curve.

[0115] Optionally, the first preset algorithm includes at least one of the following: autocorrelation method, average amplitude difference function method, maximum peak method, minimum peak method.

[0116] Optionally, the determination module 302 is specifically used to determine multiple suspected heartbeats that meet preset screening conditions in the heartbeat signal based on the heartbeat differential signal; determine the similarity of any two suspected heartbeats among the multiple suspected heartbeats based on a second preset algorithm; and determine multiple consecutive suspected heartbeats whose similarities are greater than the preset similarity threshold as the target heartbeat.

[0117] In one possible design, the above Figure 3 The structure of the heart rate determination device shown can be realized as an electronic device. Figure 4 As shown, the electronic device may include: a processor 41, a memory 42, and a communication interface 43. The memory 42 stores executable code, which, when executed by the processor 41, enables the processor 41 to at least implement the heart rate determination device provided in the aforementioned embodiment.

[0118] In addition, an embodiment of the present application provides a non-temporary machine-readable storage medium, on which executable code is stored. When the executable code is executed by a processor of an electronic device, the processor can at least implement the heart rate determination method provided in the aforementioned embodiment.

[0119] The device embodiments described above are merely illustrative, wherein the network elements described as separate components may or may not be physically separate. Some or all of these modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art can understand and implement these embodiments without inventive effort.

[0120] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding the necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a computer product. This application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] Figure 5 This is a schematic diagram of another electronic device provided by an exemplary embodiment of the present application. Figure 5 As shown, the electronic device includes: an electronic device body 50 , and a memory 51 and a processor 52 are provided on the server body 50 .

[0122] The memory 51 is primarily used to store computer programs that can be executed by the processor 52, causing the processor 52 to control the electronic device to perform corresponding tasks. In addition to storing computer programs, the memory 51 can also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, map data of the environment / scene in which the electronic device is located, operating modes, operating parameters, and the like.

[0123] The memory 51 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0124] In the embodiment of the present application, the implementation form of the processor 52 is not limited, for example, it can be but not limited to a CPU, GPU or MCU. The processor 52 can be regarded as a control system of the electronic device, which can be used to execute the computer program stored in the memory 51 to control the electronic device to implement corresponding functions and complete corresponding actions or tasks. It is worth noting that depending on the implementation form of the electronic device and the scene in which it is located, the functions to be implemented, the actions or tasks to be completed will be different; accordingly, the computer programs stored in the memory 51 will also be different, and the processor 52 executing different computer programs can control the electronic device to implement different functions and complete different actions or tasks.

[0125] The processor 52 is coupled to the memory 51 and is used to execute the computer program in the memory 51 to: obtain a heartbeat signal corresponding to the cardiac impact signal of the target to be measured; process the heartbeat signal to obtain a heartbeat difference signal and a target probability density curve corresponding to the heartbeat signal; based on the heartbeat difference signal, determine multiple consecutive target heartbeats in the heartbeat signal, and the similarity between any two target heartbeats in the multiple target heartbeats is greater than a preset similarity threshold; determine multiple predicted heart rates according to the target probability density curve, the multiple target heartbeats and the sampling rate of the cardiac impact signal; and determine the target heart rate of the target to be measured based on the multiple predicted heart rates.

[0126] Further optionally, the processor 52 determines multiple predicted heart rates based on the target probability density curve, multiple target heartbeats, and the sampling rate of the heartbeat signal, specifically for:

[0127] According to the target probability density curve, a first heartbeat interval corresponding to the heartbeat signal is determined; based on the first heartbeat interval and the sampling rate of the heartbeat signal, a first predicted heart rate of the target to be measured is determined.

[0128] Further optionally, the processor 52 determines multiple predicted heart rates based on the target probability density curve, multiple target heartbeats, and the sampling rate of the heartbeat signal, specifically for:

[0129] Based on multiple target heartbeats, the second heartbeat interval and heartbeat template corresponding to the heartbeat signal are determined; based on the heartbeat template, the third heartbeat interval corresponding to the heartbeat signal is determined; based on the second heartbeat interval, the third heartbeat interval and the sampling rate of the cardiac impact signal, the second predicted heart rate and the third predicted heart rate of the target to be measured are determined respectively.

[0130] Further optionally, the processor 52 determines the target heart rate of the target to be measured based on the multiple predicted heart rates, specifically for:

[0131] A target heart rate is determined based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate.

[0132] Further optionally, the processor 52 processes the heartbeat signal to obtain a target probability density curve corresponding to the heartbeat signal, specifically for:

[0133] The heartbeat signal is processed based on a first preset algorithm to obtain at least one initial probability density curve corresponding to the heartbeat signal; and a target probability density curve is determined based on the at least one initial probability density curve.

[0134] Further optionally, the first preset algorithm includes at least one of the following: autocorrelation method, average amplitude difference function method, maximum peak method, minimum peak method.

[0135] Further optionally, the processor 52 determines a plurality of consecutive target heartbeats in the heartbeat signal based on the heartbeat differential signal, specifically for:

[0136] Based on the heartbeat differential signal, multiple suspected heartbeats that meet the preset screening conditions are determined in the heartbeat signal; based on the second preset algorithm, the similarity between any two suspected heartbeats among the multiple suspected heartbeats is determined; and multiple consecutive suspected heartbeats whose similarities are greater than the preset similarity threshold are determined as target heartbeats.

[0137] In some optional embodiments, the server may further include some basic components, such as a communication component 55, a power supply component 56, etc. In this embodiment, these components are merely illustrative and do not imply that the electronic device only includes these components. To meet different application requirements, the server may further include other components, depending on the product form of the electronic device.

[0138] The communication component is configured to facilitate wired or wireless communication between the device containing the communication component and other devices. The device containing the communication component can access a wireless network based on a communication standard, such as Wi-Fi, 2G, 3G, 4G, 5G, or a combination thereof. In an exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component may also include a near-field communication (NFC) module, radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, etc.

[0139] The power supply assembly provides power to various components of the device in which the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply assembly is located.

[0140] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement the steps in the above method embodiment that can be performed by the mobile device.

[0141] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining heart rate, characterized in that: The method comprises: Acquire a heartbeat signal corresponding to the heartbeat signal of the target to be measured; Processing the heartbeat signal to obtain a heartbeat difference signal and a target probability density curve corresponding to the heartbeat signal; Based on the heartbeat differential signal, determining a plurality of consecutive target heartbeats in the heartbeat signal, wherein a similarity between any two target heartbeats in the plurality of target heartbeats is greater than a preset similarity threshold; Determining a first heartbeat interval corresponding to the heartbeat signal according to the target probability density curve using a short-time average amplitude difference function; Determine, according to the multiple target heartbeats, a second heartbeat interval, a heartbeat peak template, and a heartbeat valley template corresponding to the heartbeat signal; Performing template matching on the heartbeat signal according to the heartbeat peak template and the heartbeat valley template to obtain two heartbeats; Refreshing the heartbeat peak template and the heartbeat valley template based on the two heartbeats, and performing a secondary search and confirmation on the positions of all suspected heartbeats between the two heartbeats, and if the two heartbeats do not contain any missed heartbeats, determining a third heartbeat interval based on the two heartbeats; determining a plurality of predicted heart rates according to the first heartbeat interval, the second heartbeat interval, the third heartbeat interval, and a sampling rate of the heartbeat signal; Based on the multiple predicted heart rates, a target heart rate of the target is determined.

2. The method according to claim 1, characterized in that The step of determining a plurality of predicted heart rates according to the first heartbeat interval, the second heartbeat interval, the third heartbeat interval, and the sampling rate of the heartbeat signal comprises: Determining a first predicted heart rate of the target based on the first heartbeat interval and the sampling rate of the ballistocardi signal; Based on the second heartbeat interval, the third heartbeat interval and the sampling rate of the cardiac impulse signal, a second predicted heart rate and a third predicted heart rate of the target to be measured are determined respectively.

3. The method according to claim 2, characterized in that Determining the target heart rate of the target based on the multiple predicted heart rates includes: The target heart rate is determined based on the first predicted heart rate, the second predicted heart rate, and the third predicted heart rate.

4. The method according to claim 1, wherein Processing the heartbeat signal to obtain a target probability density curve corresponding to the heartbeat signal includes: Processing the heartbeat signal based on a first preset algorithm to obtain at least one initial probability density curve corresponding to the heartbeat signal; The target probability density curve is determined based on the at least one initial probability density curve.

5. The method according to claim 4, characterized in that The first preset algorithm includes at least one of the following: autocorrelation method, average amplitude difference function method, maximum peak method, and minimum peak method.

6. The method according to claim 1, characterized in that The determining of a plurality of consecutive target heartbeats in the heartbeat signal based on the heartbeat differential signal includes: Based on the heartbeat differential signal, determining a plurality of suspected heartbeats that meet a preset screening condition in the heartbeat signal; Determining the similarity between any two suspected heartbeats among the multiple suspected heartbeats based on a second preset algorithm; A plurality of consecutive suspected heartbeats whose similarities are greater than the preset similarity threshold are determined as the target heartbeat.

7. An electronic device, characterized in that: include: A memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the heart rate determination method according to any one of claims 1 to 6.

8. A non-transitory machine-readable storage medium, characterized in that The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor is caused to perform the heart rate determination method according to any one of claims 1 to 6.

Images