WO2020143161A1

WO2020143161A1 - Heart rate detection method and device

Info

Publication number: WO2020143161A1
Application number: PCT/CN2019/091102
Authority: WO
Inventors: 张旺; 庄伯金; 王少军; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-01-09
Filing date: 2019-06-13
Publication date: 2020-07-16
Also published as: CN109758140A

Abstract

A heart rate detection method and device. The method comprises: measuring the heart rate of a user to be detected by means of a built-in sensor of a terminal to obtain a signal to be detected (S102); configuring a sliding window of a preset duration (S104); segmenting the signal to be detected according to the sliding window and a preset step size to obtain N segments, N being a natural number greater than 1 (S106); determining whether the signal within each segment among the N segments is strong noise (S108); if the signal within an i-th segment is strong noise, determining the i-th segment to be a target segment, i being a natural number, and i being 1 to N sequentially (S110); combining all target segments to obtain a strong noise region (S112); deleting the strong noise region in the signal to be detected to obtain an effective signal region (S114); and detecting a heart rate signal in the effective signal region (S116). The technical solution may solve the problem in the existing technology wherein the accuracy of heart rate detection is low.

Description

Heart rate detection method and device

This application requires the priority of the Chinese patent application filed on January 9, 2019, filed with the Chinese Patent Office, with the application number 201910020063.6 and the application name "a heart rate detection method and device", the entire content of which is incorporated by reference in this application .

【Technical field】

The present application relates to the field of signal processing technology, and in particular, to a heart rate detection method and device.

【Background technique】

When using the mobile phone's built-in sensor to measure the human heart rate based on micro-vibration, the vibration of the heartbeat is very weak, and the human body is often accompanied by complicated conditions such as large shaking of the limbs, coughing, leg shaking, hand shaking, etc. during the measurement process, and these An abnormal interference signal is much stronger than a heartbeat, and it is easy to overwhelm the heartbeat signal, resulting in low accuracy of heart rate detection.

【Application Content】

In view of this, the embodiments of the present application provide a heart rate detection method and device to solve the problem of low accuracy of heart rate detection in the prior art.

On the one hand, an embodiment of the present application provides a heart rate detection method. The method includes: measuring the heart rate of a user to be detected through a sensor built in the terminal to obtain a signal to be detected; setting a sliding window of a preset duration; according to the sliding window and Split the signal to be detected with a preset step size to obtain N segments, where N is a natural number greater than 1; determine whether the signal in each segment of the N segments belongs to strong noise; if the If the signal belongs to strong noise, the i-th segment is determined to be the target segment, i is a natural number, and i is sequentially taken from 1 to N; all target segments are combined to obtain a strong noise region; the strong noise in the signal to be detected The area is deleted to obtain an effective signal area; the heart rate signal in the effective signal area is detected.

On the one hand, an embodiment of the present application provides a heart rate detection device. The device includes: a measurement unit for measuring the heart rate of a user to be detected through a sensor built in the terminal to obtain a signal to be detected; and a setting unit for setting a preset A sliding window with a set duration; a segmentation unit for segmenting the signal to be detected according to the sliding window and a predetermined step size to obtain N segments, where N is a natural number greater than 1; a determination unit is used to determine the N Whether the signal in each segment in the segment belongs to strong noise; the determining unit is used to determine that the i-th segment is the target segment if the signal in the i-th segment belongs to strong noise, i is a natural number, and i takes 1 in turn To N; the merging unit is used to merge all the target fragments to obtain a strong noise region; the deletion unit is used to delete the strong noise region in the signal to be detected to obtain a valid signal region; the detection unit is used to The heart rate signal in the effective signal area is detected.

On the one hand, an embodiment of the present application provides a storage medium, the storage medium includes a stored program, wherein, when the program is running, the device where the storage medium is located is controlled to execute the above-mentioned heart rate detection method.

On the one hand, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory is used to store information including program instructions, and the processor is used to control execution of the program instructions, and the program instructions are processed by the processor When loading and executing, the steps of the above-mentioned heart rate detection method are realized.

In the embodiment of the present application, the signal to be detected is divided according to the sliding window and the preset step size to obtain N segments, and it is determined whether the signal in each segment of the N segments belongs to strong noise, and if the signal in a segment belongs to If there is strong noise, the segment is determined as the target segment, and all target segments are merged to obtain a strong noise region, and the strong noise region in the signal to be detected is deleted to obtain an effective signal region, and the heart rate signal in the effective signal region is detected , Because the strong noise area is deleted, thus avoiding the strong noise interference caused by large limb shaking, coughing, leg shaking, and hand shaking, improving the accuracy of detecting heart rate, and solving the low accuracy of detecting heart rate in the prior art The problem.

[Description of the drawings]

In order to more clearly explain the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. Those of ordinary skill in the art can obtain other drawings based on these drawings without paying any creative labor.

FIG. 1 is a flowchart of an optional heart rate detection method provided by an embodiment of the present application;

2 is a schematic diagram of an optional heart rate detection device provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a computer device provided by an embodiment of the present application.

【detailed description】

In order to better understand the technical solution of the present application, the following describes the embodiments of the present application in detail with reference to the accompanying drawings.

It should be clear that the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

The terminology used in the embodiments of the present application is for the purpose of describing specific embodiments only, and is not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include the majority forms unless the context clearly indicates other meanings.

It should be understood that the term "and/or" used herein is merely an association relationship describing an associated object, indicating that there may be three relationships, for example, A and/or B, which may indicate: A exists alone, and A and B, there are three cases of B alone. In addition, the character “/” in this article generally indicates that the related objects before and after it are in an “or” relationship.

FIG. 1 is a flowchart of an optional heart rate detection method provided by an embodiment of the present application. As shown in FIG. 1, the method includes the following steps:

Step 102: The heart rate of the user to be detected is measured by a sensor built in the terminal to obtain a signal to be detected.

Step 104: Set a sliding window with a preset duration.

Step 106: Divide the detection signal according to the sliding window and the preset step size to obtain N segments, where N is a natural number greater than 1.

Step 108: Determine whether the signal in each of the N segments belongs to strong noise.

In step 110, if the signal in the i-th segment belongs to strong noise, it is determined that the i-th segment is the target segment, i is a natural number, and i is sequentially taken from 1 to N.

In step 112, all target segments are combined to obtain a strong noise region.

Step 114, the strong noise area in the signal to be detected is deleted to obtain an effective signal area.

Step 116: Detect the heart rate signal in the effective signal area.

Use the built-in sensor of the terminal to measure the human heart rate based on micro-vibration to obtain the signal to be detected.

The signal to be detected includes a pulse wave signal.

Large shaking of the limbs, coughing, leg shaking, and hand shaking can cause strong noise and interfere with heart rate detection.

Optionally, determining whether the signal in each segment of the N segments belongs to strong noise includes: determining whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold; if the signal amplitude in the i-th segment is If the variance is greater than the preset variance threshold, it is determined that the signal in the i-th segment belongs to strong noise.

If the variance of the signal amplitude in a certain segment is large, it means that the signal in the segment is likely to be strong noise caused by large limb shaking, coughing, leg shaking, and hand shaking. In this case, determine the segment The signal inside belongs to strong noise and deletes the strong noise, to avoid the influence of strong noise on the accuracy of heart rate detection, and to improve the accuracy of heart rate detection.

There are three main types of noise in the detection of pulse wave signals: EMG interference, baseline drift and power frequency interference. Among them, the most significant one is EMG interference. The so-called myoelectric interference refers to a mixture of various electrical phenomena in the human body. A certain physiological quantity is sometimes a signal. In another occasion, it may be noise, that is, noise caused by electrical phenomena other than the measured physiological variable. EMG interference is caused by human muscle tremor and occurs randomly, with a frequency range between 5 and 2,000 Hz. Power frequency interference, the frequency of the mains voltage is 50Hz, it will cause interference to people's daily life in the form of electromagnetic wave radiation, and this interference is called power frequency interference. During the oscilloscope process, unstable baseline fluctuations, sudden jumps, oscillations, or slow drifts are often troublesome problems encountered. Because of this baseline drift, it is difficult to see the various bands, or cause ST segment elevation or depression, or similar to various serious arrhythmias, etc., which makes diagnosis difficult.

The strong noise area in the signal to be detected is deleted to obtain an effective signal area. The effective signal area may still contain EMG interference, baseline drift and power frequency interference. To ensure the accuracy of detection, the effective signal area needs to be The noise reduction processing of the heart rate signal is as follows:

Perform mean filtering on the heart rate signal in the effective signal area to calculate the gradient value of each signal point; perform non-local mean denoising on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result; according to each signal point Gradient value correction non-local mean pre-filtering results; detection of modified non-local mean pre-filtering results.

Optionally, performing non-local mean noise reduction on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result includes: calculating the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area; according to the i The attenuation coefficient of the signal points is subjected to non-local mean denoising to obtain the i-th signal point of the non-local mean pre-filtering result, where the attenuation coefficient of the i-th signal point is calculated according to the following formula:

Where h _i is the attenuation coefficient of the i-th signal point, h ₀ is a fixed attenuation coefficient, g _i is the gradient value of the i-th signal point, g _max is the preset maximum gradient value, and T is the preset gradient threshold.

g _max can be set to a value between 15 and 20. T can be set to a value between 10 and 13. h ₀ can be set to a value between 0.2 and 20.

Optionally, performing non-local mean noise reduction according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result includes: according to the formula

Calculate the signal block and similar window weights, where ω(i,j) represents the weight of the i-th signal block and the jth similar window, C _i represents the normalization parameter, G represents the Gaussian kernel function, and * represents the convolution operation, O(N _i ) represents the i-th signal block, O(N _j ) represents the j-th similar window,

Denotes the L2 norm, h _i denotes the attenuation coefficient of the i-th signal point; according to the equation _{_{M i = Σ j∈Ω ω (i}} , j) · O j i th signal points calculated local mean non-pre-filtered results, M _i represents the i-th signal point of the non-local mean pre-filtering result, Ω represents the search window, ω(i, j) represents the weight of the i-th signal block and the j-th similar window, and O _j represents the heart rate signal in the effective signal area The jth signal point.

The size of the search window can be set to 7×7, and the signal block has the same size as the similar window, which can be set to 3×3.

The current non-local mean noise reduction method of heart rate signals does not take into account that the heart rate signal has obvious periodicity and regional characteristics. The same attenuation coefficient is sampled in different wave band regions of the heart rate signal, which makes it difficult to take into account the smoothness of the uniform region And the protection of detailed information, the filtering effect is poor.

In this solution, for different band regions of the heart rate signal in the effective signal region, the core parameter of non-local mean noise reduction, that is, the attenuation coefficient, is adaptively adjusted, which can effectively suppress the noise while better protecting the details of the signal to achieve A better filtering effect.

After the noise reduction processing of the heart rate signal in the effective signal area is completed, determine the respective troughs and peaks of the heart rate signal in the effective signal area and the interval between two adjacent troughs or two adjacent peaks to obtain the amplitudes of the troughs and peaks Change curve and interval signal; generate heart rate data according to the amplitude change curve and interval signal of trough and peak.

An embodiment of the present application further provides a heart rate detection device, which is used to perform the above heart rate detection method. As shown in FIG. 2, the device includes: a measurement unit 10, a setting unit 20, a division unit 30, a judgment unit 40, and a determination Unit 50, merge unit 60, delete unit 70, detection unit 80.

The measuring unit 10 is configured to measure the heart rate of the user to be detected through a sensor built in the terminal to obtain a signal to be detected.

The setting unit 20 is used to set a sliding window with a preset duration.

The dividing unit 30 is configured to divide the detection signal according to the sliding window and the preset step size to obtain N segments, where N is a natural number greater than 1.

The judging unit 40 is used to judge whether the signal in each of the N segments belongs to strong noise.

The determining unit 50 is configured to determine that the i-th segment is a target segment, i is a natural number if the signal in the i-th segment belongs to strong noise, and i takes 1 to N in sequence.

The merging unit 60 is used for merging all target segments to obtain strong noise regions.

The deleting unit 70 is configured to delete the strong noise area in the signal to be detected to obtain an effective signal area.

The detection unit 80 is configured to detect the heart rate signal in the effective signal area.

The signal to be detected includes a pulse wave signal.

Optionally, the judgment unit 40 includes: a judgment subunit and a determination subunit. The judging subunit is used to judge whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold. The determination subunit is used to determine that the signal in the i-th segment belongs to strong noise if the variance of the signal amplitude in the i-th segment is greater than the preset variance threshold.

Optionally, the detection unit 80 includes: a filtering subunit, a noise reduction subunit, a correction subunit, and a detection subunit. The filtering subunit is used to perform average filtering on the heart rate signal in the effective signal area and calculate the gradient value of each signal point. The noise reduction sub-unit is used for performing non-local mean denoising on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result. The correction subunit is used for correcting the non-local mean pre-filtering result according to the gradient value of each signal point. The detection subunit is used for detecting the corrected non-local mean pre-filtering result.

Optionally, the noise reduction subunit includes: a calculation module and a noise reduction module. The calculation module is used to calculate the attenuation coefficient of the ith signal point of the heart rate signal in the effective signal area. The noise reduction module is used to perform non-local mean denoising according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result. Among them, the attenuation coefficient of the i-th signal point is calculated according to the following formula:

Optionally, the noise reduction module includes: a first calculation submodule and a second calculation submodule. The first calculation submodule is used according to the formula

Denotes the L2 norm, h _i denotes the attenuation coefficient of the i-th signal point. The second calculation submodule is used to calculate the i-th signal point of the non-local mean pre-filtering result according to the formula M _i =∑ _j∈Ω ω(i,j)·O _j , and M _i represents the non-local mean pre-filtering result. For the i-th signal point, Ω represents the search window, ω(i, j) represents the weight of the i-th signal block and the j-th similar window, and O _j represents the j-th signal point of the heart rate signal in the effective signal area.

An embodiment of the present application provides a computer nonvolatile readable storage medium, where the storage medium includes a stored program, wherein, when the program is running, the device where the computer nonvolatile readable storage medium is located is controlled to perform the following steps: The sensor of the user to measure the heart rate of the user to be detected, get the signal to be detected; set the sliding window of the preset duration; segment the signal to be detected according to the sliding window and the preset step size, get N segments, N is a natural number greater than 1; judge Whether the signal in each segment of the N segments belongs to strong noise; if the signal in the i segment belongs to strong noise, determine the i segment as the target segment, i is a natural number, i takes 1 to N in turn; The target fragments are combined to obtain a strong noise area; the strong noise area in the signal to be detected is deleted to obtain an effective signal area; and the heart rate signal in the effective signal area is detected.

Optionally, when the program is running, the device where the computer non-volatile readable storage medium is located also performs the following steps: determine whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold; if the If the variance of the signal amplitude is greater than the preset variance threshold, it is determined that the signal in the i-th segment belongs to strong noise.

Optionally, when the program is running, the device where the computer non-volatile readable storage medium is located also performs the following steps: performing an average filtering on the heart rate signal in the effective signal area, calculating the gradient value of each signal point; The heart rate signal in is subjected to non-local mean denoising to obtain the non-local mean pre-filtering result; the non-local mean pre-filtering result is modified according to the gradient value of each signal point; the corrected non-local mean pre-filtering result is detected.

Optionally, when the program is running, the device where the computer non-volatile readable storage medium is located also performs the following steps: calculating the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area; according to the i-th signal point The attenuation coefficient is used to reduce the noise of the non-local mean to obtain the i-th signal point of the non-local mean pre-filtering result, where the attenuation coefficient of the i-th signal point is calculated according to the following formula:

Optionally, controlling the device where the computer non-volatile readable storage medium is located while the program is running also performs the following steps:

Represents the L2 norm, h _i represents the attenuation coefficient of the ith signal point; according to the formula

Calculate the i-th signal point of the non-local mean pre-filtering result, M _i represents the i-th signal point of the non-local mean pre-filtering result, Ω represents the search window, and ω(i, j) represents the i-th signal block and j-th Similar window weights, O _j represents the jth signal point of the heart rate signal in the effective signal area.

An embodiment of the present application provides a computer device including a memory and a processor. The memory is used to store information including program instructions. The processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, the following steps are implemented: The built-in sensor of the terminal measures the heart rate of the user to be detected to obtain the signal to be detected; sets the sliding window of the preset duration; divides the detection signal according to the sliding window and the preset step size to obtain N segments, N is a natural number greater than 1 Determine whether the signal in each segment of the N segments belongs to strong noise; if the signal in the i segment belongs to strong noise, determine the i segment as the target segment, i is a natural number, and i takes 1 to N in turn; All target segments are combined to obtain a strong noise area; the strong noise area in the signal to be detected is deleted to obtain an effective signal area; and the heart rate signal in the effective signal area is detected.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: determine whether the variance of the signal amplitude in the i-th segment is greater than the preset variance threshold; if the variance of the signal amplitude in the i-th segment is greater than the preset The variance threshold determines that the signal in the ith segment belongs to strong noise.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: the heart rate signal in the effective signal area is average filtered to calculate the gradient value of each signal point; and the heart rate signal in the effective signal area is non-local Mean value noise reduction to obtain non-local mean pre-filtering results; correct non-local mean pre-filtering results according to the gradient value of each signal point; detect the corrected non-local mean pre-filtering results.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: calculating the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area; performing non-local mean reduction according to the attenuation coefficient of the i-th signal point Noise, the i-th signal point of the non-local mean pre-filtering result is obtained, where the attenuation coefficient of the i-th signal point is calculated according to the following formula:

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: according to the formula

FIG. 3 is a schematic diagram of a computer device provided by an embodiment of the present application. As shown in FIG. 3, the computer device 50 of this embodiment includes a processor 51, a memory 52, and a computer program 53 stored in the memory 52 and executable on the processor 51. When the computer program 53 is executed by the processor 51 To implement the heart rate detection method in the embodiment, in order to avoid repetition, they are not described here one by one. Alternatively, when the computer program is executed by the processor 51, the functions of each model/unit in the center rate detection device of the embodiment are implemented. To avoid repetition, details are not described here one by one.

The computer device 50 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer equipment may include, but is not limited to, the processor 51 and the memory 52. Those skilled in the art may understand that FIG. 3 is only an example of the computer device 50, and does not constitute a limitation on the computer device 50, and may include more or less components than shown, or combine some components, or different components. For example, computer equipment may also include input and output devices, network access devices, buses, and so on.

The so-called processor 51 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 52 may be an internal storage unit of the computer device 50, such as a hard disk or a memory of the computer device 50. The memory 52 may also be an external storage device of the computer device 50, for example, a plug-in hard disk equipped on the computer device 50, a smart memory card (Smart Media (SMC), a secure digital (SD) card, and a flash memory card (Flash Card) etc. Further, the memory 52 may also include both the internal storage unit of the computer device 50 and the external storage device. The memory 52 is used to store computer programs and other programs and data required by computer devices. The memory 52 may also be used to temporarily store data that has been or will be output.

Those skilled in the art can clearly understand that for the convenience and conciseness of the description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the unit is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined Or it can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical, or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.

The above integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium. The above software functional unit is stored in a storage medium, and includes several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) or processor (Processor) to perform the methods described in the embodiments of the present application Partial steps. The foregoing storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

The above are only the preferred embodiments of this application and are not intended to limit this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application should be included in this application Within the scope of protection.

Claims

A heart rate detection method, characterized in that the method includes:

Measure the heart rate of the user to be detected through the sensor built in the terminal to obtain the signal to be detected;

Sliding window with preset duration;

Divide the signal to be detected according to the sliding window and the preset step size to obtain N segments, where N is a natural number greater than 1;

Determine whether the signal in each of the N segments belongs to strong noise;

If the signal in the i-th segment belongs to strong noise, it is determined that the i-th segment is the target segment, i is a natural number, and i takes 1 to N in sequence;

Combine all target fragments to get strong noise area;

Delete the strong noise area in the signal to be detected to obtain an effective signal area;

Detecting the heart rate signal in the effective signal area.
The method according to claim 1, wherein the determining whether the signal in each of the N segments belongs to strong noise includes:

Determine whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold;

If the variance of the signal amplitude in the i-th segment is greater than the preset variance threshold, it is determined that the signal in the i-th segment belongs to strong noise.
The method according to any one of claims 1 or 2, wherein the detecting the heart rate signal in the effective signal area includes:

Perform an average filtering on the heart rate signal in the effective signal area to calculate the gradient value of each signal point;

Performing non-local mean noise reduction on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result;

Modify the non-local mean pre-filtering result according to the gradient value of each signal point;

The pre-filtered results of the corrected non-local mean are detected.
The method according to claim 3, wherein performing non-local mean noise reduction on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result includes:

Calculating the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area;

Performing non-local mean noise reduction according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result,

The attenuation coefficient of the i-th signal point is calculated according to the following formula:

Where h i is the attenuation coefficient of the i-th signal point, h 0 is a fixed attenuation coefficient, g i is the gradient value of the i-th signal point, g max is the preset maximum gradient value, and T is the preset Gradient threshold.
The method according to claim 4, wherein the performing the non-local mean noise reduction according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result includes: :

According to the formula
Calculate the signal block and similar window weights, where ω(i,j) represents the weight of the i-th signal block and the jth similar window, C i represents the normalization parameter, G represents the Gaussian kernel function, and * represents the convolution operation, O(N i ) represents the i-th signal block, O(N j ) represents the j-th similar window,
Denotes the L2 norm, h i denotes the attenuation coefficient of the i-th signal point;

Calculate the i-th signal point of the non-local mean pre-filtering result according to the formula M i =∑ j∈Ω ω(i,j)·O j , M i represents the i-th signal of the non-local mean pre-filtering result Point, Ω represents the search window, ω(i,j) represents the weight of the i-th signal block and the j-th similar window, and O j represents the j-th signal point of the heart rate signal in the effective signal area.
A heart rate detection device, characterized in that the device comprises:

The measuring unit is used to measure the heart rate of the user to be detected through the sensor built in the terminal to obtain the signal to be detected;

Setting unit, used to set the sliding window of preset duration;

A segmentation unit, configured to segment the signal to be detected according to a sliding window and a preset step size to obtain N segments, where N is a natural number greater than 1;

The judging unit is used to judge whether the signal in each of the N segments belongs to strong noise;

A determining unit, configured to determine that the i-th segment is a target segment, i is a natural number if the signal in the i-th segment belongs to strong noise, and i is sequentially taken from 1 to N;

The merging unit is used to merge all target fragments to obtain strong noise regions;

A deleting unit, configured to delete a strong noise area in the signal to be detected to obtain an effective signal area;

The detection unit is configured to detect the heart rate signal in the effective signal area.
The apparatus according to claim 6, wherein the judgment unit comprises:

A judgment subunit, used to judge whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold;

A determining subunit, configured to determine that the signal in the i-th segment belongs to strong noise if the variance of the signal amplitude in the i-th segment is greater than the preset variance threshold.
The device according to any one of claims 6 or 7, wherein the detection unit comprises:

The filtering subunit is used to perform average filtering on the heart rate signal in the effective signal area and calculate the gradient value of each signal point;

A noise reduction subunit, configured to perform non-local mean noise reduction on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result;

A correction subunit, configured to correct the non-local mean pre-filtering result according to the gradient value of each signal point;

The detection subunit is used for detecting the corrected non-local mean pre-filtering result.
The apparatus according to claim 8, wherein the noise reduction subunit comprises:

A calculation module, configured to calculate the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area;

A noise reduction module, configured to perform non-local mean noise reduction according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result, wherein, the i-th signal point The attenuation coefficient is calculated according to the following formula:
Where h i is the attenuation coefficient of the i-th signal point, h 0 is a fixed attenuation coefficient, g i is the gradient value of the i-th signal point, g max is the preset maximum gradient value, and T is the preset Gradient threshold.
The device according to claim 9, wherein the noise reduction module comprises:

The first calculation submodule is used according to the formula
Calculate the weights of the signal block and the similar window, where ω(i,j) represents the weight of the i-th signal block and the jth similar window, C i represents the normalization parameter, G represents the Gaussian kernel function, and * represents the convolution operation, O(N i ) represents the i-th signal block, O(N j ) represents the j-th similar window,
Denotes the L2 norm, h i denotes the attenuation coefficient of the i-th signal point;

The second calculation submodule is used to calculate the i-th signal point of the non-local mean pre-filtering result according to the formula M i =∑ j∈Ω ω(i,j)·O j , and M i represents the non-local mean The i-th signal point of the pre-filtering result, Ω represents the search window, ω(i,j) represents the weight of the i-th signal block and the j-th similar window, and O j represents the j-th of the heart rate signal in the effective signal region Signal points.
A computer device includes a memory and a processor, the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that the program instructions are loaded by the processor And implement the following steps when executing:

Measure the heart rate of the user to be detected through the sensor built in the terminal to obtain the signal to be detected;

Set a sliding window of preset duration;

Divide the signal to be detected according to the sliding window and the preset step size to obtain N segments, where N is a natural number greater than 1;

Determine whether the signal in each of the N segments belongs to strong noise;

If the signal in the i-th segment belongs to strong noise, it is determined that the i-th segment is the target segment, i is a natural number, and i takes 1 to N in sequence;

Combine all target fragments to get strong noise area;

Delete the strong noise area in the signal to be detected to obtain an effective signal area;

Detecting the heart rate signal in the effective signal area.
The computer device according to claim 11, wherein when the program instructions are loaded and executed by the processor, the following steps are further implemented:

Determine whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold;

If the variance of the signal amplitude in the i-th segment is greater than the preset variance threshold, it is determined that the signal in the i-th segment belongs to strong noise.
The computer device according to claim 11 or 12, wherein when the program instructions are loaded and executed by the processor, the following steps are further implemented:

Perform an average filtering on the heart rate signal in the effective signal area to calculate the gradient value of each signal point;

Performing non-local mean noise reduction on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result;

Modify the non-local mean pre-filtering result according to the gradient value of each signal point;

The pre-filtered results of the corrected non-local mean are detected.
The computer device according to claim 13, wherein when the program instructions are loaded and executed by the processor, the following steps are further implemented:

Calculating the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area;

Performing non-local mean noise reduction according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result,

The attenuation coefficient of the i-th signal point is calculated according to the following formula:

Where h i is the attenuation coefficient of the i-th signal point, h 0 is a fixed attenuation coefficient, g i is the gradient value of the i-th signal point, g max is the preset maximum gradient value, and T is the preset Gradient threshold.
The computer device according to claim 14, wherein when the program instructions are loaded and executed by the processor, the following steps are further implemented:

According to the formula
Calculate the signal block and similar window weights, where ω(i,j) represents the weight of the i-th signal block and the jth similar window, C i represents the normalization parameter, G represents the Gaussian kernel function, and * represents the convolution operation, O(N i ) represents the i-th signal block, O(N j ) represents the j-th similar window,
Denotes the L2 norm, h i denotes the attenuation coefficient of the i-th signal point;

Calculate the i-th signal point of the non-local mean pre-filtering result according to the formula M i =∑ j∈Ω ω(i,j)·O j , M i represents the i-th signal of the non-local mean pre-filtering result Point, Ω represents the search window, ω(i,j) represents the weight of the i-th signal block and the j-th similar window, and O j represents the j-th signal point of the heart rate signal in the effective signal area.
A computer nonvolatile readable storage medium, characterized in that the computer nonvolatile readable storage medium includes a stored program, wherein the computer nonvolatile readable storage is controlled when the program is running The device where the storage medium is located performs the following steps:

Measure the heart rate of the user to be detected through the sensor built in the terminal to obtain the signal to be detected;

Set a sliding window of preset duration;

Divide the signal to be detected according to the sliding window and the preset step size to obtain N segments, where N is a natural number greater than 1;

Determine whether the signal in each of the N segments belongs to strong noise;

If the signal in the i-th segment belongs to strong noise, it is determined that the i-th segment is the target segment, i is a natural number, and i takes 1 to N in sequence;

Combine all target fragments to get strong noise area;

Delete the strong noise area in the signal to be detected to obtain an effective signal area;

Detecting the heart rate signal in the effective signal area.
The computer non-volatile readable storage medium according to claim 16, wherein the device where the computer non-volatile readable storage medium is located while the program is running further executes the following steps:

Determine whether the variance of the signal amplitude in the i-th segment is greater than a preset variance threshold;

If the variance of the signal amplitude in the i-th segment is greater than the preset variance threshold, it is determined that the signal in the i-th segment belongs to strong noise.
The computer non-volatile readable storage medium according to claim 16 or 17, wherein the device where the computer non-volatile readable storage medium is located while the program is running further executes the following steps:

Perform an average filtering on the heart rate signal in the effective signal area to calculate the gradient value of each signal point;

Performing non-local mean noise reduction on the heart rate signal in the effective signal area to obtain a non-local mean pre-filtering result;

Modify the non-local mean pre-filtering result according to the gradient value of each signal point;

The pre-filtered results of the corrected non-local mean are detected.
The computer non-volatile readable storage medium according to claim 18, wherein the device where the computer non-volatile readable storage medium is located while the program is running further executes the following steps:

Calculating the attenuation coefficient of the i-th signal point of the heart rate signal in the effective signal area;

Performing non-local mean noise reduction according to the attenuation coefficient of the i-th signal point to obtain the i-th signal point of the non-local mean pre-filtering result,

The attenuation coefficient of the i-th signal point is calculated according to the following formula:

Where h i is the attenuation coefficient of the i-th signal point, h 0 is a fixed attenuation coefficient, g i is the gradient value of the i-th signal point, g max is the preset maximum gradient value, and T is the preset Gradient threshold.
The computer non-volatile readable storage medium according to claim 19, wherein, when the program is running, controlling the device where the computer non-volatile readable storage medium is located further performs the following steps:

According to the formula
Calculate the signal block and similar window weights, where ω(i,j) represents the weight of the i-th signal block and the jth similar window, C i represents the normalization parameter, G represents the Gaussian kernel function, and * represents the convolution operation, O(N i ) represents the i-th signal block, O(N j ) represents the j-th similar window,
Denotes the L2 norm, h i denotes the attenuation coefficient of the i-th signal point;

Calculate the i-th signal point of the non-local mean pre-filtering result according to the formula M i =∑ j∈Ω ω(i,j)·O j , M i represents the i-th signal of the non-local mean pre-filtering result Point, Ω represents the search window, ω(i,j) represents the weight of the i-th signal block and the j-th similar window, and O j represents the j-th signal point of the heart rate signal in the effective signal area.