Electrocardiosignal quality evaluation method, electronic equipment and chip system

Abstract

The invention provides an electrocardiosignal quality evaluation method, electronic equipment and a chip system, and relates to the technical field of signal evaluation. The method comprises the following steps: carrying out statistics on peak value variability characteristics and peak value number variability characteristics of a plurality of electrocardiosignal samples, taking the peak value variability characteristics of the plurality of electrocardiosignal samples as an abnormal demarcation point, and taking the peak value number variability characteristics of the plurality of electrocardiosignal samples as another abnormal demarcation point; according to the relation between the peak value variability characteristic and the peak value number variability characteristic of the electrocardiosignal to be evaluated and the two abnormal demarcation points, whether the electrocardiosignal to be evaluated is a normal signal, an abnormal signal or a noise signal is determined, and the normal electrocardiosignal can be accurately detected through the method.

Description

Electrocardiogram signal quality assessment method, electronic device, and chip system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on September 15, 2022, with application number 202211120062.7 and application name “A method for evaluating electrocardiogram signal quality, electronic equipment and chip system”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of signal evaluation technology, and in particular to an electrocardiogram signal quality evaluation method, electronic equipment, and chip system. Background Art

[0003] ECG signals are weak, nonlinear, non-stationary, and random signals, typically with a maximum amplitude of mV. Therefore, ECG signal monitoring typically requires the device to be placed in close proximity to the surface of a living organism to collect the ECG signal. Of course, due to the inherent characteristics of ECG signals and the monitoring scenarios, ECG signals are highly susceptible to interference from both within the organism (e.g., myoelectric interference, respiratory interference, etc.) and outside the organism (e.g., power frequency interference, signal pickup processes, etc.).

[0004] Currently, collected ECG signals may be accompanied by a significant amount of noise or abnormal signals (caused by anomalies during the acquisition process), which can overwhelm the ECG signals and cause them to lose some of their original characteristics. In particular, when ECG signals contain certain pathological features, these pathological features may be interfered with by the noise and / or abnormal signals, reducing the accuracy of early warning algorithms related to pathological signals.

[0005] Summary of the Invention

[0006] In view of this, the present application provides an electrocardiogram signal quality assessment method, electronic equipment, and chip system, which can detect normal signals in electrocardiogram signals.

[0007] To achieve the above objectives, this application adopts the following technical solutions:

[0008] In a first aspect, the present application provides a method for evaluating the quality of an electrocardiogram signal, the method comprising:

[0009] Acquiring a first electrocardiogram signal;

[0010] Calculating a peak variability feature and a peak number variability feature of the first electrocardiogram signal;

[0011] If the peak variability characteristic of the first ECG signal is less than a first threshold value, and the peak quantity variability characteristic of the first ECG signal is less than a second threshold value, then the first ECG signal is a normal signal, wherein the first threshold value is used to indicate the abnormal demarcation point of the peak variability characteristic, and the first threshold value is determined by the peak variability characteristics of multiple ECG signal samples, and the second threshold value is used to indicate the abnormal demarcation point of the peak quantity variability characteristic, and the second threshold value is determined by the peak quantity variability characteristics of multiple ECG signal samples.

[0012] In this application, the peak variability characteristics and peak number variability characteristics of multiple ECG signal samples are statistically analyzed. The peak variability characteristics of multiple ECG signal samples are used as an abnormality cutoff point, and the peak number variability characteristics of multiple ECG signal samples are used as another abnormality cutoff point. The type of the ECG signal to be evaluated is determined based on the relationship between the peak variability characteristics and peak number variability characteristics of the ECG signal to be evaluated and the two abnormal cutoff points. This method can accurately distinguish normal signals.

[0013] As an implementation of the first aspect, acquiring the first electrocardiogram signal includes:

[0014] Obtaining the original ECG signal of the first duration;

[0015] The original electrocardiogram signal is filtered to obtain a first electrocardiogram signal.

[0016] In this application, the variability feature related to the peak value is used as the different types of features of the ECG signal. Therefore, in order to improve the accuracy of the feature, filtering processing is required to remove the burrs in the ECG signal waveform.

[0017] As another implementation of the first aspect, filtering the original electrocardiogram signal includes:

[0018] The original ECG signal is processed by low-pass filtering and high-pass filtering.

[0019] As another implementation of the first aspect, calculating the peak variability feature and the peak number variability feature of the first electrocardiogram signal includes:

[0020] Segmenting the first electrocardiogram signal to obtain multiple signal segments;

[0021] Calculate the peak list and peak number of each signal segment, the peak list includes N peaks, N represents the number of peaks;

[0022] Obtaining a peak variability feature of the first electrocardiogram signal according to a peak list of the plurality of signal segments;

[0023] A peak quantity variability feature of the first electrocardiogram signal is obtained according to the peak quantities of the plurality of signal segments.

[0024] The embodiment of the present application obtains multiple signal segments by segmenting the first electrocardiogram signal, determines the peak variability characteristics of the first electrocardiogram signal based on the data characteristics of the peak lists of the multiple signal segments, and determines the peak number variability characteristics of the first electrocardiogram signal based on the data characteristics of the peak numbers of the multiple signal segments.

[0025] As another implementation of the first aspect, the signal segment includes multiple discrete data points, and calculating the peak list of each signal segment includes:

[0026] Calculate the absolute value of the difference between each two adjacent data points in the first signal segment, where the first signal segment is any signal segment in the signal segment. The peak list of the first signal segment includes one or more first peaks, and the first peak is a difference absolute value that is greater than the previous difference absolute value, greater than the next difference absolute value, and greater than the peak finding threshold. The peak finding threshold is determined by the difference absolute values ​​corresponding to multiple signal segments of the first electrocardiogram signal.

[0027] As another implementation of the first aspect, a method for determining a peak-finding threshold includes:

[0028] Calculating a first product of a first quantile in a set of absolute values ​​of differences corresponding to a plurality of signal segments of the first electrocardiogram signal and a first constant;

[0029] Calculate a second product of a second quantile in a set of absolute values ​​of differences corresponding to a plurality of signal segments of the first electrocardiogram signal and a second constant;

[0030] The difference between the first product and the second product is calculated to obtain the peak finding threshold.

[0031] As another implementation of the first aspect, obtaining the peak variability feature of the first electrocardiogram signal according to the peak lists of the plurality of signal segments includes:

[0032] Calculating a standard deviation and a mean of peak values ​​of a plurality of signal segments of the first electrocardiogram signal;

[0033] The ratio of the standard deviation to the mean of the peak values ​​of the plurality of signal segments is calculated to obtain a peak variability feature of the first electrocardiogram signal.

[0034] As another implementation of the first aspect, obtaining the peak number variability feature of the first electrocardiogram signal according to the peak numbers of multiple signal segments includes:

[0035] Calculating a first difference between a maximum value and a minimum value of the number of peaks of a plurality of signal segments of the first electrocardiogram signal;

[0036] calculating a median value of the number of peaks of the plurality of signal segments of the first electrocardiogram signal;

[0037] The ratio of the first difference value to the median value is calculated to obtain a peak quantity variability characteristic of the first electrocardiogram signal.

[0038] As another implementation of the first aspect, a method for determining the first threshold and the second threshold includes:

[0039] Acquire multiple ECG signal samples, where the durations of the multiple ECG signal samples are all the first duration;

[0040] Calculate the peak variability feature and peak number variability feature of each ECG signal sample;

[0041] Obtaining a first threshold value according to a peak variability characteristic of a plurality of electrocardiogram signal samples;

[0042] A second threshold is obtained according to a peak quantity variability characteristic of the plurality of electrocardiogram signal samples.

[0043] As another implementation of the first aspect, obtaining the first threshold according to the peak variability characteristics of the plurality of electrocardiogram signal samples includes:

[0044] calculating a third product of a third quantile and a third constant in a peak variability feature of a plurality of ECG signal samples;

[0045] calculating a fourth product of a fourth quantile and a fourth constant in a peak variability feature of a plurality of ECG signal samples;

[0046] A difference between the third product and the fourth product is calculated to obtain a first threshold.

[0047] As another implementation of the first aspect, obtaining the second threshold according to a peak quantity variability characteristic of a plurality of electrocardiogram signal samples includes:

[0048] calculating a fifth product of a fifth quantile and a fifth constant in a peak quantity variability feature of a plurality of ECG signal samples;

[0049] calculating a sixth product of a sixth quantile and a sixth constant in a peak quantity variability feature of a plurality of electrocardiogram signal samples;

[0050] A difference between the fifth product and the sixth product is calculated to obtain a second threshold.

[0051] As another implementation of the first aspect, the method further includes:

[0052] If the peak variability characteristic of the first electrocardiogram signal is greater than a first threshold value and the peak number variability characteristic of the first electrocardiogram signal is greater than a second threshold value, the first electrocardiogram signal is an abnormal signal;

[0053] If the peak variability characteristic of the first electrocardiogram signal is greater than or equal to a first threshold value, and the peak number variability characteristic of the first electrocardiogram signal is less than or equal to a second threshold value, then the first electrocardiogram signal is a noise signal;

[0054] If the peak variability characteristic of the first electrocardiogram signal is less than or equal to the first threshold, and the peak quantity variability characteristic of the first electrocardiogram signal is greater than or equal to the second threshold, the first electrocardiogram signal is a noise signal.

[0055] As another implementation of the first aspect, obtaining multiple electrocardiogram signal samples includes:

[0056] Acquire multiple original ECG signals;

[0057] Performing data segmentation on the multiple original ECG signals to obtain multiple original ECG signals of a first duration;

[0058] Low-pass filtering and high-pass filtering are performed on each original electrocardiogram signal of the first duration to obtain a plurality of electrocardiogram signal samples.

[0059] As another implementation of the first aspect, the method of calculating the peak variability feature of each electrocardiogram signal sample is the same as the method of calculating the peak variability feature of the first electrocardiogram signal;

[0060] The manner of calculating the peak quantity variability feature of each electrocardiogram signal sample is the same as the manner of calculating the peak quantity variability feature of the first electrocardiogram signal.

[0061] In a second aspect, an electronic device is provided, comprising a processor, wherein the processor is configured to execute a computer program stored in a memory to implement the steps of any one of the methods of the first aspect of the present application.

[0062] In a third aspect, a chip system is provided, comprising a processor coupled to a memory, wherein the processor executes a computer program stored in the memory to implement the steps of any one of the methods of the first aspect of the present application.

[0063] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the steps of any one of the methods of the first aspect of the present application are implemented.

[0064] In a fifth aspect, the present application provides a computer program product, which, when executed on a device, enables the device to execute the steps of any one of the methods of the first aspect of the present application.

[0065] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] FIG1 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application;

[0067] FIG2 is a flow chart of an electrocardiogram signal quality assessment method according to an embodiment of the present application;

[0068] FIG3 is a flow chart of an electrocardiogram signal feature learning process according to an embodiment of the present application;

[0069] FIG4 is a schematic diagram of a waveform of an electrocardiogram signal before filtering provided in an embodiment of the present application;

[0070] FIG5 is a waveform diagram of a filtered ECG signal according to an embodiment of the present application;

[0071] FIG6 is a schematic diagram of peak points obtained according to an embodiment of the present application;

[0072] FIG7 is a flow chart of an electrocardiogram signal quality assessment process according to an embodiment of the present application;

[0073] FIG8 is a schematic diagram of waveforms of four signal segments before filtering, after filtering, and at peak points provided by an embodiment of the present application;

[0074] FIG9 shows the classification results of four ECG signals and more signal segments provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] In the following description, specific details such as specific system structures and technologies are provided for illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details.

[0076] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0077] It should also be understood that in the embodiments of this application, "one or more" refers to one, two, or more than two; "and / or" describes the relationship between associated objects, indicating that three relationships can exist; for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0078] In addition, in the description of this application specification and the appended claims, the terms "first", "second", "third", "fourth", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0079] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0080] The ECG signal quality assessment method provided in the embodiments of this application can be applied to electronic devices such as ECG monitoring devices and wearable devices. Of course, it can also be applied to electronic devices such as mobile phones connected to ECG monitoring devices. The embodiments of this application do not limit the specific type of electronic device.

[0081] Figure 1 shows a schematic diagram of the structure of an electronic device. Electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, antenna 1, antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, a camera 193, a display 194, and a subscriber identification module (SIM) card interface 195. Sensor module 180 may include a pressure sensor 180A, a touch sensor 180K, and the like.

[0082] It should be understood that the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0083] The processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0084] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0085] Processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. This memory can store instructions or data that have just been used or are being recycled by processor 110. If processor 110 needs to use the same instruction or data again, it can directly retrieve it from the memory. This avoids duplicate accesses, reduces processor 110 latency, and thus improves system efficiency.

[0086] The USB interface 130 is an interface that complies with USB standards, and may be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 130 may be used to connect a charger to charge the electronic device 100, and may also be used to transfer data between the electronic device 100 and peripheral devices.

[0087] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 via the external memory interface 120 to implement data storage functions. For example, files such as music and videos can be stored on the external memory card.

[0088] The internal memory 121 can be used to store computer executable program code, which includes instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.).

[0089] In addition, the internal memory 121 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0090] The charging management module 140 is configured to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from the wired charger via the USB interface 130.

[0091] The power management module 141 is used to connect the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140 to provide power to the processor 110, the internal memory 121, the external memory, the display 194, the camera 193, and the wireless communication module 160.

[0092] In some other embodiments, the power management module 141 may also be provided in the processor 110. In some other embodiments, the power management module 141 and the charging management module 140 may also be provided in the same device.

[0093] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0094] Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In other embodiments, the antennas can be used in conjunction with a tuning switch.

[0095] The mobile communication module 150 can provide wireless communication solutions, including 2G / 3G / 4G / 5G, for the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low-noise amplifier (LNA), and the like. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the modem processor for demodulation. The mobile communication module 150 can also amplify the signals modulated by the modem processor and convert them into electromagnetic waves for radiation via the antenna 1.

[0096] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices that integrate at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0097] In some embodiments, antenna 1 of electronic device 100 is coupled to mobile communication module 150 , and antenna 2 is coupled to wireless communication module 160 , so that electronic device 100 can communicate with the network and other devices through wireless communication technology.

[0098] The electronic device 100 can implement audio functions such as music playback and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0099] The audio module 170 is used to convert digital audio signals into analog audio signals for output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be provided in the processor 110, or some functional modules of the audio module 170 can be provided in the processor 110.

[0100] The speaker 170A, also called a "speaker", is used to convert audio electrical signals into sound signals. The electronic device 100 can listen to music or listen to hands-free calls through the speaker 170A.

[0101] The receiver 170B, also called a "handset", is used to convert audio electrical signals into sound signals. When the electronic device 100 receives a call or a voice message, the user can place the receiver 170B close to the ear to hear the voice.

[0102] Microphone 170C, also known as "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to the microphone 170C to input the sound signal into the microphone 170C. The electronic device 100 can be provided with at least one microphone 170C. In other embodiments, the electronic device 100 can be provided with two microphones 170C, which can not only monitor voice information but also realize noise reduction function. In other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to realize the collection of sound signals, noise reduction, identification of sound sources, and directional recording functions.

[0103] The headphone jack 170D is used to connect a wired headphone and can be the USB interface 130 or a 3.5mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0104] The pressure sensor 180A is used to sense pressure signals and convert them into electrical signals. In some embodiments, the pressure sensor 180A can be provided on the display screen 194. There are many types of pressure sensors 180A, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, etc. A capacitive pressure sensor can be a device comprising at least two parallel plates having a conductive material. When a force acts on the pressure sensor 180A, the capacitance between the electrodes changes. The electronic device 100 determines the intensity of the pressure based on the change in capacitance. When a touch operation is applied to the display screen 194, the electronic device 100 detects the intensity of the touch operation based on the pressure sensor 180A. The electronic device 100 can also calculate the position of the touch based on the detection signal of the pressure sensor 180A.

[0105] The touch sensor 180K is also called a "touch panel." The touch sensor 180K can be disposed on the display screen 194. The touch sensor 180K and the display screen 194 form a touch screen, also called a "touch screen." The touch sensor 180K is used to detect touch operations applied thereto or in the vicinity thereof. The touch sensor can transmit the detected touch operations to the application processor to determine the type of touch event. Visual output related to the touch operations can be provided via the display screen 194. In other embodiments, the touch sensor 180K can also be disposed on the surface of the electronic device 100, in a location different from that of the display screen 194.

[0106] The buttons 190 include a power button, a volume button, and the like. The buttons 190 may be mechanical buttons or touch buttons. The electronic device 100 may receive key inputs and generate key signal inputs related to user settings and function control of the electronic device 100.

[0107] Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts and can also be used for touch vibration feedback.

[0108] Electronic device 100 implements display functionality through a GPU, display screen 194, and an application processor. A GPU is a microprocessor for image processing that connects display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or modify display information.

[0109] The display screen 194 is used to display images, videos, etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194 , where N is a positive integer greater than 1.

[0110] The camera 193 is used to capture still images or videos. In some embodiments, the electronic device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.

[0111] The SIM card interface 195 is used to connect a SIM card. The SIM card can be connected to and disconnected from the electronic device 100 by inserting or removing the SIM card into or from the SIM card interface 195. The electronic device 100 may support one or N SIM card interfaces, where N is a positive integer greater than one.

[0112] The embodiments of the present application do not particularly limit the specific structure of the execution body of the ECG signal quality assessment method. As long as the code recording the ECG signal quality assessment method provided by the embodiments of the present application can be executed to perform processing according to the ECG signal quality assessment method provided by the embodiments of the present application, the execution body of the ECG signal quality assessment method provided by the embodiments of the present application can be, for example, a functional module in an electronic device that can call and execute a program, or a processing device used in an electronic device, such as a chip.

[0113] ECG signals are weak signals that are nonlinear, non-stationary, and random, usually with a maximum value of mV. Therefore, ECG signal monitoring usually requires the ECG monitoring device to be close to the surface of the organism to collect the ECG signal of the organism. Of course, due to the characteristics of the ECG signal itself and the scenario of ECG signal monitoring, the ECG signal is very susceptible to interference from inside the organism (for example, myoelectric interference, respiratory interference, etc.) or outside the organism (for example, power frequency interference, signal pickup process, etc.). Therefore, the collected ECG signal may be accompanied by a large amount of noise or abnormal signals (caused by abnormalities in the acquisition process), causing the ECG signal to be overwhelmed by the noise and / or abnormal signals and lose some of its original characteristics. In particular, when the ECG signal carries some case characteristics, these pathological characteristics may be interfered with by noise and / or abnormal signals, resulting in a reduction in the accuracy of the relevant early warning algorithm for the pathological signal.

[0114] Therefore, an embodiment of the present application provides an electrocardiogram signal quality assessment method, which can detect normal signals in electrocardiogram signals, so that pathology-related early warnings can be performed based on the detected normal signals.

[0115] The ECG signal quality assessment algorithm provided in the embodiments of the present application can be applied to electronic devices used for ECG monitoring. Since wearable ECG monitoring devices need to be worn on a biological body when monitoring ECG signals, the wearing method of the wearable ECG monitoring device may not be standardized or may not fully meet the requirements of ECG monitoring. Therefore, the ECG signals monitored by the wearable ECG monitoring device are more susceptible to contamination by noise or abnormal signals. Therefore, the embodiments of the present application are more suitable for wearable ECG monitoring devices.

[0116] The ECG signal quality assessment method provided in the embodiment of the present application uses the peak variability feature and the peak number variability feature of the ECG signal as features for evaluating whether the ECG signal is a normal signal, an abnormal signal, or a noise signal.

[0117] The normal signal in the embodiments of this application may or may not contain pathological characteristics, depending on the physical condition of the organism itself. Abnormal signals are ECG signals collected due to abnormalities in the collection process caused by errors in the user wearing the wearable ECG monitoring device; noise signals are various noises during the test process.

[0118] It should be noted that in the embodiments of the present application, the final evaluation of a normal signal does not mean that the normal signal does not contain abnormal points and noise points; it only means that the abnormal points and / or noise points contained are not sufficient to affect the subsequent processing of the signal. Similarly, the final evaluation of a noise signal does not mean that the noise signal does not contain normal points and abnormal points. It only means that the normal points and / or abnormal points contained are relatively small, and most of them are still noise points. Similarly, the final evaluation of an abnormal signal does not mean that the abnormal signal does not contain normal points and noise points. It only means that the normal points and / or abnormal points contained are relatively small, and most of them are still abnormal points.

[0119] In specific implementations, it is necessary to set abnormal cutoff points for the peak variability feature and the peak number variability feature. Based on the relationship between the peak variability feature and the abnormal cutoff point of the peak variability feature, and the relationship between the peak number variability feature and the abnormal cutoff point of the peak number variability feature, the ECG signal is determined to be normal, abnormal, or noise.

[0120] In order to ensure that the electronic device can determine the quality (normal, abnormal, or noise) of the monitored ECG signal based on the relationship between the peak variability characteristics of the monitored ECG signal and the abnormal demarcation point of the peak variability characteristics, as well as the relationship between the peak number variability characteristics of the monitored ECG signal and the abnormal demarcation point of the peak number variability characteristics, after monitoring the ECG signal, it is necessary to determine the abnormal demarcation point of the peak variability characteristics and the abnormal demarcation point of the peak number variability characteristics in advance.

[0121] Referring to FIG. 2 , steps A1 to A5 in FIG. 2 are an example of determining an abnormal cutoff point (which may be recorded as a first threshold) of a peak variability feature and an abnormal cutoff point (which may be recorded as a second threshold) of a peak quantity variability feature.

[0122] Step A1: signal acquisition.

[0123] In the embodiments of the present application, it is necessary to learn an abnormal cutoff point for distinguishing different types of ECG signals. To learn this abnormal cutoff point, it is necessary to collect multiple raw ECG signals from multiple people and multiple scenarios. Of course, in actual applications, multiple raw ECG signals can also be obtained from a raw ECG signal sample library. The embodiments of the present application do not limit the method for obtaining raw ECG signals.

[0124] Step A2: signal segmentation.

[0125] In the specific implementation, it is necessary to perform signal segmentation in the time domain on multiple original ECG signals of multiple people and multiple scenes, and finally obtain multiple original ECG signals of fixed time length, so as to learn the abnormal demarcation point from multiple original ECG signals of fixed time length.

[0126] Step A3: signal noise reduction.

[0127] Before learning a plurality of original ECG signals of fixed duration, it is necessary to perform filtering processing on the plurality of original ECG signals of fixed duration to eliminate burrs. After the filtering processing, a plurality of ECG signal samples are obtained.

[0128] Step A4: feature construction.

[0129] In the embodiment of the present application, the peak value variability feature and the peak number variability feature of multiple electrocardiogram signal samples are used as features for distinguishing different types of signals.

[0130] Therefore, it is necessary to construct features for each ECG signal sample to obtain the peak variability feature and peak number variability feature of each ECG signal sample.

[0131] Step A5: Generate a threshold.

[0132] By counting the peak variability characteristics of multiple ECG signal samples, an abnormal demarcation point of the peak variability characteristics, i.e., a first threshold, is determined;

[0133] By counting the peak quantity variation characteristics of multiple electrocardiogram signal samples, an abnormal demarcation point of the peak variation characteristics, that is, a second threshold value, is determined.

[0134] After steps A1 to A5, two characteristic abnormality demarcation points can be determined based on multiple electrocardiogram signal samples: a first threshold value and a second threshold value.

[0135] After determining the first and second thresholds, the first and second thresholds, as well as the algorithm for generating the peak variability feature and the peak number variability feature, can be pre-installed in an electronic device used for ECG signal monitoring. The electronic device can then use the first and second thresholds, as well as the algorithm for generating the peak variability feature and the peak number variability feature, to perform a quality assessment of the ECG signal monitored by the electronic device. For details, see steps B1 to B5 in FIG. 2 .

[0136] Step B1: signal acquisition.

[0137] In an embodiment of the present application, the electrocardiogram signal can be monitored in real time by an electronic device.

[0138] Step B2: signal segmentation.

[0139] In an embodiment of the present application, the method of performing signal segmentation on the real-time monitored ECG signal is the same as step A2, and the monitored ECG signal also needs to be segmented into ECG signals of fixed duration, wherein the duration of the ECG signal segmented in step B2 is the same as the duration of the ECG signal segmented in step A2.

[0140] In practical applications, after the electronic device finishes monitoring the ECG signal of a biological body, the monitored original ECG signal can be segmented to obtain multiple ECG signals of fixed duration.

[0141] Alternatively, during the process of monitoring ECG signals of a biological body by an electronic device, each ECG signal of a fixed length is collected and the ECG signal of the fixed length is segmented, and each ECG signal of a fixed length is subsequently processed.

[0142] The embodiments of the present application do not limit the specific method to be adopted.

[0143] Step B3: signal noise reduction.

[0144] In this step, the noise reduction method for the segmented ECG signal of fixed duration is the same as that in step A3.

[0145] Step B4, feature construction.

[0146] In this step, the feature construction method of the fixed-length ECG signal after noise reduction is the same as that in step A4.

[0147] Among them, steps B2 to B4 are the process of calculating the peak variability characteristics and peak number variability characteristics of the monitored electrocardiogram signal by using an algorithm preset in the electronic device for generating the peak variability characteristics and the peak number variability characteristics.

[0148] Step B5: threshold comparison.

[0149] After obtaining the peak variability characteristics and peak signal variability characteristics of the monitored ECG signal through steps B1 to B4, the obtained peak variability characteristics are compared with the first threshold preset in the electronic device, and the obtained peak quantity variability characteristics are compared with the second threshold preset in the electronic device.

[0150] As an example, if the peak variability characteristic of the monitored ECG signal (fixed duration) is greater than a first threshold and the peak quantity variability characteristic of the monitored ECG signal is greater than a second threshold, the monitored ECG signal is an abnormal signal.

[0151] If the peak variability characteristic of the monitored ECG signal (fixed duration) is greater than or equal to the first threshold, and the peak quantity variability characteristic of the monitored ECG signal is less than or equal to the second threshold, the monitored ECG signal is a noise signal.

[0152] If the peak variability characteristic of the monitored ECG signal (fixed duration) is less than or equal to the first threshold, and the peak quantity variability characteristic of the monitored ECG signal is greater than or equal to the second threshold, the monitored ECG signal is a noise signal.

[0153] If the peak variability characteristic of the monitored ECG signal (fixed duration) is less than the first threshold and the peak quantity variability characteristic of the monitored ECG signal is less than the second threshold, the monitored ECG signal is a normal signal.

[0154] The embodiment of the present application analyzes a large number of ECG signals and finds that there are large differences between the peak values ​​and the number of peak values ​​of normal signals, abnormal signals, and noise signals of fixed duration. Therefore, the embodiment of the present application uses the peak variability characteristics and the peak number variability characteristics of ECG signals of fixed duration as features for classifying ECG signals. Then, by learning the above two features of multiple ECG signals of fixed duration, the abnormal demarcation point for classifying ECG signals is obtained. The type of the monitored ECG signal is determined by the relationship between the above two features and the abnormal demarcation point of the monitored ECG signal.

[0155] In addition, in the above embodiment, if the first threshold, the second threshold, and the algorithm for calculating the above two features are preset in the electronic device of model A, then the original ECG signal in step A1 can be collected on an electronic device of the same model A, and the consistent ECG signal can make the signal classification more accurate. Of course, after obtaining the first and second thresholds from the original ECG signals of multiple people and multiple scenes collected on the electronic device of model A 1, the first and second thresholds and the corresponding algorithm for calculating the two features can be preset on multiple electronic devices of the same model A, for example, electronic device of type A 2, electronic device of type A 3, electronic device of type A 4, etc.

[0156] Of course, in actual applications, if the ECG monitoring device and ECG monitoring method of an electronic device of another model (for example, model B) are consistent with those of the electronic device of this model (for example, model A), then the first threshold and the second threshold and the corresponding algorithm for calculating the two features can be preset in the electronic device of the other model.

[0157] In order to have a clearer understanding of the multiple steps of the above embodiment, reference may be made to the flowchart shown in FIG3 . The flowchart shown in FIG3 corresponds to steps A1 to A5 in the embodiment shown in FIG2 .

[0158] S101 , obtaining a plurality of electrocardiogram signal samples, wherein the durations of the plurality of electrocardiogram signal samples are all a first duration.

[0159] In the embodiment of the present application, the multiple electrocardiogram signal samples can be understood as multiple electrocardiogram signal samples of a fixed duration that have been obtained through steps A1 to A3 and have been filtered.

[0160] As another embodiment of the present application, acquiring multiple electrocardiogram signal samples includes:

[0161] Step A1: Acquire multiple original ECG signals.

[0162] As mentioned above, the multiple original ECG signals may be original ECG signals of multiple users and multiple scenarios collected by electronic devices of the same model (or the same ECG monitoring device and ECG monitoring method).

[0163] Step A2: performing data segmentation on the multiple original ECG signals to obtain multiple original ECG signals of a first duration.

[0164] After obtaining multiple original ECG signals, each original ECG signal needs to be segmented.

[0165] Since the signal segmentation process is used to obtain multiple original signal samples of fixed duration, original ECG signals with a total duration less than the fixed duration are discarded. One or more original ECG signals of a fixed duration are segmented from each original ECG signal with a total duration greater than or equal to the fixed duration. The fixed duration can be a first duration.

[0166] It should be noted that an original ECG signal of the first duration may be segmented from each original ECG signal whose total duration is greater than or equal to the first duration.

[0167] Alternatively, as many original ECG signals of the first duration as possible may be segmented from each original ECG signal whose total duration is greater than or equal to the first duration. Of course, the number of original ECG signals of the first duration that are segmented from each original ECG signal whose total duration is greater than or equal to the first duration may also be limited.

[0168] Based on the above segmentation method, it can be understood that among multiple original ECG signals with a total duration greater than or equal to the first duration, some original ECG signals may be segmented into an original ECG signal of the first duration, and some original ECG signals may be segmented into multiple original ECG signals of the first duration.

[0169] Regardless of the segmentation method used, multiple original ECG signals of the first duration are finally obtained. It should be noted that in the above segmentation process, there is no time domain overlap between the multiple original ECG signals of the first duration obtained by segmenting the same original ECG signal.

[0170] In the embodiment of the present application, the first time length can be t, assuming that the sampling rate of the original ECG signal is F s , then each original ECG signal of the first duration contains t×F s discrete data points.

[0171] Step A3: performing low-pass filtering and high-pass filtering on each original ECG signal of the first duration to obtain the multiple ECG signal samples.

[0172] In an embodiment of the present application, the original ECG signal of the first duration can be subjected to low-pass filtering and high-pass filtering to eliminate glitches in the original ECG signal of the first duration, thereby improving the accuracy of subsequent peak determination and peak number determination.

[0173] In practical applications, low-pass filtering may be performed first and then high-pass filtering, or high-pass filtering may be performed first and then low-pass filtering.

[0174] When low-pass filtering is performed, an α-order low-pass filter is used, where the upper frequency limit of the low-pass filter is F h .

[0175] When high-pass filtering is performed, a β-order high-pass filter is used, where the lower limit of the frequency of the high-pass filter is F l .

[0176] FIG4 is an original electrocardiogram signal of the first duration without filtering provided by an embodiment of the present application; FIG5 is an electrocardiogram signal after filtering provided by an embodiment of the present application.

[0177] As can be understood from Figures 4 and 5, the ECG signal glitches disappear after filtering. Since the features used in the present embodiment to distinguish different types of ECG signals are peak value and number of peaks, it is necessary to remove the glitches in the original ECG signal that easily interfere with the peak value and number of peaks.

[0178] The present embodiment uses high-pass filtering and low-pass filtering as examples for eliminating glitches in the original ECG signal. In actual applications, other filtering methods can also be used to eliminate glitches in the original ECG signal. The present embodiment does not limit this.

[0179] It should be noted that in actual applications, the original ECG signal that is greater than or equal to the first time length can be first segmented to obtain multiple original ECG signals of the first time length, and then each original ECG signal of the first time length can be filtered; or the original ECG signal that is greater than or equal to the first time length can be first filtered to obtain each original ECG signal that is greater than or equal to the first time length after filtering, and then each original ECG signal that is greater than or equal to the first time length after filtering can be segmented.

[0180] The embodiment of the present application does not limit the order of the above-mentioned signal segmentation and filtering processing.

[0181] To facilitate differentiation, the original ECG signal is segmented and filtered to obtain ECG signal samples. The duration of these ECG signal samples is the first duration, and these ECG signal samples are high-pass filtered and low-pass filtered.

[0182] In this embodiment of the present application, the number of obtained ECG signal samples can be recorded as S.

[0183] S102, calculating the peak value variation feature and the peak number variation feature of each electrocardiogram signal sample.

[0184] This step corresponds to the above-mentioned step A4.

[0185] The embodiment of the present application takes the calculation of the peak variability feature and the peak number variability feature of one ECG signal sample as an example. In actual applications, the method of calculating the peak variability feature and the peak number variability feature of each ECG signal sample is the same.

[0186] Step C1 : Segment an ECG signal sample to obtain multiple sample segments of the ECG signal sample.

[0187] The segmentation process in this step is also a non-overlapping segmentation performed in the time domain.

[0188] Each ECG signal sample can be divided into n sample segments that do not overlap in the time domain. The number of discrete data points contained in each sample segment is The embodiment of this application can It is recorded as k. That is, each sample segment contains k discrete data points.

[0189] Assuming that an ECG signal sample can be recorded as X, after the ECG signal sample X is divided, X=[X1|X2|...|X n ];in, in, represents the jth discrete data point in the i-th sample segment of the ECG signal sample X, 1≤j≤k.

[0190] Step C2, calculating the peak list and peak number of each sample segment.

[0191] For the i-th sample segment X i Perform the following peak search operation to obtain the peak list and peak number for each sample fragment.

[0192] First, calculate the sample fragment X iThe absolute value of the difference between each two adjacent discrete data points in the , the absolute value of the difference is obtained in, No other examples will be given.

[0193] Then, the absolute value of the difference that is greater than the absolute value of the previous difference, greater than the absolute value of the next difference, and greater than the peak search threshold is searched, and the absolute values ​​of the difference that meet the above conditions are found to form a peak list.

[0194] As an example, if and but is the peak point, where 1<γ<k-1.

[0195] The multiple peak points found constitute X i The peak list P i .X i The number of peak points in the peak list is given as X i The number of peaks S i ,.but Among them, S i As an example of peak numbers.

[0196] Of course, in practical applications, it is necessary to analyze multiple sample segments (X1 to X2) of the ECG signal sample X. n ) perform the above peak search operation to obtain the peak list and peak number of each sample segment.

[0197] Based on the above understanding, the peak list of ECG signal sample X Among them, P i Including S i The number of peak points, the number of peak points of ECG signal sample X is S=[S1,S2,...,S n ], where S i P i Indicates the number of peak points in the peak list.

[0198] See Figure 6, which shows the peak values ​​of the five sample segments obtained after dividing ECG signal sample X equally into the five segments. In Figure 6, the dividing lines represent the splitting moments when ECG signal sample X is divided into the five segments; the peak points are the peak points obtained after the peak-finding operation; and the peak-finding threshold calculation process can be described below.

[0199] As mentioned above, during the peak search operation, it is also necessary to and the peak finding threshold T M By comparison, the peak-finding threshold value for each sample segment of an ECG signal sample during the peak-finding operation is equal, so the peak-finding threshold value is related to the ECG signal sample X.

[0200] As an example, the peak-finding threshold is determined by the absolute value of the difference corresponding to the multiple sample segments of the ECG signal sample. That is, the peak-finding threshold is determined by the absolute value of the difference corresponding to the multiple sample segments X1 to X n M1 to M n Related.

[0201] First construct the sequence The sequence represents a set of absolute values ​​of differences between multiple sample segments of an electrocardiogram signal sample.

[0202] Calculate a first product of the 75th percentile of a set of absolute values ​​of differences between multiple sample segments of the electrocardiogram signal sample and a first constant; calculate a second product of the 25th percentile of a set of absolute values ​​of differences between multiple sample segments of the electrocardiogram signal sample and a second constant; calculate the difference between the first product and the second product to obtain a peak finding threshold value for the electrocardiogram signal sample X.

[0203] As an example, T M =a1*percentile(M BH ,75)-a2*percentile(M BH ,25).

[0204] Among them, percentile (M BH ,75) represents the sequence M BH The 75th percentile of the sequence M BH The elements in are arranged from small to large; then the sequence M is calculated BH The total number of elements in Q; from the sorted sequence M BH Select the 75%Q (75% multiplied by Q) element, the percentile (M BH ,75) is the selected element.

[0205] The same method can be used to obtain percentile(M BH ,25), that is, sequence M BH The elements in are arranged from small to large; then the sequence M is calculated BH The total number of elements in Q; from the sorted sequence M BH Select the 25%Q (25% multiplied by Q) element, the percentile (M BH ,25) is the selected element.

[0206] Of course, the values ​​75 and 25 in the above examples are merely examples. In practical applications, the values ​​75 and 25 can be the first product of the first quantile and the first constant, and the second product of the second quantile and the second constant. Of course, other more appropriate values ​​can be selected based on the actual ECG signal collected by the electronic device monitoring the ECG signal. These values ​​can be obtained through multiple experiments. Similarly, the first constant a1 and the second constant a2 in the above examples can also be selected differently depending on the specific situation. For example, a1 can be 4 and a2 can be 3.

[0207] Step C3: obtaining the peak variability feature of the ECG signal sample according to the peak lists of the multiple sample segments.

[0208] The above example can get a peak list of ECG signal sample X

[0209] The data feature values ​​of the peak list of the electrocardiographic signal sample X may be used as the peak variability features of the electrocardiographic signal sample.

[0210] As an example, the standard deviation and mean of the peak values ​​of multiple sample segments of the ECG signal sample are calculated;

[0211] The ratio of the standard deviation to the mean of the peak values ​​of the plurality of sample segments is calculated to obtain a peak variability feature of the electrocardiogram signal sample.

[0212] Right now

[0213] Where f1 represents the peak variability feature of the ECG signal sample X, std(P) represents the standard deviation of the peaks in the peak list P, and mean(P) represents the mean of the peaks in the peak list P.

[0214] Step C4: obtaining a peak quantity variability feature of the ECG signal sample according to the peak quantities of the plurality of sample segments.

[0215] In the above example, the number of peaks of an ECG signal sample X can be obtained as S = [S1, S2, ..., S n ].

[0216] The data characteristic value of the number of peak values ​​of the electrocardiographic signal sample X may be used as a peak value variability feature of the electrocardiographic signal sample.

[0217] As an example, the difference between the maximum value and the minimum value of the peak number of multiple sample segments of the electrocardiogram signal sample is calculated;

[0218] Calculating a median of the number of peaks of multiple sample segments of the ECG signal sample;

[0219] The ratio of the difference to the median is calculated to obtain the peak quantity variability characteristic of the ECG signal sample.

[0220] Right now

[0221] Where f2 represents the peak number variability feature of the ECG signal sample X, max(S) represents the maximum number of peaks in the peak number set S, min(S) represents the minimum number of peaks in the peak number set S, and median(S) represents the median number of peaks in the peak number set S.

[0222] In the above manner, the peak value variability feature and the peak number variability feature of each electrocardiogram signal sample of the first duration can be obtained.

[0223] S103 : Obtain the first threshold value according to the peak value variability characteristics of the plurality of electrocardiogram signal samples, and obtain the second threshold value according to the peak value quantity variability characteristics of the plurality of electrocardiogram signal samples.

[0224] This step corresponds to step A5 in the embodiment shown in FIG. 2 .

[0225] Assuming that the embodiment of the present application uses W electrocardiogram signal samples as samples for learning, the embodiment of the present application can obtain W peak value variation features and W peak number variation features based on the W electrocardiogram signal samples.

[0226] Correspondingly, the peak variability feature set

[0227] Peak number variability collection

[0228] Then, the data characteristic values ​​of the peak variability feature set are calculated to obtain the abnormal demarcation point (first threshold) of the peak variability feature.

[0229] As an example, calculating a third product of a third quantile and a third constant in the peak variability features of the plurality of electrocardiogram signal samples;

[0230] Calculating a fourth product of a fourth quantile and a fourth constant in the peak variability features of the plurality of electrocardiogram signal samples;

[0231] A difference between the third product and the fourth product is calculated to obtain the first threshold.

[0232] In the embodiment of the present application, the third quantile is the 75th quantile, the fourth quantile is the 25th quantile, the third constant is 4, and the fourth constant is 3. U1=4×percentile(F1,75)-3×percentile(F1,25).

[0233] Among them, U1 is the first threshold representing the abnormal demarcation point of the peak variability feature.

[0234] In the same way, the abnormal demarcation point (second threshold) of the peak quantity variability feature can be obtained.

[0235] As an example, calculating a fifth product of a fifth quantile and a fifth constant in the peak number variability feature of the plurality of electrocardiogram signal samples;

[0236] Calculating a sixth product of a sixth quantile and a sixth constant in the peak number variability feature of the plurality of electrocardiogram signal samples;

[0237] A difference between the fifth product and the sixth product is calculated to obtain the second threshold.

[0238] In the embodiment of the present application, the fifth quantile is the 75th quantile, the sixth quantile is the 25th quantile, the fifth constant is 4, and the sixth constant is 3. U2=4×percentile(F2,75)-3×percentile(F2,25).

[0239] Among them, U2 is the first threshold representing the abnormal demarcation point of the peak quantity variability characteristic.

[0240] In this way, the first threshold and the second threshold for classifying the type of the monitored electrocardiographic signal can be determined.

[0241] After determining the first and second thresholds, the first and second thresholds, as well as an algorithm model for calculating the peak variability feature and the peak number variability feature, are pre-installed in the electronic device. The electronic device can then perform real-time detection of ECG signals and quality assessment of the ECG signals.

[0242] 7 , which is a flow chart of an electrocardiogram signal quality assessment method according to an embodiment of the present application, is based on the flow chart shown in FIG3 , and corresponds to steps B1 to B5 in the embodiment shown in FIG2 .

[0243] Step S201: Acquire a first electrocardiogram signal.

[0244] In the embodiment of the present application, an ECG monitoring device on an electronic device can be used to measure an ECG signal, and then the electronic device processes the ECG signal to evaluate the quality of the ECG signal.

[0245] In actual applications, after the ECG signal is measured by the ECG monitoring device, the ECG monitoring device sends the measured ECG signal to an electronic device for ECG signal quality assessment, and another electronic device performs the quality assessment work, that is, the ECG signal monitoring and ECG signal quality assessment processes can be set on different electronic devices respectively, and the embodiments of the present application do not limit this.

[0246] As another embodiment of the present application, acquiring the first electrocardiogram signal includes:

[0247] Get the original ECG signal of the first duration.

[0248] The original electrocardiogram signal is subjected to low-pass filtering and high-pass filtering to obtain the first electrocardiogram signal.

[0249] In the embodiment of the present application, after the ECG monitoring device measures the ECG signal, the ECG signal is the original ECG signal; the electronic device can perform segmentation processing and filtering on the measured original ECG signal to obtain the first ECG signal. This step corresponds to steps B1 to B3.

[0250] The first ECG signal is a filtered ECG signal of a first duration. The ECG signal in the test phase has the same duration as the ECG signal in the learning phase, thereby ensuring that the quality of the ECG signal can be evaluated using the learned first and second thresholds.

[0251] See Figure 8, which is a schematic diagram of the waveform changes during the processing of four ECG signals (A, B, C, and D) provided in an embodiment of the present application. Each ECG signal shows: the original ECG signal of the first duration (located in the first row of Figure 8), the first ECG signal obtained after filtering (located in the second row of Figure 8), and the peak point after peak finding (located in the third row of Figure 8).

[0252] Step S202: Calculate the peak variability feature and the peak number variability feature of the first electrocardiogram signal.

[0253] In the embodiment of the present application, this step corresponds to step B4 in the embodiment shown in FIG. 2 .

[0254] The method of calculating the peak variability feature of the first electrocardiogram signal is the same as the method of calculating the peak variability feature of an electrocardiogram signal sample of the first duration.

[0255] Similarly, the method for calculating the peak value number variation feature of the first electrocardiogram signal is consistent with the method for calculating the peak value number variation feature of an electrocardiogram signal sample of the first duration.

[0256] As another embodiment of the present application, calculating the peak variability feature and the peak number variability feature of the first electrocardiogram signal includes:

[0257] Segmenting the first electrocardiogram signal to obtain multiple signal segments;

[0258] Calculating a peak list and a peak number for each signal segment, wherein the peak list includes N peaks, where N represents the peak number;

[0259] Obtaining a peak variability feature of the first electrocardiogram signal according to the peak lists of the plurality of signal segments;

[0260] A peak quantity variability feature of the first electrocardiogram signal is obtained according to the peak quantities of the multiple signal segments.

[0261] In the embodiment of the present application, the signal segment includes a plurality of discrete data points, and the signal segment is equivalent to a sample segment in the learning phase. Specific details can be referred to the description of the sample segment in the above embodiment, which will not be repeated here.

[0262] As another embodiment of the present application, calculating the peak list of each signal segment includes:

[0263] Calculate the absolute value of the difference between each two adjacent data points in a first signal segment, where the first signal segment is any signal segment in the signal segments, and the peak list of the first signal segment includes one or more first peaks, where the first peak is an absolute value of the difference that is greater than the previous absolute value of the difference, greater than the next absolute value of the difference, and greater than a peak finding threshold, and the peak finding threshold is determined by the absolute values ​​of the differences corresponding to multiple signal segments of the first electrocardiogram signal.

[0264] As another embodiment of the present application, the method for determining the peak-finding threshold includes:

[0265] Calculating a first product of a first quantile in a set of absolute values ​​of differences corresponding to a plurality of signal segments of the first electrocardiogram signal and a first constant;

[0266] Calculating a second product of a second quantile in a set of absolute values ​​of differences corresponding to a plurality of signal segments of the first electrocardiogram signal and a second constant;

[0267] The difference between the first product and the second product is calculated to obtain the peak finding threshold.

[0268] As another embodiment of the present application, obtaining the peak variability feature of the first electrocardiogram signal according to the peak list of the multiple signal segments includes:

[0269] Calculating a standard deviation and a mean of peak values ​​of a plurality of signal segments of the first electrocardiogram signal;

[0270] The ratio of the standard deviation to the mean of the peak values ​​of the plurality of signal segments is calculated to obtain a peak variability feature of the first electrocardiogram signal.

[0271] As another embodiment of the present application, obtaining the peak number variability feature of the first electrocardiogram signal according to the peak numbers of the multiple signal segments includes:

[0272] Calculating a first difference between a maximum value and a minimum value of the number of peaks of a plurality of signal segments of the first electrocardiogram signal;

[0273] Calculating a median of the number of peaks of a plurality of signal segments of the first electrocardiogram signal;

[0274] The ratio of the first difference to the median is calculated to obtain a peak quantity variability characteristic of the first electrocardiogram signal.

[0275] The specific implementation process of calculating the peak variability feature and the peak number variability feature of the first ECG signal can refer to the specific implementation process of calculating the peak variability feature and the peak number variability feature of an ECG signal sample in the above embodiment, which will not be repeated here.

[0276] Step S2031: If the peak variability characteristic of the first ECG signal is greater than a first threshold and the peak number variability characteristic of the first ECG signal is greater than a second threshold, the first ECG signal is an abnormal signal.

[0277] Step S2032: If the peak variability characteristic of the first ECG signal is greater than or equal to the first threshold, and the peak quantity variability characteristic of the first ECG signal is less than or equal to the second threshold, then the first ECG signal is a noise signal.

[0278] Step S2033: If the peak variability characteristic of the first ECG signal is less than or equal to the first threshold, and the peak quantity variability characteristic of the first ECG signal is greater than or equal to the second threshold, then the first ECG signal is a noise signal.

[0279] Step S2034: If the peak variability characteristic of the first ECG signal is smaller than the first threshold and the peak quantity variability characteristic of the first ECG signal is smaller than the second threshold, the first ECG signal is a normal signal.

[0280] 9 , which shows the evaluation results obtained after quality evaluation of the ECG signals A, B, C, and D after the threshold comparison in step B5 .

[0281] The two-dimensional feature plane is divided into four regions by the first threshold and the second threshold: a normal region, an abnormal region, and a noise region.

[0282] Among them, if the peak variability feature of the electrocardiogram signal B is less than the first threshold and the peak quantity variability feature of the electrocardiogram signal B is less than the second threshold, the electrocardiogram signal B is a normal signal.

[0283] If the peak variability characteristic of the electrocardiogram signal C is greater than the first threshold and the peak quantity variability characteristic of the electrocardiogram signal C is greater than the second threshold, the electrocardiogram signal C is an abnormal signal.

[0284] If the peak variability characteristic of the electrocardiographic signal A is greater than or equal to the first threshold and the peak quantity variability characteristic of the electrocardiographic signal A is less than or equal to the second threshold, the electrocardiographic signal A is a noise signal.

[0285] If the peak variability characteristic of the electrocardiographic signal D is less than or equal to the first threshold and the peak quantity variability characteristic of the electrocardiographic signal D is greater than or equal to the second threshold, the electrocardiographic signal D is a noise signal.

[0286] Of course, in actual applications, during or after ECG signal acquisition, multiple signal segments may be obtained. After evaluating these multiple signal segments, the signal segment in area B is considered a normal signal, the signal segment in area C is considered an abnormal signal, and the signal segments in areas A and D are considered noise segments. This method can accurately evaluate the classification of ECG signals.

[0287] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0288] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0289] An embodiment of the present application further provides a computer program product. When the computer program product is run on an electronic device, the electronic device can implement the steps in the above-mentioned various method embodiments.

[0290] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the first device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0291] The present application also provides a chip system, comprising a processor coupled to a memory, the processor executing a computer program stored in the memory to implement the steps of any method embodiment of the present application. The chip system can be a single chip or a chip module composed of multiple chips.

[0292] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0293] Those skilled in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0294] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for evaluating the quality of an electrocardiogram signal, characterized in that: include: Acquiring a first electrocardiogram signal; Calculating a peak variability feature and a peak number variability feature of the first electrocardiogram signal; If the peak variability characteristic of the first ECG signal is less than a first threshold value, and the peak quantity variability characteristic of the first ECG signal is less than a second threshold value, then the first ECG signal is a normal signal, wherein the first threshold value is used to indicate the abnormal demarcation point of the peak variability characteristic, and the first threshold value is determined by the peak variability characteristics of multiple ECG signal samples, and the second threshold value is used to indicate the abnormal demarcation point of the peak quantity variability characteristic, and the second threshold value is determined by the peak quantity variability characteristics of multiple ECG signal samples.

2. The method according to claim 1, wherein Acquiring the first electrocardiogram signal includes: Obtaining the original ECG signal of the first duration; The original electrocardiogram signal is filtered to obtain the first electrocardiogram signal.

3. The method according to claim 2, wherein Filtering the original electrocardiogram signal includes: The original electrocardiogram signal is subjected to low-pass filtering and high-pass filtering.

4. The method according to any one of claims 1 to 3, wherein The calculating of the peak variability feature and the peak number variability feature of the first electrocardiogram signal includes: Segmenting the first electrocardiogram signal to obtain multiple signal segments; Calculating a peak list and a peak number for each signal segment, wherein the peak list includes N peaks, where N represents the peak number; Obtaining a peak variability feature of the first electrocardiogram signal according to the peak lists of the plurality of signal segments; A peak quantity variability feature of the first electrocardiogram signal is obtained according to the peak quantities of the multiple signal segments.

5. The method according to claim 4, wherein The signal segment includes a plurality of discrete data points, and calculating a peak list for each signal segment includes: Calculate the absolute value of the difference between each two adjacent data points in a first signal segment, where the first signal segment is any signal segment in the signal segments, and the peak list of the first signal segment includes one or more first peaks, where the first peak is an absolute value of the difference that is greater than the previous absolute value of the difference, greater than the next absolute value of the difference, and greater than a peak finding threshold, and the peak finding threshold is determined by the absolute values ​​of the differences corresponding to multiple signal segments of the first electrocardiogram signal.

6. The method according to claim 5, wherein The method for determining the peak-finding threshold comprises: Calculating a first product of a first quantile in a set of absolute values ​​of differences corresponding to a plurality of signal segments of the first electrocardiogram signal and a first constant; Calculating a second product of a second quantile in a set of absolute values ​​of differences corresponding to a plurality of signal segments of the first electrocardiogram signal and a second constant; The difference between the first product and the second product is calculated to obtain the peak finding threshold.

7. The method according to any one of claims 4 to 6, characterized in that The step of obtaining the peak variability feature of the first electrocardiogram signal according to the peak list of the plurality of signal segments includes: Calculating a standard deviation and a mean of peak values ​​of a plurality of signal segments of the first electrocardiogram signal; The ratio of the standard deviation to the mean of the peak values ​​of the plurality of signal segments is calculated to obtain a peak variability feature of the first electrocardiogram signal.

8. The method according to any one of claims 4 to 6, characterized in that The step of obtaining the peak quantity variability feature of the first electrocardiogram signal according to the peak quantities of the plurality of signal segments includes: Calculating a first difference between a maximum value and a minimum value of the number of peaks of a plurality of signal segments of the first electrocardiogram signal; Calculating a median of the number of peaks of a plurality of signal segments of the first electrocardiogram signal; The ratio of the first difference to the median is calculated to obtain a peak quantity variability characteristic of the first electrocardiogram signal.

9. The method according to any one of claims 1 to 8, wherein The first threshold and the second threshold are determined in the following manner: Acquire multiple electrocardiogram signal samples, where the durations of the multiple electrocardiogram signal samples are all the first duration; Calculating the peak variability feature and the peak number variability feature of each of the electrocardiogram signal samples; Obtaining the first threshold value according to the peak variability characteristics of the plurality of electrocardiogram signal samples; A second threshold is obtained according to a peak quantity variability characteristic of the plurality of electrocardiogram signal samples.

10. The method according to claim 9, wherein Obtaining the first threshold according to the peak variability characteristics of the plurality of electrocardiogram signal samples includes: Calculating a third product of a third quantile and a third constant in the peak variability features of the plurality of electrocardiogram signal samples; Calculating a fourth product of a fourth quantile and a fourth constant in the peak variability features of the plurality of electrocardiogram signal samples; A difference between the third product and the fourth product is calculated to obtain the first threshold.

11. The method according to claim 9, wherein Obtaining the second threshold according to the peak quantity variability characteristics of the plurality of electrocardiogram signal samples includes: Calculating a fifth product of a fifth quantile and a fifth constant in the peak number variability feature of the plurality of electrocardiogram signal samples; Calculating a sixth product of a sixth quantile and a sixth constant in the peak number variability feature of the plurality of electrocardiogram signal samples; A difference between the fifth product and the sixth product is calculated to obtain the second threshold.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: If the peak variability characteristic of the first electrocardiogram signal is greater than the first threshold value, and the peak number variability characteristic of the first electrocardiogram signal is greater than the second threshold value, then the first electrocardiogram signal is an abnormal signal; If the peak variability characteristic of the first ECG signal is greater than or equal to the first threshold, and the peak quantity variability characteristic of the first ECG signal is less than or equal to the second threshold, then the first ECG signal is a noise signal; If the peak variability characteristic of the first electrocardiogram signal is less than or equal to the first threshold, and the peak quantity variability characteristic of the first electrocardiogram signal is greater than or equal to the second threshold, then the first electrocardiogram signal is a noise signal.

13. The method according to any one of claims 9 to 12, characterized in that Acquiring multiple electrocardiogram signal samples includes: Acquire multiple original ECG signals; Performing data segmentation on the multiple original ECG signals to obtain multiple original ECG signals of a first duration; Low-pass filtering and high-pass filtering are performed on each original electrocardiogram signal of the first duration to obtain the multiple electrocardiogram signal samples.

14. The method according to any one of claims 9 to 12, characterized in that The method of calculating the peak variability feature of each of the electrocardiogram signal samples is the same as the method of calculating the peak variability feature of the first electrocardiogram signal; The method of calculating the peak value number variability feature of each electrocardiogram signal sample is the same as the method of calculating the peak value number variability feature of the first electrocardiogram signal.

15. An electronic device, characterized in that: The electronic device includes a processor, and the processor is configured to run a computer program stored in a memory, so that the electronic device implements the method according to any one of claims 1 to 14.

16. A chip system, characterized in that: The chip system includes a processor coupled to a memory, and the processor executes a computer program stored in the memory to implement the method according to any one of claims 1 to 14.

Images