A signal recognition method, apparatus, computer device, and storage medium

Abstract

This invention discloses a signal recognition method, apparatus, computer device, and storage medium. The method includes: acquiring a signal indicating ventricular fibrillation in a human body; performing time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points; and identifying the type of the signal based on the frequency content of different frequency bands corresponding to each time point, wherein the type includes non-shockable ventricular tachycardia signals and ventricular fibrillation signals. In this technical solution, by utilizing the different frequency content of non-shockable ventricular tachycardia signals and ventricular fibrillation signals, the two signals can be effectively distinguished, thereby reducing the probability of misidentification of non-shockable ventricular tachycardia signals.

Description

Technical Field

[0001] This invention relates to the field of signal processing technology, and in particular to a signal recognition method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Sudden cardiac death (SCD) refers to unexpected death caused by cardiac reasons. It occurs within one hour of the onset of acute symptoms, leading to cardiac arrest, a sudden interruption of blood flow to the brain, and loss of consciousness. Patients can survive with timely treatment; otherwise, they will die biologically. Ventricular fibrillation (VFiB) is a malignant arrhythmia caused by multiple abnormal excitation foci in the ventricles. It is the main cause of SCD. When VFiB occurs, defibrillation is the only effective treatment as quickly as possible. During the identification of VFiB, some non-shockable signals may lead to false positives. Such false positives inevitably cause irreversible harm. Non-shockable ventricular tachycardia accounts for a large proportion of false positives; therefore, reducing the false positive rate of non-shockable ventricular tachycardia can greatly improve the effectiveness of defibrillation. Summary of the Invention

[0003] The main objective of this invention is to provide a signal recognition method, device, computer equipment, and storage medium that can solve the problem of misidentification of non-electric shock ventricular tachycardia signals in the prior art.

[0004] To achieve the above objectives, the first aspect of the present invention provides a signal recognition method, the method comprising:

[0005] Acquire signals when ventricular fibrillation occurs in the human body;

[0006] Perform time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points;

[0007] Based on the frequency content of different frequency bands corresponding to each time point, the type of the signal is identified, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal.

[0008] In conjunction with the first aspect, in one possible implementation, identifying the type of the signal based on the frequency content of different frequency bands corresponding to each time point includes: calculating a first standard deviation between the frequency content of different frequency bands corresponding to each time point based on the frequency content of different frequency bands corresponding to each time point; and identifying the type of the signal based on the first standard deviation corresponding to each time point.

[0009] In conjunction with the first aspect, in one possible implementation, identifying the type of the signal based on the first standard deviation corresponding to each time point includes: calculating a second standard deviation between the first standard deviations corresponding to each time point, and calculating the average peak spacing and average trough spacing of the signal; identifying the type of the signal based on the second standard deviation, the average peak spacing, and the average trough spacing.

[0010] In conjunction with the first aspect, in one possible implementation, identifying the type of the signal based on the second standard deviation, the average peak spacing, and the average trough spacing includes: identifying the type of the signal by comparing the second standard deviation with a standard deviation threshold, comparing the average peak spacing with a peak spacing threshold, and comparing the average trough spacing with a trough spacing threshold.

[0011] In conjunction with the first aspect, in one possible implementation, the identification of the signal type based on the comparison of the second standard deviation with a standard deviation threshold, the comparison of the average peak spacing with a peak spacing threshold, and the comparison of the average trough spacing with a trough spacing threshold includes: when the average trough spacing is not less than the average trough spacing threshold, the average peak spacing is greater than the average peak spacing threshold, and the standard deviation between the standard deviations corresponding to each time point is less than the standard deviation threshold, then the signal is a shockable ventricular tachycardia signal; when the average trough spacing is less than the average trough spacing threshold, and the standard deviation between the standard deviations corresponding to each time point is less than the standard deviation threshold, then the signal is a ventricular fibrillation signal.

[0012] In conjunction with the first aspect, in one possible implementation, the above-mentioned calculation of the first standard deviation between the frequency contents of different frequency segments corresponding to each time point based on the frequency contents of different frequency segments corresponding to each time point includes: taking the frequency contents of different frequency segments corresponding to the i-th time point as the i-th row element of the matrix to obtain the matrix; calculating the standard deviation between each row element of the matrix to obtain N first standard deviations, wherein the N first standard deviations correspond to the standard deviations between the frequency contents of different frequency segments corresponding to different time points.

[0013] In conjunction with the first aspect, in one possible implementation, the above-mentioned calculation of the second standard deviation between the first standard deviations corresponding to each time point based on the first standard deviation corresponding to each time point includes: using the first standard deviation corresponding to each time point as elements of a vector to form a vector; calculating the standard deviation between each element in the vector to obtain the second standard deviation.

[0014] To achieve the above objectives, a second aspect of the present invention provides a signal recognition device, the device comprising:

[0015] Acquisition module: Used to acquire signals when ventricular fibrillation occurs in a human body;

[0016] Analysis module: used to perform time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points;

[0017] Identification module: used to identify the type of the signal based on the frequency content of different frequency bands corresponding to each time point, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal.

[0018] To achieve the above objectives, a third aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0019] Acquire signals when ventricular fibrillation occurs in the human body;

[0020] Perform time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points;

[0021] Based on the frequency content of different frequency bands corresponding to each time point, the type of the signal is identified, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal.

[0022] To achieve the above objectives, a fourth aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor causes the processor to perform the following steps:

[0023] Acquire signals when ventricular fibrillation occurs in the human body;

[0024] Perform time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points;

[0025] Based on the frequency content of different frequency bands corresponding to each time point, the type of the signal is identified, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal.

[0026] The embodiments of the present invention have the following beneficial effects:

[0027] This invention provides a signal differentiation method. By performing time-frequency analysis on the signal, the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range is obtained. A first standard deviation is calculated between the frequency content of different frequency bands corresponding to each time point, and a second standard deviation is calculated between the first standard deviations. The average peak spacing and average trough spacing of the signal are also calculated. Based on comparisons of the second standard deviation with standard deviation thresholds, the average peak spacing with peak spacing thresholds, and the average trough spacing with trough spacing thresholds, the method differentiates the signal from a non-shockable ventricular tachycardia (VT) signal to a ventricular fibrillation (VFiB) signal. In this technical solution, by leveraging the different frequency content of VT and VFiB signals, this method can effectively differentiate between them, thereby reducing the probability of misidentification of VT signals. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] in:

[0030] Figure 1 This is a flowchart illustrating a signal recognition method according to an embodiment of the present invention;

[0031] Figure 2 This is a structural block diagram of a signal recognition device according to an embodiment of the present invention;

[0032] Figure 3 This is a structural block diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] This embodiment provides a signal recognition method applicable to scenarios where ventricular fibrillation signals are identified during defibrillation of a human body, avoiding misidentification of non-shockable ventricular tachycardia signals as ventricular fibrillation signals.

[0035] Reference Figure 1 ,like Figure 1This is a flowchart illustrating a signal recognition method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the specific steps of this method are as follows:

[0036] Step S101: Obtain the signal when ventricular fibrillation occurs in the human body.

[0037] The system acquires the signal when ventricular fibrillation occurs in the human body. This signal is initially identified as a ventricular fibrillation signal. In this embodiment, the signal is further identified and judged to determine its final type. Since ventricular fibrillation signals and unshockable ventricular tachycardia signals have time-frequency characteristics, this embodiment identifies whether the signal is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal based on the frequency content of the unshockable ventricular tachycardia signal and the ventricular fibrillation signal.

[0038] Step S102: Perform time-frequency analysis on the signal to obtain the frequency content of different frequency segments corresponding to the i-th time point within the preset Hertz range.

[0039] Where i ranges from 1 to N, and N is the total number of time points.

[0040] Specifically, time-frequency analysis is performed on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range. Here, the preceding and following time points are consecutive. For example, the preset Hertz can be 1–10 Hz, and N can be 12. Time-frequency analysis of the signal yields the frequency content of different time periods within 12 seconds within the 1–10 Hz range. Specifically, 1–10 Hz is divided into 1–4 Hz, 4–6 Hz, and 6–10 Hz. Then, the frequency content of 1–4 Hz, 4–6 Hz, and 6–10 Hz at the 1st second is obtained; the frequency content of 1–4 Hz, 4–6 Hz, and 6–10 Hz at the 2nd second is obtained; the frequency content of 1–4 Hz, 4–6 Hz, and 6–10 Hz at the 3rd second is obtained; and so on, until the frequency content of 1–4 Hz, 4–6 Hz, and 6–10 Hz at the 12th second is obtained.

[0041] Step S103: Identify the type of signal based on the frequency content of different frequency bands corresponding to each time point.

[0042] Among them, the type is either an unshockable ventricular tachycardia signal or a ventricular fibrillation signal.

[0043] The signal type is identified based on the frequency content of different frequency bands corresponding to each time point, as shown in steps S201-S202:

[0044] Step S201: Based on the frequency content of different frequency bands corresponding to each time point, calculate the first standard deviation between the frequency content of different frequency bands corresponding to each time point.

[0045] Calculate the standard deviation between the frequency content of different frequency bands corresponding to each time point to obtain the first standard deviation for each time point. For example, when performing time-frequency analysis on a signal, obtain the frequency content of different time periods within 12 seconds in the range of 1–10 Hz. Specifically, obtain the frequency content of 1–4 Hz as a1, 4–6 Hz as a2, and 6–10 Hz as a3 at the 1st second; obtain the frequency content of 1–4 Hz as b1, 4–6 Hz as b2, and 6–10 Hz as b3 at the 2nd second; obtain the frequency content of 1–4 Hz as c at the 3rd second. 1. The frequency content of 4-6Hz is c2 and the frequency content of 6-10Hz is c3; and so on, until the 12th second is obtained, the frequency content of 1-4Hz is L1, the frequency content of 4-6Hz is L2 and the frequency content of 6-10Hz is L3. Then calculate the standard deviation between a1, a2 and a3 to obtain the first standard deviation A, calculate the standard deviation between b1, b2 and b3 to obtain the first standard deviation B, calculate the standard deviation between c1, c2 and c3 to obtain the first standard deviation C, and so on, until the standard deviation between L1, L2 and L3 is calculated to obtain the first standard deviation L.

[0046] In one possible implementation, the first standard deviation between the frequency contents of different frequency bands at each time point is calculated based on the frequency contents of different frequency bands at each time point. This can be achieved as follows:

[0047] The matrix is ​​obtained by taking the frequency content of different frequency bands corresponding to the i-th time point as the i-th row element. For example, if N is 12, the first time point is the 1s. At the 1s, the frequency content of 1-4Hz is a1, the frequency content of 4-6Hz is a2, and the frequency content of 6-10Hz is a3. Then, a1, a2, and a3 are arranged in order as the first row element of the matrix. At the second time point is the 2s, the frequency content of 1-4Hz is b1, the frequency content of 4-6Hz is b2, and the frequency content of 6-10Hz is b3. Then, b1, b2, and b3 are arranged in order as the second row element of the matrix. At the third time point is the 3s, the frequency content of 1-4Hz is c1, the frequency content of 4-6Hz is c2, and the frequency content of 6-10Hz is c3. Then, c1, c2, and c3 are arranged in order as the second row element of the matrix, and so on, to form the matrix.

[0048] Then, by calculating the standard deviation between the elements in each row of the matrix, we can obtain N first standard deviations. As shown above, the N first standard deviations can correspond to the standard deviations between the frequency contents of different frequency bands at different time points.

[0049] Step S202: Identify the type of the signal based on the first standard deviation corresponding to each time point.

[0050] The type of the signal is identified based on the first standard deviation corresponding to each time point, as shown in steps S301-S302:

[0051] Step S301: Based on the first standard deviation corresponding to each time point, calculate the second standard deviation between the first standard deviations corresponding to each time point, and calculate the average peak spacing and average trough spacing of the signal.

[0052] Calculate the second standard deviation between the first standard deviations at each time point. For example, if there are 12 first standard deviations, namely first standard deviation A, first standard deviation B, first standard deviation C, ..., first standard deviation L, calculate the standard deviation between first standard deviation A, first standard deviation B, first standard deviation C, ..., first standard deviation L to obtain the second standard deviation.

[0053] In one possible implementation, the second standard deviation is calculated based on the first standard deviation at each time point, which can also be achieved in the following way:

[0054] By taking the first standard deviation corresponding to each time point as an element of a vector in chronological order, and calculating the standard deviation between each element in the vector, we can obtain the second standard deviation.

[0055] Step S302: Identify the type of the signal based on the second standard deviation, the average spacing between the peaks, and the average spacing between the troughs.

[0056] The signal type is identified by comparing the second standard deviation with the standard deviation threshold, the average peak spacing with the average peak spacing threshold, and the average trough spacing with the average trough spacing threshold. The standard deviation threshold, average peak spacing threshold, and average trough spacing threshold can be determined empirically, for example, by conducting experiments on signals under similar conditions to determine each threshold.

[0057] Specifically, firstly, the average peak spacing is compared with the average peak spacing threshold Vale_Thd. If the average peak spacing is less than the average peak spacing threshold Vale_Thd, then the second standard deviation is compared with the standard deviation threshold STD_THD. If the second standard deviation is less than the standard deviation threshold STD_THD, then the signal is determined to be a ventricular fibrillation signal. If the average peak spacing is not less than the average peak spacing threshold Vale_Thd, then the average peak spacing is compared with the average peak spacing threshold Peak_Thd. If the average peak spacing is greater than the average peak spacing threshold Peak_Thd, then the second standard deviation is compared with the standard deviation threshold STD_THD. If the second standard deviation is less than the standard deviation threshold STD_THD, then the signal is determined to be an unshockable ventricular tachycardia signal.

[0058] If the average peak spacing is less than the peak spacing threshold Vale_Thd, and the second standard deviation is not less than the standard deviation threshold STD_THD, then the signal is determined to be another type of non-shockable signal. If the average peak spacing is not less than the peak spacing threshold Vale_Thd, and the average peak spacing is not greater than the peak spacing threshold Peak_Thd, then the signal is determined to be another type of non-shockable signal. If the average peak spacing is not less than the peak spacing threshold Vale_Thd, and the average peak spacing is greater than the peak spacing threshold Peak_Thd, and the second standard deviation is not less than the standard deviation threshold STD_THD, then the signal is determined to be another type of non-shockable signal.

[0059] Based on the above method, by performing time-frequency analysis on the signal, the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range is obtained. The first standard deviation between the frequency content of different frequency bands corresponding to each time point is calculated, and the second standard deviation between the first standard deviations is calculated. The average peak spacing and average trough spacing of the signal are also calculated. By comparing the second standard deviation with a standard deviation threshold, comparing the average peak spacing with a peak spacing threshold, and comparing the average trough spacing with a trough spacing threshold, the signal can be distinguished as either a shockable ventricular tachycardia signal or a ventricular fibrillation signal. In this technical solution, by utilizing the different frequency content characteristics of shockable ventricular tachycardia signals and ventricular fibrillation signals, the frequency content of shockable ventricular tachycardia signals and ventricular fibrillation signals can be effectively distinguished, thereby reducing the probability of misidentification of shockable ventricular tachycardia signals.

[0060] To better implement the above method, embodiments of the present invention provide a signal recognition device, referring to... Figure 2 , Figure 2 This is a structural block diagram of a signal recognition device provided in an embodiment of the present invention, such as... Figure 2 As shown, the device 20 specifically includes:

[0061] Acquisition module 201: Used to acquire signals when ventricular fibrillation occurs in a human body.

[0062] Analysis module 202: used to perform time-frequency analysis on the signal to obtain the frequency content of different frequency segments corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points.

[0063] Identification module 203: used to identify the type of the signal based on the frequency content of different frequency bands corresponding to each time point, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal.

[0064] In one possible design, the identification module 203 is specifically used to: calculate the first standard deviation between the frequency contents of different frequency bands corresponding to each time point based on the frequency contents of different frequency bands corresponding to each time point; and identify the type of the signal based on the first standard deviation corresponding to each time point.

[0065] In one possible design, the identification module 203 is specifically used to: calculate the second standard deviation between the first standard deviations corresponding to each time point based on the first standard deviation corresponding to each time point, and calculate the average peak spacing and average trough spacing of the signal; and identify the type of the signal based on the second standard deviation, the average peak spacing and the average trough spacing.

[0066] In one possible design, the identification module 203 is specifically used to: identify the type of the signal based on the comparison of the second standard deviation with the standard deviation threshold, the comparison of the average peak spacing with the average peak spacing threshold, and the comparison of the average trough spacing with the average trough spacing threshold.

[0067] In one possible design, the identification module 203 is specifically used to: when the average trough spacing is not less than the average trough spacing threshold, the average peak spacing is greater than the average peak spacing threshold, and the standard deviation between the standard deviations corresponding to each time point is less than the standard deviation threshold, then the signal is a non-shockable ventricular tachycardia signal; when the average trough spacing is less than the average trough spacing threshold, and the standard deviation between the standard deviations corresponding to each time point is less than the standard deviation threshold, then the signal is a ventricular fibrillation signal.

[0068] In one possible design, the identification module 203 is specifically used to: take the frequency content of different frequency bands corresponding to the i-th time point as the i-th row element of the matrix to obtain the matrix; calculate the standard deviation between each row element of the matrix to obtain N first standard deviations, wherein the N first standard deviations correspond to the standard deviations between the frequency content of different frequency bands corresponding to different time points.

[0069] In one possible design, the identification module 203 is specifically used to: use the first standard deviation corresponding to each time point as elements of a vector to form a vector; calculate the standard deviation between each element in the vector to obtain the second standard deviation.

[0070] Based on the above device, by performing time-frequency analysis on the signal, the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range is obtained. The first standard deviation between the frequency content of different frequency bands corresponding to each time point is calculated, and the second standard deviation between the first standard deviations is calculated. The average peak spacing and average trough spacing of the signal are also calculated. By comparing the second standard deviation with a standard deviation threshold, comparing the average peak spacing with a peak spacing threshold, and comparing the average trough spacing with a trough spacing threshold, the signal can be distinguished as either a non-shockable ventricular tachycardia signal or a ventricular fibrillation signal. In this technical solution, by utilizing the different frequency content characteristics of non-shockable ventricular tachycardia signals and ventricular fibrillation signals, the frequency content of non-shockable ventricular tachycardia signals and ventricular fibrillation signals can be effectively distinguished, thereby reducing the probability of misidentification of non-shockable ventricular tachycardia signals.

[0071] Figure 3 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 3 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program causes the processor to perform all the steps of the above-described method. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform all the steps of the above-described method. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0072] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the aforementioned method.

[0073] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps of the aforementioned method.

[0074] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0075] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0076] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A signal recognition method, characterized in that, The method includes: Acquire signals when ventricular fibrillation occurs in the human body; Perform time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points; Based on the frequency content of different frequency bands corresponding to each time point, the type of the signal is identified, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal; in, The method of identifying the type of signal based on the frequency content of different frequency bands corresponding to each time point includes: Based on the frequency content of different frequency bands corresponding to each time point, the first standard deviation between the frequency content of different frequency bands corresponding to each time point is calculated. The type of the signal is identified based on the first standard deviation corresponding to each time point; The step of identifying the type of the signal based on the first standard deviation corresponding to each time point includes: Based on the first standard deviation corresponding to each time point, the second standard deviation between the first standard deviations corresponding to each time point is calculated, and the average peak spacing and average trough spacing of the signal are calculated. The type of signal is identified based on the second standard deviation, the average spacing between the peaks, and the average spacing between the troughs.

2. The method according to claim 1, characterized in that, The step of identifying the type of the signal based on the second standard deviation, the average peak spacing, and the average trough spacing includes: The type of signal is identified by comparing the second standard deviation with the standard deviation threshold, the average peak spacing with the average peak spacing threshold, and the average trough spacing with the average trough spacing threshold.

3. The method according to claim 2, characterized in that, The step of identifying the type of signal based on the comparison of the second standard deviation with a standard deviation threshold, the comparison of the average peak spacing with a peak spacing threshold, and the comparison of the average trough spacing with a trough spacing threshold includes: When the average trough spacing is not less than the average trough spacing threshold, the average peak spacing is greater than the average peak spacing threshold, and the standard deviation between the standard deviations corresponding to each time point is less than the standard deviation threshold, then the signal is a non-shockable ventricular tachycardia signal. When the average trough spacing is less than the average trough spacing threshold, and the standard deviation between the standard deviations corresponding to each time point is less than the standard deviation threshold, then the signal is a ventricular fibrillation signal.

4. The method according to claim 1, characterized in that, The calculation of the first standard deviation between the frequency contents of different frequency bands at each time point, based on the frequency contents of different frequency bands at each time point, includes: The matrix is ​​obtained by taking the frequency content of different frequency bands corresponding to the i-th time point as the i-th row element; Calculate the standard deviation between each row of elements in the matrix to obtain N first standard deviations, where the N first standard deviations correspond to the standard deviations between the frequency contents of different frequency bands at different time points.

5. The method according to claim 1, characterized in that, The step of calculating the second standard deviation between the first standard deviations corresponding to each time point, based on the first standard deviation corresponding to each time point, includes: The first standard deviation corresponding to each time point is used as the element of the vector to form a vector; Calculate the standard deviation between each element in the vector to obtain the second standard deviation.

6. A signal recognition device, characterized in that, The device includes: Acquisition module: Used to acquire signals when ventricular fibrillation occurs in a human body; Analysis module: used to perform time-frequency analysis on the signal to obtain the frequency content of different frequency bands corresponding to the i-th time point within a preset Hertz range; where i ranges from 1 to N, and N is the total number of time points; Identification module: used to identify the type of the signal based on the frequency content of different frequency bands corresponding to each time point, wherein the type is an unshockable ventricular tachycardia signal or a ventricular fibrillation signal; in, The method of identifying the type of signal based on the frequency content of different frequency bands corresponding to each time point includes: Based on the frequency content of different frequency bands corresponding to each time point, the first standard deviation between the frequency content of different frequency bands corresponding to each time point is calculated. The type of the signal is identified based on the first standard deviation corresponding to each time point; The step of identifying the type of the signal based on the first standard deviation corresponding to each time point includes: Based on the first standard deviation corresponding to each time point, the second standard deviation between the first standard deviations corresponding to each time point is calculated, and the average peak spacing and average trough spacing of the signal are calculated. The type of signal is identified based on the second standard deviation, the average spacing between the peaks, and the average spacing between the troughs.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the processor performs the steps of the method as described in any one of claims 1 to 5.

8. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 5.

Images