Electrocardiosignal detection method and apparatus, computer device, and storage medium

Abstract

The present application relates to an electrocardiosignal detection method and apparatus and a computer device. The method comprises: obtaining a target electrocardiogram type signal and a current noise signal of a current electrocardiosignal according to a preset signal detection threshold; calculating a signal change degree based on a signal feature of the target electrocardiogram type signal; generating a signal verification feature when the signal change degree is within a preset change degree range, and obtaining a target signal detection threshold based on an amplitude feature of the target electrocardiogram type signal and a signal value of the current noise signal; detecting an electrocardiosignal to be detected according to the target signal detection threshold and the signal verification feature; calculating an updated signal detection threshold based on the target signal detection threshold and a noise signal of the electrocardiosignal to be detected when a signal feature to be detected is matched with the signal verification feature; and calculating an updated signal detection threshold based on an amplitude feature of the electrocardiosignal to be detected when the signal feature to be detected is not matched with the signal verification feature. By adopting the method, the accuracy of electrocardiosignal detection can be improved.

Description

ECG signal detection method, device, computer equipment and storage medium Technical Field

[0001] The present application relates to the field of signal processing technology, and in particular to an electrocardiogram signal detection method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] The intra-aortic balloon pump (IABP) is a medical device widely used to assist patients with heart failure. It consists of a control unit, a monitoring system, connecting tubing, and a balloon. The balloon is placed within the aorta, typically in the descending aorta in the chest. The control unit primarily controls the solenoid valves for the inflation and deflation pathways. Under real-time monitoring of the ECG (electrocardiogram), the control unit opens the solenoid valves for the inflation and deflation pathways according to the heart's rhythm to control the expansion and contraction of the balloon. The R wave in the ECG represents the heart's contraction and marks the moment of cardiac pacing.

[0003] However, because the physical movement of gas between the connecting tube and the balloon requires a minimum amount of time to fully inflate and deflate, when the heart rate is too fast, the balloon's inflation and deflation rate cannot keep up with the patient's cardiac cycle. If the balloon remains inflated when the ventricles begin to contract, it can cause increased pressure in the aorta, increasing the workload on the heart and even leading to serious problems such as aortic rupture. Therefore, to avoid the above problems, it is necessary to accurately detect the R-wave signal in the ECG signal to synchronize balloon inflation and deflation with the heart. Currently, there are algorithms for detecting R-waves, such as template matching. However, template matching methods are easily interfered with by high-frequency noise, resulting in low accuracy in R-wave signal detection. Summary of the Invention

[0004] Based on this, it is necessary to provide an electrocardiogram signal detection method, device, computer equipment, computer-readable storage medium and computer program product that can achieve early detection of R waves while maintaining the detection accuracy of R-wave electrocardiogram signals in response to the above technical problems.

[0005] In a first aspect, the present application provides an electrocardiogram (ECG) signal detection method, comprising:

[0006] Acquire a current ECG signal corresponding to a current time period, divide the current ECG signal according to a preset signal detection threshold, and obtain a target ECG type signal and a current noise signal corresponding to the current ECG signal, wherein the preset signal detection threshold is obtained by using an amplitude characteristic of a historical ECG signal according to a signal type of the historical ECG signal when a degree of change of a historical signal corresponding to the historical ECG signal is not within a preset change range;

[0007] Extract the signal features corresponding to the target ECG type signal, calculate the signal change based on the signal features, and obtain the signal change degree corresponding to the target ECG type signal in the current ECG signal;

[0008] When the signal change degree is within the preset change degree range, a signal verification feature corresponding to the target ECG type signal is generated according to the signal feature, and a target signal detection threshold corresponding to the target ECG type signal is obtained based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal;

[0009] Acquire the ECG signal to be detected, perform target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and signal verification characteristics, and obtain the ECG signal detection result;

[0010] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, the signal detection threshold is updated based on the target signal detection threshold and the noise signal of the ECG signal to be detected;

[0011] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature, an updated signal detection threshold is calculated based on the amplitude feature corresponding to the ECG signal to be detected, and the updated signal detection threshold is used to perform target ECG type signal detection.

[0012] In a second aspect, the present application further provides an electrocardiogram signal detection device, comprising:

[0013] a signal acquisition module for acquiring a current ECG signal corresponding to a current time period, dividing the current ECG signal according to a preset signal detection threshold, and obtaining a target ECG type signal and a current noise signal corresponding to the current ECG signal, wherein the preset signal detection threshold is obtained by using an amplitude characteristic of a historical ECG signal according to a signal type of the historical ECG signal when a change degree of a historical signal corresponding to the historical ECG signal is not within a preset change degree range;

[0014] A feature extraction module is used to extract the signal features corresponding to the target ECG type signal, perform signal change calculation based on the signal features, and obtain the signal change degree corresponding to the target ECG type signal in the current ECG signal;

[0015] A threshold generation module is used to generate a signal verification feature corresponding to the target ECG type signal according to the signal feature when the signal change degree is within a preset change degree range, and obtain a target signal detection threshold corresponding to the target ECG type signal based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal;

[0016] The signal detection module is used to obtain the ECG signal to be detected, perform target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and signal verification characteristics, and obtain the ECG signal detection result;

[0017] a feature matching module, configured to calculate and update a signal detection threshold based on a target signal detection threshold and a noise signal of the ECG signal to be detected when a feature of the signal to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches a signal verification feature;

[0018] The feature mismatch module is used to calculate and update the signal detection threshold based on the amplitude feature corresponding to the ECG signal to be detected when the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature. The updated signal detection threshold is used to perform target ECG type signal detection.

[0019] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0020] Acquire a current ECG signal corresponding to a current time period, divide the current ECG signal according to a preset signal detection threshold, and obtain a target ECG type signal and a current noise signal corresponding to the current ECG signal, wherein the preset signal detection threshold is obtained by using an amplitude characteristic of a historical ECG signal according to a signal type of the historical ECG signal when a degree of change of a historical signal corresponding to the historical ECG signal is not within a preset change range;

[0021] Extract the signal features corresponding to the target ECG type signal, calculate the signal change based on the signal features, and obtain the signal change degree corresponding to the target ECG type signal in the current ECG signal;

[0022] When the signal change degree is within the preset change degree range, a signal verification feature corresponding to the target ECG type signal is generated according to the signal feature, and a target signal detection threshold corresponding to the target ECG type signal is obtained based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal;

[0023] Acquire the ECG signal to be detected, perform target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and signal verification characteristics, and obtain the ECG signal detection result;

[0024] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, the signal detection threshold is updated based on the target signal detection threshold and the noise signal of the ECG signal to be detected;

[0025] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature, an updated signal detection threshold is calculated based on the amplitude feature corresponding to the ECG signal to be detected, and the updated signal detection threshold is used to perform target ECG type signal detection.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0027] Acquire a current ECG signal corresponding to a current time period, divide the current ECG signal according to a preset signal detection threshold, and obtain a target ECG type signal and a current noise signal corresponding to the current ECG signal, wherein the preset signal detection threshold is obtained by using an amplitude characteristic of a historical ECG signal according to a signal type of the historical ECG signal when a degree of change of a historical signal corresponding to the historical ECG signal is not within a preset change range;

[0028] Extract the signal features corresponding to the target ECG type signal, calculate the signal change based on the signal features, and obtain the signal change degree corresponding to the target ECG type signal in the current ECG signal;

[0029] When the signal change degree is within the preset change degree range, a signal verification feature corresponding to the target ECG type signal is generated according to the signal feature, and a target signal detection threshold corresponding to the target ECG type signal is obtained based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal;

[0030] Acquire the ECG signal to be detected, perform target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and signal verification characteristics, and obtain the ECG signal detection result;

[0031] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, the signal detection threshold is updated based on the target signal detection threshold and the noise signal of the ECG signal to be detected;

[0032] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature, an updated signal detection threshold is calculated based on the amplitude feature corresponding to the ECG signal to be detected, and the updated signal detection threshold is used to perform target ECG type signal detection.

[0033] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0034] Acquire a current ECG signal corresponding to a current time period, divide the current ECG signal according to a preset signal detection threshold, and obtain a target ECG type signal and a current noise signal corresponding to the current ECG signal, wherein the preset signal detection threshold is obtained by using an amplitude characteristic of a historical ECG signal according to a signal type of the historical ECG signal when a degree of change of a historical signal corresponding to the historical ECG signal is not within a preset change range;

[0035] Extract the signal features corresponding to the target ECG type signal, calculate the signal change based on the signal features, and obtain the signal change degree corresponding to the target ECG type signal in the current ECG signal;

[0036] When the signal change degree is within the preset change degree range, a signal verification feature corresponding to the target ECG type signal is generated according to the signal feature, and a target signal detection threshold corresponding to the target ECG type signal is obtained based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal;

[0037] Acquire the ECG signal to be detected, perform target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and signal verification characteristics, and obtain the ECG signal detection result;

[0038] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, the signal detection threshold is updated based on the target signal detection threshold and the noise signal of the ECG signal to be detected;

[0039] When the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature, an updated signal detection threshold is calculated based on the amplitude feature corresponding to the ECG signal to be detected, and the updated signal detection threshold is used to perform target ECG type signal detection.

[0040] The above-described ECG signal detection method, apparatus, computer device, storage medium, and computer program product use a preset signal detection threshold to identify the target ECG type signal and the current noise signal in the current ECG signal, and determine the degree of change of the target ECG type signal in the target preceding ECG signal, thereby ensuring the stability of the target ECG type signal. A signal verification feature is then generated based on the signal characteristics of the target ECG type signal. The signal verification feature can verify the signal type of the ECG signal to be detected, ensuring the detection accuracy of the target ECG type signal. The target signal detection threshold is then generated based on the amplitude characteristics of the target ECG type signal and the signal value corresponding to the current noise signal, achieving real-time updating of the signal detection threshold. The target ECG type signal is detected based on the signal verification feature, thereby improving the accuracy of ECG signal detection. Furthermore, different signal detection thresholds are generated based on whether the degree of change of the ECG signal is within a preset range, achieving adaptive signal detection thresholds. Different data are then used to update the signal detection threshold based on the matching results between the ECG signal characteristics and the signal verification feature, ensuring the real-time and accuracy of the signal detection threshold, thereby improving ECG signal detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] FIG1 is a diagram showing an application environment of an electrocardiogram signal detection method according to an embodiment;

[0043] FIG2 is a schematic flow chart of an electrocardiogram signal detection method according to an embodiment;

[0044] FIG3 is a flow chart of an electrocardiogram signal detection step in one embodiment;

[0045] FIG4 is a schematic diagram of a flow chart of counterpulsation device control in one embodiment;

[0046] FIG5 is a schematic diagram of a flow chart of control of a counterpulsation device in another embodiment;

[0047] FIG6 is a schematic diagram of an ECG signal processing flow in one embodiment;

[0048] FIG7 is a schematic diagram of a flow chart of ECG signal processing in another embodiment;

[0049] FIG8 is a schematic diagram of a process for preprocessing an ECG signal in one embodiment;

[0050] FIG9 is a structural block diagram of an electrocardiogram signal detection device according to an embodiment;

[0051] FIG10 is a diagram showing the internal structure of a computer device according to one embodiment;

[0052] FIG11 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0054] The ECG signal detection method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Therein, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 collects the current ECG signal corresponding to the current time period from the human body through a sensor, divides the current ECG signal according to a preset signal detection threshold, and obtains the target ECG type signal and the current noise signal corresponding to the current ECG signal. The preset signal detection threshold is obtained by using the amplitude characteristics of the historical ECG signal according to the signal type of the historical ECG signal when the degree of change of the historical signal corresponding to the historical ECG signal is not within the preset degree of change range; the terminal 102 extracts the signal characteristics corresponding to the target ECG type signal, calculates the signal change based on the signal characteristics, and obtains the degree of change of the target ECG type signal in the current ECG signal; when the signal change degree is within the preset degree of change range, the terminal 102 generates a signal verification feature corresponding to the target ECG type signal according to the signal characteristics, based on the amplitude characteristics in the target ECG type signal. The signal value corresponding to the current noise signal is used to obtain a target signal detection threshold corresponding to the target ECG type signal; the terminal 102 obtains the ECG signal to be detected, performs target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and the signal verification feature, and obtains an ECG signal detection result; when the terminal 102 detects that the signal feature corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, the terminal 102 calculates an updated signal detection threshold based on the target signal detection threshold and the noise signal of the ECG signal to be detected; when the terminal 102 detects that the signal feature corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature, the terminal 102 calculates an updated signal detection threshold based on the amplitude feature corresponding to the ECG signal to be detected, and performs target ECG type signal detection using the updated signal detection threshold. The terminal 102 can then send the ECG signal to be detected and the corresponding ECG signal detection result to the server 104 for storage. The terminal 102 can be, but is not limited to, an ECG signal detection device, such as an ECG detector. The server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0055] In one embodiment, as shown in FIG2 , a method for detecting an electrocardiogram signal is provided. The method is described by taking the terminal in FIG1 as an example. The method includes the following steps:

[0056] Step 202, collect the current ECG signal corresponding to the current time period, divide the current ECG signal according to the preset signal detection threshold, and obtain the target ECG type signal and the current noise signal corresponding to the current ECG signal. The preset signal detection threshold is obtained by using the amplitude characteristics of the historical ECG signal according to the signal type of the historical ECG signal when the degree of change of the historical signal corresponding to the historical ECG signal is not within the preset change range.

[0057] The current ECG signal refers to the ECG signal segment collected during the current time period. The ECG signal refers to the electrical signal generated by the monitored heart during operation. The preset signal detection threshold refers to the pre-set detection threshold for detecting the target ECG type signal. The target ECG type refers to the pre-specified type of ECG signal to be detected, and the target ECG type signal refers to the ECG signal corresponding to the target ECG type. The target ECG type signal may refer to the R wave signal. The R wave peak is the highest peak in the QRS complex in the ECG signal, indicating ventricular contraction. The QRS complex characterizes the potential changes caused by left and right ventricular depolarization. The current noise signal refers to the signal in the current ECG signal other than the target ECG type signal, which serves as the noise signal. The amplitude characteristic refers to the amplitude characteristic of the target ECG type signal in the ECG signal, such as the amplitude characteristic of the R wave. The preset variation range refers to the pre-set judgment criteria for determining whether the ECG signal is stable. Whether the ECG signal is stable refers to whether the characteristic differences between ECG signals are obvious. The signal type refers to the occurrence state of the ECG signal, including initial ECG signals and non-initial ECG signals.

[0058] Specifically, the terminal collects the current ECG signal corresponding to the current time period, filters the current ECG signal, and then compares the signal value corresponding to the filtered current ECG signal with the preset signal detection threshold, and uses the ECG signal whose signal value exceeds the preset signal detection threshold as the target ECG type signal, and uses the ECG signal whose signal value does not exceed the preset signal detection threshold as the current noise signal. The preset signal detection threshold can be pre-set or determined based on the amplitude characteristics of the historical ECG signal of the historical time period. When the target ECG type signal is not detected in the current ECG signal using the preset signal detection threshold, the reset preset signal detection threshold is obtained, or the historical time period is extended, and the historical ECG signal of the extended historical time period is obtained to redetermine the preset signal detection threshold.

[0059] In one embodiment, the preset signal detection threshold is obtained by using the amplitude characteristics of the historical ECG signal according to the signal type of the historical ECG signal when the historical signal change degree corresponding to the historical ECG signal is not within the preset change degree range, and includes:

[0060] When the historical signal change degree corresponding to the historical ECG signal is not within the preset change degree range, and the signal type of the historical ECG signal is an initial ECG signal, calculating a preset signal detection threshold according to the amplitude characteristics of the initial ECG signal;

[0061] When the degree of change of the historical signal corresponding to the historical ECG signal is not within the preset change range, and the signal type of the historical ECG signal is a non-initial ECG signal, the preset signal detection threshold is used to determine the target ECG type signal in the non-initial ECG signal, and the preset signal detection threshold is calculated based on the amplitude characteristics of the target ECG type signal in the non-initial ECG signal.

[0062] Specifically, the terminal collects a segment of historical ECG signals, which includes historical ECG signals whose signal type is an initial ECG signal and historical ECG signals whose signal type is a non-initial ECG signal. When the terminal detects that the historical ECG signal is an initial ECG signal, it calculates a preset signal detection threshold based on the amplitude characteristics of the initial ECG signal. For example, the preset signal detection threshold is generated based on the multiple value of the peak value corresponding to the initial ECG signal. Since there is no signal detection threshold to detect the initial ECG signal, it is set that the signal change degree of the initial ECG signal is not within the preset change degree range.

[0063] Then the terminal uses the preset signal detection threshold generated based on the amplitude characteristics of the initial ECG signal to detect the historical ECG signal at the next moment, and the historical ECG signal at the next moment is a non-initial ECG signal. The terminal detects the target ECG type signal corresponding to the non-initial ECG signal at the next moment, and calculates the signal change degree corresponding to the non-initial ECG signal. When the signal change degree of the non-initial ECG signal is not within the preset change degree range, the threshold calculation is performed based on the amplitude characteristics of the target ECG type signal corresponding to the non-initial ECG signal. For example, the terminal counts the amplitudes of each signal point in the non-initial ECG signal whose signal value exceeds the preset signal detection threshold generated based on the amplitude characteristics of the initial ECG signal, and performs an average calculation to obtain the threshold calculation result; the terminal can also perform an average calculation and then a multiple calculation to obtain the threshold calculation result. The terminal uses the threshold calculation result as the preset signal detection threshold to detect the historical ECG signal at the next moment.

[0064] Based on the above execution logic, for ECG signals whose signal change degree is not within the preset change range, the terminal updates the preset signal detection threshold according to the amplitude characteristics corresponding to the target ECG type signal in the ECG signal, and detects the ECG signal at the next moment.

[0065] Step 204: extracting signal features corresponding to the target ECG type signal, performing signal change calculation based on the signal features, and obtaining a signal change degree corresponding to the target ECG type signal;

[0066] Step 206: When the signal change degree is within the preset change degree range, a signal verification feature corresponding to the target ECG type signal is generated according to the signal feature, and a target signal detection threshold corresponding to the target ECG type signal is obtained based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal.

[0067] The signal feature refers to the characteristic value that characterizes the target ECG signal type. The signal change degree refers to the degree of change in the signal feature. The signal verification feature is the characteristic information used to verify whether the ECG signal is the target ECG signal type.

[0068] Specifically, the current ECG signal includes at least two ECG signal cycles. The terminal extracts the signal features corresponding to the target ECG type signal in each ECG signal cycle, calculates the feature difference between the signal features corresponding to the target ECG type signal in each ECG signal cycle, and obtains the signal change degree corresponding to the target ECG type signal in the current ECG signal. The signal change degree may refer to the feature value difference between the signal features corresponding to the target ECG type signal in each ECG signal cycle. When the signal change degree is within a preset change degree range, the feature value of the signal feature corresponding to the target ECG type signal in the current ECG signal may be used as a signal verification feature; or a feature value range may be determined based on the feature value of the signal feature corresponding to the target ECG type signal in the current ECG signal, and the feature value range may be used as a signal verification feature. The terminal may also pre-set a feature value range. When the signal change degree of the current ECG signal is within the preset change degree range, a signal verification feature is generated based on the preset feature value range. At the same time, the terminal updates the preset feature value range for subsequent use of the updated preset feature value range to update the signal verification feature. In one embodiment, signal verification information is generated based on the signal value corresponding to the target ECG type signal, specifically including: averaging the signal values ​​of the target ECG type signal corresponding to each ECG signal cycle to obtain the average signal value of the target ECG type signal corresponding to the current ECG signal, and generating signal verification information based on the average signal value of the target ECG type signal, such as a target ECG type signal verification graph, an ECG signal value sequence, etc.; the signal value range of the target ECG type signal can also be determined based on the average signal value of the target ECG type signal, and signal verification information is generated based on the signal value range of the target ECG type signal.

[0069] The terminal then obtains the amplitude feature corresponding to the target ECG type signal. The amplitude feature may be, for example, the peak value of the target ECG type signal, or the signal average value corresponding to each signal point in the current ECG signal whose signal value exceeds the preset signal detection threshold. The terminal calculates the upper limit of the signal detection threshold based on the amplitude feature, and determines the lower limit of the signal detection threshold based on the signal value corresponding to the current noise signal. The terminal generates a signal detection threshold range based on the upper limit of the signal detection threshold and the lower limit of the signal detection threshold, and determines the target signal detection threshold corresponding to the target ECG type signal based on the signal detection threshold range. Alternatively, the preset signal detection threshold may be used as the upper limit of the signal detection threshold, and the lower limit of the signal detection threshold may be determined based on the signal value corresponding to the current noise signal. The terminal calculates the target signal detection threshold based on the upper limit of the signal detection threshold and the lower limit of the signal detection threshold.

[0070] Step 208 , obtaining the ECG signal to be detected, performing target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and the signal verification feature, and obtaining an ECG signal detection result.

[0071] Specifically, the terminal receives an ECG signal to be detected. When the signal value corresponding to the ECG signal to be detected exceeds the target signal detection threshold, the terminal collects the ECG type signal to be detected whose signal value exceeds the target signal detection threshold in the ECG signal to be detected, extracts the features of the ECG type signal to be detected corresponding to the ECG type signal to be detected, and matches the features of the signal to be detected with the signal verification features. When the features of the signal to be detected match the signal verification features, the terminal determines that the ECG type signal to be detected in the ECG signal to be detected is the target ECG type signal.

[0072] Step 210 : When the signal feature of the to-be-detected ECG signal corresponding to the to-be-detected ECG signal in the ECG signal detection result matches the signal verification feature, an updated signal detection threshold is calculated based on the target signal detection threshold and the noise signal of the to-be-detected ECG signal.

[0073] Specifically, when the terminal detects that the feature of the signal to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches, it determines that the ECG type signal to be detected in the ECG signal to be detected is the target ECG type signal, which is generally an R-wave type signal. The terminal then extracts the noise signal in the ECG signal to be detected, and uses the target signal detection threshold and the noise signal of the ECG signal to be detected to calculate the updated signal detection threshold. The terminal uses the updated signal detection threshold and the signal verification feature to detect the target ECG type signal for the next new ECG signal. According to the above execution logic, when the terminal detects that the signal feature of the new ECG signal matches the signal verification feature, it uses the current latest signal threshold and the noise signal of the current new ECG signal to update the signal threshold until it detects that the signal feature of the ECG signal does not match the signal verification feature.

[0074] Step 212: When the signal feature of the to-be-detected ECG signal corresponding to the to-be-detected ECG signal in the ECG signal detection result does not match the signal verification feature, an updated signal detection threshold is calculated based on the amplitude feature corresponding to the to-be-detected ECG signal. The updated signal detection threshold is used for target ECG type signal detection.

[0075] Specifically, when the terminal detects that the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result is not matched, it determines that the ECG type signal to be detected in the ECG signal to be detected is not the target ECG type signal, and the terminal discards the target signal detection threshold and signal verification feature. Then, the terminal uses the amplitude feature of the ECG signal to be detected to calculate the updated signal detection threshold. The terminal uses the updated signal detection threshold to detect the target ECG type signal for the next new ECG signal, and continues to update the updated signal detection threshold based on the amplitude feature of the next new ECG signal to detect the target ECG type signal for the next ECG signal, while continuously calculating the signal change degree of the new ECG signal. According to the above execution logic, when the terminal detects that the signal characteristics of the ECG signal to be detected do not match the signal verification characteristics, each time the latest ECG signal is detected, it determines whether the signal change degree of the new ECG signal is within the preset change degree range, including: if it is within the preset change degree range, the signal verification characteristics are updated using the signal characteristics of the new ECG signal; if it is not within the preset change degree range, the signal threshold is updated using the amplitude characteristics of the latest ECG signal until it is detected that the signal change degree of the new ECG signal is within the preset change degree range.

[0076] In the above-described ECG signal detection method, a preset signal detection threshold is used to identify the target ECG type signal and the current noise signal in the current ECG signal, and the degree of change of the target ECG type signal in the target preceding ECG signal is determined, thereby ensuring the stability of the target ECG type signal. A signal verification feature is then generated based on the signal characteristics of the target ECG type signal. The signal verification feature can verify the signal type of the ECG signal to be detected, ensuring the detection accuracy of the target ECG type signal. The target signal detection threshold is generated based on the peak value of the target ECG type signal and the signal value corresponding to the current noise signal, achieving real-time update of the signal detection threshold. The target ECG type signal is detected using the signal verification feature, thereby improving the accuracy of ECG signal detection. Furthermore, different signal detection thresholds are generated based on whether the degree of change of the corresponding ECG signal falls within the preset change range, achieving adaptive signal detection thresholds. Different data is then used to update the signal detection threshold based on the matching results between the ECG signal characteristics and the signal verification feature, ensuring the real-time and accuracy of the signal detection threshold, thereby improving ECG signal detection accuracy.

[0077] In one embodiment, as shown in FIG3 , step 206 , obtaining a target signal detection threshold corresponding to the target ECG type signal based on the amplitude feature of the target ECG type signal and the signal value corresponding to the current noise signal, includes:

[0078] Step 302: multiplying the amplitude characteristics based on preset parameters to obtain an upper limit of the signal detection threshold;

[0079] Step 304: Obtain the noise sampling frequency corresponding to the current noise signal, and perform an average calculation based on the signal value corresponding to the current noise signal and the noise sampling frequency to obtain a lower limit value of the signal detection threshold;

[0080] Step 306 : Calculate a target signal detection threshold corresponding to the target ECG type signal using the signal detection threshold upper limit value and the signal detection threshold lower limit value.

[0081] The upper limit of the signal detection threshold refers to the upper limit of the threshold for detecting the target ECG type signal, and the lower limit of the signal detection threshold refers to the lower limit of the threshold for detecting the target ECG type signal.

[0082] Specifically, when the terminal detects that the signal change degree corresponding to the current ECG signal is within a preset change range, it determines that the current ECG signal is an ECG signal with stable signal characteristics, and generates a signal verification feature based on the signal characteristics of the current ECG signal. The signal verification feature can be used as a signal matching template.

[0083] After the terminal determines that the signal verification feature generated based on the current ECG signal is successful, the current ECG signal is used to calculate the signal detection threshold for the ECG signal in a stable state of the signal feature. Specifically, the terminal extracts the amplitude feature of the target ECG type signal in the current ECG signal, generally the peak value corresponding to the target ECG type signal, and uses the preset parameters to multiply the peak value to obtain the upper limit of the signal detection threshold; when the current ECG signal contains multiple signal cycles of the target ECG type signal, the terminal can calculate the peak average of the peak values ​​of the target ECG type signal of the multiple signal cycles, and use the preset parameters to multiply the peak average to obtain the upper limit of the signal detection threshold. The preset parameter can be any value between 0.3 and 0.8. Preferably, the preset parameter is 0.7.

[0084] The terminal can then preset a sliding window and calculate the noise level of the current ECG signal based on the sliding window. Specifically, the signal value and frequency point number of any window width in the current ECG signal except the target ECG type signal are calculated. For example, the width from the end of the previous R wave to the arrival of the next R wave, and the width from the end of the T wave to the arrival of the R wave are calculated. The average value of the signal within the window width, or the median value, or the integrated value within the area is calculated and estimated as the lower limit of the signal detection threshold.

[0085] The terminal can also obtain the noise sampling frequency of the current noise signal, and count the number of noise signal data points corresponding to the current noise signal based on the noise sampling frequency. The noise sampling frequency can be the sampling frequency of the current ECG signal collected by the terminal, specifically the sampling frequency or resampling frequency of the current ECG signal by the terminal. According to the noise judgment rule, the noise data points corresponding to each signal value in the current noise signal are filtered out, and the signal value of the noise data point and the total number of noise data points of the current noise signal are statistically obtained. The terminal accumulates the signal value of each noise data point in the current noise signal to obtain the signal cumulative value, and then calculates the ratio of the signal cumulative value to the total number of noise data points to obtain the lower limit value of the signal detection threshold.

[0086] The terminal determines the signal detection threshold range based on the signal detection threshold upper limit and the signal detection threshold lower limit, and determines the target signal detection threshold based on the signal detection threshold. Specifically, the value between the signal detection threshold upper limit and the signal detection threshold lower limit can be used as the target signal detection threshold.

[0087] The terminal then uses the target signal detection threshold corresponding to the current ECG signal to perform target ECG type signal detection on the ECG signal at the next moment of the current ECG signal. When the ECG signal at the next moment meets the detection conditions for the target ECG type signal detection, the threshold is updated using the target signal detection threshold and the noise signal of the ECG signal at the next moment.

[0088] In this embodiment, the upper limit of the signal detection threshold is calculated based on the peak value, and the lower limit of the signal detection threshold is calculated based on the current noise signal. The target signal detection threshold is calculated using the upper limit of the signal detection threshold and the lower limit of the signal detection threshold, thereby ensuring the real-time performance of the target signal detection threshold and avoiding the signal detection from being affected by the noise signal, thereby ensuring the accuracy of the ECG signal detection.

[0089] In one embodiment, step 210, when the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, calculating and updating the signal detection threshold based on the target signal detection threshold and the noise signal of the ECG signal to be detected includes:

[0090] When the signal value corresponding to the to-be-detected ECG signal reaches the target signal detection threshold, the to-be-detected signal is divided based on the target signal detection threshold to obtain the to-be-detected ECG type signal and the noise signal corresponding to the to-be-detected ECG signal;

[0091] Extracting the signal feature to be detected corresponding to the ECG type signal to be detected, and when the signal feature to be detected matches the signal verification feature, determining that the ECG type signal to be detected is the target ECG type signal;

[0092] The target signal detection threshold is used as the upper limit value of the signal detection threshold, the noise signal corresponding to the electrocardiogram signal to be detected is used as the current noise signal, and the average calculation is returned to the signal value corresponding to the current noise signal and the noise sampling frequency to obtain the lower limit value of the signal detection threshold; the step of using the signal detection threshold upper limit value and the signal detection threshold lower limit value to calculate the target signal detection threshold corresponding to the target electrocardiogram type signal is executed to obtain the updated signal detection threshold.

[0093] Specifically, when the terminal detects that the signal value corresponding to the ECG signal to be detected reaches the target signal detection threshold, the ECG signal whose signal value exceeds the target signal detection threshold in the ECG signal to be detected is used as the ECG type signal to be detected, and the ECG signal whose signal value does not exceed the target signal detection threshold is used as the noise signal. The terminal then extracts the signal feature of the ECG type signal to be detected. Specifically, when the terminal detects that the signal value in the ECG signal to be detected begins to exceed the target signal detection threshold, it begins to extract the signal feature corresponding to the ECG type signal to be detected. When the signal value corresponding to the ECG signal to be detected begins to be less than the target signal detection threshold, the terminal completely extracts the signal feature corresponding to the ECG type signal to be detected. When the signal feature of the signal to be detected matches the signal verification feature, it is determined that the ECG type signal to be detected is the target ECG type signal.

[0094] The terminal may also obtain signal verification information when it detects that the signal value corresponding to the ECG signal to be detected reaches the target signal detection threshold. The signal verification information includes the signal value verification range of each signal value in the target ECG type signal. The terminal detects whether the signal value of the ECG type signal to be detected is within the corresponding signal value verification range in the signal verification information. When the signal values ​​of the ECG type signal to be detected are all within the corresponding signal value verification range, or the number of signal points with signal values ​​within the corresponding signal value verification range exceeds a preset number threshold, the ECG type signal to be detected is determined to be the target ECG type signal.

[0095] The terminal then uses the target signal detection threshold as the upper limit of the signal detection threshold and uses a sliding window to calculate the noise level of the noise signal of the detected ECG signal to obtain the lower limit of the signal detection threshold. The terminal uses the upper and lower limits of the signal detection threshold to update the threshold and generate an updated signal detection threshold. When a new ECG signal to be detected is subsequently acquired, the terminal uses the updated signal detection threshold and signal verification features to detect the target ECG type signal.

[0096] In this embodiment, by detecting the peak value and noise signal of the target ECG type signal, the signal detection threshold is updated according to the peak value and noise signal, thereby ensuring the real-time performance of the signal detection threshold and improving the accuracy of ECG signal detection.

[0097] In one embodiment, the electrocardiogram signal detection method further includes:

[0098] When the characteristics of the signal to be detected do not match the signal verification characteristics, a signal change calculation is performed based on the characteristics of the signal to be detected to obtain a degree of change of the signal to be detected corresponding to the electrocardiogram signal to be detected;

[0099] When the degree of change of the signal to be detected is within the preset change range, the ECG type signal to be detected is determined to be the target ECG type signal of the signal change, and an updated signal verification feature is generated according to the characteristics of the signal to be detected. The updated signal verification feature is used to verify the target ECG type signal.

[0100] Specifically, when the terminal detects that the characteristics of the signal to be detected do not match the signal verification characteristics, it means that the waveform of the electrocardiogram signal to be detected and the waveform of the historical electrocardiogram signal have changed. Then the signal verification characteristics generated according to the signal characteristics of the historical electrocardiogram signal are outdated, and it does not meet the signal characteristics of the electrocardiogram signal to be detected, and the signal verification characteristics need to be updated.

[0101] The terminal calculates the signal change based on the characteristics of the signal to be detected to obtain the degree of change of the signal to be detected corresponding to the ECG signal to be detected. When the degree of change of the signal to be detected is within a preset range of change, it indicates that the waveform of the ECG signal to be detected is stable, and the ECG type signal to be detected is determined to be a target ECG type signal that has undergone a signal change relative to the historical ECG signal. The terminal then generates an updated signal verification feature based on the characteristics of the signal to be detected. The terminal also generates a current signal detection threshold based on the amplitude characteristics or peak value and signal value corresponding to the noise signal in the target ECG type signal corresponding to the ECG signal to be detected, and uses the current signal detection threshold to update the target signal detection threshold so that when a new ECG signal to be detected is subsequently acquired, the terminal uses the current signal detection threshold and the updated signal verification feature to perform target ECG type signal detection on the newly acquired ECG signal to be detected.

[0102] In a specific embodiment, when the signal feature to be detected does not match the signal verification feature, the signal verification feature needs to be regenerated, and a continuous segment of the ECG signal to be detected can be used to update the signal verification feature. In this process, the terminal extracts the peak value of the initial ECG signal to be detected in the ECG signal segment to be detected, uses the multiple value of the peak value of the initial ECG signal to be detected as the signal detection threshold, and uses this signal detection threshold to detect the ECG signal to be detected at the next moment, and at the same time determines whether the signal change degree of the ECG signal to be detected is within a preset change range. If it is within the preset change range, the signal feature of the ECG signal to be detected is used to generate an updated signal verification feature, and at the same time, a target signal detection threshold is generated under the stable state of the signal feature based on the amplitude feature of the ECG signal to be detected and the noise signal. The target signal detection threshold and the updated signal verification feature are used to detect subsequent ECG signals to be detected; if it is not within the preset change range, the multiple value of the peak value of the ECG signal to be detected is used as the signal detection threshold under the unstable state of the signal feature, and the signal detection threshold is used to detect subsequent ECG signals to be detected until the signal change degree of the ECG signal to be detected is within the preset signal change range.

[0103] In a specific embodiment, when the signal characteristics of the ECG signal to be detected match the signal verification characteristics, the target signal detection threshold and the noise signal of the ECG signal to be detected are used to calculate an updated signal detection threshold, and subsequent ECG signals are detected using the updated signal detection threshold and the signal verification characteristics. In the subsequent signal detection process, for ECG signals whose signal characteristics continue to match the signal verification characteristics, after each signal detection is completed, a new signal detection threshold is calculated using the signal detection threshold of that detection and the noise value of the ECG signal detected that time, and the new signal detection threshold is used to detect the next ECG signal until the signal detection threshold approaches the noise signal value of the current ECG signal, at which point the update of the signal detection threshold is stopped.

[0104] In this embodiment, when it is detected that the signal feature to be detected does not match the signal verification feature, an updated signal verification feature is generated according to the signal feature to be detected, thereby ensuring the real-time performance of the signal verification feature and improving the accuracy of ECG signal detection.

[0105] In one embodiment, the signal verification feature includes a signal period feature. As shown in FIG4 , in step 208 , after performing target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and the signal verification feature and obtaining the ECG signal detection result, the following steps are further included:

[0106] Step 402: Match the signal period feature to be detected with the signal period feature in the signal feature to be detected, and determine the device deflation trigger threshold from the signal detection threshold upper limit and the updated signal detection threshold based on the matching result;

[0107] Step 404 , obtaining an updated ECG signal to be detected, generating a device deflation instruction when the signal value corresponding to the updated ECG signal to be detected reaches the device deflation trigger threshold, and controlling the counterpulsation device to deflate the device based on the device deflation instruction.

[0108] The device deflation trigger threshold refers to the threshold used to control the deflation of the balloon in a counterpulsation device. Counterpulsation devices synchronize external blood pumping with the heart's contraction cycle. For example, an intra-aortic balloon counterpulsation pump uses the patient's ECG or blood pressure signals input into the counterpulsation control device, causing the balloon pump to synchronize and reverse the heartbeat.

[0109] Specifically, the terminal detects that the ECG type signal to be detected in the ECG signal to be detected is the target ECG type signal, and extracts the periodic feature of the signal to be detected of the target ECG type signal in the ECG signal to be detected. The periodic feature of the signal to be detected can specifically be the RR interval in the ECG signal. The RR interval refers to the interval between two R waves, indicating the interval between two heartbeats. The terminal matches the periodic feature of the signal to be detected with the signal periodic feature in the signal verification feature. When the periodic feature of the signal to be detected does not match the signal periodic feature, for example, when the periodic feature of the signal to be detected is less than the signal periodic feature, when the periodic feature of the signal to be detected matches the signal periodic feature, or when the periodic feature of the signal to be detected is greater than the signal periodic feature, the preset signal detection threshold is used as the device deflation trigger threshold.

[0110] When the periodic feature of the signal to be detected matches the periodic feature of the signal, the updated signal detection threshold is used as the device deflation trigger threshold, which can realize early control of the counterpulsation device to deflate the device.

[0111] The terminal acquires an updated ECG signal to be detected. When the signal value corresponding to the updated ECG signal reaches the device deflation trigger threshold and the counterpulsation device is in the undeflated state, it generates a device deflation command. The terminal sends the device deflation command to the counterpulsation device, controlling the counterpulsation device to deflate the balloon for the preset deflation time. If the signal value corresponding to the updated ECG signal reaches the device deflation trigger threshold and the balloon in the counterpulsation device is in the deflation-started or deflation-completed state, no processing is performed.

[0112] In this embodiment, the device deflation trigger threshold is determined in the signal detection threshold upper limit and the updated signal detection threshold according to the matching result of the signal periodic characteristics, and the counterpulsation device is controlled to deflate the balloon according to the device deflation trigger threshold, thereby achieving early detection of the arrival of the R wave, allowing more time for the balloon to be deflated before the aortic valve opens, and more time to prepare for balloon inflation after the aortic valve closes, thereby achieving accuracy in controlling the counterpulsation device for balloon inflation and deflation and heart synchronization.

[0113] In one embodiment, as shown in FIG5 , in step 208 , after performing target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and the signal verification feature and obtaining the ECG signal detection result, the following steps are further included:

[0114] Step 502: When the signal occurrence time point of the target ECG type signal in the ECG signal to be detected is detected, a detection time period is obtained. The detection time period is the time period from the signal occurrence time point to the current time point. The signal occurrence time point is the time point when the peak value of the target ECG type signal in the ECG signal to be detected is detected.

[0115] Step 504: When the detection time period is consistent with the preset inflation delay time period, a device inflation instruction is generated, and the counterpulsation device is controlled to inflate the device based on the device inflation instruction.

[0116] Specifically, when the terminal detects the time point when the signal value corresponding to the ECG signal to be detected reaches the target signal detection threshold, it records the signal detection time point, represents the prediction point of the target ECG type signal, and monitors the peak value of the target ECG type signal of the ECG signal to be detected, records the occurrence point of the peak value of the target ECG type signal, and determines the time point as the signal occurrence time point. The target ECG type signal can be an R wave signal.

[0117] Specifically, the terminal can detect the signal detection time point, then collect the signal values ​​at each time point after the signal detection time point, calculate the difference between the signal values ​​at each time point, and based on the difference between the signal values ​​at each time point, when the difference between the signal values ​​at each time point is negative, determine that the peak value of the R wave in the electrocardiogram signal to be detected is detected, and use the time point corresponding to the peak value as the signal occurrence time point, and trigger a timer to count. The terminal then obtains a preset inflation delay time period, which can be determined based on the RR interval.

[0118] The terminal starts counting from the time the signal is generated. When the accumulated detection period at the current time matches the preset inflation delay period, it generates a device inflation command. The terminal sends the device inflation command to the counterpulsation device, which controls the counterpulsation device to inflate the balloon.

[0119] In one embodiment, when the terminal detects the signal detection time point, it can generate a device inflation preparation instruction, send the device inflation preparation instruction to the counterpulsation device, and control the counterpulsation device to perform the balloon inflation preparation operation. Then, when the terminal detects the signal generation point, it obtains the detection time period. When the detection time period coincides with the preset inflation delay time period, it generates a device inflation instruction. The terminal sends the device inflation instruction to the counterpulsation device, and controls the counterpulsation device to inflate the balloon.

[0120] In this embodiment, by controlling the counterpulsation device to inflate the balloon according to the signal detection point and the time period to be inflated, the arrival of the R wave is detected in advance, so that the balloon has more time to deflate before the aortic valve opens, and more time to prepare for balloon inflation after the aortic valve closes, thereby achieving the accuracy of the counterpulsation device control of balloon inflation and deflation and heart synchronization.

[0121] In one embodiment, step 202, collecting the current ECG signal corresponding to the current time period, includes:

[0122] Collecting the initial current ECG signal corresponding to the current time period, performing filtering difference calculation based on the initial current ECG signal, and obtaining a differential ECG signal;

[0123] Obtain a preset average sliding window, perform average sliding processing on the differential ECG signal based on the average sliding window, and obtain the current ECG signal.

[0124] Specifically, the terminal uses an electrocardiogram (ECG) instrument to continuously collect the patient's ECG signal, typically collecting the initial current ECG signal corresponding to the current time period in milliseconds. The initial current ECG signal is preprocessed, including filtering and denoising, to obtain a preprocessed ECG signal. The terminal then performs a first-order difference calculation on the preprocessed ECG signal to identify steep peaks in the initial current ECG signal and obtain a differential ECG signal. The terminal then obtains a preset average sliding window, uses the average sliding window to remove noise peaks, highlights the R-wave feature, and obtains the current ECG signal.

[0125] In this embodiment, the R-wave feature in the ECG signal is made more distinct by removing noise and redundant information. By controlling the window size within an appropriate range, the smoothing process of the signal is ensured to not introduce excessive delay while maintaining the real-time nature of the data, thereby improving the accuracy of signal detection.

[0126] In a specific embodiment, as shown in FIG6 , a schematic diagram of an ECG signal processing flow is provided. The specific steps are as follows:

[0127] Step 602: collect ECG signals for preprocessing, use the peak value of the initial ECG signal to establish an initial signal detection threshold, use it as the target signal detection threshold, and perform ECG signal detection;

[0128] Step 604: During the process of establishing the stable signal verification feature, the peak value of the ECG signal in the unstable signal feature state is used to update the target signal detection threshold, and the target signal detection threshold is used to perform ECG signal detection. The ECG detection result of the ECG signal in the unstable signal feature state is output, and step 610 is simultaneously executed to control the counterpulsation device to inflate or deflate the balloon according to the ECG detection result.

[0129] Step 606: After establishing the stable signal verification feature, a new target signal detection threshold is generated using the peak value and noise value of the ECG signal in the stable signal feature state. ECG signal detection is performed using the new target signal detection threshold, and an ECG detection result of the ECG signal in the stable signal feature state is output. Simultaneously, step 610 is executed to control the counterpulsation device to inflate or deflate the balloon based on the ECG detection result.

[0130] Step 608, obtain a new ECG signal, extract the R wave feature and the signal verification feature for matching. When the features match, return to step 606 for execution; when the features do not match, return to step 604 for execution.

[0131] In a specific embodiment, as shown in FIG7 , a schematic diagram of ECG signal processing is provided. In this embodiment, the R-wave signal is the target ECG signal type. The ECG signal processing process includes: establishing an initial signal detection threshold, establishing a signal verification feature, matching features and updating thresholds, and reestablishing signal verification features.

[0132] Establishing the initial signal detection threshold stage: obtaining the initial sampled initial ECG signal stage, establishing the initial signal detection threshold according to the amplitude characteristics of the initial signal, for example, the multiple of the peak value of the signal within the dotted window range is the initial signal detection threshold.

[0133] Establish signal verification feature stage: perform R wave detection on the new ECG signal according to the initial signal detection threshold, collect points based on the threshold updated by the peak value for threshold calculation, and obtain the threshold updated based on the peak value. Use the threshold updated based on the peak value to perform R wave detection on the new ECG signal, and collect points where all R wave features are extracted in this stage. When the stability of the ECG signal of two or more beats is within the preset stability range, or the signal change range is within the preset change range, the signal verification feature is established. The terminal also updates the threshold through the noise extraction window. The noise extraction window is the evaluation value of the window signal of the signal set except the R wave. For example, it can be the evaluation value of the signal size such as the amplitude and average value of the signal within 100ms after 200ms of the peak value of the R wave, or it can be the signal that has been directly preprocessed.

[0134] Feature matching and threshold update stage: When the signal feature of the new ECG signal matches the signal verification feature, the threshold is updated based on the amplitude feature or peak value and noise size of the feature-matched ECG signal; when the signal feature of the new ECG signal does not match the signal verification feature and the degree of signal change is not within the preset change range, the threshold is continuously updated based on the peak value of the new ECG signal.

[0135] Re-establishing signal verification feature stage: When the signal characteristics of the new ECG signal do not match the signal verification characteristics, and the degree of signal change is not within the preset change range, the threshold is updated based on the peak value of the new ECG signal, and the signal change degree of the new ECG signal is continuously judged to be within the preset change range. If so, the signal verification feature is re-established.

[0136] In a specific embodiment, signal acquisition and preprocessing: the terminal continuously acquires the patient's ECG signal through an electrocardiogram instrument, usually sampling in milliseconds; preprocessing is performed, including filtering and denoising, to eliminate high-frequency noise and baseline drift. Commonly used filters include bandpass filters and wavelet transforms.

[0137] Differential smoothing: Calculate the first-order difference of the filtered ECG signal to capture the steep peaks in the signal; select an appropriate window size and use a sliding window to average the ECG signal to smooth out the noise peaks and highlight the signal characteristics of the R wave.

[0138] Establish an initial target signal detection threshold: Set an initial threshold as the detection threshold for the target ECG type signal. The initial threshold is generally 1 / 3 of the signal amplitude after sliding window averaging processing.

[0139] Stability determination: It can be used to determine the stability of the signal. The stability of the signal is determined by the following steps:

[0140] Analyze the amplitude variation of the signal. Under normal circumstances, the R wave amplitude is relatively stable.

[0141] Calculate the degree of change in the periodicity of the signal. Under normal circumstances, the ECG signal has obvious and stable periodicity;

[0142] Evaluate the degree of change in the noise level of the signal by calculating the ratio of the peak value of the signal to the noise level.

[0143] Signal-to-noise level calculation: The signal level measured during periods of no cardiac electrical activity is estimated as the signal-to-noise level. The specific calculation method is the signal value and frequency of any window width in the ECG signal, excluding the R wave signal. For example, within the width from the end of the previous R wave to the onset of the next R wave, or from the end of the T wave to the onset of the R wave, the signal-to-noise level is estimated by calculating the average value, median value, or integrated value within the window width.

[0144] Based on the above stability indicators, the ECG signal is determined to meet the stability criteria. If it does, the ECG waveform is considered stable. R-wave features are then extracted and used to form a prediction template, or signal verification feature, based on these features. This template includes information such as the R-wave amplitude, rising edge slope, and width, which are used to compare and detect the upcoming R-wave. The signal detection threshold is then updated based on the R-wave peak value and the noise signal value. Generally, the updated signal detection threshold is lower than the historical signal detection threshold before the update. By implementing dynamic threshold reduction, R-wave detection can be detected earlier to accommodate balloon inflation and deflation tracking at fast heart rates.

[0145] Threshold update: Differential threshold detection method updates the threshold, including initial target signal detection threshold adjustment and signal detection threshold upper limit adjustment; details are as follows:

[0146] Sample points in the detection signal that exceed the target signal detection threshold are used as candidate points of the R wave; the candidate points are post-processed, for example, by checking the interval time and amplitude of the R wave to eliminate false detections; the signal detection threshold is dynamically and adaptively updated based on the peak value of the detected R wave.

[0147] The terminal will first use the established initial target signal detection threshold as the target signal detection threshold to detect the first R wave in the ECG signal, and then use the differential threshold method to update the initial target signal detection threshold. After detecting the R wave and obtaining the R wave peak, the detection threshold is adaptively updated based on the stored historical peak value and the current peak value, preferably 0.7 of the R wave peak value, to obtain the upper limit value of the target signal detection threshold.

[0148] The core idea of ​​this method is to gradually lower the R-wave detection threshold when the signal stability is met, so as to achieve the effect of early detection of R waves. The following is a detailed description:

[0149] When the signal meets the stability criteria—that is, the R-wave amplitude is relatively stable, the ECG signal exhibits clear and stable periodicity, and the signal noise level is low—the detection threshold can be further lowered, with the threshold remaining above the noise level. If the signal is deemed stable, the target signal detection threshold is appropriately lowered, including setting the upper limit to 2 / 3 of the range between the upper limit and the signal-to-noise value. This adjustment helps increase sensitivity to smaller R-wave amplitudes, enabling earlier R-wave detection. This process is repeated until the target signal detection threshold converges to the set lower limit, enabling early detection.

[0150] Using a dual-threaded parallel computing method, the signal is processed simultaneously using a differential threshold detection method and a stability-based threshold update method. When the signal meets the stability criterion, the target signal detection threshold of the stability-based threshold update method is gradually lowered to detect potential R waves in advance.

[0151] Specifically, if the detection results of the two methods match for five consecutive heartbeats, this threshold is used to replace the threshold of the differential threshold detection method, and the target signal detection threshold is further lowered. This process is repeated iteratively until the threshold of the new method converges to the minimum limit we set, thus achieving early detection. Rather than only using the differential threshold detection method when the stability criterion is not met, the target signal detection threshold of the method based on the stability judgment threshold update is gradually optimized under stable conditions to achieve more accurate R-wave detection.

[0152] If the signal doesn't meet the stability criteria, valid R-wave detection is still possible. In this case, the upper limit of the signal detection threshold is used for R-wave detection and signal extraction. Simultaneously, stability assessment is re-performed and signal verification features are established to ensure the accuracy and reliability of the obtained R-wave signal.

[0153] Real-time detection and output: In the real-time ECG signal stream, the terminal continuously monitors the ECG signal; when an R wave is detected through the signal detection threshold, a timestamp will be output. The timestamp is a millisecond parameter converted by the sampling rate and is used to indicate the occurrence of the R wave for controlling the counterpulsation device.

[0154] Controlling the counterpulsation device:

[0155] The terminal integrates with the IABP system based on the timestamp. The IABP system then deflates and delays inflation based on system settings and the balloon's current condition. By further lowering the R-wave detection threshold based on stability, the arrival of the R-wave can be predicted in advance, allowing more time for balloon deflation before cardiac contraction. This relaxes the performance requirements for the solenoid valve and compensates for the physical time delay of balloon activity.

[0156] In this embodiment, the R-wave signal is detected using a preset signal detection threshold, the stability of the R-wave signal is judged, and a detection template is generated using the R-wave signal, thereby improving the detection accuracy of the R-wave signal. By updating the signal detection threshold in real time, the signal detection threshold is appropriately lowered after the signal stabilizes, thereby achieving early detection of the R-wave signal, thereby allowing the balloon to be deflated earlier than usual, allowing the balloon to be fully deflated just before the onset of the cardiac systole, better compensating for the physical time delay of the balloon activity, improving the control accuracy of the aortic balloon counterpulsation device, and reducing the performance requirements for the solenoid valve of the inflation and deflation air circuit.

[0157] In a specific embodiment, as shown in FIG8 , a schematic diagram of an ECG signal preprocessing process is provided. In this embodiment, the R wave signal is a target ECG type signal, and the ECG signal processing process is as follows:

[0158] The surface lead ECG signals collected by the machine are filtered out through a high-pass filter to remove baseline drift and a low-pass filter to remove high-frequency noise. 50Hz and 60Hz notch filters are used to remove power frequency interference. The filtered ECG signals are processed by first-order difference, squaring, and small window sliding average to obtain an ECG signal with a significant and clean R wave. In the sliding average of the small window, the output delay is half the window size. The appropriate window size setting can keep the overall delay low. In the subsequent processing steps, by controlling the window size within an appropriate range, excessive delay will not be introduced, making the R wave feature in the ECG signal more obvious, removing noise and redundant information, and maintaining the real-time nature of the data, so as to better predict the periodic rhythm of the heart and achieve more accurate control of the timing of aortic balloon counterpulsation.

[0159] In one specific embodiment, R-wave characteristic parameters are acquired, including morphological features such as R-wave amplitude, RR interval, R-wave width, and R-wave rising and falling slopes. ECG signal segments encompassing several complete cardiac cycles are collected, and the R-wave locations within these cycles are detected using an adaptive differential thresholding method. Based on the dynamic changes in the signal, the threshold is automatically adjusted to accurately locate the occurrence of the R-wave. At each R-wave location, features such as R-wave amplitude, R-wave width, and rising slope are calculated. By calculating the time intervals between adjacent R waves, the RR intervals within the cardiac cycle are obtained and their mean is calculated to assess heart rate stability and whether it is within the normal range. Based on the RR interval analysis, the regularity and stability of the heart rate are determined to detect possible arrhythmias or arrhythmias. For possible ventricular premature beats, the ratio of ventricular premature beats to normal heartbeats within the cardiac cycle is calculated to obtain information about the relative frequency of arrhythmias in the signal.

[0160] Forming a template for early R-wave detection: Based on the pre-acquisition calculation results obtained in the previous steps, if the heart rate is clearly regular, the estimated noise level is low, and the timing of premature ventricular beats is stable, the R-wave detection threshold can be safely lowered to detect R waves in advance. The detection threshold is automatically adjusted based on the current signal noise level to ensure that noise does not interfere with accurate R-wave detection.

[0161] R-wave matching verification and template update: Calculation of R-wave morphology and rhythm is performed at the location of the pre-detected R-wave, including calculation of R-wave characteristics such as amplitude, width, and slope. These characteristics are compared with the expected R-wave morphology in the template. If the pre-detected R-wave morphology matches the template, the pre-detection is accurate and the current template can be used for pre-detection. The currently detected R-wave rhythm is checked to ensure that the pre-detected R-wave rhythm is consistent with the current template. If the pre-detected R-wave rhythm is consistent with the current template, the current detection template is considered reliable and can be used. The threshold is adaptively updated based on the available information and the template is used continuously for future heartbeats. If the pre-detected R-wave morphology or rhythm does not match the current template, indicating that the current template is invalid or no longer applicable, the historical template is cleared, the ECG signal is re-acquired, and a new template adapted to the new signal characteristics is established.

[0162] Evaluating Early Detection Effectiveness: For each early R wave detected, the time difference between the detection time and the actual R wave peak is recorded. This time difference indicates the accuracy of the early detection, that is, the accuracy of the predicted R wave appearance. Over a specific time period, the time difference between all early R waves detected and the actual R wave peak is collected and calculated. The accuracy of early R wave detection can be determined by calculating statistical indicators such as the average time difference and standard deviation.

[0163] In one specific embodiment, when the signal characteristics of an ECG signal do not match a feature template, a differential threshold method is used to generate a threshold for detecting an R wave. Specifically, a signal detection threshold is calculated based on the amplitude characteristics or peak value of the ECG signal, and then the detected R wave characteristics are used to determine whether the R wave characteristics are stable. During the judgment process, if the signal characteristics of the new ECG signal are detected to be unstable, the signal detection threshold is updated based on the peak value or amplitude characteristics of the new ECG signal until the signal characteristics of the ECG signal are stable. If the signal characteristics of the new ECG signal are detected to be stable, a new feature template is established using the stable R wave characteristics. After the new feature template is successfully established, the signal detection threshold is calculated using the peak value and noise value of the stable ECG signal. When a new ECG signal is subsequently detected and its signal characteristics match the feature template, the signal detection threshold is updated using the previously calculated signal detection threshold and the noise value of the new ECG signal. The above steps are repeated until an unstable ECG signal is detected, or until the newly calculated signal detection threshold approaches the noise signal, at which point the signal detection threshold update is stopped when the signal characteristics are stable. In this embodiment, the original acquired ECG signal is preprocessed by filtering and other preprocessing processes to obtain a preprocessed signal, which facilitates the execution of subsequent detection processes.

[0164] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0165] Based on the same inventive concept, embodiments of the present application also provide an ECG signal detection device for implementing the aforementioned ECG signal detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the ECG signal detection device provided below can be found in the above-described limitations on the ECG signal detection method and will not be further elaborated here.

[0166] In an exemplary embodiment, as shown in FIG9 , an electrocardiogram signal detection device 900 is provided, comprising: a signal acquisition module 902 , a feature extraction module 904 , a threshold generation module 906 , a signal detection module 908 , a feature matching module 910 , and a feature mismatching module 912 , wherein:

[0167] Signal acquisition module 902, configured to acquire a current ECG signal corresponding to a current time period, divide the current ECG signal according to a preset signal detection threshold, and obtain a target ECG type signal and a current noise signal corresponding to the current ECG signal. The preset signal detection threshold is obtained by using the amplitude characteristics of the historical ECG signal according to the signal type of the historical ECG signal when the degree of change of the historical signal corresponding to the historical ECG signal is not within a preset change range;

[0168] The feature extraction module 904 is used to extract the signal features corresponding to the target ECG type signal, perform signal change calculation based on the signal features, and obtain the signal change degree corresponding to the target ECG type signal in the current ECG signal;

[0169] Threshold generation module 906 is configured to generate a signal verification feature corresponding to the target ECG type signal according to the signal feature when the signal variation degree is within a preset variation degree range, and obtain a target signal detection threshold corresponding to the target ECG type signal based on the amplitude feature in the target ECG type signal and the signal value corresponding to the current noise signal;

[0170] The signal detection module 908 is used to obtain the ECG signal to be detected, perform target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and signal verification characteristics, and obtain the ECG signal detection result;

[0171] A feature matching module 910 is configured to calculate and update a signal detection threshold based on a target signal detection threshold and a noise signal of the ECG signal to be detected when a signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result matches a signal verification feature;

[0172] The feature mismatch module 910 is used to calculate and update the signal detection threshold based on the amplitude feature corresponding to the ECG signal to be detected when the signal feature to be detected corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature. The updated signal detection threshold is used to perform target ECG type signal detection.

[0173] In one embodiment, the threshold generation module 906 includes:

[0174] Threshold limit calculation is used to multiply the peak value based on preset parameters to obtain the upper limit of the signal detection threshold; obtain the noise sampling frequency corresponding to the current noise signal, and perform an average calculation based on the signal value and noise sampling frequency corresponding to the current noise signal to obtain the lower limit of the signal detection threshold; use the upper limit of the signal detection threshold and the lower limit of the signal detection threshold to calculate the target signal detection threshold corresponding to the target ECG type signal.

[0175] In one embodiment, the feature matching module 910 includes:

[0176] A signal determination unit is used to divide the signal to be detected based on the target signal detection threshold when the signal value corresponding to the electrocardiogram signal to be detected reaches the target signal detection threshold, so as to obtain the electrocardiogram type signal to be detected and the noise signal corresponding to the electrocardiogram signal to be detected; extract the signal feature to be detected corresponding to the electrocardiogram type signal to be detected, and when the signal feature to be detected matches the signal verification feature, determine that the electrocardiogram type signal to be detected is the target electrocardiogram type signal; use the target signal detection threshold as the upper limit value of the signal detection threshold, use the noise signal corresponding to the electrocardiogram signal to be detected as the current noise signal, and return to the signal value corresponding to the current noise signal and the noise sampling frequency for averaging calculation to obtain the lower limit value of the signal detection threshold; and execute the step of using the signal detection threshold upper limit value and the signal detection threshold lower limit value to calculate the target signal detection threshold corresponding to the target electrocardiogram type signal to obtain an updated signal detection threshold.

[0177] In one embodiment, the ECG signal detection device 900 further includes:

[0178] The verification feature updating unit is used to calculate the signal change based on the signal feature to be detected to obtain the degree of change of the signal to be detected corresponding to the ECG signal to be detected when the signal feature to be detected does not match the signal verification feature; when the degree of change of the signal to be detected is within the preset change degree range, determine that the ECG type signal to be detected is the target ECG type signal of the signal change, generate an updated signal verification feature according to the signal feature to be detected, and the updated signal verification feature is used to verify the target ECG type signal.

[0179] In one embodiment, the ECG signal detection device 900 further includes:

[0180] The device deflation trigger unit is used to perform product calculation on the peak value of the target ECG type signal in the ECG signal to be detected based on preset parameters to obtain the upper limit value of the signal detection threshold corresponding to the ECG signal to be detected; match the periodic feature of the signal to be detected with the signal periodic feature in the signal to be detected feature, and determine the device deflation trigger threshold from the upper limit value of the signal detection threshold and the updated signal detection threshold based on the matching result; obtain the updated ECG signal to be detected, and when the signal value corresponding to the updated ECG signal to be detected reaches the device deflation trigger threshold, generate a device deflation instruction, and control the counterpulsation device to deflate the device based on the device deflation instruction.

[0181] In one embodiment, the ECG signal detection device 900 further includes:

[0182] The device inflation trigger unit is used to obtain a detection time period when the signal occurrence time point of the target ECG type signal in the ECG signal to be detected is detected. The detection time period is the time period from the signal occurrence time point to the current time point. The signal occurrence time point refers to the time point when the peak value of the target ECG type signal in the ECG signal to be detected is detected; when the detection time period is consistent with the preset inflation delay time period, a device inflation instruction is generated, and the counterpulsation device is controlled to inflate the device based on the device inflation instruction.

[0183] In one embodiment, the signal acquisition module 902 includes:

[0184] The signal acquisition unit is used to collect the initial current ECG signal corresponding to the current time period, perform filtering difference calculation based on the initial current ECG signal to obtain a differential ECG signal; obtain a preset average sliding window, perform average sliding processing on the differential ECG signal based on the average sliding window to obtain the current ECG signal.

[0185] Each module in the aforementioned ECG signal detection device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0186] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 10. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store electrocardiogram signal data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an electrocardiogram signal detection method is implemented.

[0187] In an exemplary embodiment, a computer device is provided, which may be a terminal. A diagram of its internal structure may be shown in FIG11 . The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and an external device. The communication interface of the computer device is configured to communicate with an external terminal via wired or wireless communication, where the wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for detecting electrocardiogram signals. The display unit of the computer device is configured to produce a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0188] Those skilled in the art will understand that the structures shown in Figures 10-11 are merely block diagrams of partial structures related to the present application solution, and do not constitute a limitation on the computer device to which the present application solution is applied. The specific computer device may include more or fewer components than shown in the figures, or combine certain components, or have a different component arrangement.

[0189] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0190] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0191] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0192] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0193] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0194] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, 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.

[0195] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for detecting electrocardiogram signals, characterized in that, The method includes: Collecting a current electrocardiogram (ECG) signal corresponding to a current time period, and dividing the current ECG signal according to a preset signal detection threshold to obtain a target ECG type signal and a current noise signal corresponding to the current ECG signal. The preset signal detection threshold is obtained according to the amplitude characteristics of the historical ECG signal when the degree of change of the historical signal corresponding to the historical ECG signal is not within a preset range of change degrees; Extracting signal characteristics corresponding to the target ECG type signal, and performing signal change calculation based on the signal characteristics to obtain the degree of change of the target ECG type signal corresponding to the current ECG signal; When the degree of change is within a preset range of change degrees, generating a signal verification feature corresponding to the target ECG type signal according to the signal characteristics, and obtaining a target signal detection threshold corresponding to the target ECG type signal based on the amplitude characteristics in the target ECG type signal and the signal value corresponding to the current noise signal; Obtaining an ECG signal to be detected, and performing target ECG type signal detection on the ECG signal to be detected according to the target signal detection threshold and the signal verification feature to obtain an ECG signal detection result; When the detected signal feature corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature, calculating an updated signal detection threshold based on the target signal detection threshold and the noise signal of the ECG signal to be detected; When the detected signal feature corresponding to the ECG signal to be detected in the ECG signal detection result does not match the signal verification feature, calculating an updated signal detection threshold based on the amplitude characteristics corresponding to the ECG signal to be detected, and the updated signal detection threshold is used for target ECG type signal detection.

2. The method according to claim 1, wherein The obtaining the target signal detection threshold corresponding to the target ECG type signal based on the amplitude characteristics in the target ECG type signal and the signal value corresponding to the current noise signal includes: Performing a product calculation on the amplitude characteristics based on preset parameters to obtain an upper limit value of the signal detection threshold; Obtaining the noise sampling frequency corresponding to the current noise signal, and performing an average calculation based on the signal value corresponding to the current noise signal and the noise sampling frequency to obtain a lower limit value of the signal detection threshold; Calculating the target signal detection threshold corresponding to the target ECG type signal by using the upper limit value of the signal detection threshold and the lower limit value of the signal detection threshold.

3. The method according to claim 2, wherein The calculating the updated signal detection threshold based on the target signal detection threshold and the noise signal of the ECG signal to be detected when the detected signal feature corresponding to the ECG signal to be detected in the ECG signal detection result matches the signal verification feature includes: When the signal value corresponding to the ECG signal to be detected reaches the target signal detection threshold, dividing the ECG signal to be detected based on the target signal detection threshold to obtain a target ECG type signal and a noise signal corresponding to the ECG signal to be detected; Extract the signal features to be detected corresponding to the electrocardiogram type signal to be detected. When the signal features to be detected match the signal verification features, determine that the electrocardiogram type signal to be detected is the target electrocardiogram type signal; Use the target signal detection threshold as the upper limit value of the signal detection threshold. Use the noise signal corresponding to the electrocardiogram signal to be detected as the current noise signal, and return it to perform an average calculation based on the signal value corresponding to the current noise signal and the noise sampling frequency to obtain the lower limit value of the signal detection threshold. Execute the step of calculating the target signal detection threshold corresponding to the target electrocardiogram type signal using the upper limit value of the signal detection threshold and the lower limit value of the signal detection threshold to obtain the updated signal detection threshold.

4. The method according to claim 1, wherein The method further includes: When the signal features to be detected do not match the signal verification features, perform signal change calculation based on the signal features to be detected to obtain the degree of signal change corresponding to the electrocardiogram signal to be detected; When the degree of signal change to be detected is within the preset range of signal change, determine that the electrocardiogram type signal to be detected is the target electrocardiogram type signal with signal change, and generate updated signal verification features according to the signal features to be detected. The updated signal verification features are used for verifying the target electrocardiogram type signal.

5. The method according to claim 3, characterized in that The signal verification features include signal period features. After detecting the target electrocardiogram type signal of the electrocardiogram signal to be detected according to the target signal detection threshold and the signal verification features to obtain the electrocardiogram signal detection result, it further includes: Match the signal period feature to be detected in the signal features to be detected with the signal period feature, and determine the device deflation trigger threshold based on the matching result between the upper limit value of the signal detection threshold corresponding to the electrocardiogram signal to be detected and the updated signal detection threshold; Obtain the updated electrocardiogram signal to be detected. When the signal value corresponding to the updated electrocardiogram signal to be detected reaches the device deflation trigger threshold, generate a device deflation instruction, and control the counterpulsation device to deflate based on the device deflation instruction.

6. The method according to claim 1, wherein After detecting the target electrocardiogram type signal of the electrocardiogram signal to be detected according to the target signal detection threshold and the signal verification features to obtain the electrocardiogram signal detection result, it further includes: When the signal occurrence time point of the target electrocardiogram type signal in the electrocardiogram signal to be detected is detected, obtain the detection time period. The detection time period is the time period from the signal occurrence time point to the current time point. The signal occurrence time point refers to the time point when the peak value of the target electrocardiogram type signal in the electrocardiogram signal to be detected is detected; When the detection time period is consistent with the preset inflation delay time period, generate a device inflation instruction, and control the counterpulsation device to inflate based on the device inflation instruction.

7. The method according to claim 1, characterized in that, The acquisition of the current electrocardiogram signal corresponding to the current time period includes: Acquire the initial current electrocardiogram signal corresponding to the current time period, and perform filtered difference calculation based on the initial current electrocardiogram signal to obtain the differential electrocardiogram signal; Obtain a preset average sliding window, and perform average sliding processing on the differential electrocardiogram signal based on the average sliding window to obtain the current electrocardiogram signal.

8. An electrocardiogram signal detection device, characterized in that, The device includes: A signal acquisition module, configured to acquire a current electrocardiogram signal corresponding to a current time period, and divide the current electrocardiogram signal according to a preset signal detection threshold to obtain a target electrocardiogram type signal and a current noise signal corresponding to the current electrocardiogram signal. The preset signal detection threshold is obtained based on the amplitude feature of the historical electrocardiogram signal according to the signal type of the historical electrocardiogram signal when the signal change degree corresponding to the historical electrocardiogram signal is not within the preset change degree range; A feature extraction module, configured to extract a signal feature corresponding to the target electrocardiogram type signal, and perform signal change calculation based on the signal feature to obtain the signal change degree corresponding to the target electrocardiogram type signal in the current electrocardiogram signal; A threshold generation module, configured to, when the signal change degree is within the preset change degree range, generate a signal verification feature corresponding to the target electrocardiogram type signal according to the signal feature, and obtain a target signal detection threshold corresponding to the target electrocardiogram type signal based on the amplitude feature in the target electrocardiogram type signal and the signal value corresponding to the current noise signal; A signal detection module, configured to obtain a to-be-detected electrocardiogram signal, and perform target electrocardiogram type signal detection on the to-be-detected electrocardiogram signal according to the target signal detection threshold and the signal verification feature to obtain an electrocardiogram signal detection result; A feature matching module, configured to, when the to-be-detected signal feature corresponding to the to-be-detected electrocardiogram signal in the electrocardiogram signal detection result matches the signal verification feature, calculate and update a signal detection threshold based on the target signal detection threshold and the noise signal of the to-be-detected electrocardiogram signal; A feature non-matching module, configured to, when the to-be-detected signal feature corresponding to the to-be-detected electrocardiogram signal in the electrocardiogram signal detection result does not match the signal verification feature, calculate and update a signal detection threshold based on the amplitude feature corresponding to the to-be-detected electrocardiogram signal. The updated signal detection threshold is used for target electrocardiogram type signal detection.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images