Monitoring method, device and equipment of electrocardio analog front end and storage medium

Abstract

The invention relates to a monitoring method, device and equipment for an electrocardio analog front end and a storage medium. The method comprises the steps that multiple paths of electrocardio signals output by the electrocardio analog front end are monitored; acquiring an abnormal monitoring result corresponding to at least one path of electrocardiosignal in the plurality of paths of electrocardiosignals; if the abnormal monitoring result is recognized to meet the preset monitoring condition, it is determined that an abnormal event happens to the electrocardio analog front end. By means of the monitoring method of the electrocardio analog front end, the interference signals in the electrocardio signals can be recognized.

Description

Technical Field

[0001] The present application relates to the technical field of electrocardiogram monitoring, and in particular to a monitoring method, device, equipment, computer-readable storage medium and computer program product for an electrocardiogram simulation front end. Background Art

[0002] With the development of life science and technology, health monitoring through the collection of bioelectric signals has been widely used. The human body's bioelectric signals include electrocardiogram, electroencephalogram and electromyography, which can be picked up by electrodes using a certain lead method. The primary biological signal is obtained by removing the interference of the original signal through the signal processing circuit, and then the signal that can reflect the functional characteristics of the organ is obtained through signal processing.

[0003] At present, the signal monitored by the wearable ECG monitoring device is a weak physiological signal that is non-stationary, nonlinear, and highly random. Its signal amplitude is about mV (millivolt) level, and the frequency of the AC (alternating current) component of the waveform is relatively low, usually between 0.05Hz and 40Hz. The ECG simulation front end included in the wearable ECG monitoring device amplifies and filters the human ECG signal and samples and quantizes it into a digital signal, and then performs QRS waveform detection after denoising. It is not difficult to find that if the ECG simulation front end is interfered by the external environment, such as human static electricity interference, the digital signal output by the ECG simulation front end includes the interference signal, which will affect the accuracy of signal detection.

[0004] Therefore, it is necessary to timely monitor whether the ECG simulation front end is disturbed by external factors and causes abnormal events. The inventors found that the ECG signal abnormality detection schemes provided in the prior art are all for identifying symptoms, but do not monitor whether the ECG simulation front end is disturbed by external factors and causes abnormal events. Summary of the invention

[0005] Based on this, it is necessary to provide a monitoring method that can monitor whether an abnormal event occurs in the electrocardiogram simulation front end in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for monitoring an electrocardiogram simulation front end, the method comprising:

[0007] Monitor the multi-channel ECG signals output by the ECG simulation front end;

[0008] Obtaining an abnormal monitoring result corresponding to at least one electrocardiogram signal among multiple electrocardiogram signals;

[0009] If the identified abnormal monitoring result meets the preset monitoring conditions, it is determined that an abnormal event has occurred in the ECG simulation front end.

[0010] In one embodiment, the preset monitoring conditions include:

[0011] The number of abnormal ECG signals exceeds the preset threshold.

[0012] In one embodiment, the abnormal monitoring result includes the number of abnormal ECG signals, and obtaining the abnormal monitoring result corresponding to at least one ECG signal among the multiple ECG signals includes:

[0013] Acquire an abnormal signal recognition model;

[0014] The number of abnormal ECG signals in at least one ECG signal is obtained through an abnormal signal recognition model.

[0015] In one embodiment, obtaining an abnormal signal recognition model includes:

[0016] Obtain data labels related to ECG signal samples and construct an ECG signal dataset;

[0017] According to the ECG signal data set, a training data set, a verification data set and a test data set are obtained;

[0018] An abnormal signal recognition model framework is constructed, the abnormal signal recognition model framework is trained through a training data set and a verification data set, and the trained abnormal signal recognition model framework is tested through a test data set to obtain an abnormal signal recognition model.

[0019] In one embodiment, obtaining data labels related to ECG signal samples and constructing an ECG signal dataset includes:

[0020] Obtain data labels related to ECG signal samples;

[0021] Extract the features of the data labels and generate the corresponding weight matrix based on the features of the data labels;

[0022] The weight matrix is ​​divided based on the preset threshold interval group to obtain a labeling matrix;

[0023] The ECG signal samples are processed based on the labels in the label matrix to construct an ECG signal dataset.

[0024] In one embodiment, obtaining an abnormal monitoring result corresponding to at least one of the multiple ECG signals includes:

[0025] Performing abnormal monitoring on one channel of the multiple channels of ECG signals, determining abnormal sampling points in the one channel of the ECG signal, and determining an abnormal monitoring result according to the number of abnormal sampling points in the one channel of the ECG signal;

[0026] Alternatively, each of the multiple ECG signals is monitored for abnormality, abnormal sampling points in the multiple ECG signals are determined, and the abnormal monitoring result is determined according to the number of abnormal sampling points in the multiple ECG signals.

[0027] In one embodiment, abnormality monitoring is performed on one channel of the multiple channels of ECG signals to determine abnormal sampling points in the one channel of the ECG signals, including:

[0028] Setting a sliding window for the ECG signal, obtaining ECG data of sampling points of the ECG signal within the sliding window; and performing differential processing on the ECG data of the sampling points to obtain differential values;

[0029] Determine the abnormal sampling points whose difference values ​​are higher than the abnormal high threshold or lower than the abnormal low threshold.

[0030] In one embodiment, a sliding window is set for the ECG signal, and ECG data of sampling points of the ECG signal within the sliding window are obtained; and the ECG data of the sampling points are differentially processed to obtain differential values, including:

[0031] Obtain the ECG data of the current sampling point and the ECG data of the previous sampling point in the sliding window;

[0032] Calculate the current difference value between the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment;

[0033] Determine the abnormal sampling points whose difference values ​​are higher than the abnormal high threshold or lower than the abnormal low threshold, including:

[0034] Establish a data queue, and store the current differential values ​​of all sampling points in the data queue in sequence;

[0035] Obtaining the first differential value stored earliest in the data queue, and determining whether the first differential value is higher than an abnormally high threshold or whether the first differential value is lower than an abnormally low threshold;

[0036] If the first difference value is higher than the abnormal high threshold, the sampling point corresponding to the first difference value is determined to be the first high abnormal sampling point, and the number of abnormal sampling points is divided by the number of the first high abnormal sampling points; if the first difference value is lower than the abnormal low threshold, the sampling point corresponding to the first difference value is determined to be the first low abnormal sampling point, and the number of abnormal sampling points is divided by the number of the first low abnormal sampling points;

[0037] Determine whether the current difference value is higher than the abnormally high threshold or whether the current difference value is lower than the abnormally low threshold;

[0038] If the current differential value is higher than the abnormal high threshold, the sampling point corresponding to the current differential value is determined to be the second highest abnormal sampling point, and the number of abnormal sampling points is increased by the number of the second highest abnormal sampling points; if the current differential value is lower than the abnormal low threshold, the sampling point corresponding to the current differential value is determined to be the second lowest abnormal sampling point, and the number of abnormal sampling points is increased by the number of the second lowest abnormal sampling points.

[0039] In one embodiment, determining the abnormal monitoring result according to the number of abnormal sampling points in one electrocardiogram signal includes:

[0040] When the number of abnormal sampling points in one ECG signal meets a preset number condition, it is determined that one ECG signal is abnormal, and the ECG signal is marked as abnormal.

[0041] In one embodiment, the abnormal event refers to electrostatic failure of the ECG simulation front end, and determining that the abnormal event occurs at the ECG simulation front end further includes:

[0042] Execute ECG analog front end reset operation and / or execute alarm operation.

[0043] In one embodiment, obtaining an abnormal monitoring result of at least one electrocardiogram signal among multiple electrocardiogram signals includes:

[0044] Monitoring waveform changes of at least one ECG signal; the waveform changes include periodic waveform changes and / or abnormal waveform changes;

[0045] According to the abnormal waveform changes, the abnormal monitoring results are determined.

[0046] In a second aspect, an embodiment of the present application provides a monitoring device for an electrocardiogram module front end, comprising:

[0047] A monitoring module, used to monitor the multi-channel ECG signals output by the ECG simulation front end;

[0048] An acquisition module, used for acquiring an abnormal monitoring result corresponding to at least one ECG signal among multiple ECG signals;

[0049] The determination module is used to determine that an abnormal event has occurred in the ECG simulation front end if the abnormal monitoring result meets the preset monitoring conditions.

[0050] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first aspect are implemented.

[0051] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used for monitoring an electrocardiogram simulation front end. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0052] In a fifth aspect, an embodiment of the present application provides a computer program product for use in monitoring an electrocardiogram simulation front end, comprising a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0053] The above-mentioned monitoring method of the ECG simulation front end monitors the multi-channel ECG signals output by the front end of the ECG module; obtains the abnormal monitoring result corresponding to at least one of the multi-channel ECG signals; and determines that an abnormal event has occurred in the ECG simulation front end if it is identified that the abnormal monitoring result meets the preset monitoring condition. In this embodiment, by identifying the abnormal monitoring result of at least one of the multi-channel ECG signals, it is possible to monitor the abnormal event that has occurred in the ECG simulation front end, so that it is possible to monitor the interference signal in the acquired multi-channel ECG signals, that is, the interference signal in the ECG signal caused by the abnormal event in the ECG simulation front end, thereby improving the accuracy of signal detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of the structure of an electrocardiogram monitoring system in an embodiment;

[0055] Figure 2 is a schematic diagram of the structure of a computer device in one embodiment;

[0056] Figure 3 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in one embodiment;

[0057] Figure 4 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0058] Figure 5 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0059] Figure 6 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0060] Figure 7 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0061] Figure 8 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0062] Fig. 9 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0063] Fig.10 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0064] Fig.11 A schematic diagram of the steps of a monitoring method of an electrocardiogram simulation front end in another embodiment;

[0065] Fig.12 FIG. 4 is a schematic diagram of the structure of a monitoring device for an electrocardiogram simulation front end in one embodiment. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0067] The serial numbers assigned to the components in this application, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0068] First of all, before specifically introducing the technical solutions of the embodiments disclosed in the present application, the background technology or technical evolution context on which the embodiments of the present application are based is introduced. With the development of life science and technology, health monitoring by collecting bioelectric signals has been widely used. The bioelectric signals of the human body include electrocardiogram, electroencephalogram and electromyography, which can be picked up by electrodes using a certain lead method, and then the interference of the collected signals is removed by the signal processing circuit to obtain the primary biological signals, and then the signals are processed to obtain the signals that can reflect the functional characteristics of the organs.

[0069] In the conventional technology, a wearable ECG monitoring device is used to collect ECG signals of the human body. The ECG simulation front end included in the wearable ECG monitoring device amplifies and filters the ECG signals of the human body and samples and quantizes them into digital signals, and then performs QRS waveform detection after denoising. However, when using the wearable ECG monitoring device to collect ECG signals, the ECG simulation front end is susceptible to external interference, such as strong static interference, which can cause the ECG simulation front end to fail, thereby making the signal output by the ECG simulation front end abnormal. Therefore, it is very necessary to timely monitor whether the ECG simulation front end has received external interference and abnormal events. The inventors found that the ECG signal abnormality monitoring schemes provided by the prior art are all for identifying symptoms, and there is no situation in which the ECG simulation front end is monitored for abnormal events caused by external interference.

[0070] The technical solution of the present application and how the technical solution of the present application solves the technical problem are described in detail below with specific embodiments.

[0071] The monitoring method of the ECG simulation front end provided in this application can be applied to an ECG monitoring system. The structure of the ECG monitoring system is as follows: Figure 1As shown, it includes an ECG monitoring device 10 and a computer device 11. The ECG monitoring device 10 includes an ECG simulation front end 12. The ECG monitoring device 10 processes the collected ECG signals through the ECG simulation front end 12. The computer device 11 is connected to the ECG monitoring device 10 and is used to receive the processed ECG signals output by the ECG monitoring device 10 through the ECG simulation front end. The computer device can be, but is not limited to, an industrial computer, a laptop computer, a tablet computer, etc. The internal structure diagram of the computer device can be as shown in FIG. Figure 2 As shown, the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a monitoring method for an electrocardiographic simulation front end is implemented. The display screen of the computer device 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 covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse, etc.

[0072] In one embodiment, Figure 3 As shown, a monitoring method for an electrocardiogram simulation front end is provided. In this embodiment, the method is applied to Figure 1 The computer device shown is used as an example. In this embodiment, the method includes the following steps:

[0073] Step 300: monitor multiple channels of ECG signals output by the ECG simulation front end.

[0074] The multi-channel ECG signals can be collected by the ECG monitoring device from the monitored object and output through the ECG simulation front end in the ECG monitoring device. The ECG monitoring device can store the collected multi-channel ECG signals in a specific storage device, and the computer device can obtain them from the specific storage device for monitoring when needed. The ECG monitoring device can also transmit the collected multi-channel ECG signals to the computer device and store them in the storage device of the computer device, and the computer device can directly obtain them from the storage device when needed. The computer device obtains the multi-channel ECG signals.

[0075] Step 310: Obtain an abnormal monitoring result corresponding to at least one of the multiple ECG signals.

[0076] After acquiring multiple channels of ECG signals, the computer device performs abnormal monitoring on at least one of the multiple channels of ECG signals to obtain abnormal monitoring results. That is, the computer device can select any one channel of ECG signals from the multiple channels for abnormal monitoring and determine the corresponding abnormal monitoring results; it can also perform abnormal monitoring on each channel of ECG signals in the multiple channels and obtain the corresponding abnormal monitoring results; the abnormal monitoring results may include the presence of an abnormality in one channel of ECG signals, or may include the presence of multiple abnormal ECG signals in the multiple channels; or it may include that all the multiple channels of ECG signals are normal.

[0077] In an optional embodiment, when the computer device monitors each of the multiple ECG signals for abnormalities, it may monitor each ECG signal in turn, or it may monitor the multiple ECG signals in parallel, that is, monitor the multiple ECG signals simultaneously.

[0078] Step 320: If the identified abnormal monitoring result meets the preset monitoring condition, it is determined that an abnormal event occurs in the ECG simulation front end.

[0079] The preset monitoring condition can be pre-set by the user according to the actual application and stored in the computer device. After the computer device obtains the abnormal monitoring result corresponding to at least one of the multiple ECG signals, it determines whether an abnormal event occurs in the ECG simulation front end by identifying whether the abnormal monitoring result meets the preset monitoring condition. If it is determined that the abnormal monitoring result meets the preset monitoring condition, it is determined that an abnormal event occurs in the ECG simulation front end; if it is determined that the abnormal monitoring result does not meet the preset monitoring condition, it is determined that no abnormal event occurs in the ECG simulation front end.

[0080] The monitoring method of the ECG simulation front end provided in the embodiment of the present application obtains the abnormal monitoring result corresponding to at least one of the multiple ECG signals by monitoring the multiple ECG signals output by the ECG simulation front end; if the identified abnormal monitoring result meets the preset monitoring condition, it is determined that an abnormal event has occurred in the ECG simulation front end. In this embodiment, by identifying the abnormal monitoring result of at least one of the multiple ECG signals, it is possible to monitor whether an abnormal event has occurred in the ECG simulation front end, so that it is possible to timely and accurately judge whether there is an interference signal in the acquired multiple ECG signals, that is, to monitor the interference signal in the ECG signal caused by the abnormal event in the ECG simulation front end, thereby improving the accuracy of signal detection. Compared with the prior art, the monitoring method provided in the embodiment of the present application can timely monitor whether an abnormal event has occurred in the ECG simulation front end, timely eliminate the interference of the abnormal event on the ECG signal monitoring, and provide a more accurate ECG signal monitoring result.

[0081] In one embodiment, the preset monitoring conditions include:

[0082] The number of abnormal ECG signals exceeds the preset threshold.

[0083] The preset threshold value may be set by the user according to the actual application. The preset threshold value is related to the abnormal monitoring result obtained. If the computer device obtains the abnormal monitoring result corresponding to one ECG signal among multiple ECG signals, the preset threshold value may be set to zero; that is, if the abnormal monitoring result obtained by the computer device is that the ECG signal is an abnormal ECG signal, it is determined that an abnormal event has occurred in the ECG simulation front end. If the computer device obtains the abnormal monitoring result corresponding to multiple ECG signals among multiple ECG signals, the preset threshold value may be set to a first number; that is, if the abnormal monitoring obtained by the computer device is that more than the first number of ECG signals are abnormal ECG signals, it is determined that an abnormal event has occurred in the ECG simulation front end.

[0084] The computer device determines the number of abnormal ECG signals in the multiple ECG signals by monitoring at least one of the acquired ECG signals; determines whether an abnormal event occurs in the ECG simulation front end by identifying whether the number of abnormal ECG signals exceeds a preset threshold; if the number of abnormal ECG signals exceeds the preset threshold, it determines that an abnormal event occurs in the ECG simulation front end; if the number of abnormal ECG signals does not exceed the preset threshold, it determines that no abnormal event occurs in the ECG simulation front end.

[0085] In this embodiment, it is described that the preset monitoring conditions include the number of abnormal ECG signals exceeding the preset threshold value, so that by identifying the number of abnormal ECG signals in the abnormal monitoring results, it is possible to determine whether an abnormal event has occurred in the ECG simulation front end, which can improve the efficiency of determining the abnormal event in the ECG simulation front end. The abnormal ECG signals in this case are different from the heart disease monitoring signals. For example, the ECG simulation front end encounters a failure event due to human electrostatic discharge. At this time, the ECG signal includes an abnormal ECG signal that indicates an abnormal event (such as an electrostatic failure event) has occurred in the ECG simulation front end.

[0086] In one embodiment, the abnormal monitoring result includes the number of abnormal ECG signals, such as Figure 4 As shown, an implementation method for obtaining an abnormal monitoring result corresponding to at least one electrocardiogram signal among multiple electrocardiogram signals includes the following steps:

[0087] Step 400: Acquire an abnormal signal recognition model.

[0088] The abnormal signal recognition model can be pre-trained by the user and stored in the storage device of the computer device. The abnormal signal recognition model can adopt a machine learning model, such as support vector machines (SVM), random forest (RF), neural network (NN), etc. This application does not limit the type of abnormal signal recognition model, as long as it can achieve its function.

[0089] Step 410: Obtain the number of abnormal ECG signals in at least one ECG signal through an abnormal signal recognition model.

[0090] After acquiring the abnormal signal recognition model, the computer device uses the abnormal signal recognition model to identify at least one of the multiple ECG signals acquired to obtain the number of abnormal ECG signals, that is, at least one of the multiple ECG signals is input into the abnormal signal recognition model for recognition processing, and the number of abnormal ECG signals is output.

[0091] In an optional embodiment, when using an abnormal signal recognition model to identify and process multiple ECG signals, multiple abnormal signal recognition models can be used to respectively identify the multiple ECG signals to obtain the number of ECG signals with abnormal signals. That is, the number of abnormal signal recognition models is the same as the number of ECG signals, and each ECG signal is input into an abnormal signal recognition model, and the number of abnormal ECG signals is determined according to the output result of the abnormal signal recognition model. If the output result of the abnormal signal recognition model is that the signal is normal, the ECG signal of this channel is determined to be a normal ECG signal; if the output result of the abnormal signal recognition model is that the signal is abnormal, the ECG signal of this channel is determined to be an abnormal ECG signal, and the number of abnormal ECG signals is determined by statistics. An abnormal signal recognition model can also be used to sequentially identify multiple ECG signals to obtain abnormal signals. That is, each ECG signal is sequentially input into the abnormal signal recognition model for recognition to obtain the number of abnormal ECG signals.

[0092] In this embodiment, at least one of the multiple ECG signals is directly identified by using the acquired abnormal signal identification model to determine the abnormal monitoring result. This method of determining the abnormal monitoring result is fast and easy to implement, and can improve the efficiency of monitoring the ECG simulation front end.

[0093] In one embodiment, Figure 5 As shown, an implementation method of obtaining an abnormal signal recognition model is involved, and the steps of the implementation method include:

[0094] Step 500: Obtain data labels related to ECG signal samples and construct an ECG signal data set.

[0095] The ECG signal sample refers to the signal required for training the abnormal signal recognition model. The ECG signal sample includes multiple ECG signal samples, each of which has a related data label. The data label is a mark for whether each ECG signal is an abnormal ECG signal. The data label related to the ECG signal sample can be pre-stored in the computer device.

[0096] In an optional embodiment, the user analyzes each ECG signal in the ECG signal sample to determine whether the ECG signal is an abnormal ECG signal. If the user determines that the ECG signal is an abnormal ECG signal, the ECG signal can be marked as abnormal and data label A can be set; if the user determines that the ECG signal is a normal ECG signal, the ECG signal can be marked as normal and data label B can be set. For example, data label A is 1 and data label B is 0.

[0097] The computer device obtains data labels related to the ECG signal samples from the storage device, and constructs an ECG signal data set according to the obtained data labels and the corresponding ECG signal samples. In other words, the ECG signal data set includes the ECG signal samples and the data labels corresponding to the ECG signal samples.

[0098] In one embodiment, Figure 6 As shown, it involves obtaining data labels related to ECG signal samples and constructing an implementation method of an ECG signal data set. The steps of the implementation method include:

[0099] Step 600: Obtain data labels related to ECG signal samples.

[0100] The description of the ECG signal samples and data labels can refer to the description in the above embodiment, which will not be repeated here.

[0101] The data label related to the ECG signal sample acquired by the computer device refers to the setting of a sliding window and a sliding distance for each ECG signal in the ECG signal sample. The sliding window is moved according to the sliding distance, and a data label is set for whether the ECG signal in each sliding window is abnormal. In other words, if the ECG signal in the sliding window is abnormal, data label A is set; if the ECG signal in the sliding window is normal, data label B is set.

[0102] Step 610: extract the features of the data labels, and generate a corresponding weight matrix based on the features of the data labels.

[0103] After obtaining the data label related to the ECG signal sample, the computer device extracts the features of the data label, that is, determines the features of whether the ECG data of each sampling point of the ECG signal in each sliding window is abnormal. After obtaining the features of the data label, the computer device generates a corresponding weight matrix according to the features of the data label. That is, a weight matrix is ​​generated for the features of whether the ECG data of each sampling point of the ECG signal in each sliding window is abnormal.

[0104] In an optional embodiment, the feature of extracting the data label is to mark whether the ECG data of each sampling point in the sliding window is abnormal. If the ECG data is abnormal, it is marked as C, that is, the feature is C; if the ECG signal is normal, it is marked as D, that is, the feature is D. A data vector (weight vector) is generated according to the features corresponding to each sampling point.

[0105] Step 620: Divide the weight matrix based on the preset threshold interval group to obtain a labeling matrix.

[0106] The preset threshold interval group may be used to be pre-stored in a computer device. After determining the weight matrix corresponding to each ECG signal in the abnormal signal sample, that is, the weight matrix of each sliding window in each ECG signal, the computer device divides and marks the weight matrix based on the preset threshold interval group to obtain a marking matrix. In other words, the computer device marks the weight matrix by determining whether the number of features as abnormal in the weight matrix in each sliding window is within the preset threshold interval group to obtain a marking matrix. If the computer device determines that the number of features as abnormal in the weight matrix in the sliding window exceeds the preset threshold interval group, it indicates that the ECG signal corresponding to the sliding window is an abnormal ECG signal, and the ECG signal is marked as abnormal; if it is determined that the number of features as abnormal in the weight matrix in each sliding window in one ECG signal does not exceed the preset threshold interval group, it indicates that the ECG signal of the path is a normal ECG signal, and the ECG signal is marked as normal.

[0107] Step 630: Process the ECG signal samples based on the labels in the label matrix to construct an ECG signal data set.

[0108] After obtaining the labeling matrix, the computer device processes the ECG signal samples according to the labels in the labeling matrix, that is, labels the ECG signals in the ECG signal samples according to the labels in the labeling matrix to obtain an ECG signal data set. In other words, if the labels in the labeling matrix are normal labels, the ECG signals are labeled normally, and if the labels in the labeling matrix are abnormal labels, the ECG signals are labeled abnormally.

[0109] Step 510: Obtain a training data set, a verification data set, and a test data set according to the ECG signal data set.

[0110] After acquiring the ECG signal data set, the computer device divides the ECG signal data set into a training data set, a verification data set, and a test data set according to a preset ratio. The preset ratio can be pre-stored in the computer device by the user. This embodiment does not limit the preset ratio as long as its function can be achieved.

[0111] In an optional embodiment, the preset ratio is 8:1:1, that is, 8 / 10 of the abnormal signal data set is used as a training data set, 1 / 10 is used as a verification data set, and the remaining 1 / 10 is used as a test data set.

[0112] Step 520: construct an abnormal signal recognition model framework, train the abnormal signal recognition model framework using a training data set and a verification data set, and test the trained abnormal signal recognition model framework using a test data set to obtain an abnormal recognition model.

[0113] For the description of the types of abnormal signal recognition model frameworks, reference may be made to the above description of the types of abnormal signal recognition models, which will not be repeated here.

[0114] After obtaining the training data set, the verification data set and the test data set, the computer device uses the training data set to train the abnormal signal recognition model framework to obtain the initial abnormal signal recognition model; the initial abnormal signal recognition model is verified using the verification data set to verify the generalization ability (accuracy and recall rate, etc.) of the initial abnormal signal recognition model. After the initial abnormal signal recognition model is verified, the verified initial abnormal signal recognition model is tested using the test data set to evaluate the quality of the verified initial abnormal signal recognition model. After the initial abnormal signal recognition test is passed, the initial abnormal signal recognition model is determined as the abnormal signal recognition model. If the initial abnormal signal verification fails, or the initial abnormal signal test fails, the initial abnormal signal recognition model needs to be retrained.

[0115] In this embodiment, an ECG signal data set is constructed using data labels related to the acquired ECG signal samples; the ECG signal data set is divided into a training data set, a verification data set, and a test data set; the abnormal signal recognition model framework is trained using the training data set and the verification data set, and the abnormal signal recognition model framework is tested using the test data set to obtain an abnormal signal recognition model. In this way, an accurate abnormal signal recognition model can be obtained quickly, thereby improving the efficiency of obtaining abnormal monitoring results, and further improving the efficiency of determining abnormal events occurring in the ECG simulation front end, making the monitoring method of the ECG simulation front end more practical.

[0116] In one embodiment, obtaining the abnormal monitoring result corresponding to at least one of the multiple ECG signals includes obtaining the abnormal monitoring result corresponding to one of the multiple ECG signals, or the abnormal monitoring result corresponding to each of the multiple ECG signals. Figure 7 As shown, another implementation method of obtaining an abnormal monitoring result corresponding to at least one ECG signal among multiple ECG signals includes the following steps:

[0117] Step 700: perform abnormal monitoring on one channel of the multiple channels of ECG signals, determine abnormal sampling points in the one channel of the ECG signal, and determine an abnormal monitoring result according to the number of abnormal sampling points in the one channel of the ECG signal.

[0118] The computer device acquires one channel of ECG signals from multiple channels and performs abnormal monitoring on the channel of ECG signals. When the ECG acquisition device acquires the ECG signals, it acquires them in the form of sampling points. The computer device performs abnormal monitoring on the channel of ECG signals and can determine the abnormal sampling points in the channel of ECG signals.

[0119] In an optional embodiment, when acquiring one channel of ECG signal, the computer device may randomly select one channel of ECG signal from multiple channels of ECG signals.

[0120] After determining the abnormal sampling points in the ECG signal, the computer device determines the abnormal monitoring result according to the number of abnormal sampling points in the ECG signal. In other words, it determines whether the ECG signal is an abnormal ECG signal according to the number of abnormal sampling points in the ECG signal.

[0121] Step 710: perform abnormal monitoring on each of the multiple ECG signals, determine abnormal sampling points in the multiple ECG signals, and determine abnormal monitoring results according to the number of abnormal sampling points in the multiple ECG signals.

[0122] After acquiring multiple channels of ECG signals, the computer device performs abnormal monitoring on each of the multiple channels of ECG signals to obtain abnormal sampling points in each channel of ECG signals, that is, abnormal sampling points in the multiple channels of ECG signals.

[0123] After obtaining the abnormal sampling points in the multiple ECG signals, the computer device determines the abnormal monitoring result according to the number of abnormal sampling points in the multiple ECG signals. In other words, the computer device determines whether each ECG signal is an abnormal ECG signal or a normal ECG signal according to the number of abnormal sampling points in each ECG signal, so as to obtain the number of abnormal ECG signals, i.e., the abnormal monitoring result.

[0124] In this embodiment, when determining the abnormal monitoring result, one channel of the multi-channel ECG signals can be directly monitored for abnormality, and the abnormal sampling point of the one channel of ECG signals can be determined to determine the abnormal monitoring result; or each channel of the multi-channel ECG signals can be monitored for abnormality, and the abnormal sampling points of the multi-channel ECG signals can be determined to determine the abnormal monitoring result. The user can choose according to actual needs. This can improve the practicality of the monitoring method of the ECG simulation front end.

[0125] In one embodiment, Figure 8 As shown, it involves an implementation method of performing abnormal monitoring on one channel of multiple channels of ECG signals and determining an abnormal sampling point in one channel of ECG signals. The steps of the implementation method include:

[0126] Step 800: set a sliding window for one ECG signal, obtain ECG data of sampling points of one ECG signal within the sliding window; and perform differential processing on the ECG data of the sampling points to obtain differential values.

[0127] The computer device sets a sliding window for one ECG signal, and the sliding window slides according to a preset sliding distance. When the ECG acquisition device acquires the ECG signal, it acquires it in the form of sampling points, and the preset sliding distance can be one sampling point or multiple sampling points.

[0128] In an optional embodiment, the sliding window may be fixed and the ECG signal may be slid according to a preset sliding distance; or one ECG signal may be fixed and the sliding window may be slid according to a preset sliding distance.

[0129] A sliding window includes ECG data of multiple sampling points of the ECG signal. The computer device obtains the ECG data of the sampling points of the ECG signal in the sliding window, performs differential processing on the ECG data of the obtained sampling points, and obtains differential values.

[0130] Step 810: Determine abnormal sampling points whose difference values ​​are higher than an abnormally high threshold or whose difference values ​​are lower than an abnormally low threshold.

[0131] After obtaining the differential values ​​corresponding to multiple sampling points of an ECG signal in a sliding window, the computer device updates the number of abnormal sampling points according to whether the differential value is higher than an abnormal high threshold and whether the differential value is lower than an abnormal low threshold. An abnormal sampling point refers to an abnormal sampling point among multiple sampling points in a sliding window.

[0132] In an optional embodiment, after obtaining the differential value, the computer device determines whether the differential value is higher than the abnormally high threshold. If the differential value is higher than the abnormally high threshold, the sampling point corresponding to the differential value is determined to be an abnormal sampling point; if the differential value is not higher than the abnormally high threshold, it is determined whether the differential value is lower than the abnormally low threshold; if the differential value is lower than the abnormally low threshold, the sampling point corresponding to the differential value is determined to be an abnormal sampling point; if the differential value is not lower than the abnormally low threshold, it indicates that the sampling point corresponding to the differential value is a normal sampling point.

[0133] In another optional embodiment, after obtaining the differential value, the computer device determines whether the differential value is lower than the abnormally low threshold. If the differential value is lower than the abnormally low threshold, the sampling point corresponding to the differential value is determined to be an abnormal sampling point; if the differential value is not lower than the abnormally low threshold, it is determined whether the differential value is higher than the abnormally high threshold; if the differential value is higher than the abnormally high threshold, the sampling point corresponding to the differential value is determined to be an abnormal sampling point; if the differential value is not higher than the abnormally high threshold, it indicates that the sampling point corresponding to the differential value is a normal sampling point.

[0134] In this embodiment, a sliding window is set for one ECG signal, and for the ECG data of the sampling points of one ECG signal within the sliding window, the abnormal sampling points of the ECG signal are determined by the differential values ​​after differential processing of the ECG data of the sampling points. This method for determining the abnormal sampling points of one ECG signal is quick and easy to implement, and can improve the efficiency of determining abnormal monitoring results, making the monitoring method of the ECG simulation front end more practical.

[0135] In one embodiment, Fig. 9 As shown, it involves setting a sliding window for one ECG signal, obtaining ECG data of sampling points of one ECG signal within the sliding window; and performing differential processing on the ECG data of the sampling points to obtain a differential value. The steps of the implementation method include:

[0136] Step 900: Obtain the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment in the sliding window.

[0137] The computer device obtains the ECG data of the current sampling point in one ECG signal within the sliding window, and the ECG data of the sampling point at the previous moment (the sampling point before the current sampling point).

[0138] Step 910: Calculate the current difference value corresponding to the ECG data at the current sampling point and the ECG data at the sampling point at the previous moment.

[0139] After obtaining the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment, the computer device performs differential processing on the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment, that is, calculates the difference between the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment to obtain the current differential value.

[0140] Using the same method as above, the current differential values ​​of all sampling points in the sliding window can be obtained.

[0141] In this case, the implementation method of determining the abnormal sampling point whose difference value is higher than the abnormal high threshold or whose difference value is lower than the abnormal low threshold may include:

[0142] Step 920: Establish a data queue, and store the current differential values ​​of all sampling points in the data queue in sequence.

[0143] The data queue may be pre-stored in a storage device of a computer device by a user, or may be established by a computer device. The data queue includes a fixed storage space, that is, it can store differential values ​​of fixed data. When the data queue is full, when a differential value needs to be stored in the data queue, a differential value needs to be removed from the data queue.

[0144] In an optional embodiment, a fixed number of default difference values ​​may be pre-stored in the data queue, and the data queue may also be empty.

[0145] After obtaining the data queue, the computer device sequentially stores the current differential values ​​calculated based on the ECG data of the sampling points of one ECG signal in the sliding window in the data queue. In the process of storing the calculated differential values ​​in the data queue, the differential values ​​pre-stored in the data queue need to be removed accordingly.

[0146] Step 930: Obtain the first differential value stored earliest in the data queue, and determine whether the first differential value is higher than an abnormally high threshold or whether the first differential value is lower than an abnormally low threshold.

[0147] For the differential data stored in the data queue, the computer device obtains the differential value stored earliest in the data queue as the first differential value, and determines whether the first differential value is higher than an abnormally high threshold or lower than an abnormally low threshold.

[0148] In an optional embodiment, the computer device may first determine whether the first differential value is higher than an abnormally high threshold value. If the first differential value is higher than the abnormally high threshold value, there is no need to determine whether the first differential value is lower than an abnormally low threshold value; if the first differential value is not higher than the abnormally high threshold value, then determine whether the first differential value is lower than the abnormally low threshold value. The computer device may also first determine whether the first differential value is lower than an abnormally low threshold value. If the first differential value is lower than the abnormally low threshold value, there is no need to determine whether the first differential value is higher than an abnormally high threshold value; if the first differential value is not lower than the abnormally low threshold value, then determine whether the first differential value is higher than an abnormally high threshold value.

[0149] Step 940: If the first differential value is higher than the abnormal high threshold, the sampling point corresponding to the first differential value is determined to be the first high abnormal sampling point, and the number of abnormal sampling points is divided by the number of the first high abnormal sampling points; if the first differential value is lower than the abnormal low threshold, the sampling point corresponding to the first differential value is determined to be the first low abnormal sampling point, and the number of abnormal sampling points is divided by the number of the first low abnormal sampling points.

[0150] The abnormal sampling points include high abnormal sampling points and low abnormal sampling points. If the computer device determines through judgment that the first differential value is higher than the abnormal high threshold, indicating that the sampling point corresponding to the first differential value is a high abnormal sampling point, the number of abnormal sampling points is subtracted from the number of sampling points corresponding to the first differential value, that is, the number of abnormal sampling points is cumulatively subtracted, that is, subtracted by 1.

[0151] If the computer device determines through judgment that the first differential value is lower than the abnormal low threshold, indicating that the sampling point corresponding to the first differential value is a low abnormal sampling point, the number of abnormal sampling points is subtracted from the number of sampling points corresponding to the first differential value, that is, the number of abnormal sampling points is cumulatively subtracted, that is, subtracted by 1.

[0152] Step 950: Determine whether the current differential value is higher than an abnormally high threshold or whether the current differential value is lower than an abnormally low threshold.

[0153] After obtaining the current differential value, the computer device determines whether the current differential value is higher than an abnormally high threshold, or whether the current differential value is lower than an abnormally low threshold.

[0154] In an optional embodiment, the computer device may first determine whether the current differential value is higher than an abnormally high threshold, and if the current differential value is not higher than the abnormally high threshold, determine whether the current differential value is lower than an abnormally low threshold. The computer device may also first determine whether the current differential value is lower than an abnormally low threshold, and if the current differential value is not lower than the abnormally low threshold, determine whether the current differential value is higher than the abnormally low threshold.

[0155] Step 960: If the current differential value is higher than the abnormal high threshold, the sampling point corresponding to the current differential value is determined to be the second highest abnormal sampling point, and the number of abnormal sampling points is increased by the number of the second highest sampling points; if the current differential value is lower than the abnormal low threshold, the sampling point corresponding to the current differential value is determined to be the low abnormal sampling point, and the number of abnormal sampling points is increased by the number of the second lowest abnormal sampling points.

[0156] The computer device updates the number of abnormal sampling points according to the judgment result after judging whether the current differential value is higher than the abnormal high threshold value or lower than the abnormal low threshold value. If the computer device determines that the current differential value is higher than the abnormal high threshold value, it means that the sampling point corresponding to the current differential value is a high abnormal sampling point, and the number of abnormal sampling points is subtracted from the number of sampling points corresponding to the current differential value, that is, the number of abnormal sampling points is accumulated, that is, added by 1.

[0157] If the computer device determines through judgment that the current differential value is lower than the abnormal low threshold, it means that the sampling point corresponding to the current differential value is a low abnormal sampling point, then the number of abnormal sampling points is subtracted from the number of sampling points corresponding to the current differential value, that is, the number of abnormal sampling points is cumulatively subtracted, that is, added by 1.

[0158] When the current differential values ​​of all sampling points are stored in the data queue, the corresponding first differential values ​​need to be removed from the data queue. That is, each time a current differential value is stored in the data queue, a corresponding first differential value needs to be removed from the data queue. The number of abnormal sampling points represents the sum of the number of abnormal sampling points corresponding to all differential values ​​stored in the data queue. Therefore, each time a current differential value is stored and a first differential value is removed, the number of abnormal sampling points needs to be updated.

[0159] In this embodiment, a method is provided for obtaining a current differential value corresponding to an ECG signal in a sliding window and a first differential value in a data queue, and updating the number of abnormal sampling points according to the current differential value and the first differential value. The method is simple and easy to implement, and can improve the efficiency of determining the number of abnormal sampling points, thereby making the monitoring method of the ECG simulation front end more practical.

[0160] In one embodiment, an implementation method of determining an abnormal monitoring result according to the number of abnormal sampling points in an electrocardiogram signal includes:

[0161] When the number of abnormal sampling points in one ECG signal meets a preset number condition, it is determined that one ECG signal is abnormal, and the ECG signal is marked as abnormal.

[0162] After obtaining the abnormal sampling points in one ECG signal, the computer device obtains the number of the abnormal sampling points, and determines whether the number of the abnormal sampling points meets the preset number condition to determine whether the ECG signal is abnormal, that is, whether the ECG signal is an abnormal ECG signal. If it is determined that the ECG signal is an abnormal ECG signal, the ECG signal is marked as abnormal.

[0163] In an optional embodiment, the preset quantity condition includes that the number of high abnormal sampling points among the abnormal sampling points is higher than a first quantity threshold, and the sum of the number of high abnormal sampling points and low abnormal sampling points among the abnormal sampling points is higher than a second quantity threshold.

[0164] That is to say, if the computer device determines that the number of high-abnormal sampling points in one ECG signal is higher than the first number threshold, and the sum of the number of high-abnormal sampling points and the number of low-abnormal sampling points is higher than the second number threshold, then it is determined that there is an abnormality in the ECG signal; if it is determined that the number of high-abnormal sampling points in one ECG signal is not higher than the first number threshold, or the sum of the number of high-abnormal sampling points and the number of low-abnormal sampling points is not higher than the second number threshold, then the ECG signal is determined to be a normal ECG signal.

[0165] In this embodiment, by determining whether the number of abnormal sampling points in one ECG signal satisfies the pre-processed number condition, it is determined whether one ECG signal is abnormal. This method of determining whether one ECG signal is abnormal is quick and easy to implement, and can make the monitoring method of the ECG simulation front end more practical.

[0166] When performing abnormal monitoring on each of the multiple ECG signals and determining the abnormal sampling points in the multiple ECG signals, each of the multiple ECG signals can be used as one ECG signal, and the above method for determining the abnormal sampling points in one ECG signal can be used to determine the abnormal sampling points in the multiple ECG signals. Similarly, when determining the abnormal monitoring results based on the number of abnormal sampling points in the multiple ECG signals, that is, the number of abnormal sampling points in each ECG signal, the above method for determining the abnormal monitoring results based on the number of abnormal sampling points in one ECG signal can be used to determine whether each ECG signal is abnormal, and mark it if abnormal.

[0167] In an optional embodiment, for each of the multiple ECG signals, after setting a sliding window for the ECG signal, the method for determining the number of abnormal sampling points in the ECG signal may include:

[0168] Step A: obtaining the ECG data of the current sampling point of the ECG signal in the sliding window, and the ECG data of the sampling point before the current sampling point;

[0169] Step B: Calculate the difference between the ECG data of the current sampling point and the ECG data of the sampling point before the current sampling point to obtain the current difference value;

[0170] Step C: Update the number of abnormal sampling points according to whether the current difference value is higher than the abnormal high threshold and whether the current difference value is lower than the abnormal low threshold;

[0171] The number of abnormal sampling points includes the number of high abnormal sampling points and the number of low abnormal sampling points. If the current difference value is higher than the abnormal high threshold, the number of high abnormal sampling points is accumulated; if the current difference value is lower than the abnormal low threshold, the number of low abnormal sampling points is accumulated.

[0172] Step D: Obtain the ECG data of the next sampling point of the current sampling point of the ECG data in the sliding window, use the ECG data of the next sampling point as the ECG data of the current sampling point, and use the ECG data of the current sampling point as the ECG data of the previous sampling point to return to execute steps B to D;

[0173] Step E, determine whether the number of abnormal sampling points corresponding to the sliding window meets the preset conditions. If so, mark the ECG signal as abnormal; if not, move the sliding window according to the preset moving distance, reset the number of abnormal sampling points, and return to step A-step E.

[0174] The preset conditions include that the number of high outlier points is higher than a first set value, and the sum of the number of high outlier points and the number of low outlier points is higher than a second set value.

[0175] In one embodiment, the abnormal event refers to electrostatic failure of the ECG simulation front end, and the monitoring method of the ECG simulation front end further includes:

[0176] Execute ECG analog front end reset operation and / or execute alarm operation.

[0177] When the computer device determines based on the abnormal monitoring results that the abnormal event occurring in the ECG simulation front end is an electrostatic failure of the simulated ECG front end, that is, the ECG simulation front end is subjected to electrostatic discharge, resulting in failure of the ECG simulation front end, it will perform an ECG simulation front end reset operation and / or perform an alarm operation.

[0178] In an optional embodiment, the ECG simulation front-end reset operation may be performed by the computer device sending a control signal to the ECG sampling device, and the ECG sampling device performs a reset operation on the ECG simulation front-end based on the received control signal; or the computer device directly controls the ECG simulation front-end to perform a reset operation. The alarm operation may be performed by the computer device sending an alarm signal to the ECG sampling device, and the ECG sampling device performs an alarm operation based on the received alarm signal. The alarm operation may be to generate a warning light, or to generate a warning bell, etc.

[0179] In this embodiment, when it is determined that an abnormal event has occurred in the ECG simulation front end, performing an ECG simulation front end reset operation can enable the ECG simulation front end to return to normal as soon as possible; performing an alarm operation can inform the user that an abnormal event has occurred in the ECG simulation front end, so that the user can perform corresponding maintenance operations on the ECG simulation front end to enable the ECG simulation front end to return to normal as soon as possible.

[0180] In one embodiment, Fig.10 As shown, an implementation method involves obtaining an abnormal monitoring result of at least one electrocardiogram signal among multiple electrocardiogram signals, and the steps of the implementation method include:

[0181] Step 101: monitor waveform changes of at least one ECG signal; the waveform changes include periodic waveform changes and / or abnormal waveform changes.

[0182] After acquiring multiple channels of ECG signals, the computer device monitors the waveform change of one channel of the multiple channels of ECG signals, or monitors the waveform change of all channels of ECG signals to determine the waveform change type of the ECG signals.

[0183] Step 102: Determine an abnormal monitoring result according to the abnormal waveform change.

[0184] After obtaining the waveform changes of at least one ECG signal, the computer device analyzes the waveform changes to determine whether the waveform changes have abnormal waveform changes, that is, determines the number of abnormal waveform changes, determines whether the ECG signal is abnormal, and determines the abnormal monitoring results.

[0185] In an optional embodiment, the computer device may recognize the waveform through a pre-trained waveform recognition model, and determine the abnormal monitoring result according to the output result of the waveform recognition model (the situation where the waveform changes show abnormal waveform changes).

[0186] In this embodiment, another method for determining abnormal monitoring results by waveform changes of at least one of multiple ECG signals is proposed. Users can select the method provided in this embodiment and any one of the methods provided in the above embodiments to determine abnormal monitoring results according to actual applications, which can improve the practicality of the monitoring method of the ECG simulation front end.

[0187] See also Fig.11 An embodiment of the present application provides a method for monitoring an electrocardiogram simulation front end, the steps of the monitoring method comprising:

[0188] Step 110: establishing a data queue for each of the multiple ECG signals;

[0189] Step 111, obtaining the first differential value stored earliest in the data queue, and determining whether the first differential value is higher than an abnormally high threshold or whether the first differential value is higher than a first abnormally low threshold;

[0190] Step 112, remove the first differential value from the data queue, determine whether the first differential value is higher than an abnormally high threshold, or the first differential value is higher than an abnormally low threshold, and remove the number of sampling points corresponding to the first differential value from the number of abnormal sampling points;

[0191] Step 113, setting a sliding window for the ECG signal, and obtaining the current differential value corresponding to the ECG data of the current sampling point of the ECG signal in the sliding window and the ECG data of the sampling point at the previous moment;

[0192] Step 114, storing the current differential value in the data queue, and determining whether the current differential value is higher than an abnormally high threshold or whether the current differential value is lower than an abnormally low threshold;

[0193] Step 115: Determine whether the current differential value is higher than the abnormal high threshold or lower than the abnormal low threshold, and the number of abnormal sampling points is increased by the number of current sampling points;

[0194] Step 116: When the number of abnormal sampling points is higher than the set value, it is determined that the ECG signal is abnormal, and the ECG signal is marked as abnormal;

[0195] Step 117, monitoring whether the abnormal marks corresponding to the multiple ECG signals meet a preset condition; the preset condition is that the number of abnormal marks corresponding to the multiple ECG signals exceeds a threshold;

[0196] Step 118: If the abnormal marks corresponding to the multiple ECG signals meet the preset conditions, it is determined that an abnormal event occurs in the ECG simulation front end; the abnormal event refers to electrostatic failure of the ECG simulation front end.

[0197] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed 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 part of the steps or stages in other steps.

[0198] Based on the same inventive concept, the embodiment of the present application also provides an analog front end abnormality monitoring device for implementing the analog front end abnormality monitoring method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more analog front end abnormality monitoring devices provided below can refer to the limitations of the analog front end abnormality monitoring method above, and will not be repeated here.

[0199] In one embodiment, Fig.12 As shown, a monitoring device 20 for an electrocardiogram simulation front end is provided, comprising: a monitoring module 21, an acquisition module 22 and a determination module 23, wherein:

[0200] The monitoring module 21 is used to monitor the multi-channel ECG signals output by the ECG simulation front end.

[0201] The acquisition module 22 is used to acquire an abnormal monitoring result corresponding to at least one ECG signal among the multiple ECG signals.

[0202] The determination module 23 is used to determine that an abnormal event occurs in the ECG simulation front end if the abnormal monitoring result meets the preset monitoring condition.

[0203] In one embodiment, the preset monitoring condition includes: the number of abnormal ECG signals exceeds a preset threshold.

[0204] In one embodiment, the acquisition module 22 includes a model acquisition unit and a result acquisition unit. The model acquisition unit is used to acquire an abnormal signal recognition model; and the recognition unit is used to acquire the number of abnormal ECG signals in at least one ECG signal through the abnormal signal recognition model.

[0205] In one embodiment, the model acquisition unit is specifically used to acquire data labels related to ECG signal samples and construct an ECG signal data set; obtain a training data set, a verification data set and a test data set based on the ECG signal data set; construct an abnormal signal recognition model framework, train the abnormal signal recognition model framework with the training data set and the verification data set, and test the trained abnormal signal recognition model framework with the test data set to obtain an abnormal signal recognition model.

[0206] In one embodiment, the model acquisition unit includes a label acquisition subunit, a generation subunit, a division subunit and a construction subunit. The label acquisition subunit is used to obtain data labels related to the ECG signal samples; the generation subunit is used to extract the features of the data labels and generate corresponding weight matrices based on the features of the data labels; the division subunit is used to divide the weight matrix based on the preset threshold interval group to obtain a label matrix; the construction subunit is used to process the ECG signal samples based on the labels in the label matrix to construct an ECG signal data set.

[0207] In one embodiment, the acquisition module 22 includes a determination unit. The determination unit is used to perform abnormal monitoring on one channel of the multiple channels of ECG signals, determine abnormal sampling points in the one channel of the ECG signals, and determine the abnormal monitoring result according to the number of abnormal sampling points in the one channel of the ECG signals; or perform abnormal monitoring on each channel of the multiple channels of ECG signals, determine abnormal sampling points in the multiple channels of the ECG signals, and determine the abnormal monitoring result according to the number of abnormal sampling points in the multiple channels of the ECG signals.

[0208] In one embodiment, the determination unit includes a processing subunit and a determination subunit. The processing subunit is used to set a sliding window for one ECG signal, obtain ECG data of sampling points of one ECG signal within the sliding window, and perform differential processing on the ECG data of the sampling points to obtain differential values. The determination subunit is used to determine abnormal sampling points whose differential values ​​are higher than an abnormally high threshold or whose differential values ​​are lower than an abnormally low threshold.

[0209] In one embodiment, the processing subunit is specifically used to obtain the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment in the sliding window; and calculate the current differential value corresponding to the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment. The determination subunit is specifically used to establish a data queue, and store the current differential values ​​of all sampling points in the data queue in sequence; obtain the first differential value stored earliest in the data queue, and determine whether the first differential value is higher than the abnormal high threshold or whether the first differential value is lower than the abnormal low threshold; if the first differential value is higher than the abnormal high threshold, determine the sampling point corresponding to the first differential value as a high abnormal sampling point, and divide the number of sampling points corresponding to the first differential value by the number of sampling points; if the first differential value is lower than the abnormal low threshold, determine the sampling point corresponding to the first differential value as a low abnormal sampling point, and divide the number of sampling points corresponding to the first differential value by the number of sampling points; determine whether the current differential value is higher than the abnormal high threshold or whether the current differential value is lower than the abnormal low threshold; if the current differential value is higher than the abnormal high threshold, determine the sampling point corresponding to the current differential value as a high abnormal sampling point, and increase the number of abnormal sampling points by the number of sampling points corresponding to the current differential value; if the current differential value is lower than the abnormal low threshold, determine the sampling point corresponding to the current differential value as a low abnormal sampling point, and increase the number of abnormal sampling points by the number of sampling points corresponding to the current differential value.

[0210] In one embodiment, the determination unit is further configured to determine that an abnormality exists in one ECG signal when the number of abnormal sampling points in one ECG signal meets a preset number condition, and mark the ECG signal as abnormal.

[0211] In one embodiment, the monitoring device 20 for the ECG simulation front end further includes an execution module. The execution module is used to execute an ECG simulation front end reset operation and / or an alarm operation.

[0212] In one embodiment, the acquisition unit is further used to monitor the waveform changes of at least one ECG signal; the waveform changes include periodic waveform changes and / or abnormal waveform changes; and the abnormal monitoring results are determined according to the occurrence of abnormal waveform changes in the waveform changes.

[0213] Each module in the monitoring device of the ECG simulation front end can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0214] In one embodiment, a computer device is provided, whose internal structure diagram can be as follows: Figure 2 As shown. Those skilled in the art can understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0215] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0216] Monitor the multi-channel ECG signals output by the ECG simulation front end;

[0217] Obtaining an abnormal monitoring result corresponding to at least one electrocardiogram signal among multiple electrocardiogram signals;

[0218] If the identified abnormal monitoring result meets the preset monitoring conditions, it is determined that an abnormal event has occurred in the ECG simulation front end.

[0219] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0220] Monitor the multi-channel ECG signals output by the ECG simulation front end;

[0221] Obtaining an abnormal monitoring result corresponding to at least one electrocardiogram signal among multiple electrocardiogram signals;

[0222] If the identified abnormal monitoring result meets the preset monitoring conditions, it is determined that an abnormal event has occurred in the ECG simulation front end.

[0223] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0224] Monitor the multi-channel ECG signals output by the ECG simulation front end;

[0225] Obtaining an abnormal monitoring result corresponding to at least one electrocardiogram signal among multiple electrocardiogram signals;

[0226] If the identified abnormal monitoring result meets the preset monitoring conditions, it is determined that an abnormal event has occurred in the ECG simulation front end.

[0227] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed 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 the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an 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 each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0228] The technical features of the above embodiments may 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.

[0229] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A monitoring method for an electrocardiogram simulation front end, characterized in that: include: Monitor the multi-channel ECG signals output by the ECG simulation front end; Obtaining an abnormal monitoring result corresponding to at least one of the multiple ECG signals; If it is identified that the abnormal monitoring result meets the preset monitoring condition, it is determined that an abnormal event occurs in the electrocardiogram simulation front end.

2. The monitoring method of the ECG simulation front end according to claim 1, characterized in that: The preset monitoring conditions include: The number of abnormal ECG signals exceeds the preset threshold.

3. The monitoring method of the ECG simulation front end according to claim 1, characterized in that: The abnormal monitoring result includes the number of abnormal ECG signals, and the obtaining of the abnormal monitoring result corresponding to at least one ECG signal among the multiple ECG signals includes: Acquire an abnormal signal recognition model; The number of abnormal electrocardiogram signals in the at least one electrocardiogram signal is obtained through the abnormal signal recognition model.

4. The method for monitoring an ECG simulation front end as claimed in claim 3, characterized in that: The obtaining of the abnormal signal recognition model comprises: Obtain data labels related to ECG signal samples and construct an ECG signal dataset; Obtaining a training data set, a verification data set and a test data set according to the electrocardiogram signal data set; The abnormal signal recognition model framework is constructed, the abnormal signal recognition model framework is trained by the training data set and the verification data set, and the trained abnormal signal recognition model framework is tested by the test data set to obtain the abnormal signal recognition model.

5. The monitoring method of the ECG simulation front end as claimed in claim 4, characterized in that: The step of obtaining data labels related to the ECG signal samples and constructing an ECG signal dataset includes: Obtain data labels related to ECG signal samples; Extracting features of the data labels, and generating corresponding weight matrices based on the features of the data labels; Dividing the weights of the weight matrix based on a preset threshold interval group to obtain a labeling matrix; The electrocardiogram signal samples are processed based on the labels in the label matrix to construct the electrocardiogram signal data set.

6. The method for monitoring an ECG simulation front end according to any one of claims 1 to 5, characterized in that: The obtaining of the abnormal monitoring result corresponding to at least one of the multiple ECG signals includes: Performing abnormal monitoring on one channel of the multiple channels of ECG signals, determining abnormal sampling points in the one channel of ECG signal, and determining the abnormal monitoring result according to the number of abnormal sampling points in the one channel of ECG signal; Alternatively, each of the multiple channels of ECG signals is monitored for abnormality, abnormal sampling points in the multiple channels of ECG signals are determined, and the abnormal monitoring result is determined according to the number of abnormal sampling points in the multiple channels of ECG signals.

7. The method for monitoring an ECG simulation front end as claimed in claim 6, characterized in that: The abnormality monitoring of one channel of the multiple channels of ECG signals and determining the abnormal sampling point in the one channel of ECG signals includes: Setting a sliding window for the one-way ECG signal, acquiring ECG data of sampling points of the one-way ECG signal within the sliding window; and performing differential processing on the ECG data of the sampling points to obtain differential values; An abnormal sampling point where the difference value is higher than an abnormally high threshold or the difference value is lower than an abnormally low threshold is determined.

8. The method for monitoring an ECG simulation front end according to claim 7, characterized in that: Setting a sliding window for the one channel of ECG signal to obtain ECG data of sampling points of the ECG signal within the sliding window; And performing differential processing on the ECG data of the sampling points to obtain differential values, including: Acquire the ECG data of the current sampling point and the ECG data of the sampling point at the previous moment within the sliding window; Calculate the current difference value corresponding to the electrocardiogram data of the current sampling point and the electrocardiogram data of the sampling point at the previous moment; The determining of the abnormal sampling point where the difference value is higher than an abnormally high threshold, or the difference value is lower than an abnormally low threshold, includes: Establishing a data queue, and storing the current differential values ​​of all sampling points in the data queue in sequence; Obtaining a first differential value stored earliest in the data queue, and determining whether the first differential value is higher than the abnormally high threshold or whether the first differential value is lower than the abnormally low threshold; If the first differential value is higher than the abnormal high threshold, the sampling point corresponding to the first differential value is determined to be a first high abnormal sampling point, and the number of abnormal sampling points is divided by the number of the first high abnormal sampling points; if the first differential value is lower than the abnormal low threshold, the sampling point corresponding to the first differential value is determined to be a first low abnormal sampling point, and the number of abnormal sampling points is divided by the number of the first low abnormal sampling points; Determining whether the current difference value is higher than the abnormally high threshold or whether the current difference value is lower than the abnormally low threshold; If the current differential value is higher than the abnormal high threshold, the sampling point corresponding to the current differential value is determined to be the second high abnormal sampling point, and the number of abnormal sampling points is increased by the number of the second high abnormal sampling points; if the current differential value is lower than the abnormal low threshold, the sampling point corresponding to the current differential value is determined to be the second low abnormal sampling point, and the number of abnormal sampling points is increased by the number of the second low abnormal sampling points.

9. The monitoring method of the ECG simulation front end according to claim 6, characterized in that: The determining the abnormal monitoring result according to the number of abnormal sampling points in the one channel of electrocardiogram signal includes: When the number of abnormal sampling points in the one channel of electrocardiogram signal meets a preset number condition, it is determined that the one channel of electrocardiogram signal is abnormal, and the one channel of electrocardiogram signal is marked as abnormal.

10. The method for monitoring an ECG simulation front end according to claim 1, characterized in that: The abnormal event refers to electrostatic failure of the ECG simulation front end, and determining that the abnormal event occurs at the ECG simulation front end also includes: Execute ECG analog front end reset operation and / or execute alarm operation.

11. The monitoring method of the ECG simulation front end according to claim 5, characterized in that: The step of obtaining an abnormal monitoring result of at least one of the multiple ECG signals includes: Monitoring the waveform change of the at least one ECG signal; the waveform change includes periodic waveform change and / or abnormal waveform change; The abnormal monitoring result is determined according to the situation that an abnormal waveform change occurs in the waveform change.

12. A monitoring device at the front end of an electrocardiogram module, characterized in that: include: A monitoring module, used to monitor the multi-channel ECG signals output by the ECG simulation front end; An acquisition module, used for acquiring an abnormal monitoring result corresponding to at least one of the multiple ECG signals; The determination module is used to determine that an abnormal event occurs in the electrocardiogram simulation front end if it is identified that the abnormal monitoring result meets a preset monitoring condition.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium, used for monitoring an electrocardiogram simulation front end, wherein a computer program is stored on the computer-readable storage medium, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

15. A computer program product, used for monitoring an electrocardiogram simulation front end, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images