Heart beat monitoring method and device, electronic equipment, medium and electrocardiogram monitoring system

Abstract

The embodiment of the invention is suitable for the technical field of medical electronics, and provides a heart beat monitoring method and device, electronic equipment, a medium and an electrocardiograph monitoring system.The heart beat monitoring method comprises the steps that an electrocardiograph scatter diagram is constructed based on a plurality of RR intervals of electrocardiograph data, the electrocardiograph scatter diagram comprises a plurality of scatter points, each scatter point corresponds to one heart beat in the electrocardiogram data; according to the electrocardio scatter diagram, multiple target heart beats are determined, and the target heart beats are used for determining the to-be-monitored position of the electrocardio data; acquiring an electrocardio fragment corresponding to each target cardiac beat from the electrocardio data; carrying out superposition processing on the plurality of electrocardio fragments to obtain a superposition graph; and monitoring the missed cardiac beat of the electrocardiogram data according to the overlay graph. By means of the method, monitoring of missed cardiac beats in the electrocardio data can be achieved, and the cardiac beat monitoring result is perfected.

Description

Technical Field

[0001] The present application belongs to the field of signal analysis technology, and in particular relates to a heartbeat monitoring method, device, electronic equipment, medium and electrocardiogram monitoring system. Background Art

[0002] Cardiovascular disease is the leading disease threatening human health. A large number of people die from cardiovascular disease. With the general improvement of people's health awareness, some people with cardiovascular disease wear ECG monitoring equipment to record dynamic ECG data. After recording, the ECG data is fed back to the doctor for symptom examination in combination with ECG analysis algorithm. Doctors guide patients to intervene in the disease in time according to the conclusion of ECG data analysis, prevent sudden disease, and reduce the impact of cardiovascular disease on patients. Dynamic ECG data refers to the ECG signals obtained by patients wearing ECG monitoring equipment for a long time (24 hours or more). After the collection is completed, the user (such as a doctor) reads the data of the ECG monitoring equipment into the computer software through the ECG analysis software for analysis and processing, and finally gives a diagnosis conclusion.

[0003] At present, ECG scatter plots are mainly used to analyze and process dynamic electrocardiogram data to enhance the diagnosis and identification functions of dynamic electrocardiograms. ECG scatter plots are also called Lorenz scatter plots. The length of the previous RR interval of two adjacent cardiac cycles is used as the horizontal coordinate, and the length of the next RR interval is used as the vertical coordinate. The scatter plot is drawn on a plane. Through the shape of the Lorenz scatter plot, the qualitative analysis of the rhythm type can be achieved relatively quickly. However, in clinical use, it is generally required that patients wear ECG monitoring equipment for no less than 24 hours, or even up to 72 hours, and the ECG monitoring equipment records at least 100,000 heartbeats. Due to the long recording time, large amount of data and high noise, the existing ECG analysis software is prone to missed heartbeats during the heartbeat analysis process, that is, some heartbeats are not recognized by the ECG analysis software. If there are more missed heartbeats during the analysis process, the ECG monitoring results will be biased, which makes it easy for doctors to make mistakes when judging patients with arrhythmias and abnormalities based on the ECG monitoring results. Based on this, how to prevent the problem of missed heart beats is an issue that needs to be solved urgently. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a heartbeat monitoring method, device, electronic device, medium and ECG monitoring system, which can accurately monitor missed heartbeats, thereby providing doctors with more accurate and complete ECG data.

[0005] A first aspect of an embodiment of the present application provides a heart rate monitoring method, comprising the following steps:

[0006] Construct an electrocardiogram scatter plot based on multiple RR intervals of electrocardiogram data. The electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to one heartbeat in the electrocardiogram data;

[0007] Determine multiple target heartbeats according to the electrocardiogram scatter plot. The target heartbeats are used to determine the positions to be monitored in the electrocardiogram data;

[0008] Obtain the electrocardiogram segments corresponding to each of the target heartbeats from the electrocardiogram data;

[0009] Perform superposition processing on multiple electrocardiogram segments to obtain a superposition map;

[0010] Monitor the missed heartbeats in the electrocardiogram data according to the superposition map.

[0011] The second aspect of the embodiments of the present application provides a heartbeat monitoring device, including:

[0012] An electrocardiogram scatter plot construction module, configured to construct an electrocardiogram scatter plot based on multiple RR intervals of electrocardiogram data. The electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to one heartbeat in the electrocardiogram data;

[0013] A target heartbeat determination module, configured to determine multiple target heartbeats according to the electrocardiogram scatter plot. The target heartbeats are used to determine the positions to be monitored in the electrocardiogram data;

[0014] An electrocardiogram segment determination module, configured to obtain the electrocardiogram segments corresponding to each of the target heartbeats from the electrocardiogram data;

[0015] A superposition module, configured to perform superposition processing on multiple electrocardiogram segments to obtain a superposition map;

[0016] A monitoring module, configured to monitor the missed heartbeats in the electrocardiogram data according to the superposition map.

[0017] The third aspect of the embodiments of the present application provides an electrocardiogram monitoring system, which includes: an electrocardiogram data acquisition module, an R wave recognition module, and a missed heartbeat monitoring module, where:

[0018] The electrocardiogram data acquisition module is configured to acquire electrocardiogram data to be processed;

[0019] The R wave recognition module is configured to identify the R wave peak positions of heartbeats from the electrocardiogram data. The R wave peak positions are used to determine the RR intervals corresponding to the heartbeats;

[0020] A missed heartbeat monitoring module is configured to construct an electrocardiogram scatter plot based on multiple RR intervals. The electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to a heartbeat in the electrocardiogram data. According to the electrocardiogram scatter plot, multiple target heartbeats are determined. The target heartbeats are used to determine the positions to be monitored in the electrocardiogram data. Electrocardiogram segments corresponding to each of the target heartbeats are obtained from the electrocardiogram data. The multiple electrocardiogram segments are subjected to superposition processing to obtain a superposition map. The electrocardiogram data is monitored for missed heartbeats according to the superposition map.

[0021] A fourth aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in the first aspect above is implemented.

[0022] A fifth aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the method described in the first aspect above.

[0023] Compared with the prior art, the embodiments of the present application have the following advantages:

[0024] When determining the heartbeat monitoring using the method in the embodiments of the present application, each heartbeat in the electrocardiogram can be used as a scatter point to establish a scatter plot. In the scatter plot, the abscissa of the scatter point represents the RR interval value of the heartbeat, and the ordinate represents the RR interval value of the next heartbeat of the heartbeat. Therefore, the position of each scatter point in the scatter plot can reflect the distance relationship between the heartbeat corresponding to the scatter point and the next heartbeat. Since the heartbeat has a certain pattern, in the electrocardiogram, the interval between two heartbeats should be maintained within an appropriate range. When the distance between two heartbeats is too large, there may be a missed heartbeat between these two heartbeats. Since the position of the scatter point corresponding to the heartbeat in the scatter plot can characterize the interval between the heartbeat and the next heartbeat, the abnormal area where the target heartbeat is located can be determined from the scatter plot. The target heartbeat may be the heartbeat before the missed heartbeat, and the position after the target heartbeat may be the position of the missed heartbeat. In a single waveform diagram, the sampling point characteristics of the missed heartbeat position are not obvious, but when the waveform diagrams of multiple target heartbeats are superimposed, the sampling points of the missed heartbeats after each target heartbeat can gather together, so as to show certain waveform characteristics. Therefore, in the embodiments of the present application, it is possible to determine whether there is a missed heartbeat after the target heartbeat based on the superimposed diagram of the electrocardiogram segment corresponding to the target heartbeat. The present application determines the existence of the missed heartbeat based on the waveform characteristics in the superimposed diagram, which can reduce the difficulty of determining the missed heartbeat, and when determining the missed heartbeat, less computing resources are consumed. The method in the embodiments of the present application can automatically complete the comprehensive positioning of the missed heartbeat based on the electrocardiogram scatter points and reduce the positioning difficulty of the missed heartbeat, so as to better improve the heartbeat monitoring result. Description of the Drawings

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art.

[0026] Figure 1 It is a schematic flowchart of the steps of a heartbeat monitoring method provided by an embodiment of the present application;

[0027] Figure 2 It is a schematic diagram of an electrocardiogram scatter plot provided by an embodiment of the present application;

[0028] Figure 3 It is a schematic diagram of a segmented electrocardiogram scatter plot provided by an embodiment of the present application;

[0029] Figure 4 It is a schematic diagram of a superimposed waveform diagram provided by an embodiment of the present application;

[0030] Figure 5 It is a schematic diagram of splitting the superimposed waveform diagram provided by an embodiment of the present application;

[0031] Figure 6 It is a schematic diagram of the ST segment of the superimposed graph provided by an embodiment of the present application;

[0032] Figure 7 It is a schematic diagram of the statistical result of sampling point statistics for the middle segment of the ST segment provided by an embodiment of the present application;

[0033] Figure 8 It is a schematic diagram that the amplitude of the QRS wave is greater than the amplitude of the T wave provided by an embodiment of the present application;

[0034] Figure 9 It is a schematic diagram that the amplitude of the QRS wave is less than or equal to the amplitude of the T wave provided by an embodiment of the present application;

[0035] Figure 10 It is a schematic diagram of the step flow of another heart beat monitoring method provided by an embodiment of the present application;

[0036] Figure 11 It is a schematic diagram of a heart beat monitoring device provided by an embodiment of the present application;

[0037] Figure 12 It is a schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0038] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0039] Currently, when monitoring missed heart beats, usually the user manually selects the positions of the missed heart beats in the electrocardiogram, and then based on the positions of the missed heart beats selected by the user, determines the characteristics of the positions corresponding to the missed heart beats, so as to query the positions of other possible missed heart beats from the electrocardiogram based on the characteristics of the positions corresponding to the missed heart beats. This makes the probability of successful re-examination of missed heart beats highly dependent on the user's operation. At the same time, due to the large number of heart beats in the electrocardiogram data, this will cause the user to have a large workload and low efficiency.

[0040] Based on this, the present application proposes a heart beat monitoring method, which can realize the automatic monitoring of missed heart beats.

[0041] The heartbeat monitoring method provided by the embodiments of the present application can be applied to electronic devices such as tablet computers, laptop computers, Ultra-Mobile Personal Computers (UMPCs), netbooks, and Personal Digital Assistants (PDAs). The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.

[0042] First, relevant concepts in electrocardiograms used in the present application are introduced. An electrocardiogram can include multiple heartbeats, and a heartbeat can include a P wave, a QRS wave, and a T wave. Among them, the QRS wave reflects the depolarization potential and time changes of the left and right ventricles. In the QRS wave, the first downward wave is the Q wave, the upward wave is the R wave, and the subsequent downward wave is the S wave. The QRS wave of a heartbeat has relatively obvious waveform characteristics. In the present application, the RR interval value of each heartbeat can be the interval duration between the R waves of the current heartbeat and the previous heartbeat. Under normal circumstances, the RR interval value of a heartbeat generally remains within a certain range. For example, the normal value of the RR interval in an electrocardiogram is 0.6 - 1.0 seconds.

[0043] Refer to Figure 1 , which shows a schematic flowchart of the steps of a heartbeat monitoring method provided by the embodiments of the present application, and specifically may include the following steps:

[0044] S101, construct an electrocardiogram scatter plot based on multiple RR intervals of electrocardiogram data. The electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to a heartbeat in the electrocardiogram data.

[0045] The above electrocardiogram data can be obtained by reading the monitoring data of wearable devices, patches, electrocardiographs, etc. For the electrocardiogram data to be processed, the heartbeats can be automatically identified by software. For each heartbeat, the peak position of the R wave can be identified, and thus the RR interval of each heartbeat can be calculated based on the peak positions of the R waves of each heartbeat. Then, the above electrocardiogram scatter plot can be determined based on the RR interval of each heartbeat.

[0046] Figure 2 is an electrocardiogram scatter plot provided by the embodiments of the present application. In the electrocardiogram scatter plot shown in Figure 2 , x is the RR interval value of the current heartbeat, and y is the RR interval value of the next heartbeat after the current heartbeat. The ratio of y to x can reflect the distance relationship between the heartbeat corresponding to this scatter point and the next heartbeat.

[0047] Under normal circumstances, the RR interval values of two adjacent heartbeats do not differ much. When the RR interval values between two heartbeats differ too much, there may be a missed heartbeat between these two heartbeats. Therefore, the embodiments of the present application establish a scatter plot based on the RR interval value to locate the missed heartbeat.

[0048] S102. Determine multiple target heartbeats according to the electrocardiogram scatter plot, where the target heartbeats are used to determine the positions to be monitored of the electrocardiogram data.

[0049] The above-mentioned target heartbeat may be the heartbeat before the missed heartbeat. That is, the electrocardiogram segment after the target heartbeat is the segment that needs to be monitored for missed heartbeats. Therefore, the target heartbeat can be used to determine the position to be monitored of the electrocardiogram data, and the position to be monitored is the electrocardiogram segment after the target heartbeat, which is the electrocardiogram segment where missed heartbeats may exist.

[0050] When determining the target heartbeat, the electrocardiogram scatter plot can be cut into multiple grids according to the set conditions; then multiple target heartbeats are determined from the scatter plot according to the grids. Specifically, the electronic device can determine the first area in the electrocardiogram scatter plot that meets the first set condition, and then cut the first area according to the second set condition to obtain multiple grids.

[0051] Among them, the above-mentioned first set condition can be determined by the ratio of the ordinate to the abscissa corresponding to the scatter point. The above-mentioned first area is equivalent to the abnormal area where the target heartbeat is located. The RR interval ratio between the heartbeat corresponding to the scatter point in this abnormal area and the next adjacent heartbeat is too large, indicating that there may be missed heartbeats after the target heartbeat corresponding to the scatter point in this abnormal area.

[0052] Specifically, since the position of the scatter point corresponding to the heartbeat in the scatter plot can represent the distance between this heartbeat and the next heartbeat, the first area where the target heartbeat is located can be determined from the scatter plot.

[0053] When there is a missed heartbeat after the current heartbeat, the RR interval ratio obtained by dividing the RR interval value of the next heartbeat of the current heartbeat by the RR interval value of the current heartbeat is not 1. For example, it may be greater than 2. When the RR interval ratio is larger, it indicates that there are more missed heartbeats between the two heartbeats.

[0054] In the embodiment of the present application, the target RR interval ratio can be determined. The target RR interval ratio is the minimum ratio obtained by dividing the RR interval value of the next heartbeat of the current heartbeat by the RR interval value of the current heartbeat when there is a missed heartbeat after the current heartbeat; then a dividing line passing through the origin of coordinates is established based on the target RR interval ratio. This dividing line is a linear function and the coefficient is the target RR interval ratio; this dividing line can divide the scatter plot into two parts. As Figure 3 shown, y = kx is the dividing line, and k is the target RR interval ratio. The scatter points in the angular region between this dividing line and the vertical axis have too large RR interval ratios. Therefore, there may be one or more missed heartbeats after the corresponding heartbeats. Therefore, the angular region between this dividing line and the vertical axis is determined as the first area.

[0055] Exemplarily, the electronic device may calculate the ratio of the RR interval of each normal heartbeat to the sum of the RR intervals of the next two normal heartbeats to form a sequence k1, k2, …, kn, and then calculate the median k of the sequence. Then, taking y = k * x as the dividing line, the range where y > k * x in the coordinate system is taken as the first region, and the heartbeats corresponding to all the scatter points included in the range where y > k * x in the coordinate system are the target heartbeats.

[0056] The above second setting condition may be determined based on the ratio of the ordinate to the abscissa of the scatter points corresponding to the target heartbeats. Since the number of heartbeats in the electrocardiogram data is huge, therefore, several of the target heartbeats can be selected each time for monitoring missed heartbeats. In order to comprehensively monitor missed heartbeats, the first region may be divided based on the second setting condition, so that based on the divided grid, the monitoring of missed heartbeats can be carried out in sequence, avoiding the existence of unprocessed target heartbeats.

[0057] Exemplarily, after determining the first region, the first region may be cut into multiple grids. Then, the monitoring of missed heartbeats is carried out in the order of the grids. Exemplarily, the part where y > x in the scatter plot may be cut with y = k * x, (k + 1) * x, (k + 2) * x, …… (k + 9) * x to obtain multiple regions; then, in the x-axis direction, with a step of T ms, the electrocardiogram scatter plot is cut again into a mesh structure using x = T ms, 2T ms …… as shown in Figure 3 shown.

[0058] Based on the position of the grid, the processing order of the grid can be determined. When monitoring missed heartbeats of the target heartbeats in the first region, it can start from the triangular region close to the vertical axis and be processed in the clockwise direction. Then, according to the processing order, the currently processed grid can be determined.

[0059] In this embodiment, when specifically determining whether there is a missed heartbeat, the electrocardiogram segments corresponding to multiple target heartbeats with the same RR interval may be superimposed and processed. Therefore, multiple target heartbeats need to be selected each time. Assume that the multiple target heartbeats are a preset number.

[0060] If the number of scatter points in the currently processed grid is greater than the preset number, then multiple target heartbeats can be selected from the currently processed grid.

[0061] If the number of scattered points in the currently processed grid is less than or equal to the preset number, the scattered points in the currently processed grid can be classified into the next grid of the currently processed grid, and the next grid of the currently processed grid can be used as the new currently processed grid. Then, based on the new currently processed grid, multiple target heartbeats can be determined. For example, if the preset number is 10 and grid 1 is the currently processed grid, and the number of scattered points in grid 1 is 6 and the number of scattered points in grid 2 is 8, the scattered points in grid 1 can be classified into grid 2. Then, there are 14 scattered points in grid 2. Grid 2 is used as the currently processed grid, and then 10 scattered points are selected from the 14 scattered points in grid 2, and the target heartbeats corresponding to the 10 scattered points are used as the heartbeats processed this time.

[0062] In another possible implementation, the user can also manually select the target heartbeats to be superimposed. The electronic device can display an electrocardiogram scatter plot; the user can determine the target heartbeats in the electrocardiogram scatter plot according to the displayed electrocardiogram scatter plot and select the target heartbeats for superimposition processing. If the electronic device detects a selection operation on the scattered points on the electrocardiogram scatter plot, the heartbeats corresponding to the selected scattered points can be used as the selected target heartbeats.

[0063] S103. Obtain the electrocardiogram segments corresponding to each of the target heartbeats from the electrocardiogram data.

[0064] Since the position to be monitored is after the target heartbeat, the electrocardiogram segment corresponding to the target heartbeat can be determined from the electrocardiogram data. This electrocardiogram segment can include the electrocardiogram corresponding to the target heartbeat and a segment of the electrocardiogram after the target heartbeat. For example, the electrocardiogram corresponding to the target heartbeat and the electrocardiogram with a preset length after the target heartbeat can be jointly used as the above electrocardiogram segment. The preset length can be determined according to the RR interval value of the target heartbeat. For example, it can be the length corresponding to 1.5 times the RR interval value.

[0065] In the embodiment of the present application, based on the step of S103, the electronic device can automatically locate the heartbeat immediately before all the missed heartbeats in the electrocardiogram data, that is, the above-mentioned target heartbeat.

[0066] After the electronic device locates the target heartbeat, multiple target heartbeats can be determined therefrom. For each target heartbeat, the electrocardiogram within a period of time before and after the target heartbeat can be used as the electrocardiogram segment of the target heartbeat. That is, the waveform diagram of the target heartbeat not only includes the electrocardiogram of the target heartbeat itself, but also includes the electrocardiogram within a period of time after the target heartbeat. Since the missed heartbeat is at the position after the target heartbeat, at least the waveform corresponding to the length of one heartbeat needs to be retained after the target heartbeat in the electrocardiogram segment corresponding to the target heartbeat. For example, the electrocardiogram segment of the target heartbeat can include the electrocardiogram signal diagram within 1 s after the target heartbeat.

[0067] In another possible implementation, the user can also manually select the ECG segment corresponding to the target heartbeat. The user can circle the corresponding ECG segment in the ECG data, and the electronic device can obtain the corresponding ECG segment from the ECG data according to the user's circling operation.

[0068] S104. Perform superposition processing on the multiple ECG segments to obtain a superposition diagram.

[0069] Based on the R-wave peak position as a reference, the ECG segments of multiple target heartbeats can be superimposed to obtain a superposition diagram. Based on the R-wave peak position as a reference, it is equivalent to aligning the R-wave peak positions of the target heartbeats in each ECG segment, so as to perform superposition in the ECG segments.

[0070] In the ECG data, the QRS wave of the heartbeat generally has obvious characteristics and is relatively easy to locate. Therefore, based on the R-wave peak of the QRS wave of the target heartbeat as a reference, the waveform diagrams of each target heartbeat can be superimposed together to obtain a superimposed waveform diagram. Figure 4 It is a schematic diagram of a superimposed waveform diagram provided by an embodiment of the present application. As Figure 4 shown, the central heartbeat position is the aligned R-wave peak position.

[0071] In a possible implementation, if the waveform in the superimposed waveform diagram is to be obvious, it is necessary to ensure that the waveforms of the target heartbeats are similar. If the RR interval values of the target heartbeats are similar, then their wavelengths are relatively close, and correspondingly, the waveforms are more likely to be similar. Therefore, the waveform diagrams of multiple target heartbeats with similar RR interval values can be selected for superposition.

[0072] In the superimposed waveform diagram, if the waveforms of the multiple target heartbeats superimposed are not highly similar, the waveforms in the superposition diagram are relatively messy. At this time, it is difficult to monitor missed heartbeats from the superposition diagram based on waveform characteristics. Therefore, when the waveform similarity between the target heartbeats in the superposition diagram does not meet the preset requirements, the superposition diagram can be split into multiple superposition diagrams, and the waveform similarity between the multiple target heartbeats corresponding to each superposition diagram meets the preset requirements. When the waveform similarity between the target heartbeats in the superimposed waveform diagram meets the preset requirements, the superimposed waveform diagram can be used as a superposition diagram.

[0073] In a possible implementation, it is possible to determine whether the waveform similarities between target heartbeats meet a preset requirement based on the waveform similarity between a target heartbeat and a heartbeat template. Exemplarily, the similarity between each target heartbeat and the heartbeat template can be calculated respectively, and then multiple target heartbeats with similarities within the same range can be grouped into one group. For the waveform diagrams of multiple target heartbeats in each group, they are superimposed to obtain a superimposed diagram. For the superimposed diagram, after the R peaks are aligned, the occurrence times and morphologies of the subsequent T waves are highly consistent. Among them, the waveform similarity between the target heartbeat and the heartbeat template can be characterized based on the waveform similarity between the QRS wave of the target heartbeat and the QRS wave of the heartbeat template. The above-mentioned heartbeat template can be a heartbeat randomly selected from the electrocardiogram data, or a preset heartbeat. During the calculation process, the morphology of the heartbeat template can be updated and the number can be expanded based on the heartbeats in the electrocardiogram data.

[0074] Figure 5 is a schematic diagram for splitting the superimposed diagram provided by an embodiment of the present application. From Figure 4 it can be seen that the superimposed effect of the heartbeat located at the center position in the superimposed diagram is not good. Therefore, it is necessary to Figure 4 split the superimposed diagram into multiple superimposed diagrams. As Figure 5 shown, Figure 4 the superimposed diagram in

[0075] can be split into two upper and lower superimposed diagrams. After splitting, the waveform superimposed effect in each superimposed diagram is better.

[0076] S105, monitor the missed heartbeats in the electrocardiogram data according to the superimposed diagram.

[0077] When monitoring the missed heartbeats, the superimposed waveform in the superimposed diagram can be obtained; the band with the QRS morphology in the superimposed waveform is identified. The band with the QRS morphology is the band composed of the QRSs of the target heartbeats, and the waveform characteristics are relatively obvious. When there are missed heartbeats after the target heartbeat, the waveforms of the missed heartbeats are generally similar to the waveforms of the target heartbeats. Therefore, the QRS wave amplitude and T wave amplitude of the missed heartbeats can be characterized by the QRS wave amplitude and T wave amplitude of the target heartbeat. Therefore, the QRS wave amplitude and T wave amplitude of the band with the QRS morphology can be determined; then, according to the QRS wave amplitude and T wave amplitude, different methods are used to determine whether the electrocardiogram data includes missed heartbeats.

[0078] When monitoring missed heartbeats, the band to be monitored can be determined from the superimposed graph. The superimposed graph may include waveforms obtained by superimposing target heartbeats, and the waveforms may include QRS waves and T waves. The end position of the QRS wave, the start position of the T wave, and the end position of the T wave of the superimposed graph can be identified based on image recognition technology or other monitoring technologies. The position after the end position of the T wave is where the next heartbeat may exist. Therefore, the end position of the T wave can be used as the start position of the band to be monitored.

[0079] The superimposed graph is obtained by superimposing multiple target heartbeats with similar morphologies based on the peak value of the R wave. Therefore, the closer to the peak position of the R wave in the superimposed graph, the better the waveform superimposition effect and the more obvious the waveform characteristics. Since in this application, missed heartbeats are monitored based on waveform characteristics, the waveform characteristics in the band to be monitored need to be relatively obvious. Therefore, in this embodiment, only the adjacent positions of the target heartbeats are monitored for missed heartbeats. That is to say, the length of the band to be monitored can be the length that a heartbeat may occupy. In a possible implementation manner, the length of the band to be monitored can be set by the user according to experience. In another possible implementation manner, the length that a heartbeat may occupy can be the RR interval value. Therefore, the average RR interval value of multiple target heartbeats in the superimposed graph can be determined; then, according to the average RR interval value, the band length of the band to be monitored can be determined. Exemplarily, the band length of the band to be monitored can be 1.5 times the average RR interval value.

[0080] Based on the start position and the band length of the band to be monitored, the band to be monitored can be determined from the superimposed graph. The band to be monitored is the possible range of the next heartbeat of the target heartbeat in the superimposed graph.

[0081] In a possible implementation manner, the band to be monitored in the superimposed graph can be manually selected by the user. The electronic device can display the superimposed graph; when the electronic device detects a selection operation by the user on the superimposed graph, the band corresponding to the selection operation can be used as the band to be monitored.

[0082] The electronic device can also determine the baseline floating range of the ECG data. The ECG data has a baseline, which is a straight line. When the myocardial cells are in a resting state or a polarized state, the electric couple on the membrane surface disappears, the potentials at all locations are equal and there is no potential difference. The straight line recorded by the ammeter is the isopotential line. The isopotential line exists on the baseline of the ECG data. The sampling points within the baseline range generally do not form a waveform. Therefore, when determining the waveform characteristics, the sampling points within the baseline range can be eliminated. If the sampling points within the baseline range are to be eliminated, the baseline floating range needs to be determined. Under normal circumstances, the isopotential line includes three parts: the PR segment, the ST segment, and the TP segment. The baseline and the isopotential line are on the same horizontal line. When the end position of the QRS wave and the starting position of the T wave are determined, it is equivalent to determining the ST segment. Therefore, the baseline range of the overlay graph can be determined based on the ST segment. Figure 6 It is a schematic diagram of the ST segment of the overlay diagram provided in the embodiment of the present application. Figure 6 The band between the two vertical lines is the ST segment.

[0083] In one possible implementation, the range of the ST segment can be directly identified based on image recognition technology, and the range of the ST segment can be used as the baseline range. In another possible implementation, the baseline range can be determined based on the distribution characteristics of the sampling points of the ST segment. Exemplarily, the ST segment of the overlay image can be divided into three equal segments. Since the front and rear segments of the ST segment are respectively connected to the wave, the amplitude of the sampling points at the connection may be too large. In order to determine the baseline range more accurately, it can be determined based on the middle segment of the ST segment. Specifically, the number of sampling points in different height areas corresponding to the middle segment of the ST segment can be counted; then the baseline range is determined based on the number of sampling points obtained by counting. For example, the ST segment can be divided into 3 segments on average, each with a length of X ms; then a rectangular box is created with a width of X ms and a height of Y mV. Then align the rectangular box with the middle segment position, slide from top to bottom and count the number of sampling points in the box. With the moving distance of the rectangular box as the horizontal coordinate and the number of sampling points in the box as the vertical coordinate, a trapezoidal diagram is formed in the coordinate system, such as Figure 7 The height range corresponding to the upper and lower sides in the ladder diagram is the baseline range.

[0084] Exemplarily, the electronic device can obtain the QRS wave end position and the T wave starting position in the superimposed waveform; determine the ST segment according to the QRS wave end position and the T wave starting position; divide the ST segment into three segments; and set a sliding window; align the sliding window with the middle segment of the ST segment and slide it along the set route; synchronously count the number of sampling points in the sliding window; set the horizontal coordinate according to the moving distance of the sliding window, set the number of sampling points as the vertical coordinate, and draw a trapezoidal diagram in the plane coordinate system; determine the baseline floating range of the superimposed diagram according to the trapezoidal diagram.

[0085] By removing the sampling points within the baseline floating range in the band to be monitored, the image to be monitored can be obtained. Then, it is possible to determine whether the image to be monitored includes missed heartbeats based on the amplitudes of QRS waves and T waves.

[0086] When monitoring missed heartbeats, different processing methods can be determined based on the amplitudes of QRS waves and T waves. When it is determined that the amplitude of the QRS wave is greater than the amplitude of the T wave, the number and dispersion of sampling points in the image to be monitored are statistically analyzed; if the statistical result meets the third set condition, it can be determined that the electrocardiogram data includes missed heartbeats. If the amplitude of the QRS wave is greater than the amplitude of the T wave, the number feature and dispersion feature of the sampling points can be used as waveform features to monitor missed heartbeats. Exemplarily, the number and dispersion of sampling points in the band to be monitored can be statistically analyzed, and missed heartbeats can be monitored based on the statistical results. For example, as Figure 8 shown, a rectangular sliding window can be determined, and then it starts sliding from the starting position of the band to be monitored to determine the number and dispersion of sampling points within each sliding window, and the number and dispersion of sampling points are statistically analyzed at different heights. Then, based on the statistical results, the electronic device can monitor missed heartbeats based on preset logical judgment conditions. Or the statistical results can be displayed, and then the user can circle out the missed heartbeats according to the statistical results. Since the amplitude of the QRS wave is greater than the amplitude of the T wave, therefore, within the region where the amplitude is greater than that of the T wave, if there are a preset number of sampling points in the target region and the dispersion of the sampling points reaches the preset value, it can be considered that there is a QRS wave of a missed heartbeat in the target region. As Figure 8 shown, the region corresponding to the rectangular frame is the region where the QRS wave of the missed heartbeat is located.

[0087] When it is determined that the amplitude of the QRS wave is less than or equal to the amplitude of the T wave, starting from the end position of the T wave, the amplitudes of all sampling points within the sliding window within the preset time are obtained and superimposed. If the amplitude of the QRS wave is less than or equal to the amplitude of the T wave, the amplitude feature of the sampling point is used as the waveform feature to determine the insertion position. The electronic device can monitor missed heartbeats based on the amplitudes of the sampling points within the band to be monitored. When monitoring missed heartbeats, multiple rectangular regions can be determined according to the band to be monitored, and the amplitudes of each sampling point within each rectangular region are determined. Based on the above-determined baseline range, the sampling points within the baseline range in each rectangular region are removed; then, within each rectangular region, the multiple maximum absolute values of the amplitudes of the sampling points corresponding to multiple target heartbeats are determined, as well as the differences between the amplitudes of the sampling points corresponding to each maximum absolute value and the relevant sampling points, where the relevant sampling points can be two sampling points apart from the sampling point; then, based on the differences, the target region where the QRS wave of the missed heartbeat is located can be determined from multiple rectangular regions. The electronic device can calculate the sum of differences of the differences corresponding to multiple target heartbeats in each rectangular region respectively; then determine the maximum value of the sum of differences in multiple rectangular regions; if the maximum value is greater than the preset threshold, the rectangular region corresponding to the maximum value is determined as the target region. After determining the target region, the electronic device can monitor missed heartbeats from the target region. Specifically, the electronic device can calculate the slope of each sampling point within the target region; then use the position of the sampling point corresponding to the maximum slope value as the R-wave peak position of the missed heartbeat, and the R-peak position is used to characterize the missed heartbeat. The slope value of the sampling point can be the slope of the wave at the position corresponding to the sampling point. Figure 9 is a schematic diagram provided by an embodiment of the present application where the amplitude of the QRS wave is less than or equal to the amplitude of the T wave; as Figure 9 shown, the area corresponding to the rectangular frame is the area where the QRS wave of the missed heartbeat is located.

[0088] Exemplarily, starting from the end position of the T wave, the amplitudes of all sampling points within the sliding window of K ms are calculated. The sliding window continuously moves backward without overlap, and the above steps are repeated. All sampling points included within the floating range are removed from the superimposed graph. And the proportion of sampling points exceeding the baseline range under each sliding window is statistically synchronized. Within one pulse range, the maximum value of the absolute value of each electrocardiogram data included is queried, and then the difference between the maximum value and the amplitude of the point corresponding to two points apart is calculated. The cumulative sum Sum1 of all differences within the pulse range is calculated. The above steps are repeated for each pulse, and then Sum2, Sum3,... are obtained. When the pulse corresponding to the maximum value of Sum satisfies the threshold P, it corresponds to the position of the missed QRS wave. For all participating heartbeats, within the above-determined position range, the position of the maximum slope, that is, the R-wave peak position of the missed heartbeat, is found.

[0089] In the above process, an option for manual operation can also be added to increase the flexibility of the function. For example, the user can manually select the range of the superimposed heartbeats on the scatter plot, and then the electronic device groups the heartbeats within the selected range. The user can also manually group the QRS wave patterns of the superimposed graph. The user can manually define the range of the inserted heartbeats, and the electronic device uses the range selected by the user as the waveband to be monitored, and performs precise positioning of the heartbeats within the defined range based on S105 in this embodiment.

[0090] In the embodiment of the present application, the R peak position of the missed heartbeats can be determined based on the superimposed graph. After the R peak position of the missed heartbeats, it is equivalent to determining the position of the missed heartbeats. Monitoring the missed heartbeats based on the superimposed graph can greatly reduce the computational complexity and the difficulty of determining the missed heartbeats compared to monitoring the missed heartbeats based on a deep learning model.

[0091] Refer to Figure 10 , which shows a schematic flowchart of steps of another heartbeat monitoring method provided by the embodiment of the present application, and specifically may include the following steps:

[0092] S1001, construct an electrocardiogram scatter plot based on multiple RR intervals of electrocardiogram data, where the electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to a heartbeat in the electrocardiogram data.

[0093] S1002, determine multiple target heartbeats according to the electrocardiogram scatter plot, where the target heartbeats are used to determine the position to be monitored of the electrocardiogram data.

[0094] S1003, obtain the electrocardiogram segments corresponding to each of the target heartbeats from the electrocardiogram data.

[0095] S1004, perform a superimposition process on the multiple electrocardiogram segments to obtain a superimposed graph.

[0096] S1005, monitor the missed heartbeats in the electrocardiogram data according to the superimposed graph.

[0097] S1001 - S1005 in this embodiment is similar to S101 - S105 in the previous embodiment and can be referred to each other, and will not be elaborated here.

[0098] S1006, if it is monitored that the electrocardiogram data includes missed heartbeats, update the scatter points corresponding to the missed heartbeats to the electrocardiogram scatter plot.

[0099] After performing superposition processing on multiple target heartbeats in the electrocardiogram scatter plot to monitor whether there is a missed heartbeat after the target heartbeat, if there is a missed heartbeat after the target heartbeat, the R-wave peak position of the missed heartbeat can be identified, and based on the R-wave peak position of the missed heartbeat, the RR interval value of the missed heartbeat can be calculated, so that the scatter point corresponding to the missed heartbeat can be updated to the electrocardiogram scatter plot.

[0100] If there is no missed heartbeat after the target heartbeat, the scatter point corresponding to the target heartbeat can be marked, so that in the subsequent identification process of the missed heartbeat, this scatter point does not need to be processed. Exemplarily, the scatter point corresponding to the target heartbeat can be deleted from the electrocardiogram scatter plot.

[0101] S1007, based on the updated scatter plot, continue to monitor the electrocardiogram data for missed heartbeats.

[0102] When monitoring for missed heartbeats after the target heartbeat, the target heartbeat can be directly used as the waveform template for the missed heartbeat; or the heartbeat template for the missed heartbeat can be obtained based on deep learning. After determining the heartbeat template, the R-peak position of the missed heartbeat template can be aligned with the R-peak position monitored in the previous step, and the missed heartbeat template can be inserted into the electrocardiogram data.

[0103] Taking the heartbeats in the range of y>k*x to y<(k + 1)*x as an example, extract the electrocardiogram signals for a period of time before and after the heartbeats corresponding to all scatter points in the selected grid, and perform heartbeat superposition based on the R-wave peak to form a superposition diagram. Then, through the following superposition diagram heartbeat missed detection algorithm, monitor the first missed heartbeat after the current heartbeat, and mark the positions of the heartbeats without missed detection.

[0104] After processing all the grouped heartbeats in the selected grid with the superposition diagram heartbeat missed detection algorithm, perform the monitoring operation for missed heartbeats and update the scatter plot. If there are still scatter points in the abnormal area in the updated scatter plot, continue to perform the monitoring for missed heartbeats based on the updated scatter plot. Exemplarily, after the scatter plot is updated, query again whether there are scatter points in the currently processed grid. If there are still scatter points, continue to select multiple scatter points and execute steps S1003 and S1005 until there are no missed heartbeats within the selected grid range, and then process the scatter points of the next grid.

[0105] In the embodiments of the present application, the detected heartbeats can be used to form a scatter plot and a superposition diagram, and based on the RR interval characteristics and the statistical characteristics of the superposition waveform reflected by these two graphs, the automatic positioning and intelligent insertion of the missed heartbeats can be realized to improve the heartbeat monitoring result. Based on the solution in the present application, the monitoring difficulty can be reduced.

[0106] The scatter plots of electrocardiogram (ECG) in this application can comprehensively locate missed heartbeats and sequentially monitor the missed heartbeats of the target heartbeats in the first area, which may have the following effects. If there are multiple missed heartbeats between the first heartbeat and the second heartbeat, when monitoring the missed heartbeats of the heartbeats after the first heartbeat based on the superimposed graph, the third heartbeat adjacent to the first heartbeat can be updated in the scatter plot; at this time, the scatter point corresponding to the third heartbeat can also be updated in the ECG scatter plot, and then the missed heartbeats between the third heartbeat and the second heartbeat can be continuously monitored. Based on this, the heartbeat monitoring method in this application can achieve comprehensive monitoring of missed heartbeats.

[0107] It should be noted that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0108] Refer to Figure 11 , which shows a schematic diagram of a heartbeat monitoring device provided by an embodiment of this application. Specifically, it may include an ECG scatter plot construction module 1101, a target heartbeat determination module 1102, an ECG segment determination module 1103, a superimposition module 1104, and a monitoring module 1105, where:

[0109] The ECG scatter plot construction module 1101 is used to construct an ECG scatter plot based on multiple RR intervals of the ECG data. The ECG scatter plot includes multiple scatter points, and each scatter point corresponds to a heartbeat in the ECG data;

[0110] The target heartbeat determination module 1102 is used to determine multiple target heartbeats according to the ECG scatter plot. The target heartbeats are used to determine the positions to be monitored of the ECG data;

[0111] The ECG segment determination module 1103 is used to obtain the ECG segments corresponding to each of the target heartbeats from the ECG data;

[0112] The superimposition module 1104 is used to perform a superimposition process on multiple ECG segments to obtain a superimposed graph;

[0113] The monitoring module 1105 is used to monitor the missed heartbeats of the ECG data according to the superimposed graph.

[0114] In a possible implementation manner, the above device further includes:

[0115] An update module, which is used to update the scatter points corresponding to the missed heartbeats to the ECG scatter plot if it is monitored that the ECG data includes missed heartbeats;

[0116] The above monitoring module 1105 is further configured to continue to monitor missed heartbeats in the electrocardiogram data based on the updated scatter plot.

[0117] In a possible implementation, the above target heartbeat determination module 1102 includes:

[0118] A cutting sub-module, configured to cut the electrocardiogram scatter plot into multiple grids according to set conditions;

[0119] A determination sub-module, configured to determine multiple target heartbeats from the scatter plot according to the grids.

[0120] In a possible implementation, the above cutting sub-module is configured to:

[0121] A first determination unit, configured to determine a first region in the electrocardiogram scatter plot that satisfies a first set condition;

[0122] A second determination unit, configured to cut the first region according to a second set condition to obtain multiple grids.

[0123] In a possible implementation, the above target heartbeat determination module 1102 includes:

[0124] A display sub-module, configured to display the electrocardiogram scatter plot;

[0125] An identification sub-module, configured to use the heartbeat corresponding to the selected scatter point on the electrocardiogram scatter plot as the target heartbeat if a selection operation on the scatter points on the electrocardiogram scatter plot is detected.

[0126] In a possible implementation, the above superposition module 1104 includes:

[0127] A superposition sub-module, configured to perform a superposition process on multiple electrocardiogram segments based on the R-wave peak positions of multiple target heartbeats to form a superposition diagram.

[0128] In a possible implementation, the above monitoring module 1105 includes:

[0129] A superposition waveform acquisition sub-module, configured to acquire the superposition waveform in the superposition diagram;

[0130] An identification sub-module, configured to identify the band with QRS morphology in the superposition waveform and determine the QRS wave amplitude and T wave amplitude of the band with QRS morphology;

[0131] A monitoring sub-module, configured to determine whether the electrocardiogram data includes missed heartbeats according to the QRS wave amplitude and the T wave amplitude.

[0132] In a possible implementation, the above monitoring sub-module includes:

[0133] A baseline floating range determination unit for determining the baseline floating range of the electrocardiogram data;

[0134] A to-be-monitored band determination unit for determining the to-be-monitored band in the superimposed graph;

[0135] A to-be-monitored image determination unit for removing the sampling points within the baseline floating range in the to-be-monitored band to obtain a to-be-monitored image;

[0136] A monitoring unit for determining whether the to-be-monitored image includes missed detected heartbeats according to the QRS wave amplitude and the T wave amplitude.

[0137] In a possible implementation manner, the above-mentioned to-be-monitored band determination unit includes:

[0138] A superimposed graph display subunit for displaying the superimposed graph;

[0139] A to-be-monitored band identification subunit for, when detecting a user's circle selection operation on the superimposed graph, using the band corresponding to the circle selection operation as the to-be-monitored band.

[0140] In a possible implementation manner, the above-mentioned baseline floating range determination unit includes:

[0141] A position acquisition subunit for acquiring the QRS wave end position and the T wave start position in the superimposed waveform;

[0142] An ST segment determination subunit for determining the ST segment according to the QRS wave end position and the T wave start position;

[0143] A division subunit for dividing the ST segment into three segments; and setting a sliding window;

[0144] A sliding subunit for aligning the sliding window with the middle segment of the ST segment and sliding it along a set route;

[0145] A statistics subunit for synchronously counting the number of sampling points within the sliding window;

[0146] A plotting subunit for setting the abscissa according to the moving distance of the sliding window and setting the number of sampling points as the ordinate, and plotting a trapezoid graph in a plane coordinate system;

[0147] A determination subunit for determining the baseline floating range of the superimposed graph according to the trapezoid graph.

[0148] In a possible implementation manner, the above-mentioned monitoring unit includes:

[0149] The first judgment subunit is configured to, when determining that the amplitude of the QRS wave is greater than the amplitude of the T wave, count the number and dispersion of sampling points in the image to be monitored.

[0150] The first determination subunit is configured to determine that the electrocardiogram data includes missed heartbeats if the statistical result meets the third set condition.

[0151] In a possible implementation manner, the above monitoring unit includes:

[0152] The second judgment subunit is configured to, when determining that the amplitude of the QRS wave is less than or equal to the amplitude of the T wave, obtain the amplitude superposition of all sampling points within a sliding window within a preset time starting from the end position of the T wave.

[0153] The plotting subunit is configured to continuously move the sliding window and plot a curve graph according to the amplitude information output by each sliding window.

[0154] The monitoring subunit is configured to process the curve graph and monitor and obtain the characteristic information of a rectangular pulse.

[0155] The accumulation subunit is configured to obtain the accumulated difference value corresponding to all heartbeats within a pulse range.

[0156] The second determination subunit is configured to determine that the position corresponding to the accumulated difference value is the R wave peak position of the missed heartbeat if the accumulated difference value meets the fourth set condition.

[0157] In a possible implementation manner, the above monitoring unit includes:

[0158] The image to be monitored display subunit is configured to display the image to be monitored.

[0159] The R wave peak position recognition subunit is configured to, when detecting a marking operation by a user in the image to be monitored, determine the position corresponding to the marking operation as the R wave peak position of the missed heartbeat.

[0160] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For related parts, refer to the description in the method embodiment section.

[0161] The embodiment of the present application further provides an electrocardiogram monitoring system, which includes: an electrocardiogram data acquisition module, an R wave recognition module, and a missed heartbeat monitoring module, where:

[0162] The electrocardiogram data acquisition module is configured to acquire electrocardiogram data to be processed.

[0163] The R wave recognition module is configured to identify the R wave peak position of a heartbeat from the electrocardiogram data, and the R wave peak position is used to determine the RR interval corresponding to the heartbeat.

[0164] The missed heartbeat monitoring module is used to construct an electrocardiogram scatter plot based on multiple RR intervals. The electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to a heartbeat in the electrocardiogram data. According to the electrocardiogram scatter plot, multiple target heartbeats are determined, and the target heartbeats are used to determine the positions to be monitored in the electrocardiogram data. An electrocardiogram segment corresponding to each target heartbeat is obtained from the electrocardiogram data. The multiple electrocardiogram segments are subjected to superposition processing to obtain a superposition diagram. The electrocardiogram data is monitored for missed heartbeats according to the superposition diagram.

[0165] Figure 12 This is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 12 shown, the electronic device 120 in this embodiment includes: at least one processor 1200 ( Figure 12 only one is shown in the figure), a memory 1201, and a computer program 1202 stored in the memory 1201 and executable on the at least one processor 1200. When the processor 1200 executes the computer program 1202, the steps in any of the above method embodiments are implemented.

[0166] The electronic device 120 may be a desktop computer, a notebook, a palm computer, a cloud server, or other electronic devices. The electronic device may include, but is not limited to, a processor 1200 and a memory 1201. Those skilled in the art can understand that Figure 12 this is only an example of the electronic device 120, and does not limit the electronic device 120. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0167] The so-called processor 1200 may be a central processing unit (CPU), and this processor 1200 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0168] In some embodiments, the memory 1201 may be an internal storage unit of the electronic device 120, such as a hard disk or memory of the electronic device 120. In some other embodiments, the memory 1201 may also be an external storage device of the electronic device 120, such as a plug-in hard disk equipped on the electronic device 120, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 1201 may also include both the internal storage unit and the external storage device of the electronic device 120. The memory 1201 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program, etc. The memory 1201 may also be used to temporarily store data that has been output or will be output.

[0169] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0170] An embodiment of the present application provides a computer program product, and when the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executed.

[0171] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. Heartbeat monitoring method, characterized in that, it includes the following steps: Based on multiple RR intervals of electrocardiogram data, construct an electrocardiogram scatter plot, the electrocardiogram scatter plot includes multiple scatter points, and each scatter point corresponds to one heartbeat in the electrocardiogram data; According to the electrocardiogram scatter plot, determine multiple target heartbeats, and the target heartbeats are used to determine the positions to be monitored in the electrocardiogram data; Obtain the electrocardiogram segments corresponding to each of the target heartbeats from the electrocardiogram data; Perform superposition processing on multiple electrocardiogram segments to obtain a superposition map; Monitor missed heartbeats in the electrocardiogram data according to the superposition map.

2. The heartbeat monitoring method according to claim 1, characterized in that, it further includes: If it is monitored that the electrocardiogram data includes missed heartbeats, update the scatter points corresponding to the missed heartbeats to the electrocardiogram scatter plot; Based on the updated scatter plot, continue to monitor missed heartbeats in the electrocardiogram data.

3. The heartbeat monitoring method according to claim 2, characterized in that, The step of determining multiple target heartbeats according to the scatter plot includes: Cut the electrocardiogram scatter plot into multiple grids according to set conditions; Determine multiple target heartbeats from the scatter plot according to the grids.

4. The heartbeat monitoring method according to claim 3, characterized in that, The step of cutting the electrocardiogram scatter plot into multiple grids according to set conditions includes: Determine a first region in the electrocardiogram scatter plot that satisfies a first set condition; Cut the first region according to a second set condition to obtain multiple grids.

5. The heartbeat monitoring method according to any one of claims 1 to 4, characterized in that, The step of determining multiple target heartbeats according to the scatter plot includes: Display the electrocardiogram scatter plot; If a selection operation on the scatter points on the electrocardiogram scatter plot is monitored, use the heartbeat corresponding to the selected scatter point as the target heartbeat.

6. The heartbeat monitoring method according to claim 5, characterized in that, The step of performing superposition processing on multiple electrocardiogram segments to obtain a superposition map includes the following steps: Based on the R-wave peak positions of multiple target heartbeats, perform superposition processing on multiple electrocardiogram segments to form a superposition map.

7. The heartbeat monitoring method according to claim 1, characterized in that, The step of monitoring missed heartbeats in the electrocardiogram data according to the superposition map includes the following steps: Obtain the superimposed waveform in the superposition map; Identify the bands with QRS morphology in the superimposed waveform, and determine the QRS wave amplitude and T wave amplitude of the bands with QRS morphology; Determine whether the electrocardiogram data includes missed heartbeats according to the QRS wave amplitude and the T wave amplitude.

8. The heartbeat monitoring method according to claim 7, characterized in that, The step of determining whether the electrocardiogram data includes missed heartbeats according to the QRS wave amplitude and the T wave amplitude includes: Determine the baseline floating range of the electrocardiogram data; Determine the band to be monitored in the superposition map; Remove the sampling points within the baseline floating range in the band to be monitored to obtain an image to be monitored; Determine whether the image to be monitored includes missed heartbeats according to the QRS wave amplitude and the T wave amplitude.

9. The heartbeat monitoring method according to claim 8, characterized in that, the determination of the wave band to be monitored in the superimposed graph includes: displaying the superimposed graph; when a user's selection operation on the superimposed graph is detected, the wave band corresponding to the selection operation is used as the wave band to be monitored.

10. The heartbeat monitoring method according to claim 8, characterized in that, the determination of the baseline floating range of the electrocardiogram data includes: obtaining the end position of the QRS wave and the start position of the T wave in the superimposed waveform; determining the ST segment according to the end position of the QRS wave and the start position of the T wave; dividing the ST segment into three segments; and setting a sliding window; aligning the sliding window with the middle segment of the ST segment and sliding it along a set route; synchronously counting the number of sampling points within the sliding window; setting the abscissa according to the moving distance of the sliding window and setting the number of sampling points as the ordinate, and drawing a ladder diagram in a plane coordinate system; determining the baseline floating range of the superimposed graph according to the ladder diagram.

11. The heartbeat monitoring method according to claim 8, characterized in that, the determination of whether the image to be monitored includes missed detected heartbeats according to the amplitude of the QRS wave and the amplitude of the T wave includes the following steps: when it is determined that the amplitude of the QRS wave is greater than the amplitude of the T wave, counting the number and dispersion of sampling points in the image to be monitored; if the statistical result meets the third set condition, it is determined that the electrocardiogram data includes missed detected heartbeats.

12. The heartbeat monitoring method according to claim 8, characterized in that, the determination of whether the image to be monitored includes missed detected heartbeats according to the amplitude of the QRS wave and the amplitude of the T wave includes the following steps: when it is determined that the amplitude of the QRS wave is less than or equal to the amplitude of the T wave, starting from the end position of the T wave, obtaining the amplitude superposition of all sampling points within the sliding window within a preset time; continuously moving the sliding window and drawing a curve graph according to the amplitude information output by each sliding window; processing the curve graph and monitoring and obtaining the characteristic information of the rectangular pulse; within a pulse range, obtaining the cumulative value of the differences corresponding to all heartbeats, if the cumulative value of the differences meets the fourth set condition, determining the position corresponding to the cumulative value of the differences as the peak position of the R wave of the missed detected heartbeat.

13. The heartbeat monitoring method according to claim 8, characterized in that, the determination of whether the image to be monitored includes missed detected heartbeats according to the amplitude of the QRS wave and the amplitude of the T wave includes: displaying the image to be monitored; when a user's marking operation in the image to be monitored is detected, determining the position corresponding to the marking operation as the peak position of the R wave of the missed detected heartbeat.

14. A heartbeat monitoring device, characterized in that, it includes: an electrocardiogram scatter plot construction module, configured to construct an electrocardiogram scatter plot based on multiple RR intervals of electrocardiogram data, the electrocardiogram scatter plot including multiple scatter points, each scatter point corresponding to a heartbeat in the electrocardiogram data; a target heartbeat determination module, configured to determine multiple target heartbeats according to the electrocardiogram scatter plot, the target heartbeats being used to determine the position to be monitored of the electrocardiogram data; An electrocardiogram segment determination module, configured to obtain an electrocardiogram segment corresponding to each of the target heartbeats from the electrocardiogram data; An overlay module, configured to perform an overlay process on a plurality of the electrocardiogram segments to obtain an overlay graph; A monitoring module, configured to monitor missed heartbeats in the electrocardiogram data according to the overlay graph.

15. An electrocardiogram monitoring system, characterized in that, the electrocardiogram monitoring system includes: an electrocardiogram data acquisition module, an R-wave identification module, and a missed heartbeat monitoring module, wherein: the electrocardiogram data acquisition module is configured to acquire electrocardiogram data to be processed; the R-wave identification module is configured to identify the peak position of the R-wave of a heartbeat from the electrocardiogram data, and the peak position of the R-wave is used to determine the RR interval corresponding to the heartbeat; The missed heartbeat monitoring module is configured to construct an electrocardiogram scatter plot based on a plurality of RR intervals, the electrocardiogram scatter plot includes a plurality of scatter points, and each scatter point corresponds to a heartbeat in the electrocardiogram data; determine a plurality of target heartbeats according to the electrocardiogram scatter plot, the target heartbeats are used to determine the position to be monitored of the electrocardiogram data; obtain an electrocardiogram segment corresponding to each of the target heartbeats from the electrocardiogram data; perform an overlay process on a plurality of the electrocardiogram segments to obtain an overlay graph; and monitor missed heartbeats in the electrocardiogram data according to the overlay graph.

16. An electronic device, characterized in that, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method described in claims 1-13 is implemented.

17. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the method described in claims 1-13 is implemented.

Images