Electrocardiosignal processing method, system and equipment and storage medium

Abstract

The invention is suitable for the technical field of signal processing, and provides an electrocardiosignal processing method, system and device and a storage medium. According to the electrocardiosignal processing method, the operation instruction is responded, the corresponding functional component is called according to the operation instruction to process the stored result file, and the current electrocardiosignal analysis data is obtained; the current electrocardiogram analysis data is used as the result file, the stored result file is updated, any one or more functional components can be flexibly called to process the processed stored result file again, and discretization of the electrocardiogram signal processing function is achieved. The corresponding functional component can be called according to the actual demand of the user, so that targeted local processing can be performed on part of the electrocardiosignals according to the actual demand, and compared with global processing performed on the complete electrocardiosignals by re-operating the preset analysis model, the local processing can improve the processing freedom degree and the processing speed of the electrocardiosignals, and the processing efficiency is improved. And the diagnosis efficiency of doctors is improved.

Description

Technical Field

[0001] This application belongs to the technical field of signal processing, and particularly relates to an electrocardiogram (ECG) signal processing method, system, device, and storage medium. Background Art

[0002] Dynamic electrocardiogram (ECG) examination is a long-term electrocardiogram examination method in clinical practice. By wearing a dynamic ECG recorder for a long time, users can record ECG waveform information for more than 24 hours. Doctors can view the ECG waveform information immediately through a dynamic ECG analysis system or replay the historical ECG waveform information, obtain characteristic information, and issue a diagnostic report, which greatly improves the efficiency of electrocardiogram examination.

[0003] Currently, a dynamic ECG analysis system processes ECG signals through a preset analysis model. The preset analysis model can adjust parameters according to the needs of doctors or patients. For example, user age, event judgment threshold, or the switch of a certain sub-analysis function, etc. After adjusting the parameters and processing the ECG signals, it is necessary to run the preset analysis model completely again. ECG signals can help diagnose various heart diseases and the medical principles of heart diseases are relatively complex, and it is easy to need to adjust parameters and perform multiple processes in a comprehensive diagnosis. The more processes are performed, the more time doctors need to wait for the preset analysis model to execute the analysis, resulting in a decrease in diagnostic efficiency. Therefore, how to improve the processing efficiency of ECG signals has become an urgent problem to be solved currently. Summary of the Invention

[0004] In view of this, the embodiments of this application provide an ECG signal processing method to solve the problem that the existing dynamic ECG analysis system has low processing efficiency for ECG signals, resulting in low diagnostic efficiency.

[0005] The first aspect of the embodiments of this application provides an ECG signal processing method, including:

[0006] Responding to an operation instruction, calling a corresponding functional component according to the operation instruction to process a stored result file, and obtaining current ECG analysis data;

[0007] Taking the current ECG analysis data as a result file and updating the stored result file.

[0008] In the first aspect of the embodiments of the present application, a method for processing electrocardiogram (ECG) signals is provided. By responding to an operation instruction, the corresponding functional component is called according to the operation instruction to process the stored result file, and the current ECG analysis data is obtained. Taking the current ECG analysis data as the result file and updating the stored result file, any one or more functional components can be flexibly called to process the result file that has been processed and stored locally again, realizing the discretization of the ECG signal processing function. And the corresponding functional component can be called according to the actual needs of the user, so that partial processing can be performed on some ECG signals. Compared with re-running the preset analysis model to perform global processing on the complete ECG signals, local processing can improve the processing freedom and processing speed of the ECG signals, thereby improving the doctor's diagnosis efficiency.

[0009] In the second aspect of the embodiments of the present application, an ECG signal processing system is provided, including a processing end and a display end, and the processing end is connected to the display end;

[0010] The display end is used to display an operation interface and generate a corresponding operation instruction in response to an operation action of the user in the operation interface;

[0011] The processing end is used for:

[0012] Responding to an operation instruction, calling the corresponding functional component according to the operation instruction to process the stored result file, and obtaining the current ECG analysis data;

[0013] Taking the current ECG analysis data as the result file and updating the stored result file.

[0014] In the third aspect of the embodiments of the present application, an electronic device is provided, including a display, 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 steps of the method for processing ECG signals provided in the first aspect of the embodiments of the present application are implemented;

[0015] The display is used to display an operation interface and generate a corresponding operation instruction in response to an operation action of the user in the operation interface.

[0016] In the fourth aspect of the embodiments of the present application, a medical device is provided, including at least one ECG signal acquisition device and the electronic device provided in the second aspect of the embodiments of the present application, and the electronic device is respectively connected to each ECG signal acquisition device;

[0017] The ECG signal acquisition device is used to acquire the ECG signal of the target user and send the ECG signal to the electronic device.

[0018] The fifth aspect of the embodiments of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the electrocardiogram signal processing method provided in the first aspect of the embodiments of the present application are implemented.

[0019] It can be understood that the beneficial effects of the above second aspect to the fifth aspect can be referred to the relevant descriptions in the above first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

[0022] Figure 2 is a schematic structural diagram of a medical device provided by an embodiment of the present application;

[0023] Figure 3 is a first flow schematic diagram of the electrocardiogram signal processing method provided by an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of an interface for processing a stored result file through a function interface provided by an embodiment of the present application;

[0025] Figure 5 is a timing schematic diagram of template matching of QRS waves through a template matching template provided by an embodiment of the present application;

[0026] Figure 6 is a schematic diagram of a method for dividing the comprehensive characteristics of QRS waves provided by an embodiment of the present application;

[0027] Figure 7 is a schematic diagram of an interface for editing a scatter plot through a partition screening module provided by an embodiment of the present application;

[0028] Figure 8 is a first schematic diagram of an interface for configuring noise sensitivity provided by an embodiment of the present application;

[0029] Figure 9 is a second schematic diagram of an interface for configuring noise sensitivity provided by an embodiment of the present application;

[0030] Figure 10 is a schematic structural diagram of an electrocardiogram signal processing system provided by an embodiment of the present application. Detailed implementation manners

[0031] In the following description, specific details such as specific system architectures, technologies, etc. 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.

[0032] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0033] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0034] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if detecting [the described condition or event]" can be interpreted as meaning "once determined", "in response to determining", "once detecting [the described condition or event]", or "in response to detecting [the described condition or event]" according to the context.

[0035] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0036] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that specific features, structures, or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0037] In applications, currently, a dynamic electrocardiogram (ECG) analysis system processes ECG signals through a preset analysis model. The preset analysis model can adjust parameters according to the needs of doctors or patients. For example, user age, the judgment threshold of events, or the switch of a certain sub-analysis function, etc. After adjusting the parameters and processing the ECG signals, it is necessary to run the preset analysis model completely again. ECG signals can help diagnose various heart diseases and the medical principles of heart diseases are relatively complex, and it is easy to need to adjust parameters and perform multiple processes in a comprehensive diagnosis. The more processes are performed, the more time doctors need to wait for the preset analysis model to execute the analysis, resulting in a decrease in the diagnosis efficiency. Therefore, how to improve the processing efficiency of ECG signals has become an urgent problem to be solved currently.

[0038] In view of the above technical problems, an embodiment of the present application provides an ECG signal processing method. By responding to an operation instruction, calling a corresponding functional component according to the operation instruction to process a stored result file, and obtaining current ECG analysis data; taking the current ECG analysis data as the result file and updating the stored result file, any one or more functional components can be flexibly called to process the result file that has been processed and stored locally again, realizing the discretization of the ECG signal processing function, and corresponding functional components can be called according to the actual needs of users, so that partial ECG signals can be processed locally in a targeted manner. Compared with re-running the preset analysis model to globally process the complete ECG signals, local processing can improve the processing freedom and processing speed of the ECG signals, thereby improving the doctor's diagnosis efficiency.

[0039] The ECG signal processing method provided by the embodiment of the present application can be applied to an electronic device 100. Figure 1 An exemplary structural diagram of the electronic device 100 is shown. The electronic device 100 includes a display 101, a memory 102, a processor 103, and a computer program 104 stored in the memory 102 and executable on the processor 103. When the processor 103 executes the computer program 104, the above-mentioned ECG signal processing method is implemented.

[0040] In applications, the electronic device 100 can specifically be a terminal device such as a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA). The embodiment of the present application does not impose any restrictions on the specific type of the electronic device.

[0041] In an application, the display 101 of the electronic device 100 may be a display of types such as LCD (Liquid Crystal Display), LED (Light Emitting Diode, an LED display performs display by controlling light emitting diodes), OLED, QLED, or Mini LED. The embodiments of the present application do not limit the specific type of the display 101. The display 101 is used to display the stored result file and the processing process of processing the above-mentioned stored result file through functional components, and is also used to display an operation interface and generate corresponding operation instructions in response to the operation actions of the user in the operation interface.

[0042] On the basis of Figure 1 the corresponding electronic device, the embodiments of the present application further provide a medical device. Figure 2 The structural schematic diagram of the medical device 200 is exemplarily shown. The medical device 200 includes at least one electrocardiogram signal acquisition device 201 and the above-mentioned electronic device 100. The electronic device 100 is respectively connected to each electrocardiogram signal acquisition device 201.

[0043] The electrocardiogram signal acquisition device 201 is used to acquire the electrocardiogram signal of the target user and send the electrocardiogram signal to the electronic device 100.

[0044] In an application, the connection manner between the electronic device and the electrocardiogram signal acquisition device includes wired connection and wireless connection. Among them, the communication manners of wireless connection may include Bluetooth, Mobile Communications, Wireless Local Area Network (WLAN), Near Field Communication (NFC), and ZigBee, etc. Specifically, it can be determined based on the communication manners jointly supported by the electronic device and the electrocardiogram signal acquisition device. The embodiments of the present application do not impose any restrictions on the connection manner and communication manner between the electronic device and the electrocardiogram signal acquisition device.

[0045] In an application, the electrocardiogram signal acquisition device 201 may be a fixed or portable electrocardiogram monitor. Specifically, it may be a fixed medical electrocardiograph or a portable dynamic electrocardiogram detection bracelet, watch, chest strap, or recorder, etc. The electrocardiogram signal acquisition device 201 may also be an electrocardiogram electrode patch. The embodiments of the present application do not impose any restrictions on the specific type of the electrocardiogram signal acquisition device 201.

[0046] It can be understood that the structures illustrated in the embodiments of the present application do not constitute specific limitations on the electronic device 100 and the medical device 200. In other embodiments of the present application, the electronic device 100 and the medical device 200 may include more or fewer components than those illustrated, or combine certain components, or different components. For example, it may further include a Graphics Processing Unit (GPU, which can be used for GPU-accelerated operations on electrocardiogram data), etc. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0047] As Figure 3 shown, the electrocardiogram signal processing method provided by the embodiments of the present application can be applied to the above-mentioned electronic device or medical device, and includes the following steps S301 and S302:

[0048] Step S301, in response to an operation instruction, call a corresponding functional component according to the operation instruction to process the stored result file, and obtain current electrocardiogram analysis data.

[0049] In application, after receiving an electrocardiogram signal, it is possible to globally process the electrocardiogram signal through a preset analysis model to obtain multiple result files, and store the multiple result files. Specifically, the preset analysis model may include multiple processing modules, and each processing module is used to perform a targeted processing on the electrocardiogram signal and obtain a corresponding result file. The functions that different processing modules can execute include: arrhythmia detection, ST segment analysis, QT segment analysis, T Wave Alternan (TWA) analysis, Heart Rate Turberlence (HRT) analysis, Heart Rate Variability (HRV) analysis, template matching, template merging, partition screening, fragment graph classification, and heartbeat insertion, etc.

[0050] In application, it is possible to call the processing modules of the above-mentioned preset analysis model through a functional component. The functional component may be a preset function in the dynamic electrocardiogram analysis system run by the electronic / medical device, or a small program in the dynamic electrocardiogram analysis system. When the functional component is a small program, the functional component can be expanded according to actual needs, improving the flexibility of functional component development and installation.

[0051] In application, the user can initiate an operation instruction to call a corresponding functional component to process the stored result file to obtain current electrocardiogram analysis data. Among them, the operation instruction can be used to determine the called functional component and select the file type of the above-mentioned stored result file. The following describes the specific working method of processing the stored result file through the operation instruction:

[0052] In one embodiment, the functional component includes at least one processing module, and step S301 includes:

[0053] Determine the processing module to be called according to the operation instruction and the logical relationship;

[0054] Call the stored result file according to the operation instruction, and input the stored result file into the processing module;

[0055] Process the stored result file through the processing module;

[0056] Wherein, the logical relationship refers to the association relationship for selecting the processing module according to the operation instruction.

[0057] In application, the types and quantities of the processing modules called by the functional component can be arranged and combined according to actual needs. For example, assuming that the preset analysis model includes a first processing module and a second processing module, a first / second functional component can be set up to call the first / second processing module, or a third functional component can be set up to call the first processing module and the second processing module simultaneously. The embodiments of the present application do not impose any restrictions on the types and quantities of the processing modules called by the functional component.

[0058] In application, the operation instruction can call different functional components to process the stored result files of different file types. It should be noted that for the stored result files of different file types, the instruction types of the operation instructions that can be executed can also be different. For example, when the stored result file is a scatter plot, the supported operation instructions can include scatter plot editing instructions; when the stored result file is a fragment graph, the supported operation instructions can include fragment similarity analysis; when the stored result file is heartbeat data, the supported operation instructions can include heartbeat insertion processing; when the stored result file is a QRS wave, the supported operation instructions can be QRS wave similarity analysis, arrhythmia detection, ST segment analysis, QT segment analysis, etc.

[0059] In application, when receiving the operation instruction, the processing module to be called can be determined according to the operation instruction and the logical relationship. The logical relationship can include the instruction type of the operation instruction and the association relationship of the processing module. Specifically, it can include the corresponding relationship between the instruction type of the operation instruction and the processing module; it can also include the corresponding relationship between the instruction type of the operation instruction, the file type of the stored result file and the processing module; it can also include the corresponding relationship between the instruction type of the operation instruction, the functional component and the processing module; it can also include the corresponding relationship between the instruction type of the operation instruction, the file type of the stored result file, the functional component and the processing module. The embodiments of the present application do not impose any restrictions on the specific association relationship of the logical relationship.

[0060] In an application, after determining the processing module to be called, the selected stored result file can be called according to the operation instruction and input to the processing module, and the stored result file is processed by the processing module.

[0061] Step S302: Use the current electrocardiogram analysis data as the result file and update the stored result file.

[0062] In an application, for any functional component, the functional component can include one or more processing modules, and the stored result file can be input to multiple processing modules in parallel for processing to obtain corresponding multiple pieces of current electrocardiogram analysis data; or multiple processing modules can be sorted to obtain an analysis processing stream, and the stored result file is input to the analysis processing stream, and the stored result file is processed sequentially by the sorted multiple processing modules.

[0063] For example, assume that the functional component includes a first processing module, a second processing module, and a third processing module, and the processing order is the first processing module, the second processing module, and the third processing module in sequence. Then the stored result file is input to the first processing module to obtain a first processed file, and then the first processed file is continuously output to the second processing module to obtain a second processed file. Finally, the second processed file is input to the third processing module to obtain the current electrocardiogram analysis data.

[0064] In an application, for the result data output after the electrocardiogram signal is processed by a preset analysis model, the electronic device / medical device or the server connected to the electronic device / medical device can temporarily store the above result data, that is, the stored result file. When the stored result file is processed by the functional component, if the processing module corresponding to the functional component needs to process any stored result file, the above stored result file / temporarily stored result data can be obtained for processing, so as to realize the sharing of the result file between each processing module, and it can be avoided that when the corresponding processing module is called through the functional component, other processing modules are indirectly called to execute the analysis, thereby reducing the resource call during the electrocardiogram signal processing and improving the analysis speed of the electrocardiogram signal.

[0065] In an application, after the stored result file is processed by the functional component, the obtained current electrocardiogram analysis data can be used as the result file to update the above stored result file, so that the stored result file is always the data output by the corresponding functional interface most recently.

[0066] In an application, any one or more processing modules of a preset analysis model are called through a functional component to process a stored result file, so that the preset analysis model / electrocardiogram (ECG) signal analysis function can be discretized, and the corresponding processing module can be called according to the actual needs of the user, so that targeted local processing can be performed on the processed part of the ECG signal. Compared with re-running all the processing modules of the preset analysis model to perform global processing on the complete ECG signal, local processing can improve the processing freedom and speed of the ECG signal, thereby improving the doctor's diagnosis efficiency.

[0067] Figure 4 An exemplary schematic diagram of an interface for processing a stored result file through a functional component is shown, where Figure 4 The file type of the exemplary stored result file is a target fragment graph (QRS wave), and the operation instruction is fragment similarity analysis, and the corresponding functional component is a fragment graph classification module.

[0068] It should be noted that the functional component and the preset analysis model can run on an Figure 4 ECG analysis platform as shown. The ECG analysis platform can be a local application or a cloud platform running on an electronic device / medical device (which can be accessed through a web page or other cloud methods). The following is an exemplary description of the interaction method for calling the functional component: An operation console can be provided on the ECG analysis platform. The operation console can be embedded in the display interface of the ECG analysis platform or can float on the display interface of the ECG analysis platform. The operation console is used to provide the operation instructions supported by the currently selected stored result file to the user; alternatively, after the user selects the stored result file, the operation instructions supported by the stored result file can be displayed, so as to determine the corresponding functional component based on the data type and operation instructions of the stored result file.

[0069] In an application, the following is an exemplary description of the specific processing method for processing a stored result file through a functional component based on Figures 5 to 9 :

[0070] In one embodiment, the operation instruction is a template matching instruction, and the stored result file includes QRS waves; the processing module to be called is determined according to the operation instruction and the logical relationship, including:

[0071] Determining that the processing module to be called according to the template matching instruction and the logical relationship includes a template matching module;

[0072] Processing the stored result file through the processing module, including:

[0073] Performing template matching on the QRS waves through the template matching module to determine the template corresponding to each QRS wave.

[0074] In an application, when the file type of the stored result file is QRS wave and the operation instruction is a template matching instruction, it is determined that the corresponding functional component is a template matching template. The template matching template is used to obtain the templates corresponding to each QRS wave included in the stored result file, improve the matching degree between each QRS wave and the corresponding template, and can also be used to split the template corresponding to the stored result file to improve the classification fineness of the template. The working principle of the template matching template is described below:

[0075] In one embodiment, template matching of QRS waves is performed through a template matching module to determine the template corresponding to each QRS wave, including:

[0076] Based on the noise characteristics of the QRS wave, determine the first matching template of the QRS wave;

[0077] Based on the first matching template of the QRS wave and the comprehensive characteristics of the QRS wave, determine the second matching template of the QRS wave;

[0078] The comprehensive characteristics of the QRS wave include direction characteristics, amplitude characteristics, and noise characteristics. The matching accuracy of the second matching template is greater than that of the first matching template.

[0079] In an application, the template matching template can perform template matching on the QRS waves of the stored result file based on the following five steps:

[0080] (1) For any QRS wave, obtain the noise characteristics of the QRS wave: Specifically, noise detection can be performed on the QRS wave to obtain the noise coefficient of the QRS wave, and the noise coefficient is used to reflect the noise level of the QRS wave;

[0081] Sort the QRS waves according to the noise coefficient to quantify the noise level of all QRS waves in the stored result file; then detect whether the QRS wave has a mutation feature according to the target noise index, and the mutation feature is used to reflect the abnormal information contained in the QRS wave; the noise characteristics of the QRS wave include the noise coefficient and the mutation feature;

[0082] (2) Determine the first matching template of the QRS complex according to the heart beat type of the QRS complex and the noise characteristics of the QRS complex: Specifically, if the heart beat type of the QRS complex is ventricular beat, the first matching template can be determined as ventricular beat (low noise level), suspected ventricular beat (moderate noise level), or artifact (indicating high noise level) according to the noise characteristics of the QRS complex; if the heart beat type of the QRS complex is atrial beat, the first matching template can be determined as atrial beat (low noise level), suspected atrial beat (moderate noise level), or artifact (indicating high noise level) according to the noise characteristics of the QRS complex; if the heart beat type of the QRS complex is normal beat, the first matching template can be determined as normal beat (low noise level), suspected normal beat (moderate noise level), or artifact (indicating high noise level) according to the noise characteristics of the QRS complex;

[0083] (3) Aggregate the QRS complexes with the first matching templates of suspected ventricular beats, suspected atrial beats, and suspected normal beats, and classify them as unclassified beats;

[0084] (4) Obtain the comprehensive characteristics of the QRS complex, and determine the second matching template of the QRS complex according to the first matching template of the QRS complex and the comprehensive characteristics of the QRS complex: Specifically, the comprehensive characteristics of the QRS complex include direction characteristics, amplitude characteristics, and noise characteristics (which can be referred to Figure 7 as shown). The direction characteristics are used to reflect the wave band and waveform direction of the QRS complex, the amplitude characteristics are used to reflect the waveform amplitude of the QRS complex, and the noise characteristics include the noise coefficient and mutation characteristics of the QRS complex. When determining the comprehensive characteristics according to the three sub-characteristics of direction characteristics, amplitude characteristics, and noise characteristics, the weight ratios of the three sub-characteristics can be determined according to actual diagnostic needs. The weight ratios can be sorted from largest to smallest as direction characteristics, amplitude characteristics, and noise characteristics; on the basis of the first matching template, the first matching template can be adjusted according to the comprehensive characteristics of the QRS complex to obtain the second matching template;

[0085] It should be noted that the number of the second matching templates is greater than the number of the first matching templates, and the matching accuracy of the second matching templates is greater than the matching accuracy of the first matching templates;

[0086] (5) After obtaining the second matching template, determine the third matching template of the QRS complex according to the target characteristics of the QRS complex: Specifically, after automatically obtaining the first matching template and the second matching template of the QRS complex through template matching, the target characteristics can be added for further template matching of the QRS complex. The data type of the target characteristics can be set according to actual diagnostic needs. The target characteristics can include time characteristics, lead time characteristics, or interval characteristics, etc. The embodiments of the present application do not impose any restrictions on the data type of the target characteristics.

[0087] Figure 5An exemplary timing schematic diagram of template matching by matching a template with a template is shown, where Figure 5 The preset analysis model shown in Figure 5 for performing QRS wave detection and QRS wave classification is only one processing module in the preset analysis model and does not represent a limitation on the preset analysis model.

[0088] Figure 6 An exemplary schematic diagram of a method for dividing the comprehensive features of QRS waves is shown, where the letters Q / q, R / r, and S / s represent the segment / band positions of the QRS waves, the upper and lower cases of the letters represent the amplitude sizes, and the R with a single quote represents a repeated or abnormal R band.

[0089] In an application, the above method for calculating the noise coefficient is as follows:

[0090] (1) Sample the QRS wave to obtain a target window, and obtain the maximum amplitude and the minimum amplitude of the target window:

[0091] Specifically, the target window can be captured according to a preset window length, or the target window can be captured according to the actual window length of the corresponding QRS wave; after obtaining the target window, the first-direction maximum amplitude and the second-direction maximum amplitude within the target window can be obtained. The first direction can be the direction pointed to when the amplitude is greater than 0, and the second direction can be the direction pointed to when the amplitude is less than 0;

[0092] Among them, the preset window length can be 0.5 s, 1 s, 1.5 s, 2 s, etc., and the embodiments of the present application do not impose any limitation on the length of the preset window length;

[0093] (2) Obtain the crossing situation of the QRS wave in the target window, and the crossing situation includes the number of crossings and the crossing width:

[0094] Specifically, the absolute value of the maximum amplitude can be obtained first. The absolute value of the maximum amplitude is obtained by taking the larger value between the absolute value of the first-direction maximum amplitude and the absolute value of the second-direction maximum amplitude; and at least two crossing thresholds are set. Among them, the size of the first crossing threshold can be set according to the amplitude situation of the actual QRS wave, such as 1 mV or 2 mV, etc., and the sizes of the second crossing threshold or the third crossing threshold, etc., can be set according to the absolute value of the maximum amplitude. For example, the second crossing threshold can be half of the absolute value of the maximum amplitude, and the third crossing threshold can be one-fourth of the absolute value of the maximum amplitude;

[0095] After setting the crossing threshold, the crossing times and crossing widths of the QRS wave in the target window can be obtained according to the crossing threshold; the crossing times are used to represent the number of times the QRS wave exceeds each crossing threshold in the target window, and the crossing widths are used to represent the cumulative time that the QRS wave exceeds each crossing threshold in the target window; for example, when three crossing thresholds are set, there are corresponding first / second / third crossing times, which are used to represent the number of times the QRS wave exceeds the first / second / third crossing thresholds in the target window. Similarly, there are corresponding first / second / third crossing widths, which are used to represent the cumulative time that the QRS wave exceeds the first / second / third crossing thresholds in the target window.

[0096] (3) Sample and integrate the waveform of the QRS wave in the target window to obtain the amplitude parameter:

[0097] Specifically, the sampling frequency of the QRS wave can be set, and multiple sampling points can be obtained according to the sampling frequency. The sampling frequency can be 125Hz, 250Hz, 500Hz or 1000Hz, etc. For example, when the sampling frequency is 500Hz and the window length of the target window is 1s, the number of sampling points is 500. By calculating the absolute value of the amplitude of each sampling point, integrating, and accumulating the integrals of the absolute values of the amplitudes of all sampling points, the amplitude parameter is obtained, which is used to reflect the global fluctuation of the QRS wave in the target window.

[0098] (4) Calculate the noise coefficient according to the maximum amplitude, minimum amplitude, crossing situation and amplitude parameter:

[0099] Specifically, when calculating the noise coefficient, the weight ratios of the four parameters of the maximum amplitude, minimum amplitude, crossing situation and amplitude parameter can be set according to actual needs. The embodiments of the present application do not impose any restrictions on the weight ratios and calculation formulas of the four parameters when calculating the noise coefficient.

[0100] In one embodiment, it further includes:

[0101] When determining the second matching template of any QRS wave, obtain the other QRS waves included in the first matching template of any QRS wave;

[0102] Based on the comprehensive characteristics of any QRS wave, obtain the first similar QRS wave corresponding to any QRS wave among the other QRS waves; wherein, the similarity between the comprehensive characteristics of the first similar QRS wave and the comprehensive characteristics of any QRS wave is greater than the preset similarity;

[0103] Use the first matching template of any QRS wave as the second matching template of any QRS wave and the second matching template of the first similar QRS wave.

[0104] In an application, for any QRS complex, when determining the second matching template, the template matching for each QRS complex can be carried out progressively by means of template splitting. Taking one round of template splitting as an example, the working principle of template splitting is described as follows:

[0105] Each template can contain multiple QRS complexes. Therefore, other QRS complexes included in the first matching template of any of the above QRS complexes can be obtained, and there is a certain similarity between any QRS complex and other QRS complexes; the comprehensive features of any QRS complex and the comprehensive features of other QRS complexes can be extracted, and the first similar QRS complex can be selected according to the similarity of the comprehensive features, and the first matching template of any QRS complex can be used as the second matching template of any QRS complex and the second matching template of the first similar QRS complex;

[0106] Based on the comprehensive features of any QRS complex, a low-similarity QRS complex corresponding to any QRS complex can also be obtained from other QRS complexes, and the similarity between the comprehensive features of the above low-similarity QRS complex and the comprehensive features of any QRS complex is not greater than a preset similarity; the first matching template can be adjusted according to the comprehensive features of the above low-similarity QRS complex to obtain the second matching template of the above low-similarity QRS complex;

[0107] Among them, any of the above QRS complexes can specifically be the QRS complex with the highest matching degree in the first matching template where it is located, or any QRS complex in the first matching template where it is located; after one round of splitting is completed, the second matching templates corresponding to any of the above QRS complexes and the first similar QRS complex can be further split, and / or, the second matching template of the above low-similarity QRS complex can be further split.

[0108] In one embodiment, it further includes:

[0109] When the number of second matching templates is greater than the preset number of templates, obtain the similarity between any two second matching templates;

[0110] If the similarity between any two second matching templates is greater than the preset similarity, merge any two second matching templates.

[0111] In an application, after obtaining multiple second matching templates through multiple template splits, it is possible to detect whether the number of second matching templates is greater than a preset template number. If so, it indicates that the current number of second matching templates is excessive. It is possible to obtain the similarity between any two second matching templates. If the similarity between any two of the above second matching templates is greater than a preset similarity, then any two second matching templates are merged. If the similarity between any two of the above second matching templates is not greater than the preset similarity, then any two of the above second matching templates are retained. Among them, the preset template number can be 6, 7, 8, etc., and the preset similarity can be 80%, 90%, 95%, etc. The embodiments of the present application do not impose any restrictions on the specific sizes of the preset template number and the preset similarity.

[0112] In an application, by performing template merging when the number of second matching templates is greater than the preset template number, the number of second matching templates can be controlled within a reasonable range. And by merging according to the similarity between the second matching templates, similar second matching templates can be merged, so that the merged second matching templates have a certain difference, avoiding the situation of excessive template numbers and high similarity of many templates, and improving the distribution rationality of the second matching templates.

[0113] In one embodiment, the operation instruction is a scatter plot editing instruction, and the stored result file includes a scatter plot; determining the processing module to be called according to the operation instruction and the logical relationship, including:

[0114] Determining the processing module to be called according to the scatter plot editing instruction and the logical relationship includes a partition screening module;

[0115] Processing the stored result file through the processing module, including:

[0116] Performing data point screening on the scatter plot through the partition screening module to obtain a processed scatter plot.

[0117] In an application, when the file type of the stored result file is a scatter plot (a scatter trend plot for reflecting the change of RR interval over time), and the operation instruction is a scatter plot editing instruction, the corresponding functional component is determined to be a partition screening module. The partition screening module is used to perform data point screening for each partition selected by the scatter plot editing instruction to determine whether all data points in each partition are data abnormal. If the data is abnormal, the corresponding data points are removed from the scatter plot. If the data is not abnormal, the corresponding data points are retained, so as to obtain a screened scatter plot, which can improve the confidence of each data point in the scatter plot. The working principle of the partition screening module is described below:

[0118] In one embodiment, performing data point screening on the scatter plot through the partition screening module to obtain a processed scatter plot, including:

[0119] For any data point, through the partition screening module, based on the confidence level of any data point and the noise characteristics of any data point, it is determined whether any data point is retained in the scatter plot; the confidence level is determined according to the partition to which any data point belongs.

[0120] In an application, when performing a scatter plot editing instruction on the scatter plot through the partition screening module, for any data point in any partition, the confidence level and noise characteristics of the data point can be obtained, or the confidence level, noise characteristics, and comprehensive characteristics of the data point can be obtained. Among them, the methods for obtaining the noise characteristics and comprehensive characteristics can refer to the relevant descriptions in the above template matching template and will not be elaborated here. The following describes the calculation method of the confidence level of the data point:

[0121] (1) Obtain the smallest partition of the scatter plot, and the smallest partition represents the area in the scatter plot where the data points are most concentrated and the confidence level is the highest:

[0122] Specifically, the smallest partition of the scatter plot can be framed by a contour detection algorithm, or the smallest partition of the scatter plot can be framed based on the coordinate axes, or the smallest partition of the scatter plot can be framed based on the RR interval (the interval time between each heartbeat). Among them, the contour detection algorithm can adopt existing contour detection algorithms and will not be elaborated here;

[0123] When framing the smallest partition of the scatter plot based on the coordinate axes, the center point coordinates can be set first. The center point coordinates can be custom-set by the user, or the geometric center of the scatter plot can be used as the center point coordinates, or the average value of the RR interval can be used as the center point coordinates. After determining the center point coordinates, using the center point as the center of the circle, the coordinate axes are divided into multiple fan-shaped regions with the same area. For any one fan-shaped region, starting from the center point, a data point coverage rate scan is performed in the centrifugal direction of the fan-shaped region. When the data point coverage rate in the scanned area reaches the preset coverage rate, it is determined that the above scanned area reaches the smallest partition of the above fan-shaped region, and so on, to obtain the smallest partition of each fan-shaped region, thereby obtaining the smallest partition of the scatter plot in the coordinate axes; among them, the preset coverage rate can be 75%, 80%, 85%, or 90%, etc.; the number of fan-shaped regions can be 10, 15, or 20, etc. Generally speaking, the more the number of fan-shaped regions, the finer the division of the smallest partition;

[0124] When framing the smallest partition of the scatter plot based on the RR interval, the RR interval of each data point can be obtained, and the data points are sorted according to the difference between the RR intervals of any two data points, so as to obtain the RR interval confidence level of the data points. The contour boundary is determined according to the preset confidence interval, and the preset confidence interval can specifically be [25%, 75%], [24%, 76%], or [23%, 77%], etc.

[0125] (2) Determining the extended partition based on the minimum partition of the scatter plot:

[0126] Specifically, the scatter plot may include a minimum partition and at least one extended partition. The extended partition is located outside the minimum partition, and the position of the extended partition can be determined by the dilation algorithm or according to a preset extension range. The dilation algorithm can refer to the existing dilation algorithms and will not be elaborated here. Assume that the preset extension range is 100 ms, that is, for each additional extended partition, it extends 100 ms outward based on the outermost partition (which can be the minimum partition or the extended partition).

[0127] (3) Determining the confidence level based on the position of the data points:

[0128] Specifically, the first confidence level can be determined according to the partition to which the data point belongs. The closer the extended partition is to the minimum partition, the higher the first confidence level of the data points within the corresponding extended partition. For example, assume there are three extended partitions, which are sorted in ascending order of the distance from the minimum partition as the first extended partition, the second extended partition, and the third extended partition. Then, the first confidence level of the data points within the minimum partition is 100%, the first confidence level of the data points within the first extended partition is 90%, the first confidence level of the data points within the second extended partition is 80%, and the first confidence level of the data points within the third extended partition is 70%.

[0129] The second confidence level can also be determined according to the size of the RR interval of the data point. For example, when the size of the RR interval is 400 ms, the corresponding second confidence level is 20%; when the size of the RR interval is 800 ms, the corresponding second confidence level is 40%; when the size of the RR interval is 1200 ms, the corresponding second confidence level is 60%; when the size of the RR interval is 1600 ms, the corresponding second confidence level is 80%; when the size of the RR interval is 2000 ms, 2400 ms, or 2800 ms, the corresponding second confidence level is 100%; when the size of the RR interval is 3200 ms, the corresponding second confidence level is 90%; when the size of the RR interval is 3600 ms, the corresponding second confidence level is 80%; when the size of the RR interval is 4000 ms, the corresponding second confidence level is 70%.

[0130] The comprehensive confidence level can also be determined according to the first confidence level and the second confidence level. The weight ratios of the first confidence level and the second confidence level can be set according to actual needs. Specifically, the weight ratio of the first confidence level can be 80%, and the weight ratio of the second confidence level can be 20%. Or the weight ratios of the first confidence level and the second confidence level can both be 50%. The embodiments of the present application do not impose any restrictions on the weight ratios of the first confidence level and the second confidence level.

[0131] In one embodiment, it further includes:

[0132] Determine at least two partitions of the scatter plot based on the target area selected by the scatter plot editing instruction;

[0133] Alternatively, determine multiple partitions of the scatter plot based on the distribution of all data points in the scatter plot.

[0134] In an application, when performing scatter plot editing on the scatter plot through the partition screening module, the user can manually select the target area and determine that the data points within the target area belong to the minimum partition, and the data points outside the target area belong to the extended partition; or the partition screening module can automatically divide the minimum partition and the extended partition according to the distribution of all data points (refer to the relevant description in the calculation method of the confidence of the above data points).

[0135] Figure 7 An exemplary interface schematic diagram of scatter plot editing through the partition screening module is shown.

[0136] In one embodiment, the operation instruction is fragment similarity analysis, and the stored result file includes a target fragment map, and the target fragment map includes a fragment map of an electrocardiogram, a fragment map of a superimposed map, a fragment map of a scatter plot, a fragment map of a histogram, or a fragment map of a template; determine the processing module to be called according to the operation instruction and the logical relationship, including:

[0137] Determine that the processing module to be called according to the fragment similarity analysis and the logical relationship includes a fragment map classification module;

[0138] Process the stored result file through the processing module, including:

[0139] Obtain the data characteristics of the target fragment map through the fragment map classification module to obtain at least one similar fragment map corresponding to the target fragment map.

[0140] In an application, when the file type of the stored result file is a target fragment map, and the operation instruction is fragment similarity analysis, and the corresponding functional component is a fragment map classification module; the target fragment map includes a fragment map of an electrocardiogram, a fragment map of a superimposed map, a fragment map of a scatter plot, a fragment map of a histogram, or a fragment map of a template. The data characteristics of the target fragment map may include RR interval, direction characteristics, amplitude characteristics, and / or noise characteristics, etc. The present application embodiment does not impose any restrictions on the data types included in the data characteristics of the target fragment map. The interface schematic diagram for performing fragment similarity analysis on the target fragment map can refer to Figure 4 .

[0141] In one embodiment, the operation instruction is heartbeat insertion processing, and the stored result file includes heartbeat data; determine the processing module to be called according to the operation instruction and the logical relationship, including:

[0142] Based on the heartbeat insertion process, it is determined that the processing module to be called includes the heartbeat insertion module;

[0143] The stored result file is processed by the processing module, including:

[0144] Based on the amplitude characteristics and inter-beat interval characteristics of the heartbeat data, the second similar QRS wave corresponding to the QRS wave where the heartbeat data is located is obtained, and the heartbeat is inserted into the second similar QRS wave through the heartbeat insertion module.

[0145] In an application, when the file type of the stored result file is heartbeat data, and the operation instruction is the heartbeat insertion process, the corresponding functional component is the heartbeat insertion module; the heartbeat data is any heartbeat manually inserted into the fragment diagram. Through the heartbeat insertion module, the amplitude characteristics and inter-beat interval characteristics of the heartbeat data can be analyzed, so as to obtain the second similar QRS wave corresponding to the QRS wave where the heartbeat data is located, and insert the heartbeat into the second similar QRS wave.

[0146] In one embodiment, it further includes:

[0147] The electrocardiogram is processed by the noise sensitivity adjustment module according to the target noise sensitivity to obtain the processed electrocardiogram.

[0148] In an application, when the file type of the stored result file is an electrocardiogram, and the operation instruction is to adjust the noise sensitivity to the target noise sensitivity, the corresponding functional component is the noise sensitivity adjustment module; the noise sensitivity is used to determine the sensitivity of a heartbeat being recognized as noise.

[0149] In an application, through the noise sensitivity adjustment module: the preset noise coefficient of each window is obtained according to the target noise sensitivity; the window includes multiple heartbeats; the noise window is determined based on the preset noise coefficient, and the noise coefficient of the noise window is greater than the preset noise coefficient; all noise windows are masked in the electrocardiogram to obtain the processed electrocardiogram. The parameters and determination method included in the noise coefficient can refer to the relevant description in the above calculation method of the noise coefficient, which will not be elaborated here. The difference is that the above calculation method of the noise coefficient is used to calculate the noise coefficient according to four parameters: the maximum amplitude, the minimum amplitude, the crossing situation, and the amplitude parameter, while the noise sensitivity adjustment window is used to adjust the preset noise coefficient to quantify how to determine the noise window according to the four parameters of the maximum amplitude, the minimum amplitude, the crossing situation, and the amplitude parameter.

[0150] In an application, the target noise sensitivity can be used to adjust the global noise sensitivity setting, can also be used to adjust the high-frequency noise sensitivity setting, can also be used to adjust the low-frequency noise sensitivity setting, and can also be used to adjust the medium-frequency noise sensitivity setting, so as to adaptively adjust the noise sensitivity of different frequencies and improve the flexibility of noise screening.

[0151] Figure 8 and Figure 9 The following is an exemplary diagram of an interface for configuring noise sensitivity, wherein: Figure 9 An operating console for adjusting noise sensitivity is provided in the menu bar, and the operating console calls out a floating operating console for high-frequency noise sensitivity, low-frequency noise sensitivity and preset window length in response to an interactive action; Figure 8 and Figure 9 The difference is that Figure 10 An operating console for adjusting high frequency noise sensitivity, low frequency noise sensitivity and preset window length is provided directly on the menu bar.

[0152] In one embodiment, it further includes:

[0153] When the stored result file is processed by the functional component, the processing process of the stored result file by the functional component is demonstrated on the display interface.

[0154] In the application, when the user calls the functional component to process the stored result file, the processing process of the functional component on the stored result file can be demonstrated on the display interface, so as to intuitively show the user the intermediate data contained in the conversion of the stored result file into the current ECG analysis data during the processing, thereby assisting doctors in diagnosis and improving diagnostic efficiency.

[0155] In one embodiment, it further includes:

[0156] Generate corresponding operation instructions based on the signal input by the user.

[0157] In the application, the user can input signals through the touch screen or through peripheral devices such as a mouse or keyboard. The electronic device / medical device can generate corresponding operation instructions based on the signals input by the user.

[0158] like Figure 10 As shown, in one embodiment, an electrocardiogram signal processing system 300 is provided, including a processing end 310 and a display end 320, wherein the processing end 310 and the display end 320 are connected;

[0159] The display terminal 320 is used to display the operation interface and generate corresponding operation instructions in response to the user's operation actions in the operation interface;

[0160] The processing end 310 is used for:

[0161] In response to the operation instruction, the corresponding functional component is called according to the operation instruction to process the stored result file to obtain the current ECG analysis data;

[0162] Use the current electrocardiogram analysis data as the result file and update the stored result file.

[0163] In the application, the display end 320 is used to display the operation interface and generate corresponding operation instructions in response to the operation actions of the user in the operation interface. The working principle of the processing end 310 can refer to the relevant descriptions in the above electrocardiogram signal processing method and will not be elaborated here.

[0164] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0165] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above embodiments of various electrocardiogram signal processing methods can be implemented.

[0166] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiments of the method of the present application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above embodiments of various methods can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can at least include: any entity or device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code to the photographing terminal device. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc.

[0167] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0168] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0169] In the embodiments provided in this application, it should be understood that the disclosed terminal devices and methods can be implemented in other ways. For example, the terminal device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, indirect couplings or communication connections of devices or modules, and can be in electrical, mechanical or other forms.

[0170] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this 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 recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An electrocardiogram signal processing method, characterized in that, it includes: In response to an operation instruction, call a corresponding functional component according to the operation instruction to process the stored result file to obtain current electrocardiogram analysis data; Use the current electrocardiogram analysis data as the result file and update the stored result file.

2. The electrocardiogram signal processing method according to claim 1, characterized in that, The functional component includes at least one processing module, and the step of calling a corresponding functional component according to the operation instruction to process the stored result file includes the following steps: Determine the processing module to be called according to the operation instruction and the logical relationship; Call the stored result file according to the operation instruction and input the stored result file into the processing module; Process the stored result file through the processing module; wherein, the logical relationship refers to the association relationship for selecting the processing module according to the operation instruction.

3. The electrocardiogram signal processing method according to claim 2, characterized in that, The operation instruction is a template matching instruction, and the stored result file includes QRS waves; determining the processing module to be called according to the operation instruction and the logical relationship includes: Determine that the processing module to be called according to the template matching instruction and the logical relationship includes a template matching module; The step of processing the stored result file through the processing module includes: Perform template matching on the QRS waves through the template matching module to determine the template corresponding to each QRS wave.

4. The electrocardiogram signal processing method according to claim 3, characterized in that, Performing template matching on the QRS waves through the template matching module to determine the template corresponding to each QRS wave includes: Based on the noise characteristics of the QRS wave, determine the first matching template of the QRS wave; Based on the first matching template of the QRS wave and the comprehensive characteristics of the QRS wave, determine the second matching template of the QRS wave; The comprehensive characteristics of the QRS wave include direction characteristics, amplitude characteristics and noise characteristics, and the matching accuracy of the second matching template is greater than that of the first matching template.

5. The electrocardiogram signal processing method according to claim 4, characterized in that, The method further includes: When determining the second matching template of any QRS wave, obtain the other QRS waves included in the first matching template of the any QRS wave; Based on the comprehensive characteristics of the any QRS wave, obtain the first similar QRS wave corresponding to the any QRS wave from the other QRS waves; wherein, the similarity between the comprehensive characteristics of the first similar QRS wave and the comprehensive characteristics of the any QRS wave is greater than a preset similarity; Use the first matching template of the any QRS wave as the second matching template of the any QRS wave and the second matching template of the first similar QRS wave.

6. The electrocardiogram signal processing method according to claim 5, characterized in that, The method further includes: When the number of second matching templates is greater than a preset number of templates, obtain the similarity between any two second matching templates; If the similarity between any two second matching templates is greater than a preset similarity, merge the any two second matching templates.

7. The electrocardiogram signal processing method according to claim 3, characterized in that the operation instruction is a scatter plot editing instruction, and the stored result file includes a scatter plot; the determining of the processing module to be called according to the operation instruction and the logical relationship includes: Determining that the processing module to be called according to the scatter plot editing instruction and the logical relationship includes a partition screening module; The processing of the stored result file by the processing module includes: Performing data point screening on the scatter plot through the partition screening module to obtain a processed scatter plot.

8. The electrocardiogram signal processing method according to claim 7, characterized in that The performing data point screening on the scatter plot through the partition screening module to obtain a processed scatter plot includes: For any data point in the scatter plot, through the partition screening module, based on the confidence level of the any data point and the noise feature of the any data point, determine whether the any data point is retained in the scatter plot; the confidence level is determined according to the partition to which the any data point belongs.

9. The electrocardiogram signal processing method according to claim 8, characterized in that The method further includes: Based on the target area selected by the scatter plot editing instruction, determining at least two partitions of the scatter plot; Or, based on the distribution of all data points in the scatter plot, determining multiple partitions of the scatter plot.

10. The electrocardiogram signal processing method according to claim 3, characterized in that the operation instruction is a fragment similarity analysis, the stored result file includes a target fragment map, and the target fragment map includes a fragment map of an electrocardiogram, a fragment map of a superimposed map, a fragment map of a scatter plot, a fragment map of a histogram, or a fragment map of a template; the determining of the processing module to be called according to the operation instruction and the logical relationship includes: Determining that the processing module to be called according to the fragment similarity analysis and the logical relationship includes a fragment map classification module; The processing of the stored result file by the processing module includes: Obtaining the data features of the target fragment map through the fragment map classification module to obtain at least one similar fragment map corresponding to the target fragment map.

11. The electrocardiogram signal processing method according to claim 3, characterized in that the operation instruction is a heart beat insertion process, the stored result file includes heart beat data; the determining of the processing module to be called according to the operation instruction and the logical relationship includes: Determining that the processing module to be called according to the heart beat insertion process includes a heart beat insertion module; The processing of the stored result file by the processing module includes: Based on the amplitude feature and the heart beat interval feature of the heart beat data, obtaining a second similar QRS wave corresponding to the QRS wave where the heart beat data is located, and inserting a heart beat through the heart beat insertion module in the second similar QRS wave.

12. The electrocardiogram signal processing method according to any one of claims 1 to 11, characterized in that The method further includes: Generate corresponding operation instructions based on the signals input by the user.

13. An electrocardiogram signal processing system, characterized in that, it includes a processing end and a display end, and the processing end is connected to the display end; the display end is used to display an operation interface and generate corresponding operation instructions in response to the operation actions of the user in the operation interface; the processing end is used for: in response to the operation instructions, call corresponding functional components according to the operation instructions to process the stored result files to obtain the current electrocardiogram analysis data; use the current electrocardiogram analysis data as the result file and update the stored result file.

14. An electronic device, characterized in that, it includes a display, a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the electrocardiogram signal processing method according to any one of claims 1 to 12; the display is used to display an operation interface and generate corresponding operation instructions in response to the operation actions of the user in the operation interface.

15. A medical device, characterized in that, it includes at least one electrocardiogram signal acquisition device and the electronic device according to claim 14, and the electronic device is respectively connected to each electrocardiogram signal acquisition device; the electrocardiogram signal acquisition device is used to acquire the electrocardiogram signals of the target user and send the electrocardiogram signals to the electronic device.

16. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the electrocardiogram signal processing method according to any one of claims 1 to 12.

Images