Electrocardiosignal processing method and device, computer equipment and storage medium

Abstract

The invention relates to an electrocardiosignal processing method and device, computer equipment and a storage medium. The method comprises the steps that electrocardiosignals of a to-be-detected object are obtained; performing signal segmentation processing on the electrocardiosignal to obtain a plurality of cardiac cycle waveforms contained in the electrocardiosignal; performing statistical processing on the plurality of cardiac cycle waveforms to obtain a target cardiac cycle waveform; and comparing the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the to-be-detected object, and determining a matching result between the electrocardiosignal and the to-be-detected object. By adopting the method, the matching judgment of the electrocardiosignal and the to-be-detected object can be realized, so that the confusion of the identity information of the detected object and the electrocardiosignal can be avoided, and the correct matching of the electrocardiosignal input into a computer and the identity of the detected object is ensured.

Description

Technical Field

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

[0002] A dynamic ECG examination uses an ECG acquisition device to collect the ECG data of the subject for 24 hours, 48 ​​hours or longer, and then imports the data from the ECG acquisition device into a computer for analysis.

[0003] In the current dynamic ECG examination, generally after completing the dynamic ECG data collection for each test object, the identity information of the test object and the ECG data of each test object collected by the ECG collection device are manually entered into the computer. However, when there are many test objects, this entry method is prone to confuse the identity information of the test object with the ECG data, resulting in the dynamic ECG data entered into the computer not matching the identity of the test object. In the existing ECG signal identity recognition method, the user usually selects the feature points of the ECG signal from the ECG signal of the inspection, and then compares the selected feature points with the feature points of the ECG signal of the user's identity to determine which user's ECG signal the inspection ECG signal belongs to. However, in the existing method, the selection of feature points is affected by human subjective factors, and the recognition accuracy of feature points depends on the waveform of the ECG signal. Therefore, if the ECG signal waveform is abnormal, the feature point extraction will be inaccurate or even wrong. In this case, the accuracy of the feature values ​​generated by multiple feature points will also be greatly affected, thereby greatly reducing the accuracy of identity recognition. Summary of the invention

[0004] Based on this, it is necessary to provide an ECG signal processing method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the technical problem of low accuracy in identity recognition based on the selection of ECG signal feature points.

[0005] In a first aspect, the present application provides a method for processing an electrocardiogram signal. The method comprises:

[0006] Acquire the electrocardiogram signal of the object to be detected;

[0007] Performing signal segmentation processing on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms contained in the electrocardiogram signal;

[0008] Processing the multiple cardiac cycle waveforms to obtain a target cardiac cycle waveform;

[0009] The target cardiac cycle waveform is compared with a predetermined reference cardiac cycle waveform of the subject to be detected to determine a matching result between the electrocardiogram signal and the subject to be detected.

[0010] In one embodiment, the signal segmentation processing is performed on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms, including:

[0011] Performing R point detection on the ECG signal to obtain a plurality of target R points of the ECG signal; the R point is the highest peak point in the signal wave group of the ECG signal;

[0012] A plurality of cardiac cycle waveforms are segmented from the electrocardiographic signal according to the plurality of target R points.

[0013] In one embodiment, the processing of the plurality of cardiac cycle waveforms to obtain a target cardiac cycle waveform includes:

[0014] Performing abnormality detection processing on the multiple cardiac cycle waveforms, eliminating abnormal cardiac cycle waveforms from the multiple cardiac cycle waveforms, and obtaining multiple screened cardiac cycle waveforms;

[0015] Statistical processing is performed on the plurality of screened cardiac cycle waveforms to obtain a target cardiac cycle waveform.

[0016] In one embodiment, each cardiac cycle waveform includes electrocardiographic signal values ​​at multiple sampling points, and the number of sampling points of each cardiac cycle waveform is the same;

[0017] The statistical processing of the plurality of screened cardiac cycle waveforms to obtain a target cardiac cycle waveform includes:

[0018] Performing statistical processing on the electrocardiogram signal values ​​of each screened cardiac cycle waveform at the same sampling point to obtain statistical values ​​at each sampling point; the same sampling point means the sampling points in each cardiac cycle waveform with the same sampling order;

[0019] Based on the statistical values ​​at the various sampling points, the target cardiac cycle waveform is obtained.

[0020] In one embodiment, comparing the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the subject to be detected to determine a matching result between the electrocardiogram signal and the subject to be detected includes:

[0021] Constructing an ECG data matrix according to the number of sampling points corresponding to the target cardiac cycle waveform and the ECG signal value of the target cardiac cycle waveform at each sampling point;

[0022] Determining first characteristic information of the target cardiac cycle waveform according to the electrocardiogram data matrix;

[0023] The first characteristic information of the target cardiac cycle waveform is compared with the second characteristic information of the reference cardiac cycle waveform to determine a matching result between the electrocardiogram signal and the object to be detected.

[0024] In one embodiment, determining the first characteristic information of the target cardiac cycle waveform according to the electrocardiogram data matrix includes:

[0025] Performing singular value decomposition processing on the ECG data matrix to obtain a feature matrix corresponding to the ECG data matrix;

[0026] Based on the element values ​​in the characteristic matrix, first characteristic information of the target cardiac cycle waveform is determined.

[0027] In one embodiment, before performing signal segmentation processing on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms, the method further includes:

[0028] Performing filtering on the electrocardiogram signal to obtain a filtered electrocardiogram signal;

[0029] The signal segmentation processing is performed on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms, including:

[0030] The filtered electrocardiogram signal is subjected to signal segmentation processing to obtain a plurality of cardiac cycle waveforms.

[0031] In one embodiment, the method further comprises:

[0032] Performing interruption detection on the electrocardiogram signal;

[0033] When an interruption of the electrocardiogram signal is detected, splitting the acquired electrocardiogram signal into multiple segments of electrocardiogram signals according to the interruption information;

[0034] The identity of each segment of the ECG signal is matched with the corresponding object to be detected.

[0035] In a second aspect, the present application also provides an electrocardiogram signal processing device. The device comprises:

[0036] An acquisition module, used for acquiring the electrocardiogram signal of the object to be detected;

[0037] A segmentation module, used for performing signal segmentation processing on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms contained in the electrocardiogram signal;

[0038] A processing module, used for processing the multiple cardiac cycle waveforms to obtain a target cardiac cycle waveform;

[0039] The determination module is used to compare the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the object to be detected, and determine a matching result between the electrocardiogram signal and the object to be detected.

[0040] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any of the above methods is implemented.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0042] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0043] The above-mentioned ECG signal processing method, device, computer equipment, storage medium and computer program product perform signal segmentation processing on the ECG signal of the object to be detected, obtain multiple cardiac cycle waveforms contained in the ECG signal, and then process the multiple cardiac cycle waveforms to obtain a target cardiac cycle waveform. Then compare the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the object to be detected to determine the matching result between the ECG signal and the object to be detected. The method utilizes the uniqueness of the ECG signal of each object, extracts the cardiac cycle waveform corresponding to the ECG signal, and compares it with the reference cardiac cycle of the object to be detected. According to the similarity between the two cardiac cycle waveforms, the matching judgment between the ECG signal and the object to be detected is realized, thereby avoiding confusion between the identity information of the detected object and the ECG signal, and ensuring the correct matching between the ECG signal entered into the computer and the identity of the detected object. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A diagram showing an application environment of an electrocardiogram signal processing method in an embodiment;

[0045] Figure 2 A schematic diagram of a flow chart of an electrocardiogram signal processing method in one embodiment;

[0046] Figure 3 Schematic diagram of a P-QRS-T waveform in one embodiment;

[0047] Figure 4 is a schematic diagram of a complete cardiac cycle waveform in an electrocardiogram signal in an embodiment;

[0048] Figure 5is a flow chart of the steps of determining the matching result between the electrocardiogram signal and the object to be detected in one embodiment;

[0049] Figure 6 is a schematic diagram of performing singular value decomposition on a matrix in one embodiment;

[0050] Figure 7 is a schematic diagram of performing singular value decomposition on a matrix in another embodiment;

[0051] Figure 8 A schematic diagram of a flow chart of an electrocardiogram signal processing method in another embodiment;

[0052] Fig. 9 is a structural block diagram of an electrocardiogram signal processing device in an embodiment;

[0053] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0056] The electrocardiogram signal processing method provided in the embodiment of the present application can be applied to Figure 1The application environment shown includes a terminal 102 and an ECG acquisition device 104. The terminal 102 and the ECG acquisition device 104 can communicate with each other via a data line, that is, the terminal 102 obtains the ECG signal of the object to be detected collected by the ECG acquisition device 104 via the data line. The terminal 102 and the ECG acquisition device 104 can also communicate wirelessly via wireless transmission methods such as WiFi and Bluetooth, that is, the terminal 102 can obtain the ECG signal of the object to be detected collected by the ECG acquisition device 104 via wireless transmission. In the application scenario of the present application, the terminal 102 can obtain the ECG signal of the object to be detected from the ECG acquisition device 104, and then perform signal segmentation processing on the ECG signal to obtain multiple cardiac cycle waveforms contained in the ECG signal; further process the multiple cardiac cycle waveforms to obtain the target cardiac cycle waveform; finally, compare the target cardiac cycle waveform with the predetermined reference cardiac cycle waveform of the object to be detected to determine the matching result between the ECG signal and the object to be detected. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The ECG acquisition device 104 may be a device with wireless communication function or wired communication function that can be used to collect ECG signals.

[0057] In one embodiment, Figure 2 As shown, a method for processing an electrocardiogram signal is provided. Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0058] Step S210, obtaining the electrocardiogram signal of the subject to be detected.

[0059] The object to be detected refers to an object for which electrocardiogram signals need to be collected. For example, the object to be detected may be a human body.

[0060] Among them, the electrocardiogram signal, namely the ECG (Electrocardiogram) signal, is a biopotential signal generated by the heartbeat, which reflects the electrical activity process of the heart. Since the heart position, size, shape, chest structure, age, gender, weight, emotion and exercise condition of different people are different, the electrocardiogram signal has the characteristic of uniqueness.

[0061] In a specific implementation, the terminal can obtain the ECG signal of the object to be detected from the ECG acquisition device through a wired connection method of a data cable or a wireless transmission method such as WiFi, Bluetooth, etc.

[0062] It can be understood that the ECG acquisition device generally collects ECG signals by connecting ECG leads to the biological object. The ECG leads are generally 12 leads, and each lead will collect a set of ECG signals. In practical applications, taking 12 leads as an example, the ECG signals obtained from the ECG acquisition device correspond to 12 sets of ECG signals. For ease of understanding, when not limited in the following embodiments, the description is based on a set of ECG signals as an example.

[0063] Step S220, performing signal segmentation processing on the ECG signal to obtain a plurality of cardiac cycle waveforms contained in the ECG signal.

[0064] The cardiac cycle waveform is a complete cardiac cycle waveform including a complete P-QRS-T wave group, wherein P, QRS, and T in the P-QRS-T wave group refer to P wave, QRS wave, and T wave, respectively.

[0065] refer to Figure 3 , shows a schematic diagram of a P-QRS-T waveform, based on Figure 3 The characteristics of the P-QRS-T wave shown in the figure can be used to segment the ECG signal to obtain multiple cardiac cycle waveforms contained in the ECG signal. Figure 4 , which is a schematic diagram of a complete cardiac cycle waveform in the ECG signal. Figure 4 The ECG signal shown includes 9 cardiac cycle waveforms in total.

[0066] Step S230, processing the plurality of cardiac cycle waveforms to obtain a target cardiac cycle waveform.

[0067] In a specific implementation, each cardiac cycle waveform can be regarded as composed of ECG signal values ​​based on multiple sampling points. Therefore, each cardiac cycle waveform corresponds to multiple ECG signal values. Statistical processing is performed on multiple cardiac cycle waveforms to process each ECG signal value contained in each cardiac cycle waveform. More specifically, the ECG signal values ​​of each cardiac cycle waveform at the sampling points in the same sampling order are processed, and the target cardiac cycle waveform is formed according to the corresponding ECG signal values ​​at each sampling point.

[0068] For example, as shown in Table 1 below, there are 1000 sampling points corresponding to each cardiac cycle waveform, and there are 9 cardiac cycle waveforms obtained by dividing the ECG signal. Then, the ECG signal values ​​of each cardiac cycle waveform at sampling point 1 are counted, that is, x1, y1, ... r1 are counted to obtain the statistical value corresponding to sampling point 1, recorded as f(x1, y1, ... r1). Similarly, the statistical values ​​at other sampling points can be obtained. The target cardiac cycle waveform can be constructed from the statistical values ​​at 1000 sampling points.

[0069] Table 1 Statistical value calculation table

[0070] Sampling point 1 Sampling point 2 … Sampling point 1000 Waveform 1 <![CDATA[x1]]> <![CDATA[x2]]> … <![CDATA[x 1000 ]]> Waveform 2 <![CDATA[y1]]> <![CDATA[y2]]> … <![CDATA[y 1000 ]]> … … … … … Waveform 9 <![CDATA[r1]]> <![CDATA[r2]]> … <![CDATA[r 1000 ]]> Statistics <![CDATA[f(x1,y1,…r1)]]> <![CDATA[f(x2,y2,…r2)]]> … <![CDATA[f(x 1000 ,y 1000 ,…r 1000 )]]>

[0071] Step S240 , comparing the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the subject to be detected, and determining a matching result between the ECG signal and the subject to be detected.

[0072] It can be understood that for different objects, the ECG signal is unique, and therefore, the cardiac cycle waveform that can characterize the ECG signal is also unique. That is, the cardiac cycle waveform of each object to be detected is unique, so the cardiac cycle waveform of the object to be detected can be predetermined as a reference cardiac cycle waveform. When judging whether a certain ECG signal matches the object to be detected, the target cardiac cycle waveform of the ECG signal is extracted and compared with the reference cardiac cycle waveform of the object to be detected, and the comparison result can be used to determine whether the ECG signal matches the object to be detected.

[0073] In one embodiment, considering that the cardiac cycle waveform may change due to the influence of the age, weight, mood, exercise condition, physical health status, etc. of the subject to be detected, the reference cardiac cycle waveform of the subject to be detected may also be updated regularly to ensure the real-time nature of the reference cardiac cycle waveform.

[0074] Specifically, when the target cardiac cycle waveform of the ECG signal is slightly different from the reference cardiac cycle waveform of the object to be detected, that is, they are relatively similar, it can be determined that the ECG signal matches the object to be detected. Conversely, when the target cardiac cycle waveform of the ECG signal is significantly different from the reference cardiac cycle waveform of the object to be detected, that is, they are relatively dissimilar, it can be determined that the ECG signal does not match the object to be detected.

[0075] In one case, there may be a scenario where there is no reference cardiac cycle waveform of the object to be detected. In this case, the object to be detected can be considered as a new object, and its identity information and corresponding reference cardiac cycle waveform can be newly created.

[0076] In the above-mentioned ECG signal processing method, after performing signal segmentation processing on the ECG signal of the object to be detected and obtaining multiple cardiac cycle waveforms contained in the ECG signal, the multiple cardiac cycle waveforms are processed to obtain a target cardiac cycle waveform. Then, the target cardiac cycle waveform is compared with a predetermined reference cardiac cycle waveform of the object to be detected to determine the matching result between the ECG signal and the object to be detected. The method utilizes the uniqueness of the ECG signal of each object, extracts the cardiac cycle waveform corresponding to the ECG signal, and compares it with the reference cardiac cycle of the object to be detected. According to the similarity between the two cardiac cycle waveforms, the matching judgment between the ECG signal and the object to be detected is realized, thereby avoiding confusion between the identity information of the object to be detected and the ECG signal, and ensuring the correct matching between the ECG signal entered into the computer and the identity of the object to be detected.

[0077] The matching judgment between the electrocardiogram signal collected by cardiac cycle waveform detection and the object to be detected provided by the present application does not need to rely on human subjective influence, and the detection result is more accurate.

[0078] In an exemplary embodiment, in the above step S220, the ECG signal is segmented to obtain multiple cardiac cycle waveforms, including: performing R point detection on the ECG signal to obtain multiple target R points of the ECG signal; the R point is the highest peak point in the signal wave group of the ECG signal; and based on the multiple target R points, multiple cardiac cycle waveforms are segmented from the ECG signal.

[0079] Among them, point R refers to the signal wave group of the ECG signal, that is, the highest peak point in the P-QRS-T wave group, for example Figure 3 Point R in .

[0080] In a specific implementation, each signal wave group of the ECG signal can be subjected to R point detection to obtain multiple R points, which are recorded as target R points. Then, the cardiac cycle waveform containing a complete P-QRS-T wave group corresponding to each target R point is segmented from the ECG signal by using the characteristics of the P wave, QRS wave and T wave in the P-QRS-T wave group. For example, Figure 4 In the ECG signal shown, nine complete cardiac cycle waveforms can be segmented.

[0081] In this embodiment, the feature that point R is the highest peak point in the signal wave group of the ECG signal is utilized to first detect point R in the ECG signal. The starting point of each cardiac cycle can be accurately located through point R, thereby ensuring the accuracy of the segmentation result.

[0082] In an exemplary embodiment, in the above step S230, multiple cardiac cycle waveforms are processed to obtain a target cardiac cycle waveform, specifically including: performing abnormality detection processing on multiple cardiac cycle waveforms, eliminating abnormal cardiac cycle waveforms from the multiple cardiac cycle waveforms, and obtaining multiple screened cardiac cycle waveforms; performing statistical processing on the multiple screened cardiac cycle waveforms to obtain a target cardiac cycle waveform.

[0083] In the specific implementation, the ECG signal may be disturbed by external factors during the acquisition process, resulting in the presence of affected cardiac cycles in the acquired ECG signal. For example, if the ECG signal is disturbed by motion, when the motion artifact has the same frequency component as the ECG signal, the motion artifact will be superimposed on the ECG signal to produce unreliable eigenvalues, which cannot be completely filtered out by filtering, so these abnormal cardiac cycles need to be removed.

[0084] More specifically, before removing the abnormal cardiac cycle, each cardiac cycle waveform needs to be detected for abnormality. When a cardiac cycle waveform with abnormal waveform change is detected, it can be determined as an abnormal cardiac cycle waveform. Further, the abnormal cardiac cycle waveform can be removed from the multiple cardiac cycle waveforms segmented from the electrocardiogram signal to obtain multiple screened cardiac cycle waveforms. Finally, the multiple screened cardiac cycle waveforms are statistically processed to obtain the target cardiac cycle waveform.

[0085] In this embodiment, by performing abnormal detection processing on multiple cardiac cycle waveforms, eliminating abnormal cardiac cycle waveforms therein, and determining the target cardiac cycle waveform from the obtained screened cardiac cycle waveforms, it is possible to avoid interference of abnormal cardiac cycle waveforms on the target cardiac cycle waveform and improve the accuracy of the determined target cardiac cycle waveform.

[0086] In an exemplary embodiment, each cardiac cycle waveform includes ECG signal values ​​at multiple sampling points, and each cardiac cycle waveform has the same number of sampling points; the above-mentioned statistical processing of multiple screened cardiac cycle waveforms to obtain a target cardiac cycle waveform includes: performing statistical processing on the ECG signal values ​​of each screened cardiac cycle waveform at the same sampling point to obtain statistical values ​​at each sampling point; the same sampling points represent sampling points with the same sampling order in each cardiac cycle waveform; and obtaining the target cardiac cycle waveform based on the statistical values ​​at each sampling point.

[0087] In a specific implementation, the ECG signal values ​​of each screened cardiac cycle waveform at the same sampling point are statistically processed, and the implementation method for obtaining the statistical value at each sampling point can be: the median value of the ECG signal values ​​of each screened cardiac cycle waveform at the same sampling point is used as the statistical value at the sampling point. For example, suppose there are 5 cardiac cycle waveforms in total, and the ECG signal values ​​of each cardiac cycle waveform at sampling point 1 are 2, 5, 6, 8, and 3 respectively, then the statistical value corresponding to sampling point 1 is the median value 5 among 2, 5, 6, 8, and 3. By analogy, the statistical value corresponding to each sampling point can be determined, and then the statistical value corresponding to each sampling point can be fitted to the target cardiac cycle waveform according to the order of each sampling point.

[0088] In this embodiment, for each sampling point, the median value of the electrocardiographic signal value of each screened cardiac cycle waveform at the sampling point is used as a statistical value to determine the target cardiac cycle waveform, which can further reduce the influence of possible abnormal maximum and minimum values, etc., and is more stable and accurate than the method of randomly selecting a cardiac cycle waveform as the target cardiac cycle waveform.

[0089] In an exemplary embodiment, Figure 5As shown, in the above step S240, comparing the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the object to be detected, and determining the matching result between the ECG signal and the object to be detected, specifically includes:

[0090] Step S241 , constructing an ECG data matrix according to the number of sampling points corresponding to the target cardiac cycle waveform and the ECG signal value of the target cardiac cycle waveform at each sampling point.

[0091] Specifically, the number of sampling points can be the number of rows, and the number of target cardiac cycle waveforms can be the number of columns to construct an ECG data matrix. Each lead corresponds to a set of ECG signals, and each set of ECG signals corresponds to a target cardiac cycle waveform. Therefore, when a single lead is taken as an example, the number of target cardiac cycle waveforms is 1. If the number of sampling points is set to 1000, the constructed ECG data matrix is ​​a matrix of 1000 rows and 1 column. When 12 leads are taken as an example, the number of target cardiac cycle waveforms is 12. If the number of sampling points is set to 1000, the constructed ECG data matrix is ​​a matrix of 1000 rows and 12 columns.

[0092] In practical applications, considering that the heart is a three-dimensional structure and the cardiac electrical activity is also three-dimensional, the 12-lead ECG records more spatial information and can reflect more comprehensive identity information compared to using a single-lead signal. Therefore, the 12-lead ECG signal can be used to match the object to be detected.

[0093] In this step, the complete cardiac cycle waveform is used to construct the ECG data matrix, which contains more complete information than the method of extracting waveform amplitude, interval and other characteristic values. In addition, if the amplitude, interval and other characteristic values ​​are calculated incorrectly, the recognition results will also be affected.

[0094] Step S242, determining the first characteristic information of the target cardiac cycle waveform according to the ECG data matrix.

[0095] The first characteristic information may be understood as characteristic information that may characterize the target cardiac cycle waveform.

[0096] Specifically, ECG data can be understood as a digitized ECG signal. Since the number of sampling points of the ECG signal is large, the constructed ECG data matrix will also be large. Therefore, before determining the first characteristic information of the target cardiac cycle waveform, the ECG data matrix can be firstly subjected to dimensionality reduction processing, and the first characteristic information of the target cardiac cycle waveform can be determined according to the ECG data matrix after dimensionality reduction. This method takes into account that the value of the ECG data matrix constructed based on the number of sampling points is large and the processing time is also long. Therefore, the method of extracting its characteristic information after dimensionality reduction of the ECG data matrix can improve the extraction rate of characteristic information on the basis of ensuring accurate feature extraction.

[0097] Step S243, comparing the first characteristic information of the target cardiac cycle waveform with the second characteristic information of the reference cardiac cycle waveform to determine a matching result between the electrocardiogram signal and the object to be detected.

[0098] Specifically, the reference cardiac cycle waveform preset for the object to be detected also has corresponding characteristic information, which is recorded as the second characteristic information. The second characteristic information is determined in the same way as the first characteristic information. The characteristic information can be used to characterize the uniqueness of the cardiac cycle waveform, and the cardiac cycle waveform can be used to characterize the uniqueness of the object. Therefore, after determining the first characteristic information of the target cardiac cycle waveform, the first characteristic information can be compared with the second characteristic information of the reference cardiac cycle waveform of the object to be detected, and the matching result between the electrocardiogram signal and the object to be detected is determined based on the comparison result.

[0099] More specifically, the difference between the first feature information and the second feature information can be obtained; when the difference is less than or equal to a threshold, it is determined that the ECG signal matches the object to be detected. Conversely, when the difference is greater than the threshold, it is determined that the ECG signal does not match the object to be detected. Specifically, the difference can be obtained by calculating the Euclidean distance of the two feature information, and the Euclidean distance can be specifically a standardized Euclidean distance.

[0100] If the first feature information is recorded as X(x 11 ,x 12 ,…,x 1n ), the second feature information is M(x 21 ,x 22 ,…,x 2n ), then the standardized Euclidean distance d between the first feature information and the second feature information can be expressed as:

[0101]

[0102] Among them, s k is the standard deviation.

[0103] In this embodiment, when comparing the target cardiac cycle waveform with the reference cardiac cycle waveform, considering that it is difficult to directly compare the cardiac cycle waveforms, a method is adopted to construct an ECG data matrix, extract feature information of the ECG data matrix, and then compare the feature information to achieve comparison between the cardiac cycle waveforms. This can improve the comparison rate while ensuring the accuracy of the comparison results.

[0104] Further, in an exemplary embodiment, in step S242, the first characteristic information of the target cardiac cycle waveform is determined based on the ECG data matrix, specifically including: performing singular value decomposition processing on the ECG data matrix to obtain a characteristic matrix corresponding to the ECG data matrix; and determining the first characteristic information of the target cardiac cycle waveform based on the element values ​​in the characteristic matrix.

[0105] Among them, singular value decomposition (SVD) refers to decomposing a matrix into two unitary matrices and a diagonal matrix. The two unitary matrices are matrices on rows and columns respectively.

[0106] Specifically, let the ECG data matrix be A, the number of sampling points be 1000, and the ECG signal be a 12-lead ECG signal, then A is a matrix with 1000 rows and 12 columns. Figure 6 As shown, when the matrix A is subjected to singular value decomposition, it can be divided into:

[0107] A=UΣV T

[0108] Where U is a 1000×1000 unitary matrix, V is a 12×12 unitary matrix, and Σ is a 1000×12 diagonal matrix. Where U and V satisfy: U T U=I,V T V=I. Among them, V T represents the transposed matrix of V, U T Represents the transposed matrix of U.

[0109] Among them, UΣV T These three matrices represent the characteristic matrix of the ECG data matrix A. After determining the characteristic matrix, the characteristic vector X corresponding to the largest number (for example, 3) of singular values ​​in the diagonal matrix Σ in the characteristic matrix can be selected, and the characteristic vector X is used as the first characteristic information of the target cardiac cycle waveform. It should be noted that, if Figure 7 As shown, since each element in the diagonal matrix Σ corresponds to 1000 element values ​​of the column vector in the matrix U, in the matrix V T There are 12 element values ​​corresponding to the row vector in . Therefore, when the selected eigenvector X is the eigenvector corresponding to the three largest singular values ​​in the diagonal matrix Σ, X has a total of 3×(1000+12+1)=3039 numbers.

[0110] In this embodiment, by performing singular value decomposition on the ECG data matrix, the data can be effectively reduced in dimension. For example, when the ECG data matrix is ​​a 1000×12 matrix, if the ECG data matrix is ​​used directly as a eigenvector, the amount of data is 12×1000=12000, while the amount of data of the eigenvector X formed by singular value decomposition is only one-fourth of that, which effectively reduces the data storage space and computational complexity, thereby improving the matching efficiency between the ECG signal and the object to be detected.

[0111] In an exemplary embodiment, before the above step S220 performs signal segmentation processing on the ECG signal to obtain a plurality of cardiac cycle waveforms, it further includes: performing filtering processing on the ECG signal to obtain a filtered ECG signal;

[0112] Correspondingly, step S220 also includes: performing signal segmentation processing on the filtered ECG signal to obtain a plurality of cardiac cycle waveforms.

[0113] In a specific implementation, after acquiring the ECG signal of the object to be detected, the ECG signal can be first filtered, and the filtered ECG signal can be segmented to obtain multiple cardiac cycle waveforms. More specifically, the filtering of the ECG signal can be implemented using a high-pass Butterworth filter, a low-pass Butterworth filter, and a notch filter. Among them, the high-pass Butterworth filter can be used to filter out the baseline drift of the ECG signal; the low-pass Butterworth filter can be used to remove high-frequency noise (such as myoelectric noise, etc.); the notch filter can be used to suppress the interference of the 50 / 60Hz power frequency.

[0114] In this embodiment, by filtering the ECG signal, the baseline drift, high-frequency noise and some industrial frequency interference of the ECG signal can be filtered out, thereby improving the quality of the ECG signal. Subsequently, the cardiac cycle waveform is segmented to improve the accuracy of the segmented cardiac cycle waveform.

[0115] It is understandable that ECG signals are obtained from ECG acquisition devices. After the ECG acquisition devices commonly used in hospitals are used by the previous subject, medical staff will replace the battery with a new one before giving it to the next subject. When the battery is replaced, the data in the ECG acquisition device will be cleared. However, if the battery is forgotten, there will be a phenomenon that the dynamic ECG data of multiple subjects will exist in one ECG acquisition device. If these dynamic ECG data are entered into the computer and mistakenly analyzed as the data of one subject, it will cause misdiagnosis.

[0116] Therefore, in order to solve this problem, the present application also proposes a method for processing the situation where the acquired ECG signal contains ECG signals of multiple objects.

[0117] Correspondingly, in an exemplary embodiment, the method also includes: performing interruption detection on the ECG signal; when an interruption is detected in the ECG signal, splitting the acquired ECG signal into multiple segments of ECG signals according to the interruption information; and performing identity matching on each segment of the ECG signal with the corresponding object to be detected.

[0118] In a specific implementation, when there are multiple objects to be detected corresponding to the ECG signals collected by the ECG acquisition device, the ECG signals obtained from the ECG acquisition device also correspond to multiple objects to be detected. Taking this situation into consideration, after obtaining the ECG signals, an interruption detection can be performed on the ECG signals, that is, whether there is a situation where there is no ECG signal data for a period of time. If an interruption is detected, the obtained ECG signal is split into multiple segments of ECG signals according to the interruption information of the detected ECG signal. That is, each time an interruption information is detected, a split is performed, thereby splitting the ECG signal obtained from the ECG acquisition device into multiple segments of ECG signals. Further, the identity of each segment of the ECG signal can be matched with the corresponding object to be detected, and the matching method is the same as the method described in the above embodiment.

[0119] In this embodiment, the acquired ECG signal is split into multiple segments according to the interruption information of the ECG signal; the identity of each segment of the ECG signal is matched with the corresponding object to be detected respectively, so as to realize automatic identification whether there are multiple objects sharing one ECG acquisition device, thereby avoiding the problem that the dynamic ECG data of multiple objects in one ECG acquisition device are difficult to distinguish, resulting in misdiagnosis or the need to re-acquire the ECG signal.

[0120] In one embodiment, in order to facilitate those skilled in the art to understand the embodiment of the present application, the following will take the ECG signal collected by 12 leads as an example. Figure 8 This application is described in detail. Figure 8 As shown, the specific steps include:

[0121] (1) Obtain 12 sets of ECG signals from the subject to be tested.

[0122] (2) Filtering is performed on each group of ECG signals to obtain 12 groups of filtered ECG signals.

[0123] (3) Comprehensive R-point detection is performed on the 12 groups of ECG signals, and based on the detected multiple target R-points, multiple cardiac cycle waveforms are segmented from each group of ECG signals.

[0124] Specifically, when performing R point detection on 12 groups of ECG signals, it is necessary to comprehensively consider the conditions of each group of ECG signals, and each R point determined is an R point shared by the 12 groups of ECG signals.

[0125] (4) Abnormal cardiac cycle waveforms are eliminated from the multiple cardiac cycle waveforms contained in each group of electrocardiogram signals to obtain multiple screened cardiac cycle waveforms.

[0126] Specifically, when removing abnormal cardiac cycle waveforms from 12 groups of ECG signals, it is necessary to comprehensively consider the abnormal conditions of each group of ECG signals. Specifically, when a cardiac cycle waveform of a group of ECG signals is detected to be abnormal and needs to be removed, in addition to removing the abnormal cardiac cycle waveform from the group of ECG signals, the cardiac cycle waveforms corresponding to the abnormal cardiac cycle waveform need to be removed from the other 11 groups of ECG signals, regardless of whether they are abnormal, to ensure that the number of cardiac cycle waveforms in each group of ECG signals is consistent.

[0127] (5) Based on each filtered cardiac cycle waveform of each group of electrocardiographic signals, the dominant heartbeat of each lead is extracted as the target cardiac cycle waveform.

[0128] In this step, when extracting the target cardiac cycle waveform, each group of ECG signals can be extracted separately, and the groups of ECG signals do not affect each other.

[0129] Specifically, for each group of ECG signals, the median value of the ECG signal value of each filtered cardiac cycle waveform in the group of ECG signals at the same sampling point can be determined respectively as the statistical value at each sampling point; based on the statistical value at each sampling point, the target cardiac cycle waveform of the group of ECG signals is obtained.

[0130] (6) Construct an ECG data matrix based on the 12 target cardiac cycle waveforms corresponding to the 12 groups of ECG signals.

[0131] (7) Performing singular value decomposition on the ECG data matrix to extract first feature information of the target cardiac cycle waveform.

[0132] (8) Calculate the standard Euclidean distance d between the first characteristic information and the second characteristic information of the reference cardiac cycle waveform of the object to be detected.

[0133] (9) When d is less than or equal to the threshold, the identity authentication is determined to be successful, and the second feature information is replaced by the first feature information to implement the update of the second feature information.

[0134] (10) When d is greater than the threshold, it is determined that the identity authentication fails, new user identity information is created in the identity database, and the mapping relationship between the user identity information and its corresponding first feature information is saved.

[0135] The ECG signal processing method for matching an ECG signal with an object to be detected provided in this embodiment has the following beneficial effects:

[0136] (1) Using the dominant heartbeat for identity recognition can further reduce the impact of interference or abnormal conditions and is more stable than randomly selecting a cardiac cycle waveform.

[0137] (2) Compared with extracting waveform amplitude, interval and other eigenvalues, using the complete cardiac cycle waveform to construct the ECG data matrix contains more complete information; in addition, if the amplitude, interval and other eigenvalues ​​are calculated incorrectly, it will also affect the recognition results.

[0138] (3) The heart is a three-dimensional structure, and its electrical activity is also three-dimensional. The 12-lead recording records more spatial information and can reflect more comprehensive identity information compared to using a single-lead signal.

[0139] (4) Singular value decomposition (SVD) can effectively reduce the dimension of data, effectively reducing the storage space and computational complexity of the data.

[0140] (5) By updating the characteristic information of the reference cardiac cycle waveform of the user in the identity database, timely updating of the identity database is ensured.

[0141] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0142] Based on the same inventive concept, the embodiment of the present application also provides an ECG signal processing device for implementing the ECG signal processing method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more ECG signal processing device embodiments provided below can refer to the limitations of the ECG signal processing method above, and will not be repeated here.

[0143] In one embodiment, Fig. 9 As shown, an electrocardiogram signal processing device is provided, including: an acquisition module 910, a segmentation module 920, a processing module 930 and a determination module 940, wherein:

[0144] An acquisition module 910 is used to acquire an electrocardiogram signal of a subject to be detected;

[0145] The segmentation module 920 is used to perform signal segmentation processing on the ECG signal to obtain multiple cardiac cycle waveforms contained in the ECG signal;

[0146] A processing module 930 is used to perform statistical processing on multiple cardiac cycle waveforms to obtain a target cardiac cycle waveform;

[0147] The determination module 940 is used to compare the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the object to be detected, and determine the matching result between the ECG signal and the object to be detected.

[0148] In one of the embodiments, the segmentation module 920 is also used to perform R point detection on the ECG signal to obtain multiple target R points of the ECG signal; the R point is the highest peak point in the signal wave group of the ECG signal; based on the multiple target R points, multiple cardiac cycle waveforms are segmented from the ECG signal.

[0149] In one embodiment, the processing module 930 is also used to perform abnormality detection processing on multiple cardiac cycle waveforms, eliminate abnormal cardiac cycle waveforms from the multiple cardiac cycle waveforms, and obtain multiple screened cardiac cycle waveforms; perform statistical processing on the multiple screened cardiac cycle waveforms to obtain a target cardiac cycle waveform.

[0150] In one embodiment, each cardiac cycle waveform includes ECG signal values ​​at multiple sampling points, and each cardiac cycle waveform has the same number of sampling points; the processing module 930 is further used to perform statistical processing on the ECG signal values ​​of each screened cardiac cycle waveform at the same sampling point to obtain statistical values ​​at each sampling point; the same sampling points represent sampling points with the same sampling order in each cardiac cycle waveform; based on the statistical values ​​at each sampling point, the target cardiac cycle waveform is obtained.

[0151] In one of the embodiments, the determination module 940 is also used to construct an ECG data matrix based on the number of sampling points corresponding to the target cardiac cycle waveform and the ECG signal values ​​of the target cardiac cycle waveform at each sampling point; determine the first characteristic information of the target cardiac cycle waveform based on the ECG data matrix; compare the first characteristic information of the target cardiac cycle waveform with the second characteristic information of the reference cardiac cycle waveform to determine the matching result between the ECG signal and the object to be detected.

[0152] In one embodiment, the determination module 940 is further used to perform singular value decomposition processing on the ECG data matrix to obtain a feature matrix corresponding to the ECG data matrix; and determine the first feature information of the target cardiac cycle waveform based on the element values ​​in the feature matrix.

[0153] In one of the embodiments, the device further comprises a filtering module, which is used to filter the ECG signal to obtain a filtered ECG signal;

[0154] The segmentation module 920 is also used to perform signal segmentation processing on the filtered ECG signal to obtain multiple cardiac cycle waveforms.

[0155] In one embodiment, the device further comprises:

[0156] A detection module, used for detecting interruption of ECG signals;

[0157] A splitting module is used to split the acquired ECG signal into multiple segments according to the interruption information when an interruption of the ECG signal is detected;

[0158] The matching module is used to perform identity matching between each segment of the ECG signal and the corresponding object to be detected.

[0159] Each module in the above-mentioned ECG signal processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0160] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for processing electrocardiogram signals is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0161] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0163] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0164] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0166] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0167] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0168] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing an electrocardiogram signal, characterized in that: The method comprises: Acquire the electrocardiogram signal of the object to be detected; Performing signal segmentation processing on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms contained in the electrocardiogram signal; Processing the multiple cardiac cycle waveforms to obtain a target cardiac cycle waveform; The target cardiac cycle waveform is compared with a predetermined reference cardiac cycle waveform of the subject to be detected to determine a matching result between the electrocardiogram signal and the subject to be detected.

2. The method according to claim 1, characterized in that The signal segmentation processing is performed on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms, including: Performing R point detection on the ECG signal to obtain a plurality of target R points of the ECG signal; the R point is the highest peak point in the signal wave group of the ECG signal; A plurality of cardiac cycle waveforms are segmented from the electrocardiographic signal according to the plurality of target R points.

3. The method according to claim 1, characterized in that The processing of the plurality of cardiac cycle waveforms to obtain a target cardiac cycle waveform includes: Performing abnormality detection processing on the multiple cardiac cycle waveforms, eliminating abnormal cardiac cycle waveforms from the multiple cardiac cycle waveforms, and obtaining multiple screened cardiac cycle waveforms; Statistical processing is performed on the plurality of screened cardiac cycle waveforms to obtain a target cardiac cycle waveform.

4. The method according to claim 3, characterized in that: Each cardiac cycle waveform includes electrocardiographic signal values ​​at multiple sampling points, and the number of sampling points of each cardiac cycle waveform is the same; The statistical processing of the plurality of screened cardiac cycle waveforms to obtain a target cardiac cycle waveform includes: Performing statistical processing on the electrocardiogram signal values ​​of each screened cardiac cycle waveform at the same sampling point to obtain statistical values ​​at each sampling point; the same sampling point means the sampling points in each cardiac cycle waveform with the same sampling order; Based on the statistical values ​​at the various sampling points, the target cardiac cycle waveform is obtained.

5. The method according to claim 1, characterized in that: The step of comparing the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the object to be detected to determine a matching result between the electrocardiogram signal and the object to be detected includes: Constructing an ECG data matrix according to the number of sampling points corresponding to the target cardiac cycle waveform and the ECG signal value of the target cardiac cycle waveform at each sampling point; Determining first characteristic information of the target cardiac cycle waveform according to the electrocardiogram data matrix; The first characteristic information of the target cardiac cycle waveform is compared with the second characteristic information of the reference cardiac cycle waveform to determine a matching result between the electrocardiogram signal and the object to be detected.

6. The method according to claim 5, characterized in that Determining the first characteristic information of the target cardiac cycle waveform according to the electrocardiogram data matrix includes: Performing singular value decomposition processing on the ECG data matrix to obtain a feature matrix corresponding to the ECG data matrix; Based on the element values ​​in the characteristic matrix, first characteristic information of the target cardiac cycle waveform is determined.

7. The method according to claim 1, characterized in that Before performing signal segmentation processing on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms, the method further includes: Performing filtering on the electrocardiogram signal to obtain a filtered electrocardiogram signal; The signal segmentation processing is performed on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms, including: The filtered electrocardiogram signal is subjected to signal segmentation processing to obtain a plurality of cardiac cycle waveforms.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Performing interruption detection on the electrocardiogram signal; When an interruption of the electrocardiogram signal is detected, splitting the acquired electrocardiogram signal into multiple segments of electrocardiogram signals according to the interruption information; The identity of each segment of the ECG signal is matched with the corresponding object to be detected.

9. An electrocardiogram signal processing device, characterized in that: The device comprises: An acquisition module, used for acquiring the electrocardiogram signal of the object to be detected; A segmentation module, used for performing signal segmentation processing on the electrocardiogram signal to obtain a plurality of cardiac cycle waveforms contained in the electrocardiogram signal; A processing module, used for processing the multiple cardiac cycle waveforms to obtain a target cardiac cycle waveform; The determination module is used to compare the target cardiac cycle waveform with a predetermined reference cardiac cycle waveform of the object to be detected, and determine a matching result between the electrocardiogram signal and the object to be detected.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the electrocardiographic signal processing method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the electrocardiographic signal processing method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the electrocardiographic signal processing method according to any one of claims 1 to 8 are implemented.

Images