Method, device and equipment for quality grading extraction of ballistocardiogram signals and storage medium

Abstract

The present application relates to the technical field of signal processing, and particularly relates to a quality grading extraction method, device and equipment of a ballistocardiogram signal and a storage medium, wherein a plurality of ballistocardiogram unit signals of a ballistocardiogram signal to be detected are subjected to empty bed detection, body movement detection, positioning detection and waveform integrity detection, objective factors influencing the quality of the ballistocardiogram unit signals are fully considered, the multi-dimensional characteristics of the ballistocardiogram unit signals can be analyzed, and the precision of extraction of the ballistocardiogram unit signals under a complex application scenario is improved.

Description

Technical Field

[0001] This invention relates to the field of signal processing technology, and in particular to a method, apparatus, device, and storage medium for quality grading extraction of cardiac impaction signals. Background Technology

[0002] Ballistocardiography (BCG) describes the subtle vibrations in the human body caused by the heart's ejection of blood and has been proven to be an effective method for monitoring the heart. The BCG signal is a weak force signal that can be converted into an electrical signal by a pressure sensor without direct contact, enabling the unobstructed acquisition of the user's vital signs.

[0003] The existing technical solution is to extract features based on peak positioning and perform quality control on the detection signal based on these features. However, the above method relies too much on synchronous ECG signals, and uses positioning features in unknown signals without knowing whether the signal can meet the positioning conditions. The results are somewhat random and unreasonable. Secondly, due to the weakness of BCG signals, their morphology is easily affected by interference. In practical applications, the signal can be affected by noise, respiration, body movement, etc., leading to increased signal complexity or weakened rhythmicity, making it impossible to perform equivalent analysis and applications. When the signal quality is poor, the physiological information contained in the signal morphology cannot be effectively extracted.

[0004] Therefore, quality control of the signals acquired by impactography and selection of relatively better quality data are of great significance for subsequent data processing and analysis (such as signal localization, HRV analysis, sleep staging, sleep apnea, etc.). Summary of the Invention

[0005] Based on this, the purpose of the present invention is to provide a method, apparatus, device, and storage medium for quality grading extraction of cardiac impaction signals. By performing empty bed detection, body motion detection, positioning detection, and waveform integrity detection on several cardiac impaction signal units to be detected, the present invention fully considers the objective factors affecting the quality of cardiac impaction signal units, and can analyze the multidimensional features of cardiac impaction signal units, thereby improving the accuracy of extracting cardiac impaction signal units in complex application scenarios.

[0006] In a first aspect, embodiments of this application provide a method for quality grading extraction of cardiac impaction signals, comprising the following steps: The cardiac impact image signal to be detected is obtained, and the cardiac impact image signal is divided according to a preset signal length to obtain several cardiac impact image unit signals. Empty bed detection is performed on the signals of the plurality of cardiac impaction units to obtain the empty bed detection results of the signals of the plurality of cardiac impaction units; Based on the empty bed detection results, body motion detection is performed on the signals of the plurality of cardiac impact maps to obtain the body motion detection results of the signals of the plurality of cardiac impact maps. Based on the body motion detection results, the location detection of the plurality of cardiac impaction unit signals is performed to obtain the location detection results of the plurality of cardiac impaction unit signals; Based on the positioning detection results, waveform integrity detection is performed on the signals of the plurality of cardiac impactor units to obtain the waveform integrity detection of the signals of the plurality of cardiac impactor units; Based on the empty bed detection results, body motion detection results, positioning detection results, and waveform integrity detection results of the several cardiac impaction unit signals, the quality assessment results of the several cardiac impaction unit signals are obtained, and based on the quality assessment results, several target signals are extracted from the several cardiac impaction unit signals.

[0007] Secondly, embodiments of this application provide a quality grading extraction device for cardiac impaction signals, comprising: The signal acquisition module is used to acquire the cardiac impact map signal to be detected, and divide the cardiac impact map signal into several cardiac impact map unit signals according to the preset signal length. An empty bed detection module is used to perform empty bed detection on the signals of the plurality of cardiac impaction units and obtain the empty bed detection results of the signals of the plurality of cardiac impaction units; The body movement detection module is used to perform body movement detection on the signals of the plurality of cardiac impact maps based on the empty bed detection results, and to obtain the body movement detection results of the signals of the plurality of cardiac impact maps. The positioning detection module is used to perform positioning detection on the signals of the plurality of cardiac impactor units based on the body motion detection results, and obtain the positioning detection results of the signals of the plurality of cardiac impactor units; The waveform integrity detection module is used to perform waveform integrity detection on the signals of the plurality of cardiac impactor units based on the positioning detection results, and obtain the waveform integrity detection of the signals of the plurality of cardiac impactor units. The signal extraction module is used to obtain the quality assessment results of the several cardiac impaction unit signals based on the empty bed detection results, body motion detection results, positioning detection results and waveform integrity detection results of the several cardiac impaction unit signals, and to extract several target signals from the several cardiac impaction unit signals based on the quality assessment results.

[0008] Thirdly, embodiments of this application provide a computer device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the cardiac impaction signal quality grading extraction method as described in the first aspect.

[0009] Fourthly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the steps of the cardiac impaction signal quality grading extraction method as described in the first aspect.

[0010] In this application embodiment, a method, apparatus, device, and storage medium for quality grading extraction of cardiac impaction signals are provided. By performing empty bed detection, body motion detection, positioning detection, and waveform integrity detection on several cardiac impaction signal units to be detected, the objective factors affecting the quality of cardiac impaction signal units are fully considered. This enables the analysis of multi-dimensional features of cardiac impaction signal units and improves the accuracy of extracting cardiac impaction signal units in complex application scenarios.

[0011] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0012] Figure 1 A schematic flowchart illustrating a method for quality grading extraction of cardiac impaction signals according to an embodiment of this application; Figure 2 A flowchart illustrating a method for quality grading extraction of cardiac impaction signals according to another embodiment of this application; Figure 3 This is a schematic diagram of step S2 in the process of a method for quality grading extraction of cardiac impaction signals provided in one embodiment of this application; Figure 4 This is a schematic diagram of step S3 in the process of a method for quality grading extraction of cardiac impaction signals provided in one embodiment of this application; Figure 5 This is a schematic diagram of step S5 in the process of a method for quality grading extraction of cardiac impaction signals provided in one embodiment of this application; Figure 6 This is a schematic diagram of step S4 in the process of the quality grading extraction method for cardiac impaction signals provided in another embodiment of this application; Figure 7 This is a schematic diagram of step S4 in the process of a method for quality grading extraction of cardiac impaction signals provided in an embodiment of this application; Figure 8 This is a schematic diagram of step S5 in the process of a method for quality grading extraction of cardiac impaction signals provided in one embodiment of this application; Figure 9 A schematic diagram of a quality grading and extraction device for cardiac impaction signals provided in one embodiment of this application; Figure 10 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation

[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0014] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0015] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0016] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for quality grading extraction of cardiac impaction signals according to an embodiment of this application. The method includes the following steps: S1: Obtain the cardiac impact map signal to be detected, and divide the cardiac impact map signal into several cardiac impact map unit signals according to the preset signal length.

[0017] The execution subject of the quality grading extraction method for cardiac impaction signals is the extraction device for the quality grading extraction method of cardiac impaction signals (hereinafter referred to as the extraction device). In an optional embodiment, the extraction device may be a computer device, a server, or a server cluster composed of multiple computer devices.

[0018] In one optional embodiment, the extraction device can obtain the user's physiological signals by querying a preset database. In another optional embodiment, the extraction device can use a piezoelectric sensor to obtain the user's human body micro-vibration signals without affecting the user's normal sleep. The human body micro-vibration signals are converted into digital signals by an analog-to-digital conversion module. The data processing module analyzes the digital signals and extracts the user's physiological signals from the digital signals. The physiological signals are represented as a time series composed of vectors corresponding to several sampling points. Since the energy of physiological signals is mainly between 0 and 50 Hz, with the energy spectrum of respiratory signals ranging from 0.01 to 1 Hz and the energy spectrum of cardiac impact signals ranging from 1 to 10 Hz, the extraction device can filter the physiological signals to separate the respiratory and cardiac impact signals. Specifically, the extraction device can input the physiological signals into a preset Butterworth bandpass filter to filter out respiratory information and high-frequency interference noise, thereby obtaining the cardiac impact signal.

[0019] The cardiac impact signal is used in heart rate detection, heart rate variability monitoring, cardiac contractility and cardiac output change monitoring.

[0020] The piezoelectric sensor can be a piezoelectric ceramic sensor, a piezoelectric thin film sensor, etc., and can be placed under the heart when lying flat or under the pillow to acquire the user's human body micro-vibration signals.

[0021] The analog-to-digital conversion module can be an external chip or a corresponding built-in analog-to-digital conversion interface to convert human body micro-vibration signals into digital signals.

[0022] The data processing module can use a DSP (Digital Signal Processing) or ARM (Advanced RISC Machines) processor to analyze the digital signal and extract the user's physiological signals from it.

[0023] In this embodiment, the extraction device performs windowing processing on the cardiac impact map signal according to the preset signal length, dividing it into several corresponding cardiac impact map unit signals. The cardiac impact map unit signal includes several ts segments, and each segment has t*1000 sampling points.

[0024] Please see Figure 2 , Figure 2 A flowchart illustrating a method for quality grading extraction of cardiac impaction signals according to another embodiment of this application is provided, further comprising step S7, wherein step S7, prior to step S2, comprises the following steps: S7: Standardize the signals of the several cardiac impactor units respectively to obtain several standard cardiac impactor unit signals.

[0025] In this embodiment, the extraction device takes the plurality of cardiac impaction imaging unit signals as input signal segments, and performs standardization processing on the input signal segments according to a preset standardization algorithm, that is, subtracts the mean and divides the variance from each data in the input signal segment to obtain several standard cardiac impaction imaging unit signals. The calculation formula of the standardization algorithm is as follows:

[0026] In the formula, For the first i One input signal segment, For the first i The first input signal segment j One data point, It is the mean of the input signal segment. It is the standard deviation of the input signal segment.

[0027] S2: Perform empty bed detection on the signals of the plurality of cardiac impaction units to obtain the empty bed detection results of the signals of the plurality of cardiac impaction units.

[0028] An empty bed refers to an invalid signal generated by the subject that is not detected by the sensor. In this embodiment, the extraction device performs empty bed detection on the signals of the several cardiac impaction units to obtain the empty bed detection results of the signals of the several cardiac impaction units.

[0029] Please see Figure 3 , Figure 3 This is a schematic diagram of step S2 in the flow chart of the method for quality grading extraction of cardiac impaction signals provided in an embodiment of this application, including steps S21 to S22, as follows: S21: Obtain the amplitude of each sampling point in each of the standard cardiac impact diagram unit signals, and mark each sampling point of each of the standard cardiac impact diagram unit signals according to the preset amplitude threshold, so as to obtain the marking data of each sampling point in each of the standard cardiac impact diagram unit signals.

[0030] In this embodiment, the extraction device obtains the amplitude of each sampling point in each of the standard cardiac impaction unit signals, and marks each sampling point of each of the standard cardiac impaction unit signals according to a preset amplitude threshold, thereby obtaining the marked data of each sampling point in each of the standard cardiac impaction unit signals. The marked data includes empty bed marked data and non-empty bed marked data.

[0031] Specifically, when the amplitude of a sampling point of the standard cardiac impact diagram unit signal is greater than the amplitude threshold, the sampling point of the standard cardiac impact diagram unit signal is marked as empty bed marker data; when the amplitude of a sampling point of the standard cardiac impact diagram unit signal is less than or equal to the amplitude threshold, the sampling point of the standard cardiac impact diagram unit signal is marked as non-empty bed marker data.

[0032] S22: Based on the labeled data of all sampling points of the same standard cardiac impaction unit signal, calculate the empty bed signal ratio of each standard cardiac impaction unit signal. According to the empty bed signal ratio of each standard cardiac impaction unit signal and the preset empty bed signal ratio threshold, obtain the empty bed detection result of each standard cardiac impaction unit signal. The empty bed detection result includes the empty bed detection success result and the empty bed detection failure result.

[0033] In this embodiment, the device extracts the labeled data of all sampling points of the same standard cardiac impaction unit signal, calculates the empty bed signal ratio of each standard cardiac impaction unit signal, and obtains the empty bed detection result of each standard cardiac impaction unit signal based on the empty bed signal ratio of each standard cardiac impaction unit signal and a preset empty bed signal ratio threshold. The empty bed detection result includes a successful empty bed detection result and a failed empty bed detection result.

[0034] Specifically, when the empty bed signal ratio of the standard cardiac impact mapping unit is greater than the empty bed signal ratio threshold, the extraction device obtains a successful empty bed detection result for the standard cardiac impact mapping unit; when the empty bed signal ratio of the standard cardiac impact mapping unit is less than or equal to the empty bed signal ratio threshold, the extraction device obtains a failed empty bed detection result for the standard cardiac impact mapping unit.

[0035] S3: Based on the empty bed detection results, perform body motion detection on the signals of the plurality of cardiac impact maps to obtain the body motion detection results of the signals of the plurality of cardiac impact maps.

[0036] Body motion refers to the motion artifacts caused by the subject's body movement during signal acquisition. Since the subject's movement is random, the amplitude distribution of motion artifacts is also random, typically exhibiting a long-tailed distribution. In this embodiment, the extraction device performs body motion detection on the signals of the several cardiac impactor units based on the empty bed detection results, obtaining the body motion detection results for the signals of the several cardiac impactor units.

[0037] Please see Figure 4 , Figure 4 This is a schematic diagram of step S3 in the flow chart of the quality grading extraction method for impact imaging signals provided in an embodiment of this application, including steps S31 to S34, as follows: S31: When the empty bed detection result is a successful empty bed detection result, wavelet decomposition is performed on each of the standard cardiac impact map unit signals to obtain the corresponding sub-band signal set of each of the standard cardiac impact map unit signals.

[0038] In this embodiment, when the empty bed detection result is a successful empty bed detection result, the extraction device performs wavelet decomposition on each of the standard cardiac impact map unit signals to obtain the corresponding sub-band signal set of each of the standard cardiac impact map unit signals, wherein the sub-band signal set includes several sub-band signals.

[0039] Specifically, the extraction device can select the Daubechies 4th order wavelet basis to perform wavelet decomposition on each of the standard cardiac impaction unit signals, decompose them into several sub-band signals, and obtain the corresponding sub-band signal set of each of the standard cardiac impaction unit signals.

[0040] S32: Using the box counting fractal dimension method, the fractal dimension of each standard cardiac impactor unit signal is obtained based on the corresponding sub-band signal set of each standard cardiac impactor unit signal.

[0041] Box-counting fractal dimension is a commonly used method for characterizing the geometric features of fractal objects. It describes the detailed hierarchical structure of fractal objects based on their self-similarity and scale invariance. To calculate the box-counting fractal dimension, the fractal object is first overlaid on a grid. Then, the relationship between the number of smallest squares in the overlaid grid and the side length of the smallest square is statistically analyzed. A scatter plot is then created using logarithmic coordinates, and a straight line is fitted; the slope of this line represents the fractal dimension.

[0042] Based on the self-similarity and scale invariance of cardiac impaction signals—meaning that their local features exhibit similar morphology and distribution patterns at different scales—most data is concentrated on the left side of the distribution, while the tail data is relatively small and has relatively large values. Therefore, in this implementation, the extraction device employs the box-counting fractal dimension method to obtain the fractal dimension of each standard cardiac impaction unit signal based on the corresponding sub-band signal set.

[0043] Specifically, the extraction device has a corresponding set of boxes for each of the aforementioned standard cardiac impaction unit signals, and the size of the box is [missing information]. ε can be set to [2, 4, 6…]. For each box size, the extraction device collects the corresponding sub-band signals of each standard cardiac impaction unit signal, divides each sub-band signal into non-overlapping sub-sequences, and places each sub-sequence within its corresponding box. It then calculates the range of sub-sequences contained within each box, i.e., the difference between the maximum and minimum values, denoted as Ni(ε). The average value of Ni(ε) for each box is calculated and denoted as C(ε). The box size ε and the average value C(ε) are expressed on a logarithmic scale. and The system performs linear fitting based on a preset least squares algorithm to obtain the fractal dimension array corresponding to each standard cardiac impactor unit signal. The extraction device then calculates the mean value of each fractal dimension array to obtain the fractal dimension of each standard cardiac impactor unit signal. The least squares algorithm is as follows:

[0044] In the formula, B is the fitting constant. It is a fractal dimension array of length L.

[0045] The extraction device assesses the stability of local signal features by calculating the fractal dimension of each standard cardiac impact map unit signal. When the signal exhibits good self-similarity and scale invariance, the calculated fractal dimension is stable, indicating that the signal's local features possess a definite fractal dimension. Conversely, when the signal has high complexity and poor rhythmicity, the calculated fractal dimension is unstable, indicating that the signal's local features are difficult to describe with a definite fractal dimension, which may affect the feasibility of signal localization.

[0046] S33: Based on the signals of each standard cardiac impactor unit and the preset skewness statistics algorithm, obtain the skewness statistics of each standard cardiac impactor signal.

[0047] The algorithm for the skewness statistic is as follows:

[0048] In the formula, This is a skewness statistic. This refers to the sequence data corresponding to the standard cardiac impaction unit signal. It is the mean of the sequence data. is the standard deviation of the sequence data, and E[] is the expectation function.

[0049] In this embodiment, the extraction device obtains the skewness statistics of each standard cardiac impactor signal based on the signals of each standard cardiac impactor unit and a preset skewness statistics algorithm.

[0050] S34: Based on the fractal dimension, skewness statistics, and preset first fractal dimension threshold and skewness statistics threshold of each standard cardiac impactor unit signal, obtain the body motion detection result of each standard cardiac impactor signal.

[0051] In this embodiment, the extraction device obtains the body motion detection results of each standard cardiac impactor signal based on the fractal dimension, skewness statistics, and preset first fractal dimension threshold and skewness statistics threshold of each standard cardiac impactor unit signal. The body motion detection results include successful body motion detection results and failed body motion detection results.

[0052] Specifically, when the fractal dimension of the standard cardiac impact map unit signal is greater than the first fractal dimension threshold, or the skewness statistic of the standard cardiac impact map unit signal is greater than the skewness statistic threshold, the extraction device obtains a successful motion detection result for the standard cardiac impact map unit signal. When the fractal dimension of the standard cardiac impact map unit signal is less than or equal to the first fractal dimension threshold, and the skewness statistic of the standard cardiac impact map unit signal is less than or equal to the skewness statistic threshold, the extraction device obtains a failed motion detection result for the standard cardiac impact map unit signal.

[0053] The extraction device uses fractal dimension and skewness statistics to jointly discriminate signals from various standard cardiac impaction unit signals, thereby improving the accuracy of body motion detection.

[0054] S4: Based on the body motion detection results, perform localization detection on the signals of the plurality of cardiac impact maps to obtain the localization detection results of the signals of the plurality of cardiac impact maps.

[0055] In the waveform of a cardiac impactogram, the J wave is the most prominent. These wave groups repeatedly recur with the heartbeat rhythm, exhibiting a certain periodicity. However, when the signal complexity is high and the rhythmicity is poor, the wave groups may be distorted, making accurate localization difficult. Therefore, in order to accurately quantify the complexity and rhythmicity of each cardiac impactogram signal, in this embodiment, the extraction device performs localization detection on the several cardiac impactogram unit signals based on the body motion detection results, obtaining the localization detection results of the several cardiac impactogram unit signals.

[0056] Please see Figure 5 , Figure 5 This is a schematic diagram of step S5 in the flow chart of a method for quality grading extraction of cardiac impaction signals provided in an embodiment of this application, including step S41, as follows: S41: Based on the fractal dimension of each standard cardiac impactor unit signal and the preset second fractal dimension threshold, obtain the positioning detection result of each standard cardiac impactor unit signal.

[0057] In this embodiment, the extraction device obtains the positioning detection results of each standard cardiac impaction unit signal based on the fractal dimension of each standard cardiac impaction unit signal and a preset second fractal dimension threshold. The positioning detection results include successful positioning detection results and failed positioning detection results.

[0058] Specifically, when the fractal dimension of the standard cardiac impact map unit signal is greater than the second fractal dimension threshold, the extraction device obtains a successful positioning detection result for the standard cardiac impact map unit signal; when the fractal dimension of the standard cardiac impact map unit signal is less than or equal to the second fractal dimension threshold, the extraction device obtains a successful or unsuccessful positioning detection result for the standard cardiac impact map unit signal.

[0059] Please see Figure 6 , Figure 6 The schematic diagram of step S4 in the process of the quality grading extraction method for cardiac impaction signals provided in another embodiment of this application further includes step S42: when the positioning detection result is positioning detection failure, the positioning detection of each standard cardiac impaction unit signal is re-performed according to the corresponding sub-band signal set of each standard cardiac impaction unit signal, and the positioning detection result of each standard cardiac impaction unit signal is obtained again.

[0060] Please see Figure 7 , Figure 7 This is a schematic diagram of step S4 in the flow chart of the method for quality grading extraction of cardiac impaction signals provided in an embodiment of this application, including steps S421 to S423, as follows: S421: Based on the sub-band signal set corresponding to each of the standard cardiac impactor unit signals and the preset energy calculation algorithm, obtain the energy value of each sub-band signal in the sub-band signal set corresponding to each of the standard cardiac impactor unit signals.

[0061] In this embodiment, the extraction device, based on the sub-band signal set corresponding to each standard cardiac impaction unit signal and a preset energy calculation algorithm, uses the square of the data at different sub-band signal scales as the signal energy, and accumulates them according to different scales to obtain the energy value of each sub-band signal in the sub-band signal set corresponding to each standard cardiac impaction unit signal. The energy calculation algorithm is as follows:

[0062] In the formula, For the first i The energy value of the individual signal For the first i Individual signal scale For the first i The first sub-band signal j Data.

[0063] S422: Obtain the center frequency value of each sub-band signal in the sub-band signal set corresponding to each standard cardiac impact diagram unit signal, and obtain the Hast index of each sub-band signal according to the energy value, center frequency value and preset Hast index calculation algorithm of each sub-band signal.

[0064] The Hurst exponent is a commonly used indicator to describe the autocorrelation of time series. It can be used to determine whether a time series exhibits characteristics such as self-similarity, long memory, or periodicity. For time series with long memory effects, the Hurst exponent value will be high or low, close to 1 or 0; while for time series without long memory effects, the Hurst exponent value will be close to 0.5.

[0065] In this embodiment, the extraction device obtains the center frequency value of each sub-band signal from the corresponding sub-band signal set of each standard cardiac impaction unit signal. Based on the energy value, center frequency value, and preset Hastings index calculation algorithm of each sub-band signal, a least squares method is used for linear fitting to obtain the Hastings index of each sub-band signal. The Hastings index calculation algorithm is as follows:

[0066] In the formula, For the first i The Haast index, which carries a signal, For the first i The center frequency value of each sub-band signal These are constants generated during the fitting process.

[0067] S423: Collect the corresponding sub-band signals of each standard cardiac impact map unit signal, and calculate the weighted average of the Haast index of each sub-band signal according to the corresponding energy value to obtain the Haast index of each standard cardiac impact map unit signal. Based on the Haast index of each standard cardiac impact map unit signal and the preset Haast index threshold, obtain the positioning detection result of each standard cardiac impact map unit signal.

[0068] In this embodiment, the extraction device collects the corresponding sub-band signals of each standard cardiac impact map unit signal, and performs a weighted average of the Haast index of each sub-band signal according to the corresponding energy value to obtain the Haast index of each standard cardiac impact map unit signal. Based on the Haast index of each standard cardiac impact map unit signal and a preset Haast index threshold, the positioning detection result of each standard cardiac impact map unit signal is obtained.

[0069] Specifically, when the Haast index of the standard cardiac impact map unit signal is greater than the Haast index threshold, the extraction device obtains a successful positioning detection result for the standard cardiac impact map unit signal; when the Haast index of the standard cardiac impact map unit signal is less than or equal to the Haast index threshold, the extraction device obtains a successful positioning detection result for the standard cardiac impact map unit signal.

[0070] S5: Based on the positioning detection results, perform waveform integrity detection on the signals of the plurality of cardiac impact diagram units to obtain the waveform integrity detection of the signals of the plurality of cardiac impact diagram units.

[0071] The cardiac impaction unit signal includes corresponding wave group data, which comprises several peaks such as the H wave, I wave, J wave, K wave, L wave, M wave, and N wave. Waves H to L roughly correspond to the systolic phase of the heart, while waves L to N roughly correspond to the diastolic phase. However, due to tachycardia or wave group overlap, the M, N, and H waves may be lost from the wave group data. In such cases, it is impossible to extract more detailed information from these peak-related wave groups.

[0072] Therefore, in this embodiment, the extraction device performs waveform integrity detection on the signals of the plurality of cardiac impactor units based on the positioning detection results, and obtains the waveform integrity detection of the signals of the plurality of cardiac impactor units.

[0073] Please see Figure 8 , Figure 8 This is a schematic diagram of step S5 in the flowchart of a method for quality grading extraction of cardiac impaction signals provided in an embodiment of this application, including steps S51 to S55, as follows: S51: When the positioning detection result is a successful positioning detection result, construct a peak positioning signal set for each of the standard cardiac impact diagram unit signals, and perform arithmetic averaging on several peak positioning signal segments in each of the peak positioning signal sets to obtain the cardiac impact diagram template signal corresponding to each of the standard cardiac impact diagram unit signals.

[0074] In this embodiment, when the positioning detection result is a successful positioning detection result, the device extracts the peak positioning signal set of each of the standard cardiac impact map unit signals.

[0075] Specifically, the extraction device sets an initial peak-finding interval [L1, L2], with a window size of W. The initial values ​​are typically L1=0 and L2=W. Based on the initial peak-finding interval, the maximum value of the initial peak-finding interval for each of the standard cardiac impaction unit signals is obtained, and its index is recorded. Based on the index, the initial peak-finding interval [L1, L2] is updated as follows: ,

[0076] In the formula, max() is the maximum value extraction function, and min() is the minimum value extraction function. The above steps are repeated until the entire standard cardiac impaction signal is traversed, and the peak index set corresponding to each standard cardiac impaction signal is obtained. ,in Round down to the nearest integer. t Let be the length of the standard cardiac impact map unit signal. For each standard cardiac impact map unit signal and its corresponding peak index set, taking 0.4*T of data forward and 0.6*T of data backward from the above index, a peak location signal set for each standard cardiac impact map unit signal is constructed, as shown below:

[0077] In the formula, For peak positioning signal set, For the first m One peak positioning signal segment.

[0078] The extraction device performs arithmetic averaging on several peak positioning signal segments from each of the aforementioned peak positioning signal sets to obtain the cardiac impact map template signal corresponding to each of the aforementioned standard cardiac impact map unit signals. Even when the forward-backward cross-correlation signal and Euclidean distance signal positioning points differ, it can construct the peak positioning signal set for each of the aforementioned standard cardiac impact map unit signals by statistically analyzing the differences between each positioning point, thereby improving the accuracy of the signal positioning results and effectively obtaining the cardiac impact map template signal corresponding to each of the aforementioned standard cardiac impact map unit signals.

[0079] S52: Based on each of the standard cardiac impactor unit signals, the corresponding cardiac impactor template signal, and the preset correlation function sequence calculation algorithm, obtain the correlation function sequence of each of the standard cardiac impactor unit signals.

[0080] The algorithm for calculating the relevant function sequence is as follows:

[0081] In the formula, For a sequence of related functions, The template length is the template length for the cardiac impact pattern template signal. For cardiac impact pattern template signal, For standard cardiac impaction unit signals, For the first A standard cardiac impact diagram unit signal. The time interval between the standard cardiac impaction unit signal and the corresponding cardiac impaction template signal.

[0082] In this embodiment, the extraction device obtains the correlation function sequence of each standard cardiac impactor unit signal based on the corresponding cardiac impactor template signal and a preset correlation function sequence calculation algorithm.

[0083] S53: Based on each of the standard cardiac impactor unit signals, the corresponding cardiac impactor template signal, and the preset Euclidean distance sequence calculation algorithm, obtain the Euclidean distance sequence of each of the cardiac impactor unit signals.

[0084] The Euclidean distance sequence calculation algorithm is as follows:

[0085] In the formula, It is a Euclidean distance sequence.

[0086] In this embodiment, the extraction device obtains the Euclidean distance sequence of each of the standard cardiac impactor unit signals, the corresponding cardiac impactor template signal, and a preset Euclidean distance sequence calculation algorithm.

[0087] S54: Based on the correlation function sequence and Euclidean distance sequence of each standard cardiac impact diagram unit signal, perform peak localization on each standard cardiac impact diagram unit signal to obtain the peak index sequence of each standard cardiac impact diagram unit signal.

[0088] In this embodiment, the extraction device performs peak localization on each standard cardiac impact map unit signal based on the correlation function sequence and Euclidean distance sequence of each standard cardiac impact map unit signal, thereby obtaining the peak index sequence of each standard cardiac impact map unit signal.

[0089] Specifically, the extraction device compares the corresponding position elements of the correlation function sequence and the Euclidean distance sequence of the same standard cardiac impaction unit signal one by one. If they are the same, they are recorded as peak indices; if they are different, the average of the two is taken as the peak index, thus obtaining the peak index sequence of each standard cardiac impaction unit signal, as shown below:

[0090] In the formula, For peak index sequence, For the first m Peak index.

[0091] S55: Based on the peak index sequence, perform local maximum count detection on each of the standard cardiac impact diagram unit signals to obtain the number of local maxima of each of the standard cardiac impact diagram unit signals. Based on the number of local maxima of each of the standard cardiac impact diagram unit signals and a preset local maximum count threshold, obtain the waveform integrity detection result of each of the standard cardiac impact diagram unit signals.

[0092] In this embodiment, the extraction device performs local maxima count detection on each of the standard cardiac impact map unit signals according to the peak index sequence, thereby obtaining the number of local maxima of each of the standard cardiac impact map unit signals.

[0093] Specifically, the extraction device obtains the position of each peak index in the corresponding standard impact map unit signal according to the peak index sequence, obtains the sampling point corresponding to each peak index, and traverses backward from the sampling point corresponding to each peak index according to a preset step, to obtain the signal segment corresponding to each peak index and the amplitude of each sampling point in the signal segment, as shown below: , ], ]; Where count is the number of local maxima. a For the first The amplitude of the sampling point corresponding to the amplitude of each peak index. For the first The amplitude of the sampling point corresponding to the amplitude of each peak index. For the first The amplitude of the sampling point corresponding to the amplitude of each peak index. [ ] represents the amplitude of the sampling point of the standard cardiac impact diagram unit signal.

[0094] Based on the signal segment corresponding to the same peak index and the amplitude of each sampling point within the signal segment, the number of local maxima for each peak index corresponding to the signal segment is obtained. Specifically, let count = 0, where count is the number of local maxima. a > b > c or a < b < c hour, Each step backward by 1 is performed on the standard cardiac impact diagram unit signal. b > a and b > c At that time, count = count + .

[0095] The extraction device obtains the waveform integrity detection result of each standard cardiac impact diagram unit signal based on the number of local maxima of each standard cardiac impact diagram unit signal and a preset local maxima number threshold. Specifically, when the number of local maxima of the standard cardiac impact diagram unit signal is greater than the local maxima number threshold, the extraction device obtains a successful waveform integrity detection result for the standard cardiac impact diagram unit signal; when the number of local maxima of the standard cardiac impact diagram unit signal is less than or equal to the local maxima number threshold, the extraction device obtains a failed waveform integrity detection result for the standard cardiac impact diagram unit signal.

[0096] S6: Based on the empty bed detection results, body motion detection results, positioning detection results, and waveform integrity detection results of the several cardiac impaction unit signals, obtain the quality assessment results of the several cardiac impaction unit signals, and extract several target signals from the several cardiac impaction unit signals based on the quality assessment results.

[0097] In this embodiment, the extraction device obtains the quality assessment results of the several cardiac impaction unit signals based on the empty bed detection results, body motion detection results, positioning detection results, and waveform integrity detection results of the several cardiac impaction unit signals.

[0098] Specifically, when the cardiac impact map unit signal only includes the result of empty bed detection failure, the extraction device sets the quality assessment result of the cardiac impact map unit signal to level D.

[0099] When the cardiac impact map unit signal only includes successful empty bed detection results and failed body motion detection results, the quality assessment result of the cardiac impact map unit signal is set to level D.

[0100] When the cardiac impact map unit signal only includes successful empty bed detection results, successful body movement detection results, and failed positioning detection results, the quality assessment result of the cardiac impact map unit signal is set to level C.

[0101] If the cardiac impact graph unit signal only includes the results of successful empty bed detection, successful body motion detection, successful positioning detection, and failed waveform integrity detection, the quality assessment result of the cardiac impact graph unit signal is set to level B.

[0102] When the cardiac impact map unit signal only includes the successful results of empty bed detection, body motion detection, positioning detection, and waveform integrity detection, the quality assessment result of the cardiac impact map unit signal is set to level A.

[0103] Based on the quality assessment results, the extraction device can extract several target signals corresponding to the corresponding levels from the several cardiac impaction unit signals according to the actual application scenario.

[0104] Please refer to Figure 9 , Figure 9 This is a schematic diagram of a quality grading extraction device for cardiac impaction signals according to an embodiment of this application. The device can be implemented entirely or partially through software, hardware, or a combination of both. The device 9 includes: The signal acquisition module 91 is used to acquire the cardiac impact map signal to be detected, and divide the cardiac impact map signal into several cardiac impact map unit signals according to the preset signal length. Empty bed detection module 92 is used to perform empty bed detection on the signals of the plurality of cardiac impaction units and obtain the empty bed detection results of the signals of the plurality of cardiac impaction units; The body movement detection module 93 is used to perform body movement detection on the signals of the plurality of cardiac impact maps based on the empty bed detection results, and obtain the body movement detection results of the signals of the plurality of cardiac impact maps. The positioning detection module 94 is used to perform positioning detection on the signals of the plurality of cardiac impactor units based on the body motion detection results, and obtain the positioning detection results of the signals of the plurality of cardiac impactor units; The waveform integrity detection module 95 is used to perform waveform integrity detection on the plurality of cardiac impactor unit signals based on the positioning detection results, and obtain the waveform integrity detection of the plurality of cardiac impactor unit signals; The signal extraction module 96 is used to obtain the quality assessment results of the several cardiac impaction unit signals based on the empty bed detection results, body motion detection results, positioning detection results and waveform integrity detection results of the several cardiac impaction unit signals, and to extract several target signals from the several cardiac impaction unit signals based on the quality assessment results.

[0105] In this embodiment, a signal acquisition module is used to acquire the cardiac impact map signal to be detected, and divides the cardiac impact map signal into several cardiac impact map unit signals according to a preset signal length; an empty bed detection module is used to perform empty bed detection on the several cardiac impact map unit signals to obtain empty bed detection results; a body movement detection module is used to perform body movement detection on the several cardiac impact map unit signals based on the empty bed detection results to obtain body movement detection results; and a positioning detection module is used to perform positioning detection on the several cardiac impact map unit signals based on the body movement detection results. The system performs location detection on several cardiac impact map unit signals to obtain location detection results. A waveform integrity detection module then performs waveform integrity detection on these signals based on the location detection results to obtain waveform integrity results. A signal extraction module then obtains a quality assessment result for each cardiac impact map unit signal based on the empty bed detection result, body motion detection result, location detection result, and waveform integrity detection result. Based on the quality assessment result, several target signals are extracted from these cardiac impact map unit signals. By performing empty bed detection, body motion detection, location detection, and waveform integrity detection on several cardiac impact map unit signals to be tested, the system fully considers the objective factors affecting the quality of the cardiac impact map unit signals, enabling the analysis of multi-dimensional features of the signals and improving the accuracy of extracting cardiac impact map unit signals in complex application scenarios.

[0106] Please refer to Figure 10 , Figure 10 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. The computer device 10 includes: a processor 101, a memory 102, and a computer program 103 stored in the memory 102 and executable on the processor 101. The computer device can store multiple instructions, which are adapted to be loaded and executed by the processor 101. Figures 1 to 8 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figures 1 to 8 The specific details of the illustrated embodiments will not be elaborated here.

[0107] The processor 101 may include one or more processing cores. The processor 101 connects to various parts of the server using various interfaces and lines. It executes instructions, programs, code sets, or instruction sets stored in the memory 102, and retrieves data from the memory 102 to perform various functions and process data from the cardiac impact imaging signal quality grading extraction device 9. Optionally, the processor 101 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 101 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 101 and may be implemented as a separate chip.

[0108] The memory 102 may include random access memory (RAM) or read-only memory. Optionally, the memory 102 may include a non-transitory computer-readable storage medium. The memory 102 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 102 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 102 may also be at least one storage device located remotely from the aforementioned processor 101.

[0109] This application embodiment also provides a storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figures 1 to 8 For details of the method steps described in the embodiment, please refer to [link / reference]. Figures 1 to 8 The specific details of the embodiments will not be elaborated here.

[0110] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0111] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the algorithm. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0113] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms.

[0117] This invention is not limited to the above-described embodiments. If any modifications or variations to this invention do not depart from the spirit and scope of this invention, and if such modifications and variations fall within the scope of the claims and equivalent technologies of this invention, then this invention also intends to include such modifications and variations.

Claims

1. A method for quality grading extraction of cardiac impaction signals, characterized in that, Includes the following steps: The cardiac impact image signal to be detected is obtained, and the cardiac impact image signal is divided according to a preset signal length to obtain several cardiac impact image unit signals. Empty bed detection is performed on the signals of the plurality of cardiac impaction units to obtain the empty bed detection results of the signals of the plurality of cardiac impaction units; Based on the empty bed detection results, body motion detection is performed on the signals of the plurality of cardiac impact maps to obtain the body motion detection results of the signals of the plurality of cardiac impact maps. Based on the body motion detection results, the location detection of the plurality of cardiac impaction unit signals is performed to obtain the location detection results of the plurality of cardiac impaction unit signals; If the positioning detection result is a positioning detection failure, the positioning detection of each standard cardiac impact map unit signal is re-performed based on the corresponding sub-band signal set of each standard cardiac impact map unit signal, and the positioning detection result of each standard cardiac impact map unit signal is obtained again, as follows: Based on the sub-band signal set corresponding to each of the standard cardiac impaction unit signals and a preset energy calculation algorithm, the energy value of each sub-band signal in the corresponding sub-band signal set of each of the standard cardiac impaction unit signals is obtained, wherein the energy calculation algorithm is as follows: In the formula, For the first i The energy value of the individual signal For the first i Individual signal scale For the first i The first sub-band signal j One data point; Obtain the center frequency value of each sub-band signal from the corresponding sub-band signal set of each standard cardiac impact diagram unit signal. Based on the energy value, center frequency value, and a preset Hastach index calculation algorithm, obtain the Hastach index of each sub-band signal. The Hastach index calculation algorithm is as follows: In the formula, For the first i The Haast index, which carries a signal, For the first i The center frequency value of each sub-band signal These are constants generated during the fitting process; The corresponding sub-band signals of each standard cardiac impact map unit signal are collected, and the Haast index of each sub-band signal is weighted and averaged according to the corresponding energy value to obtain the Haast index of each standard cardiac impact map unit signal. Based on the Haast index of each standard cardiac impact map unit signal and the preset Haast index threshold, the positioning detection result of each standard cardiac impact map unit signal is obtained. Based on the positioning detection results, waveform integrity detection is performed on the signals of the plurality of cardiac impactor units to obtain the waveform integrity detection of the signals of the plurality of cardiac impactor units; Based on the empty bed detection results, body motion detection results, positioning detection results, and waveform integrity detection results of the several cardiac impaction unit signals, the quality assessment results of the several cardiac impaction unit signals are obtained, and based on the quality assessment results, several target signals are extracted from the several cardiac impaction unit signals.

2. The method for quality grading and extraction of cardiac impaction signals according to claim 1, characterized in that, Before performing empty bed detection on the signals of the plurality of cardiac impact mapping units to obtain the empty bed detection results of the signals of the plurality of cardiac impact mapping units, the method further includes the following steps: The signals of the several cardiac impactor units are standardized to obtain several standard cardiac impactor unit signals.

3. The method for quality grading and extraction of cardiac impaction signals according to claim 2, characterized in that: The standard cardiac impaction unit signal includes several sampling points; The step of performing empty bed detection on the signals of the plurality of cardiac impact mapping units to obtain the empty bed detection results of the signals of the plurality of cardiac impact mapping units includes the following steps: The amplitude of each sampling point in each of the standard cardiac impact diagram unit signals is obtained. According to the preset amplitude threshold, each sampling point of each of the standard cardiac impact diagram unit signals is marked to obtain the marking data of each sampling point in each of the standard cardiac impact diagram unit signals. Based on the labeled data of all sampling points of the same standard cardiac impaction unit signal, the empty bed signal ratio of each standard cardiac impaction unit signal is calculated. According to the empty bed signal ratio of each standard cardiac impaction unit signal and the preset empty bed signal ratio threshold, the empty bed detection result of each standard cardiac impaction unit signal is obtained. The empty bed detection result includes the empty bed detection success result and the empty bed detection failure result.

4. The method for quality grading and extraction of cardiac impaction signals according to claim 3, characterized in that, The step of performing body motion detection on the signals of the plurality of cardiac impact maps based on the empty bed detection results to obtain the body motion detection results of the plurality of cardiac impact map signals includes the following steps: When the empty bed detection result is a successful empty bed detection result, wavelet decomposition is performed on each of the standard cardiac impact map unit signals to obtain the corresponding sub-band signal set of each of the standard cardiac impact map unit signals, wherein the sub-band signal set includes several sub-band signals; The fractal dimension of each standard cardiac impactor unit signal is obtained by using the box counting fractal dimension method based on the corresponding sub-band signal set of each standard cardiac impactor unit signal. Based on the signals of each standard cardiac impactor unit and a preset skewness statistics algorithm, the skewness statistics of each standard cardiac impactor signal are obtained, wherein the skewness statistics algorithm is as follows: In the formula, This is a skewness statistic. This refers to the sequence data corresponding to the standard cardiac impaction unit signal. It is the mean of the sequence data. E[] is the standard deviation of the sequence data, and E[] is the expectation function; Based on the fractal dimension, skewness statistics, and preset first fractal dimension threshold and skewness statistics threshold of each standard cardiac impactor unit signal, the body motion detection result of each standard cardiac impactor signal is obtained, wherein the body motion detection result includes a successful body motion detection result and a failed body motion detection result.

5. The method for quality grading and extraction of cardiac impaction signals according to claim 4, characterized in that, The step of performing localization detection on the signals of the plurality of cardiac impact maps based on the body motion detection results to obtain the localization detection results of the plurality of cardiac impact map signals includes the following steps: Based on the fractal dimension of each standard cardiac impactor unit signal and a preset second fractal dimension threshold, the positioning detection result of each standard cardiac impactor unit signal is obtained, wherein the positioning detection result includes a successful positioning detection result and a failed positioning detection result.

6. The method for quality grading and extraction of cardiac impaction signals according to claim 5, characterized in that, The step of performing waveform integrity detection on the plurality of cardiac impaction unit signals based on the positioning detection results to obtain the waveform integrity detection of the plurality of cardiac impaction unit signals includes the following steps: When the positioning detection result is a successful positioning detection result, a peak positioning signal set of each of the standard cardiac impact diagram unit signals is constructed. Based on several peak positioning signal segments in each of the peak positioning signal sets, an arithmetic average is performed to obtain the cardiac impact diagram template signal corresponding to each of the standard cardiac impact diagram unit signals. Based on the standard cardiac impaction imaging unit signals, the corresponding cardiac impaction imaging template signals, and a preset correlation function sequence calculation algorithm, the correlation function sequence of each standard cardiac impaction imaging unit signal is obtained, wherein the correlation function sequence calculation algorithm is as follows: In the formula, For a sequence of related functions, The template length is the template length for the cardiac impact pattern template signal. For cardiac impact pattern template signal, For standard cardiac impaction unit signals, For the first A standard cardiac impact diagram unit signal. The time interval between the standard cardiac impaction unit signal and the corresponding cardiac impaction template signal; Based on the standard cardiac impactogram unit signals, the corresponding cardiac impactogram template signals, and a preset Euclidean distance sequence calculation algorithm, the Euclidean distance sequence of each cardiac impactogram unit signal is obtained, wherein the Euclidean distance sequence calculation algorithm is as follows: In the formula, It is a Euclidean distance sequence; Based on the correlation function sequence and Euclidean distance sequence of each standard cardiac impact map unit signal, peak localization is performed on each standard cardiac impact map unit signal to obtain the peak index sequence of each standard cardiac impact map unit signal. Based on the peak index sequence, the number of local maxima of each standard cardiac impact map unit signal is detected to obtain the number of local maxima of each standard cardiac impact map unit signal. Based on the number of local maxima of each standard cardiac impact map unit signal and a preset threshold for the number of local maxima, the waveform integrity detection result of each standard cardiac impact map unit signal is obtained.

7. A quality grading and extraction device for cardiac impaction signals, characterized in that, include: The signal acquisition module is used to acquire the cardiac impact map signal to be detected, and divide the cardiac impact map signal into several cardiac impact map unit signals according to the preset signal length. An empty bed detection module is used to perform empty bed detection on the signals of the plurality of cardiac impaction units and obtain the empty bed detection results of the signals of the plurality of cardiac impaction units; The body movement detection module is used to perform body movement detection on the signals of the plurality of cardiac impact maps based on the empty bed detection results, and to obtain the body movement detection results of the signals of the plurality of cardiac impact maps. The positioning detection module is used to perform positioning detection on the signals of the plurality of cardiac impactor units based on the body motion detection results, and obtain the positioning detection results of the signals of the plurality of cardiac impactor units; If the positioning detection result is a positioning detection failure, the positioning detection of each standard cardiac impact map unit signal is re-performed based on the corresponding sub-band signal set of each standard cardiac impact map unit signal, and the positioning detection result of each standard cardiac impact map unit signal is obtained again, as follows: Based on the sub-band signal set corresponding to each of the standard cardiac impaction unit signals and a preset energy calculation algorithm, the energy value of each sub-band signal in the corresponding sub-band signal set of each of the standard cardiac impaction unit signals is obtained, wherein the energy calculation algorithm is as follows: In the formula, For the first i The energy value of the individual signal For the first i Individual signal scale For the first i The first sub-band signal j One data point; Obtain the center frequency value of each sub-band signal from the corresponding sub-band signal set of each standard cardiac impact diagram unit signal. Based on the energy value, center frequency value, and a preset Hastach index calculation algorithm, obtain the Hastach index of each sub-band signal. The Hastach index calculation algorithm is as follows: In the formula, For the first i The Haast index, which carries a signal, For the first i The center frequency value of each sub-band signal These are constants generated during the fitting process; The corresponding sub-band signals of each standard cardiac impact map unit signal are collected, and the Haast index of each sub-band signal is weighted and averaged according to the corresponding energy value to obtain the Haast index of each standard cardiac impact map unit signal. Based on the Haast index of each standard cardiac impact map unit signal and the preset Haast index threshold, the positioning detection result of each standard cardiac impact map unit signal is obtained. The waveform integrity detection module is used to perform waveform integrity detection on the signals of the plurality of cardiac impactor units based on the positioning detection results, and obtain the waveform integrity detection of the signals of the plurality of cardiac impactor units. The signal extraction module is used to obtain the quality assessment results of the several cardiac impaction unit signals based on the empty bed detection results, body motion detection results, positioning detection results and waveform integrity detection results of the several cardiac impaction unit signals, and to extract several target signals from the several cardiac impaction unit signals based on the quality assessment results.

8. A computer device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the quality grading extraction method for cardiac impaction signals as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the quality grading extraction method for cardiac impaction signals as described in any one of claims 1 to 6.

Images