Edge device-based electrocardio data monitoring method, device, equipment and medium

Abstract

This invention provides a method, apparatus, device, and medium for monitoring electrocardiogram (ECG) data based on edge devices. The method includes: acquiring ECG data collected by an ECG device within a time unit for a target population; calculating the QTc sequence within the time unit based on the ECG data; inputting the QTc sequence and a preset standard QTc threshold into a preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold; performing a weighted average of the deviations corresponding to multiple time units to obtain a comprehensive deviation; adjusting the standard QTc threshold using the comprehensive deviation to obtain a specific QTc threshold corresponding to the target population; and distributing the specific QTc threshold to the edge device corresponding to the target population for ECG data monitoring. This invention improves the accuracy of ECG data monitoring.

Description

Technical Field

[0001] This invention relates to the field of medical data monitoring technology, and in particular to a method, apparatus, device, and medium for monitoring electrocardiogram data based on edge devices. Background Technology

[0002] Traditional medical devices for ECG data acquisition and monitoring are primarily used in hospitals. For example, when a user feels unwell and needs an ECG measurement, the main solution is to go to the hospital for testing. Therefore, data acquisition cannot be timely or effective. ECG data requires continuity and cross-period comparison of multiple data samples taken within the same time period, which is why Holter monitors exist. However, Holter monitors are limited by their inconvenience in wearing and the need to return to the hospital to schedule a doctor's appointment for data analysis, making real-time performance difficult to achieve.

[0003] With the development of smart wearable device technologies, devices such as smartwatches have emerged that can collect ECG-related data in real time. However, these devices cannot perform monitoring and analysis of the data. For example, monitoring ECG data from edge devices with long QT cycles based on a standard QTc threshold still requires doctors to analyze the data in conjunction with the user's individual characteristics due to individual differences. This still causes inconvenience for users' ECG data monitoring. On the other hand, if monitoring and analysis are based on a uniform standard QTc threshold, ignoring individual differences, the accuracy of ECG data monitoring from edge devices will be low.

[0004] Therefore, how to improve the accuracy of ECG data monitoring while satisfying the comprehensiveness of ECG data monitoring has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The purpose of this invention is to provide a method, apparatus, device, and medium for monitoring electrocardiogram data based on edge devices, in order to solve the aforementioned technical problems in the prior art.

[0006] On the one hand, in order to achieve the above objectives, the present invention provides a method for monitoring electrocardiogram data based on edge devices.

[0007] The method for monitoring ECG data based on edge devices includes: acquiring ECG data collected by an ECG device within a time unit for a target group; calculating the QTc sequence within the time unit based on the ECG data; inputting the QTc sequence and a preset standard QTc threshold into a preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold; performing a weighted average of the deviations corresponding to multiple time units to obtain a comprehensive deviation; adjusting the standard QTc threshold using the comprehensive deviation to obtain a specific QTc threshold corresponding to the target group; and distributing the specific QTc threshold to the edge device corresponding to the target group for ECG data monitoring.

[0008] Further, the step of calculating the QTc sequence within the time unit based on the electrocardiogram data includes: calculating the QT sequence {Q...} based on the electrocardiogram data. n T n} and RR sequence {R n-1 R n}, where n is a natural number, Q n T n R is the time interval between the nth Q wave and the nth T wave within the time unit. n-1 R n The time interval between the (n-1)th R wave and the nth R wave; and according to the QT sequence {Q n T n} and the RR sequence {R n-1 R n} Calculate the QTc sequence {QTc} n}

[0009] Furthermore, the following formula is used based on the QT sequence {Q n T n} and the RR sequence {R n-1 R n} Calculate the QTc sequence {QTc} n}:

[0010]

[0011] Furthermore, the step of weighted averaging the deviations corresponding to multiple time units to obtain the comprehensive deviation includes: determining the weighting weight corresponding to the time unit according to the time period to which the time unit belongs; and performing a weighted average based on the deviation and weighting weight corresponding to each time unit to obtain the comprehensive deviation.

[0012] Furthermore, the step of sending the specific QTc threshold to the edge end of the target group for ECG data monitoring includes: acquiring ECG data to be monitored collected by the ECG device in real time; calculating the real-time QTc value based on the ECG data to be monitored; and recording the trend of the real-time QTc value deviating from the specific QTc threshold within a first preset time period.

[0013] Further, the step of sending the specific QTc threshold to the edge of the target group for ECG data monitoring includes: acquiring the ECG data to be monitored collected by the ECG device within the time unit; calculating the QTc sequence to be monitored within the time unit based on the ECG data to be monitored; inputting the QTc sequence to be monitored and the specific QTc threshold into the neural network model for calculation to obtain the deviation of the QTc sequence to be monitored from the specific QTc threshold; and recording the trend of the QTc sequence to be monitored deviating from the specific QTc threshold within a second preset time period.

[0014] Furthermore, the target group includes individuals who meet any one or more of the following conditions: the region to which the individual belongs, their physical condition, their age, and the month in which their electrocardiogram data was collected.

[0015] On the other hand, in order to achieve the above objectives, the present invention provides a monitoring device for electrocardiogram data based on edge devices.

[0016] The edge device-based ECG data monitoring device includes: an acquisition module for acquiring ECG data collected by an ECG device within a time unit for a target group; a calculation module for calculating the QTc sequence within the time unit based on the ECG data; a first processing module for inputting the QTc sequence and a preset standard QTc threshold into a preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold; a second processing module for performing a weighted average of the deviations corresponding to multiple time units to obtain a comprehensive deviation; an adjustment module for adjusting the standard QTc threshold using the comprehensive deviation to obtain a specific QTc threshold corresponding to the target group; and a monitoring module for distributing the specific QTc threshold to the edge device corresponding to the target group for ECG data monitoring.

[0017] To achieve the above objectives, the present invention also provides a computer device, including a memory, a processor, 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 above method.

[0018] To achieve the above objectives, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method.

[0019] The present invention provides a method, apparatus, device, and medium for monitoring ECG data with long QT cycles based on edge devices. First, for a target group, ECG data collected by an ECG device within multiple time units are acquired. Then, for each time unit, its QTc sequence is calculated using the ECG data. The QTc sequence and a preset standard QTc threshold are input into a preset neural network model for calculation, yielding the deviation of the QTc sequence from the standard QTc threshold. Next, the deviations corresponding to each time unit are weighted and averaged to obtain the comprehensive deviation corresponding to the target group. The standard QTc threshold is adjusted based on the comprehensive deviation to obtain a specific QTc threshold for the target group. This specific QTc threshold is suitable for monitoring ECG data of individuals within the target group. Therefore, this specific QTc threshold is distributed to the edge device corresponding to the target group for ECG data monitoring. On the one hand, long QT cycle ECG data monitoring can be achieved at the edge device based on the QTc threshold, which is convenient for users. On the other hand, the QTc threshold is a specific QTc threshold adjusted based on the comprehensive deviation calculated from the actual ECG data of the target group, thus improving the accuracy of ECG data monitoring. Attached Figure Description

[0020] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0021] Figure 1 A flowchart of a method for monitoring electrocardiogram data based on edge devices provided in Embodiment 1 of the present invention;

[0022] Figure 2 and Figure 3 These are all schematic diagrams of the neural network structure provided in the embodiments of the present invention;

[0023] Figure 4 This is a flowchart of a method for monitoring electrocardiogram data based on edge devices provided in Embodiment 2 of the present invention;

[0024] Figure 5 This is a flowchart of the ECG data monitoring method based on edge devices provided in Embodiment 3 of the present invention;

[0025] Figure 6 This is a block diagram of a monitoring device for ECG data based on an edge device provided in Embodiment 4 of the present invention;

[0026] Figure 7 This is a hardware structure diagram of a computer device provided in Embodiment 5 of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0028] Example 1

[0029] Embodiment 1 of the present invention provides a method for monitoring electrocardiogram (ECG) data based on edge devices. This method improves the accuracy of ECG data monitoring while satisfying the requirement for comprehensive monitoring coverage. Specifically, Figure 1 The flowchart is as follows: This is a method for monitoring ECG data based on edge devices provided in Embodiment 1 of the present invention. Figure 1 As shown, the ECG data monitoring method based on edge devices provided in this embodiment includes the following steps S101 to S106.

[0030] Step S101: For the target group, acquire the electrocardiogram data collected by the ECG device within the time unit.

[0031] Optionally, the target group refers to a population that meets one or more conditions that affect electrocardiogram (ECG) data. Specifically, the target group in this application includes populations that meet any one or more of the following conditions: the population's geographical location, the population's physical condition, the population's age, and the month in which the ECG data was collected. For example, the target group could be a population whose geographical location is entirely in North China, or a population with hypertension, or a population aged 70 or older, or a population whose ECG data was collected in December and January.

[0032] Optionally, in step S101, electrocardiogram (ECG) data is acquired using an ECG device. Specifically, the ECG device includes, but is not limited to, single-lead, dual-lead, 4-lead, or 12-lead devices. The acquired ECG data includes QRS-related data, where QRS is the waveform voltage data of an ECG data cycle, consisting of the voltage data of the Q wave, T wave, R wave, and S wave, along with the corresponding acquisition time.

[0033] Optionally, the time unit can be 3 minutes, 5 minutes, or 1 minute, etc. Specifically, ECG data with a duration longer than the time unit can be collected, and then the noise time before and after can be filtered out to obtain the ECG data within the time unit.

[0034] Step S102: Calculate the QTc sequence within the time unit based on the electrocardiogram data.

[0035] Optionally, step S102 specifically includes: calculating the QT sequence {Q...} based on the electrocardiogram data. n T n} and RR sequence {R n-1 R n}, where n is a natural number, Q n T n R is the time interval between the nth Q wave and the nth T wave within a time unit. n-1 R n The time interval between the (n-1)th R wave and the nth R wave; and according to the QT sequence {Q n T n} and RR sequence {R n-1 R n} Calculate the QTc sequence {QTc} n}

[0036] Optionally, the collected electrocardiogram data includes: Q wave sequence {(Q n , t n )}、T-wave sequence {(T n , t n )} and R-wave sequence {(R n , t n )}, where t n For the data acquisition time, use the formula Q. n T n =T n -Q n R n-1 R n =R n -R n-1 The QT sequence {Q} can be calculated. n T n} and RR sequence {R n-1 R n Optionally, R0 can be a predetermined value or the last R value of the previous time unit. For example:

[0037] Q1 value: (0.23, 10), R1 value: (0.28, 90), T1 value: (0.95, 40)

[0038] Q² value: (1.30, 18), R² value: (1.39, 100)

[0039] R1R2=R2-R1=1.39-0.28=1.11, Q1T1 is T1-Q1=0.95-0.23=0.72.

[0040] Further, optionally, the following formula is used based on the QT sequence {Q n T n} and RR sequence {Rn-1 R n} Calculate the QTc sequence {QTc} n}:

[0041]

[0042] The discrete sequence data QTc sequence {QTc} can be calculated using the above formula. n}

[0043] Step S103: Input the QTc sequence and the preset standard QTc threshold into the preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold.

[0044] The neural network model can be pre-trained to perform operations on discrete sequence data and calculate the deviation of the discrete sequence data from a standard threshold. Thus, by inputting each discrete data in the QTc sequence and the preset standard QTc threshold into the neural network model, the deviation of the QTc sequence from the standard QTc threshold corresponding to a time unit can be obtained.

[0045] Optionally, Figure 2 and Figure 3 All of these are schematic diagrams of the neural network structure provided in the embodiments of the present invention, such as... Figure 2 As shown, a neural network includes an input layer, a convolutional layer, a residual block layer, a fully connected layer, and an output layer.

[0046] Specifically, such as Figure 3 As shown, the input layer receives the QTc sequence {QTc} n That is, X = QTc n Time series.

[0047] Convolutional layers include Conv, BN, and ReLU. Conv is a one-dimensional convolutional layer (Y = WX + B). BN (Batch Normalization) layers accelerate network convergence, control overfitting, and effectively address the vanishing and exploding gradient problems by normalizing the data. The ReLU function is a type of activation function. It is essentially a piecewise linear function that sets all negative values ​​to 0 while leaving positive values ​​unchanged. This operation is called one-sided inhibition. In other words, when the input is negative, it outputs 0, meaning the neuron is not activated. This means that only a subset of neurons are activated at any given time, making the network sparse and computationally efficient. It is precisely this one-sided inhibition that gives neurons in a neural network their sparse activation.

[0048] The Residual Block (ResBlk) layer includes Conv, BN, ReLU, Dropout, Conv again, and MaxPooling. Conv, BN, and ReLU are described above and will not be repeated here. During forward propagation, the activation value of a neuron is deactivated with a certain probability p. This improves the model's generalization ability because it doesn't rely too heavily on local features. Dropout effectively mitigates overfitting and achieves a degree of regularization. p can be distributed using the Bernoulli function. The MaxPooling layer uses the maximum value from the MaxPooling window data instead of the window data itself.

[0049] Fully connected layers include Dense and Softmax. The core operation of a fully connected layer is matrix-vector multiplication y = Wx, which is essentially a linear transformation from one feature space to another. Therefore, the purpose of the Dense layer is to extract the correlations between the previously extracted features through a non-linear transformation, and finally map them onto the output space. Softmax is a normalized exponential function, a generalization of the binary classification function sigmoid to multi-class classification. Its purpose is to represent the results of multi-class classification in probabilities. Softmax converts the prediction results from negative infinity to positive infinity into probabilities in the following two steps: 1) the predicted probability is non-negative; 2) the sum of the probabilities of all prediction results equals 1.

[0050] The output layer outputs y = σ, which is the trend value or deviation from the standard QTc threshold.

[0051] Step S104: Calculate the weighted average of the deviations corresponding to multiple time units to obtain the comprehensive deviation.

[0052] Specifically, ECG data can be collected within one time period (e.g., 9:00 AM - 11:00 AM) or multiple time periods (e.g., 9:00 AM - 11:00 AM, 5:00 PM - 8:00 PM). This data is then processed through steps S101 to S103 to obtain multiple deviations. A weighted average of these deviations yields the comprehensive deviation. For example, the weighted average might use a weight of 0.4 for 9:00 AM - 11:00 AM, 0.5 for 5:00 PM - 8:00 PM, and 0.1 for the remaining time periods.

[0053] Optionally, step S104 specifically includes: determining the weighting weight corresponding to the time unit based on the time period to which the time unit belongs; and performing a weighted average based on the deviation and weighting weight of each time unit to obtain the comprehensive deviation. Specifically, different weighting weights can be set for different time periods. When the collected time units belong to the same time period, the deviations of each time unit can be directly averaged; when the collected time units belong to different time periods, the deviations belonging to the same time period can be averaged first, and then the averages can be summed according to the determined weighting weights to obtain the comprehensive deviation. For electrocardiogram data, there will be corresponding changes in different time periods. By weighting and summing the deviations determined in different time periods, the influence of the time period can be reduced, and the accuracy of the comprehensive deviation calculation can be improved while covering the data collection range.

[0054] Step S105: Adjust the standard QTc threshold using the comprehensive deviation to obtain the specific QTc threshold corresponding to the target group.

[0055] After obtaining the comprehensive deviation for a target population based on actual collected data, this comprehensive deviation reflects the QTc threshold corresponding to the actual ECG data of that target population. The standard QTc threshold is then adjusted based on this comprehensive deviation, making the adjusted standard QTc threshold, i.e., the specific QTc threshold corresponding to the target population, more suitable for that population. For example, when the comprehensive deviation indicates that the QTc sequence is higher than the standard QTc threshold, the standard QTc threshold is increased; when the comprehensive deviation indicates that the QTc sequence is lower than the standard QTc threshold, the standard QTc threshold is decreased.

[0056] Step S106: Send a specific QTc threshold to the edge device corresponding to the target group for ECG data monitoring.

[0057] Optionally, an edge computing terminal, or edge terminal, is set up relative to the cloud. The edge terminal communicates and connects with the ECG device and the cloud. When the cloud calculates the specific QTc threshold corresponding to the target group, it can send the specific QTc threshold to the edge terminal that communicates and connects with the ECG device of the target group member, so that the edge terminal can monitor the electrocardiogram data of the target group member member collected by the ECG device.

[0058] The method for monitoring ECG data based on edge devices provided in this embodiment first acquires ECG data collected by ECG devices within multiple time units for the target group. Then, for each time unit, the QTc sequence is calculated using the ECG data. The QTc sequence and a preset standard QTc threshold are input into a preset neural network model for calculation, which yields the deviation of the QTc sequence from the standard QTc threshold. Next, the deviations corresponding to each time unit are weighted and averaged to obtain the comprehensive deviation corresponding to the target group. The standard QTc threshold is adjusted based on the comprehensive deviation to obtain a specific QTc threshold for the target group. This specific QTc threshold is suitable for monitoring ECG data of individuals in the target group. Therefore, this specific QTc threshold is distributed to the edge device corresponding to the target group for ECG data monitoring. On the one hand, it enables the monitoring of long QT period ECG data at the edge device based on the QTc threshold, which is convenient for users. On the other hand, the QTc threshold is a specific QTc threshold adjusted based on the comprehensive deviation calculated from the actual ECG data of the target group, which improves the accuracy of ECG data monitoring.

[0059] Example 2

[0060] Embodiment 2 of the present invention provides a preferred method for monitoring electrocardiogram (ECG) data based on edge devices. This method can improve the accuracy of ECG data monitoring while satisfying the traversal of ECG data monitoring, and provide real-time monitoring of ECG data.

[0061] Specifically, in one use case, a cloud platform, an ECG device acquisition terminal, and an edge terminal (i.e., an edge device) are set up, with the edge terminal communicating with both the cloud platform and the ECG device acquisition terminal. The ECG device acquisition terminal collects ECG data and sends it to the edge terminal. The edge terminal uploads the ECG data, carrying the target group identifier, to the cloud platform. The cloud platform, based on the target group's ECG data, executes steps S201 to S208 to send the calculated specific QTc threshold to the corresponding edge terminal for the target group. Then, the edge terminal communicates with the ECG device acquisition terminal to acquire ECG data in real time, executing steps S209 to S211 to achieve real-time monitoring of ECG data.

[0062] Figure 4 The flowchart is as follows: This is a method for monitoring ECG data based on edge devices provided in Embodiment 2 of the present invention. Figure 4 As shown, the ECG data monitoring method based on edge devices provided in this embodiment includes the following steps S201 to S211, wherein the technical features that are the same as or corresponding to those in Embodiment 1 above will not be repeated here.

[0063] Step S201: For the target group, acquire the electrocardiogram data collected by the ECG device within the time unit.

[0064] Step S202: Calculate the QT sequence and RR sequence based on the ECG data.

[0065] Among them, the QT sequence {Q} is calculated based on electrocardiogram data. n T n} and RR sequence {R n-1 R n}. n is a natural number, Q n T n R is the time interval between the nth Q wave and the nth T wave within a time unit. n-1 R n This is the time interval between the (n-1)th R wave and the nth R wave.

[0066] Step S203: Calculate the QTc sequence based on the QT sequence and the RR sequence.

[0067] The following formula can be used for calculation:

[0068]

[0069] Step S204: Input the QTc sequence and the preset standard QTc threshold into the preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold.

[0070] Step S205: Determine the weighting weight corresponding to the time unit based on the time period to which the time unit belongs.

[0071] Step S206: Perform a weighted average based on the deviation and weighting of each time unit to obtain the comprehensive deviation.

[0072] Step S207: Adjust the standard QTc threshold using the comprehensive deviation to obtain the specific QTc threshold corresponding to the target group.

[0073] Step S208: Send the specific QTc threshold to the edge terminal corresponding to the target group.

[0074] Step S209: Acquire the ECG data to be monitored from the ECG device in real time.

[0075] Step S210: Calculate the real-time QTc value based on the ECG data to be monitored.

[0076] Specifically, Q can be calculated in real time based on electrocardiogram data. n T n =T n -Q n R n-1 R n =R n -R n-1 Further calculations yielded QTc. nThat is, the real-time QTc value.

[0077] Step S211: Record the trend of the real-time QTc value deviating from a specific QTc threshold within the first preset time period.

[0078] Specifically, each QTc value within a certain preset time period can be compared with a specific QTc threshold to obtain the trend of the real-time QTc value deviating from the specific QTc threshold within that preset time period.

[0079] Example 3

[0080] Embodiment 3 of the present invention provides a preferred method for monitoring electrocardiogram (ECG) data based on edge devices. This method can improve the accuracy of ECG data monitoring while satisfying the traversal of ECG data monitoring, and provide continuous ECG data monitoring over a certain period of time.

[0081] Specifically, in one use case, a cloud platform, an ECG device acquisition terminal, and an edge terminal are set up, with the edge terminal communicating with both the cloud platform and the ECG device acquisition terminal. The ECG device acquisition terminal collects ECG data and sends it to the edge terminal. The edge terminal uploads the ECG data, carrying the target group identifier, to the cloud platform. Based on the target group's ECG data, the cloud platform executes steps S301 to S308 to send the calculated specific QTc threshold to the edge terminal corresponding to the target group. Then, the edge terminal communicates with the ECG device acquisition terminal to continuously acquire ECG data. After obtaining ECG data within a certain time period, steps S309 to S312 are executed to achieve monitoring of the ECG data within that time period.

[0082] Figure 5 The flowchart is as follows: This is a method for monitoring ECG data based on edge devices provided in Embodiment 3 of the present invention. Figure 5 As shown, the ECG data monitoring method based on edge devices provided in this embodiment includes the following steps S301 to S312, wherein the technical features that are the same as or corresponding to those in Embodiment 1 above will not be repeated here.

[0083] Step S301: For the target group, acquire the electrocardiogram data collected by the ECG device within the time unit.

[0084] Step S302: Calculate the QT sequence and RR sequence based on the ECG data.

[0085] Among them, the QT sequence {Q} is calculated based on electrocardiogram data. n T n} and RR sequence {R n-1 R n}. n is a natural number, Q n T n R is the time interval between the nth Q wave and the nth T wave within a time unit.n-1 R n This is the time interval between the (n-1)th R wave and the nth R wave.

[0086] Step S303: Calculate the QTc sequence based on the QT sequence and the RR sequence.

[0087]

[0088] Step S304: Input the QTc sequence and the preset standard QTc threshold into the preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold.

[0089] Step S305: Determine the weighting weight corresponding to the time unit based on the time period to which the time unit belongs.

[0090] Step S306: Perform a weighted average based on the deviation and weighting of each time unit to obtain the comprehensive deviation.

[0091] Step S307: Adjust the standard QTc threshold using the comprehensive deviation to obtain the specific QTc threshold corresponding to the target group.

[0092] Step S308: Send the specific QTc threshold to the edge terminal corresponding to the target group.

[0093] Step S309: Acquire the ECG data to be monitored collected by the ECG device within the time unit.

[0094] Step S310: Calculate the QTc sequence to be monitored within the time unit based on the ECG data to be monitored.

[0095] Step S311: Input the QTc sequence to be monitored and a specific QTc threshold into the neural network model for calculation to obtain the deviation of the QTc sequence to be monitored from the specific QTc threshold.

[0096] The specific technical details of steps S309 to S311 can be found in the corresponding technical features in the above embodiment 1, and will not be repeated here.

[0097] Step S312: Record the trend of the QTc sequence to be monitored deviating from a specific QTc threshold within the second preset time period.

[0098] Example 4

[0099] Corresponding to the above embodiments of the method for monitoring ECG data based on edge devices, Embodiment 4 of the present invention provides a monitoring device for ECG data based on edge devices. The technical features and corresponding technical effects can be referred to Embodiments 1 to 3 above, and will not be repeated in Embodiment 4. Figure 6This is a block diagram of the ECG data monitoring device based on edge devices provided in Embodiment 4 of the present invention, as shown below. Figure 6 As shown, the device includes an acquisition module 401, a calculation module 402, a first processing module 403, a second processing module 404, an adjustment module 405, and a monitoring module 406.

[0100] The system includes: an acquisition module 401 for acquiring ECG data collected by an ECG device within a time unit for a target group; a calculation module 402 for calculating the QTc sequence within the time unit based on the ECG data; a first processing module 403 for inputting the QTc sequence and a preset standard QTc threshold into a preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold; a second processing module 404 for performing a weighted average of the deviations corresponding to multiple time units to obtain a comprehensive deviation; an adjustment module 405 for adjusting the standard QTc threshold using the comprehensive deviation to obtain a specific QTc threshold corresponding to the target group; and a monitoring module 406 for distributing the specific QTc threshold to the edge terminal corresponding to the target group for ECG data monitoring.

[0101] Optionally, in one embodiment, the calculation module includes: a first calculation unit, configured to calculate the QT sequence {Q} based on the electrocardiogram data. n T n} and RR sequence {R n-1 R n}, where n is a natural number, Q n T n R is the time interval between the nth Q wave and the nth T wave within the time unit. n-1 R n The time interval between the (n-1)th R wave and the nth R wave; and a second calculation unit, used to calculate based on the QT sequence {Q n T n} and the RR sequence {R n-1 R n} Calculate the QTc sequence {QTc} n}

[0102] Optionally, in one embodiment, the second computing unit uses the following formula based on the QT sequence {Q n T n} and the RR sequence {R n-1 R n} Calculate the QTc sequence {QTc} n}:

[0103]

[0104] Optionally, in one embodiment, the second processing module includes: a determining unit, configured to determine the weighting weight corresponding to the time unit according to the time period to which the time unit belongs; and a weighting module, configured to perform a weighted average based on the deviation and weighting weight corresponding to each time unit to obtain a comprehensive deviation.

[0105] Optionally, in one embodiment, the monitoring module includes: a first acquisition unit, configured to acquire ECG data to be monitored collected by an ECG device in real time; a first calculation unit, configured to calculate a real-time QTc value based on the ECG data to be monitored; and a first processing unit, configured to record the trend of the real-time QTc value deviating from the specific QTc threshold within a first preset time period.

[0106] Optionally, in one embodiment, the monitoring module includes: a second acquisition unit, configured to acquire ECG data to be monitored collected by an ECG device within the time unit; a second calculation unit, configured to calculate the QTc sequence to be monitored within the time unit based on the ECG data to be monitored; a processing unit, configured to input the QTc sequence to be monitored and the specific QTc threshold into the neural network model for calculation to obtain the deviation of the QTc sequence to be monitored from the specific QTc threshold; and a second processing unit, configured to record the deviation of the QTc sequence to be monitored from the specific QTc threshold within a second preset time period.

[0107] Optionally, in one embodiment, the target group includes a population that meets any one or more of the following conditions: the region to which the population belongs, the physical condition of the population, the age of the population, and the month in which the population's electrocardiogram data was collected.

[0108] Example 5

[0109] This fifth embodiment also provides a computer device, such as a smartphone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server, or cabinet server (including a standalone server or a server cluster composed of multiple servers), etc., capable of executing programs. Figure 7 As shown, the computer device 01 in this embodiment includes, but is not limited to, a memory 012 and a processor 011 that can be interconnected via a system bus, such as... Figure 7 As shown. It should be noted that, Figure 7 Only a computer device 01 with component memory 012 and processor 011 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0110] In this embodiment, the memory 012 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 012 may be an internal storage unit of the computer device 01, such as the hard disk or memory of the computer device 01. In other embodiments, the memory 012 may also be an external storage device of the computer device 01, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 01. Of course, the memory 012 may include both the internal storage unit and its external storage device of the computer device 01. In this embodiment, the memory 012 is typically used to store the operating system and various application software installed on the computer device 01, such as the program code of the ECG data monitoring device based on the edge device in Embodiment 4. In addition, memory 012 can also be used to temporarily store various types of data that have been output or will be output.

[0111] In some embodiments, processor 011 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. Processor 011 is typically used to control the overall operation of computer device 01. In this embodiment, processor 011 is used to run program code stored in memory 012 or process data, such as a method for monitoring electrocardiogram data based on edge devices.

[0112] Example 6

[0113] This sixth embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, App application store, etc., which stores a computer program. When the program is executed by a processor, it implements the corresponding function. The computer-readable storage medium of this embodiment is used to store a monitoring device for ECG data based on an edge device. When executed by a processor, it implements the ECG data monitoring method based on an edge device according to the embodiments of this application.

[0114] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0115] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0116] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0117] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for monitoring electrocardiogram (ECG) data based on edge devices, characterized in that, include: For the target group, acquire electrocardiogram data collected by ECG devices within a time unit; Calculate the QTc sequence within the time unit based on the electrocardiogram data; The QTc sequence and a preset standard QTc threshold are input into a preset neural network model for calculation to obtain the deviation of the QTc sequence from the standard QTc threshold; The weighted average of the deviations corresponding to multiple time units is used to obtain the comprehensive deviation. The standard QTc threshold is adjusted using the comprehensive deviation to obtain the specific QTc threshold corresponding to the target group; as well as The specific QTc threshold is sent to the edge terminal corresponding to the target group for ECG data monitoring.

2. The method for monitoring ECG data based on edge devices according to claim 1, characterized in that, The steps for calculating the QTc sequence within the time unit based on the electrocardiogram data include: calculating a QT sequence {Q n T n} and an RR sequence {R n-1 R n} from the electrocardio data, wherein n is a natural number, Q n T n is a time interval between an nth Q wave and an nth T wave in the time unit, and R n-1 R n is a time interval between an (n-1)th R wave and an nth R wave; and According to the QT sequence {Q n T n} and the RR sequence {R n-1 R n}, a QTc sequence {QTc n} is calculated.

3. The method for monitoring ECG data based on edge devices according to claim 2, characterized in that, The following formula is used based on the QT sequence {Q n T n } and the RR sequence {R n-1 R n } Calculate the QTc sequence {QTc} n }:

4. The method for monitoring ECG data based on edge devices according to claim 1, characterized in that, The step of taking a weighted average of the deviations corresponding to multiple time units to obtain the comprehensive deviation includes: The weighting weight corresponding to the time unit is determined based on the time period to which the time unit belongs; and The overall deviation is obtained by performing a weighted average based on the deviation and weighting of each time unit.

5. The method for monitoring ECG data based on edge devices according to claim 1, characterized in that, The steps of sending the specific QTc threshold to the edge of the target group for ECG data monitoring include: Real-time acquisition of ECG data collected by ECG equipment; Calculate the real-time QTc value based on the ECG data to be monitored; and Record the trend of the real-time QTc value deviating from the specific QTc threshold within a first preset time period.

6. The method for monitoring ECG data based on edge devices according to claim 1, characterized in that, The steps of sending the specific QTc threshold to the edge of the target group for ECG data monitoring include: Acquire the ECG data to be monitored collected by the ECG device within the time unit; Calculate the QTc sequence to be monitored within the time unit based on the ECG data to be monitored; The QTc sequence to be monitored and the specific QTc threshold are input into the neural network model for calculation to obtain the deviation of the QTc sequence to be monitored from the specific QTc threshold; Record the trend of the monitored QTc sequence deviating from the specific QTc threshold within a second preset time period.

7. The method for monitoring ECG data based on edge devices according to claim 1, characterized in that, The target group includes individuals who meet one or more of the following conditions: their geographical location, their physical condition, their age, and the month in which their electrocardiogram data was collected.

8. A monitoring device for electrocardiogram data based on edge devices, characterized in that, include: The acquisition module is used to acquire electrocardiogram data collected by ECG devices within a time unit for the target group. The calculation module is used to calculate the QTc sequence within the time unit based on the electrocardiogram data; The first processing module is used to input the QTc sequence and a preset standard QTc threshold into a preset neural network model for calculation, and obtain the deviation of the QTc sequence from the standard QTc threshold; The second processing module is used to perform a weighted average of the deviations corresponding to the multiple time units to obtain a comprehensive deviation. The adjustment module is used to adjust the standard QTc threshold using the comprehensive deviation to obtain the specific QTc threshold corresponding to the target group; as well as The monitoring module is used to send the specific QTc threshold to the edge terminal corresponding to the target group for ECG data monitoring.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images