Heart rate monitoring data automatic collection and analysis system and method
By dynamically adjusting the acquisition frequency of the heart rate monitoring system and analyzing heart rate data using machine learning models, the problem that the existing technology cannot capture abnormal heart rate fluctuations in time is solved, more accurate health monitoring and early intervention are achieved, and user safety and Effectiveness of heart health management.
Patent Information
- Application Number
- CN202411245636.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The existing heart rate monitoring system cannot capture the rapid fluctuations of the heart rate in time when there is potential abnormality in the user's heart rate, resulting in the failure of the abnormal heart rhythm to be detected immediately, which may lead to further damage to the heart or fatal heart events.
Through dynamic and intelligent acquisition frequency adjustment, the heart rate data is extracted and analyzed based on machine learning models, and the acquisition frequency is automatically increased. When the heart rate changes rapidly, it ensures timely capture of key data and reduces the risk of delay detection.
It significantly improves the early detection rate of cardiac rhythm abnormalities, provides more accurate health monitoring for high-risk users, and helps take measures at the earliest intervention time to reduce the risk of further cardiac damage or fatal heart events.
Smart Images

Figure CN118749936B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of heart rate monitoring, and in particular to a system and method for automatically collecting and analyzing heart rate monitoring data. Background Art
[0002] The heart rate monitoring data automatic collection and analysis system is a system that combines sensors and data processing technology. It can collect the user's heart rate data in real time and automatically analyze it. The system continuously monitors heart rate changes through sensors worn on the user (such as smart watches or heart rate belts) and transmits the collected data to a central processing unit or cloud platform for processing. The analysis part usually includes the detection of heart rate fluctuations, the identification of abnormal conditions (such as arrhythmia or tachycardia), and the generation of reports or alarms based on preset algorithms, thereby providing timely information to users or medical personnel.
[0003] The prior art has the following deficiencies:
[0004] When performing heart rate monitoring with existing technologies, most of them use a pre-set initial collection frequency to collect heart rate data. This initial collection frequency can meet normal monitoring needs. For people with heart diseases (such as arrhythmias, heart failure) or people at high risk of cardiovascular events, when there are potential abnormalities in the user's heart rate that cause rapid fluctuations in heart rate, if the pre-set initial collection frequency is still used, the abnormal fluctuations in heart rate may not be captured in time, resulting in abnormal heart rhythm (such as ventricular tachycardia or atrial fibrillation), which cannot be detected in the first time. Delayed detection may miss the critical opportunity for intervention, causing further damage to the heart, or even leading to fatal heart events, such as cardiac arrest.
[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0006] The purpose of the present invention is to provide a system and method for automatic collection and analysis of heart rate monitoring data, which effectively improves the sensitivity and timeliness of detecting abnormal heart rate fluctuations through dynamic and intelligent adjustment of the collection frequency. When the heart rate changes rapidly or is potentially abnormal, the system can automatically increase the collection frequency, capture key data in a timely manner, and reduce the risk of delayed detection. The system significantly improves the early detection rate of abnormal heart rhythms, provides more accurate health monitoring for high-risk users, and helps take measures at the earliest opportunity for intervention, thereby improving user safety and the effectiveness of heart health management to solve the problems in the above-mentioned background technology.
[0007] In order to achieve the above object, the present invention provides the following technical solutions:
[0008] A method for automatically collecting and analyzing heart rate monitoring data comprises the following steps:
[0009] Based on the needs of heart rate monitoring under normal physiological conditions, an initial acquisition frequency is set for the heart rate monitoring system, heart rate data is collected at the initial acquisition frequency, and the collected data is transmitted to the central processing unit;
[0010] After collecting the heart rate data, the central processing unit extracts features from the heart rate data, analyzes the extracted features, predicts the analyzed features through a machine learning model, and comprehensively evaluates the changes in the heart rate data;
[0011] Based on the prediction results, the heart rate changes are divided into different modes, including normal change state and rapid change state;
[0012] For heart rate changes under normal conditions, the heart rate data will continue to be collected at the initial collection frequency. Once the heart rate monitoring system determines that the user's heart rate is changing rapidly, the actual collection frequency will be dynamically adjusted based on the initial collection frequency to meet the heart rate data collection needs under rapid changes.
[0013] After the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy, adjusts the collection frequency from the initial collection frequency to the actual collection frequency, and collects the user's heart rate data at the actual collection frequency;
[0014] When the heart rate monitoring system detects that the user's heart rate fluctuation has returned to a normal state, it automatically restores the collection frequency to the initial collection frequency.
[0015] Preferably, the initial acquisition frequency is set based on the demand for heart rate fluctuations under normal physiological conditions, which can meet the basic requirements of daily monitoring and capture heart rate changes in daily activities without consuming excessive battery energy and computing resources.
[0016] Preferably, the extracted heart rate data include the degree of deviation of the current heart rate from the user's normal baseline heart rate and the drastic mutation of the heart rate in a short period of time. After acquisition, within the detection time window, the degree of deviation of the current heart rate from the user's normal baseline heart rate and the drastic mutation of the heart rate in a short period of time are analyzed, and a heart rate deviation index and a heart rate mutation index are generated respectively. The heart rate deviation index and the heart rate mutation index are input into a pre-trained machine learning model, and a heart rate dynamic change coefficient is generated by the model. The changes in the heart rate data are comprehensively evaluated by the heart rate dynamic change coefficient.
[0017] Preferably, within the detection time window, the specific steps of generating the heart rate deviation index after analyzing the degree of deviation between the current heart rate and the user's normal baseline heart rate are as follows:
[0018] In the detection window, the user's current heart rate data is first collected and recorded as , Represents the currently collected heart rate value. At the same time, obtain the user's normal baseline heart rate, recorded as , Indicates the user's baseline heart rate under normal conditions, representing the user's heart rate in a stable state. These data are used for subsequent analysis;
[0019] Calculate the heart rate deviation between the current heart rate and the baseline heart rate. The calculation expression is: , Indicates the weighted heart rate deviation value, reflecting the difference between the current heart rate and the baseline heart rate. represents the logarithmic weighting factor of the baseline heart rate;
[0020] The time weight factor is introduced to adjust according to the duration of the heart rate deviation. The calculation expression of the time weight factor is: , represents the time weight factor, Indicates the duration of the heart rate deviation. Indicates the total duration of the detection window;
[0021] Calculate the heart rate deviation index. The calculation expression is: , where Indicates the heart rate excursion index.
[0022] Preferably, within the detection time window, the specific steps of analyzing the sudden changes in the user's heart rate in a short period of time and generating the heart rate mutation index are as follows:
[0023] In the detection window, the heart rate change gradient is calculated for every two consecutive heart rate data points. The calculation expression of the heart rate change gradient is: , where Indicates at a point in time i The heart rate gradient at and Respectively at time points i and i Heart rate value at +1, Indicates time point i and i +1 time interval,
[0024] Within the detection window, after calculating the heart rate change at each time point through the gradient, the instantaneous cumulative effect of these changes is calculated to capture the overall severity of the heart rate fluctuation. The calculation expression is: , Indicates at a point in timei The cumulative effect value at Indicates at a point in time k The heart rate gradient calculated at represents the attenuation coefficient, which is used to control the time sensitivity of the cumulative effect, N Represents the total number of data points within the detection window;
[0025] Calculate the heart rate mutation index within the entire detection window. The calculation expression is: , where Indicates the heart rate mutation index, which indicates the degree of violent fluctuation of heart rate in the entire detection window. Indicates time point i The cumulative effect value.
[0026] Preferably, the heart rate dynamic change coefficient predicted by the machine learning model is compared and analyzed with a preset heart rate dynamic change coefficient reference threshold, and the heart rate change is divided into different modes. The specific division steps are as follows:
[0027] If the heart rate dynamic change coefficient is greater than or equal to the heart rate dynamic change coefficient reference threshold, the heart rate change within the detected time window is classified as a rapid change state;
[0028] If the heart rate dynamic change coefficient is less than the heart rate dynamic change coefficient reference threshold, the heart rate change within the detected time window is classified as a normal change state.
[0029] Preferably, for the change of heart rate in a fast changing state, the actual acquisition frequency is dynamically adjusted based on the initial acquisition frequency. The specific steps are as follows: Reference threshold value of heart rate dynamic change coefficient The relationship between , calculate the control coefficient, the calculation expression is: , R Represents the control coefficient, which is used to adjust the actual acquisition frequency. represents the adjustment parameter, which is used to control the sensitivity of the control coefficient. represents the gain coefficient, which is used to control the strength of the response to the deviation;
[0030] After obtaining the control coefficient R After that, the acquisition frequency increment is calculated, and the calculation expression is: , Indicates the acquisition frequency increment, that is, the part that needs to be increased on the initial acquisition frequency. represents the initial acquisition frequency, represents the weight coefficient, which is used to control the influence of the heart rate dynamic change coefficient on the acquisition frequency increment;
[0031] Based on the calculated acquisition frequency increment, the actual acquisition frequency is calculated, and the calculation expression is: , where Indicates the actual acquisition frequency after regulation.
[0032] The present invention also provides a heart rate monitoring data automatic collection and analysis system, which is used to implement the above-mentioned heart rate monitoring data automatic collection and analysis method, and the system includes an initial collection module, a data processing and feature extraction module, a pattern classification module, a dynamic control preparation module, a frequency adjustment execution module and a collection frequency recovery module;
[0033] The initial acquisition module sets an initial acquisition frequency for the heart rate monitoring system based on the needs of heart rate monitoring under normal physiological conditions, collects heart rate data at the initial acquisition frequency, and transmits the collected data to the central processing unit;
[0034] Data processing and feature extraction module: After collecting the heart rate data, the central processing unit extracts the features of the heart rate data and analyzes the extracted features. The analyzed features are predicted through a machine learning model to comprehensively evaluate the changes in the heart rate data.
[0035] The pattern classification module divides the heart rate changes into different patterns based on the prediction results, including normal change state and rapid change state;
[0036] The dynamic control preparation module continues to collect heart rate data at the initial collection frequency for heart rate changes in normal changing states. Once the heart rate monitoring system determines that the user's heart rate changes are in a rapid changing state, the actual collection frequency is dynamically adjusted based on the initial collection frequency to meet the heart rate data collection needs in the rapid changing state;
[0037] The frequency adjustment execution module, after the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy, adjusts the collection frequency from the initial collection frequency to the actual collection frequency, and collects the user's heart rate data at the actual collection frequency;
[0038] The acquisition frequency recovery module automatically restores the acquisition frequency to the initial acquisition frequency when the heart rate monitoring system detects that the user's heart rate fluctuation has returned to a normal state.
[0039] In the above technical solution, the technical effects and advantages of the present invention are as follows:
[0040] The heart rate monitoring system of the present invention can realize dynamic and intelligent adjustment of the collection frequency, effectively improving the detection sensitivity and timeliness of abnormal heart rate fluctuations. In particular, when the user's heart rate changes rapidly or has potential abnormalities, the system can automatically increase the collection frequency to ensure the timely capture of key data and reduce the risk of delayed detection. This real-time frequency regulation not only improves the early detection rate of abnormal heart rhythm, but also provides more accurate health monitoring for high-risk users, helps to take necessary measures at the earliest intervention time, thereby reducing the risk of further damage to the heart or causing fatal cardiac events, and ultimately significantly improving the safety of users and the effectiveness of heart health management. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0042] Figure 1 The present invention is a flowchart of the method for automatically collecting and analyzing heart rate monitoring data.
[0043] Figure 2 This is a module schematic diagram of the heart rate monitoring data automatic collection and analysis system of the present invention. DETAILED DESCRIPTION
[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.
[0045] like Figure 1 As shown, the present invention provides a method for automatically collecting and analyzing heart rate monitoring data, comprising the following steps:
[0046] Based on the needs of heart rate monitoring under normal physiological conditions, an initial acquisition frequency is set for the heart rate monitoring system, heart rate data is collected at the initial acquisition frequency, and the collected data is transmitted to the central processing unit;
[0047] First, set an initial acquisition frequency for the heart rate monitoring system. This frequency is usually set based on the needs of heart rate fluctuations under normal physiological conditions and can meet the basic requirements of daily monitoring. The initial acquisition frequency should be high enough to capture heart rate changes during daily activities without consuming too much battery energy and computing resources. After the system is started, the user's heart rate data is collected in real time according to the pre-set initial acquisition frequency. The heart rate data is captured by a sensor device (such as a smart watch or a heart rate belt) and then transmitted to the central processing unit.
[0048] After collecting the heart rate data, the central processing unit extracts features from the heart rate data and analyzes the extracted features. It uses the analyzed features to predict changes in the heart rate data through a machine learning model and conducts a comprehensive evaluation of changes in the heart rate data.
[0049] The extracted heart rate data includes the degree of deviation between the current heart rate and the user's normal baseline heart rate and the drastic mutation of the heart rate in a short period of time. After acquisition, within the detection time window, the degree of deviation between the current heart rate and the user's normal baseline heart rate and the drastic mutation of the heart rate in a short period of time are analyzed, and a heart rate deviation index and a heart rate mutation index are generated respectively. The heart rate deviation index and the heart rate mutation index are input into a pre-trained machine learning model, and the heart rate dynamic change coefficient is generated by the model. The changes in the heart rate data are comprehensively evaluated through the heart rate dynamic change coefficient.
[0050] A pre-trained machine learning model is an algorithm model that has been built and optimized through training with historical data and related features, and is used to predict or classify the behavior of new data. The pre-trained machine learning model accepts the input heart rate deviation index and heart rate mutation index, and generates a heart rate dynamic change coefficient. The training process usually includes the following steps:
[0051] First, a large amount of historical heart rate data is collected. These data include the characteristics of heart rate changes in various situations, including normal baseline heart rate and sudden changes in heart rate during intense exercise.
[0052] Next, feature extraction is performed on these data, such as heart rate deviation index and heart rate mutation index, as input features of the model.
[0053] Then, a suitable machine learning algorithm (such as decision tree, random forest, support vector machine or neural network, etc.) is selected to train the model using the labeled historical data. The training process involves repeatedly adjusting the model parameters to minimize the prediction error so that the model can accurately capture the regularity and abnormality of heart rate changes. After training, the model is verified and tested to ensure that it has high accuracy in predicting new data.
[0054] Finally, the model is saved and used in real-time analysis, and when new heart rate data is input, the model predicts or classifies it based on previously learned patterns. The machine learning model generates a heart rate dynamic change coefficient by receiving the heart rate deviation index and the heart rate mutation index, which helps to comprehensively evaluate the changes in heart rate data. The heart rate dynamic change coefficient comprehensively considers the degree of deviation of the user's heart rate from the normal baseline and the drastic changes in a short period of time, thereby providing more comprehensive health monitoring and risk warning. In this way, the machine learning model can identify potential health risks in complex heart rate data and provide timely and effective decision support for users and medical personnel.
[0055] When a user's heart rate deviates significantly from their normal baseline heart rate, it usually indicates that the user's heart rate fluctuates greatly. This deviation may reflect that the heart is facing an abnormal physiological or psychological load, causing the heart rate to increase or decrease significantly. Large deviations may indicate that the heart is experiencing a severe stress response, such as strenuous exercise, extreme tension, panic attacks, or more serious conditions, such as arrhythmias, myocardial ischemia, or even cardiac arrest. The baseline heart rate usually represents the user's heart working in a calm and stable state. Any significant deviation may be an early warning sign of heart health problems, indicating that further monitoring or immediate medical intervention is needed. Therefore, closely monitoring the difference between heart rate and baseline heart rate can help identify potential health risks early and respond in time to ensure the safety of the user.
[0056] The specific steps for generating the heart rate deviation index after analyzing the degree of deviation between the current heart rate and the user's normal baseline heart rate within the detection time window are as follows:
[0057] In the detection window, the user's current heart rate data is first collected and recorded as , Represents the currently collected heart rate value. At the same time, obtain the user's normal baseline heart rate, recorded as , Indicates the user's baseline heart rate under normal circumstances, representing the user's heart rate in a stable state. These data are used for subsequent analysis;
[0058] The user's current heart rate data is usually obtained in real time through wearable devices (such as smart watches, heart rate belts or other wearable sensors), which capture heart rate signals through photoplethysmography (PPG) or electrocardiogram (ECG) technology and transmit them to the monitoring system.
[0059] Obtaining the user's normal baseline heart rate requires continuous monitoring over a period of time. When the user is in a resting state (such as waking up in the morning or sitting in meditation), heart rate data is collected multiple times. After eliminating abnormal fluctuations, the user's stable heart rate level is comprehensively analyzed. This process usually requires several days of monitoring to ensure the accuracy and representativeness of the baseline heart rate.
[0060] Calculate the heart rate deviation between the current heart rate and the baseline heart rate. The calculation expression is: , Indicates the weighted heart rate deviation value, reflecting the difference between the current heart rate and the baseline heart rate. The logarithmic weighting factor of the baseline heart rate is used to amplify the sensitivity of the high heart rate segment and increase the attention to rapid heart rate changes;
[0061] In order to consider the impact of the duration of heart rate deviation, a time weight factor is introduced and adjusted according to the duration of the heart rate deviation. The calculation expression of the time weight factor is: , represents the time weight factor, Indicates the duration of the heart rate deviation. Indicates the total duration of the detection window;
[0062] Calculate the heart rate deviation index. The calculation expression is: , where Indicates the heart rate excursion index.
[0063] It can be seen from the heart rate deviation index that, within the detection time window, the larger the performance value of the heart rate deviation index generated after analyzing the deviation degree of the current heart rate from the user's normal baseline heart rate, the greater the deviation of the current heart rate from the user's normal baseline heart rate, which usually means that the user's heart rate fluctuations are more drastic. A higher heart rate deviation index may reflect that the user has experienced significant physiological or psychological stress in a short period of time, such as strenuous exercise or mood swings. On the contrary, a smaller performance value of the heart rate deviation index indicates that the current heart rate deviates less from the baseline heart rate, which means that the heart rate is in a relatively stable state and the user's physiological state is relatively stable.
[0064] When a user's heart rate changes dramatically in a short period of time, it usually indicates that the heart rate fluctuates significantly. This dramatic change means that the heart has experienced abnormal acceleration or deceleration in a very short period of time. This is often the body's response to severe physical or psychological stress, and may also indicate instability in the heart's regulatory function. For example, a dramatic heart rate change may be caused by sudden intense exercise, sharp emotional fluctuations (such as fright or extreme excitement), or more serious conditions such as the onset of arrhythmia. When this happens, the heart needs to quickly adapt to the new state. If the heart cannot adjust in time, it may lead to unstable blood pressure, insufficient oxygen supply, and even serious cardiovascular events such as myocardial ischemia or cardiac arrest. Therefore, a dramatic change in heart rate in a short period of time is not only a manifestation of increased heart burden, but also a warning signal of potential crisis, which needs to be taken seriously.
[0065] The specific steps for analyzing the sudden changes in the user's heart rate within a short period of time within the detection time window and generating the heart rate mutation index are as follows:
[0066] In the detection window, the heart rate change gradient is calculated for every two consecutive heart rate data points. The calculation expression of the heart rate change gradient is: , where Indicates at a point in time i The heart rate gradient at and Respectively at time points i and i Heart rate value at +1, Indicates time point i and i The time interval between +1 uses the square of the time interval, so that the time interval has a significant impact on the gradient calculation to emphasize the drastic changes in a short time;
[0067] Within the detection window, after calculating the heart rate change at each time point through the gradient, the instantaneous cumulative effect of these changes is calculated to capture the overall severity of the heart rate fluctuation. The calculation expression is: , Indicates at a point in time i The cumulative effect value at Indicates at a point in time k The heart rate gradient calculated at represents the attenuation coefficient, which is used to control the time sensitivity of the cumulative effect. The value will reduce the impact of earlier data, making It reflects the current drastic changes. N Represents the total number of data points within the detection window;
[0068] Calculate the heart rate mutation index within the entire detection window. The calculation expression is: , where Indicates the heart rate mutation index, which indicates the degree of violent fluctuation of heart rate in the entire detection window. Indicates time point i The cumulative effect value.
[0069] It can be seen from the heart rate mutation index that within the detection time window, the larger the performance value of the heart rate mutation index generated after analyzing the user's heart rate mutation in a short period of time, the more drastic the user's heart rate fluctuations within the detection window. This means that the heart has undergone significant changes in a short period of time, which may be caused by strenuous exercise, emotional fluctuations or potential heart problems. When the heart rate mutation index is high, it means that the heart rate mutations are frequent and large in magnitude, which may require vigilance and further medical monitoring. On the contrary, the smaller the heart rate mutation index, the relatively stable heart rate during this time period, with smaller fluctuations, which usually means that the user's heart state is relatively stable and there are no obvious abnormal fluctuations.
[0070] The machine learning model is not specifically limited here, and can achieve the heart rate deviation index Heart rate variability index Comprehensive analysis to generate heart rate dynamic change coefficient In order to realize the technical solution of the present invention, the present invention provides a specific implementation method;
[0071] Heart rate dynamic variation coefficient The resulting calculation formula is: , where , Heart Rate Excursion Index Heart rate variability index The preset scaling factor of , Both are greater than 0.
[0072] It can be seen from the heart rate dynamic change coefficient that within the detection time window, the larger the performance value of the heart rate deviation index generated after analyzing the degree of deviation between the current heart rate and the user's normal baseline heart rate, the larger the performance value of the heart rate mutation index generated after analyzing the drastic mutation of the user's heart rate in a short period of time, that is, the larger the performance value of the heart rate dynamic change coefficient generated within the detection time window, the more drastic the user's heart rate fluctuations, and vice versa, the more stable the user's heart rate fluctuations.
[0073] Based on the prediction results, the heart rate changes are divided into different modes, including normal change state and rapid change state;
[0074] The heart rate dynamic change coefficient predicted by the machine learning model is compared and analyzed with the preset heart rate dynamic change coefficient reference threshold, and the heart rate changes are divided into different modes. The specific division steps are as follows:
[0075] If the heart rate dynamic change coefficient is greater than or equal to the heart rate dynamic change coefficient reference threshold, the heart rate change within the detected time window is classified as a rapid change state;
[0076] If the heart rate dynamic change coefficient is less than the heart rate dynamic change coefficient reference threshold, the heart rate change within the detected time window is classified as a normal change state.
[0077] For heart rate changes under normal conditions, the heart rate data will continue to be collected at the initial collection frequency. Once the heart rate monitoring system determines that the user's heart rate is changing rapidly, the actual collection frequency will be dynamically adjusted based on the initial collection frequency to meet the heart rate data collection needs under rapid changes.
[0078] In view of the changes in heart rate under rapid changes, the actual acquisition frequency is dynamically adjusted based on the initial acquisition frequency. The specific steps are as follows:
[0079] According to the heart rate dynamic change coefficient Reference threshold value of heart rate dynamic change coefficient The relationship between , calculate the control coefficient, the calculation expression is: , R Represents the control coefficient, which is used to adjust the actual acquisition frequency. represents the adjustment parameter, which is used to control the sensitivity of the control coefficient. represents the gain coefficient, which is used to control the strength of the response to the deviation;
[0080] After obtaining the control coefficient R After that, the acquisition frequency increment is calculated, and the calculation expression is: , Indicates the acquisition frequency increment, that is, the part that needs to be increased on the initial acquisition frequency. represents the initial acquisition frequency, represents the weight coefficient, which is used to control the influence of the heart rate dynamic change coefficient on the acquisition frequency increment;
[0081] Based on the calculated acquisition frequency increment, the actual acquisition frequency is calculated, and the calculation expression is: , where Indicates the actual acquisition frequency after regulation.
[0082] After the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy, adjusts the collection frequency from the initial collection frequency to the actual collection frequency, and collects the user's heart rate data at the actual collection frequency;
[0083] After the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy to dynamically adjust the actual acquisition frequency of the heart rate changes under the fast-changing state, and adjusts the acquisition frequency from the initial acquisition frequency to the actual acquisition frequency. The user's heart rate data is collected at the actual collection frequency to meet the needs of heart rate data collection under rapidly changing conditions.
[0084] When the heart rate monitoring system detects that the user's heart rate fluctuation has returned to a normal state, it automatically restores the collection frequency to the initial collection frequency.
[0085] The heart rate monitoring system of the present invention can realize dynamic and intelligent adjustment of the acquisition frequency, effectively improving the detection sensitivity and timeliness of abnormal heart rate fluctuations. In particular, when the user's heart rate changes rapidly or has potential abnormalities, the system can automatically increase the acquisition frequency to ensure the timely capture of key data and reduce the risk of delayed detection. This real-time frequency regulation not only improves the early detection rate of abnormal heart rhythms (such as ventricular tachycardia or atrial fibrillation), but also provides more accurate health monitoring for high-risk users, helps to take necessary measures at the earliest intervention time, thereby reducing the risk of further damage to the heart or causing fatal cardiac events, and ultimately significantly improving the safety of users and the effectiveness of heart health management.
[0086] like Figure 2 As shown, the heart rate monitoring data automatic collection and analysis system provided by the present invention includes an initial collection module, a data processing and feature extraction module, a pattern classification module, a dynamic control preparation module, a frequency adjustment execution module and a collection frequency recovery module;
[0087] An initial acquisition module, used to set an initial acquisition frequency for the heart rate monitoring system based on the needs of heart rate monitoring under normal physiological conditions, collect heart rate data at the initial acquisition frequency, and transmit the collected data to the central processing unit;
[0088] The data processing and feature extraction module is used for the central processing unit to extract features from the heart rate data after collecting the heart rate data, analyze the extracted features, predict the analyzed features through a machine learning model, and conduct a comprehensive evaluation of the changes in the heart rate data;
[0089] A pattern classification module, used for classifying the heart rate changes into different patterns based on the predicted results, including a normal change state and a rapid change state;
[0090] The dynamic control preparation module is used to continue to collect heart rate data at the initial collection frequency for heart rate changes in a normal state. Once the heart rate monitoring system determines that the user's heart rate changes are in a rapid change state, the actual collection frequency is dynamically adjusted based on the initial collection frequency to meet the heart rate data collection needs in a rapid change state;
[0091] A frequency adjustment execution module, used for, after the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy, adjusts the collection frequency from the initial collection frequency to the actual collection frequency, and collects the user's heart rate data at the actual collection frequency;
[0092] The acquisition frequency recovery module is used to automatically restore the acquisition frequency to the initial acquisition frequency when the heart rate monitoring system detects that the user's heart rate fluctuation has returned to a normal change state;
[0093] The method for automatic collection and analysis of heart rate monitoring data provided in an embodiment of the present invention is implemented by the above-mentioned system for automatic collection and analysis of heart rate monitoring data. The specific methods and processes of the system for automatic collection and analysis of heart rate monitoring data are detailed in the embodiment of the method for automatic collection and analysis of heart rate monitoring data, which will not be repeated here.
[0094] The above formulas are all dimensionless and numerical calculations. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0095] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.
[0096] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0097] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0098] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0101] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.
[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for automatically collecting and analyzing heart rate monitoring data, characterized in that: The following steps are involved: Based on the needs of heart rate monitoring under normal physiological conditions, an initial acquisition frequency is set for the heart rate monitoring system, heart rate data is collected at the initial acquisition frequency, and the collected data is transmitted to the central processing unit; After collecting the heart rate data, the central processing unit extracts features from the heart rate data, analyzes the extracted features, predicts the analyzed features through a machine learning model, and comprehensively evaluates the changes in the heart rate data; Based on the prediction results, the heart rate changes are divided into different modes, including normal change state and rapid change state; For heart rate changes under normal conditions, the heart rate data will continue to be collected at the initial collection frequency. Once the heart rate monitoring system determines that the user's heart rate is changing rapidly, the actual collection frequency will be dynamically adjusted based on the initial collection frequency to meet the heart rate data collection needs under rapid changes. After the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy, adjusts the collection frequency from the initial collection frequency to the actual collection frequency, and collects the user's heart rate data at the actual collection frequency; When the heart rate monitoring system detects that the user's heart rate fluctuation has returned to a normal state, it automatically restores the acquisition frequency to the initial acquisition frequency; The extracted heart rate data includes the degree of deviation between the current heart rate and the user's normal baseline heart rate and the drastic mutation of the heart rate in a short period of time. After acquisition, within the detection time window, the degree of deviation between the current heart rate and the user's normal baseline heart rate and the drastic mutation of the heart rate in a short period of time are analyzed, and a heart rate deviation index and a heart rate mutation index are generated respectively. The heart rate deviation index and the heart rate mutation index are input into a pre-trained machine learning model, and a heart rate dynamic change coefficient is generated through the model. The change of the heart rate data is comprehensively evaluated through the heart rate dynamic change coefficient; The specific steps for generating the heart rate deviation index after analyzing the degree of deviation between the current heart rate and the user's normal baseline heart rate within the detection time window are as follows: In the detection window, the user's current heart rate data is first collected and recorded as , Indicates the currently collected heart rate value. At the same time, obtain the user's normal baseline heart rate, recorded as , Indicates the user's baseline heart rate under normal circumstances, representing the user's heart rate in a stable state. These data are used for subsequent analysis; Calculate the heart rate deviation between the current heart rate and the baseline heart rate. The calculation expression is: ; Indicates the weighted heart rate deviation value, reflecting the difference between the current heart rate and the baseline heart rate. represents the logarithmic weighting factor of the baseline heart rate; The time weight factor is introduced to adjust according to the duration of the heart rate deviation. The calculation expression of the time weight factor is: , represents the time weight factor, Indicates the duration of the heart rate deviation. Indicates the total duration of the detection window; Calculate the heart rate deviation index. The calculation expression is: , where Indicates the heart rate excursion index; The specific steps for analyzing the sudden changes in the user's heart rate within a short period of time within the detection time window and generating the heart rate mutation index are as follows: In the detection window, the heart rate change gradient is calculated for every two consecutive heart rate data points. The calculation expression of the heart rate change gradient is: , where Indicates at a point in time i The heart rate gradient at and Respectively at the time point i and i Heart rate value at +1, Indicates time point i and i +1 time interval, Within the detection window, after calculating the heart rate change at each time point through the gradient, the instantaneous cumulative effect of these changes is calculated to capture the overall severity of the heart rate fluctuation. The calculation expression is: , Indicates at a point in time i The cumulative effect value at Indicates at a point in time k The heart rate gradient calculated at represents the attenuation coefficient, which is used to control the time sensitivity of the cumulative effect, Represents the total number of data points in the detection window; calculate the heart rate mutation index in the entire detection window, and the calculation expression is: , where Indicates the heart rate mutation index, which indicates the degree of violent fluctuation of heart rate in the entire detection window. Indicates time point i The cumulative effect value.
2. The method for automatically collecting and analyzing heart rate monitoring data according to claim 1, characterized in that: The initial acquisition frequency is set based on the needs of heart rate fluctuations under normal physiological conditions. It can meet the basic requirements of daily monitoring and capture heart rate changes in daily activities without consuming too much battery energy and computing resources.
3. The method for automatically collecting and analyzing heart rate monitoring data according to claim 1, characterized in that: The heart rate dynamic change coefficient predicted by the machine learning model is compared and analyzed with the preset heart rate dynamic change coefficient reference threshold, and the heart rate changes are divided into different modes. The specific division steps are as follows: If the heart rate dynamic change coefficient is greater than or equal to the heart rate dynamic change coefficient reference threshold, the heart rate change within the detected time window is classified as a rapid change state; If the heart rate dynamic change coefficient is less than the heart rate dynamic change coefficient reference threshold, the heart rate change within the detected time window is classified as a normal change state.
4. The method for automatically collecting and analyzing heart rate monitoring data according to claim 3, characterized in that: In view of the changes in heart rate under rapid changes, the actual acquisition frequency is dynamically adjusted based on the initial acquisition frequency. The specific steps are as follows: According to the heart rate dynamic change coefficient Reference threshold value of heart rate dynamic change coefficient The relationship between , calculate the control coefficient, the calculation expression is: , Represents the control coefficient, which is used to adjust the actual acquisition frequency. represents the adjustment parameter, which is used to control the sensitivity of the control coefficient. represents the gain coefficient, which is used to control the strength of the response to the deviation; After obtaining the control coefficient After that, the acquisition frequency increment is calculated, and the calculation expression is: , Indicates the acquisition frequency increment, that is, the part that needs to be increased on the initial acquisition frequency. represents the initial acquisition frequency, represents the weight coefficient, which is used to control the influence of the heart rate dynamic change coefficient on the acquisition frequency increment; Based on the calculated acquisition frequency increment, the actual acquisition frequency is calculated, and the calculation expression is: , where Indicates the actual acquisition frequency after regulation.
5. A heart rate monitoring data automatic collection and analysis system, used to implement the heart rate monitoring data automatic collection and analysis method according to any one of claims 1 to 4, characterized in that: It includes an initial acquisition module, a data processing and feature extraction module, a pattern classification module, a dynamic control preparation module, a frequency adjustment execution module and an acquisition frequency recovery module; An initial acquisition module, used to set an initial acquisition frequency for the heart rate monitoring system based on the needs of heart rate monitoring under normal physiological conditions, collect heart rate data at the initial acquisition frequency, and transmit the collected data to the central processing unit; The data processing and feature extraction module is used for the central processing unit to extract features from the heart rate data after collecting the heart rate data, analyze the extracted features, predict the analyzed features through a machine learning model, and conduct a comprehensive evaluation of the changes in the heart rate data; A pattern classification module, used for classifying the heart rate changes into different patterns based on the predicted results, including a normal change state and a rapid change state; The dynamic control preparation module is used to continue to collect heart rate data at the initial collection frequency for heart rate changes in a normal state. Once the heart rate monitoring system determines that the user's heart rate changes are in a rapid change state, the actual collection frequency is dynamically adjusted based on the initial collection frequency to meet the heart rate data collection needs in a rapid change state; A frequency adjustment execution module, used for, after the dynamic adjustment strategy is formulated, the heart rate monitoring system immediately executes the strategy, adjusts the collection frequency from the initial collection frequency to the actual collection frequency, and collects the user's heart rate data at the actual collection frequency; The acquisition frequency recovery module is used to automatically restore the acquisition frequency to the initial acquisition frequency when the heart rate monitoring system detects that the user's heart rate fluctuation has returned to a normal change state.
