Wearable wireless transmission electrocardiogram monitoring and warning vest

Abstract

The present invention discloses a wearable wireless transmission electrocardiogram monitoring and warning vest, which relates to the technical field of medical devices. In order to solve the problems in the prior art that the local storage space of the device is limited, a large amount of electrocardiogram data cannot be stored for a long time, and it cannot be remotely analyzed and managed and transmitted to medical professionals or the guardians of users in real time, affecting timely treatment; through comprehensive and accurate electrocardiogram signal acquisition, when an abnormality is detected, the user is notified in time through a buzzer, and the wristband active alarm can also give an active alarm when the user is uncomfortable, and send an alarm message to the preset emergency contact through a wireless network. The main control chip conducts data interaction with the cloud monitoring platform based on the wireless network, so that doctors or family members can remotely monitor the electrocardiogram condition of the user and provide timely medical intervention suggestions. The backup power supply effectively ensures that the device can still work continuously in the case of the exhaustion of the main power supply, guaranteeing the life safety of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a wearable wireless transmission electrocardiogram monitoring and warning vest. Background Art

[0002] With the development of wearable technology, a variety of portable electrocardiogram monitoring devices have emerged on the market. For example, a Chinese patent with the publication number CN214804773U discloses a wearable cervical electrocardiogram monitoring vest, which includes a cervical protection body and a vest body. The cervical protection body and the vest body are respectively connected by a first wire and a second wire. An electrocardiogram monitor is provided on the vest body, and the electrocardiogram monitor is arranged on the inner side of the left front chest of the vest body. A controller is also provided on the vest body. An indicator light, a power battery, a display screen and a switch button are respectively provided on the vest body. The controller is respectively connected to the indicator light, the power battery, the electrocardiogram monitor, the display screen and the switch button. A jack is provided at the bottom of one side of the vest body, and the power battery is connected to the jack through a wire. This vest realizes the integration of electrocardiogram monitoring, drug prevention, massage and cervical protection, which can facilitate people to carry out electrocardiogram monitoring and can perform massage, drug prevention and cervical protection, enabling patients to detect diseases early and prevent them, and increasing the curative effect of diseases.

[0003] Although the above patent can provide users with comprehensive health monitoring and health care services, there are still the following problems:

[0004] In the prior art, the local storage space of the device is limited, and a large amount of electrocardiogram data cannot be stored for a long time, and it cannot be remotely analyzed and managed and transmitted to medical professionals or the guardians of users in real time, which affects timely treatment. When electrocardiogram abnormalities are detected, it is impossible to automatically send warnings to users or medical institutions. Summary of the Invention

[0005] The purpose of the present invention is to provide a wearable wireless transmission electrocardiogram monitoring and warning vest, which realizes real-time, accurate monitoring and intelligent warning of users' electrocardiogram data. At the same time, the data processing ability and intelligent analysis ability of the cloud monitoring platform further improve the accuracy of monitoring and the timeliness of warning, providing strong guarantee for users' health, so as to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions.

[0007] A wearable wireless transmission electrocardiogram monitoring and warning vest, including a wireless monitoring vest. A sensor module is installed inside the wireless monitoring vest. The sensor module is electrically connected to a main control chip. One side of the main control chip is electrically connected to a buzzer and an active alarm. The main control chip performs data interaction with a cloud monitoring platform based on a wireless network. A backup power supply is installed on one side of the wireless monitoring vest.

[0008] Further, the main control chip includes:

[0009] A signal acquisition module, configured to obtain the electrocardiogram monitoring data collected by the sensor module and preprocess the electrocardiogram monitoring data;

[0010] A signal amplification module, configured to amplify the preprocessed electrocardiogram monitoring data through a circuit to generate an analog signal of the electrocardiogram monitoring data;

[0011] An analog-to-digital conversion module, configured to convert the amplified analog signal into a digital signal and perform data verification on the converted digital signal;

[0012] A wireless transmission module, configured to real-time transmit the verified complete digital signal to the cloud monitoring platform based on the wireless network;

[0013] A power supply module, configured to provide a stable power supply for the main control chip based on the main power supply, monitor the status data of the main power supply, and switch to the backup power supply charging mode when the power of the main power supply is lower than a preset threshold.

[0014] Further, the main control chip further includes:

[0015] A user information acquisition module, configured to actively collect the basic information of the user and perform identity verification. At the same time, a unique account identifier is assigned to each user;

[0016] A user information management module, configured to review and correct the user information, and generate the personal profile of the user based on the basic information of the user and the unique account identifier;

[0017] A user data binding module, configured to bind the wireless monitoring vest to the user's account through an identity verification process before the user starts electrocardiogram monitoring.

[0018] Further, the cloud monitoring platform includes:

[0019] A data processing unit, configured to perform redundancy processing on the obtained complete digital signal to obtain the processed monitoring data;

[0020] An anomaly monitoring unit, configured to identify anomalies in the monitoring data output by the data processing unit, monitor abnormal waveforms and abnormal parameter change data, and determine the anomaly type and anomaly level according to the anomaly monitoring results,

[0021] The anomaly monitoring unit is further configured to compare the current data with the historical data of the user, analyze the abnormal change trend, and at the same time, obtain the real-time positioning data of the user when an anomaly is detected;

[0022] An early warning unit, configured to match corresponding early warning instructions from a preset early warning strategy library according to the abnormal type and level, and send the early warning instructions to the main control chip based on a wireless network;

[0023] Meanwhile, for severe anomalies exceeding the preset risk level, a direct alarm process is automatically triggered to send a distress signal to a medical institution or an emergency rescue center and provide real-time location data of the user.

[0024] Further, the data processing unit performs redundancy processing, specifically:

[0025] Divide the complete digital signal into multiple data segments according to a fixed time window, perform transient timing verification on the sub-data in each data segment, and determine the modal feature change value and sequence feedback coefficient of the sub-data according to the verification results;

[0026] Determine the modal feature attenuation exponent of the sub-data according to the attenuation rate of the signal energy with respect to the modal feature change value of the sub-data;

[0027] Calculate the target hash value of the sub-data according to the modal feature attenuation exponent and sequence feedback coefficient of the sub-data, and statistically analyze the normal electrocardiogram data obtained based on big data to determine the preset hash value;

[0028] Confirm whether the target hash value of each sub-data is greater than or equal to the preset hash value. If so, confirm that the sub-data is not redundant data. If not, confirm that the sub-data is redundant data;

[0029] Extract the redundant data in the complete digital signal, determine the specific location and attributes of the redundant data, and perform redundancy removal to obtain the processed monitoring data.

[0030] Further, the time length setting of the time window is obtained through the following process, including:

[0031] Set the heart rate acquisition time period;

[0032] Collect the heart rate data of the user per unit time within the heart rate acquisition time period, where the value of the unit time is 1 min;

[0033] Retrieve the reference time window length stored in the database;

[0034] Obtain the heart rate characterization coefficient by using the heart rate data of the user per unit time;

[0035] Among them, the heart rate characterization coefficient is obtained through the following formula:

[0036]

[0037] Wherein, S represents the heart rate characterization coefficient; T represents the length of the reference time window; t represents the length of a unit of time; n represents the number of units of time experienced in heart rate data acquisition, and nt is not less than 5T; HR i represents the heart rate value of the i-th unit of time; HR e represents a preset reference value of the heart rate value; HR max and HR min represent the maximum heart rate value and the minimum heart rate value corresponding to n units of time; m represents the number of units of time between the maximum heart rate value and the minimum heart rate value; λ represents a regulation coefficient, and the regulation coefficient is obtained through the following formula:

[0038]

[0039] Wherein, λ represents the regulation coefficient; n represents the number of units of time experienced in heart rate data acquisition; HR i represents the heart rate value of the i-th unit of time; HR e represents a preset reference value of the heart rate value; HR z represents the median heart rate value corresponding to n units of time; k i represents the number of units of time between the heart rate value of the i-th unit of time and the unit of time to which the median heart rate value belongs; t represents the length of a unit of time;

[0040] Compare the heart rate characterization coefficient with a preset heart rate characterization coefficient threshold;

[0041] Determine the time length of the fixed time window according to the quantitative relationship between the heart rate characterization coefficient and the preset heart rate characterization coefficient threshold.

[0042] Further, determining the time length of the fixed time window according to the quantitative relationship between the heart rate characterization coefficient and the preset heart rate characterization coefficient threshold includes:

[0043] When the heart rate characterization coefficient is lower than the preset heart rate characterization coefficient threshold, keep the time length of the time window as the reference time window length, that is, use the reference time window length as the fixed time window;

[0044] When the heart rate characterization coefficient exceeds the preset heart rate characterization coefficient threshold, then retrieve the heart rate characterization coefficient;

[0045] Use the heart rate characterization coefficient in combination with the reference time window length to obtain the time length of the fixed time window;

[0046] Wherein, the time length of the fixed time window is obtained through the following formula:

[0047]

[0048] Among them, T g represents the time length corresponding to a fixed time window; S represents the heart rate characterization coefficient; S y represents the preset threshold of the heart rate characterization coefficient; n represents the number of unit time periods experienced in the heart rate data acquisition; k i represents the number of unit time periods between the heart rate value of the i-th unit time period and the unit time period to which the heart rate median belongs; m represents the number of unit time periods between the maximum heart rate value and the minimum heart rate value; T represents the reference time window length.

[0049] Furthermore, the data processing unit further includes:

[0050] The data analysis module is used to analyze the long-term and short-term trends in the processed monitoring data, identify potential electrocardiogram activity patterns in the processed monitoring data, and present the analysis results to the user in the form of charts, reports, and other visualizations;

[0051] The feature extraction module is used to extract electrocardiogram signals from the processed monitoring data, determine the key features of the electrocardiogram signals, extract the frequency domain features of the electrocardiogram signals based on the key features, and identify weak changes and potential risks in the electrocardiogram signals based on the frequency domain features.

[0052] Furthermore, the abnormal monitoring unit includes:

[0053] The abnormal identification module is used to, based on the identified electrocardiogram activity patterns and the feature extraction results, identify abnormal waveforms and parameter change data in which the electrocardiogram activity pattern of the monitoring data does not match the normal pattern, determine the abnormal type of the monitoring data according to the abnormal features of the abnormal waveforms and parameter change data, and determine the preset abnormal threshold based on the classification result;

[0054] The risk assessment module is used to compare the output result of the abnormal identification module with the preset abnormal threshold, evaluate the abnormal level of the monitoring data, combine the historical data of the user to analyze the change trend of the monitoring data with abnormalities, predict possible future impacts, and match corresponding emergency treatment plans according to the risk assessment results;

[0055] The positioning data processing module is used to, when an abnormality is detected, automatically trigger a data instruction for collecting the user's real-time location, associate the monitoring data with abnormalities with the positioning data, and identify the specific location and scenario where the abnormality occurs.

[0056] Furthermore, the warning unit includes:

[0057] An early warning instruction generation module, which is used to match corresponding early warning instructions according to the abnormal type and abnormal level evaluation result of monitoring data, and formulate an early warning strategy according to the user's personal information and electrocardiogram monitoring history record;

[0058] An early warning notification module, which is used to send the generated early warning instructions to the main control chip through a wireless network, trigger the buzzer for sound and light alarm, receive the user's confirmation feedback on the early warning notification, and determine the reception and processing situation of the early warning information;

[0059] A rescue dispatching module, which is used to conduct a risk assessment for serious abnormalities exceeding the preset risk level, decide whether to trigger a direct alarm process based on the assessment result, send a distress signal to the nearby medical institution or emergency rescue center, provide the user's real-time positioning data, and update the rescue status in real time based on the rescue feedback data.

[0060] Compared with the prior art, the beneficial effects of the present invention are:

[0061] Through comprehensive and accurate electrocardiogram signal acquisition, the vest can monitor electrocardiogram data in real time, and when an abnormality is detected, it can notify the user in time through the buzzer. The wristband active alarm can remind the user through vibration or sound, and the wristband active alarm can also actively alarm when the user feels unwell, send an alarm message to the preset emergency contact through a wireless network. The wireless monitoring vest made of soft and breathable elastic material enables the user to wear it for a long time without discomfort, improving the user's wearing experience. The main control chip conducts data interaction with the cloud monitoring platform based on the wireless network, enabling doctors or family members to remotely monitor the user's electrocardiogram condition and provide timely medical intervention suggestions. The backup power supply effectively ensures that the device can still work continuously in case the main power supply runs out, ensuring the user's life safety. Description of the Drawings

[0062] Figure 1 It is a schematic diagram of the wireless monitoring vest of the present invention;

[0063] Figure 2 It is a module diagram of the main control chip of the present invention;

[0064] Figure 3 It is a module diagram of the cloud monitoring platform of the present invention.

[0065] In the figure: 1. Wireless monitoring vest; 2. Sensor module; 3. Main control chip; 4. Buzzer; 5. Active alarm; 6. Backup power supply. Detailed Embodiments

[0066] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0067] To solve the technical problems in the prior art that the local storage space of the device is limited, a large amount of electrocardiogram data cannot be stored for a long time, and it cannot be remotely analyzed and managed and transmitted to medical professionals or the guardians of users in real time, affecting timely treatment, please refer to Figures 1-3 , the following technical solutions are provided in this embodiment,

[0068] The wearable wireless transmission electrocardiogram monitoring and warning vest includes a wireless monitoring vest 1. A sensor module 2 is installed in the wireless monitoring vest 1. Electrocardiogram sensors are sewn at key positions such as the chest and left abdomen of the wireless monitoring vest 1 to ensure correspondence with the heart position and ensure comprehensive and accurate signal acquisition. The wireless monitoring vest 1 is made of a soft, breathable and elastic material to ensure comfort during long-term wear. The sensor module 2 is composed of a plurality of sewn electrocardiogram sensors, that is, electrode patches, and is designed to be detachable for easy regular cleaning by users. Keeping the electrode patches clean can effectively improve the accuracy of data acquisition. The sensor module 2 is electrically connected to the main control chip 3. One side of the main control chip 3 is electrically connected to a buzzer 4 and an active alarm 5. The active alarm 5 is worn on the user's wrist through a wristband. The main control chip 3 performs data interaction with the cloud monitoring platform based on a wireless network. A backup power supply 6 is installed on one side of the wireless monitoring vest 1.

[0069] In this embodiment, the main control chip 3 includes:

[0070] A signal acquisition module, which is used to obtain the electrocardiogram monitoring data collected by the sensor module 2, preprocess the electrocardiogram monitoring data, and automatically adjust the gain according to the signal strength to ensure that the electrocardiogram signals of different patients or the same patient at different times can be optimally collected;

[0071] A signal amplification module, which is used to amplify the preprocessed electrocardiogram monitoring data by a circuit to generate an analog signal of the electrocardiogram monitoring data;

[0072] An analog-to-digital conversion module, which is used to convert the amplified analog signal into a digital signal and perform data verification on the converted digital signal to ensure the integrity and accuracy of the data during the conversion process;

[0073] A wireless transmission module, which is used to transmit the verified complete digital signal to the cloud monitoring platform in real time based on a wireless network;

[0074] A power supply module, which is used to provide a stable power supply for the main control chip 3 based on the main power supply, monitor the status data of the main power supply, and switch to the charging mode of the backup power supply 6 when the power of the main power supply is lower than the preset threshold;

[0075] A user information collection module, which is used to actively collect basic user information, such as name, age, gender, contact information, etc., and perform identity verification to ensure the authenticity and uniqueness of the user's identity. At the same time, a unique account identifier is assigned to each user;

[0076] A user information management module, which is used to review and correct user information, generate the user's personal profile based on the basic user information and the unique account identifier, and allow the user to update and modify it, including contact information changes, allergy history, etc.;

[0077] A user data binding module, which is used to bind the wireless monitoring vest 1 to the user's account through the identity verification process before the user starts electrocardiogram monitoring.

[0078] In this embodiment, through comprehensive and accurate electrocardiogram signal acquisition, the vest can monitor electrocardiogram data in real time, and when an abnormality is detected, the user is notified in time through the buzzer 4. The wristband active alarm 5 reminds the user through vibration or sound. The wristband active alarm 5 can also actively alarm when the user feels unwell, send an alarm message to the preset emergency contact through the wireless network. The wireless monitoring vest 1 is made of a soft, breathable and elastic material, so that the user can wear it for a long time without discomfort, improving the user's wearing experience. The main control chip 3 performs data interaction with the cloud monitoring platform based on the wireless network, so that doctors or family members can remotely monitor the user's electrocardiogram condition and provide timely medical intervention suggestions. The backup power supply 6 effectively ensures that the device can still work continuously in the case of the main power supply running out, ensuring the user's life safety.

[0079] In this embodiment, the cloud monitoring platform includes:

[0080] A data processing unit, which is used to perform redundancy processing on the acquired complete digital signal to obtain the processed monitoring data. Specifically:

[0081] The complete digital signal is divided into multiple data segments according to a fixed time window, each data segment contains 1 second of electrocardiogram data, transient time series verification is performed on the sub-data in each data segment, and the modal feature change value and sequence feedback coefficient of the sub-data are determined according to the verification result;

[0082] The transient time series verification includes the detection of features such as the waveform, amplitude, and frequency of the electrocardiogram signal to ensure the integrity and accuracy of the data. The modal feature change value is determined by calculating parameters such as the peak-to-peak value and heart rate variability of the signal waveform within the data segment;

[0083] Determine the modal feature decay index of the sub-data according to the attenuation rate of the signal energy with respect to the change value of the modal feature of the sub-data;

[0084] Calculate the target hash value of the sub-data according to the modal feature decay index of the sub-data and the sequence feedback coefficient, and statistically analyze the normal electrocardiogram data obtained based on big data to determine the preset hash value;

[0085] Confirm whether the target hash value of each sub-data is greater than or equal to the preset hash value. If so, confirm that the sub-data is not redundant data. If not, confirm that the sub-data is redundant data;

[0086] Extract the redundant data in the complete digital signal, determine the specific location and attributes of the redundant data, and perform redundant data removal to obtain the processed monitoring data;

[0087] Specifically, the time length setting of the time window is obtained through the following process, including:

[0088] Set the heart rate acquisition time period;

[0089] Collect the heart rate data of the user per unit time within the heart rate acquisition time period, where the value of the unit time is 1 min;

[0090] Retrieve the reference time window length stored in the database;

[0091] Obtain the heart rate characterization coefficient using the heart rate data of the user per unit time;

[0092] Among them, the heart rate characterization coefficient is obtained through the following formula:

[0093]

[0094] Among them, S represents the heart rate characterization coefficient; T represents the reference time window length; t represents the duration of the unit time; n represents the number of unit times experienced in the heart rate data acquisition, and nt is not less than 5T; HR i represents the heart rate value of the i-th unit time; HR e represents the preset heart rate value reference; HR max and HR min represent the maximum and minimum heart rate values corresponding to n unit times; m represents the number of unit times between the maximum and minimum heart rate values; λ represents the adjustment coefficient, and the adjustment coefficient is obtained through the following formula:

[0095]

[0096] Among them, λ represents the adjustment coefficient; n represents the number of unit time experienced by heart rate data collection; HR i Represents the heart rate value of the i-th unit time; HR e Indicates the preset heart rate reference value; HR z represents the median heart rate corresponding to n unit time; k i represents the number of unit times between the heart rate value of the i-th unit time and the unit time to which the middle value of the heart rate belongs; t represents the duration of the unit time;

[0097] Comparing the heart rate characterization coefficient with a preset heart rate characterization coefficient threshold;

[0098] The time length corresponding to the fixed time window is determined according to the quantitative relationship between the heart rate characterization coefficient and a preset heart rate characterization coefficient threshold.

[0099] The technical effect of the above technical solution is: by collecting the user's heart rate data for each unit time (1 minute) within a specific time period (heart rate collection time period), and combining a series of calculations and analyses, the technical solution can set a personalized time window length for the user. This personalized setting method is more flexible and accurate than a fixed time window, and can better adapt to the physiological characteristics and heart rate change patterns of different users. By calculating the heart rate characterization coefficient S, the technical solution can comprehensively evaluate the user's heart rate changes within the heart rate collection time period. This coefficient not only takes into account the fluctuation range of the heart rate value (HR max and HR min ), and also considers the heart rate value and the reference value (HR e ) and median heart rate (HR z ) and how these deviations change with time (k i and t). Therefore, the heart rate characterization coefficient can reflect the user's heart rate characteristics more comprehensively and accurately. The introduction of the adjustment coefficient λ makes the setting of the time window length more flexible. The calculation of λ takes into account the deviation between the heart rate value and the heart rate median value and the change of these deviations over time, so the length of the time window can be dynamically adjusted according to the user's heart rate changes. This dynamic adjustment mechanism helps to improve the accuracy and adaptability of the time window setting. By comparing the heart rate characterization coefficient S with the preset heart rate characterization coefficient threshold, and determining the time length corresponding to the fixed time window based on the quantitative relationship between the two, the technical solution can ensure that the length of the time window is consistent with the user's physiological characteristics and can meet the needs of practical applications. This optimized time window length helps to improve the accuracy and efficiency of heart rate monitoring.

[0100] In summary, by introducing parameters such as the heart rate characterization coefficient and the adjustment coefficient, the technical solution realizes personalized, dynamic and accurate setting of the time window length, which helps to improve the accuracy and efficiency of heart rate monitoring and provide more accurate health management services for users.

[0101] Specifically, determining the time length of the fixed time window according to the quantitative relationship between the heart rate characterization coefficient and the preset heart rate characterization coefficient threshold includes:

[0102] When the heart rate characterization coefficient is lower than the preset heart rate characterization coefficient threshold, keep the time length of the time window as the reference time window length, that is, use the reference time window length as the fixed time window;

[0103] When the heart rate characterization coefficient exceeds the preset heart rate characterization coefficient threshold, then retrieve the heart rate characterization coefficient;

[0104] Use the heart rate characterization coefficient combined with the reference time window length to obtain the time length of the fixed time window;

[0105] Among them, the time length of the fixed time window is obtained through the following formula:

[0106]

[0107] Among them, T g represents the time length of the fixed time window; S represents the heart rate characterization coefficient; S y represents the preset heart rate characterization coefficient threshold; n represents the number of unit times experienced in heart rate data acquisition; k i represents the number of unit times between the heart rate value of the i-th unit time and the unit time to which the heart rate median value belongs; m represents the number of unit times between the maximum heart rate value and the minimum heart rate value; T represents the reference time window length.

[0108] The technical effect of the above technical solution is: According to the quantitative relationship between the heart rate characterization coefficient (S) and the preset heart rate characterization coefficient threshold (S y ), the time length (T g ) of the fixed time window is dynamically adjusted. This dynamic adjustment mechanism enables the length of the time window to more accurately reflect the user's heart rate change situation, thereby improving the accuracy and efficiency of heart rate monitoring. By introducing the heart rate characterization coefficient, the technical solution can comprehensively consider the user's heart rate change situation during the heart rate acquisition period, including the fluctuation range of the heart rate value, the deviation between the heart rate value and the reference value and the heart rate median value, etc. This personalized time window setting method is more flexible and accurate than the fixed time window and can better adapt to the physiological characteristics and heart rate change patterns of different users.

[0109] When calculating the time length corresponding to a fixed time window, this technical solution not only considers the heart rate characterization coefficient and the preset heart rate characterization coefficient threshold, but also combines the number of unit times (n) experienced in heart rate data acquisition, the number of unit times (k i ) between the heart rate value and the unit time to which the heart rate median belongs, and the number of unit times (m) between the maximum and minimum heart rate values. This calculation method that comprehensively considers multiple factors makes the determination of the time window length more scientific and reasonable. By dynamically adjusting the time window length and setting the time window personalized, this technical solution can more accurately capture the user's heart rate changes, thereby improving the accuracy and reliability of heart rate monitoring. This is of great significance for preventing cardiovascular diseases, evaluating exercise effects, and providing personalized health management suggestions, etc.

[0110] In summary, this technical solution improves the accuracy and efficiency of heart rate monitoring by dynamically adjusting the time window length, setting the time window personalized, and optimizing the calculation of the time window length, and provides users with more accurate health management services.

[0111] The data processing unit further includes:

[0112] The data analysis module is used to analyze the long-term and short-term trends in the processed monitoring data, help users and doctors understand the changes in electrocardiogram activities, provide data support for chronic disease management, identify potential electrocardiogram activity patterns in the processed monitoring data, contribute to the discovery of heart problems such as arrhythmia, provide a basis for early diagnosis, and present the analysis results to users in the form of charts, reports, and other visualizations;

[0113] It also includes the statistical analysis of heart rate variability, the detection and classification of QRS complexes, and extracts electrocardiogram parameters helpful for diagnosis, such as the time intervals and amplitudes of P waves, QRS complexes, and T waves;

[0114] The feature extraction module is used to extract electrocardiogram signals from the processed monitoring data, determine the key features of the electrocardiogram signals, such as the peak value of the R wave, RR interval, heart rate variability HRV, etc., realize waveform recognition and classification, distinguish normal and abnormal electrocardiogram activities, provide data support for subsequent early warning and diagnosis, extract the frequency domain features of the electrocardiogram signals based on the key features, and identify weak changes and potential risks in the electrocardiogram signals based on the frequency domain features;

[0115] The abnormal monitoring unit is used to identify abnormalities in the monitoring data output by the data processing unit, monitor abnormal waveforms and abnormal parameter change data, and determine the abnormal type and abnormal level according to the abnormal monitoring results, such as minor abnormality, severe abnormality, etc.;

[0116] The abnormal monitoring unit is further configured to compare the current data with the user's historical data, analyze the abnormal change trend, and at the same time, when an abnormality is detected, obtain the user's real-time positioning data;

[0117] The warning unit is configured to match a corresponding warning instruction from a preset warning strategy library according to the abnormal type and the abnormal level, and send the warning instruction to the main control chip 3 based on the wireless network. The main control chip 3 controls the buzzer 4 to give an audible and visual alarm according to the received warning instruction;

[0118] At the same time, for a serious abnormality exceeding the preset risk level, a direct alarm process is automatically triggered, a distress signal is sent to a medical institution or an emergency rescue center, and the user's real-time positioning data is provided.

[0119] In this embodiment, through transient timing verification, key features such as the waveform, amplitude, and frequency of the electrocardiogram signal are carefully detected, ensuring the integrity and accuracy of the data, reducing data noise and errors, real-time monitoring of abnormal waveforms and parameter changes in the electrocardiogram data, quickly identifying and determining the abnormal type and level, early detection of potential health problems, striving for precious treatment time for patients, realizing personalized warning responses according to the abnormal type and level, improving the pertinence and effectiveness of the warning, reducing false alarms and missed alarms, and for serious abnormalities exceeding the preset risk level, being able to automatically trigger a direct alarm process, being able to quickly mobilize rescue forces, and striving for life rescue time for patients.

[0120] In this embodiment, the abnormal monitoring unit includes:

[0121] The abnormal recognition module is configured to, based on the recognized electrocardiogram activity pattern and the feature extraction result, recognize abnormal waveforms and parameter change data whose electrocardiogram activity pattern in the monitoring data does not match the normal pattern, determine the abnormal type of the monitoring data according to the abnormal features of the abnormal waveforms and parameter change data, such as hardware failure, software error, data abnormality, etc., and determine a preset abnormal threshold based on the classification result;

[0122] The risk assessment module is configured to compare the output result of the abnormal recognition module with the preset abnormal threshold, evaluate the abnormal level of the monitoring data, analyze the change trend of the monitoring data with abnormalities in combination with the user's historical data, predict possible future impacts, and match a corresponding emergency treatment plan according to the risk assessment result;

[0123] The positioning data processing module is configured to, when an abnormality is detected, automatically trigger a data instruction for collecting the user's real-time positioning, associate the monitoring data with abnormalities with the positioning data, identify the specific location and scenario where the abnormality occurs, and generate a detailed report including information such as the abnormal type, level, and location according to the analysis result.

[0124] In this embodiment, the anomaly recognition module accurately identifies the abnormal waveforms and parameter changes in the monitoring data, compares the anomaly recognition results with the preset anomaly thresholds, further improves the accuracy and reliability of anomaly recognition, can objectively evaluate the anomaly level of the monitoring data, the evaluation process combines the user's historical data, analyzes the change trend of the abnormal data, and predicts the possible future impacts, which helps to take timely measures before the problem expands. Associating the abnormal data with the real-time positioning data makes the specific location and scenario of the anomaly clearly presented, provides strong support for on-site handling of the problem, and the generated detailed report provides comprehensive and accurate information for subsequent review analysis, accountability, and process improvement. The efficient emergency response mechanism greatly shortens the time from problem discovery to problem handling and reduces the threat of potential risks to the user's health.

[0125] In this embodiment, the warning unit includes:

[0126] A warning instruction generation module, which is used to match the corresponding warning instructions according to the anomaly type and anomaly level evaluation results of the monitoring data, and formulate a warning strategy based on the user's personal information and electrocardiogram monitoring history records to ensure the accuracy and timeliness of the warning instructions;

[0127] In this embodiment, the warning strategy specifically includes:

[0128] Fixed threshold warning: Set a fixed value as the warning limit, and trigger a warning when the monitoring value exceeds this limit;

[0129] Dynamic threshold warning: Dynamically adjust the warning threshold according to historical data or real-time data to adapt to changes in the environment or conditions;

[0130] Rising trend warning: Trigger a warning when the monitoring data shows an upward trend for several consecutive cycles;

[0131] Falling trend warning: Trigger a warning when the monitoring data shows a downward trend for several consecutive cycles;

[0132] Behavior pattern anomaly warning: Analyze the user's behavior pattern and trigger a warning when the behavior deviates from the normal pattern;

[0133] Mean value warning: Trigger a warning when the monitoring value deviates from the average value by more than a certain standard deviation;

[0134] Variance warning: Trigger a warning when the variance of the monitoring data exceeds the preset threshold;

[0135] Multi-parameter combined warning: Combine multiple monitoring parameters and trigger a warning when the comprehensive index of multiple monitoring parameters exceeds the preset threshold;

[0136] Multi-level warning: Set multiple warning levels and gradually upgrade warning measures according to the severity of anomalies;

[0137] Seasonal change warning: Consider the time series characteristics of data, such as seasonal fluctuations, and trigger a warning when the monitored value deviates from the seasonal expectation;

[0138] Cyclical change warning: For data with clear periodicity, trigger a warning when the change of the monitored value within the cycle is abnormal;

[0139] Warning notification module, used to send the generated warning instructions to the main control chip 3 via a wireless network, trigger the buzzer 4 for audible and visual alarms to alert the user, send text messages or application push notifications to the user's preset contacts via the mobile network, inform the abnormal situation and necessary countermeasures, and receive the user's confirmation feedback on the warning notification to determine the reception and processing status of the warning information;

[0140] Rescue dispatch module, used to conduct a risk assessment for severe anomalies beyond the preset risk level, decide whether to trigger the direct alarm process based on the assessment results, send a distress signal to the nearby medical institution or emergency rescue center, and provide the user's real-time location data so that the rescue personnel can quickly and accurately locate the patient's position, maintain communication with the rescue agency, and update the rescue status in real time based on the rescue feedback data to ensure the smooth progress of the rescue process.

[0141] In this embodiment, through timely and effective warning and rescue dispatch, the safety guarantee of users in case of electrocardiogram abnormalities is significantly improved. The personalized warning strategy and instant notification enhance the user experience, making health management more considerate and convenient. Moreover, the automated risk assessment and rescue dispatch process greatly improves the rescue efficiency and success rate, providing a strong guarantee for the user's life safety.

[0142] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A wearable wireless transmission ECG monitoring and early warning vest, comprising a wireless monitoring vest (1), characterized in that: A sensor module (2) is installed in the wireless monitoring vest (1), the sensor module (2) is electrically connected to a main control chip (3), one side of the main control chip (3) is electrically connected to a buzzer (4) and an active alarm (5), the main control chip (3) performs data exchange with a cloud monitoring platform based on a wireless network, and a backup power supply (6) is installed on one side of the wireless monitoring vest (1); Cloud monitoring platform, including: A data processing unit, used for performing redundant processing on the acquired complete digital signal to obtain processed monitoring data; The data processing unit performs redundancy processing, including dividing the complete digital signal into multiple data segments according to a fixed time window, performing transient timing verification on the sub-data in each data segment, and determining the modal characteristic change value and sequence feedback coefficient of the sub-data according to the verification result; Determine the modal characteristic attenuation index of the sub-data according to the attenuation rate of the modal characteristic change value of the sub-data to the signal energy; The target hash value of the sub-data is calculated according to the modal characteristic attenuation index and the sequence feedback coefficient of the sub-data, and the normal ECG data obtained based on the big data are statistically analyzed to determine the preset hash value; Confirm whether the target hash value of each sub-data is greater than or equal to the preset hash value. If so, confirm that the sub-data is not redundant data. If not, confirm that the sub-data is redundant data. Extract redundant data from the complete digital signal, determine the specific location and attributes of the redundant data, and eliminate the redundant data to obtain the processed monitoring data; The time length setting of the time window is obtained through the following process, including: Set the heart rate collection time period; Collect the user's heart rate data in each unit time during the heart rate collection time period, wherein the value of the unit time is 1 minute; Retrieve the reference time window length stored in the database; Obtaining a heart rate characterization coefficient using the user's heart rate data per unit time; The heart rate characterization coefficient is obtained by the following formula: Where S represents the heart rate characterization coefficient; T represents the length of the reference time window; t represents the length of the unit time; n represents the number of unit times experienced by the heart rate data collection, and nt is not less than 5T; HR i Represents the heart rate value of the i-th unit time; HR e Indicates the preset heart rate reference value; HR max and HR min represents the maximum heart rate value and the minimum heart rate value corresponding to n unit time; m represents the number of unit time intervals between the maximum heart rate value and the minimum heart rate value; λ represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula: Among them, λ represents the adjustment coefficient; n represents the number of unit time experienced by heart rate data collection; HR i Represents the heart rate value of the i-th unit time; HR e Indicates the preset heart rate reference value; HR z represents the median heart rate corresponding to n unit time; k i represents the number of unit times between the heart rate value of the i-th unit time and the unit time to which the middle value of the heart rate belongs; t represents the duration of the unit time; Comparing the heart rate characterization coefficient with a preset heart rate characterization coefficient threshold; The time length corresponding to the fixed time window is determined according to the quantitative relationship between the heart rate characterization coefficient and a preset heart rate characterization coefficient threshold.

2. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 1, characterized in that: Main control chip (3), including: A signal acquisition module, used to acquire the electrocardiogram monitoring data collected by the sensor module (2) and to pre-process the electrocardiogram monitoring data; A signal amplification module, used to amplify the pre-processed ECG monitoring data to generate an analog signal of the ECG monitoring data; The analog-to-digital conversion module is used to convert the amplified analog signal into a digital signal and perform data verification on the converted digital signal; A wireless transmission module is used to transmit the verified complete digital signal to the cloud monitoring platform in real time based on a wireless network; The power module is used to provide a stable power supply to the main control chip (3) based on the main power supply, and monitor the main power supply status data, and when the power of the main power supply is lower than a preset threshold, switch to the backup power supply (6) charging mode.

3. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 2, characterized in that: The main control chip (3) further includes: The user information collection module is used to actively collect basic user information and perform identity authentication. At the same time, a unique account identifier is assigned to each user; User information management module, used to review and modify user information and generate the user's personal profile based on the user's basic information and unique account identifier; The user data binding module is used to bind the wireless monitoring vest (1) to the user's account through identity authentication before the user starts electrocardiogram monitoring.

4. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 3, characterized in that: The cloud monitoring platform also includes: The abnormality monitoring unit is used to identify abnormalities in the monitoring data output by the data processing unit, monitor abnormal waveforms and abnormal parameter change data, and determine the abnormality type and abnormality level according to the abnormality monitoring results; The anomaly monitoring unit is also used to compare the current data with the user's historical data, analyze the abnormal change trend, and at the same time, obtain the user's real-time positioning data when an abnormality is detected; An early warning unit, used to match a corresponding early warning instruction from a preset early warning strategy library according to the abnormality type and abnormality level, and send the early warning instruction to the main control chip (3) based on the wireless network; At the same time, for serious anomalies that exceed the preset risk level, the direct alarm process will be automatically triggered, sending a distress signal to medical institutions or emergency rescue centers, and providing users with real-time positioning data.

5. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 4, characterized in that: Determining the time length corresponding to the fixed time window according to the quantitative relationship between the heart rate characterization coefficient and a preset heart rate characterization coefficient threshold includes: When the heart rate characterization coefficient is lower than a preset heart rate characterization coefficient threshold, maintaining the time length of the time window as a reference time window length, that is, taking the reference time window length as a fixed time window; When the heart rate characterization coefficient exceeds a preset heart rate characterization coefficient threshold, the heart rate characterization coefficient is retrieved; Using the heart rate characterization coefficient in combination with the reference time window length, obtaining the time length corresponding to the fixed time window; The time length corresponding to the fixed time window is obtained by the following formula: Among them, T g represents the time length corresponding to the fixed time window; S represents the heart rate characterization coefficient; S y represents the preset heart rate characterization coefficient threshold; n represents the number of unit time experienced by heart rate data collection; k i It represents the number of unit times between the heart rate value of the ith unit time and the unit time to which the middle heart rate value belongs; m represents the number of unit times between the maximum heart rate value and the minimum heart rate value; T represents the length of the reference time window.

6. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 5, characterized in that: The data processing unit further includes: A data analysis module, which is used to analyze the long-term and short-term trends in the processed monitoring data, identify the potential ECG activity patterns in the processed monitoring data, and present the analysis results to the user in a visual form; The feature extraction module is used to extract the ECG signal from the processed monitoring data, determine the key features of the ECG signal, and extract the frequency domain features of the ECG signal based on the key features.

7. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 6, characterized in that: Abnormal monitoring unit, including: An abnormality identification module is used to identify abnormal waveforms and parameter change data of the ECG activity pattern of the monitoring data that are inconsistent with the normal pattern based on the identified ECG activity pattern and feature extraction results, determine the abnormal type of the monitoring data according to the abnormal characteristics of the abnormal waveform and parameter change data, and determine a preset abnormal threshold based on the classification result; The risk assessment module is used to compare the output of the anomaly identification module with the preset anomaly threshold, assess the anomaly level of the monitoring data, analyze the changing trend of the abnormal monitoring data in combination with the user's historical data, predict possible future impacts, and match the corresponding emergency response plan according to the risk assessment results; The positioning data processing module is used to automatically trigger the data instruction of collecting the user's real-time positioning when an anomaly is detected, associate the monitoring data with the abnormality with the positioning data, and identify the specific location and scene where the anomaly occurs.

8. The wearable wireless transmission ECG monitoring and early warning vest as claimed in claim 7, characterized in that: Early warning unit, including: The warning instruction generation module is used to match the corresponding warning instructions according to the abnormal type and abnormal level assessment results of the monitoring data, and formulate a warning strategy based on the user's personal information and ECG monitoring history records; An early warning notification module is used to send the generated early warning instruction to the main control chip (3) via a wireless network, trigger a buzzer (4) to sound and light alarm, receive confirmation feedback from the user on the early warning notification, and determine the receipt and processing of the early warning information; The rescue dispatch module is used to conduct risk assessment on serious anomalies that exceed the preset risk level, and decide whether to trigger the direct alarm process based on the assessment results, provide users with real-time positioning data, and update the rescue status in real time based on rescue feedback data.

Images