An electrocardiogram signal monitoring system and method for smart underwear

Abstract

The present invention discloses an electrocardiogram signal monitoring system and method for smart underwear, which relates to the technical field of signal monitoring. The data collection process of the smart underwear is tested, and data accuracy is generated by a scene test data set. If the data accuracy is not lower than expected, different working modes are set for the smart underwear, and its working modes are switched according to changes in the use scenarios of the smart underwear; the smart underwear collects data from elderly postoperative patients, encrypts the collected data, and uses a trained abnormal indicator recognition model to identify the data after decryption. If an abnormal electrocardiogram signal exists, the smart underwear sends an alarm instruction to the outside; after feature extraction of the electrocardiogram data of elderly postoperative patients, the knowledge graph of postoperative rehabilitation intervention of the patients is used to match the corresponding intervention plan; when abnormalities occur in the patient's body, timely and targeted processing can be carried out to implement intervention and protection of the patient's rehabilitation process.

Description

Technical Field

[0001] The present invention relates to the technical field of signal monitoring, and in particular to an electrocardiogram signal monitoring system and method for smart underwear. Background Art

[0002] Heart surgery for elderly patients is a complex and delicate medical process that aims to improve heart function, relieve symptoms such as angina and heart failure, and improve the patient's quality of life by repairing or replacing damaged heart structures, such as coronary artery bypass grafting, heart valve replacement or repair, and pacemaker implantation. The postoperative rehabilitation stage is crucial, and it involves close cooperation between a multidisciplinary team, including experts in cardiac surgery, cardiology, rehabilitation medicine, etc., to develop a personalized rehabilitation plan for the patient. Accordingly, the rehabilitation process not only includes drug management and regular review, but also emphasizes lifestyle adjustments, such as moderate exercise, a balanced diet, smoking cessation and alcohol restriction, and psychological support, to promote the recovery of heart function, reduce the occurrence of complications, and help elderly patients return to normal life smoothly.

[0003] Smart underwear is a new type of product that combines the comfort of traditional underwear with modern technology elements. It can be simply understood as ordinary underwear + smart chips and sensors. Compared with traditional underwear, smart underwear has the following characteristics: Real-time monitoring of health data: Through built-in sensors, smart underwear can monitor and evaluate the wearer's health status in real time, such as heart rate, body temperature, respiratory rate, etc. Data transmission and analysis: Some smart underwear supports wireless transmission function, which can transmit the monitored data to mobile phones or computers for users to view and analyze at any time.

[0004] Combined with the above application and the contents of the prior art:

[0005] When elderly patients undergoing heart surgery are in the recovery process in nursing institutions, they need to monitor and collect their various health indicators in real time, especially ECG signals and related data, so that when the patient's health is abnormal, medical staff can intervene and deal with it in time, so that the patient can recover normally. However, considering that there are certain inconveniences in collecting the patient's various health indicators through various medical monitoring equipment for a long time, in order to solve this problem, smart underwear is introduced for the patient after the patient is in the recovery process, and the smart underwear collects the patient's various data;

[0006] When there are abnormal environmental conditions in the rehabilitation area, such as noise, or large fluctuations in temperature or humidity in the rehabilitation institution, the patient's sleep quality will be disturbed to a large extent. When the patient's sleep quality is poor, his or her rehabilitation state will be significantly affected, and the risk of abnormalities in the patient's rehabilitation process will also be greater. In this usage scenario, after the smart underwear collects abnormal ECG signals, it will usually send an alarm command to the outside in real time. However, considering that there will be a certain delay in the medical staff's intervention in the patient when receiving the alarm command, it is difficult to carry out targeted treatment in a timely manner when the patient's body has abnormalities, and it is difficult to form effective feedback on the patient's rehabilitation process in real time.

[0007] To this end, the present invention provides an electrocardiogram signal monitoring system and method for smart underwear. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies in the prior art, the present invention provides an ECG signal monitoring system and method for smart underwear, which sets different working modes for the smart underwear and switches its working modes according to changes in the usage scenarios of the smart underwear; the smart underwear collects data from elderly postoperative patients, encrypts the collected data, and uses the trained abnormal indicator recognition model to identify the data after decryption. If there is an abnormal ECG signal, the smart underwear sends an alarm instruction to the outside; after feature extraction of the ECG data of elderly postoperative patients, the knowledge graph of postoperative rehabilitation intervention of the patients is used to match the corresponding intervention plan; when abnormalities occur in the patient's body, targeted treatment can be carried out in a timely manner to implement intervention and protection of the patient's rehabilitation process, thereby solving the technical problems raised in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A method for monitoring electrocardiogram signals of smart underwear, comprising:

[0013] Monitor and obtain environmental condition data in the rehabilitation area, aggregate them to generate an environmental monitoring data set, and generate environmental condition coefficients from the environmental monitoring data set , if the environmental condition coefficient Exceed expectations, identify the current sleep quality of elderly postoperative patients, and send a displacement test instruction to the outside if their sleep quality is lower than expected;

[0014] The sensor displacement data set is generated by recording the sensor displacement data. If the average displacement of the sensor is Without exceeding expectations, the data collection process of the smart underwear is tested in the preset usage scenarios, and the test data is aggregated to generate a scenario test data set;

[0015] Data accuracy generated by the scene test data set If the data accuracy Not less than expected, set different working modes for smart underwear, and switch its working mode according to the changes in the usage scenarios of smart underwear;

[0016] The smart underwear collects data from elderly patients after surgery. If the encryption trigger condition is met, the collected data is encrypted and decrypted at the data receiving end. The trained abnormal indicator recognition model is used for identification. If there is an abnormal ECG signal, the smart underwear sends an alarm command to the outside.

[0017] After extracting features from the ECG data of elderly patients after surgery, the corresponding intervention plan is matched with the patient's postoperative rehabilitation intervention knowledge graph, and the alarm density is generated according to the time node when the alarm command is received. , if the alarm density Exceeding expectations, the collected ECG data was uploaded to the medical platform.

[0018] Furthermore, data collection points are set up in the rehabilitation area, and environmental conditions are monitored at each monitoring node and corresponding environmental condition data are obtained, which are aggregated to generate an environmental monitoring data set;

[0019] Generate environmental condition coefficients from environmental condition data in the environmental monitoring data set , if the environmental condition coefficient When the preset condition threshold is exceeded, a sleep quality recognition instruction is issued to the outside.

[0020] Furthermore, the temperature in the rehabilitation area ,humidity and noise Perform linear normalization and map the corresponding data values ​​to the interval The environmental condition coefficient is generated as follows :

[0021] ;

[0022] Weight coefficient: , , , ;

[0023] For the i The temperature of the monitoring node, is the acceptable value of temperature, is the mean temperature; For the i The humidity of each monitoring node, is the acceptable value of humidity, is the mean humidity; For the i The noise of the monitoring nodes, is the acceptable value of noise, is the mean of the noise.

[0024] Furthermore, after receiving the sleep quality recognition instruction, the patient's sleep quality data is continuously collected, and the collected sleep quality data is used as input. The trained sleep quality assessment model is used to identify the current sleep quality score of elderly postoperative patients. If the identified sleep quality score is lower than expected, a displacement test instruction is issued to the outside.

[0025] Further, after receiving the displacement test instruction, when the elderly postoperative patient is in a sleeping state, the displacement data of the sensor at each recording node is recorded, and the acquired displacement data is aggregated to generate a sensor displacement data set;

[0026] The displacement of the sensor is generated from the sensor displacement data set , to obtain the displacement Mark each sensor. If the average displacement of the sensor If the average displacement of the sensor does not exceed the expected value, a scene test instruction is issued to the outside. If it exceeds expectations, adjust the position of the sensor;

[0027] After receiving the scene test instruction, several test scenes are set for the smart underwear in advance, the data collection process of the smart underwear is tested under the preset usage scenarios, and the ECG signal data collected by the smart underwear are summarized to generate a scene test data set.

[0028] Furthermore, the shortest distance between the real-time position of the sensor and the target position is taken as the displacement. Perform linear normalization and map the corresponding data values ​​to the interval The displacement of the sensor is generated as follows :

[0029] ;

[0030] in, is the number of displacements, It is i The displacement of each node is recorded. is the average value of displacement, is the acceptable value of displacement, weight coefficient: , ,and .

[0031] Furthermore, the deviation ratio between the monitored value and the true value in the scene test data set is used as the deviation ratio. Data accuracy when generating smart underwear for data collection , if the data accuracy of smart underwear in different test scenarios When the mean value is lower than the accuracy threshold, an adjustment instruction is issued to the outside.

[0032] Furthermore, the deviation ratio Perform linear normalization and map the corresponding data values ​​to the interval The data accuracy is generated as follows :

[0033] ;

[0034] in, is the number of test nodes, It is i The deviation ratio of the test nodes, is the average value of the deviation ratio, is the acceptable value of the deviation ratio; weight coefficient: , ,and .

[0035] Furthermore, after the smart underwear enters the working state, a sleeping environment threshold is set for the smart underwear. , set different working modes for smart underwear, according to the environment sleep ratio Sleeping environment threshold The working mode is switched by the relationship as follows:

[0036] ;

[0037] in, , Environmental sleep ratio The number of is the environmental sleep ratio, specifically the ratio of the environmental condition coefficient to the sleep quality score; For the i The ambient sleep ratio within the monitoring cycle, is the mean of the ambient sleep ratio.

[0038] Furthermore, in the selected working mode, the sensor network of the smart underwear collects ECG and related data of elderly patients after surgery, preprocesses the acquired ECG data of the patients, and obtains the preprocessed data; after obtaining the data volume of the ECG data of the patients in the current encryption cycle, the encryption density is generated in the following manner under dimensionless conditions: ;

[0039] The encryption density obtained When the encryption trigger condition is reached beyond the expected time, the corresponding encryption method is selected to encrypt the collected data, and the corresponding key is sent to the data receiving end; wherein, the encryption key is generated in the following manner :

[0040] ;

[0041] Weight coefficient, , ; is the number of times the patient's ECG data is received within the encryption period. It is i The first received j The difference in the amount of data received each time, is the average value of the data volume difference.

[0042] Furthermore, when the encrypted patient ECG data is received at the data receiving end, it is decrypted according to the corresponding key, and the decrypted patient ECG data is used as input, and the trained abnormal indicator recognition model is used for recognition, and the recognized abnormal ECG signal is output. After the abnormal ECG signal is recognized, the smart underwear sends an alarm command to the outside.

[0043] Furthermore, feature engineering is used to extract features from the received patient ECG data to obtain corresponding intervention features. Rehabilitation intervention for elderly patients after heart surgery is used as the target word to pre-construct a knowledge graph for postoperative rehabilitation intervention for patients. After receiving an alarm instruction, the knowledge graph for postoperative rehabilitation intervention for patients provides corresponding intervention plans for elderly patients after surgery based on the correspondence between the intervention features and the intervention plans.

[0044] Furthermore, after receiving several alarm instructions continuously within the preset observation period, an alarm density is generated according to the time node of receiving the alarm instruction. , if the alarm density When the density threshold is exceeded, the ECG data collected continuously by the smart underwear will be uploaded to the medical platform, where:

[0045] ;

[0046] Weight coefficient: , ,and ; is the number of alarm instructions, It is i Alarm command to j The time interval between alarm instructions. is the average value of the time interval, Acceptable values ​​for the time interval.

[0047] An electrocardiogram signal monitoring system for smart underwear, comprising:

[0048] The environmental analysis unit monitors and obtains environmental condition data in the rehabilitation area, aggregates the data and generates an environmental monitoring data set, which in turn generates an environmental condition coefficient. , if the environmental condition coefficient Exceed expectations, identify the current sleep quality of elderly postoperative patients, and send a displacement test instruction to the outside if their sleep quality is lower than expected;

[0049] The scene test unit generates a sensor displacement data set from the recorded sensor displacement data. If the average displacement of the sensor Without exceeding expectations, the data collection process of the smart underwear is tested in the preset usage scenarios, and the test data is aggregated to generate a scenario test data set;

[0050] Model adjustment unit, generates data accuracy from scene test data set If the data accuracy Not less than expected, set different working modes for smart underwear, and switch its working mode according to the changes in the usage scenarios of smart underwear;

[0051] The alarm unit uses the smart underwear to collect data from elderly patients after surgery. If the encryption trigger condition is met, the collected data is encrypted and decrypted at the data receiving end. The trained abnormal indicator recognition model is used for identification. If there is an abnormal ECG signal, the smart underwear sends an alarm command to the outside.

[0052] The emergency intervention unit extracts features from the ECG data of elderly patients after surgery, matches the corresponding intervention plan with the patient's postoperative rehabilitation intervention knowledge graph, and generates an alarm density based on the time node when the alarm command is received. , if the alarm density Exceeding expectations, the collected ECG data was uploaded to the medical platform.

[0053] (III) Beneficial effects

[0054] The present invention provides an electrocardiogram signal monitoring system and method for smart underwear, which has the following beneficial effects:

[0055] 1. Based on the environmental condition coefficient obtained A comprehensive evaluation of environmental conditions can be used to adjust abnormal environmental conditions based on the evaluation results, thereby reducing the impact of environmental conditions on patients' sleep and recovery; the trained sleep quality assessment model can be used to identify the patient's current sleep quality and judge the patient's sleep quality.

[0056] 2. Based on displacement By judging the displacement degree of the sensor and improving the stability of the sensor, the stability of the collected data can be improved; through actual scene testing, the accuracy and reliability of the data collected by the smart underwear can be verified, which facilitates timely adjustment and processing.

[0057] 3. Based on data accuracy The reliability of smart underwear during operation can be judged, and the data accuracy When it is insufficient, the reliability of data collection of the smart underwear can be guaranteed by optimizing adjustments and signal processing, thereby forming effective feedback on the rehabilitation process of elderly patients after heart disease surgery in the rehabilitation area.

[0058] 4. Switch the working mode of smart underwear according to changes in environmental conditions and sleep quality, strike a balance between usage scenarios and energy consumption, and extend the use time of smart underwear. When the encryption trigger conditions are met, encrypt the collected data to avoid loss and leakage of key data and ensure the security of the acquired data.

[0059] 5. Use the trained abnormal indicator recognition model to identify abnormal ECG signals or similar abnormal information, and issue an alarm in a timely manner. After receiving the alarm, patients and medical management personnel in the rehabilitation area can handle abnormalities in the patient's rehabilitation process in a timely manner to ensure the patient's rehabilitation process.

[0060] 6. The knowledge map of postoperative rehabilitation intervention for patients provides corresponding intervention plans for elderly postoperative patients. Based on the intervention plan as a reference, targeted treatment can be carried out when abnormalities occur in the patient's body.

[0061] 7. Based on alarm density The severity of the patient's current abnormal recovery can be judged and evaluated. With the assistance of smart underwear, it can guide the intervention of medical staff, provide timely treatment for patients with abnormal recovery status, and provide protection for elderly postoperative patients who enter the sleep state. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flow chart of the electrocardiogram signal monitoring method of the smart underwear of the present invention;

[0063] Figure 2 It is a structural schematic diagram of the electrocardiogram signal monitoring system of the smart underwear of the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] See also Figure 1 The present invention provides an electrocardiogram signal monitoring method for smart underwear, comprising:

[0066] Step 1: Monitor and obtain environmental condition data in the rehabilitation area, summarize and generate an environmental monitoring data set, and generate environmental condition coefficients from the environmental monitoring data set , if the environmental condition coefficient Exceed expectations, identify the current sleep quality of elderly postoperative patients, and send a displacement test instruction to the outside if their sleep quality is lower than expected;

[0067] The step 1 includes the following contents:

[0068] Step 101: after determining the activity area of ​​the elderly postoperative patient when entering the rehabilitation stage, the activity area is used as the rehabilitation area, a monitoring cycle including a number of monitoring nodes is pre-set, a data collection point is set in the rehabilitation area, and the environmental conditions are monitored at each monitoring node and the corresponding environmental condition data is obtained, including the temperature, humidity and noise of the environment, and the environmental monitoring data set is generated after being aggregated;

[0069] When in use, after the elderly patient enters the rehabilitation stage, the rehabilitation environment will have a certain impact on the patient's rehabilitation status. By monitoring and collecting the environmental conditions in the rehabilitation area, adjustments can be made when the environmental conditions in the rehabilitation area become abnormal.

[0070] Step 102: Generate environmental condition coefficients from environmental condition data in the environmental monitoring data set , where the temperature in the rehabilitation area ,humidity and noise Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0071] ;

[0072] Weight coefficient: , , , , the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0073] For the i The temperature of the monitoring node, is the acceptable value of temperature, is the mean temperature; For the i The humidity of each monitoring node, is the acceptable value of humidity, is the mean humidity; For the i The noise of the monitoring nodes, is the acceptable value of noise, is the mean of the noise;

[0074] Based on historical data and patient rehabilitation environment management expectations, condition thresholds are set in advance; if the environmental condition coefficient If the preset condition threshold is exceeded, it means that the patient's sleep quality may be affected to a certain extent when entering the sleep stage in the rehabilitation area. At this time, a sleep quality recognition instruction is sent to the outside.

[0075] When in use, after completing the collection of environmental condition data and generating environmental condition coefficients , based on the environmental condition coefficient obtained Environmental conditions can be comprehensively evaluated, and abnormal environmental conditions can be adjusted based on the evaluation results to reduce the impact of environmental conditions on patients' sleep and rehabilitation;

[0076] Step 103: After receiving the sleep quality recognition instruction, continuously collect the patient's sleep quality data, such as EEG, ECG, eye movement, electromyography, respiratory rate, sleep onset time, wake-up time, blood oxygen saturation, blood pressure and heart rate; use the labeled sample data to train the neural convolution network to obtain the trained sleep quality assessment model; use the collected sleep quality data as input, use the trained sleep quality assessment model to identify the current sleep quality score of the elderly postoperative patient, and if the sleep quality score obtained by recognition is lower than expected, send a displacement test instruction to the outside;

[0077] When using, combine the contents in steps 101 to 103:

[0078] When there are abnormal environmental conditions in the rehabilitation area, after collecting sleep data, the trained sleep quality assessment model is used to identify the patient's current sleep quality, and the patient's sleep quality is judged based on the identification results. When the sleep quality is poor, the patient's rehabilitation status will be significantly affected, and the risk of abnormalities in the rehabilitation process will also be greater.

[0079] When there are abnormal environmental conditions in the rehabilitation area, such as noise, or large fluctuations in temperature or humidity in the rehabilitation institution, the patient's sleep quality will be disturbed to a large extent. When the patient's sleep quality is poor, his or her rehabilitation state will be significantly affected, and the risk of abnormalities in the patient's rehabilitation process will also be greater. In this usage scenario, after the smart underwear collects abnormal ECG signals, it will usually send an alarm command to the outside in real time. However, considering that there will be a certain delay in the medical staff's intervention in the patient when receiving the alarm command, it is difficult to carry out targeted treatment in a timely manner when the patient's body has abnormalities, and it is difficult to form effective feedback on the patient's rehabilitation process in real time.

[0080] Step 2: Generate a sensor displacement data set from the recorded sensor displacement data. If the average displacement of the sensor is Without exceeding expectations, the data collection process of the smart underwear is tested in the preset usage scenarios, and the test data is aggregated to generate a scenario test data set;

[0081] The step 2 includes the following contents:

[0082] Step 201: Select sensors and arrange them on the smart underwear, usually including the chest, shoulders and abdomen, etc., to ensure good contact between the electrodes and the skin and reduce displacement during movement; after receiving the displacement test instruction, when the elderly postoperative patient is in a sleeping state, record the displacement data of the sensor at each recording node, and aggregate the acquired displacement data to generate a sensor displacement data set;

[0083] Step 202: Generate the displacement degree of the sensor from the sensor displacement data set , where the shortest distance between the real-time position of the sensor and the target position is taken as the displacement. Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0084] ;

[0085] in, is the number of displacements, It is i The displacement of each node is recorded. is the average displacement value, is the acceptable value of displacement, weight coefficient: , ,and ;The weight coefficient can be obtained by referring to the hierarchical analysis method;

[0086] To obtain the displacement Mark each sensor. If the average displacement of the sensor If it does not exceed expectations, it means that the displacement of the smart underwear is low and the accuracy of various data such as ECG signals is high. At this time, a scene test command is issued to the outside;

[0087] If the average displacement of the sensor If the sensor position exceeds expectations, the sensor displacement should be minimized to ensure the accuracy and stability of the data collection point;

[0088] When in use, after the patient falls asleep, the relative position changes of the sensors of the smart underwear are recorded, and the displacement degree is constructed based on the relative changes and displacement data. , according to the displacement Determine the displacement degree of the sensor. If the displacement degree of the sensor is high, the accuracy of the data collected by the sensor network may be affected in this usage scenario. At this time, by improving the stability of the sensor, the stability of the collected data can be improved.

[0089] Step 203: After receiving the scene test instruction, several test scenes are pre-set for the smart underwear, such as poor sleep quality and large fluctuations in environmental conditions;

[0090] Test the data collection process of the smart underwear in a preset usage scenario, test the accuracy of the smart underwear in collecting ECG signals, and aggregate the ECG signal data collected by the smart underwear to generate a scenario test data set;

[0091] When using, combine the contents in steps 201 to 203:

[0092] When the accuracy of the collected data may be insufficient, actual scenario testing can be used to verify the accuracy and reliability of the data collected by the smart underwear, facilitating timely adjustments and processing.

[0093] Step 3: Generate data accuracy from the scene test data set If the data accuracy Not less than expected, set different working modes for smart underwear, and switch its working mode according to the changes in the usage scenarios of smart underwear;

[0094] The step three includes the following contents:

[0095] Step 301: The deviation ratio between the monitored value and the true value in the scene test data set is used as the deviation ratio. Data accuracy when generating smart underwear for data collection , where the deviation ratio Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0096] ;

[0097] in, is the number of test nodes, It is i The deviation ratio of the test nodes, is the average value of the deviation ratio, is the acceptable value of the deviation ratio; weight coefficient: , ,and ;The weight coefficient can be obtained by referring to the hierarchical analysis method;

[0098] Pre-set accuracy thresholds based on historical data and performance management expectations for smart underwear;

[0099] If the data accuracy of smart underwear in different test scenarios The mean value of is lower than the accuracy threshold, indicating that the data accuracy of the smart underwear may be insufficient when collecting data from elderly patients undergoing surgery in a sleeping state. At this time, an adjustment instruction is issued to the outside.

[0100] After receiving the adjustment instruction, the electrode sensitivity and signal processing algorithm are adjusted according to the test results to improve the accuracy of data collection by the smart underwear;

[0101] When using, when testing the smart underwear in different test scenarios, the data accuracy generated by different test data , based on data accuracy Ability to judge the reliability of smart underwear during operation and the accuracy of data When it is insufficient, the reliability of data collection of the smart underwear can be guaranteed by optimizing adjustment and signal processing, so as to form effective feedback on the rehabilitation process of elderly patients after heart disease surgery in the rehabilitation area;

[0102] Step 302: according to historical data and management expectations of the working mode of the smart underwear, different working modes are set for the smart underwear, including full load, medium load and low load, so as to extend the battery life by switching the working mode of the smart underwear;

[0103] After the smart underwear enters the working state, the working mode of the smart underwear is switched according to the changes in environmental conditions or the changes in sleep quality, and the sleeping environment threshold is set for the smart underwear. , as follows:

[0104] ;

[0105] in, , Environmental sleep ratio The number of is the environmental sleep ratio, specifically the ratio of the environmental condition coefficient to the sleep quality score; For the i The ambient sleep ratio within the monitoring cycle, is the mean of the ambient sleep ratio;

[0106] If the patient's environmental sleep ratio Below the sleeping environment threshold , the smart underwear enters full-load operation; if the patient's ambient sleep is Above the sleeping environment threshold , the smart underwear enters the medium load operation state; if the patient's ambient sleep ratio is Threshold of sleeping environment Inside, the smart underwear enters a low-load operating state;

[0107] When using, combine the contents in steps 301 and 302:

[0108] Different working modes are set for the smart underwear. When the smart underwear is in use, the working mode is switched according to changes in environmental conditions and sleep quality. Under different working modes, the smart underwear collects data at different frequencies, and the actual energy consumption also varies to a certain extent. A balance is achieved between usage scenarios and energy consumption to extend the usage time of the smart underwear.

[0109] Step 4: The smart underwear collects data from elderly patients after surgery. If the encryption trigger condition is met, the collected data is encrypted, and after decryption at the data receiving end, the trained abnormal indicator recognition model is used for identification. If there is an abnormal ECG signal, the smart underwear sends an alarm command to the outside.

[0110] The step 4 includes the following contents:

[0111] Step 401: After selecting a corresponding working mode for the smart underwear, the sensor network of the smart underwear collects ECG and related data from the elderly postoperative patient under the selected working mode, pre-processes the acquired ECG data of the patient, and obtains pre-processed data;

[0112] Step 402: After obtaining the amount of patient ECG data in the current encryption period, generate the encryption density in the following manner under dimensionless conditions: :

[0113] ;

[0114] Weight coefficient, , ;The weight coefficient can be obtained by referring to the hierarchical analysis method; is the number of times the patient's ECG data is received within the encryption period. It is i The first received j The difference in the amount of data received each time, is the average value of the data volume gap;

[0115] The encryption density obtained When the encryption trigger condition is reached beyond the expectation, the corresponding encryption method is selected to encrypt the collected data, and the corresponding key is sent to the data receiving end;

[0116] When in use, after the smart underwear completes the staged data collection and monitoring of the patient, it determines whether the collected data needs to be encrypted. When the encryption trigger conditions are met, the collected data is encrypted to avoid the loss and leakage of key data, and the security of the acquired data can be guaranteed;

[0117] Step 403: When the encrypted patient ECG data is received at the data receiving end, it is decrypted according to the corresponding key, and a neural convolution network is trained with the labeled sample data to obtain a trained abnormal index recognition model;

[0118] The decrypted patient ECG data is used as input, and the trained abnormal indicator recognition model is used for recognition, and the recognized abnormal ECG signals are output, such as abnormal heart rate, heart rate variability, etc. After the abnormal ECG signals are recognized, the smart underwear sends an alarm command to the outside.

[0119] When used, combine the contents in steps 401 to 403:

[0120] After receiving the encrypted data and decrypting it, the trained abnormal indicator recognition model is used to identify it. If there is an abnormal ECG signal or similar abnormal information, an alarm instruction can be issued in time;

[0121] After patients and medical management personnel in the rehabilitation area receive the alarm command, they can deal with any abnormalities in the patient's rehabilitation process in a timely manner to ensure the patient's rehabilitation process.

[0122] Step 5: After extracting features from the ECG data of elderly patients after surgery, the knowledge graph of postoperative rehabilitation intervention is used to match the corresponding intervention plan, and the alarm density is generated based on the time node when the alarm command is received. , if the alarm density Exceeding expectations, the collected ECG data was uploaded to the medical platform;

[0123] The step five includes the following contents:

[0124] Step 501: extract features from the received patient ECG data through feature engineering to obtain corresponding intervention features; take rehabilitation intervention for elderly patients after heart surgery as the target word, and pre-build a knowledge graph of patient postoperative rehabilitation intervention after deep retrieval and entity relationship building;

[0125] After receiving the alarm command, according to the correspondence between the intervention characteristics and the intervention plan, the patient's postoperative rehabilitation intervention knowledge map provides a corresponding intervention plan for the elderly postoperative patients;

[0126] When in use, when the patient's current rehabilitation status may be abnormal, based on the collected data, the patient's postoperative rehabilitation intervention knowledge map will provide a corresponding intervention plan for the elderly postoperative patient. Based on the intervention plan as a reference, when the patient's body has abnormalities, targeted treatment can be carried out in a timely manner to achieve intervention and protection of the patient's rehabilitation process;

[0127] Step 502: after receiving a number of alarm instructions continuously within a preset observation period, generate an alarm density according to the time node of receiving the alarm instruction. ,in,

[0128] ;

[0129] Weight coefficient: , ,and , the weight coefficient remains the same as the previous value; is the number of alarm instructions, It is i Alarm command to j The time interval between alarm instructions. is the average value of the time interval, is the acceptable value for the time interval;

[0130] Based on historical data and rehabilitation management of elderly postoperative patients, the density threshold is pre-set; if the alarm density If the density threshold is exceeded, it means that the recovery status of the elderly patients undergoing heart surgery in the recovery area may be abnormal. At this time, an intervention instruction is issued to the outside.

[0131] After receiving the intervention instruction, the ECG data continuously collected by the smart underwear will be uploaded to the medical platform and received by the matching doctor, thus realizing the doctor's remote monitoring and diagnosis;

[0132] When using, combine the contents in steps 501 and 502:

[0133] After receiving several alarm instructions continuously during the observation period, the alarm density is generated. , when there are problems in the patient's recovery process, according to the alarm density It can judge and evaluate the severity of the patient's current abnormal recovery. In this case, on the basis of completing the collection of the patient's ECG signals and related data, with the assistance of smart underwear, it can guide the intervention of medical staff and provide timely treatment to patients with abnormal recovery status. Smart underwear can also increase the protection of elderly postoperative patients who enter the sleep state.

[0134] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0135] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0136] The method of constructing a knowledge graph of rehabilitation intervention for elderly patients after cardiac surgery can refer to the following:

[0137] First of all, it is necessary to clarify the goal of constructing the knowledge graph, which is to assist in intervention decisions for postoperative cardiac rehabilitation in the elderly, improve rehabilitation outcomes, reduce complications, and improve patients' quality of life.

[0138] Clinical guidelines and literature: Collect the latest clinical guidelines, research papers and review articles on postoperative rehabilitation of the elderly after cardiac surgery at home and abroad. These documents are important data sources for constructing knowledge graphs.

[0139] Hospital database: Utilize the hospital’s patient database to obtain rehabilitation data of elderly patients after cardiac surgery, including rehabilitation process, effect evaluation, etc.

[0140] Expert interviews: Invite experts in the fields of cardiac surgery, rehabilitation medicine, etc. to conduct interviews to obtain their professional knowledge and experience.

[0141] Entity extraction: Automatically or semi-automatically extract entities related to postoperative rehabilitation of the elderly after cardiac surgery from the data source, such as rehabilitation programs (aerobic exercise, strength training, flexibility training, etc.), drugs (antihypertensive drugs, anticoagulants, etc.), complications (arrhythmia, heart failure, etc.), patient information, etc.

[0142] Relation extraction: Identify semantic relationships between entities, such as “rehabilitation program – helps – reduce complications”, “drug – used to treat – heart disease”, etc.

[0143] Attribute extraction: For each entity, extract its attribute information, such as the frequency, intensity, and duration of rehabilitation programs, the dosage and usage of drugs, etc.

[0144] Entity alignment: Solve the problem of inconsistent entity names in different data sources and ensure that the same entity can be correctly matched in different data sources.

[0145] Attribute value filling: For different attribute values ​​of the same entity, decisions are made based on the reliability and authority of the data source, and the most accurate attribute value is selected for filling.

[0146] Ontology construction: Based on the extracted knowledge, the ontology of rehabilitation intervention after cardiac surgery for the elderly is constructed, including concepts such as rehabilitation programs, drugs, complications, and the relationships between them.

[0147] Model layer construction: Based on the ontology construction, the model layer of the knowledge graph is constructed to form a well-structured concept hierarchy tree.

[0148] Quality assessment: Perform quality assessment on the constructed knowledge graph to ensure the accuracy and completeness of the knowledge.

[0149] See also Figure 2 The present invention provides an electrocardiogram signal monitoring system for smart underwear, comprising:

[0150] The environmental analysis unit monitors and obtains environmental condition data in the rehabilitation area, aggregates the data and generates an environmental monitoring data set, which in turn generates an environmental condition coefficient. , if the environmental condition coefficient Exceed expectations, identify the current sleep quality of elderly postoperative patients, and send a displacement test instruction to the outside if their sleep quality is lower than expected;

[0151] The scene test unit generates a sensor displacement data set from the recorded sensor displacement data. If the average displacement of the sensor Without exceeding expectations, the data collection process of the smart underwear is tested in the preset usage scenarios, and the test data is aggregated to generate a scenario test data set;

[0152] Model adjustment unit, generates data accuracy from scene test data set If the data accuracy Not less than expected, set different working modes for smart underwear, and switch its working mode according to the changes in the usage scenarios of smart underwear;

[0153] The alarm unit uses the smart underwear to collect data from elderly patients after surgery. If the encryption trigger condition is met, the collected data is encrypted and decrypted at the data receiving end. The trained abnormal indicator recognition model is used for identification. If there is an abnormal ECG signal, the smart underwear sends an alarm command to the outside.

[0154] The emergency intervention unit extracts features from the ECG data of elderly patients after surgery, matches the corresponding intervention plan with the patient's postoperative rehabilitation intervention knowledge graph, and generates an alarm density based on the time node when the alarm command is received. , if the alarm density Exceeding expectations, the collected ECG data was uploaded to the medical platform.

[0155] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can 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 can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can 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 can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can 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 can be a solid-state hard disk.

[0156] 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.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] 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.

[0160] 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.

[0161] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, 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, server, or network device, etc.) to perform all or part of the steps of the method 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, and other media that can store program codes.

[0162] 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 monitoring electrocardiogram signals of smart underwear, characterized in that: include, Monitor and obtain environmental condition data in the rehabilitation area, aggregate them to generate an environmental monitoring data set, and generate environmental condition coefficients from the environmental monitoring data set , if the environmental condition coefficient Exceed expectations, identify the current sleep quality of elderly postoperative patients, and send a displacement test instruction to the outside if their sleep quality is lower than expected; The sensor displacement data set is generated by recording the sensor displacement data. If the average displacement of the sensor is Without exceeding expectations, the data collection process of the smart underwear is tested in the preset usage scenarios, and the test data is aggregated to generate a scenario test data set; Data accuracy generated by the scene test data set If the data accuracy Not less than expected, set different working modes for smart underwear, and switch its working mode according to the changes in the usage scenarios of smart underwear; The smart underwear collects data from elderly patients after surgery. If the encryption trigger condition is met, the collected data is encrypted and decrypted at the data receiving end. The trained abnormal indicator recognition model is used for identification. If there is an abnormal ECG signal, the smart underwear sends an alarm command to the outside. After extracting features from the ECG data of elderly patients after surgery, the corresponding intervention plan is matched with the patient's postoperative rehabilitation intervention knowledge graph, and the alarm density is generated according to the time node when the alarm command is received. , if the alarm density Exceeding expectations, the collected ECG data was uploaded to the medical platform.

2. The method for monitoring ECG signals of smart underwear according to claim 1, characterized in that: Data collection points are set up in the rehabilitation area to monitor environmental conditions at each monitoring node and obtain corresponding environmental condition data, which are then aggregated to generate an environmental monitoring data set; Generate environmental condition coefficients from environmental condition data in the environmental monitoring data set , if the environmental condition coefficient When the condition threshold is exceeded, a sleep quality recognition instruction is issued to the outside.

3. The method for monitoring ECG signals of smart underwear according to claim 2, characterized in that: Temperature in the recovery area ,humidity and noise Perform linear normalization and map the corresponding data values ​​to the interval The environmental condition coefficient is generated as follows : ； Weight coefficient: , , , ; For the The temperature of each monitoring node, is the acceptable value of temperature, is the mean temperature; For the The humidity of each monitoring node, is the acceptable value of humidity, is the mean humidity; For the The noise of the monitoring nodes, is the acceptable value of noise, is the mean of the noise.

4. The method for monitoring ECG signals of smart underwear according to claim 3, characterized in that: After receiving the sleep quality recognition instruction, the patient's sleep quality data is continuously collected, and the collected sleep quality data is used as input to use the trained sleep quality assessment model to identify the current sleep quality score of the elderly postoperative patient. If the sleep quality score obtained by recognition is lower than expected, a displacement test instruction is issued to the outside. After receiving the displacement test instruction, when the elderly postoperative patient is in a sleeping state, the displacement data of the sensor at each recording node is recorded, and the acquired displacement data is aggregated to generate a sensor displacement data set.

5. The method for monitoring ECG signals of smart underwear according to claim 4, characterized in that: Generate the displacement degree of the sensor from the sensor displacement data set , to obtain the displacement Mark each sensor. If the average displacement of the sensor Not exceeding expectations, issuing scenario testing instructions to external parties; If the average displacement of the sensor If it exceeds expectations, adjust the position of the sensor; After receiving the scenario test instruction, the data collection process of the smart underwear is tested in the preset usage scenario, and the ECG signal data collected by the smart underwear is summarized to generate a scenario test data set.

6. The method for monitoring ECG signals of smart underwear according to claim 5, characterized in that: The shortest distance between the real-time position of the sensor and the target position is taken as the displacement. Perform linear normalization and map the corresponding data values ​​to the interval The displacement of the sensor is generated as follows : ； in, is the number of displacements, It is The displacement of each node is recorded. is the average value of displacement, is the acceptable value of displacement, weight coefficient: , ,and .

7. The method for monitoring ECG signals of smart underwear according to claim 6, characterized in that: The deviation ratio between the monitored value and the true value in the scene test data set is used as the deviation ratio , by the deviation ratio Data accuracy when generating smart underwear for data collection , if the data accuracy of smart underwear in different test scenarios When the mean value is lower than the accuracy threshold, an adjustment instruction is issued to the outside.

8. The method for monitoring ECG signals of smart underwear according to claim 7, characterized in that: Deviation ratio Perform linear normalization and map the corresponding data values ​​to the interval The data accuracy is generated as follows : ； in, is the number of test nodes, It is The deviation ratio of the test nodes is is the average value of the deviation ratio, is the acceptable value of the deviation ratio; weight coefficient: , ,and .

9. The method for monitoring ECG signals of smart underwear according to claim 8, characterized in that: After the smart underwear enters the working state, set the sleeping environment threshold for the smart underwear , set different working modes for smart underwear, according to the environment sleep ratio Sleeping environment threshold The working mode is switched by the relationship as follows: ； in, , Environmental sleep ratio The number of Environmental sleep ratio, specifically the ratio of the environmental condition coefficient to the sleep quality score; For the The ambient sleep ratio within the monitoring cycle, is the mean of the ambient sleep ratio.

10. The method for monitoring ECG signals of smart underwear according to claim 9, characterized in that: In the selected working mode, the sensor network of the smart underwear collects ECG and related data from elderly patients after surgery, pre-processes the acquired ECG data of the patients, and obtains the pre-processed data; Obtain the amount of patient ECG data in the current encryption cycle and generate the encryption density ; The encryption density obtained When the encryption trigger condition is reached beyond the expected time, the corresponding encryption method is selected to encrypt the collected data, and the corresponding key is sent to the data receiving end; wherein, the encryption key is generated in the following manner : ； Weight coefficient, , ; is the number of times the patient's ECG data is received within the encryption period. It is The first received The difference in the amount of data received each time, is the average value of the data volume difference.

11. The method for monitoring ECG signals of smart underwear according to claim 10, characterized in that: When the encrypted patient ECG data is received at the data receiving end, it is decrypted according to the corresponding key, and the decrypted patient ECG data is used as input. The trained abnormal indicator recognition model is used for recognition, and the recognized abnormal ECG signal is output. After the abnormal ECG signal is recognized, the smart underwear sends an alarm command to the outside.

12. The method for monitoring ECG signals of smart underwear according to claim 11, characterized in that: Extract features from the received patient ECG data to obtain corresponding intervention features; take rehabilitation intervention for elderly patients after heart surgery as the target word and pre-build a knowledge graph of postoperative rehabilitation intervention for patients; After receiving the alarm command, based on the correspondence between the intervention characteristics and the intervention plan, the patient's postoperative rehabilitation intervention knowledge map provides a corresponding intervention plan for the elderly postoperative patients.

13. The method for monitoring ECG signals of smart underwear according to claim 12, characterized in that: After receiving several alarm instructions continuously within the preset observation period, the alarm density is generated according to the time node of receiving the alarm instruction. , if the alarm density When the density threshold is exceeded, the ECG data collected continuously by the smart underwear will be uploaded to the medical platform, where: ； Weight coefficient: , ,and ; is the number of alarm instructions, It is Alarm command to The time interval between alarm instructions. is the average value of the time interval, Acceptable values ​​for the time interval.

14. An electrocardiogram signal monitoring system for smart underwear, characterized in that: include, The environmental analysis unit monitors and obtains environmental condition data in the rehabilitation area, aggregates the data and generates an environmental monitoring data set, which in turn generates an environmental condition coefficient. , if the environmental condition coefficient Exceed expectations, identify the current sleep quality of elderly postoperative patients, and send a displacement test instruction to the outside if their sleep quality is lower than expected; The scene test unit generates a sensor displacement data set from the recorded sensor displacement data. If the average displacement of the sensor Without exceeding expectations, the data collection process of the smart underwear is tested in the preset usage scenarios, and the test data is aggregated to generate a scenario test data set; Model adjustment unit, generates data accuracy from scene test data set If the data accuracy Not less than expected, set different working modes for smart underwear, and switch its working mode according to the changes in the usage scenarios of smart underwear; The alarm unit uses the smart underwear to collect data from elderly patients after surgery. If the encryption trigger condition is met, the collected data is encrypted and decrypted at the data receiving end. The trained abnormal indicator recognition model is used for identification. If there is an abnormal ECG signal, the smart underwear sends an alarm command to the outside. The emergency intervention unit extracts features from the ECG data of elderly patients after surgery, matches the corresponding intervention plan with the patient's postoperative rehabilitation intervention knowledge graph, and generates an alarm density based on the time node when the alarm command is received. , if the alarm density Exceeding expectations, the collected ECG data was uploaded to the medical platform.

Images