A blood pressure management system, method and device based on dynamic environment perception

Abstract

The application discloses a blood pressure management system based on dynamic environment perception, comprising: an environment perception module for real-time monitoring of environmental parameters including temperature, humidity, air pressure, noise, and optimizing and adjusting the measurement environment to the specified state through multi-parameter coupling compensation and linkage of the external environment adjustment system; a data processing and control module for deep processing and analysis of the collected data, and making control decisions according to the analysis results to realize accurate management and monitoring of blood pressure; a blood pressure measurement and interaction module for executing blood pressure measurement operation and feeding back the measurement results to the user. The application adjusts the measurement parameters in real time by integrating environment perception technology to adapt to different environmental conditions, thereby improving the accuracy of blood pressure measurement, and enabling the device to perceive and adapt to various environmental changes, ensuring accurate blood pressure monitoring in various environments.

Description

Technical Field

[0001] This invention relates to the field of intelligent blood pressure management technology, specifically to a blood pressure management system, method, and device based on dynamic environmental perception. Background Technology

[0002] Intelligent blood pressure management is an interdisciplinary field integrating medicine, electronic engineering, and artificial intelligence, focusing on improving the convenience, accuracy, and efficiency of blood pressure monitoring through technological innovation. With an aging population and rising incidence of chronic diseases, intelligent blood pressure management technology is receiving increasing attention globally, becoming a key means of preventing cardiovascular disease and improving public health.

[0003] The latest technologies in the field of intelligent blood pressure management mainly include:

[0004] (1) Ambulatory blood pressure monitoring technology: Through wearable devices, blood pressure can be monitored continuously for 24 hours, capturing blood pressure fluctuations more accurately, which is especially helpful in detecting masked hypertension and nocturnal hypertension;

[0005] (2) Artificial intelligence application: Use AI technology to improve the accuracy of blood pressure measurement, such as by analyzing pulse sounds to measure blood pressure more accurately, and maintain high accuracy even in complex situations;

[0006] (3) New wearable blood pressure measurement devices: Combining fashion and function, such as blood pressure monitoring devices in the form of smartwatches, which are convenient for users to wear daily and achieve unobtrusive monitoring;

[0007] (4) Remote monitoring and data management: By combining the Internet and big data technologies, blood pressure data can be remotely transmitted and intelligently managed, which facilitates real-time monitoring and adjustment of treatment plans by doctors and patients.

[0008] While existing intelligent blood pressure management technologies have made some progress, they still have shortcomings. Many existing wearable blood pressure monitoring devices are still insufficient in measurement accuracy, especially during dynamic monitoring or environmental changes. They easily overlook the potential impact of environmental factors on blood pressure readings, and the measurement results may be interfered with, leading to possible deviations. Moreover, existing blood pressure monitoring devices often cannot adapt well to different environmental conditions, such as temperature changes, humidity, and noise, which may affect the accuracy of the measurement results. In addition, traditional blood pressure monitors lack personalized measurement schemes, cannot adjust measurement parameters according to the user's specific situation, and usually do not have the ability to monitor and analyze data in real time.

[0009] Therefore, this application proposes a blood pressure management system based on dynamic environment perception to solve the above-mentioned technical problems. Summary of the Invention

[0010] The main objective of this invention is to provide a blood pressure management system based on dynamic environmental perception. By integrating environmental perception technology, the system adjusts measurement parameters in real time to adapt to different environmental conditions, thereby improving the accuracy of blood pressure measurement and enabling the device to sense and adapt to various environmental changes, ensuring accurate blood pressure monitoring in various environments, thus solving the technical problems mentioned in the background art.

[0011] The present invention solves the above-mentioned technical problems by adopting the following technical solutions:

[0012] A blood pressure management system based on dynamic environment perception includes:

[0013] The environmental sensing module is used to monitor environmental parameters, including temperature, humidity, air pressure, and noise, in real time, and optimize and adjust the measured environment to a specified state through multi-parameter coupling compensation and linkage with the external environmental adjustment system.

[0014] The data processing and control module is used to perform in-depth processing and analysis of the collected data, and make control decisions based on the analysis results in order to achieve precise management and monitoring of blood pressure.

[0015] The blood pressure measurement and interaction module is used to perform blood pressure measurement operations and feed the measurement results back to the data processing and control module and the user.

[0016] Preferably, the control logic of the dynamic environment perception module for multi-parameter coupling compensation and linkage control of the external environment includes:

[0017] When the temperature is greater than 28℃ and the humidity is greater than 80%, a comprehensive compensation strategy of vasodilator compensation factor γ1 × blood viscosity correction coefficient γ2 is used to compensate for the blood pressure measurement result δ0, thus obtaining the blood pressure measurement result δ. l For: δ l =δ0×γ1×γ2;

[0018] When noise > 70dB and illumination > 1500 lux, activate the dual-channel filtering algorithm to eliminate artifact signals;

[0019] An environmental compensation system is constructed, which generates the Environmental Interference Index (EEI) in real time based on the ISO 81060-3 standard certification. When the EEI > 0.85, an environmental adjustment command is automatically triggered, which links the external environmental adjustment system to adjust the measured environment to the specified state.

[0020] Preferably, the data processing and control module is internally configured with:

[0021] The data receiving and preprocessing unit is used to receive real-time data from the environmental sensing module and the blood pressure measurement and interaction module, and to perform data preprocessing operations.

[0022] The data processing and control unit is used to perform multi-source data fusion and correction of environmental parameters and physiological data. By dynamically sensing environmental parameters and user physiological signals, it dynamically corrects the raw blood pressure value, thereby eliminating environmental interference and outputting an optimized blood pressure value (BP). adj Furthermore, an adaptive algorithm framework based on Kalman filtering is constructed to achieve noise suppression through a state-space model;

[0023] The data analysis and prediction unit is used to analyze and extract specified information from environmental and blood pressure data, and combine it with historical data for deep learning to predict blood pressure changes.

[0024] Preferably, the specific operation procedure for multi-source data fusion and correction by the data processing and control unit includes:

[0025] a1. By dynamically sensing environmental parameters including temperature, humidity, air pressure, noise, and light intensity, an environmental feature matrix E is generated for a time period t. t ,have:

[0026] E t =[T t H t ,P t N t ,L t ]

[0027] Among them, T t For temperature parameters, H t P is a humidity parameter. t For air pressure parameters, N t L is a noise parameter. t These are the lighting parameters;

[0028] a2. Model environmental impact factors and train weight coefficients w based on historical datasets using multiple linear regression or random forest algorithms. i To minimize the correction error, we have:

[0029] min∑(BP true -(BP raw -∑w i ·ΔE i )) 2

[0030] ΔE i =E i,current -E i,baseline

[0031] Among them, BP true For periodically collected blood pressure calibration values, BP raw The original blood pressure value, ΔE iE represents the error between actual and ideal environmental parameters. i,current For actual environmental parameters, E i,baseline These are the parameters for an ideal environment.

[0032] a3. During the blood pressure calibration and validation process, the calibration amplitude k is dynamically adjusted based on the individual age differences of the blood pressure test subjects to obtain the optimized blood pressure value BP. adj ,have:

[0033]

[0034] Where age represents age and β is the decay factor, which is obtained by fitting historical data of the user whose blood pressure was measured.

[0035] Preferably, the specific operation procedure for training the weight coefficients using multiple linear regression in step a2 includes: setting random small values ​​as initial regression coefficients, iteratively optimizing using gradient descent, calculating the gradient of the loss function with respect to the regression coefficients, and updating the coefficients in the opposite direction of the gradient until the loss function converges to its minimum value, thereby determining the optimal weight coefficient w. i .

[0036] Preferably, the specific operation process of training the weight coefficients using the random forest algorithm in step a2 includes: determining the number of decision trees based on the dataset size and computing resources, then constructing multiple decision trees by sampling with replacement and training them, and finally obtaining the final predicted optimal weight coefficient w from the results of the decision trees. i .

[0037] Preferably, the specific operation process of the data analysis and prediction unit performing deep learning includes:

[0038] b1. Based on time-series environmental data E t The time-corrected blood pressure value (BP) adj,t And archive data containing user health information, to build an LSTM prediction model;

[0039] b2. The input layer of the LSTM prediction model receives the timing data window [E] t-n BP adj,t-n ,…,E t BP adj,t The data is then sampled using a sliding window, where the window size n is set to 6 to represent the data from the past hour.

[0040] b3. Set up two stacked LSTM layers in the LSTM prediction model, with 64 neurons in each layer, and add Dropout=0.2 to prevent overfitting;

[0041] b4. Output the predicted blood pressure (BP) at future time point t+1 through a fully connected layer.pred Furthermore, the environmental adjustment strategy is optimized through an auxiliary fitness function.

[0042] Preferably, the specific training process of the LSTM prediction model includes:

[0043] Historical data is augmented using a sliding window sampling method, and Gaussian noise σ = 1 mmHg is added to improve the model's generalization ability. The loss function Γ is then defined as follows:

[0044]

[0045] Among them, BP pred,i Let BP be the predicted blood pressure value for the i-th time. ture,i Let λ be the blood pressure calibration value collected periodically for the i-th time, and λ be the intensity adjustment value of L2 regularization;

[0046] For user health profiles, freeze the underlying parameters of the LSTM and train only the top fully connected layer to obtain the auxiliary function:

[0047]

[0048] Among them, BP adj For the optimized blood pressure value, BP true For periodically collected blood pressure calibration values, ΔE i BP is the error between actual and ideal environmental parameters. target The target blood pressure range set by the user;

[0049] |BP in auxiliary functions adj -BP ture |、∑ i |ΔE i |、|BP pred -BP target | represent measurement error, environmental adjustment cost, and trend deviation, respectively. λ1, λ2, and λ3 represent the adjustable influencing factors of measurement error, environmental adjustment cost, and trend deviation, respectively, and λ1+λ2+λ3=1.

[0050] In another aspect, the present invention also discloses a blood pressure management method, which uses any of the above-described dynamic environment-aware blood pressure management systems to perform operations, including:

[0051] The environmental sensing module monitors environmental information in real time and regulates the environment, then transmits the data to the data processing and control module.

[0052] The data processing and control module adjusts the blood pressure measurement strategy based on environmental data, and then sends the instructions to the blood pressure measurement and interaction module;

[0053] The blood pressure measurement and interaction module controls the execution of blood pressure measurement operations and provides feedback to the user.

[0054] Furthermore, the present invention also discloses a blood pressure management device, characterized in that it includes an interactive interface, a processor, a blood pressure monitor body, a cuff, and a measuring sensor, wherein:

[0055] The user interface, the main body of the blood pressure monitor, and the measurement sensors are all connected to the processor.

[0056] The interactive interface and cuff are both located on the main body of the blood pressure monitor, which is used to contact the user to perform blood pressure measurement.

[0057] The processor includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform method steps for blood pressure management and detection based on any of the systems described above.

[0058] As can be seen from the above technical solution, the present invention provides a blood pressure management system based on dynamic environment perception. Compared with the prior art, the present invention has the following advantages:

[0059] 1. This invention can monitor environmental parameters such as temperature, humidity, air pressure, and noise in real time and link with the external environmental adjustment system to actively optimize the measurement environment, thereby eliminating the negative impact of environmental interference factors on blood pressure measurement and ultimately improving the accuracy of blood pressure measurement.

[0060] 2. This invention can perform multi-dimensional analysis by integrating environmental parameters and user physiological signals. At the same time, it can accurately correct the original blood pressure value through multiple linear regression, random forest algorithm and age difference dynamic adjustment strategy, thereby improving the reliability and personalization of blood pressure data, and ultimately achieving precise and scientific blood pressure management.

[0061] 3. This invention can predict blood pressure change trends and balance measurement errors, environmental adjustment costs, and trend deviations, thereby improving the resource utilization efficiency of health management and achieving proactive blood pressure risk prevention and control.

[0062] 4. By integrating an interactive interface, processor, and sensor into a blood pressure management device, and incorporating an adaptive algorithm and environmental adjustment linkage mechanism, this invention can provide real-time, accurate, and personalized blood pressure monitoring and environmental optimization functions, thereby enhancing the convenience and effectiveness of user health management and ultimately significantly improving the quality of life for hypertensive patients.

[0063] It should be understood that the descriptions in this section are not intended to identify key or essential features of embodiments of the invention, nor are they intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Of course, implementing any product of the invention does not necessarily require achieving all of the advantages described above simultaneously. Attached Figure Description

[0064] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0065] Figure 1 This is a block diagram of the overall system structure of the present invention;

[0066] Figure 2 This is a block diagram of the internal structure of the data processing and control module of the present invention. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] For details in the embodiments, please refer to Figures 1 to 2 .

[0069] like Figure 1 As shown in the embodiment of the present invention, a blood pressure management system based on dynamic environmental perception includes an environmental perception module, a data processing and control module, and a blood pressure measurement and interaction module. These modules cooperate to form a closed-loop control system. Specifically:

[0070] (1) Environmental sensing module, used to monitor environmental parameters (temperature, humidity, air pressure, noise, etc.) in real time, provide environmental data support for blood pressure measurement, and optimize and adjust the measurement environment to the specified state through multi-parameter coupling compensation and linkage with the external environmental adjustment system.

[0071] At this point, the dynamic environment perception module serves as the environmental data hub of the blood pressure management system. Its core function is to determine the complex influence mechanism of environmental physiology on blood pressure measurement through multi-dimensional environmental parameter monitoring, and to identify the different action paths and quantitative effects of each environmental parameter on blood pressure measurement.

[0072] The dynamic environment sensing module significantly improves the accuracy of blood pressure measurement through precise monitoring range and advanced algorithm compensation.

[0073] Regarding temperature parameters, the monitoring range is 10-40℃±0.5℃. Ambient temperature directly affects peripheral vascular tension through the thermal regulation system.

[0074] When the temperature is above 28℃, the rate of skin vasodilation increases by 30%, which leads to a redistribution of blood volume, resulting in a decrease in systolic blood pressure of 5-10 mmHg and a decrease in diastolic blood pressure of 3-5 mmHg. When the temperature is below 18℃, sympathetic nerve excitation increases catecholamine secretion by 40%, leading to falsely high blood pressure readings. Electronic blood pressure monitors without temperature compensation have a measurement error of ±8 mmHg at 32℃, while the temperature compensation algorithm in this module can effectively control the error within ±2 mmHg. The humidity monitoring range is 20-90%RH ±3%.

[0075] When the relative humidity is greater than 70%, the high humidity environment will increase the blood viscosity by 8%, which will indirectly affect the calculation of pulse wave conduction velocity. For every 10% increase in humidity, the standard deviation of the ambulatory blood pressure monitor will increase by 0.7 mmHg. During the rainy season (humidity 85-95%), a special filtering algorithm needs to be activated to maintain measurement accuracy.

[0076] The monitoring range for barometric pressure parameters is 300-1100 hPa ± 1.5%; for every 100 meters increase in altitude (barometric pressure decreases by 12 hPa), blood oxygen saturation decreases by 1.2%, triggering a compensatory increase in heart rate of 5-10 bpm; this module can automatically correct altitude-related errors through a built-in barometric pressure-altitude conversion model, and the accuracy of blood pressure measurement can be improved by 23% in a 3000-meter high-altitude environment.

[0077] The noise parameter monitoring range is 30-90dB±2dB. When the ambient noise is above 65dB, the cortisol level increases by 35%, resulting in instantaneous systolic blood pressure fluctuations of 10-15mmHg. This module adopts adaptive noise reduction technology, which can still ensure measurement stability of ±1.5mmHg even in a subway environment with 80dB noise.

[0078] The monitoring range of light parameters is 0-2000 lux ± 5%. Strong light (>1000 lux) affects the circadian rhythm through the suprachiasmatic nucleus, which will reduce the drop in blood pressure at night by 8 mmHg. The module is equipped with an intelligent light adaptation system, which can dynamically adjust the measurement time window according to the light intensity to ensure the rhythm accuracy of 24-hour ambulatory blood pressure monitoring.

[0079] Furthermore, this module innovatively constructs a multi-parameter coupled compensation algorithm: when the temperature is >28℃ and the humidity is >80%, a comprehensive compensation strategy of vasodilation compensation factor (γ1=1.15) × blood viscosity correction coefficient (γ2=0.93) is adopted to compensate for the blood pressure measurement result δ0, thus obtaining the blood pressure measurement result δ. l For: δ l =δ0×γ1×γ2;

[0080] When noise is greater than 70dB and light intensity is greater than 1500 lux, activating the dual-channel filtering algorithm can eliminate 12-15% of artifact signals. In actual use, after clinical application verification, after enabling environmental perception compensation, the standard deviation of daytime blood pressure measurement decreased from 8.7 mmHg to 3.2 mmHg, the accuracy of morning blood pressure peak detection increased by 42%, and the misjudgment rate of orthostatic hypotension decreased by 68%.

[0081] An environmental compensation system is constructed, which generates the Environmental Interference Index (EEI) in real time based on the ISO81060-3 standard certification. When the EEI > 0.85, an environmental adjustment command is automatically triggered, and the external environmental adjustment system is linked to adjust the measured environment to the specified ideal state (temperature 22±1℃, humidity 50±5%, noise <40dB).

[0082] This proactive environmental control enables high accuracy in blood pressure measurement, providing reliable environmental baseline data for personalized hypertension management.

[0083] Furthermore, it should be noted that in this way, the environmental sensing module provides comprehensive environmental information to the blood pressure management system, making blood pressure measurements more accurate and providing users with a more comfortable and suitable measurement environment.

[0084] The environmental perception module is the front end of the entire system. It provides real-time environmental data to the data processing and control module to ensure the accuracy of blood pressure measurement results.

[0085] Meanwhile, by setting up a dynamic environmental sensing module in the system, environmental parameters such as temperature, humidity, air pressure, and noise can be monitored in real time and linked with the external environmental adjustment system to actively optimize the measurement environment, thereby eliminating the negative impact of environmental interference factors on blood pressure measurement and ultimately improving the accuracy of blood pressure measurement.

[0086] (2) Data processing and control module, used to perform in-depth processing and analysis on the collected data, and make control decisions based on the analysis results, so as to achieve precise management and monitoring of blood pressure.

[0087] For details, please refer to Figure 2 The operation of this module can be divided into several key functional sub-units, specifically including:

[0088] (a) A data receiving and processing unit is used to receive real-time data from the environmental sensing module and blood pressure measurement, including sensor data such as ambient temperature, humidity, noise, air quality, and light intensity, as well as the user's blood pressure data. This data is usually transmitted to the processing module wirelessly, possibly through standard communication protocols such as Bluetooth or Wi-Fi.

[0089] The first step after receiving the data is preprocessing, which mainly includes noise removal, data verification, and format conversion to ensure the accuracy and consistency of the data.

[0090] (b) Data processing and control unit, used for multi-source data fusion and correction of environmental parameters and physiological data. By dynamically sensing environmental parameters and user physiological signals, it dynamically corrects the original blood pressure value, thereby eliminating environmental interference and outputting the optimized blood pressure value (BP). adj Furthermore, an adaptive algorithm framework based on Kalman filtering was constructed to achieve noise suppression through a state-space model.

[0091] At the data input end, the system uses a programmable analog filter to perform physical layer preprocessing on the raw signal: the temperature and humidity sensor channels are equipped with an eighth-order low-pass filter with a cutoff frequency of 0.1Hz to effectively filter out power frequency interference; the noise sensor uses a 20Hz-20kHz bandpass filter scheme to accurately match the characteristics of human hearing; and the optical sensor is equipped with an adaptive notch filter to dynamically eliminate 50 / 60Hz fluorescent lamp flicker noise.

[0092] Meanwhile, for the time-varying characteristics of dynamic environmental parameters, the system constructs an adaptive algorithm framework based on Kalman filtering, and achieves noise suppression through a state-space model.

[0093] Furthermore, the specific operational procedures for multi-source data fusion and correction in the data processing and control unit include:

[0094] a1. By dynamically sensing environmental parameters including temperature, humidity, air pressure, noise, and light, these data are collected by distributed temperature and humidity sensors, barometers, noise sensors, and light sensors. User physiological signals include body surface temperature and micro-expressions. Body surface temperature distribution is captured and analyzed by an infrared thermal imaging camera. After data collection, preprocessing is performed: first, Kalman filtering is used to eliminate sensor noise and achieve filtering and noise reduction; then, normalization is performed to map each parameter to a standard range, such as a temperature range of 0-1 corresponding to 10℃-40℃.

[0095] After these processes, the environmental feature matrix E for time period t is generated. t ,have:

[0096] E t =[Tt H t ,P t N t ,L t ]

[0097] Among them, T t For temperature parameters, H t P is a humidity parameter. t For air pressure parameters, N t L is a noise parameter. t These are the lighting parameters;

[0098] a2. Model environmental impact factors and train weight coefficients w based on historical datasets using multiple linear regression or random forest algorithms. i To minimize the correction error, we have:

[0099] min∑(BP true -(BP raw -∑w i ·ΔE i )) 2

[0100] ΔE i =E i,current -E i,baseline

[0101] Among them, BP true For periodically collected blood pressure calibration values, BP raw The original blood pressure value, ΔE i E represents the error between actual and ideal environmental parameters. i,current For actual environmental parameters, E i,baseline These are the parameters for an ideal environment.

[0102] Since the selection criteria for variables in the dataset are primarily based on their potential impact on blood pressure, environmental parameters such as temperature, humidity, air pressure, noise, and light intensity, which are associated with blood pressure, are retained. Other potential confounding variables are excluded if their correlation with blood pressure is statistically insignificant, or if they occur very infrequently and have minimal impact in actual measurement scenarios. For example, environmental factors specific to certain geographical locations that do not occur in typical usage scenarios can be excluded from the variables.

[0103] In practice, the specific steps for training weight coefficients using multiple linear regression include: setting random small values ​​as initial regression coefficients, iteratively optimizing using gradient descent, calculating the gradient of the loss function with respect to the regression coefficients, and updating the coefficients in the opposite direction of the gradient until the loss function converges to its minimum value, thereby determining the optimal weight coefficients w. i ;

[0104] In practice, the specific steps for training weight coefficients using the random forest algorithm include: determining the number of decision trees based on the dataset size and computing resources; constructing and training multiple decision trees by sampling with replacement; and finally, obtaining the optimal predicted weight coefficient w from the results of the decision trees. i This method can enhance the stability and generalization ability of the model;

[0105] a3. During the blood pressure calibration and validation process, the calibration amplitude k is dynamically adjusted based on the individual age differences of the blood pressure test subjects to obtain the optimized blood pressure value BP. adj ,have:

[0106]

[0107] Where age represents age and β is the decay factor, which is obtained by fitting historical data of the user whose blood pressure was measured.

[0108] Furthermore, regarding the dynamic adjustment of the correction amplitude based on individual user differences, the β value adjustment strategies for different age ranges and vascular elasticity indicators are as follows: For age factors, generally speaking, as age increases, vascular elasticity gradually decreases, and the sensitivity of blood pressure to environmental influences changes. Age can be divided into several intervals, such as under 30 years old, 30-50 years old, and over 50 years old. For people under 30 years old, physical function is relatively good, vascular elasticity is strong, and the impact of the environment on blood pressure is relatively small; at this time, the β value can be set to a relatively small value, such as 0.8. For people aged 30-50, blood vessels begin to show a certain degree of aging, and the impact of the environment gradually increases; the β value can be adjusted to 1.2. For people over 50 years old, vascular elasticity decreases significantly, and they are more sensitive to environmental changes; the β value can be set to 1.5.

[0109] For vascular elasticity indicators, professional medical testing methods can be used, such as vascular ultrasound to measure the elastic modulus of blood vessels. If the elastic modulus is at the upper limit of the normal range, it indicates good vascular elasticity, and the β value can be appropriately reduced; if the elastic modulus is at the lower limit of the normal range, it indicates poor vascular elasticity, and the β value should be increased accordingly. Through this refined adjustment strategy, individual differences among different users can be more accurately reflected, achieving more precise blood pressure correction.

[0110] At this point, by fusing multi-source data and performing dynamic correction in the data processing and control module, it is possible to conduct multi-dimensional analysis by comprehensively considering environmental parameters and user physiological signals. At the same time, through multiple linear regression, random forest algorithm and age difference dynamic adjustment strategy, the original blood pressure value is accurately corrected, thereby improving the reliability and personalized adaptability of blood pressure data, and ultimately achieving precise and scientific blood pressure management.

[0111] (c) Data analysis and prediction unit, used to analyze and extract specified information from environmental data and blood pressure data, and combine it with historical data for deep learning to predict blood pressure changes.

[0112] Furthermore, the analysis process includes detecting trends in blood pressure fluctuations, determining whether environmental factors have influenced the blood pressure, assessing whether the user's blood pressure is within a healthy range, and calculating potential health risks. In addition, based on learning from historical data, the system can predict future changes in the user's blood pressure. For example, if the temperature rises sharply or air quality deteriorates, the system will analyze how these changes affect the user's blood pressure levels and provide an early health warning. The predictive model may be continuously optimized using training datasets and its algorithm parameters adjusted based on real-time data.

[0113] The specific operational process of deep learning in the data analysis and prediction unit includes:

[0114] b1. Based on time-series environmental data E t The time-corrected blood pressure value (BP) adj,t And use the archive data containing user health information (including age, medical history, medication records, etc.) to build an LSTM prediction model;

[0115] b2. The input layer of the LSTM prediction model receives the timing data window [E] t-n BP adj,t-n ,…,E t BP adj,t ], and perform sliding window sampling.

[0116] When using a sliding window for sampling, a window size of 6 (i.e., data from the past hour) was chosen based on considerations of blood pressure variation characteristics and data correlation. Blood pressure changes exhibit a certain continuity and trend over a short period. A 1-hour time span captures recent blood pressure fluctuations without causing data redundancy or excessive computational burden due to an excessively large window. Furthermore, experimental comparisons show that a window size of 6 achieves a good balance between capturing blood pressure variation trends and predictive accuracy.

[0117] b3. Set up two stacked LSTM layers in the LSTM prediction model, with 64 neurons in each layer, and add Dropout=0.2 to prevent overfitting;

[0118] b4. Output the predicted blood pressure value at future time point t+1 through a fully connected layer. Furthermore, the environmental adjustment strategy is optimized through an auxiliary fitness function.

[0119] Specifically, the training process for the LSTM prediction model includes:

[0120] Data augmentation is performed on historical data using a sliding window sampling method, and Gaussian noise σ = 1 mmHg is added to improve the model's generalization ability. The loss function Γ is then defined as follows:

[0121]

[0122] Among them, BP pred,i Let BP be the predicted blood pressure value for the i-th time. ture,i Let λ be the blood pressure calibration value collected periodically for the i-th time, and λ be the intensity adjustment value of L2 regularization;

[0123] Based on the user's health profile, the underlying parameters of the LSTM are frozen, and only the top fully connected layer is trained to make the model more closely match the individual user's situation.

[0124] In summary, the auxiliary function is obtained as follows:

[0125]

[0126] Among them, BP adj For the optimized blood pressure value, BP true For periodically collected blood pressure calibration values, ΔE i BP is the error between actual and ideal environmental parameters. target The target blood pressure range set by the user;

[0127] |BP in auxiliary functions adj -BP ture |、∑ i |ΔE i |、|BP pred -BP target | represent measurement error, environmental adjustment cost, and trend deviation, respectively. λ1=0.6, λ2=0.3, and λ3=0.1 (weights are configurable) represent the adjustable influence factors (weights) of measurement error, environmental adjustment cost, and trend deviation, respectively, and λ1+λ2+λ3=1.

[0128] At this point, by constructing an LSTM-based deep learning model in the data analysis and prediction unit and combining it with an auxiliary fitness function to optimize the environmental regulation strategy, it is possible to predict blood pressure change trends and balance measurement errors, environmental regulation costs, and trend deviations, thereby improving the foresight and resource utilization efficiency of health management and ultimately helping users achieve proactive blood pressure risk control.

[0129] After data analysis, the decision support and control command output function makes specific decisions based on the analysis results. For example, if the system predicts that a user's blood pressure may rise, or that certain environmental factors (such as excessive noise or low humidity) may adversely affect blood pressure, the control module will issue corresponding control commands based on pre-set health standards and thresholds. These commands may include sending a signal to the blood pressure measurement module to request a second measurement to confirm the result, or sending a reminder notification to the user interaction module to inform the user of necessary measures, such as adjusting environmental parameters or taking a rest. Simultaneously, the decision support module can also integrate with other devices such as smart home systems, automatically adjusting the settings of air purifiers, air conditioners, and humidifiers to achieve comprehensive health management.

[0130] Coordination and communication with other modules is also a key function of the data processing and control module. The system needs to ensure seamless connectivity with the environmental sensing module, blood pressure measurement, and user interaction module, ensuring smooth and efficient data transmission and sharing. Throughout the system's operation, the data processing and control module is responsible for coordinating data flow, processing, and feedback, ensuring the synchronized operation of all modules. For example, when blood pressure measurement data is abnormal, the control module will immediately initiate an analysis program to assess whether environmental settings need to be changed or whether the user needs to be notified for further checks, ensuring the system can respond promptly.

[0131] Furthermore, to ensure the long-term stability and accuracy of the system, the data processing and control module needs to possess self-learning and optimization capabilities. Based on continuously collected real-time and historical data, the module can improve the accuracy of data analysis and prediction through algorithm iteration and optimization. Machine learning algorithms can be continuously updated, gradually improving the system's understanding of the relationship between the environment and blood pressure, thereby making more accurate health management decisions.

[0132] Replaceable components for the data processing and control module include different types of microprocessors (such as ARM, DSP, etc.) and memories (such as Flash, RAM, etc.). This module receives data from the environmental sensing module, processes it using a preset algorithm, and then transmits the processing results to the blood pressure measurement and user interaction module to achieve precise control of blood pressure measurement.

[0133] (3) Blood pressure measurement and interaction module, which is used to perform blood pressure measurement operations and feed the measurement results back to the user. In addition, this module connects with the blood pressure monitor to obtain the user's blood pressure data in real time and uploads the data to the data processing and control module for analysis.

[0134] Meanwhile, the user interface within the module will provide users with health information based on the analysis results, including real-time blood pressure readings, trend analysis, and alerts. To enhance the user experience, the module may also include a voice assistant, touchscreen display, charts, and a notification system, allowing users to more intuitively understand their health status. Alternative components could include a blood pressure monitor sensor, touchscreen display, or voice recognition module.

[0135] In summary, the various modules work together to form a closed-loop system, ensuring the accuracy and reliability of blood pressure measurement results in changing environments.

[0136] On the other hand, the present invention also discloses a blood pressure management method, which uses any of the above-mentioned dynamic environment-aware blood pressure management systems to perform operations, including:

[0137] The environmental sensing module monitors environmental information in real time and regulates the environment, then transmits the data to the data processing and control module.

[0138] The data processing and control module adjusts the blood pressure measurement strategy based on environmental data, and then sends the instructions to the blood pressure measurement and interaction module;

[0139] The blood pressure measurement and interaction module controls the execution of blood pressure measurement operations and provides feedback to the user.

[0140] In another aspect, the present invention also discloses a blood pressure management device, characterized in that it includes an interactive interface, a processor, a blood pressure monitor body, a cuff, and a measuring sensor, wherein:

[0141] The user interface, the main body of the blood pressure monitor, and the measurement sensors are all connected to the processor.

[0142] The interactive interface and cuff are both located on the main body of the blood pressure monitor. The main body of the blood pressure monitor and the measuring sensor are used to contact the user to perform blood pressure measurement operations.

[0143] The processor includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, it causes the processor to perform the steps of blood pressure management and detection based on any of the above systems.

[0144] At this point, the blood pressure measurement component mainly consists of the blood pressure monitor body, cuff, and measuring sensor, while the user interaction component includes a display screen, buttons, and voice prompts. Alternative components include blood pressure monitor bodies from different brands, different types of sensors (such as pressure sensors, photoelectric sensors, etc.), and different forms of interactive devices (such as touchscreens, voice recognition systems, etc.).

[0145] The blood pressure measurement and user interaction module is closely connected to the environmental perception module and the data processing and control module. It measures blood pressure according to the instructions of the data processing and control module and displays the results to the user. At the same time, it receives the user's operation instructions to realize human-computer interaction.

[0146] Therefore, by integrating an interactive interface, processor, and sensors into a blood pressure management device, and by incorporating adaptive algorithms and environmental adjustment mechanisms, real-time, accurate, and personalized blood pressure monitoring and environmental optimization functions can be provided. This enhances the convenience and effectiveness of user health management and ultimately significantly improves the quality of life for hypertensive patients.

[0147] In another aspect, the present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method described above.

[0148] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute a corresponding blood pressure management method through any of the dynamic environment-aware blood pressure management systems described in the above embodiments.

[0149] It is understood that the system provided in the embodiments of the present invention corresponds to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant content can be referred to the corresponding parts of the above methods.

[0150] This application also provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other via the communication bus.

[0151] Memory, used to store computer programs;

[0152] When the processor executes the program stored in the memory, it implements the corresponding blood pressure management method through the aforementioned blood pressure management system based on dynamic environment awareness.

[0153] The communication bus mentioned in the above-mentioned electronic devices can be a standard bus for interconnecting peripheral components or an extended industrial standard structure bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc.

[0154] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0155] The memory may include random access memory or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0156] The processors mentioned above can be general-purpose processors, including central processing units, network processors, etc.; they can also be digital signal processors, application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0157] It should also be noted that electronic devices include terminal devices, which can also be called terminals, user equipment, mobile stations, mobile terminals, etc. Terminal devices can be mobile phones, smart TVs, wearable devices, tablets, computers with wireless transceiver capabilities, virtual reality terminal devices, augmented reality terminal devices, wireless terminals in industrial control, wireless terminals in autonomous driving, wireless terminals in remote surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, and so on. The embodiments of this application do not limit the specific technologies or device forms used in the terminal devices.

[0158] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive SSD), etc.

[0159] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0160] Furthermore, it should be noted that if any directional indication (such as up, down, left, right, front, back, etc.) is involved in the embodiments of the present invention, the directional indication is only used to explain the relative positional relationship and movement of each component in a specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0161] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text includes three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, in the embodiments of this invention, "multiple" refers to two or more. Moreover, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

Claims

1. A dynamic environment perception based blood pressure management system, characterized in that, Comprise: An environmental perception module for real-time monitoring of environmental parameters including temperature, humidity, air pressure, noise, and compensating through multi-parameter coupling to link external environmental regulation systems to optimize the measured environment to the specified state; A data processing and control module for deep processing and analysis of collected data and making control decisions based on the analysis results to achieve accurate management and monitoring of blood pressure; A blood pressure measurement and interaction module for performing blood pressure measurement operations and feeding back the measurement results to the data processing and control module and the user; The multi-parameter coupling compensation of the environmental perception module links to the control logic of the external environment, which includes: When temperature > 28℃ and humidity > 80%, adopt blood vessel dilation compensation factor × blood viscosity correction coefficient The comprehensive compensation strategy, the blood pressure measurement result Compensation, the blood pressure measurement result Is: ; In the state of noise > 70dB and illumination > 1500lux, activate the double-channel filtering algorithm to eliminate artifact signals; Build an environmental compensation system based on ISO 81060 - 3 standard certification to generate an environmental interference index EEI in real time, and when EEI > 0.85, automatically trigger environmental regulation instructions to link external environmental regulation systems to measure the environment to the specified state; The data processing and control module is internally provided with: A data receiving and preprocessing unit for receiving real-time data from the environmental perception module and the blood pressure measurement and interaction module and performing data preprocessing operations; The data processing and control unit is used for multi-source data fusion and correction of environmental parameters and physiological data, dynamically corrects the original blood pressure value through dynamic perception of environmental parameters and user physiological signals, so as to eliminate environmental interference and output the optimized blood pressure value And an adaptive algorithm framework based on Kalman filtering is constructed to realize noise suppression through a state space model. A data analysis and prediction unit for analyzing and extracting specified information from environmental data and blood pressure data, and combining historical data for deep learning to predict blood pressure changes; The specific operation process of the data processing and control unit for multi-source data fusion and correction includes: a1. generating an environmental feature matrix within a time period by dynamically sensing environmental parameters including temperature, humidity, air pressure, noise, illumination a1. generating an environmental feature matrix within a time period by dynamically sensing environmental parameters including temperature, humidity, air pressure, noise, illumination a1. generating an environmental feature matrix within a time period by dynamically sensing environmental parameters including temperature, humidity, air pressure, noise, illumination wherein, is a temperature parameter, is a humidity parameter, is a barometric pressure parameter, is a noise parameter, is an illumination parameter; a2. Perform environmental impact factor modeling and train the weight coefficients using multiple linear regression or random forest algorithm based on historical dataset to minimize the correction error, there is: wherein, is a periodically collected blood pressure calibration value, is a raw collected blood pressure value, is an error between actual and ideal environmental parameters, is an actual environmental parameter, is an ideal environmental parameter; a3. dynamically adjusting the correction amplitude according to the age difference of the user individual in the blood pressure correction and verification process to obtain the optimized blood pressure value , wherein, represents age, is a decay factor used to fit the acquisition by the blood pressure measured user history data; The specific operation process of the data analysis and prediction unit for deep learning includes: b1. based on timing environment data , the optimized blood pressure value and the profile data containing user health information, build an LSTM prediction model; b2. The input layer of the LSTM prediction model receives a time series data window and performs sliding window sampling with window size set to 6 to represent the past 1 hour data; b3. Set two layers of stacked LSTM layers in the LSTM prediction model, set 64 neurons in each layer, and add Dropout=0.2 to prevent overfitting; b4. outputting, by the fully connected layer, a blood pressure prediction value for a future time point and optimizing the environmental conditioning policy by an auxiliary fitness function.​ 2. The dynamic environment-aware blood pressure management system as claimed in claim 1, wherein, The specific operation process of using multiple linear regression to train weight coefficients in a2 includes: A random decimal value is set as an initial regression coefficient, and a gradient descent method is used for iterative optimization, the gradient of a loss function with respect to a regression coefficient is calculated, and the coefficient is updated in the opposite direction of the gradient until the loss function converges to a minimum value, so as to determine the optimal weight coefficient .

3. The dynamic environment-aware blood pressure management system as claimed in claim 1, wherein, The specific operation process of using a random forest algorithm to train weight coefficients in a2 includes: The number of decision trees is determined according to the size of the data set and the computing resources, and then a plurality of decision trees are constructed and trained through sampling with replacement of the samples, and finally the results of the decision trees obtain the optimal weight coefficients of the final prediction .

4. The dynamic environment-aware blood pressure management system as claimed in claim 1, wherein, The specific training process of the LSTM prediction model includes: The historical data is enhanced by using a sliding window sampling method and adding Gaussian noise , so as to improve the generalization ability of the model, and the loss function is in, For the first Predicted blood pressure value, For the first Blood pressure calibration values ​​collected periodically. L2 Intensity adjustment value; For user health records, freeze the LSTM bottom layer parameters and only train the top fully connected layer to obtain the auxiliary function: wherein, is the optimized blood pressure value, is the periodically collected blood pressure calibration value, is the error between the actual and ideal environmental parameters, is the target blood pressure range set by the user; in the auxiliary function , , represent the measurement error, the environmental adjustment cost, the trend deviation, respectively, , , represent the adjustable influence factors of the measurement error, the environmental adjustment cost, the trend deviation, respectively, and .

5. A blood pressure management method using the dynamic environment-aware blood pressure management system of any one of claims 1-4 to perform operations, characterized in that, Comprise: Real-time monitoring of environmental information through the environmental perception module and regulating the environment, then transmitting the data to the data processing and control module; The data processing and control module adjusts the blood pressure measurement strategy according to the environmental data, and then sends instructions to the blood pressure measurement and interaction module; The blood pressure measurement and interaction module controls the blood pressure measurement operation and feeds back the results to the user.

6. A blood pressure management device, characterized by, Comprise an interactive interface, a processor, a sphygmomanometer body, a cuff, and a measurement sensor, wherein: The interactive interface, the sphygmomanometer body, and the measurement sensor are connected to the processor; The interactive interface and the cuff are both arranged on the sphygmomanometer body, and the sphygmomanometer body and the measurement sensor are used to contact the user to perform blood pressure measurement operations; The processor comprises a memory and a processor, and the memory stores a computer program, which, when executed by the processor, causes the processor to execute the method steps of blood pressure management and detection based on the system of any one of claims 1 to 4.

Images