Lung function evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of intelligent monitoring, and particularly discloses a lung function evaluation method and device, electronic equipment and a storage medium, and the method comprises the following steps: obtaining a universal dynamic threshold range of respiratory rate and respiratory amplitude; continuously collecting breathing data output by the MEMS breathing sensor, and obtaining and updating the moving average value and the moving standard deviation of the breathing frequency and the breathing amplitude in real time so as to calculate the change rate of the breathing frequency and the breathing amplitude in real time; according to the updated moving average value and the moving standard deviation, dynamically adjusting the dynamic threshold range of the breathing frequency and the breathing amplitude; comprehensively considering the adjusted dynamic threshold range and the change rate to carry out breathing abnormity judgment so as to carry out lung function evaluation; according to the method, finally, the adjusted dynamic threshold range and the breathing parameter change rate are comprehensively considered, breathing abnormity judgment is conducted, the lung function evaluation result is generated, breathing abnormity can be recognized more accurately, and the accuracy and reliability of lung function evaluation are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and specifically to a lung function assessment method, device, electronic device and storage medium. Background Art

[0002] In the home-based elderly care scenario, the use of wearable devices to monitor and evaluate lung function can achieve long-term tracking and management of the respiratory conditions of the elderly, which is of great significance for the timely detection and prevention of respiratory diseases.

[0003] Traditional lung function assessment methods using wearable devices typically evaluate the collected data based on preset fixed threshold standards. This method has certain applicability in professional medical environments, but its limitations are gradually becoming apparent in the complex environment of home-based elderly care. The physiological functions of the elderly vary from person to person, and their breathing patterns are susceptible to dynamic changes due to a variety of factors such as the environment, mood, and health status. Fixed threshold standards are difficult to adapt to these individual differences and dynamic changes, resulting in reduced accuracy of the assessment results. Specifically, when the elderly person's breathing pattern changes but remains within the fixed threshold range, potential abnormal breathing events may not be identified in a timely manner; conversely, when individual differences or environmental factors cause respiratory parameters to exceed the fixed threshold range, false alarms may occur, causing unnecessary concern and wasting medical resources.

[0004] There is currently no effective technical solution to the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a lung function assessment method, device, electronic device and storage medium to improve the accuracy of lung function assessment.

[0006] In a first aspect, the present application provides a lung function assessment method for monitoring and assessing the lung function of elderly people in a home-based elderly care scenario using a wearable MEMS respiratory sensor device. The method comprises the following steps: S1. Obtaining a universal dynamic threshold range of respiratory rate and respiratory amplitude; S2. Continuously collect respiratory data output by the MEMS respiratory sensor, wherein the respiratory data includes respiratory rate and respiratory amplitude. Based on a sliding window mechanism, the moving average and moving standard deviation of the respiratory rate and respiratory amplitude are obtained and updated in real time to calculate the rate of change of the respiratory rate and respiratory amplitude in real time. S3. Dynamically adjusting the dynamic threshold ranges of the respiratory rate and respiratory amplitude according to the updated moving average and moving standard deviation; S4. Comprehensively consider the adjusted dynamic threshold range and change rate to determine respiratory abnormalities and conduct lung function assessment.

[0007] The pulmonary function assessment method of the present application first obtains the universal dynamic threshold range of respiratory rate and respiratory amplitude as the initial assessment standard, then uses a wearable MEMS respiratory sensor to continuously collect the respiratory data of the elderly and combines it with a sliding window mechanism to calculate and update the moving average and moving standard deviation of the respiratory rate and respiratory amplitude in real time, thereby obtaining the change rate of the respiratory rate and respiratory amplitude, and then dynamically adjusts the dynamic threshold range of the respiratory rate and respiratory amplitude according to the updated moving average and moving standard deviation, so that the dynamic threshold range is adaptively adjusted with the change of respiratory data, and is more in line with the actual respiratory condition of the elderly. Finally, considering the adjusted dynamic threshold range and the change rate of respiratory parameters comprehensively, respiratory abnormality judgment is made and pulmonary function assessment results are generated, which can more accurately identify respiratory abnormalities and improve the accuracy and reliability of pulmonary function assessment.

[0008] In the lung function assessment method, step C3 comprises: S31. Analyze historical respiratory data and identify changing trends in breathing patterns; S32. Assess the depth of impact of chronic diseases on breathing patterns in the elderly; S33, obtaining the noise level of the MEMS respiratory sensor data; S34, configuring a compensation factor based on the change trend, the impact depth, the noise level, and the updated moving average and moving standard deviation; S35. Dynamically adjust the dynamic threshold ranges of respiratory frequency and respiratory amplitude according to the compensation factor.

[0009] During the above processing, step S31 analyzes historical respiratory data to identify the changing trend of the respiratory pattern, making up for the limitation of only considering the current moving average and standard deviation, thereby achieving the capture of the long-term changing pattern of the respiratory pattern. Step S32 evaluates the depth of the impact of chronic diseases on the respiratory pattern of the elderly, taking into account the specific impact of the disease on the respiratory pattern, making the threshold adjustment more individualized and targeted. Step S33 obtains the noise level of the sensor data, reduces the interference of noise on the threshold adjustment, and improves the accuracy of the threshold adjustment. Step S34 configures the compensation factor based on the above factors, comprehensively considering the degree of influence of various factors on the respiratory threshold. Step S35 uses the compensation factor to dynamically adjust the threshold range, achieving more accurate and reliable dynamic threshold adjustment, thereby improving the accuracy of lung function assessment. Through the above steps, the adjustment of the dynamic threshold range no longer relies solely on real-time respiratory data, but comprehensively considers multiple factors such as historical respiratory data, the impact of chronic diseases and noise levels, so that the dynamic threshold range can more accurately reflect individual respiratory characteristics and environmental changes, thereby improving the accuracy and reliability of lung function assessment.

[0010] In the lung function assessment method, step C33 includes: S331, identifying multiple noise sources in MEMS respiratory sensor data; S332. Select or combine multiple adaptive filters for the noise source, and filter the MEMS respiratory sensor data using the selected or combined adaptive filters; S333 , estimating and obtaining the noise level based on the difference between the MEMS respiratory sensor data before and after filtering.

[0011] In the lung function assessment method, step C33 further comprises: S334: Evaluate the accuracy of the noise level based on the noise verification mechanism. If the accuracy is lower than expected, return to step S331. The process of evaluating the accuracy of the noise level based on the noise verification mechanism includes: A1. Obtaining the target user's exercise status information; A2. determining the degree of influence of motion artifacts on noise level estimation based on the motion state information; A3. Adaptively adjust the evaluation strategy of the noise verification mechanism based on the impact level; A4. Using the adjusted noise verification mechanism, evaluate the accuracy of the noise level estimation.

[0012] The method for evaluating lung function, wherein step A3 comprises: A31. Using a pattern recognition algorithm to determine the motion type based on the motion state information, and extracting the motion artifact frequency corresponding to the motion type; A32. Adjust the signal-to-noise ratio threshold and cross-correlation coefficient threshold evaluation parameters in the noise verification mechanism according to the motion type; A33. Adjust the weight of each frequency band in the noise verification mechanism according to the frequency of motion artifacts.

[0013] The method for evaluating lung function, wherein step S4 comprises: Obtain preset values of respiratory rate and respiratory amplitude parameter change rates; Determine whether the respiratory frequency or respiratory amplitude exceeds the dynamic threshold range to obtain a first determination result, and determine whether the rate of change of the respiratory frequency or respiratory amplitude exceeds the preset value of the parameter change rate to obtain a second determination result; A lung function assessment result is generated according to the first judgment result, the second judgment result and a preset mapping table.

[0014] In the lung function assessment method, the process of the MEMS respiratory sensor outputting respiratory data includes: B1. Obtain pressure change information; B2. performing pressure compensation on the pressure change information using a dynamic pressure loss parameter model; B3. Obtaining flow rate change information based on the pressure change information after pressure compensation; B4. Calculating and outputting the respiratory data based on the flow change information over a preset time period; The process of the pressure compensation process includes: C1. Real-time calculation of the average pressure within the preset breathing cycle; C2. Calculating and obtaining a pressure loss parameter based on the average pressure and the type of the wearable MEMS respiratory sensor device; C3. Perform pressure compensation on the pressure change information according to the pressure loss parameter.

[0015] In a second aspect, the present application also provides a lung function assessment device for use in home-based elderly care scenarios, using a wearable MEMS respiratory sensor device to monitor and assess the lung function of the elderly. The device comprises: Setting an acquisition module for acquiring a universal dynamic threshold range of respiratory rate and respiratory amplitude; An acquisition and calculation module is used to continuously collect respiratory data output by the MEMS respiratory sensor, wherein the respiratory data includes respiratory frequency and respiratory amplitude. Based on a sliding window mechanism, the module obtains and updates the moving average and moving standard deviation of the respiratory frequency and respiratory amplitude in real time to calculate the rate of change of the respiratory frequency and respiratory amplitude in real time. A data updating module, configured to dynamically adjust the dynamic threshold ranges of the respiratory frequency and respiratory amplitude according to the updated moving average and moving standard deviation; The comprehensive assessment module is used to comprehensively consider the adjusted dynamic threshold range and change rate to make respiratory abnormality judgments for lung function assessment.

[0016] The pulmonary function assessment device of the present application can adapt to the individual differences and dynamic changes in the breathing patterns of the elderly in home-based elderly care scenarios by dynamically adjusting the threshold ranges of respiratory frequency and respiratory amplitude. It overcomes the limitations of traditional fixed threshold methods, improves the accuracy of pulmonary function assessment, and realizes long-term tracking and management of the respiratory conditions of the elderly, providing technical support for the timely detection and prevention of respiratory diseases.

[0017] In a third aspect, the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the method provided in the first aspect are executed.

[0018] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, runs the steps of the method provided in the first aspect above.

[0019] As can be seen from the above, the present application provides a lung function assessment method, device, electronic device and storage medium, wherein the lung function assessment method first obtains the general dynamic threshold range of respiratory frequency and respiratory amplitude as the initial assessment standard, and then uses a wearable MEMS respiratory sensor to continuously collect the respiratory data of the elderly and combines the sliding window mechanism to calculate and update the moving average and moving standard deviation of the respiratory frequency and respiratory amplitude in real time, thereby obtaining the change rate of the respiratory frequency and respiratory amplitude, and then dynamically adjusts the dynamic threshold range of the respiratory frequency and respiratory amplitude according to the updated moving average and moving standard deviation, so that the dynamic threshold range is adaptively adjusted with the change of respiratory data, and is more in line with the actual respiratory condition of the elderly. Finally, the adjusted dynamic threshold range and the change rate of respiratory parameters are comprehensively considered to make respiratory abnormality judgments and generate lung function assessment results, which can more accurately identify respiratory abnormalities and improve the accuracy and reliability of lung function assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Flowchart of the lung function assessment method provided in an embodiment of the present application.

[0021] Figure 2 This is a schematic diagram of the structure of the lung function assessment device provided in an embodiment of the present application.

[0022] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0023] Reference numerals: 201, setting acquisition module; 202, acquisition and calculation module; 203, data update module; 204, comprehensive evaluation module; 301, processor; 302, memory; 303, communication bus. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0025] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0026] First, please refer to Figure 1 Some embodiments of the present application provide a lung function assessment method for monitoring and assessing lung function of elderly people in a home-based elderly care scenario using a wearable MEMS respiratory sensor device. The method includes the following steps: S1. Obtaining a universal dynamic threshold range of respiratory rate and respiratory amplitude; S2. Continuously collect respiratory data output by the MEMS respiratory sensor, including respiratory rate and respiratory amplitude. Based on a sliding window mechanism, obtain and update the moving average and moving standard deviation of respiratory rate and respiratory amplitude in real time to calculate the rate of change of respiratory rate and respiratory amplitude in real time. S3. Dynamically adjust the dynamic threshold ranges of respiratory rate and respiratory amplitude based on the updated moving average and moving standard deviation; S4. Comprehensively consider the adjusted dynamic threshold range and change rate to determine respiratory abnormalities and conduct lung function assessment.

[0027] Specifically, the universal dynamic threshold range can be obtained from statistical analysis of respiratory physiological data of a large population (especially respiratory data of a large number of healthy elderly people), or the normal respiratory parameter range recommended by clinical guidelines can be used. It can actually be set as parameter data in the wearable MEMS respiratory sensor device, or it can be data obtained from the server, which can serve as the initial benchmark for subsequent evaluation and processing.

[0028] More specifically, in step S2, a sliding window mechanism is used to smooth the respiratory data and reduce instantaneous noise interference. The window size can be adjusted according to the actual application scenario and sensor performance. The calculation formulas for the moving average and the moving standard deviation are commonly used calculation formulas and will not be described in detail here. The moving average reflects the central trend or long-term change direction of the data by smoothing the short-term fluctuations in the data, while the moving standard deviation measures the degree of dispersion of the data within the moving window, revealing the intensity of volatility or abnormal behavior. The rate of change obtained by combining the data of the two can accurately reflect the actual changes in the breathing frequency and breathing amplitude. The rate of change can be obtained by dividing the difference between the current value and the moving average by the moving average. In addition, Step S2 is to continuously and dynamically update the moving average and moving standard deviation, and dynamically update the change rate of the respiratory frequency and respiratory amplitude based on the updated moving average and moving standard deviation, so that the change rate is real-time; the adjustment of the dynamic threshold range is based on the real-time updated moving average and moving standard deviation, and its adjustment can adopt a variety of strategies. For example, the adjustment coefficient can be set based on the moving average and moving standard deviation. When the moving average deviates from the center of the initial threshold range, the center position of the dynamic threshold range is adjusted accordingly. When the moving standard deviation increases, the width of the dynamic threshold range is also expanded accordingly. For example, if the moving average of the respiratory frequency is continuously high, the upper limit of the dynamic threshold range can be increased accordingly.

[0029] More specifically, the adjustment amplitude of step S3 may be proportional to the size of the moving standard deviation to accommodate the variability of individual breathing.

[0030] More specifically, in step S4, a change rate threshold can be set for determining respiratory abnormalities. For example, when the rate of change of respiratory rate or respiratory amplitude exceeds a preset threshold, a preliminary determination of respiratory abnormality is made. The pulmonary function assessment results can be comprehensively evaluated based on the respiratory abnormality determination results and the dynamic threshold range. For example, when the respiratory rate or respiratory amplitude exceeds the dynamic threshold range and the rate of change also exceeds the preset threshold, the risk of pulmonary function abnormality is assessed to be high. Furthermore, pulmonary function assessment results can be graded based on the frequency, duration, and severity of respiratory abnormalities, for example, as mild, moderate, or severe.

[0031] The pulmonary function assessment method of the embodiment of the present application first obtains the universal dynamic threshold range of respiratory rate and respiratory amplitude as the initial assessment standard, then uses the wearable MEMS respiratory sensor to continuously collect the respiratory data of the elderly and combines the sliding window mechanism to calculate and update the moving average and moving standard deviation of the respiratory rate and respiratory amplitude in real time, thereby obtaining the change rate of the respiratory rate and respiratory amplitude, and then dynamically adjusts the dynamic threshold range of the respiratory rate and respiratory amplitude according to the updated moving average and moving standard deviation, so that the dynamic threshold range is adaptively adjusted with the change of respiratory data, and is more in line with the actual respiratory condition of the elderly. Finally, considering the adjusted dynamic threshold range and the change rate of respiratory parameters, respiratory abnormality judgment is made and a pulmonary function assessment result is generated, which can more accurately identify respiratory abnormalities and improve the accuracy and reliability of pulmonary function assessment.

[0032] The pulmonary function assessment method of the embodiment of the present application can adapt to the individual differences and dynamic changes in the breathing patterns of the elderly in home-based elderly care scenarios by dynamically adjusting the threshold ranges of respiratory rate and respiratory amplitude. It overcomes the limitations of traditional fixed threshold methods, improves the accuracy of pulmonary function assessment, and realizes long-term tracking and management of the respiratory conditions of the elderly, providing technical support for the timely detection and prevention of respiratory diseases.

[0033] It should be noted that the initial dynamic threshold range can be personalized based on the elderly individual's age, gender, height, weight, and other physiological parameters. The dynamic threshold range adjustment strategy can utilize intelligent algorithms such as fuzzy control or neural networks to achieve more refined dynamic adjustments. The rate of change threshold can be adaptively adjusted based on the elderly individual's health status and daily activity level. Pulmonary function assessment results can be further refined into different levels of risk assessment and provide corresponding health recommendations.

[0034] It should be noted that there are two dynamic threshold ranges, corresponding to the respiratory frequency and respiratory amplitude respectively. Similarly, the moving average, moving standard deviation and change rate are also two.

[0035] In some preferred embodiments, step C3 comprises: S31. Analyze historical respiratory data and identify changing trends in breathing patterns; S32. Assess the depth of impact of chronic diseases on breathing patterns in the elderly; S33, obtaining the noise level of the MEMS respiratory sensor data; S34. Configure compensation factors based on the change trend, impact depth, noise level, and updated moving average and moving standard deviation; S35. Dynamically adjust the dynamic threshold ranges of the respiratory frequency and respiratory amplitude according to the compensation factor.

[0036] Specifically, in step S31, the historical respiratory data includes historical respiratory frequency and historical respiratory amplitude. These data can be combined with time series analysis methods to perform trend analysis to monitor long-term changes in respiratory frequency and / or respiratory amplitude to identify the changing trend of the respiratory pattern. For example, the historical respiratory frequency and respiratory amplitude data can be modeled using an autoregressive moving average model or an exponential smoothing method to identify the long-term changing trend of the respiratory pattern. The changing trend can be reflected in the gradual acceleration or slowing down of the respiratory frequency, the gradual shallowing or deepening of the respiratory amplitude, etc.

[0037] More specifically, in step S32, the depth assessment of the impact of chronic diseases on the breathing patterns of the elderly can be achieved by combining the elderly's medical records, disease diagnosis reports and clinical medical knowledge base. For example, for elderly people with chronic obstructive pulmonary disease, the depth of the impact of the disease on the breathing pattern is assessed to be a higher level because chronic obstructive pulmonary disease usually leads to changes such as increased respiratory rate, decreased respiratory amplitude and irregular respiratory rhythm.

[0038] More specifically, in step S33, the noise level of the MEMS respiratory sensor data can be estimated by filtering the respiratory data using an adaptive filter and comparing the differences between the data before and after filtering. For example, the respiratory data can be filtered using a minimum mean square error adaptive filter, and the noise level can be estimated by comparing the differences between the data before and after filtering. The greater the difference, the higher the noise level.

[0039] More specifically, in step S34, the configuration process of the compensation factor can first divide the change trend, impact depth, noise level, moving average and moving standard deviation into levels, for example, into three levels: low, medium and high, and then assign corresponding weights to each level. Finally, the compensation factor is calculated by weighted summation. Therefore, the compensation factor comprehensively reflects the impact of historical breathing pattern changes, chronic disease effects and sensor noise on the breathing threshold.

[0040] More specifically, in step S35, the process of dynamically adjusting the dynamic threshold range of respiratory frequency and respiratory amplitude can be to adjust the upper and lower limits of the dynamic threshold range using a compensation factor, or to adjust the adjustment speed of the dynamic threshold range, for example, by multiplying the compensation factor by the current dynamic threshold range. In this way, the dynamic threshold range can more accurately adapt to changes in individual breathing patterns and external environment, thereby achieving adaptive adjustment of the threshold range.

[0041] More specifically, during the above processing, step S31 analyzes historical respiratory data to identify the changing trend of the respiratory pattern, which makes up for the limitation of only considering the current moving average and standard deviation, thereby achieving the capture of the long-term changing pattern of the respiratory pattern. Step S32 evaluates the depth of the impact of chronic diseases on the respiratory pattern of the elderly, taking into account the specific impact of the disease on the respiratory pattern, making the threshold adjustment more individualized and targeted. Step S33 obtains the noise level of the sensor data, reduces the interference of noise on the threshold adjustment, and improves the accuracy of the threshold adjustment. Step S34 configures the compensation factor based on the above factors, comprehensively considering the degree of influence of various factors on the respiratory threshold. Step S35 uses the compensation factor to dynamically adjust the threshold range, achieving more accurate and reliable dynamic threshold adjustment, thereby improving the accuracy of lung function assessment. Through the above steps, the adjustment of the dynamic threshold range no longer relies solely on real-time respiratory data, but comprehensively considers multiple factors such as historical respiratory data, the impact of chronic diseases and noise levels, so that the dynamic threshold range can more accurately reflect individual respiratory characteristics and environmental changes, thereby improving the accuracy and reliability of lung function assessment.

[0042] In some preferred embodiments, step C34 includes: S341. Based on the preset classification rules, the change trend, impact degree, noise level, and the updated moving average and moving standard deviation levels are respectively obtained, and the level configuration compensation factor is weightedly calculated.

[0043] Specifically, in the above steps, through preset division rules, complex factors such as change trend, impact degree, noise level, and adjusted moving average and moving standard deviation are converted into quantifiable grade levels, which realizes the simplification and classification of factors, and facilitates subsequent unified processing and calculation; weighted calculation is adopted to flexibly adjust according to the importance of different factor grade levels, so that the configured compensation factor can more accurately reflect the combined impact of multiple factors, thereby providing a more accurate basis for the subsequent dynamic adjustment of the respiratory rate and respiratory amplitude threshold range.

[0044] More specifically, the acquisition of grade levels can be achieved in the following ways: pre-establishing a grade classification standard, which is used to measure the change trend, impact level, noise level, and the level of the adjusted moving average and moving standard deviation; the change trend can be divided into stable, slow change, rapid change and other levels; the impact level can be divided into mild, medium, severe and other levels; the noise level can be divided into low, medium and high levels; the moving average and moving standard deviation can be divided into different levels according to their numerical ranges. After obtaining the grade level of each factor, a weight value is preset for each grade level, and the weight value reflects the importance of each factor in the compensation factor configuration. Then, a weighted calculation is performed based on the obtained grade level and the corresponding weight value. The result of the weighted calculation is the compensation factor, which is used to dynamically adjust the respiratory rate and respiratory amplitude threshold range to more accurately reflect the actual respiratory condition of the elderly.

[0045] In some preferred embodiments, step C33 includes: S331, identifying multiple noise sources in MEMS respiratory sensor data; S332. Select or combine multiple adaptive filters for the noise source, and filter the MEMS respiratory sensor data using the selected or combined adaptive filters. S333 , estimating and obtaining a noise level based on the difference between the MEMS respiratory sensor data before and after filtering.

[0046] Specifically, in step S331, the identification of multiple noise sources may include but is not limited to motion artifacts, environmental interference, and sensor noise. Motion artifacts may be caused by the movement of the elderly's body or changes in posture, environmental interference may come from sounds or electromagnetic waves in the surrounding environment, and sensor noise may be generated by electronic components inside the MEMS respiratory sensor device. These noise sources have different presentation methods. For example, motion artifact noise may show energy concentration within a specific frequency range, while environmental noise may show random distribution characteristics. Therefore, the identification of noise sources can be achieved by analyzing the spectral characteristics or time domain characteristics of the sensor data.

[0047] More specifically, in step S332, considering the complexity of the noise components in the actual application scenario, the selection or combination of adaptive filters is determined based on the characteristics of the noise source identified in step S331. For example, for motion artifacts, an adaptive notch filter or an adaptive filter based on accelerometer signals can be selected; for environmental interference, an adaptive filter based on spectrum analysis can be selected; for sensor self-noise, a Kalman filter or a Wiener filter can be selected. A variety of adaptive filters can be used in combination to more comprehensively filter out mixed noise. In terms of filter combination, it can be implemented in series or in parallel. For example, if a series method is used, a filter can be used to filter out the main noise components first, and then another filter can be used to further reduce the residual noise. If a parallel method is used, filters can be designed separately for noise in different frequency bands, and then the outputs of each filter can be synthesized.

[0048] More specifically, in step S333, the estimation of the noise level can be achieved by calculating the mean square error, signal-to-noise ratio, or power spectral density difference of the MEMS respiratory sensor data before and after filtering. The larger the mean square error, the smaller the signal-to-noise ratio, and the larger the difference in power spectral density, all indicate a higher noise level. The noise level calculation process can be to calculate the difference in power spectral density of the signal before and after filtering, and use the difference as an estimate of the noise power spectral density, or to calculate the mean square error of the signal before and after filtering, which can reflect the level of noise energy filtered out. These data can be directly used as indicators of the noise level, or one or more of these data can be used in combination with a preset level division rule to determine the noise level.

[0049] In some preferred embodiments, step C33 further includes: S334: Evaluate the accuracy of the noise level based on the noise verification mechanism. If the accuracy is lower than expected, return to step S331. The process of evaluating the accuracy of the noise level based on the noise verification mechanism includes: A1. Obtaining the target user's exercise status information; A2. determining the degree of influence of motion artifacts on noise level estimation based on the motion state information; A3. Adaptively adjust the evaluation strategy of the noise verification mechanism based on the degree of impact; A4. Use the adjusted noise verification mechanism to evaluate the accuracy of the noise level estimation.

[0050] Specifically, in step A1, the motion status information is obtained through the wearable device's accelerometer, gyroscope and other motion sensors. The accelerometer, gyroscope and other motion sensors monitor the elderly's body acceleration data, movement direction data, etc. in real time. These data are analyzed to identify the elderly's motion status information. The motion status information can specifically include the user's motion type, exercise intensity, exercise frequency, etc. The exercise types include sitting, standing, walking, jogging and other types.

[0051] More specifically, in step A2, the degree of influence of motion artifacts on noise level estimation is determined by analyzing the frequency domain characteristics of the motion state information and the respiratory signal. For example, when the motion frequency is close to the respiratory frequency, the degree of interference of motion artifacts on the respiratory signal is higher and the influence is greater.

[0052] More specifically, in step A3, adaptively adjusting the evaluation strategy of the noise verification mechanism may include adjusting the threshold parameters, weight parameters or evaluation algorithms in the noise verification mechanism. For example, when the impact of motion artifacts is large, the sensitivity of the noise verification mechanism may be increased, and the accuracy of the noise level may be evaluated more strictly.

[0053] More specifically, in step A4, the noise level accuracy is reassessed using the adjusted noise verification mechanism and compared with the expected accuracy. If the accuracy is lower than expected, the system returns to step S331 and re-identifies the noise source and estimates the noise level, forming an iterative optimization process to ensure that the noise level accuracy meets the preset requirements and ensures the reliability of subsequent lung function assessments.

[0054] In some preferred embodiments, step A3 includes: A31. Using a pattern recognition algorithm to determine the motion type based on the motion state information, and extracting the motion artifact frequency corresponding to the motion type; A32. Adjust the signal-to-noise ratio threshold and cross-correlation coefficient threshold evaluation parameters in the noise verification mechanism according to the motion type; A33. Adjust the weight of each frequency band in the noise verification mechanism according to the frequency of motion artifacts.

[0055] Specifically, in step A31, a pattern recognition algorithm (which may be a k-nearest neighbor (KNN) algorithm, a decision tree algorithm, or other pattern recognition algorithm) is used to analyze the motion state information to determine the user's motion type. For example, the user's motion type can be identified as sitting, walking, or running, etc.; each motion type is pre-configured with a corresponding motion artifact frequency, so the corresponding motion artifact frequency can be directly extracted. For example, the walking state may correspond to a lower frequency motion artifact, while the running state may correspond to a higher frequency motion artifact.

[0056] It should be noted that, if the motion state information includes the motion type, step A31 may directly extract the motion type from the motion state information, and then extract the motion artifact frequency corresponding to the motion type.

[0057] More specifically, step A32 adjusts the evaluation parameters of the noise verification mechanism for different motion types. For example, for motion types with strong motion artifacts (such as running), the signal-to-noise ratio threshold can be appropriately relaxed and the cross-correlation coefficient threshold can be appropriately lowered to avoid misclassifying motion artifacts as noise and improve the accuracy of noise level assessment. Conversely, for motion types with weak motion artifacts (such as sitting still), the signal-to-noise ratio threshold can be appropriately tightened and the cross-correlation coefficient threshold can be appropriately increased to more sensitively detect true noise.

[0058] More specifically, in step A33, considering that motion artifacts typically have higher energy within specific frequency bands, the weights assigned to each frequency band in the noise verification mechanism are adjusted based on the frequency of the motion artifacts. For example, if the frequency of motion artifacts is concentrated in the low-frequency band, the weight assigned to the noise verification mechanism in the low-frequency band can be reduced, while the weight assigned to the high-frequency band can be increased. This reduces the impact of motion artifacts on the noise level assessment and improves the accuracy of the assessment.

[0059] More specifically, the frequency of motion artifacts can be determined through experimental testing and data analysis, or by consulting relevant literature. Evaluation parameters can be adjusted using a lookup table. A mapping table between motion type and evaluation parameters can be pre-established, and the corresponding evaluation parameters can be retrieved based on the identified motion type. Frequency band weighting can be adjusted using a segmented weighting method, dividing the frequency into multiple bands and assigning different weights to each band.

[0060] In some preferred embodiments, step A33 includes: A331. Analyze the frequency domain aliasing of motion artifacts and respiratory signals based on the motion artifact frequency and determine the aliasing frequency band range. A332. Predict individual respiratory rate range based on exercise type; A333. Based on the determined aliasing frequency band range, the predicted individual respiratory rate range, the response frequency of the MEMS respiratory sensor, and the motion artifact frequency, an adaptive weighted average method is used to adjust the weights of each frequency band in the noise verification mechanism.

[0061] Specifically, step A331 can use frequency domain analysis methods such as fast Fourier transform to analyze the frequency spectrum of motion artifacts and respiratory signals, and determine the aliasing frequency band range by the degree of spectrum overlap. The purpose is to identify the degree of mutual interference between motion artifacts and respiratory signals in the frequency domain, so as to determine which frequency bands of respiratory signals may be significantly affected by motion artifacts.

[0062] More specifically, step A332 can predict the individual respiratory frequency range according to the exercise type through a pre-established mapping relationship between the exercise type and the respiratory frequency range. This step helps to more accurately define the main frequency band distribution of the respiratory signal.

[0063] More specifically, step A333 can introduce an adaptive weighted averaging algorithm to adjust the weights of each frequency band in the noise verification mechanism based on the determined aliasing frequency band range, the predicted individual respiratory rate range, the MEMS respiratory sensor response frequency, and the motion artifact frequency. The goal of the weight adjustment is to reduce the weights of the frequency bands corresponding to the aliasing frequency band and the motion artifact frequency, and increase the weights of the frequency bands corresponding to the non-aliasing frequency band and the individual respiratory rate range, so as to pay more attention to the respiratory signal characteristics in the noise verification mechanism, reduce motion artifact interference, and ensure the effectiveness of the respiratory signal; through this refined frequency band weight adjustment, the noise verification mechanism can more effectively identify and distinguish noise from real respiratory signals, thereby improving the accuracy of noise level assessment.

[0064] In some preferred embodiments, step S4 includes: S41, obtaining preset values of the respiratory frequency and respiratory amplitude parameter change rates; S42, determining whether the respiratory frequency or respiratory amplitude exceeds the dynamic threshold range to obtain a first determination result, and determining whether the rate of change of the respiratory frequency or respiratory amplitude exceeds a preset parameter change rate value to obtain a second determination result; S43. Generate a lung function assessment result according to the first judgment result, the second judgment result, and a preset mapping table.

[0065] Specifically, in step S41, the preset value of the parameter change rate can be obtained by statistically analyzing the breathing patterns of healthy people or determining it with reference to medical guidelines. The preset value represents the expected range of the change rate of the respiratory frequency and respiratory amplitude.

[0066] More specifically, step S42 utilizes a dynamically adjusted threshold range to evaluate whether the current values of respiratory rate and respiratory amplitude are within a normal range and can adapt to individual differences and environmental changes; it also utilizes the rate of change to make a judgment, thereby identifying sudden changes in respiratory parameters by evaluating whether the rate of change of respiratory rate or respiratory amplitude exceeds a preset value.

[0067] More specifically, in step S43, after obtaining the first and second judgment results, these two results are combined and the corresponding pulmonary function assessment results are searched in a preset mapping table. The preset mapping table can be a multidimensional table, where the first dimension represents the first judgment result, the second dimension represents the second judgment result, and each entry in the table corresponds to a pulmonary function assessment result, such as "normal," "mildly abnormal," "moderately abnormal," "severely abnormal," etc. By consulting this table, the system can quickly determine the pulmonary function assessment result based on the combination of judgment results, achieving a comprehensive assessment of respiratory abnormalities.

[0068] In some preferred embodiments, the process of the MEMS respiration sensor outputting respiration data includes: B1. Obtain pressure change information; B2. Using a dynamic pressure loss parameter model to perform pressure compensation on pressure change information; B3. Obtaining flow rate change information based on the pressure change information after pressure compensation; B4. Calculate and output respiratory data based on flow rate change information over a preset time period; The pressure compensation process includes: C1. Real-time calculation of the average pressure within the preset breathing cycle; C2. Calculate and obtain pressure loss parameters based on the average pressure and the type of wearable MEMS respiratory sensor device; C3. Perform pressure compensation on the pressure change information according to the pressure loss parameter.

[0069] Specifically, in step B1, pressure change information is detected and obtained by a wearable MEMS respiratory sensor. The pressure changes sensed by this sensor during breathing are converted into electrical signals. In step B2, a dynamic pressure loss parameter model is used to evaluate and compensate for pressure losses caused by the device itself or environmental factors. Its purpose is to correct the pressure change information. In step B3, after pressure compensation, the compensated pressure data is converted into flow data. This is because flow can more directly reflect the respiratory state. Flow change information is derived from the compensated pressure change information. There is a predictable relationship between pressure and flow, so the conversion can be performed. In step B4, respiratory data such as respiratory frequency and respiratory amplitude can be calculated based on flow change information within a certain time window.

[0070] More specifically, during the pressure compensation process, step C1 is responsible for calculating the average pressure within a preset breathing cycle in real time, thereby reflecting the device's current pressure baseline. Step C2 calculates a pressure loss parameter based on the average pressure and the type of MEMS respiratory sensor device. Step C3 uses the pressure loss parameter to compensate the original pressure change information to obtain more accurate pressure data. The compensated pressure change information will more accurately reflect the pressure changes caused by actual breathing. The calculation of the pressure loss parameter takes into account the average pressure and the type of MEMS respiratory sensor device used. Different models or brands of sensors may have different pressure loss characteristics, and pressure loss may also vary with the average pressure.

[0071] In some preferred embodiments, step C2 comprises: C21. Obtain ambient temperature and humidity data and equipment usage time; C22, adjust the average pressure based on ambient temperature and humidity data and equipment usage time; C23. According to the corrected average pressure and the type of the wearable MEMS respiratory sensor device, a pre-established pressure loss parameter lookup table is consulted to obtain a corresponding pressure loss parameter.

[0072] Specifically, in step C21, the ambient temperature and humidity data can be collected in real time by the temperature and humidity sensor, and the device usage time can be obtained by the system recording the device's operating time. These data reflect the potential impact of external environmental changes and device state changes on the pressure sensor.

[0073] More specifically, in step C22, the mean pressure compensation adjustment can utilize a pre-set mathematical model that uses ambient temperature and humidity data and device usage time as input parameters and outputs a correction value for the mean pressure. For example, a multivariate regression model can be established, trained using experimental data to determine the relationship between ambient temperature and humidity, device usage time, and the mean pressure correction value. The purpose of the mean pressure compensation adjustment is to correct for mean pressure deviations caused by environmental and device factors, ensuring that the mean pressure value more accurately reflects pressure changes during actual breathing.

[0074] More specifically, in step C23, the pre-established pressure loss parameter lookup table can be a multidimensional lookup table, whose dimensions include the corrected mean pressure and the type of wearable MEMS respiratory sensor device. Each entry in the lookup table stores a pressure loss parameter for a specific mean pressure and device type. In practical applications, the corresponding pressure loss parameter can be retrieved from the lookup table based on the corrected mean pressure and device type, effectively improving the accuracy of the obtained pressure loss parameter.

[0075] More specifically, this approach no longer relies solely on average pressure and device type, but also takes into account factors such as ambient temperature and humidity, and device usage time, making the pressure loss parameter calculation more accurate. This allows for more precise pressure compensation, improving the accuracy and reliability of respiratory data collection.

[0076] Second, please refer to Figure 2 Some embodiments of the present application also provide a lung function assessment device for use in home-based elderly care scenarios, utilizing a wearable MEMS respiratory sensor device to monitor and assess the lung function of the elderly. The device comprises: Setting acquisition module 201, for acquiring a general dynamic threshold range of respiratory frequency and respiratory amplitude; An acquisition and calculation module 202 is configured to continuously acquire respiratory data output by the MEMS respiratory sensor, the respiratory data including respiratory rate and respiratory amplitude, and obtain and update the moving average and moving standard deviation of the respiratory rate and respiratory amplitude in real time based on a sliding window mechanism to calculate the rate of change of the respiratory rate and respiratory amplitude in real time; A data updating module 203 is configured to dynamically adjust the dynamic threshold ranges of respiratory frequency and respiratory amplitude according to the updated moving average and moving standard deviation; The comprehensive evaluation module 204 is used to comprehensively consider the adjusted dynamic threshold range and change rate to determine respiratory abnormalities and perform lung function evaluation.

[0077] The pulmonary function assessment device of the embodiment of the present application first obtains the universal dynamic threshold range of respiratory rate and respiratory amplitude as the initial assessment standard, then uses the wearable MEMS respiratory sensor to continuously collect the respiratory data of the elderly and combines the sliding window mechanism to calculate and update the moving average and moving standard deviation of the respiratory rate and respiratory amplitude in real time, thereby obtaining the change rate of the respiratory rate and respiratory amplitude, and then dynamically adjusts the dynamic threshold range of the respiratory rate and respiratory amplitude according to the updated moving average and moving standard deviation, so that the dynamic threshold range is adaptively adjusted with the change of respiratory data, and is more in line with the actual respiratory condition of the elderly. Finally, considering the adjusted dynamic threshold range and the change rate of respiratory parameters, respiratory abnormality judgment is made and a pulmonary function assessment result is generated, which can more accurately identify respiratory abnormalities and improve the accuracy and reliability of pulmonary function assessment.

[0078] The pulmonary function assessment device of the embodiment of the present application can adapt to the individual differences and dynamic changes in the breathing patterns of the elderly in home-based elderly care scenarios by dynamically adjusting the threshold ranges of respiratory frequency and respiratory amplitude. It overcomes the limitations of traditional fixed threshold methods, improves the accuracy of pulmonary function assessment, and realizes long-term tracking and management of the respiratory conditions of the elderly, providing technical support for the timely detection and prevention of respiratory diseases.

[0079] In some preferred embodiments, the pulmonary function assessment device of the embodiments of the present application is used to perform the pulmonary function assessment method provided in the first aspect above.

[0080] Thirdly, please refer to Figure 3 Some embodiments of the present application also provide a structural diagram of an electronic device. The present application provides an electronic device, including: a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other through a communication bus 303 and / or other forms of connection mechanisms (not marked). The memory 302 stores computer-readable instructions executable by the processor 301. When the electronic device is running, the processor 301 executes the computer-readable instructions to execute the method in any optional implementation of the above embodiments.

[0081] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method of any optional implementation of the above embodiment is executed. The computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0082] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0083] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across 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.

[0084] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0085] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0086] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A lung function assessment method for elderly people in home-based elderly care scenarios, using a wearable MEMS respiratory sensor device to monitor and assess lung function of the elderly, characterized by: The method comprises the following steps: S1. Obtaining a universal dynamic threshold range of respiratory rate and respiratory amplitude; S2. Continuously collect respiratory data output by the MEMS respiratory sensor, wherein the respiratory data includes respiratory rate and respiratory amplitude. Based on a sliding window mechanism, the moving average and moving standard deviation of the respiratory rate and respiratory amplitude are obtained and updated in real time to calculate the rate of change of the respiratory rate and respiratory amplitude in real time. S3. Dynamically adjusting the dynamic threshold ranges of the respiratory rate and respiratory amplitude according to the updated moving average and moving standard deviation; S4. Comprehensively consider the adjusted dynamic threshold range and change rate to determine respiratory abnormalities and conduct lung function assessment.

2. A lung function assessment method according to claim 1, characterized in that: Step C3 includes: S31. Analyze historical respiratory data and identify changing trends in breathing patterns; S32. Assess the depth of impact of chronic diseases on breathing patterns in the elderly; S33, obtaining the noise level of the MEMS respiratory sensor data; S34, configuring a compensation factor based on the change trend, the impact depth, the noise level, and the updated moving average and moving standard deviation; S35. Dynamically adjust the dynamic threshold ranges of respiratory frequency and respiratory amplitude according to the compensation factor.

3. A lung function assessment method according to claim 2, characterized in that: Step C33 includes: S331, identifying multiple noise sources in MEMS respiratory sensor data; S332. Select or combine multiple adaptive filters for the noise source, and filter the MEMS respiratory sensor data using the selected or combined adaptive filters; S333 , estimating and obtaining the noise level based on the difference between the MEMS respiratory sensor data before and after filtering.

4. A lung function assessment method according to claim 3, characterized in that: Step C33 further includes: S334: Evaluate the accuracy of the noise level based on the noise verification mechanism. If the accuracy is lower than expected, return to step S331. The process of evaluating the accuracy of the noise level based on the noise verification mechanism includes: A1. Obtain the target user's exercise status information; A2. determining the degree of influence of motion artifacts on noise level estimation based on the motion state information; A3. Adaptively adjust the evaluation strategy of the noise verification mechanism based on the impact level; A4. Using the adjusted noise verification mechanism, evaluate the accuracy of the noise level estimation.

5. A lung function assessment method according to claim 4, characterized in that: Step A3 includes: A31. Using a pattern recognition algorithm to determine the motion type based on the motion state information, and extracting the motion artifact frequency corresponding to the motion type; A32. Adjust the signal-to-noise ratio threshold and cross-correlation coefficient threshold evaluation parameters in the noise verification mechanism according to the motion type; A33. Adjust the weight of each frequency band in the noise verification mechanism according to the frequency of motion artifacts.

6. A lung function assessment method according to claim 1, characterized in that: Step S4 includes: Obtain preset values of respiratory rate and respiratory amplitude parameter change rates; Determine whether the respiratory frequency or respiratory amplitude exceeds the dynamic threshold range to obtain a first determination result, and determine whether the rate of change of the respiratory frequency or respiratory amplitude exceeds the preset value of the parameter change rate to obtain a second determination result; A lung function assessment result is generated according to the first judgment result, the second judgment result and a preset mapping table.

7. A lung function assessment method according to claim 1, characterized in that: The process of the MEMS respiratory sensor outputting respiratory data includes: B1. Obtain pressure change information; B2. performing pressure compensation on the pressure change information using a dynamic pressure loss parameter model; B3. Obtaining flow rate change information based on the pressure change information after pressure compensation; B4. Calculating and outputting the respiratory data based on the flow change information over a preset time period; The process of the pressure compensation process includes: C1. Real-time calculation of the average pressure within the preset breathing cycle; C2. Calculating and obtaining a pressure loss parameter based on the average pressure and the type of the wearable MEMS respiratory sensor device; C3. Perform pressure compensation on the pressure change information according to the pressure loss parameter.

8. A lung function assessment device, used in home-based elderly care scenarios, uses a wearable MEMS respiratory sensor device to monitor and assess the lung function of the elderly, characterized by: The device includes: Setting an acquisition module for acquiring a universal dynamic threshold range of respiratory rate and respiratory amplitude; An acquisition and calculation module is used to continuously collect respiratory data output by the MEMS respiratory sensor, wherein the respiratory data includes respiratory frequency and respiratory amplitude. Based on a sliding window mechanism, the module obtains and updates the moving average and moving standard deviation of the respiratory frequency and respiratory amplitude in real time to calculate the rate of change of the respiratory frequency and respiratory amplitude in real time. A data updating module, configured to dynamically adjust the dynamic threshold ranges of the respiratory frequency and respiratory amplitude according to the updated moving average and moving standard deviation; The comprehensive assessment module is used to comprehensively consider the adjusted dynamic threshold range and change rate to make respiratory abnormality judgments for lung function assessment.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 7 are executed.

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

Images