Intelligent mattress health monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of intelligent mattresses, and provides an intelligent mattress health monitoring method and system based on the Internet of Things, and the method comprises the steps: carrying out the analog-to-digital conversion of a sleep biological signal, obtaining a biological digital signal, calculating a signal quality index corresponding to the biological digital signal, and extracting a key biological signal from the sleep biological signal; performing feature extraction on the part pressure values to obtain pressure distribution features of different parts of the mattress user, calculating feature evolution intensity among the pressure distribution features, and analyzing a sleep posture corresponding to the mattress user; health risk factors in the sleep big data are analyzed, and the sleep health quality of the mattress user is evaluated; and calculating a sleep health index corresponding to the mattress user, formulating sleep feedback information of the mattress user according to the sleep health index, and generating a sleep health monitoring report of the mattress user in combination with the sleep feedback information. The invention aims to improve the accuracy of health monitoring of the intelligent mattress.

Description

Technical Field

[0001] The present invention relates to the technical field of smart mattresses, and in particular to a smart mattress health monitoring method and system based on the Internet of Things. Background Art

[0002] Smart mattress health monitoring is of great significance in today's era when people pay more and more attention to health. With the improvement of living standards, people pay more attention to sleep quality and health status. As a new health monitoring device, smart mattresses have a growing market demand, which can better meet people's needs for sleep health and improve the accuracy and convenience of health monitoring.

[0003] Existing smart mattress health monitoring mainly adopts the method of linkage with external devices. The smart mattress is linked with other smart devices (such as mobile phones, smart bracelets, smart home systems, etc.) to achieve more comprehensive health monitoring and environmental adjustment. For example, the lighting, temperature, humidity, etc. of the bedroom are automatically adjusted according to sleep data. However, during the use of this method, due to compatibility issues between devices of different brands and types, the linkage is unstable or cannot be achieved; excessive reliance on external devices, if one of the devices fails or has network connection problems, may affect the normal operation of the entire monitoring and adjustment system, thereby reducing the accuracy of smart mattress health monitoring. Summary of the invention

[0004] The present invention provides an intelligent mattress health monitoring method and system based on the Internet of Things, the main purpose of which is to improve the accuracy of intelligent mattress health monitoring.

[0005] To achieve the above purpose, the present invention provides an intelligent mattress health monitoring method based on the Internet of Things, comprising:

[0006] Using a smart mattress to detect a sleep biosignal of a mattress user, performing analog-to-digital conversion on the sleep biosignal to obtain a biodigital signal, calculating a signal quality index corresponding to the biodigital signal, and extracting a key biosignal from the sleep biosignal based on the signal quality index;

[0007] Using the preset pressure sensor in the smart mattress to collect the pressure values ​​of the parts of the mattress user in real time, extracting the features of the pressure values, obtaining the pressure distribution features of different parts of the mattress user, and calculating the feature evolution strength between the pressure distribution features, and analyzing the sleeping posture corresponding to the mattress user based on the feature evolution strength;

[0008] Connecting the smart mattress to a preset Internet of Things platform, dispatching the sleep big data related to the sleep posture from the Internet of Things platform, analyzing the health risk factors in the sleep big data, and evaluating the sleep health quality of the mattress user in combination with the health risk factors and the sleep posture;

[0009] Based on the key biological signals and the sleep health quality, the sleep health index corresponding to the mattress user is calculated, and according to the sleep health index, the sleep feedback information of the mattress user is formulated, and combined with the sleep feedback information, a sleep health monitoring report of the mattress user is generated.

[0010] Optionally, performing analog-to-digital conversion on the sleep biological signal to obtain a biological digital signal includes:

[0011] Performing noise reduction processing on the sleep biological signal to obtain a noise-reduced biological signal;

[0012] Performing a baseline flattening operation on the noise-reduced biological signal to obtain a flattened biological signal;

[0013] Performing signal enhancement on the flattened biological signal to obtain a target biological signal;

[0014] The target biological signal is converted into digital form to obtain a biological digital signal.

[0015] Optionally, calculating the signal quality index corresponding to the biological digital signal includes:

[0016] Calculating the signal strength corresponding to the biological digital signal, and calculating the average signal strength corresponding to the biological digital signal based on the signal strength;

[0017] Identifying a noise biological signal in the biological digital signal, and calculating a noise intensity corresponding to the noise biological signal;

[0018] Calculating the signal lengths corresponding to the biological digital signal and the noise biological signal respectively to obtain a first signal length and a second signal length;

[0019] Combining the signal strength and the noise strength, respectively calculating the standard deviations corresponding to the biological digital signal and the noise biological signal to obtain a first standard deviation and a second standard deviation;

[0020] In combination with the first signal length, the second signal length, the first standard deviation, the second standard deviation and the average signal strength, the signal quality index corresponding to the biological digital signal is calculated by the following formula:

[0021]

[0022] Among them, A represents the signal quality index corresponding to the biological digital signal, B represents the average signal strength, D represents the first signal length, and D a represents the second signal length, σ b represents the second standard deviation, σ d represents the first standard deviation, and T represents the signal stability threshold.

[0023] Optionally, the extracting features of the pressure values ​​at the positions to obtain pressure distribution features of different positions of the mattress user includes:

[0024] Calibrate the pressure value of the part to obtain a calibrated pressure value;

[0025] Normalizing the calibration pressure value to obtain a standard pressure value;

[0026] Extracting the dynamic characteristics of pressure at different parts of the mattress user according to the standard pressure value;

[0027] According to the pressure dynamic characteristics, the pressure distribution characteristics of different parts of the mattress user are analyzed.

[0028] Optionally, calculating the characteristic evolution intensity between the pressure distribution characteristics includes:

[0029] Performing vectorization processing on the pressure distribution characteristics to obtain a distribution characteristic vector;

[0030] Calculating a feature weight corresponding to the pressure distribution feature, and calculating a feature change rate corresponding to the pressure distribution feature based on the distribution feature vector;

[0031] In combination with the feature weight and the feature change rate of the distribution feature vector machine, the feature evolution intensity between the pressure distribution features is calculated by the following formula:

[0032]

[0033] Where E represents the characteristic evolution intensity between pressure distribution features, F i represents the eigenvector corresponding to the i-th feature in the pressure distribution feature, F i+1 represents the eigenvector corresponding to the i+1th feature in the pressure distribution feature, α represents the distance contribution, ω i represents the feature weight corresponding to the i-th feature in the pressure distribution feature, g i It represents the characteristic change rate corresponding to the i-th feature in the pressure distribution feature, and β represents the contribution of the change rate.

[0034] Optionally, analyzing the sleeping posture of the mattress user based on the characteristic evolution intensity includes:

[0035] Visualizing the characteristic evolution intensity to obtain an evolution intensity trend graph;

[0036] Based on the evolution intensity trend graph, calculating the evolution index value corresponding to the characteristic evolution intensity;

[0037] Based on the evolution index value, analyzing the evolution pattern corresponding to the characteristic evolution intensity;

[0038] Based on the evolution pattern, the sleeping posture corresponding to the mattress user is analyzed.

[0039] Optionally, analyzing the health risk factors in the sleep big data includes:

[0040] Optimizing the sleep big data to obtain optimized sleep data;

[0041] Extracting a sleep quality representation from the optimized sleep data, and dispatching user health information corresponding to the optimized sleep data;

[0042] Analyzing the health correlation between the user health information and the sleep quality representation;

[0043] Based on the health relevance, screening the health-related representation in the sleep quality representation;

[0044] Perform risk analysis on the health-related representation to obtain health risk factors.

[0045] Optionally, the combining the health risk factors and the sleeping posture to evaluate the sleeping health quality of the mattress user includes:

[0046] Identifying the body type corresponding to the sleeping body type, and analyzing the position effect of the body type on the mattress user;

[0047] Analyzing the causal dependency between the site effect and the health risk factor;

[0048] Based on the causal dependency, screening out risk-dependent sleeping postures from the sleeping postures;

[0049] Based on the risk-dependent sleeping posture, the sleeping health quality of the mattress user is evaluated.

[0050] Optionally, the step of calculating the sleep health index corresponding to the mattress user based on the key biological signal and the sleep health quality includes:

[0051] According to a preset quality scoring standard, the sleep health quality is quantified to obtain a health score;

[0052] Performing standardization processing on the key biological signal to obtain a standard biological signal;

[0053] Combining the health score and the standard biological signal, the sleep health index corresponding to the mattress user is calculated by the following formula:

[0054]

[0055] Among them, G represents the sleep health index corresponding to the mattress user, δ represents the signal regulation factor, and H c represents the cth signal value in the standard biological signal, c represents the signal sequence number corresponding to the standard biological signal, r represents the number of signals corresponding to the standard biological signal, μ represents the quality adjustment factor, and M represents the health score.

[0056] An intelligent mattress health monitoring system based on the Internet of Things, characterized in that the system comprises:

[0057] A bio-signal extraction module, for detecting a sleep bio-signal of a mattress user using a smart mattress, performing analog-to-digital conversion on the sleep bio-signal to obtain a bio-digital signal, calculating a signal quality index corresponding to the bio-digital signal, and extracting a key bio-signal from the sleep bio-signal based on the signal quality index;

[0058] A sleeping posture analysis module, for collecting the pressure values ​​of the parts of the mattress user in real time by using the pressure sensor preset in the smart mattress, performing feature extraction on the pressure values ​​of the parts to obtain the pressure distribution characteristics of different parts of the mattress user, and calculating the feature evolution strength between the pressure distribution characteristics, and analyzing the sleeping posture corresponding to the mattress user based on the feature evolution strength;

[0059] A sleep health quality evaluation module, used to connect the smart mattress to a preset Internet of Things platform, dispatch the sleep big data related to the sleep posture from the Internet of Things platform, analyze the health risk factors in the sleep big data, and evaluate the sleep health quality of the mattress user in combination with the health risk factors and the sleep posture;

[0060] The sleep health monitoring module is used to calculate the sleep health index corresponding to the mattress user based on the key biological signals and the sleep health quality, formulate the sleep feedback information of the mattress user according to the sleep health index, and generate a sleep health monitoring report for the mattress user in combination with the sleep feedback information.

[0061] The present invention can convert the sleep biological signal into a corresponding digital signal by performing analog-to-digital conversion on the sleep biological signal, so as to facilitate subsequent accurate signal processing. The present invention can obtain the pressure corresponding to the body part of the mattress user by using the preset pressure sensor in the smart mattress to collect the pressure value of the part of the mattress user in real time, and extract the characteristics of the pressure value of the part to obtain the pressure distribution description of the mattress user in the smart mattress. The present invention can obtain the potential factors that have an adverse effect on personal health by analyzing the health risk factors in the sleep big data, thereby improving the accuracy of the subsequent sleep health quality assessment. The present invention can calculate the sleep health index corresponding to the mattress user based on the key biological signal and the sleep health quality, which can comprehensively reflect the overall sleep health status of the mattress user and provide a quantitative basis for subsequent sleep improvement and health management. Therefore, the smart mattress health monitoring method and system based on the Internet of Things provided in the embodiment of the present invention can improve the accuracy of smart mattress health monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A schematic diagram of a flow chart of a smart mattress health monitoring method based on the Internet of Things provided by one embodiment of the present invention;

[0063] Figure 2 A functional module diagram of an Internet of Things-based smart mattress health monitoring system provided by one embodiment of the present invention.

[0064] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0066] The embodiment of the present application provides a smart mattress health monitoring method based on the Internet of Things. In the embodiment of the present application, the execution subject of the smart mattress health monitoring method based on the Internet of Things includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the smart mattress health monitoring method based on the Internet of Things can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0067] Reference Figure 1 FIG. 1 is a flow chart of a smart mattress health monitoring method based on the Internet of Things provided by an embodiment of the present invention. In this embodiment, the smart mattress health monitoring method based on the Internet of Things includes steps S1-S4.

[0068] S1. Use a smart mattress to detect the sleep biosignal of the mattress user, perform analog-to-digital conversion on the sleep biosignal to obtain a biodigital signal, calculate a signal quality index corresponding to the biodigital signal, and extract key biosignals from the sleep biosignal based on the signal quality index.

[0069] The present invention can convert the sleep bio-signal into a corresponding digital signal by performing analog-to-digital conversion on the sleep bio-signal, so as to facilitate subsequent accurate signal processing. The smart mattress detection mattress is a household product that uses a variety of advanced technologies to enhance sleep experience and health monitoring. The sleep bio-signal is a variety of biological information generated by the human body that can reflect the sleep state and physiological characteristics. The biological digital signal is the sleep bio-signal converted into a digital signal. Furthermore, the sleep bio-signal of the mattress user can be detected by utilizing sensors in the smart mattress, such as photoplethysmography (PPG) sensors, piezoelectric sensors, etc.

[0070] As an embodiment of the present invention, the analog-to-digital conversion of the sleep biosignal to obtain a biodigital signal includes: performing noise reduction processing on the sleep biosignal to obtain a noise-reduced biosignal, performing a baseline flattening operation on the noise-reduced biosignal to obtain a flattened biosignal, performing signal enhancement on the flattened biosignal to obtain a target biosignal, and performing analog-to-digital conversion on the target biosignal to obtain a biodigital signal.

[0071] Among them, the noise reduction biological signal is the signal obtained after the noise interference in the sleep biological signal is removed, the flattened biological signal is the signal obtained after the noise reduction biological signal is subjected to baseline flattening processing, and the target biological signal is the signal obtained after the low-intensity signal in the flattened biological signal is amplified or enhanced.

[0072] Optionally, the noise reduction processing of the sleep biological signal can be achieved by a low-pass filter; the baseline flattening operation of the noise-reduced biological signal can be achieved by a wavelet transformation method; the signal enhancement of the flattened biological signal can be achieved by a linear amplification method; the analog-to-digital conversion of the target biological signal can be achieved by an analog-to-digital converter.

[0073] The present invention calculates the signal quality index corresponding to the biological digital signal, and can use the signal quality index to understand the signal quality corresponding to the biological digital signal, thereby facilitating the subsequent extraction and processing of key biological signals, wherein the signal quality index represents the signal quality metric corresponding to the biological digital signal.

[0074] As an embodiment of the present invention, the calculation of the signal quality index corresponding to the biological digital signal includes: calculating the signal strength corresponding to the biological digital signal, calculating the average signal strength corresponding to the biological digital signal based on the signal strength, identifying the noise biological signal in the biological digital signal, and calculating the noise strength corresponding to the noise biological signal, respectively calculating the signal lengths corresponding to the biological digital signal and the noise biological signal to obtain a first signal length and a second signal length, and combining the signal strength and the noise strength, respectively calculating the standard deviations corresponding to the biological digital signal and the noise biological signal to obtain a first standard deviation and a second standard deviation, combining the first signal length, the second signal length, the first standard deviation, the second standard deviation and the average signal strength, and calculating the signal quality index corresponding to the biological digital signal by the following formula:

[0075]

[0076] Among them, A represents the signal quality index corresponding to the biological digital signal, B represents the average signal strength, D represents the first signal length, and D a represents the second signal length, σ b represents the second standard deviation, σ d represents the first standard deviation, and T represents the signal stability threshold.

[0077] Among them, the signal strength represents the signal energy corresponding to the biological digital signal, the noise biological signal is the noise signal in the biological digital signal, the noise strength represents the signal energy corresponding to the noise biological signal, the first signal length and the second signal length are the time lengths corresponding to the biological digital signal and the noise biological signal respectively, the first standard deviation and the second standard deviation represent the signal fluctuation degrees corresponding to the biological digital signal and the noise biological signal respectively, the signal stability threshold represents the stability measure of the biological digital signal, which can be set by the empirical value method, and the literature in the relevant field can be consulted to understand the signal stability threshold range commonly used in similar biological signal monitoring and analysis. Further, the calculation of the signal strength corresponding to the biological digital signal can be achieved by the root mean square algorithm; the identification of the noise biological signal in the biological digital signal can be achieved by the spectrum analysis method; the calculation of the noise strength corresponding to the noise biological signal can be achieved by the above-mentioned root mean square algorithm; the signal length corresponding to the biological digital signal and the noise biological signal can be obtained by calculating the difference between the signal timestamps to obtain the first signal length and the second signal length; the calculation of the standard deviation corresponding to the biological digital signal and the noise biological signal can be achieved by the mean square error calculation formula.

[0078] The present invention extracts key biological signals from the sleep biological signals based on the signal quality index, thereby obtaining key representative signals in the sleep biological signals, thereby providing a basis for the subsequent calculation of the sleep health index, wherein the key biological signals are representative biological signals in the sleep biological signals. Furthermore, when the signal quality index is greater than an index threshold, the key biological signals are extracted from the sleep biological signals, and the index threshold may be 0.8, or may be set according to actual application scenarios.

[0079] S2. Using the preset pressure sensor in the smart mattress to collect the pressure values ​​of the parts of the mattress user in real time, extracting the features of the pressure values, obtaining the pressure distribution features of different parts of the mattress user, and calculating the feature evolution intensity between the pressure distribution features. Based on the feature evolution intensity, analyzing the sleeping posture corresponding to the mattress user.

[0080] The present invention uses a preset pressure sensor in the smart mattress to collect the pressure values ​​of the parts of the mattress user in real time, so as to obtain the pressure corresponding to the body parts of the mattress user, and extracts the features of the part pressure values ​​to obtain a description of the pressure distribution of the mattress user in the smart mattress, wherein the pressure sensor is a device in the smart mattress for collecting pressure, the part pressure values ​​are the pressure values ​​of different parts of the mattress user in the smart mattress, and the pressure distribution characteristics are the specific manifestations of the pressure sizes at different positions of the mattress user.

[0081] As an embodiment of the present invention, the feature extraction of the pressure values ​​of the parts to obtain the pressure distribution characteristics of different parts of the mattress user includes: calibrating the pressure values ​​of the parts to obtain calibrated pressure values, normalizing the calibrated pressure values ​​to obtain standard pressure values, extracting the pressure dynamic characteristics of different parts of the mattress user according to the standard pressure values, and analyzing the pressure distribution characteristics of different parts of the mattress user based on the pressure dynamic characteristics.

[0082] Among them, the calibration pressure value is the pressure value obtained after the component pressure value is calibrated, the standard pressure value is the pressure value unified to the same scale by the calibration pressure value, and the pressure dynamic characteristics are the performance of the pressure changes of different parts of the mattress user over time. Optionally, the calibration processing of the pressure value of the part can be achieved by calibrating the sensor using a standard weight or a known pressure source to ensure the accuracy of the pressure data; the normalization processing of the calibration pressure value can be achieved by dividing the calibration pressure value by the maximum pressure value therein; according to the standard pressure value, the pressure variance and the pressure change frequency are calculated, so as to understand the degree of pressure fluctuation and the degree of pressure change, and then obtain the pressure dynamic characteristics of different parts of the mattress user; according to the different characteristics in the pressure dynamic characteristics, the pressure distribution characteristics of different parts of the mattress user are analyzed. For example, if the pressure change amplitude of a certain part is large, the frequency is high and the trend is unstable, it means that the pressure distribution of the part is uneven, and a feature description of the uneven pressure distribution is generated to generate the pressure distribution characteristics of different parts of the mattress user.

[0083] The present invention can obtain the severity of the change of the pressure distribution characteristics under different states by calculating the characteristic evolution intensity between the pressure distribution characteristics, and then understand the force change of different parts of the mattress user, so as to facilitate the subsequent analysis of the corresponding sleeping posture of the mattress user, wherein the characteristic evolution intensity represents the severity of the characteristic change between the pressure distribution characteristics.

[0084] As an embodiment of the present invention, the calculation of the characteristic evolution intensity between the pressure distribution features includes: performing vector processing on the pressure distribution features to obtain a distribution characteristic vector, calculating the characteristic weight corresponding to the pressure distribution feature, and calculating the characteristic change rate corresponding to the pressure distribution feature based on the distribution characteristic vector, combining the characteristic weight and the characteristic change rate of the distribution characteristic vector machine to calculate the characteristic evolution intensity between the pressure distribution features by the following formula:

[0085]

[0086] Where E represents the characteristic evolution intensity between pressure distribution features, F i represents the eigenvector corresponding to the i-th feature in the pressure distribution feature, F i+1 represents the eigenvector corresponding to the i+1th feature in the pressure distribution feature, α represents the distance contribution, ω i represents the feature weight corresponding to the i-th feature in the pressure distribution feature, g i It represents the characteristic change rate corresponding to the i-th feature in the pressure distribution feature, and β represents the contribution of the change rate.

[0087] Among them, the distribution feature vector is the expression vector corresponding to the pressure distribution feature, the feature change rate represents the degree of change corresponding to the pressure distribution feature, the distance contribution represents the importance of the feature distance in measuring the evolution intensity of the pressure distribution feature, and the change rate contribution represents the importance of the feature change rate in measuring the evolution intensity of the feature.

[0088] Optionally, the vectorization processing of the pressure distribution feature can be achieved through the word2vec algorithm; the feature entropy corresponding to the pressure distribution feature can be calculated and the feature entropy can be used as the feature weight of the pressure distribution feature; the difference of the distribution feature vector over time can be calculated to obtain the feature change rate corresponding to the pressure distribution feature; the distance contribution and the change rate contribution can be achieved through a machine learning algorithm, such as a support vector machine. During the training process, the support vector machine will automatically learn the relationship between the feature distance and the feature change rate and the pressure distribution change, and determine their contribution.

[0089] The present invention analyzes the sleeping posture corresponding to the mattress user based on the characteristic evolution intensity, and then obtains the sleeping posture corresponding to the mattress user, which provides a basis for the subsequent evaluation of sleep health quality, wherein the sleeping posture is the posture corresponding to the mattress user when sleeping.

[0090] As an embodiment of the present invention, analyzing the sleeping posture corresponding to the mattress user based on the characteristic evolution strength includes: visualizing the characteristic evolution strength to obtain an evolution strength trend graph, calculating an evolution index value corresponding to the characteristic evolution strength based on the evolution strength trend graph, analyzing an evolution pattern corresponding to the characteristic evolution strength based on the evolution index value, and analyzing the sleeping posture corresponding to the mattress user based on the evolution pattern.

[0091] Among them, the evolution intensity trend chart is a visualization chart corresponding to the feature evolution intensity, the evolution index value is a quantitative manifestation of the feature evolution intensity in the evolution intensity trend chart, and the evolution mode is the regular change method and state of the feature evolution intensity as time or other factors change.

[0092] Furthermore, the visualization of the characteristic evolution intensity can be achieved through a graphical method; the indicator value corresponding to the evolution intensity trend diagram is calculated according to the evolution index, so as to obtain the evolution indicator value corresponding to the characteristic evolution intensity. For example, by calculating the slope of the evolution intensity trend diagram, the change speed of the characteristic evolution intensity during this period can be obtained; the evolution pattern corresponding to the characteristic evolution intensity can be analyzed by principal component analysis, and the principal component analysis can be performed on the evolution indicator value to extract the main change pattern. PCA can convert multiple related indicator values ​​into a few unrelated principal components, each of which represents a specific evolution pattern. By analyzing the load and score of the principal component, the change of the characteristics at different times can be understood. The contribution degree of the intermediate point in each evolution mode is analyzed to analyze the evolution mode corresponding to the characteristic evolution intensity; based on the evolution mode, the corresponding sleeping posture of the mattress user is analyzed: if the characteristic evolution intensity shows periodic changes, it may mean that the sleeping posture of the mattress user repeats similar changes within a certain time interval. For example, during a whole night's sleep, the characteristic evolution intensity will increase at regular intervals, which may correspond to the user turning over at regular intervals, such as changing from lying on the back to lying on the side, or from lying on the side to lying on the back. This periodic posture change will cause the distribution of pressure on the mattress to change, thereby making the characteristic evolution intensity show periodicity.

[0093] S3. Connect the smart mattress to a preset Internet of Things platform, dispatch the sleep big data related to the sleep posture from the Internet of Things platform, analyze the health risk factors in the sleep big data, and evaluate the sleep health quality of the mattress user in combination with the health risk factors and the sleep posture.

[0094] By analyzing the health risk factors in the sleep big data, the present invention can obtain potential factors that have an adverse effect on personal health, thereby improving the accuracy of subsequent sleep health quality assessment, wherein the Internet of Things platform is the corresponding management and data interaction hub corresponding to the smart mattress, the sleep big data is the recorded data related to the sleeping posture, and the health risk factors are the factors in the sleep big data that pose a risk to health.

[0095] As an embodiment of the present invention, the analysis of health risk factors in the sleep big data includes: optimizing the sleep big data to obtain optimized sleep data, extracting sleep quality representations from the optimized sleep data, scheduling user health information corresponding to the optimized sleep data, analyzing the health correlation between the user health information and the sleep quality representation, screening the health-related representations in the sleep quality representation based on the health correlation, performing risk analysis on the health-related representations, and obtaining health risk factors.

[0096] Among them, the optimized sleep data is the selected data in the sleep big data, the sleep quality representation is the core embodiment of sleep in the optimized sleep data, the user health information is the health record information of the user corresponding to the optimized sleep data, the health relevance represents the description of the degree of correlation between the user health information and the sleep quality representation, and the health-related representation is the sleep representation in the sleep quality representation that has a relationship with health. Optionally, the optimization processing of the sleep big data can be achieved by the box plot method; the quality data related to sleep quality in the optimized sleep data is analyzed, and features are extracted for the quality data to obtain sleep quality representation, such as sleep duration, sleep depth and number of awakenings; the optimized sleep data The corresponding user health information can be realized through a preset repository, which is a database for storing user information; the analysis of the health correlation between the user health information and the sleep quality characterization can be realized through a linear regression model, and the linear coefficient between the user health information and the sleep quality characterization is calculated through the linear regression model, and the health correlation between the user health information and the sleep quality characterization is determined according to the linear coefficient; when the health correlation is highly correlated, the sleep quality characterization is screened to obtain a health correlation characterization, and a component load matrix of the health correlation characterization is constructed, and risk factors are identified from the component load matrix, It is determined which risk factors contribute more to health risks, and health risk factors are obtained.

[0097] The present invention evaluates the sleep health quality of the mattress user by combining the health risk factors and the sleeping posture. The sleep health quality can be used to understand the quality of sleep of the mattress user, thereby providing a basis for the subsequent calculation of the sleep health index, wherein the sleep health quality indicates the sleep health degree of the mattress user.

[0098] As an embodiment of the present invention, combining the health risk factors and the sleeping posture to evaluate the sleep health quality of the mattress user includes: identifying the body posture type corresponding to the sleeping posture, analyzing the site effect of the body posture type on the mattress user, analyzing the causal dependency between the site effect and the health risk factors, screening out risk-dependent sleeping postures from the sleeping postures based on the causal dependency, and evaluating the sleep health quality of the mattress user based on the risk-dependent sleeping postures.

[0099] Among them, the posture type is the specific category corresponding to the sleeping posture, such as supine, side-lying, prone, etc., the site effect is the local impact of the posture type on the part of the mattress user, the causal dependency relationship represents the causal influence relationship between the site effect and the health risk factor, the risk-dependent sleeping posture is the sleeping posture that is prone to cause health problems among the sleeping postures, and further, the corresponding posture type can be obtained by identifying the descriptive characters of the sleeping posture; the analysis of the site effect of the posture type on the mattress user can be achieved through an objective evaluation method, by using pressure distribution measurement equipment, such as a pressure sensing pad, to collect the pressure distribution of the human body in contact with the mattress in different postures. These devices can provide detailed pressure distribution maps, showing the amount of pressure borne by various parts of the body. For example, when lying on your back, the back and buttocks may be under greater pressure, and when lying on your side, the pressure on the shoulders and hips will be more prominent. By analyzing the pressure distribution data, the pressure effects of different body posture types on various parts of the body can be evaluated; the analysis of the causal dependency between the part effect and the health risk factor can be achieved through medical research methods, and the relevant medical literature can be consulted to understand the known associations between different part effects and specific health risk factors to achieve the analysis of the causal dependency; the body posture in the sleeping posture with the causal dependency is taken as the risk-dependent sleeping posture; by calculating the ratio of the number of the risk-dependent sleeping postures to the number of the sleeping postures, the sleep health quality of the mattress user is evaluated according to the ratio result. If the ratio is low, it means that the frequency of the risk-dependent sleeping posture is relatively low during the overall sleep process, which indicates that the user's posture during sleep is relatively healthy. When the ratio is high, it means that the risk-dependent sleeping posture occupies a large proportion in sleep, which may suggest that there are certain problems with the user's sleep health quality, and the sleep health quality can be set to poor or good.

[0100] S4. Based on the key biological signal and the sleep health quality, calculate the sleep health index corresponding to the mattress user, formulate the sleep feedback information of the mattress user according to the sleep health index, and generate a sleep health monitoring report for the mattress user in combination with the sleep feedback information.

[0101] The present invention calculates the sleep health index corresponding to the mattress user based on the key biological signals and the sleep health quality, which can comprehensively reflect the overall sleep health status of the mattress user and provide a quantitative basis for subsequent sleep improvement and health management, wherein the sleep health index represents the quantitative measurement value of sleep corresponding to the mattress user.

[0102] As an embodiment of the present invention, the sleep health index corresponding to the mattress user is calculated based on the key biological signal and the sleep health quality, including: according to a preset quality scoring standard, the sleep health quality is quantified to obtain a health score, the key biological signal is standardized to obtain a standard biological signal, and the sleep health index corresponding to the mattress user is calculated by combining the health score and the standard biological signal through the following formula:

[0103]

[0104] Among them, G represents the sleep health index corresponding to the mattress user, δ represents the signal regulation factor, and H c represents the cth signal value in the standard biological signal, c represents the signal sequence number corresponding to the standard biological signal, r represents the number of signals corresponding to the standard biological signal, μ represents the quality adjustment factor, and M represents the health score.

[0105] Among them, the quality scoring standard is a criterion system for quantitatively evaluating the sleep health quality and assigning corresponding scores. The quality scoring standard is set with reference to relevant domestic and international sleep health industry standards and guidelines. The health score is the specific expression value corresponding to the sleep health quality. If the sleep health quality is good, the health score can be set to 80 points. If the sleep health quality is poor, the health score can be set to 60 points. The standard biological signal is the signal obtained after the key biological signal is normalized. Furthermore, the standardized processing of the key biological signal can be achieved through the Z-score standardization method; the signal adjustment factor and the quality adjustment factor can be set through the expert evaluation method. Experts in related fields such as sleep medicine experts, biomedical engineers, data scientists, etc. are invited to form an evaluation team. The experts evaluate the importance of the key biological signals and the sleep health quality in the sleep health assessment based on their professional knowledge and experience, and determine the values ​​of the signal adjustment factor and the quality adjustment factor.

[0106] The present invention formulates sleep feedback information of the mattress user according to the sleep health index, generates corresponding feedback content about the sleep condition of the mattress user, and finally generates a sleep health monitoring report of the mattress user in combination with the sleep feedback information, thereby facilitating the mattress user to fully understand his or her own sleep health condition.

[0107] The present invention can convert the sleep biological signal into a corresponding digital signal by performing analog-to-digital conversion on the sleep biological signal, so as to facilitate subsequent accurate signal processing. The present invention can obtain the pressure corresponding to the body part of the mattress user by using the preset pressure sensor in the smart mattress to collect the pressure value of the part of the mattress user in real time, and extract the characteristics of the pressure value of the part to obtain the pressure distribution description of the mattress user in the smart mattress. The present invention can obtain the potential factors that have an adverse effect on personal health by analyzing the health risk factors in the sleep big data, thereby improving the accuracy of the subsequent sleep health quality assessment. The present invention can calculate the sleep health index corresponding to the mattress user based on the key biological signal and the sleep health quality, which can comprehensively reflect the overall sleep health status of the mattress user and provide a quantitative basis for subsequent sleep improvement and health management. Therefore, the smart mattress health monitoring method based on the Internet of Things provided in the embodiment of the present invention can improve the accuracy of smart mattress health monitoring.

[0108] like Figure 2 , which is a functional module diagram of an intelligent mattress health monitoring system based on the Internet of Things provided by an embodiment of the present invention.

[0109] The smart mattress health monitoring system 100 based on the Internet of Things of the present invention can be installed in an electronic device. According to the functions implemented, the smart mattress health monitoring system 100 based on the Internet of Things can include a biological signal extraction module 101, a sleep posture analysis module 102, a sleep health quality assessment module 103 and a sleep health monitoring module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0110] In this embodiment, the functions of each module / unit are as follows:

[0111] The bio-signal extraction module 101 is used to detect the sleep bio-signal of the mattress user using the smart mattress, perform analog-to-digital conversion on the sleep bio-signal to obtain a bio-digital signal, calculate a signal quality index corresponding to the bio-digital signal, and extract a key bio-signal from the sleep bio-signal based on the signal quality index;

[0112] The sleeping posture analysis module 102 is used to collect the pressure values ​​of the parts of the mattress user in real time by using the pressure sensor preset in the smart mattress, perform feature extraction on the pressure values, obtain the pressure distribution characteristics of different parts of the mattress user, and calculate the feature evolution strength between the pressure distribution characteristics, and analyze the sleeping posture corresponding to the mattress user based on the feature evolution strength;

[0113] The sleep health quality evaluation module 103 is used to connect the smart mattress to a preset Internet of Things platform, dispatch the sleep big data related to the sleep posture from the Internet of Things platform, analyze the health risk factors in the sleep big data, and evaluate the sleep health quality of the mattress user in combination with the health risk factors and the sleep posture;

[0114] The sleep health monitoring module 104 is used to calculate the sleep health index corresponding to the mattress user based on the key biological signals and the sleep health quality, formulate sleep feedback information of the mattress user according to the sleep health index, and generate a sleep health monitoring report for the mattress user in combination with the sleep feedback information.

[0115] In detail, each module described in the IoT-based smart mattress health monitoring system 100 described in the embodiment of the present application is used in the same manner as described above. Figure 1 The same technical means as the smart mattress health monitoring method based on the Internet of Things described in the text can produce the same technical effects, so I will not go into details here.

[0116] In the several embodiments provided by the present invention, it should be understood that the provided methods and systems can be implemented in other ways. For example, the method embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A smart mattress health monitoring method based on the Internet of Things, characterized in that: The method comprises: Using a smart mattress to detect a sleep biosignal of a mattress user, performing analog-to-digital conversion on the sleep biosignal to obtain a biodigital signal, calculating a signal quality index corresponding to the biodigital signal, and extracting a key biosignal from the sleep biosignal based on the signal quality index; Using the preset pressure sensor in the smart mattress to collect the pressure values ​​of the parts of the mattress user in real time, extracting the features of the pressure values, obtaining the pressure distribution features of different parts of the mattress user, and calculating the feature evolution strength between the pressure distribution features, and analyzing the sleeping posture corresponding to the mattress user based on the feature evolution strength; Connecting the smart mattress to a preset Internet of Things platform, dispatching the sleep big data related to the sleep posture from the Internet of Things platform, analyzing the health risk factors in the sleep big data, and evaluating the sleep health quality of the mattress user in combination with the health risk factors and the sleep posture; Based on the key biological signals and the sleep health quality, the sleep health index corresponding to the mattress user is calculated, and according to the sleep health index, the sleep feedback information of the mattress user is formulated, and combined with the sleep feedback information, a sleep health monitoring report of the mattress user is generated.

2. The method for health monitoring of an intelligent mattress based on the Internet of Things according to claim 1, characterized in that: The step of performing analog-to-digital conversion on the sleep biological signal to obtain a biological digital signal includes: Performing noise reduction processing on the sleep biological signal to obtain a noise-reduced biological signal; Performing a baseline flattening operation on the noise-reduced biological signal to obtain a flattened biological signal; Performing signal enhancement on the flattened biological signal to obtain a target biological signal; The target biological signal is converted into digital form to obtain a biological digital signal.

3. The method for health monitoring of an intelligent mattress based on the Internet of Things as claimed in claim 1, characterized in that: The calculating the signal quality index corresponding to the biological digital signal comprises: Calculating the signal strength corresponding to the biological digital signal, and calculating the average signal strength corresponding to the biological digital signal based on the signal strength; Identifying a noise biological signal in the biological digital signal, and calculating a noise intensity corresponding to the noise biological signal; Calculating the signal lengths corresponding to the biological digital signal and the noise biological signal respectively to obtain a first signal length and a second signal length; Combining the signal strength and the noise strength, respectively calculating the standard deviations corresponding to the biological digital signal and the noise biological signal to obtain a first standard deviation and a second standard deviation; In combination with the first signal length, the second signal length, the first standard deviation, the second standard deviation and the average signal strength, the signal quality index corresponding to the biological digital signal is calculated by the following formula: Among them, A represents the signal quality index corresponding to the biological digital signal, B represents the average signal strength, D represents the first signal length, and D a represents the second signal length, σ b represents the second standard deviation, σ d represents the first standard deviation, and T represents the signal stability threshold.

4. The method for health monitoring of an intelligent mattress based on the Internet of Things as claimed in claim 1, characterized in that: The feature extraction of the pressure values ​​of the parts to obtain the pressure distribution characteristics of different parts of the mattress user includes: Calibrate the pressure value of the part to obtain a calibrated pressure value; Normalizing the calibration pressure value to obtain a standard pressure value; Extracting the dynamic characteristics of pressure at different parts of the mattress user according to the standard pressure value; According to the pressure dynamic characteristics, the pressure distribution characteristics of different parts of the mattress user are analyzed.

5. The method for health monitoring of an intelligent mattress based on the Internet of Things as claimed in claim 1, characterized in that: The calculating the characteristic evolution intensity between the pressure distribution characteristics comprises: Performing vector processing on the pressure distribution characteristics to obtain a distribution characteristic vector; Calculating a feature weight corresponding to the pressure distribution feature, and calculating a feature change rate corresponding to the pressure distribution feature based on the distribution feature vector; In combination with the feature weight and the feature change rate of the distribution feature vector machine, the feature evolution intensity between the pressure distribution features is calculated by the following formula: Where E represents the characteristic evolution intensity between pressure distribution features, F i represents the eigenvector corresponding to the i-th feature in the pressure distribution feature, F i+1 represents the eigenvector corresponding to the i+1th feature in the pressure distribution feature, α represents the distance contribution, ω i represents the feature weight corresponding to the i-th feature in the pressure distribution feature, g i It represents the characteristic change rate corresponding to the i-th feature in the pressure distribution feature, and β represents the contribution of the change rate.

6. The method for monitoring health of an intelligent mattress based on the Internet of Things according to claim 1, characterized in that: The analyzing the sleeping posture of the mattress user based on the characteristic evolution intensity includes: Visualizing the characteristic evolution intensity to obtain an evolution intensity trend graph; Based on the evolution intensity trend graph, calculating the evolution index value corresponding to the characteristic evolution intensity; Based on the evolution index value, analyzing the evolution pattern corresponding to the characteristic evolution intensity; Based on the evolution pattern, the sleeping posture corresponding to the mattress user is analyzed.

7. The method for health monitoring of an intelligent mattress based on the Internet of Things as claimed in claim 1, characterized in that: The analyzing the health risk factors in the sleep big data includes: Optimizing the sleep big data to obtain optimized sleep data; Extracting a sleep quality representation from the optimized sleep data, and dispatching user health information corresponding to the optimized sleep data; Analyzing the health correlation between the user health information and the sleep quality representation; Based on the health relevance, screening the health-related representation in the sleep quality representation; Perform risk analysis on the health-related representation to obtain health risk factors.

8. The method for health monitoring of an intelligent mattress based on the Internet of Things as claimed in claim 1, characterized in that: The step of evaluating the sleep health quality of the mattress user by combining the health risk factors and the sleep posture includes: Identifying the body type corresponding to the sleeping body type, and analyzing the position effect of the body type on the mattress user; Analyzing the causal dependency between the site effect and the health risk factor; Based on the causal dependency, screening out risk-dependent sleeping postures from the sleeping postures; Based on the risk-dependent sleeping posture, the sleeping health quality of the mattress user is evaluated.

9. The method for health monitoring of an intelligent mattress based on the Internet of Things as claimed in claim 1, characterized in that: The step of calculating the sleep health index corresponding to the mattress user based on the key biological signal and the sleep health quality includes: According to a preset quality scoring standard, the sleep health quality is quantified to obtain a health score; Performing standardization processing on the key biological signal to obtain a standard biological signal; Combining the health score and the standard biological signal, the sleep health index corresponding to the mattress user is calculated by the following formula: Among them, G represents the sleep health index corresponding to the mattress user, δ represents the signal regulation factor, and H c represents the cth signal value in the standard biological signal, c represents the signal sequence number corresponding to the standard biological signal, r represents the number of signals corresponding to the standard biological signal, μ represents the quality adjustment factor, and M represents the health score.

10. An intelligent mattress health monitoring system based on the Internet of Things, characterized in that: The system comprises: A bio-signal extraction module, for detecting a sleep bio-signal of a mattress user using a smart mattress, performing analog-to-digital conversion on the sleep bio-signal to obtain a bio-digital signal, calculating a signal quality index corresponding to the bio-digital signal, and extracting a key bio-signal from the sleep bio-signal based on the signal quality index; A sleeping posture analysis module, for collecting the pressure values ​​of the parts of the mattress user in real time by using the pressure sensor preset in the smart mattress, performing feature extraction on the pressure values ​​of the parts to obtain the pressure distribution characteristics of different parts of the mattress user, and calculating the feature evolution strength between the pressure distribution characteristics, and analyzing the sleeping posture corresponding to the mattress user based on the feature evolution strength; A sleep health quality evaluation module, used to connect the smart mattress to a preset Internet of Things platform, dispatch the sleep big data related to the sleep posture from the Internet of Things platform, analyze the health risk factors in the sleep big data, and evaluate the sleep health quality of the mattress user in combination with the health risk factors and the sleep posture; The sleep health monitoring module is used to calculate the sleep health index corresponding to the mattress user based on the key biological signals and the sleep health quality, formulate the sleep feedback information of the mattress user according to the sleep health index, and generate a sleep health monitoring report for the mattress user in combination with the sleep feedback information.

Images