CN117814766A - Near infrared spectrum physical and mental pressure and sleep quality monitoring system - Google Patents
Near infrared spectrum physical and mental pressure and sleep quality monitoring system Download PDFInfo
- Publication number
- CN117814766A CN117814766A CN202410140388.9A CN202410140388A CN117814766A CN 117814766 A CN117814766 A CN 117814766A CN 202410140388 A CN202410140388 A CN 202410140388A CN 117814766 A CN117814766 A CN 117814766A
- Authority
- CN
- China
- Prior art keywords
- change
- data
- physical
- pressure
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 110
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 59
- 230000003340 mental effect Effects 0.000 title claims abstract description 37
- 230000003860 sleep quality Effects 0.000 title claims abstract description 24
- 230000008859 change Effects 0.000 claims abstract description 139
- 238000005516 engineering process Methods 0.000 claims abstract description 46
- 238000007635 classification algorithm Methods 0.000 claims abstract description 12
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 51
- 239000008280 blood Substances 0.000 claims description 51
- 210000004369 blood Anatomy 0.000 claims description 51
- 229910052760 oxygen Inorganic materials 0.000 claims description 51
- 239000001301 oxygen Substances 0.000 claims description 51
- 238000000034 method Methods 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 35
- 238000001228 spectrum Methods 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000000747 cardiac effect Effects 0.000 claims description 25
- 238000012360 testing method Methods 0.000 claims description 24
- 230000005540 biological transmission Effects 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 20
- 230000000241 respiratory effect Effects 0.000 claims description 19
- 230000008030 elimination Effects 0.000 claims description 15
- 238000003379 elimination reaction Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 230000009467 reduction Effects 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 11
- 230000008667 sleep stage Effects 0.000 claims description 11
- 230000007704 transition Effects 0.000 claims description 9
- 238000012986 modification Methods 0.000 claims description 8
- 230000004048 modification Effects 0.000 claims description 8
- 238000002360 preparation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- INGWEZCOABYORO-UHFFFAOYSA-N 2-(furan-2-yl)-7-methyl-1h-1,8-naphthyridin-4-one Chemical compound N=1C2=NC(C)=CC=C2C(O)=CC=1C1=CC=CO1 INGWEZCOABYORO-UHFFFAOYSA-N 0.000 claims description 6
- 108010054147 Hemoglobins Proteins 0.000 claims description 6
- 102000001554 Hemoglobins Human genes 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 108010002255 deoxyhemoglobin Proteins 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 108010064719 Oxyhemoglobins Proteins 0.000 claims description 3
- 238000010521 absorption reaction Methods 0.000 claims description 3
- 230000003920 cognitive function Effects 0.000 claims description 3
- 238000009472 formulation Methods 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000006996 mental state Effects 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000002618 waking effect Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 206010049816 Muscle tightness Diseases 0.000 description 1
- 208000000112 Myalgia Diseases 0.000 description 1
- 206010062519 Poor quality sleep Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 208000013465 muscle pain Diseases 0.000 description 1
- 230000036391 respiratory frequency Effects 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a near infrared spectrum physical and mental pressure and sleep quality monitoring system, which relates to the technical field of human sleep monitoring. According to the invention, the physiological characteristics of the testers are calculated and reflected by utilizing near infrared spectrum data, the sleep state identification model is built by combining a classification algorithm, the analysis model is built by combining a frequency domain change technology, the physical sign states of the testers are analyzed and evaluated from multiple dimensions, the sleep state identification model and the analysis model are integrated into the massage equipment controller, the massage equipment can monitor the pressure and the sleep state of the user in real time, the working mode of the massage equipment is adjusted in real time according to the monitoring data, personalized massage experience is provided, and more comfortable and personalized service experience is provided for the user.
Description
Technical Field
The invention relates to the technical field of human sleep monitoring, in particular to a near infrared spectrum physical and mental pressure and sleep quality monitoring system.
Background
Along with the acceleration of the life rhythm, people face high competition and working pressure, long-time work, study, social pressure and the like possibly cause physical and psychological fatigue of people, influence the sleep quality, and meanwhile, irregular work and rest time, unhealthy diet, lack of exercise and other bad life habits are factors causing sleep problems to influence the physiological rhythm and sleep cycle of the body.
In order to improve sleep quality and regulate the state of mind and body, more and more people can relieve the stress of mind and body and improve the sleep quality by using the massage equipment, the massage can promote the relaxation of body and mind and relieve the stress and anxiety, so that the sleep quality is improved, the massage equipment can help relax muscles, relieve muscle tension and pain, improve the comfort level of the body, help falling asleep and keeping the sleep state, and can also promote the blood circulation and increase the blood flow to the muscles and tissues, thereby helping the body to remove metabolic products more quickly, relieving physical fatigue and improving the sleep quality.
However, most of the working modes of the massage equipment in the prior art are fixed when the massage equipment is used, and the working modes of the massage equipment cannot be adaptively changed according to the state sleep state and the physical and psychological pressure state of a user, so that the personalized service experience of the massage equipment is reduced.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
In order to solve the problems, the invention provides a near infrared spectrum physical and mental pressure and sleep quality monitoring system, which realizes the purposes of adjusting the working mode of massage equipment in real time according to monitoring data and providing personalized massage experience.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the invention provides a near infrared spectrum physical and mental pressure and sleep quality monitoring system, which comprises a pre-test preparation unit, a signal data acquisition unit, a sleep state identification unit, a physical and mental pressure acquisition unit, a working mode formulation unit, a real-time monitoring integration unit and a monitoring modification adjustment unit, wherein the pre-test preparation unit is used for acquiring a physical and mental pressure of a user;
the early-stage test preparation unit is used for selecting a tester with a specified number of people to lie on the massage equipment based on a preset standard, and wearing near infrared spectrum equipment pre-installed on the massage equipment for the tester;
the signal data acquisition unit is used for starting the sensors inside the near infrared spectrum equipment and the massage equipment to acquire near infrared spectrum data and sign signal data;
The sleep state recognition unit is used for calculating and reflecting physiological characteristics of the testers by utilizing the near infrared spectrum data and combining the physiological characteristics with a classification algorithm to establish a sleep state recognition model;
the physical and psychological pressure acquisition unit is used for constructing an analysis model to analyze physical sign state changes of the tester by combining the physical sign signal data with the frequency domain change technology, and acquiring abnormal information according to the change results to judge physical and psychological pressure results;
the working mode making unit is used for inputting the sleep state identification result and the physical and psychological pressure result to the massage equipment controller, and the control end makes a corresponding working mode according to the result;
the real-time monitoring integration unit is used for integrating the sleep state identification model and the analysis model into the massage equipment controller and monitoring the pressure and the sleep state of the user in real time by utilizing the near infrared spectrum equipment and the sensor;
the monitoring modification and adjustment unit is used for the massage equipment controller to acquire the identification result according to the monitoring data and modify the working mode of the massage equipment to adjust the self state of the user.
Preferably, the sleep state identification unit comprises a spectrum data correction module, a physiological characteristic acquisition module, a physiological characteristic processing module and an identification model construction module;
The spectrum data correction module is used for collecting spectrum data of a tester in a waking state, a transition stage and a deep sleep stage according to near infrared spectrum equipment and preprocessing the spectrum data by utilizing a multi-element scattering correction technology;
the physiological characteristic acquisition module is used for extracting blood oxygen level change of a tester by adopting a variable elimination technology and measuring physiological characteristic indexes of blood oxygen average value, respiratory wave, heartbeat and cardiac intensity according to a blood oxygen level change result;
the physiological characteristic processing module is used for converting physiological characteristic indexes into a data set form, performing real-time missing value interpolation processing operation through a multi-order Lagrangian difference method, and setting segmentation thresholds of different sleep states based on the data set;
the recognition model construction module is used for acquiring the center of the initial cluster in the physiological characteristic index, determining the physiological characteristic of the maximum association characteristic by utilizing a classification algorithm, traversing all spectrum data to acquire a time sequence matrix, and constructing a sleep state recognition model.
Preferably, the variable elimination technology is adopted to extract the blood oxygen level change of the tester, and the physiological characteristic indexes of blood oxygen average value, respiratory wave, heartbeat and cardiac intensity are determined according to the blood oxygen level change result, including:
Performing variable elimination operation on the pretreated spectrum data by adopting a variable elimination technology to remove interference variables, and judging the absorption effect of a near infrared band in the spectrum data;
judging the content of oxyhemoglobin and deoxyhemoglobin according to the light intensity change of the infrared spectrum after the infrared spectrum is transmitted through the skin of the tester, and measuring the cognitive function of the tester;
judging the content analysis blood oxygen change level of the oxygen-containing hemoglobin and the deoxyhemoglobin of the testers in different stages, and selecting the time point with the highest blood oxygen change in the range of three stages based on the judging result;
calculating an average value of blood oxygen levels in three stages as an average blood oxygen value, and taking the average blood oxygen value as a physiological characteristic for distinguishing sleep and awake states;
and judging the respiration change and the blood volume change of the tester according to the blood oxygen change level, extracting respiration waves and cardiac signals, and analyzing the change amplitude of the hemoglobin concentration according to the cardiac signals to evaluate the cardiac intensity.
Preferably, the method comprises the steps of obtaining the center of an initial cluster in a physiological characteristic index, determining the physiological characteristic of the maximum associated characteristic by using a classification algorithm, traversing all spectrum data to obtain a time sequence matrix, and constructing a sleep state recognition model, wherein the sleep state recognition model comprises the following steps:
Performing dimension reduction processing on physiological characteristics to mine association relations among respiratory waves, heartbeat and cardiac intensity, and using a flow clustering technology to set a threshold value to select a blood oxygen average value as the center of an initial cluster;
judging the distance from the respiratory wave, the heartbeat and the cardiac intensity to the center of the initial cluster, and selecting the blood oxygen average value which is smaller than a threshold value and is close to the center of the initial cluster as a data cluster;
selecting the respiratory wave, the heartbeat and the cardiac intensity with the smallest distance as the association point with the largest association relation based on the data cluster;
obtaining an objective function of the association points by adopting a square error to determine the physiological characteristics of the maximum association characteristics, and traversing all spectrum data to obtain all physiological characteristics;
and constructing a sleep state recognition model according to a time sequence matrix of the corresponding state stage construction time sequence to obtain the recognition model operation.
Preferably, the expression of the objective function of the association point is:
；
in the method, in the process of the invention,Lan objective function value representing the association point;Ma squared error value representing the associated point;Trepresenting data points in a data cluster;arepresenting the number of data clusters;C b+ representing an initial cluster center point;Erepresenting a total number of data points in the data set;P a represent the firstaAn average of the individual data clusters; rIndicating the set threshold.
Preferably, constructing the sleep state recognition model according to the corresponding state stage construction time sequence to obtain a time sequence matrix for the recognition model to run includes:
sequentially arranging the physiological features and the corresponding state phases to construct a combined time sequence which takes the state phase feature set as a row and takes a time point as a column;
when the number of lines in the time sequence matrix is smaller than the time point, splitting the time sequence line by line according to the dimension space sequence, superposing the time sequence line by line to generate a high-dimension random matrix, and taking each column of the matrix as a single individual for extracting the dimension;
converting the high-dimensional random matrix into a sample covariance matrix, estimating the sample covariance matrix by using a maximum likelihood estimation method, and mapping the characteristic values to a complex domain to obtain a distribution rule of physiological characteristics;
and determining distinguishing features of the sleep state based on the distribution rule and a preset constraint condition, and constructing a sleep state recognition model.
Preferably, the physical and mental pressure acquisition unit comprises a physical sign signal processing module, a characteristic frequency revealing module, an analysis model establishing module and a pressure result judging module;
the physical sign signal processing module is used for capturing physical sign change signals of a tester by using a pressure sensor arranged in the massage equipment and performing noise reduction processing on the characteristic change signals by using a threshold change method;
The characteristic frequency revealing module is used for determining the number of decomposition layers based on the correlation between the scale coefficient and the original sign change signal and carrying out wavelet decomposition operation to reveal the characteristics of the change signal by combining the frequency domain change;
the analysis model establishing module is used for establishing an analysis model to analyze the physical sign state change of the tester by adopting the connection between the machine learning technology description change signal and the characteristics;
the pressure result judging module is used for setting a non-pressure, medium-pressure and high-pressure distinguishing baseline according to the sign state change result, inputting sign change signals into the analysis model and outputting distinguishing baseline to judge the physical and psychological pressure result of the tester.
Preferably, determining the number of decomposition layers based on the correlation of the scale factor and the original sign change signal, and performing the wavelet decomposition operation in combination with the frequency domain change reveals the characteristics of the change signal includes:
decomposing an original signal into a plurality of groups of layers by using scale coefficients, setting high-level capturing low-frequency information, and capturing high-frequency information at the low level;
carrying out framing and emphasis processing on the decomposed original signals based on a wavelet function to judge the correlation between each group of layers and the original signals;
and carrying out segmentation processing and correlation combination on the original signal through a time window to obtain a state coefficient, and carrying out convolution operation and discrete cosine transformation on the state coefficient to obtain a state frequency coefficient as the characteristic of the change signal.
Preferably, the establishing an analysis model for analyzing the change of the physical sign state of the tester by using the machine learning technology to describe the connection between the change signal and the characteristic comprises:
constructing a plane based on a machine learning technology as a decision plane to describe the relation between the change signal and the feature, and distinguishing the classification patterns of the sign states according to the description result;
according to the classification patterns, a state classifier is established by utilizing a support vector machine to learn and train the physical sign states, and an analysis model is established by combining the state classifier with principal component analysis;
and inputting the change signal into an analysis model to analyze the change of the physical sign state of the tester.
Preferably, the real-time monitoring integrated unit comprises an integrated conversion operation module, a control transmission connection module, a monitoring protocol control module, an integrated storage control module and a pressure sleep monitoring module;
the integrated conversion operation module is used for collecting and converting the sleep state identification result and the physical and psychological stress test result into homogeneous data in real time by utilizing a virtual database technology;
the control transmission connection module is used for converting the homogeneous data into control signals, transmitting the control signals into the massage controller by utilizing a network transmission technology, synchronously converting the control signals and the homogeneous data, and connecting the control signals with the massage controller;
The monitoring protocol control module is used for establishing an integrated monitoring protocol for the massage controller to establish a transmission channel for the control signal, and giving a monitoring protocol control value according to sleep state identification and physical and mental pressure;
the integrated storage control module is used for integrating a specified protocol control value into the massage controller, automatically detecting the change of the control parameter, and storing monitoring data and monitoring information by utilizing the port state;
the pressure sleep monitoring module is used for inputting the monitoring data and the monitoring information into the corresponding mapping areas, obtaining a correct monitoring result through corresponding control semantic analysis in the area mapping, and completing the purpose of monitoring the pressure and sleep state of the user.
The beneficial effects of the invention are as follows:
1. according to the invention, the physiological characteristics of the testers are calculated and reflected by utilizing near infrared spectrum data, the sleep state identification model is built by combining a classification algorithm, the analysis model is built by combining a frequency domain change technology, the physical sign states of the testers are analyzed and evaluated from multiple dimensions, the sleep state identification model and the analysis model are integrated into the massage equipment controller, the massage equipment can monitor the pressure and the sleep state of the user in real time, the working mode of the massage equipment is adjusted in real time according to the monitoring data, personalized massage experience is provided, and more comfortable and personalized service experience is provided for the user.
2. According to the invention, spectral data are acquired in the awake state, the transition stage and the deep sleep stage, physiological characteristic changes under different sleep states are covered, the variable elimination technology is used for extracting blood oxygen level changes to measure blood oxygen mean value, respiratory wave, heartbeat and heart intensity to provide comprehensive physiological characteristic information, meanwhile, physiological characteristic indexes are converted into a data set form, and a sleep state identification model is established based on different set sleep state segmentation thresholds, so that the aim of accurately identifying different sleep states of a tester from multiple dimensions is fulfilled.
3. The invention captures the sign change signal of the tester by using the pressure sensor arranged in the massage equipment, and carries out noise reduction treatment on the characteristic change signal by using the threshold change method, thus effectively extracting the sign change signal of the tester, describing the relation between the change signal and the characteristic by adopting the machine learning technology, establishing an analysis model, judging the dynamic change of the user when the massage equipment is used, and finding and identifying the abnormal condition of the physical and psychological pressure state of the user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a schematic block diagram of a near infrared spectrum physical and mental pressure and sleep quality monitoring system according to an embodiment of the present invention.
In the figure:
1. a preliminary test preparation unit; 2. a signal data acquisition unit; 3. a sleep state recognition unit; 301. a spectral data correction module; 302. a physiological characteristic acquisition module; 303. a physiological characteristic processing module; 304. the model construction module is identified; 4. a body and mind pressure acquisition unit; 401. the sign signal processing module; 402. a characteristic frequency revealing module; 403. an analysis model building module; 404. a pressure result judging module; 5. a working mode making unit; 6. monitoring the integrated unit in real time; 601. integrating a conversion operation module; 602. a control transmission connection module; 603. a monitoring protocol control module; 604. an integrated storage control module; 605. a pressure sleep monitoring module; 7. the modification adjustment unit is monitored.
Detailed Description
The invention is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular forms also are intended to include the plural forms, and furthermore, it is to be understood that the terms "comprises" and "comprising" and any variations thereof are intended to cover non-exclusive inclusions, such as, for example, processes, methods, systems, products or devices that comprise a series of steps or units, are not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or inherent to such processes, methods, products or devices.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, the present invention provides a near infrared spectrum physical and mental pressure and sleep quality monitoring system, which includes a pre-test preparation unit 1, a signal data acquisition unit 2, a sleep state identification unit 3, a physical and mental pressure acquisition unit 4, a working mode formulation unit 5, a real-time monitoring integration unit 6 and a monitoring modification adjustment unit 7.
The early-stage test preparation unit 1 is used for selecting a tester with a specified number of people to lie on the massage equipment based on a preset standard and wearing near infrared spectrum equipment pre-installed on the massage equipment for the tester.
In this embodiment, selecting a specified number of testers to lie on the massage device based on a preset standard, and wearing the near infrared spectrum device pre-installed on the massage device for the testers includes the following steps:
the standard of the test is definitely defined before the test is started, including determining the specific crowd of the testers, the test environment and the test index, and selecting the testers meeting the conditions according to the preset standard, wherein the factors include age, gender, health condition and the like are considered.
The selected test person is asked to a designated position of the massage device, in particular a couch or a seat of the massage device, and the test person is simultaneously provided with a near infrared spectrum device which is pre-installed to the massage device, wherein the spectrum device is installed at a specific part (such as a forehead, a wrist and the like) so as to monitor physiological data in real time.
The near infrared spectrum device is calibrated and checked before the test is started, so that the normal operation of the device is ensured, and physiological data can be accurately acquired.
And the signal data acquisition unit 2 is used for starting the sensors inside the near infrared spectrum equipment and the massage equipment to acquire near infrared spectrum data and sign signal data.
In this embodiment, starting the sensors inside the near infrared spectrum device and the massage device to acquire the near infrared spectrum data and the sign signal data includes the following steps:
the sensors inside the near infrared spectrum equipment and the massage equipment are ensured to be correctly installed and connected in a normal working state, the power supplies of the near infrared spectrum equipment and the massage equipment are started, and in the starting stage, the equipment is calibrated, so that the accurate and reliable measurement results of the near infrared spectrum equipment and the sensors are ensured.
And data communication is carried out between the near infrared spectrum device and the sensor, so that the connection and communication channels between the near infrared spectrum device and the sensor inside the massage device are smooth, and the data acquisition function of the near infrared spectrum device and the sensor inside the massage device is started.
And the sleep state recognition unit 3 is used for calculating and reflecting the physiological characteristics of the testers by utilizing the near infrared spectrum data and combining the physiological characteristics with a classification algorithm to establish a sleep state recognition model.
In the present embodiment, the sleep state recognition unit 3 includes a spectral data correction module 301, a physiological characteristic acquisition module 302, a physiological characteristic processing module 303, and a recognition model construction module 304.
The spectrum data correction module 301 is configured to collect spectrum data of a tester in an awake state, a transition stage and a deep sleep stage according to a near infrared spectrum device, and perform preprocessing on the spectrum data by using a multi-component scattering correction technology.
Specifically, the method for collecting the spectrum data of the testers in the awake state, the transition stage and the deep sleep stage according to the near infrared spectrum equipment and preprocessing the spectrum data by utilizing the multi-component scattering correction technology comprises the following steps:
when a tester enters an awake state, a transition stage and a deep sleep stage, near infrared spectrum equipment is used for collecting spectrum data in real time, and meanwhile, the collected spectrum data and the sleep stage of the tester are required to be calibrated in an accurate time synchronization mode.
The primary processing of the collected raw spectral data, including removing noise, outliers or motion artifacts, and segmenting the collected spectral data according to different sleep stages, namely, awake state, transition stage and deep sleep stage.
And (3) performing a multi-element scattering correction technology, eliminating spectral changes in the sample caused by multi-element scattering, performing baseline correction, eliminating baseline drift possibly existing in spectral data, and performing wavelength correction at the same time so as to ensure that the spectral data between different testers and different monitoring time points have consistent wavelength calibration.
The physiological characteristic obtaining module 302 is configured to extract a blood oxygen level change of the tester by using a variable elimination technique, and determine physiological characteristic indexes of a blood oxygen mean value, a respiratory wave, a heartbeat and a cardiac intensity according to a blood oxygen level change result.
Specifically, the variable elimination technology is adopted to extract the blood oxygen level change of the tester, and the physiological characteristic indexes of blood oxygen mean value, respiratory wave, heartbeat and cardiac intensity are determined according to the blood oxygen level change result, including:
performing variable elimination operation on the pretreated spectrum data by adopting a variable elimination technology to remove interference variables, and judging the absorption effect of a near infrared band in the spectrum data;
judging the content of oxyhemoglobin and deoxyhemoglobin according to the light intensity change of the infrared spectrum after the infrared spectrum is transmitted through the skin of the tester, and measuring the cognitive function of the tester;
judging the content analysis blood oxygen change level of the oxygen-containing hemoglobin and the deoxyhemoglobin of the testers in different stages, and selecting the time point with the highest blood oxygen change in the range of three stages based on the judging result;
calculating an average value of blood oxygen levels in three stages as an average blood oxygen value, and taking the average blood oxygen value as a physiological characteristic for distinguishing sleep and awake states;
And judging the respiration change and the blood volume change of the tester according to the blood oxygen change level, extracting respiration waves and cardiac signals, and analyzing the change amplitude of the hemoglobin concentration according to the cardiac signals to evaluate the cardiac intensity.
The physiological characteristic processing module 303 is configured to convert the physiological characteristic index into a data set form, perform a real-time missing value interpolation processing operation by using a multi-order lagrangian difference method, and set segmentation thresholds of different sleep states based on the data set.
Specifically, converting the physiological characteristic index into a data set form, performing real-time missing value interpolation processing operation by a multi-order Lagrangian difference method, and setting segmentation thresholds of different sleep states based on the data set comprises the following steps:
the collected physiological characteristic indexes are arranged into a data set form, physiological data of each tester should form rows of the data set, different physiological indexes form columns of the data set, and interpolation methods such as a multi-order Lagrangian difference method and the like are adopted to process missing values in real time to fill gaps in the data set.
The data set is standardized, different physiological indexes are ensured to have the same scale, and the segmentation threshold values of different sleep states are set according to the physiological characteristic indexes, including the threshold values of waking, light sleep and deep sleep are set based on respiratory waves, heartbeats and cardiac intensity.
The recognition model construction module 304 is configured to obtain a center of an initial cluster in the physiological characteristic index, determine a physiological characteristic of a maximum association characteristic by using a classification algorithm, traverse all spectrum data to obtain a time sequence matrix, and construct a sleep state recognition model.
Specifically, the center of an initial cluster in the physiological characteristic index is obtained, the physiological characteristic of the maximum association characteristic is determined by using a classification algorithm, all spectrum data are traversed to obtain a time sequence matrix, and a sleep state recognition model is constructed, wherein the method comprises the following steps:
performing dimension reduction processing on physiological characteristics to mine association relations among respiratory waves, heartbeat and cardiac intensity, and using a flow clustering technology to set a threshold value to select a blood oxygen average value as the center of an initial cluster;
judging the distance from the respiratory wave, the heartbeat and the cardiac intensity to the center of the initial cluster, and selecting the blood oxygen average value which is smaller than a threshold value and is close to the center of the initial cluster as a data cluster;
selecting the respiratory wave, the heartbeat and the cardiac intensity with the smallest distance as the association point with the largest association relation based on the data cluster;
and determining the physiological characteristic of the maximum correlation characteristic by adopting an objective function of the correlation point obtained by the square error, and traversing all spectrum data to obtain all physiological characteristics.
The expression of the objective function of the association point is as follows:
；
in the method, in the process of the invention,Lan objective function value representing the association point;Ma squared error value representing the associated point;Trepresenting data points in a data cluster;arepresenting the number of data clusters;C b+1 representing an initial cluster center point;Erepresenting a total number of data points in the data set;P a represent the firstaAn average of the individual data clusters;rindicating the set threshold.
And constructing a sleep state recognition model according to a time sequence matrix of the corresponding state stage construction time sequence to obtain the recognition model operation.
Preferably, constructing the sleep state recognition model according to the corresponding state stage construction time sequence to obtain a time sequence matrix for the recognition model to run includes:
sequentially arranging the physiological features and the corresponding state phases to construct a combined time sequence which takes the state phase feature set as a row and takes a time point as a column;
when the number of lines in the time sequence matrix is smaller than the time point, splitting the time sequence line by line according to the dimension space sequence, superposing the time sequence line by line to generate a high-dimension random matrix, and taking each column of the matrix as a single individual for extracting the dimension;
converting the high-dimensional random matrix into a sample covariance matrix, estimating the sample covariance matrix by using a maximum likelihood estimation method, and mapping the characteristic values to a complex domain to obtain a distribution rule of physiological characteristics;
And determining distinguishing features of the sleep state based on the distribution rule and a preset constraint condition, and constructing a sleep state recognition model.
Therefore, the physiological characteristic changes under different sleep states are covered by collecting the spectrum data in the awake state, the transition stage and the deep sleep stage, the variable elimination technology is used for extracting the blood oxygen level changes to measure the blood oxygen average value, the respiratory wave, the heartbeat and the heart intensity to provide comprehensive physiological characteristic information, meanwhile, the physiological characteristic index is converted into the data set form, and the sleep state identification model is built based on the set different sleep state segmentation threshold values, so that the aim of accurately identifying different sleep states of the tester from multiple dimensions is fulfilled.
And the physical and psychological pressure acquisition unit 4 is used for constructing an analysis model to analyze the physical and psychological state change of the tester by combining the physical and psychological signal data with the frequency domain change technology, and acquiring abnormal information according to the change result to judge the physical and psychological pressure result.
In this embodiment, the physical and mental pressure obtaining unit 4 includes a sign signal processing module 401, a characteristic frequency revealing module 402, an analysis model building module 403, and a pressure result judging module 404.
The sign signal processing module 401 is configured to capture a sign change signal of a tester by using a pressure sensor installed inside the massaging device, and perform noise reduction processing on the feature change signal by using a threshold change method.
Specifically, capturing a sign change signal of a tester by using a pressure sensor installed inside the massage apparatus, and performing noise reduction processing on the feature change signal by using a threshold change method, comprising the steps of:
the method comprises the steps of starting a pressure sensor in the massage equipment, collecting sign change signals of a tester in real time, including pressure change and strength, and performing preliminary processing on collected original pressure sensor data, including noise removal and abnormal value removal.
The frequency domain features are extracted from the pressure sensor data and an appropriate threshold is set according to the characteristics of the sign change signal, and it should be noted that the threshold should be set taking into account the sign change desired to be captured and the level of noise.
Using a threshold value change method, a portion of the sign change signal below a threshold value is regarded as noise and noise reduction processing is performed, and the portion identified as noise is noise reduction processed.
The characteristic frequency revealing module 402 is configured to determine the number of decomposition layers based on the correlation between the scale factor and the original sign change signal, and implement a wavelet decomposition operation in combination with the frequency domain change to reveal the characteristics of the change signal.
Specifically, determining the number of decomposition layers based on the correlation between the scale factor and the original sign change signal, and implementing wavelet decomposition operation in combination with frequency domain change reveals the characteristics of the change signal including:
Decomposing an original signal into a plurality of groups of layers by using scale coefficients, setting high-level capturing low-frequency information, and capturing high-frequency information at the low level;
carrying out framing and emphasis processing on the decomposed original signals based on a wavelet function to judge the correlation between each group of layers and the original signals;
and carrying out segmentation processing and correlation combination on the original signal through a time window to obtain a state coefficient, and carrying out convolution operation and discrete cosine transformation on the state coefficient to obtain a state frequency coefficient as the characteristic of the change signal.
The analysis model establishment module 403 is configured to use a machine learning technique to describe the connection between the change signal and the feature to establish an analysis model to analyze the change of the physical sign state of the tester.
Specifically, the method for establishing an analysis model to analyze the change of the physical sign state of the tester by adopting the machine learning technology to describe the connection between the change signal and the characteristics comprises the following steps:
constructing a plane based on a machine learning technology as a decision plane to describe the relation between the change signal and the feature, and distinguishing the classification patterns of the sign states according to the description result;
according to the classification patterns, a state classifier is established by utilizing a support vector machine to learn and train the physical sign states, and an analysis model is established by combining the state classifier with principal component analysis;
And inputting the change signal into an analysis model to analyze the change of the physical sign state of the tester.
The pressure result judging module 404 sets a non-pressure, intermediate pressure and high pressure distinguishing baseline according to the sign state change result, and inputs the sign change signal into the analysis model to output a distinguishing baseline to judge the physical and mental pressure result of the tester.
Specifically, setting a non-pressure, medium-pressure and high-pressure distinguishing baseline according to a sign state change result, inputting sign change signals into an analysis model, and outputting distinguishing baseline to judge the physical and psychological pressure result of a tester, wherein the method comprises the following steps:
according to the sign change result, different physical and psychological pressure levels are defined, including no pressure, moderate pressure and high pressure, and a corresponding base line is established for each pressure level, namely, a typical mode of sign change under the physical and psychological pressure level.
And inputting the sign change signals acquired in real time into an analysis model, and outputting the corresponding physical and psychological pressure level judgment test personnel physical and psychological pressure results in real time.
Therefore, the pressure sensor arranged in the massage equipment is used for capturing the sign change signal of the tester, and the feature change signal is subjected to noise reduction processing by a threshold change method, so that the sign change signal of the tester can be effectively extracted.
The working mode making unit 5 is used for inputting the sleep state identification result and the physical and mental pressure result to the massage equipment controller, and the control end makes a corresponding working mode according to the result.
In this embodiment, the sleep state recognition result and the physical and psychological pressure result are input to the massage device controller, and the control end formulates a corresponding working mode according to the result, including the following steps:
the sleep state recognition result and the physical and psychological pressure result are integrated into a comprehensive state index, and corresponding working mode mapping is formulated according to the comprehensive state index, wherein the mapping comprises parameters capable of setting different massage intensities, massage modes or other massage equipment functions.
According to the formulated working mode mapping, setting various parameters of the massage equipment, including strength, speed, massage position and the like, and sending the formulated massage parameters to a massage equipment controller, wherein the massage equipment can be specifically realized through wireless communication or other connection modes.
After the massage equipment controller receives the parameters, the working mode and the parameters of the massage equipment are adjusted so as to provide massage experience adapting to the current physical and mental state, feedback and physiological changes of the testers are monitored in real time in the massage process, and the massage parameters can be specifically adjusted in real time as required so as to provide more comfortable and effective massage experience.
The real-time monitoring integration unit 6 is used for integrating the sleep state identification model and the analysis model into the massage equipment controller and monitoring the pressure and the sleep state of the user in real time by utilizing the near infrared spectrum equipment and the sensor.
In this embodiment, the real-time monitoring integrated unit 6 includes an integrated switching operation module 601, a control transmission connection module 602, a monitoring protocol control module 603, an integrated storage control module 604, and a pressure sleep monitoring module 605.
The integrated conversion operation module 601 is configured to collect, combine and convert the sleep state recognition result and the physical and mental stress test result into homogeneous data in real time by using a virtual database technology.
Specifically, the method for integrating and converting the sleep state identification result and the physical and mental stress test result into homogeneous data by utilizing the virtual database technology comprises the following steps:
creating a virtual database by using a virtual database technology, wherein the virtual database comprises a table for storing sleep state identification results and physical and mental stress test results, and collecting result data generated by a sleep state identification system and a physical and mental stress test system into the respective databases.
And integrating the data in the two databases by using a virtual database technology, merging the sleep state identification result and the physical and psychological stress test result into homogeneous data, and creating a virtual view by using the virtual database technology so that the merged data is inquired and analyzed in a unified mode.
The control transmitting connection module 602 is configured to convert the homogeneous data into a control signal, transmit the control signal to the massage controller by using a network transmission technology, and synchronously convert the control signal and the homogeneous data, so as to connect the control signal with the massage controller.
Specifically, the method for converting the homogeneous data into the control signal, transmitting the control signal into the massage controller by using a network transmission technology, synchronously converting the control signal and the homogeneous data, and connecting the control signal and the massage controller comprises the following steps:
the homogenous data is converted into a control signal format suitable for understanding by the massage controller and the network transmission technique is configured to transmit the control signal from the data source into the massage controller.
The data source end is provided with a control signal transmitting end, the converted control signal is transmitted to the network transmission channel, and the control signal is transmitted from the transmitting end to the interior of the massage controller by utilizing the configured network transmission channel.
The massage controller is provided with a control signal receiving end, receives a control signal received from a network transmission channel, analyzes the received control signal in the massage controller, and converts the control signal into a control instruction which can be recognized by the massage equipment, wherein the control instruction comprises parameters such as adjustment of massage intensity, mode, time and the like.
According to the analyzed control instruction, the working mode and parameters of the massage equipment are controlled so as to achieve specified massage effect and experience, and synchronous conversion between the control signal and the homogeneous data is particularly ensured, namely, the massage controller can adjust the massage parameters according to the change of the real-time data.
The monitoring protocol control module 603 is configured to establish an integrated monitoring protocol for the massage controller to establish a transmission channel for the control signal, and to set a monitoring protocol control value according to sleep state identification and physical and mental pressure.
Specifically, the massage controller establishes an integrated monitoring protocol to establish a transmission channel for a control signal, and gives a monitoring protocol control value according to sleep state identification and physical and mental pressure, and the method comprises the following steps:
and designing an integrated monitoring protocol, definitely defining the format and transmission mode of control signals and monitoring parameters related to sleep states and physical and mental pressures, and establishing a transmission channel of the control signals according to the set protocol.
The massage controller end realizes the receiving and analyzing functions of the protocol, ensures that the massage controller can correctly identify and process the control signals from the transmission channel, and defines the control values of the monitoring parameters including the parameters of massage intensity, massage mode, massage time and the like according to the sleep state identification and the related information of physical and mental pressure.
The sleep state identification system is integrated with the control signal transmission protocol, corresponding monitoring parameter values in the control signals under different sleep states are determined, a soft massage mode can be selected during deep sleep, meanwhile, the physical and mental pressure test system is integrated with the control signal transmission protocol, corresponding monitoring parameter values under different physical and mental pressure levels are defined, and a stronger massage mode can be selected under a high pressure state.
The integrated storage control module 604 is configured to integrate a prescribed protocol control value into the massage controller, and store the monitoring data and the monitoring information by automatically detecting a change of the control parameter and using the port status.
Specifically, integrating a prescribed protocol control value into the massage controller by automatically detecting a change in a control parameter and storing monitoring data and monitoring information using a port state includes the steps of:
the prescribed protocol control values are integrated into the massage controller, so that the massage controller can identify the control values, and the massage controller can timely capture the update from the integrated protocol by periodically polling or detecting the change of the control parameters by using an event triggering mode.
When the control parameter is detected to be changed, the massage controller automatically adjusts the working mode and the parameters of the massage according to the new protocol control value so as to realize personalized massage experience, and the monitoring data and the monitoring information are stored in the port state inside the massage controller by utilizing the port state storage mechanism.
The pressure sleep monitoring module 605 is configured to input the monitoring data and the monitoring information into the corresponding mapping areas, obtain a correct monitoring result through corresponding control semantic analysis in the area mapping, and complete the purpose of monitoring the pressure and the sleep state of the user.
Specifically, the monitoring data and the monitoring information are input into the corresponding mapping areas, the correct monitoring result is obtained through the corresponding control semantic analysis in the area mapping, and the aim of monitoring the pressure and the sleep state of the user is fulfilled, which comprises the following steps:
mapping the monitoring data and the monitoring information to a specific semantic region definition mapping region, inputting the data acquired from the massage controller and the monitoring equipment into the corresponding mapping region, and inputting the monitoring data such as massage intensity, massage time, heart rate, respiratory frequency, pressure change value and the like into the monitoring information related to control parameter change.
And mapping the monitoring data and the monitoring information to corresponding semantic areas by using a pre-defined mapping rule, and performing control semantic analysis in the mapping areas, namely analyzing semantics related to the pressure and the sleep state of the personnel according to the mapped data and information, and generating a final monitoring result based on the result of the control semantic analysis, wherein the final monitoring result comprises indexes such as the pressure level and the sleep quality of the personnel.
And the monitoring modification and adjustment unit 7 is used for the massage equipment controller to acquire the identification result according to the monitoring data and modify the working mode of the massage equipment to adjust the self state of the user.
Specifically, the sleep state of the user is identified by utilizing the sleep state identification model of the near infrared spectrum data, the physical and psychological pressure condition of the user is monitored by utilizing the sensor, the massage equipment controller controls the working mode of the massage equipment according to the identification and monitoring results, personalized massage experience is provided, more comfortable and personalized service experience is provided for the user, and the self state of the user is improved.
In summary, by means of the technical scheme, the physiological characteristics of the testers are calculated and reflected by utilizing the near infrared spectrum data, the sleep state identification model is built by combining the classification algorithm, the analysis model is built by combining the frequency domain change technology, the physical sign states of the testers are analyzed and evaluated from multiple dimensions, the sleep state identification model and the analysis model are integrated into the massage equipment controller, the massage equipment can monitor the pressure and the sleep state of the user in real time, the working mode of the massage equipment is adjusted in real time according to the monitoring data, personalized massage experience is provided, and more comfortable and personalized service experience is provided for users. According to the invention, spectral data are acquired in the awake state, the transition stage and the deep sleep stage, physiological characteristic changes under different sleep states are covered, the variable elimination technology is used for extracting blood oxygen level changes to measure blood oxygen mean value, respiratory wave, heartbeat and heart intensity to provide comprehensive physiological characteristic information, meanwhile, physiological characteristic indexes are converted into a data set form, and a sleep state identification model is established based on different set sleep state segmentation thresholds, so that the aim of accurately identifying different sleep states of a tester from multiple dimensions is fulfilled. The invention captures the sign change signal of the tester by using the pressure sensor arranged in the massage equipment, and carries out noise reduction treatment on the characteristic change signal by using the threshold change method, thus effectively extracting the sign change signal of the tester, describing the relation between the change signal and the characteristic by adopting the machine learning technology, establishing an analysis model, judging the dynamic change of the user when the massage equipment is used, and finding and identifying the abnormal condition of the physical and psychological pressure state of the user.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. The near infrared spectrum body and mind pressure and sleep quality monitoring system is characterized by comprising a pre-test preparation unit (1), a signal data acquisition unit (2), a sleep state identification unit (3), a body and mind pressure acquisition unit (4), a working mode formulation unit (5), a real-time monitoring integration unit (6) and a monitoring modification adjustment unit (7);
The early-stage test preparation unit (1) is used for selecting a specified number of testers to lie on the massage equipment based on preset standards and wearing near infrared spectrum equipment pre-installed on the massage equipment for the testers;
the signal data acquisition unit (2) is used for starting a sensor inside the near infrared spectrum equipment and the massage equipment to acquire near infrared spectrum data and sign signal data;
the sleep state identification unit (3) is used for calculating and reflecting physiological characteristics of the testers by utilizing near infrared spectrum data and combining the physiological characteristics with a classification algorithm to establish a sleep state identification model;
the physical and psychological pressure acquisition unit (4) is used for combining the physical sign signal data with a frequency domain change technology to construct an analysis model to analyze the physical sign state change of the tester, and acquiring abnormal information according to the change result to judge the physical and psychological pressure result;
the working mode making unit (5) is used for inputting the sleep state identification result and the physical and psychological pressure result to the massage equipment controller, and the control end makes a corresponding working mode according to the result;
the real-time monitoring integration unit (6) is used for integrating the sleep state identification model and the analysis model into the massage equipment controller and monitoring the pressure and the sleep state of the user in real time by utilizing the near infrared spectrum equipment and the sensor;
The monitoring modification and adjustment unit (7) is used for acquiring the identification result according to the monitoring data by the massage equipment controller and modifying the working mode of the massage equipment to adjust the self state of the user.
2. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 1, wherein the sleep state identification unit (3) comprises a spectrum data correction module (301), a physiological characteristic acquisition module (302), a physiological characteristic processing module (303) and an identification model construction module (304);
the spectrum data correction module (301) is used for collecting spectrum data of a tester in a wake state, a transition stage and a deep sleep stage according to near infrared spectrum equipment and preprocessing the spectrum data by utilizing a multi-element scattering correction technology;
the physiological characteristic acquisition module (302) is used for extracting blood oxygen level change of a tester by adopting a variable elimination technology and measuring physiological characteristic indexes of blood oxygen mean value, respiratory wave, heartbeat and cardiac intensity according to the blood oxygen level change result;
the physiological characteristic processing module (303) is used for converting physiological characteristic indexes into a data set form, performing real-time missing value interpolation processing operation through a multi-order Lagrangian difference method, and setting segmentation thresholds of different sleep states based on the data set;
The recognition model construction module (304) is used for acquiring the center of an initial cluster in the physiological characteristic index, determining the physiological characteristic of the maximum association characteristic by utilizing a classification algorithm, traversing all spectrum data to acquire a time sequence matrix, and constructing a sleep state recognition model.
3. The near infrared spectrum physical and psychological pressure and sleep quality monitoring system according to claim 2, wherein the variable elimination technology is used for extracting the blood oxygen level change of the tester, and determining the blood oxygen average value, the respiratory wave, the heartbeat and the cardiac intensity physiological characteristic index according to the blood oxygen level change result comprises:
performing variable elimination operation on the pretreated spectrum data by adopting a variable elimination technology to remove interference variables, and judging the absorption effect of a near infrared band in the spectrum data;
judging the content of oxyhemoglobin and deoxyhemoglobin according to the light intensity change of the infrared spectrum after the infrared spectrum is transmitted through the skin of the tester, and measuring the cognitive function of the tester;
judging the content analysis blood oxygen change level of the oxygen-containing hemoglobin and the deoxyhemoglobin of the testers in different stages, and selecting the time point with the highest blood oxygen change in the range of three stages based on the judging result;
Calculating an average value of blood oxygen levels in three stages as an average blood oxygen value, and taking the average blood oxygen value as a physiological characteristic for distinguishing sleep and awake states;
and judging the respiration change and the blood volume change of the tester according to the blood oxygen change level, extracting respiration waves and cardiac signals, and analyzing the change amplitude of the hemoglobin concentration according to the cardiac signals to evaluate the cardiac intensity.
4. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 3, wherein the steps of obtaining the center of an initial cluster in the physiological characteristic index, determining the physiological characteristic of the maximum association characteristic by using a classification algorithm, traversing all spectrum data to obtain a time sequence matrix, and constructing a sleep state recognition model comprise the following steps:
performing dimension reduction processing on physiological characteristics to mine association relations among respiratory waves, heartbeat and cardiac intensity, and using a flow clustering technology to set a threshold value to select a blood oxygen average value as the center of an initial cluster;
judging the distance from the respiratory wave, the heartbeat and the cardiac intensity to the center of the initial cluster, and selecting the blood oxygen average value which is smaller than a threshold value and is close to the center of the initial cluster as a data cluster;
selecting the respiratory wave, the heartbeat and the cardiac intensity with the smallest distance as the association point with the largest association relation based on the data cluster;
Obtaining an objective function of the association points by adopting a square error to determine the physiological characteristics of the maximum association characteristics, and traversing all spectrum data to obtain all physiological characteristics;
and constructing a sleep state recognition model according to a time sequence matrix of the corresponding state stage construction time sequence to obtain the recognition model operation.
5. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 4, wherein the expression of the objective function of the correlation point is:
；
in the method, in the process of the invention,Lan objective function value representing the association point;
Ma squared error value representing the associated point;
Trepresenting data points in a data cluster;
arepresenting the number of data clusters;
C b+1 representing an initial cluster center point;
Erepresenting a total number of data points in the data set;
P a represent the firstaAn average of the individual data clusters;
rindicating the set threshold.
6. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 5, wherein the constructing the sleep state recognition model according to the time series matrix of the corresponding state stage construction time series to obtain the recognition model operation comprises:
sequentially arranging the physiological features and the corresponding state phases to construct a combined time sequence which takes the state phase feature set as a row and takes a time point as a column;
When the number of lines in the time sequence matrix is smaller than the time point, splitting the time sequence line by line according to the dimension space sequence, superposing the time sequence line by line to generate a high-dimension random matrix, and taking each column of the matrix as a single individual for extracting the dimension;
converting the high-dimensional random matrix into a sample covariance matrix, estimating the sample covariance matrix by using a maximum likelihood estimation method, and mapping the characteristic values to a complex domain to obtain a distribution rule of physiological characteristics;
and determining distinguishing features of the sleep state based on the distribution rule and a preset constraint condition, and constructing a sleep state recognition model.
7. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 1, wherein the physical and mental pressure acquisition unit (4) comprises a physical sign signal processing module (401), a characteristic frequency revealing module (402), an analysis model establishing module (403) and a pressure result judging module (404);
the physical sign signal processing module (401) is used for capturing physical sign change signals of a tester by using a pressure sensor arranged in the massage equipment and performing noise reduction processing on the characteristic change signals by using a threshold change method;
the characteristic frequency revealing module (402) is used for determining the number of decomposition layers based on the correlation between the scale coefficient and the original sign change signal and carrying out wavelet decomposition operation in combination with frequency domain change to reveal the characteristics of the change signal;
The analysis model establishing module (403) is used for establishing an analysis model to analyze the physical sign state change of the tester by adopting the machine learning technology to describe the connection between the change signal and the characteristic;
the pressure result judging module (404) is used for setting a non-pressure, medium pressure and high pressure distinguishing baseline according to the sign state change result, inputting the sign change signal into the analysis model and outputting the distinguishing baseline to judge the body and mind pressure result of the tester.
8. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 7, wherein the determining the number of decomposition layers based on the correlation between the scale factor and the original sign change signal, and performing wavelet decomposition operation in combination with frequency domain change reveals the characteristics of the change signal comprises:
decomposing an original signal into a plurality of groups of layers by using scale coefficients, setting high-level capturing low-frequency information, and capturing high-frequency information at the low level;
carrying out framing and emphasis processing on the decomposed original signals based on a wavelet function to judge the correlation between each group of layers and the original signals;
and carrying out segmentation processing and correlation combination on the original signal through a time window to obtain a state coefficient, and carrying out convolution operation and discrete cosine transformation on the state coefficient to obtain a state frequency coefficient as the characteristic of the change signal.
9. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 8, wherein the establishing an analytical model for analyzing the change of the physical and mental state of the tester by using the association between the machine learning technology description change signal and the characteristic comprises:
constructing a plane based on a machine learning technology as a decision plane to describe the relation between the change signal and the feature, and distinguishing the classification patterns of the sign states according to the description result;
according to the classification patterns, a state classifier is established by utilizing a support vector machine to learn and train the physical sign states, and an analysis model is established by combining the state classifier with principal component analysis;
and inputting the change signal into an analysis model to analyze the change of the physical sign state of the tester.
10. The near infrared spectrum physical and mental pressure and sleep quality monitoring system according to claim 1, wherein the real-time monitoring integrated unit (6) comprises an integrated conversion operation module (601), a control transmission connection module (602), a monitoring protocol control module (603), an integrated storage control module (604) and a pressure sleep monitoring module (605);
the integrated conversion operation module (601) is used for collecting and converting the sleep state identification result and the physical and mental pressure test result into homogeneous data in real time by utilizing a virtual database technology;
The control transmission connection module (602) is used for converting homogeneous data into control signals, transmitting the control signals into the massage controller by utilizing a network transmission technology, synchronously converting the control signals and the homogeneous data, and connecting the control signals with the massage controller;
the monitoring protocol control module (603) is used for establishing an integrated monitoring protocol for the massage controller to establish a transmission channel for the control signal, and giving a monitoring protocol control value according to sleep state identification and physical and mental pressure;
the integrated storage control module (604) is used for integrating a specified protocol control value into the massage controller, automatically detecting the change of the control parameter, and storing monitoring data and monitoring information by using the port state;
the pressure sleep monitoring module (605) is used for inputting the monitoring data and the monitoring information into the corresponding mapping areas, obtaining the correct monitoring result through the corresponding control semantic analysis in the area mapping, and completing the purpose of monitoring the pressure and the sleep state of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410140388.9A CN117814766A (en) | 2024-02-01 | 2024-02-01 | Near infrared spectrum physical and mental pressure and sleep quality monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410140388.9A CN117814766A (en) | 2024-02-01 | 2024-02-01 | Near infrared spectrum physical and mental pressure and sleep quality monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117814766A true CN117814766A (en) | 2024-04-05 |
Family
ID=90504339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410140388.9A Pending CN117814766A (en) | 2024-02-01 | 2024-02-01 | Near infrared spectrum physical and mental pressure and sleep quality monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117814766A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110004110A1 (en) * | 2000-05-30 | 2011-01-06 | Vladimir Shusterman | Personalized Monitoring and Healthcare Information Management Using Physiological Basis Functions |
| US10252058B1 (en) * | 2013-03-12 | 2019-04-09 | Eco-Fusion | System and method for lifestyle management |
| CN109745001A (en) * | 2017-11-02 | 2019-05-14 | 罗曦明 | Contactless sleep monitor method, apparatus, electronic equipment and storage medium |
| CN111588391A (en) * | 2020-05-29 | 2020-08-28 | 京东方科技集团股份有限公司 | Mental state determination method and system based on sleep characteristics of user |
| CN112188865A (en) * | 2018-05-11 | 2021-01-05 | 斯佩克卓尼克斯股份有限公司 | System and method for monitoring abnormal blood oxygenation level and self-monitoring oxygenation system and method |
| CN112450878A (en) * | 2020-10-16 | 2021-03-09 | 中国人民解放军63919部队 | Sleep detection method, system and storage medium |
| CN112545851A (en) * | 2020-11-03 | 2021-03-26 | 未来穿戴技术有限公司 | Massage method and device, electronic device and computer readable storage medium |
| CN113332560A (en) * | 2021-05-21 | 2021-09-03 | 苏州声动医疗科技有限公司 | Pillow with elastic pillow body |
| CN113952589A (en) * | 2021-12-13 | 2022-01-21 | 哈尔滨理工大学 | Intelligent mattress with sleep adjusting function |
| CN114533064A (en) * | 2022-02-28 | 2022-05-27 | 深圳市悠眠信息科技有限公司 | Online psychological consultation device, system and method convenient for insomniac |
| CN116711022A (en) * | 2020-11-20 | 2023-09-05 | 瑞思迈传感器技术有限公司 | System and method for monitoring comfort of an individual |
| CN117017295A (en) * | 2023-09-13 | 2023-11-10 | 慕思健康睡眠股份有限公司 | Pressure analysis relieving method and device based on sleep monitoring and computer equipment |
| CN117063242A (en) * | 2021-03-26 | 2023-11-14 | 数眠公司 | Sleep system with personalized sleep recommendation features |
-
2024
- 2024-02-01 CN CN202410140388.9A patent/CN117814766A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110004110A1 (en) * | 2000-05-30 | 2011-01-06 | Vladimir Shusterman | Personalized Monitoring and Healthcare Information Management Using Physiological Basis Functions |
| US10252058B1 (en) * | 2013-03-12 | 2019-04-09 | Eco-Fusion | System and method for lifestyle management |
| CN109745001A (en) * | 2017-11-02 | 2019-05-14 | 罗曦明 | Contactless sleep monitor method, apparatus, electronic equipment and storage medium |
| CN112188865A (en) * | 2018-05-11 | 2021-01-05 | 斯佩克卓尼克斯股份有限公司 | System and method for monitoring abnormal blood oxygenation level and self-monitoring oxygenation system and method |
| CN111588391A (en) * | 2020-05-29 | 2020-08-28 | 京东方科技集团股份有限公司 | Mental state determination method and system based on sleep characteristics of user |
| CN112450878A (en) * | 2020-10-16 | 2021-03-09 | 中国人民解放军63919部队 | Sleep detection method, system and storage medium |
| CN112545851A (en) * | 2020-11-03 | 2021-03-26 | 未来穿戴技术有限公司 | Massage method and device, electronic device and computer readable storage medium |
| CN116711022A (en) * | 2020-11-20 | 2023-09-05 | 瑞思迈传感器技术有限公司 | System and method for monitoring comfort of an individual |
| CN117063242A (en) * | 2021-03-26 | 2023-11-14 | 数眠公司 | Sleep system with personalized sleep recommendation features |
| CN113332560A (en) * | 2021-05-21 | 2021-09-03 | 苏州声动医疗科技有限公司 | Pillow with elastic pillow body |
| CN113952589A (en) * | 2021-12-13 | 2022-01-21 | 哈尔滨理工大学 | Intelligent mattress with sleep adjusting function |
| CN114533064A (en) * | 2022-02-28 | 2022-05-27 | 深圳市悠眠信息科技有限公司 | Online psychological consultation device, system and method convenient for insomniac |
| CN117017295A (en) * | 2023-09-13 | 2023-11-10 | 慕思健康睡眠股份有限公司 | Pressure analysis relieving method and device based on sleep monitoring and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109157202B (en) | Cardiovascular disease early warning system based on multi-physiological signal deep fusion | |
| CN111466876B (en) | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network | |
| CN108577834B (en) | A method of it is detected automatically for epilepsy interphase spike | |
| CN113397546B (en) | Method and system for constructing emotion recognition model based on machine learning and physiological signals | |
| CN111243739A (en) | Anti-interference physiological parameter telemetering method and system | |
| CN114999237B (en) | Intelligent education interactive teaching method | |
| US20240081705A1 (en) | Non-contact fatigue detection system and method based on rppg | |
| CN111513735A (en) | Major depressive disorder identification system based on brain-computer interface and deep learning and application | |
| CN111797817A (en) | Emotion recognition method and device, computer equipment and computer-readable storage medium | |
| CN109222906B (en) | Method for constructing pain state prediction model based on brain electrical signals | |
| CN115211858A (en) | Emotion recognition method and system based on deep learning and storable medium | |
| CN113925465B (en) | Rehabilitation training evaluation method and system based on myooxygen feedback information | |
| CN114974566A (en) | Cognitive function assessment method and system | |
| CN117562554A (en) | Portable sleep monitoring and quality assessment method and system | |
| KR20080107961A (en) | User adaptative pattern clinical diagnosis/medical system and method using brain waves and the sense infomation treatment techniques | |
| CN112263249A (en) | ECG-based method and device for enhancing blood oxygen saturation monitoring | |
| CN116312951B (en) | Exercise function assessment method and system based on multi-modal coupling analysis | |
| CN116269392B (en) | Multi-parameter coupling stress level assessment method and system | |
| Gaoan et al. | Heart rate measurement via smart phone acceleration sensor | |
| CN117814766A (en) | Near infrared spectrum physical and mental pressure and sleep quality monitoring system | |
| CN116269289A (en) | Method for evaluating psychological and physiological health of athlete based on short-time heart rate variability | |
| CN115251913A (en) | Multi-mode fusion blood glucose monitoring method based on ECG and PPG | |
| CN112656430A (en) | Stroke balance rehabilitation assessment method based on standing position unbalance induced electroencephalogram | |
| CN107616785A (en) | A kind of head-wearing type intelligent health diagnosis system and its implementation | |
| Ugarte et al. | An algorithm to measure the stress level from EEG, EMG and HRV signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |