CN116474239A - High-efficient feedback regulation sleep brain wave music headrest - Google Patents
High-efficient feedback regulation sleep brain wave music headrest Download PDFInfo
- Publication number
- CN116474239A CN116474239A CN202310625784.6A CN202310625784A CN116474239A CN 116474239 A CN116474239 A CN 116474239A CN 202310625784 A CN202310625784 A CN 202310625784A CN 116474239 A CN116474239 A CN 116474239A
- Authority
- CN
- China
- Prior art keywords
- sleep
- headrest
- neural network
- brain wave
- music
- 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
- 210000004556 brain Anatomy 0.000 title claims abstract description 79
- 230000009123 feedback regulation Effects 0.000 title claims abstract description 14
- 230000008667 sleep stage Effects 0.000 claims abstract description 86
- 238000007405 data analysis Methods 0.000 claims abstract description 12
- 238000013528 artificial neural network Methods 0.000 claims description 60
- 230000006870 function Effects 0.000 claims description 26
- 230000001976 improved effect Effects 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 24
- 238000000222 aromatherapy Methods 0.000 claims description 20
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 20
- 238000013527 convolutional neural network Methods 0.000 claims description 16
- 238000011176 pooling Methods 0.000 claims description 15
- 239000002033 PVDF binder Substances 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 13
- 229920002981 polyvinylidene fluoride Polymers 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 230000006872 improvement Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 229920000742 Cotton Polymers 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000004461 rapid eye movement Effects 0.000 claims description 5
- 238000011426 transformation method Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 4
- 230000003340 mental effect Effects 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000003860 sleep quality Effects 0.000 abstract description 8
- 230000033228 biological regulation Effects 0.000 abstract description 3
- 239000010408 film Substances 0.000 description 15
- 241000282414 Homo sapiens Species 0.000 description 14
- 239000000284 extract Substances 0.000 description 9
- 230000009471 action Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 239000000341 volatile oil Substances 0.000 description 7
- 208000019116 sleep disease Diseases 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000000241 respiratory effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 230000002618 waking effect Effects 0.000 description 3
- 244000178870 Lavandula angustifolia Species 0.000 description 2
- 235000010663 Lavandula angustifolia Nutrition 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000001102 lavandula vera Substances 0.000 description 2
- 235000018219 lavender Nutrition 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 230000036387 respiratory rate Effects 0.000 description 2
- 208000020685 sleep-wake disease Diseases 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000035565 breathing frequency Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 230000010247 heart contraction Effects 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000036391 respiratory frequency Effects 0.000 description 1
- 208000022925 sleep disturbance Diseases 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M21/02—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis for inducing sleep or relaxation, e.g. by direct nerve stimulation, hypnosis, analgesia
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47G—HOUSEHOLD OR TABLE EQUIPMENT
- A47G9/00—Bed-covers; Counterpanes; Travelling rugs; Sleeping rugs; Sleeping bags; Pillows
- A47G9/10—Pillows
- A47G9/1045—Pillows shaped as, combined with, or convertible into other articles, e.g. dolls, sound equipments, bags or the like
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/38—Acoustic or auditory stimuli
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0027—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the hearing sense
Abstract
A high-efficiency feedback regulation sleep brain wave music headrest comprises a sleep information collection module, a sleep data analysis module and a headrest regulation module; the high-efficiency feedback sleep brain wave music headrest provided by the invention utilizes a computer and an electronic technology to collect and analyze sleep related information, constructs a sleep stage model, classifies sleep stages, plays different brain wave music for different sleep stages, guides a user to quickly enter into a deep sleep stage, and improves sleep quality.
Description
Technical Field
The invention relates to the technical field of headrests, in particular to a high-efficiency feedback sleep brain wave music headrest.
Background
With the rapid development of modern society, people suffering from sleep disorder are more and more. It is counted that more than one third of the world's population may suffer from varying degrees of sleep disturbance. In view of this problem, there are many products for improving sleep on the market, and brain wave music sleep-aiding products are receiving more and more attention. However, most of brain wave music sleep-aiding products in the market still have some problems. First, their music types often fail to meet the needs of the user. Secondly, the fluctuation frequency adopted by many products is single, and the requirements of different crowds are difficult to adapt. Again, conventional brain wave techniques can only achieve simple relaxing and hypnotizing effects, but cannot achieve higher level adjustments. Therefore, in designing a new brain wave music sleep-aiding product, it is necessary to solve these problems. The invention provides a product named as a high-efficiency feedback sleep brain wave music headrest, which can realize real personalized adjustment by combining novel brain wave music through adopting an artificial intelligence technology, solve the problem of sleep disorder of a user, improve sleep quality, improve concentration memory and achieve the effect of body relaxation.
Disclosure of Invention
The invention aims to provide a high-efficiency feedback-regulation sleep brain wave music headrest and a control system thereof, so as to solve the problems in the background technology.
The utility model provides a brain wave music aromatherapy headrest of high-efficient feedback regulation sleep promotion brain, includes headrest main part and external cell-phone APP, and the headrest main part includes pillow and pillowcase, and the pillow setting is in the inside of pillowcase, the top of headrest main part is equipped with the intelligent piezoelectric sensor of USB rechargeable type, and the bluetooth speaker of two USB rechargeable types is built-in to the bottom left and right sides of headrest main part, and external cell-phone APP passes through bluetooth and receives intelligent piezoelectric sensor's output signal, carries out AI algorithm monitoring sleep state, simultaneously through the audio playback of APP control built-in brain wave, self-closing music playback when getting into the degree of depth sleep state.
Optionally, the pillow core is made of memory cotton.
Optionally, the intelligent piezoelectric sensor is a PVDF film piezoelectric sensor and is adapted with a USB charging port of the film piezoelectric sensor.
Optionally, two bluetooth speaker, through bluetooth speaker connecting wire electric connection to bluetooth speaker USB is charged the mouth to the adaptation.
Optionally, bluetooth speaker USB charges mouthful and film piezoelectric sensor USB charges mouthful all to set up the right flank at the headrest body.
Optionally, the main body of the headrest is externally provided with an essential oil aromatherapy cotton box.
In order to achieve the above purpose, the invention also provides a high-efficiency feedback-regulation sleep brain wave music headrest sleep lifting system, which comprises a sleep information collection module, a sleep data analysis module and a headrest regulation module; firstly, through PVDF piezoelectric film sensor installed on the headrest, sleep information is collected and preprocessed by adopting an improved wavelet transformation method, secondly, sleep stages are staged, a neural network sleep stage model is built by combining a convolutional neural network and a time sequence neural network, the sleep stages of a user are automatically staged, the headrest plays brain wave music with different functions according to the sleep stages of the user, sleep is regulated, the user is promoted to enter a deep sleep state, and the sleep stage model of the neural network is optimized through brain wave feedback.
Furthermore, the sleep information collecting module accurately captures heartbeat, respiration and body movement information of a user through the PVDF piezoelectric film sensor arranged in the headrest, is suitable for monitoring vital signals in a human body, is applied to the surface of the skin of the human body or implanted in the human body, is durable and soft, can withstand millions of bending and vibration, has high sensitivity, and can detect the vital signals through clothes.
Furthermore, the sleep information collection module uploads the collected heartbeat, respiration and body movement information to a system database corresponding to the user, adopts an SQLite database, is a small and efficient embedded relational database management system, and is widely used in mobile equipment and desktop application programs. The SQLite uses a single file storage database, supports the SQL data language, and has high portability and flexibility.
Furthermore, the sleep information collecting module converts the collected heartbeat, respiration and body movement information data into a single-channel signal for preprocessing, and the detailed process is as follows:
defining a window function w c (t) the formula is as follows:
t represents the moment corresponding to the information, T represents the total time, a represents the transformation scale, the original signal of the moment information of the sensor T is represented by x (T), and the original signal is decomposed into N inherent modal components, and the formula is as follows:
c i (t) represents the ith natural modal component, r N (t) representing residual components, filtering and denoising information collected by the sensor through improved continuous wavelet transformation, mapping the information to a time-frequency space, and positioning the information frequency components, wherein the formula is as follows:
C wt (a, τ) represents a continuous wavelet transform function,represents a mother wavelet function, and τ represents a translation amount; the invention adopts an improved wavelet transformation method for preprocessing the data, reserves the time information of the data signals of the signals and obtains more detailed and flexible characteristic information.
Furthermore, the sleep data analysis module divides the sleep stage into a waking stage, a shallow sleep stage, a rapid eye movement stage and a deep sleep stage.
Further, the sleep data analysis module constructs a neural network sleep stage model through a neural network, and the detailed process is as follows:
combining a convolutional neural network with a time sequence neural network, constructing a neural network sleep stage model, designing a convolutional layer, a pooling layer and a connecting layer, extracting characteristic signals from filtered signals in the convolutional layer to form a characteristic map, wherein the formula is as follows:
Z p represents an activation value, W p Represents the convolution kernel in the convolution layer, b p Representing the intercept error of the beam,representing the convolution operation, W p,d The D-th channel in the convolution layer is represented, D represents the total channel number of the convolution layer, p represents the p-th convolution operation, and then the net activation value is calculated through the activation function, and the formula is as follows:
entering a pooling layer, further screening the characteristic signals, and screening by adopting an average pooling layer, wherein the formula is as follows:
Y′ p representing the pooling layer output, R representing the entire pooling area; at the full connection layer, all the characteristic signal mapping is tiled, and the formula is as follows:
z represents the full-connection activation value, P represents the total convolution operation times, gamma p Representing the weight of p times, b representing residual vectors, and outputting for multiple times by using different weights at a full connection layer; in the output layer, the result is obtained by the combination calculation of the characteristic signals, the output value of the full-connection layer is divided into C classes, and class labels C are defined y C values are available for e {1,2, … C } and the conditional probability for a class is calculated using the softmax function as follows:
c represents the total value X of the tag representing a matrix of X (t),representing the weight matrix of the tag when taking c, followed by takingThe classification result is calculated by using a decision function, and the formula is as follows:
and finally outputting a final classification result by the representative output layer, combining with a time sequence neural network model to form a neural network sleep stage model, and designing an input gate, a forgetting gate and an output gate in the time sequence neural network, wherein the calculation method comprises the following steps of:
i t 、f t 、o t respectively represent an input door, a forget door and an output door, W i Wf, wo respectively represent the input iteration coefficient, U i Uf, uo represent implicit iteration coefficients, h, respectively t-1 Represents the state of the hidden layer at the moment t-1, b i The residual errors are respectively represented by bf and bo, the internal state controls the external state in the time sequence neural network, and the internal state is ready for use at the moment tThe formula is as follows:
W g represents the internal state iteration coefficient, U g Representing internal state hidden iteration coefficients, b g Representing the internal state residual error, the internal state g at time t t The calculation formula is as follows:
h t ＝ln(o t g t +1)
g t-1 represents the internal state at time t-1, h t Representing the hidden layer state at time t. The sleep stage model is constructed by combining the convolutional neural network and the time sequence neural network, the advantages of the convolutional neural network and the time sequence neural network are fused, the characteristic extraction is carried out through the convolutional neural network, the time sequence neural network extracts the sequence relations existing among the characteristics of different time points, the effective time sequence information is extracted, and the accuracy and the performance of the sleep stage model are improved.
Furthermore, the sleep data analysis module inputs brain waves of the user into the neural network sleep stage model and outputs a sleep stage where the user is located.
Furthermore, the headrest adjusting module automatically plays corresponding brain wave music according to the sleeping state of the user output by the automatic sleep stage model of the neural network, and promotes the user to enter a deep sleep stage. According to the co-frequency resonance principle and the brain wave dependency principle, the speaker is utilized to play delta wave and theta wave in a three-dimensional surrounding way, so that the brain wave of a user is induced to be gradually converted from beta wave to delta wave and theta wave, and then the user enters a sleep state, or alpha wave music is played, the brain wave is influenced to be converted into alpha wave, deep sleep is promoted, concentration and memory are improved, and physical and mental pleasure is achieved. When the system detects that the client enters a deep sleep state, the music playing function is automatically closed, so that a user can relax sleep, the situation that music is manually closed in the middle of sleep or playing equipment is damaged due to the fact that the user cannot shut down after sleeping is avoided, and the use comfort of the user is improved.
Furthermore, the headrest adjusting module automatically performs optimization training on the neural network sleep stage model according to the music played by the headrest and the sleep stage of the user, the sensitivity degree of the user to different music, and the fitness of the model is optimized, so that the personalized effect is achieved.
The beneficial effects are that:
1. according to the invention, the Bluetooth sound box is arranged in the headrest main body, the PVDF film piezoelectric sensor is arranged on the upper surface of the headrest main body, the heartbeat, the respiration and the body movement are accurately captured by the piezoelectric sensor, the sleep state is monitored and recorded by matching with an AI intelligent algorithm, the sleep state analysis is carried out, the brain wave sleep-aiding music playing is controlled by the external mobile phone APP, the deep sleep state is entered, the audio playing is automatically stopped, meanwhile, the multi-type brain wave music playing can be controlled by the Bluetooth sound box, and the purposes of improving the concentration and the memory and simultaneously curing the mind and body by matching with essential oil aromatherapy relaxation are achieved; according to the invention, by combining sleep state monitoring and brain wave audio playing technologies, audio automatic playing and stopping are realized through an AI technology, so that the sleep quality is greatly improved, and the use comfort is improved. According to the invention, by combining a daily life pillow and utilizing the sound wave resonance and dependency reaction principle, brain wave audio is played to adjust brain wave morphology, so that the effect of improving sleep and improving brain force is achieved in a free relaxation state, and by combining a sleep monitoring technology, the effect of automatically controlling and adjusting audio playing is achieved by combining APP with sleep state feedback, so that the overall sleep quality and experience are improved.
2. The invention provides a high-efficiency feedback sleep brain wave music headrest, which comprises a sleep information collection module, a sleep data analysis module and a headrest adjustment module. The PVDF piezoelectric film sensor is arranged on the music headrest, respiratory, heartbeat and body movement information of a user is collected and is transmitted into the background system database, the collected sleep information is preprocessed by adopting improved continuous wavelet transformation, noise of the collected information is accurately screened out, the convolutional neural network and the time sequence neural network are combined to construct a neural network sleep stage model, the convolutional neural network extracts characteristic signals, the time sequence neural network extracts sequence relations among the characteristic signals at different time points, the jointly constructed neural network sleep stage model has the advantages of the two, the accuracy and the effectiveness of the sleep stage model are improved, the brain wave music provided by the headrest has a beneficial effect on the sleep of the user in a deep sleep state, and the sleep quality is improved. The neural network sleep stage model can further optimize feedback to the model according to the specific information of the user, so that the user can better participate in the sleep adjustment process, the neural network sleep stage model is more suitable for the self situation of the user, and the personalized sleep requirement of the user can be better met. The invention adopts a physical mode to carry out sleep adjustment, has good comfort, can quickly promote sleep to enter a deep stage under the condition of not using external medicines and treatment, ensures that people can better enjoy high-quality sleep, ensures that the adjustment process is safer and more reliable for human bodies, carries out sleep adjustment through brain wave music in combination with sleep stage, has different brain wave music in different sleep stages, has more accurate adjustment effect, ensures that the headrest automatically closes music play after a user enters a deep sleep state, does not need to manually close music, interrupts the sleep process, and simultaneously avoids damage caused by long-time play of playing equipment. The invention can help people improve sleep quality, thereby promoting the development of physical and mental health of human beings. The invention not only meets the requirements of people on high-quality sleep, but also promotes the development of related science and technology and health industry, and has wide market prospect and application value.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation on the invention, and other drawings can be obtained by one of ordinary skill in the art without undue effort from the following drawings.
FIG. 1 is a schematic view of a headrest front direction structure according to a first embodiment of the present invention;
FIG. 2 is a schematic view showing a structure of a headrest in a back direction according to a first embodiment of the present invention;
FIG. 3 is an exploded view of a headrest according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a sleep lifting system frame module of the present invention.
In the figure: 101. a pillow core; 102. a pillowcase; 2. PVDF film piezoelectric sensor; 301. 302, a Bluetooth sound box; 303. bluetooth sound box connecting wire; 401. USB charging port of Bluetooth sound box; 402. USB charging port of the film piezoelectric sensor; 5. an external mobile phone APP.
Detailed Description
The invention is further described in connection with the following examples.
Example 1
Referring to fig. 1-3, in this embodiment, a brain wave music aromatherapy headrest for efficiently feeding back and regulating sleep and improving brain is provided, which comprises a headrest main body, an intelligent piezoelectric sensor and an external mobile phone APP5, wherein the headrest main body comprises a pillow core 101 and a pillow case 102, the pillow core 101 is arranged in the pillow case 102, the pillow core 101 is made of a memory cotton material, the top of the headrest main body is provided with a USB charging type intelligent piezoelectric sensor, the intelligent piezoelectric sensor is a PVDF film piezoelectric sensor 2, and is very suitable for monitoring a vital signal on the surface of human skin or in a human body implanted in the body, and is extremely durable and flexible, can withstand bending and vibration for millions times, has high sensitivity, and can detect a vital signal such as pressure, pulse and the like even if being separated by clothes. The pillow is arranged on the top surface of the pillow and is matched with a USB charging port 402 of the thin film piezoelectric sensor, the USB charging port is arranged on the right side surface of the headrest body and is connected with an external mobile phone APP5 through Bluetooth, and sleep monitoring data of a user are transmitted to the external mobile phone APP5 through Bluetooth.
The method for sleep stage based on the physiological signals of heart rate, respiratory rate, body movement and the like is adopted. The method extracts heart rate, respiration and body movement from data obtained by the sensor, and then judges that the user is at a certain stage of sleep by a threshold judgment mode. When a large action such as turning over is performed 3 times or more within 1 minute, it is determined that the person is in a wake stage before falling asleep at this time, and when an action such as turning over is performed 1 to 3 times within 1 minute, it is determined that the person is an unintentional action in the sleeping process, and the stage is divided into a shallow sleep stage after falling asleep; after entering the shallow sleep stage, we decide that it enters the fast eye movement phase if the heart rate and respiration rate are relatively fast, and that it has entered the deep sleep stage when both the heart rate and respiration are relatively slow. We set the median of heart rate and respiration by taking the average of heart rate and respiration over a period of time that has entered the shallow sleep phase to obtain a median.
At this time, the sleep stage is determined by heart rate, respiration, turning over and other actions: the number of actions such as turning over in 1 minute in the awake stage is more than 3; the number of actions such as turning over in 1 minute in the shallow sleep stage is less than 3; the rapid eye movement phase 76 times/minute < heart rate <86 times/minute; deep sleep stage 64 times/minute < heart rate <70 times/minute; according to the judging mode, the person can obtain each stage of sleep more accurately by using heart rate, respiration, turning over and other actions. During processing, we have to remove some of the interfering signals. Through researches, the error caused by random interference can be reduced by utilizing methods such as autocorrelation, smoothing and the like. When the human body moves too much, the output electric charge quantity of the piezoelectric film is larger, the operational amplifier is limited by the working voltage, and the piezoelectric film often enters a saturation region at the moment, so that the output signal is the upper and lower limits of the power supply voltage of the operational amplifier. In this case, information on the body movement of the human body can be obtained by using a threshold method. In a calm state, the vibrations caused by the beating heart and respiration become the main signal. Although the heart beat and respiratory lamp vibration frequencies are not single fixed, their vibration frequencies are always around a certain range over time. It is therefore entirely feasible to use the fourier transform with the amplitude maxima at frequencies between 0.3 and 0.8Hz and 1 and 2Hz as the respiration and heartbeat.
Heart beat signal extraction analysis using frequency amplitude: when a person is in a relatively stable state after sleeping, a pressure signal generated by heart pulsation of a normal person can be stabilized near a certain frequency point, and the amplitude corresponding to the frequency is also a maximum value point. The frequency corresponding to this extreme point is the average heart rate value of the person. Therefore, a Fourier transform mode is adopted, and the frequency value corresponding to the maximum value point of the frequency amplitude between 0.8 and 2Hz is obtained by extracting the maximum value point. The actual heart rate value is obtained using a heart rate that is 60 times the frequency.
Extraction and analysis of respiratory signals: for adults, the breathing rate is generally about 10-25 times per minute in calm conditions, the metabolism of children is faster, about 20-40 times per minute, and a typical female is 1-2 times faster than a male. That is, the respiratory rate of a normal person is approximately in the range of 10 to 40 times 1 minute, that is, 0.2 to 0.8 Hz. Only the amplitude change in the frequency range is concerned, so that the respiratory frequency of the person can be extracted more accurately. Compared with the heartbeat signal generated by heart beating, the respiratory signal is weak and is easily influenced by the conditions such as body movement and the like. However, in the case of a smoother sleep, we can get the breath in a less error way by judging the frequency. Compared with the heartbeat signal, the breathing frequency is approximately limited between 0.2 and 0.8Hz, and has obvious difference with the heartbeat signal of 1 to 2 Hz. Therefore, for the acquired vibration signals, the heart rate signals do not need to be filtered, and the difference of frequencies is directly utilized to obtain the heart rate signals.
Referring to the automatic sleep stage system based on the artificial intelligence algorithm of the university of south China, four stages of sleeping of a tested person at night can be obtained by using the method, wherein the four stages comprise a waking stage before sleeping, a sleeping shallow stage, a rapid eye movement stage and deep sleep, and the four stages are shown in fig. 4.
The external mobile phone APP5 is used as a platform for user interaction, and the platform receives basic data which are sent by a hardware circuit and comprise signals of heart rate, respiration, body movement and the like, and then performs sleep correlation analysis by using the data to finally obtain various sleep results. When the user is detected to enter deep sleep, the brain wave audio playing is automatically closed, so that the optimal use experience of the user is ensured.
In one aspect of the present embodiment, as shown in fig. 1-2, the headrest body conforms to an ergonomic design, and is provided with double-concave shapes on both sides, which is convenient for the user to place his arms and provides a throw pillow effect.
Example two
Improvement on the basis of the first embodiment: as shown in fig. 2-3, the music aromatherapy headrest further comprises two USB charging type bluetooth sound boxes 301 and 302 which are arranged at the left side and the right side of the bottom of the headrest main body and are connected with an external mobile phone APP5 bluetooth for playing brain wave music, wherein the two bluetooth sound boxes 301 and 302 form a surround sound effect when playing brain wave music, are easy to form a same-frequency resonance effect with brain wave, and enhance the effects of helping sleep, promoting brain, curing by music and the like; two bluetooth speaker 301, 302 are through bluetooth speaker connecting wire 303 electric connection to be fit with bluetooth speaker USB and charge mouthful 401, this USB charges mouthful locates headrest body right flank, and external cell-phone APP5 is through the output signal of bluetooth receipt intelligence piezoelectric transducer, carries out AI algorithm monitoring sleep state, simultaneously through the audio playback of APP control built-in brain wave, automatic shutdown music playback when entering the degree of depth sleep state, convenience of customers can relax the sleep and avoid the middle manual music that closes of sleep or can't shut down and lead to playback devices damage, promote user's use comfort degree because after the sleep.
In one aspect of the present embodiment, the musical characteristics include characteristics of genre, timbre, and the like, the genre including: sleep aiding, health care, concentration improving, memory improving, physical and mental healing, natural music, meditation, white noise and the like. The tone color mainly comprises pure tones and mixed tones such as musical tones, noise, human voice and the like.
Brain wave mainly consists of four wave bands, namely alpha wave (8-13 Hz/sec); beta waves (14-30 hz/sec); delta wave (0.5-3 hz/sec); theta wave (4-7 hz/sec); the method mainly comprises the steps of enabling delta wave and theta wave to exist in a sleep stage, enabling alpha wave to exist in high concentration or happy mood, enabling beta wave to exist in tension and excitation state, enabling brain wave to be in beta wave state and extremely difficult to fall asleep, enabling the head rest to play delta wave and theta wave in a three-dimensional surrounding mode through a loudspeaker according to the same-frequency resonance principle and the brain wave dependency principle, inducing the brain wave of a user to be gradually converted into delta wave and theta wave from beta wave, enabling the user to enter a sleep state, or playing alpha wave music, affecting brain wave to be converted into alpha wave, improving concentration, memory and happy mind and body.
Example III
Improvement on the basis of the first embodiment: the main body of the headrest is externally provided with an essential oil aromatherapy cotton box. The lavender aromatherapy essential oil box is internally provided with the replaceable cotton sliver, essential oil is dripped into the lavender aromatherapy essential oil box through the opening fence before sleeping, the essential oil volatilizes to play a role in aromatherapy, the nerves are relaxed, the muscles are relaxed, sleeping is promoted, the cotton sliver can be replaced regularly, and a clean and sanitary state is guaranteed.
It should be noted that in the description of the present specification, descriptions such as "first", "second", etc. are merely for distinguishing features, and there is no actual order or sense of orientation, and the present application is not limited thereto.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Example IV
Referring to fig. 4, an object of the present invention is to provide a sleep lifting system for efficiently feedback-adjusting a sleep brain wave music headrest, so as to solve the problems set forth in the background art.
In order to achieve the above purpose, the invention provides a high-efficiency feedback-regulation sleep brain wave music headrest, which comprises a sleep information collection module, a sleep data analysis module and a headrest regulation module; firstly, through PVDF piezoelectric film sensor installed on the headrest, sleep information is collected and preprocessed by adopting an improved wavelet transformation method, secondly, sleep stages are staged, a neural network sleep stage model is built by combining a convolutional neural network and a time sequence neural network, the sleep stages of a user are automatically staged, the headrest plays brain wave music with different functions according to the sleep stages of the user, sleep is regulated, the user is promoted to enter a deep sleep state, and the sleep stage model of the neural network is optimized through brain wave feedback.
In sleep information collection module, through installing the PVDF piezoelectric film sensor in the headrest, accurate capture user's heartbeat, breathe, body movement information is fit for being applied to human skin surface or implant the inside vital sign monitoring of human body in vivo, and is durable soft, can stand millions of crooked and vibrations, and sensitivity is high, can also detect vital sign through the clothing.
The SQLite database is adopted for uploading the collected heartbeat, respiration and body movement information to a system database corresponding to a user, is a small and efficient embedded relational database management system, and is widely applied to mobile equipment and desktop application programs. The SQLite uses a single file storage database, supports the SQL data language, and has high portability and flexibility.
Preprocessing the collected heartbeat, respiration and body movement information data into single-channel signals through improved wavelet transformation to define a window function w c (t) the formula is as follows:
t represents the moment corresponding to the information, T represents the total time, a represents the transformation scale, the original signal of the moment information of the sensor T is represented by x (T), and the original signal is decomposed into N inherent modal components, and the formula is as follows:
c i (t) represents the ith natural modal component, r N (t) representing residual components, filtering and denoising information collected by the sensor through improved continuous wavelet transformation, mapping the information to a time-frequency space, and positioning the information frequency components, wherein the formula is as follows:
C wt (a, τ) represents a continuous wavelet transform function,represents a mother wavelet function, and τ represents a translation amount; the invention adopts an improved wavelet transformation method for preprocessing the data, reserves the time information of the data signals of the signals and obtains more detailed and flexible characteristic information. In a specific embodiment, the data preprocessed by the improved wavelet transform is adopted, so that the classification performance of the sleep stage model is improved in the process of constructing the sleep stage model.
And the sleep data analysis module is used for dividing the sleep stage into a waking stage, a shallow sleep stage, a rapid eye movement stage and a deep sleep stage.
Through a neural network, a neural network sleep stage model is built, a convolutional neural network and a time sequence neural network are combined, the neural network sleep stage model is built, a convolutional layer, a pooling layer and a connecting layer are designed, characteristic signals are extracted from filtered signals in the convolutional layer, and characteristic mapping is formed, wherein the formula is as follows:
Z p represents an activation value, W p Represents the convolution kernel in the convolution layer, b p Representing the intercept error of the beam,representing the convolution operation, W p,d The D-th channel in the convolution layer is represented, D represents the total channel number of the convolution layer, p represents the p-th convolution operation, and then the net activation value is calculated through the activation function, and the formula is as follows:
entering a pooling layer, further screening the characteristic signals, and screening by adopting an average pooling layer, wherein the formula is as follows:
Y′ p representing the pooling layer output, R representing the entire pooling area; at the full connection layer, all the characteristic signal mapping is tiled, and the formula is as follows:
z represents the full-connection activation value, P represents the total convolution operation times, gamma p Representing the weight of p times, b representing residual vectors, and outputting for multiple times by using different weights at a full connection layer; in the output layer, the result is obtained by the combination calculation of the characteristic signals, the output value of the full-connection layer is divided into C classes, and class labels C are defined y C values are available for e {1,2, … C } and the conditional probability for a class is calculated using the softmax function as follows:
c represents the total value of the label, X represents a matrix formed by X (t),the weight matrix when the label takes c is represented, then a decision function is adopted to calculate a classification result, and the formula is as follows:
and finally outputting a final classification result by the representative output layer, combining with a time sequence neural network model to form a neural network sleep stage model, and designing an input gate, a forgetting gate and an output gate in the time sequence neural network, wherein the calculation method comprises the following steps of:
i t 、f t 、o t respectively represent an input door, a forget door and an output door, W i 、W f 、W o Respectively represent the input iteration coefficients, U i 、U f 、U o Respectively represent implicit iteration coefficients, h t-1 Represents the state of the hidden layer at the moment t-1, b i 、b f 、b o Respectively representing residual errors, and controlling the external state by the internal state in the time sequence neural network, wherein the internal state is standby at the moment tThe formula is as follows:
W g represents the internal state iteration coefficient, U g Representing internal state hidden iteration coefficients, b g Representing the internal state residual error, the internal state g at time t t The calculation formula is as follows:
h t ＝ln(o t g t +1)
g t-1 represents the internal state at time t-1, h t Representing the hidden layer state at time t. The sleep stage model of the invention adopts a convolutional neural networkThe method combines the neural network and the time sequence neural network, constructs a sleep stage model of the neural network, combines the advantages of the convolutional neural network and the time sequence neural network, extracts the characteristics through the convolutional neural network, extracts the sequence relations existing among the characteristics of different time points, extracts effective time sequence information, and improves the accuracy and performance of the sleep stage model. In a specific embodiment, the sleep stage performance of the invention is improved by ten percent by analyzing the data in the sleep database and adopting a neural network sleep stage model combining a convolutional neural network and a time sequence neural network.
Then, the brain wave of the user is input into a neural network sleep stage model, and the sleep stage of the user is output.
And in the headrest adjusting module, according to the sleeping state of the user output by the automatic sleep stage model of the neural network, the sound box arranged in the headrest automatically plays corresponding brain wave music to promote the user to enter a deep sleep stage. According to the co-frequency resonance principle and the brain wave dependency principle, the speaker is utilized to play delta wave and theta wave in a three-dimensional surrounding way, so that the brain wave of a user is induced to be gradually converted from beta wave to delta wave and theta wave, and then the user enters a sleep state, or alpha wave music is played, the brain wave is influenced to be converted into alpha wave, deep sleep is promoted, concentration and memory are improved, and physical and mental pleasure is achieved. When the system detects that the client enters a deep sleep state, the music playing function is automatically closed, so that a user can relax sleep, the situation that music is manually closed in the middle of sleep or playing equipment is damaged due to the fact that the user cannot shut down after sleeping is avoided, and the use comfort of the user is improved.
According to the music played by the headrest and the sleeping stage of the user, the sensitivity degree of the user to different music, the neural network sleeping stage model automatically performs optimization training, optimizes the fitness of the model, and achieves personalized effects.
The beneficial effect of this embodiment sleep promotion system is:
the embodiment provides a high-efficient feedback regulation sleep brain wave music headrest, includes sleep information collection module, sleep data analysis module, headrest adjustment module. The PVDF piezoelectric film sensor is arranged on the music headrest, respiratory, heartbeat and body movement information of a user is collected and is transmitted into the background system database, the collected sleep information is preprocessed by adopting improved continuous wavelet transformation, noise of the collected information is accurately screened out, the convolutional neural network and the time sequence neural network are combined to construct a neural network sleep stage model, the convolutional neural network extracts characteristic signals, the time sequence neural network extracts sequence relations among the characteristic signals at different time points, the jointly constructed neural network sleep stage model has the advantages of the two, the accuracy and the effectiveness of the sleep stage model are improved, the brain wave music provided by the headrest has a beneficial effect on the sleep of the user in a deep sleep state, and the sleep quality is improved. The neural network sleep stage model can further optimize feedback to the model according to the specific information of the user, so that the user can better participate in the sleep adjustment process, the neural network sleep stage model is more suitable for the self situation of the user, and the personalized sleep requirement of the user can be better met. The invention adopts a physical mode to carry out sleep adjustment, has good comfort, can quickly promote sleep to enter a deep stage under the condition of not using external medicines and treatment, ensures that people can better enjoy high-quality sleep, ensures that the adjustment process is safer and more reliable for human bodies, carries out sleep adjustment through brain wave music in combination with sleep stage, has different brain wave music in different sleep stages, has more accurate adjustment effect, ensures that the headrest automatically closes music play after a user enters a deep sleep state, does not need to manually close music, interrupts the sleep process, and simultaneously avoids damage caused by long-time play of playing equipment. The invention can help people improve sleep quality, thereby promoting the development of physical and mental health of human beings. The invention not only meets the requirements of people on high-quality sleep, but also promotes the development of related science and technology and health industry, and has wide market prospect and application value.
The present invention also provides a computer readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the above-described method. The computer readable storage medium may be, among other things, ROM, random access memory, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. The instructions stored therein may be loaded by a processor in the terminal and perform the methods described above.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The sleep improving system for the brain wave music aromatherapy headrest is applied to high-efficiency feedback regulation of sleep and improving brain and is characterized by comprising a sleep information collecting module, a sleep data analyzing module and a headrest regulating module; firstly, through PVDF piezoelectric film sensor installed on the headrest, sleep information is collected and preprocessed by adopting an improved wavelet transformation method, secondly, sleep stages are staged, a neural network sleep stage model is built by combining a convolutional neural network and a time sequence neural network, the sleep stages of a user are automatically staged, the headrest plays brain wave music with different functions according to the sleep stages of the user, sleep is regulated, the user is promoted to enter a deep sleep state, and the sleep stage model of the neural network is optimized through brain wave feedback.
2. The sleep improvement system for the brain wave music aromatherapy headrest for high-efficiency feedback adjustment of sleep improvement and brain according to claim 1, wherein the sleep information collection module accurately captures heartbeat, respiration and body movement information of a user through a PVDF piezoelectric film sensor arranged in the headrest; and the sleep information collection module is used for uploading the collected heartbeat, respiration and body movement information to a system database corresponding to the user.
3. The sleep improvement system for the brain wave music aromatherapy headrest for high-efficiency feedback adjustment of sleep improvement according to claim 2, wherein the sleep information collection module is used for preprocessing the collected heartbeat, respiration and body movement information data into a single-channel signal, and the detailed process is as follows:
defining a window function w c (t) the formula is as follows:
t represents the moment corresponding to the information, T represents the total time, a represents the transformation scale, the original signal of the moment information of the sensor T is represented by x (T), and the original signal is decomposed into N inherent modal components, and the formula is as follows:
c i (t) represents the ith natural modal component, r N (t) representing residual components, filtering and denoising information collected by the sensor through improved continuous wavelet transformation, mapping the information to a time-frequency space, and positioning the information frequency components, wherein the formula is as follows:
C wt (a, τ) represents a continuous wavelet transform function,representing the parent wavelet function, τ represents the amount of translation.
4. The sleep improvement system for an electroencephalogram music aromatherapy headrest for high-efficiency feedback regulation of sleep improvement according to claim 1, wherein the sleep data analysis module classifies sleep stages into a awake stage, a shallow sleep stage, a rapid eye movement stage, a deep sleep stage; the sleep data analysis module constructs a neural network sleep stage model through a neural network, and the detailed process is as follows:
combining a convolutional neural network with a time sequence neural network, constructing a neural network sleep stage model, designing a convolutional layer, a pooling layer and a connecting layer, extracting characteristic signals from filtered signals in the convolutional layer to form a characteristic map, wherein the formula is as follows:
Z p represents an activation value, W p Represents the convolution kernel in the convolution layer, b p Representing the intercept error of the beam,representing the convolution operation, W p,d The D-th channel in the convolution layer is represented, D represents the total channel number of the convolution layer, p represents the p-th convolution operation, and then the net activation value is calculated through the activation function, and the formula is as follows:
entering a pooling layer, further screening the characteristic signals, and screening by adopting an average pooling layer, wherein the formula is as follows:
Y′ p representing the pooling layer output, R representing the entire pooling area; at the full connection layer, all the characteristic signal mapping is tiled, and the formula is as follows:
z represents the full-connection activation value, P represents the total convolution operation times, gamma p Representing the weight of p times, b representing residual vectors, and outputting for multiple times by using different weights at a full connection layer; in the output layer, the result is obtained by the combination calculation of the characteristic signals, the output value of the full-connection layer is divided into C classes, and class labels C are defined y E {1,2, … C } can take C values, some calculated using the softmax functionThe conditional probability of each category is formulated as follows:
c represents the total value X of the tag representing a matrix of X (t),the weight matrix when the label takes c is represented, then a decision function is adopted to calculate a classification result, and the formula is as follows:
and finally outputting a final classification result by the representative output layer, combining with a time sequence neural network model to form a neural network sleep stage model, and designing an input gate, a forgetting gate and an output gate in the time sequence neural network, wherein the calculation method comprises the following steps of:
i t 、f t 、o t respectively represent an input door, a forget door and an output door, W i 、W f 、W o Respectively represent the input iteration coefficients, U i 、U f 、U o Respectively represent implicit iteration coefficients, h t-1 Represents the state of the hidden layer at the moment t-1, b i 、b f 、b o Respectively representing residual errors, and controlling the external state by the internal state in the time sequence neural network, wherein the internal state is standby at the moment tThe formula is as follows:
W g represents the internal state iteration coefficient, U g Representing internal state hidden iteration coefficients, b g Representing the internal state residual error, the internal state g at time t t The calculation formula is as follows:
h t ＝ln(o t g t +1)
g t-1 represents the internal state at time t-1, h t Representing the hidden layer state at time t.
5. The sleep improvement system for the brain wave music aromatherapy headrest for high-efficiency feedback regulation of sleep improvement according to claim 1, wherein the sleep data analysis module inputs brain waves of a user into a neural network sleep stage model and outputs a sleep stage in which the user is located; the headrest adjusting module automatically plays corresponding brain wave music according to the sleep state of the user output by the neural network sleep automatic stage model to promote the user to enter a deep sleep stage; the headrest adjusting module automatically performs optimization training on the neural network sleep stage model according to music played by the headrest and the sleep stage of the user, the sensitivity degree of the user to different music, and the fitness of the model is optimized, so that the personalized effect is achieved.
6. The utility model provides a brain wave music aromatherapy headrest of high-efficient feedback regulation sleep promotion brain, includes headrest main part and external cell-phone APP (5), and the headrest main part includes pillow (101) and pillowcase (102), and pillow (101) set up in the inside of pillowcase (102), its characterized in that, the top of headrest main part is equipped with the intelligent piezoelectric sensor of USB rechargeable, and the bluetooth audio amplifier (301, 302) of two USB rechargeable are built-in to the bottom left and right sides of headrest main part, and external cell-phone APP (5) receive intelligent piezoelectric sensor's output signal and carry out AI algorithm monitoring sleep state through bluetooth, and simultaneously through the audio playback of APP control built-in brain wave, the self-closing music plays when entering the degree of depth sleep state, music aromatherapy headrest still collocation has the sleep promotion system of any one of claims 1-5.
7. The brain wave music aromatherapy headrest for high-efficiency feedback regulation of sleep and brain as claimed in claim 6, wherein the pillow core (101) is made of memory cotton material.
8. An electroencephalogram music aromatherapy headrest for high-efficiency feedback regulation of sleep and brain promotion according to claim 6 or 7, characterized in that the intelligent piezoelectric sensor is a PVDF film piezoelectric sensor (2) and is fitted with a film piezoelectric sensor USB charging port (402).
9. The brain wave music aromatherapy headrest for efficient feedback adjustment of sleep and mental enhancement as claimed in claim 8, wherein two bluetooth speakers (301, 302) are electrically connected by a bluetooth speaker connection wire (303) and adapted with a bluetooth speaker USB charging port (401).
10. The brain wave music aromatherapy headrest for efficiently feeding back and regulating sleep and improving brain according to claim 9, wherein the Bluetooth sound box USB charging port (401) and the film piezoelectric sensor USB charging port (402) are arranged on the right side face of the headrest body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310625784.6A CN116474239A (en) | 2023-05-30 | 2023-05-30 | High-efficient feedback regulation sleep brain wave music headrest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310625784.6A CN116474239A (en) | 2023-05-30 | 2023-05-30 | High-efficient feedback regulation sleep brain wave music headrest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116474239A true CN116474239A (en) | 2023-07-25 |
Family
ID=87212026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310625784.6A Pending CN116474239A (en) | 2023-05-30 | 2023-05-30 | High-efficient feedback regulation sleep brain wave music headrest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116474239A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116803337A (en) * | 2023-08-22 | 2023-09-26 | 深圳市爱保护科技有限公司 | Music sleep assisting method, device and equipment based on sleep monitoring |
-
2023
- 2023-05-30 CN CN202310625784.6A patent/CN116474239A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116803337A (en) * | 2023-08-22 | 2023-09-26 | 深圳市爱保护科技有限公司 | Music sleep assisting method, device and equipment based on sleep monitoring |
| CN116803337B (en) * | 2023-08-22 | 2023-11-07 | 深圳市爱保护科技有限公司 | Music sleep assisting method, device and equipment based on sleep monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Infant cry language analysis and recognition: an experimental approach | |
| CN110522983B (en) | Brain stimulation system, method, device and storage medium based on artificial intelligence | |
| CN108310587A (en) | A kind of sleep control device and method | |
| CN103687540B (en) | Use respiratory murmur amplitude spectrogram and the pitch contour diagnosis OSA/CSA of record | |
| Gu et al. | Sleep hunter: Towards fine grained sleep stage tracking with smartphones | |
| CN107126615A (en) | Music induced hypnotic method and system based on EEG signals | |
| CN111166297B (en) | Method and device for evaluating sleep quality based on user sleep audio | |
| CN105833411A (en) | Novel intelligent sleeping-aiding and natural wakening method and device | |
| CN104257381A (en) | Voice frequency sleep assisting device based on brain wave signals | |
| US11052220B2 (en) | System and method for adjusting the volume of auditory stimulation during sleep based on sleep depth latencies | |
| CN111904424B (en) | Sleep monitoring and regulating system based on phased array microphone | |
| CN110841169A (en) | Deep sound stimulation system and method for sleep regulation | |
| CN107402635B (en) | Mental health adjusting method and system combining brain waves and virtual reality | |
| CN116474239A (en) | High-efficient feedback regulation sleep brain wave music headrest | |
| CN107898432B (en) | Snore detection method, device, equipment and medium | |
| CN113448438B (en) | Control system and method based on sleep perception | |
| CN113195031B (en) | System and method for delivering audio output | |
| US20190343455A1 (en) | System and method for outputting an indicator representative of the effects of stimulation provided to a subject during sleep | |
| CN112717253A (en) | Acousto-optic combined awakening device based on brain wave monitoring | |
| CN110367934A (en) | A kind of health monitor method and monitoring system based on non-voice body sounds | |
| CN110464344A (en) | The method for collecting the device of eeg signal acquisition and music and its playing music | |
| CN109730658A (en) | A kind of artificial intelligence mattress system | |
| TWM487053U (en) | Intelligent sleep recording device | |
| CN211884899U (en) | Sleep-aiding instrument | |
| Zhang et al. | An effective deep learning approach for unobtrusive sleep stage detection using microphone sensor |
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 |